diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index 05f6cc9592..6744f5b915 100644 --- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -1700,6 +1700,10 @@ private static void populateLlapDaemonVarsSet(Set llapDaemonVarsSetLocal "Whether or not to use a binary search to find the entries in an index table that match the filter, where possible"), // Statistics + HIVE_STATS_NDV_ESTIMATE_PERC("hive.stats.ndv.estimate.percent", (long)20, + "This many percentage of rows will be estimated as count distinct in absence of statistics."), + HIVE_STATS_NUM_NULLS_ESTIMATE_PERC("hive.stats.num.nulls.estimate.percent", (long)5, + "This many percentage of rows will be estimated as number of nulls in absence of statistics."), HIVESTATSAUTOGATHER("hive.stats.autogather", true, "A flag to gather statistics (only basic) automatically during the INSERT OVERWRITE command."), HIVESTATSCOLAUTOGATHER("hive.stats.column.autogather", false, diff --git a/itests/src/test/resources/testconfiguration.properties b/itests/src/test/resources/testconfiguration.properties index f66e19be3e..f346e3a6fb 100644 --- a/itests/src/test/resources/testconfiguration.properties +++ b/itests/src/test/resources/testconfiguration.properties @@ -523,6 +523,7 @@ minillaplocal.query.files=acid_globallimit.q,\ join_nulls.q,\ join_nullsafe.q,\ join_is_not_distinct_from.q,\ + join_reordering_no_stats.q,\ leftsemijoin_mr.q,\ limit_join_transpose.q,\ lineage2.q,\ diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/RelOptHiveTable.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/RelOptHiveTable.java index 1d49568c8c..d6387affdb 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/RelOptHiveTable.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/RelOptHiveTable.java @@ -206,14 +206,7 @@ public double getRowCount() { // predicates computePartitionList(hiveConf, null, new HashSet()); } - if (hiveTblMetadata.isPartitioned()) { - List rowCounts = StatsUtils.getBasicStatForPartitions(hiveTblMetadata, - partitionList.getNotDeniedPartns(), StatsSetupConst.ROW_COUNT); - rowCount = StatsUtils.getSumIgnoreNegatives(rowCounts); - - } else { - rowCount = StatsUtils.getNumRows(hiveTblMetadata); - } + rowCount = StatsUtils.getNumRows(hiveConf, getNonPartColumns(), hiveTblMetadata, partitionList); } if (rowCount == -1) @@ -297,39 +290,53 @@ private void updateColStats(Set projIndxLst, boolean allowNullColumnFor // 2. Obtain Col Stats for Non Partition Cols if (nonPartColNamesThatRqrStats.size() > 0) { - List hiveColStats; + List hiveColStats = new ArrayList(); if (!hiveTblMetadata.isPartitioned()) { // 2.1 Handle the case for unpartitioned table. - hiveColStats = StatsUtils.getTableColumnStats(hiveTblMetadata, hiveNonPartitionCols, - nonPartColNamesThatRqrStats); - - // 2.1.1 Record Column Names that we needed stats for but couldn't - if (hiveColStats == null) { - colNamesFailedStats.addAll(nonPartColNamesThatRqrStats); - } else if (hiveColStats.size() != nonPartColNamesThatRqrStats.size()) { - Set setOfFiledCols = new HashSet(nonPartColNamesThatRqrStats); - - Set setOfObtainedColStats = new HashSet(); - for (ColStatistics cs : hiveColStats) { - setOfObtainedColStats.add(cs.getColumnName()); + try { + Statistics stats = StatsUtils.collectStatistics(hiveConf, null, + hiveTblMetadata, hiveNonPartitionCols, nonPartColNamesThatRqrStats, + nonPartColNamesThatRqrStats, true, true); + rowCount = stats.getNumRows(); + for (String c : nonPartColNamesThatRqrStats) { + ColStatistics cs = stats.getColumnStatisticsFromColName(c); + if (cs != null) { + hiveColStats.add(cs); + } } - setOfFiledCols.removeAll(setOfObtainedColStats); - colNamesFailedStats.addAll(setOfFiledCols); - } else { - // Column stats in hiveColStats might not be in the same order as the columns in - // nonPartColNamesThatRqrStats. reorder hiveColStats so we can build hiveColStatsMap - // using nonPartColIndxsThatRqrStats as below - Map columnStatsMap = - new HashMap(hiveColStats.size()); - for (ColStatistics cs : hiveColStats) { - columnStatsMap.put(cs.getColumnName(), cs); - } - hiveColStats.clear(); - for (String colName : nonPartColNamesThatRqrStats) { - hiveColStats.add(columnStatsMap.get(colName)); + // 2.1.1 Record Column Names that we needed stats for but couldn't + if (hiveColStats.isEmpty()) { + colNamesFailedStats.addAll(nonPartColNamesThatRqrStats); + } else if (hiveColStats.size() != nonPartColNamesThatRqrStats.size()) { + Set setOfFiledCols = new HashSet(nonPartColNamesThatRqrStats); + + Set setOfObtainedColStats = new HashSet(); + for (ColStatistics cs : hiveColStats) { + setOfObtainedColStats.add(cs.getColumnName()); + } + setOfFiledCols.removeAll(setOfObtainedColStats); + + colNamesFailedStats.addAll(setOfFiledCols); + } else { + // Column stats in hiveColStats might not be in the same order as the columns in + // nonPartColNamesThatRqrStats. reorder hiveColStats so we can build hiveColStatsMap + // using nonPartColIndxsThatRqrStats as below + Map columnStatsMap = + new HashMap(hiveColStats.size()); + for (ColStatistics cs : hiveColStats) { + columnStatsMap.put(cs.getColumnName(), cs); + } + hiveColStats.clear(); + for (String colName : nonPartColNamesThatRqrStats) { + hiveColStats.add(columnStatsMap.get(colName)); + } } + } catch (HiveException e) { + String logMsg = "Collecting stats for table: " + hiveTblMetadata.getTableName() + " failed."; + LOG.error(logMsg, e); + throw new RuntimeException(logMsg, e); } } else { // 2.2 Obtain col stats for partitioned table. @@ -337,7 +344,6 @@ private void updateColStats(Set projIndxLst, boolean allowNullColumnFor if (partitionList.getNotDeniedPartns().isEmpty()) { // no need to make a metastore call rowCount = 0; - hiveColStats = new ArrayList(); for (String c : nonPartColNamesThatRqrStats) { // add empty stats object for each column hiveColStats.add(new ColStatistics(c, null)); diff --git a/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java b/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java index 3b9ab41bed..30da024854 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java @@ -176,6 +176,79 @@ private static long getDataSize(HiveConf conf, Table table) { return ds; } + /** + * Returns number of rows if it exists. Otherwise it estimates number of rows + * based on estimated data size for both partition and non-partitioned table + * RelOptHiveTable's getRowCount uses this. + * + * @param conf + * @param schema + * @param table + * @return + */ + public static long getNumRows(HiveConf conf, List schema, Table table, + PrunedPartitionList partitionList) { + //for non-partitioned table + List neededColumns = new ArrayList<>(); + for(ColumnInfo ci:schema) { + neededColumns.add(ci.getInternalName()); + } + if(!table.isPartitioned()) { + long ds = getDataSize(conf, table); + return getNumRows(conf, schema, neededColumns, table, ds); + } + else { // partitioned table + long nr = 0; + long ds = 0; + + List rowCounts = Lists.newArrayList(); + List dataSizes = Lists.newArrayList(); + + rowCounts = getBasicStatForPartitions( + table, partitionList.getNotDeniedPartns(), StatsSetupConst.ROW_COUNT); + dataSizes = getBasicStatForPartitions( + table, partitionList.getNotDeniedPartns(), StatsSetupConst.RAW_DATA_SIZE); + + nr = getSumIgnoreNegatives(rowCounts); + ds = getSumIgnoreNegatives(dataSizes); + + // we have actual number of rows + if(nr > 0) return nr; + + if (ds <= 0) { + dataSizes = getBasicStatForPartitions( + table, partitionList.getNotDeniedPartns(), StatsSetupConst.TOTAL_SIZE); + ds = getSumIgnoreNegatives(dataSizes); + } + + // if data size still could not be determined, then fall back to filesytem to get file + // sizes + if (ds <= 0) { + dataSizes = getFileSizeForPartitions(conf, partitionList.getNotDeniedPartns()); + } + ds = getSumIgnoreNegatives(dataSizes); + float deserFactor = + HiveConf.getFloatVar(conf, HiveConf.ConfVars.HIVE_STATS_DESERIALIZATION_FACTOR); + ds = (long) (ds * deserFactor); + + int avgRowSize = estimateRowSizeFromSchema(conf, schema, neededColumns); + if (avgRowSize > 0) { + setUnknownRcDsToAverage(rowCounts, dataSizes, avgRowSize); + nr = getSumIgnoreNegatives(rowCounts); + ds = getSumIgnoreNegatives(dataSizes); + + // number of rows -1 means that statistics from metastore is not reliable + if (nr <= 0) { + nr = ds / avgRowSize; + } + } + if (nr == 0) { + nr = 1; + } + return nr; + } + } + private static long getNumRows(HiveConf conf, List schema, List neededColumns, Table table, long ds) { long nr = getNumRows(table); // number of rows -1 means that statistics from metastore is not reliable @@ -210,6 +283,9 @@ public static Statistics collectStatistics(HiveConf conf, PrunedPartitionList pa List colStats = Lists.newArrayList(); if (fetchColStats) { colStats = getTableColumnStats(table, schema, neededColumns); + if(colStats.size() < 1) { + colStats = estimateStats(table,schema,neededColumns, conf, nr); + } long betterDS = getDataSizeFromColumnStats(nr, colStats); ds = (betterDS < 1 || colStats.isEmpty()) ? ds : betterDS; } @@ -294,12 +370,17 @@ public static Statistics collectStatistics(HiveConf conf, PrunedPartitionList pa // state/initialize structures. List emptyStats = Lists.newArrayList(); + // estimate stats + emptyStats = estimateStats(table, schema, neededColumns, conf, nr); + // add partition column stats addParitionColumnStats(conf, neededColumns, referencedColumns, schema, table, partList, emptyStats); - stats.addToColumnStats(emptyStats); + stats.addToDataSize(getDataSizeFromColumnStats(nr, emptyStats)); stats.updateColumnStatsState(deriveStatType(emptyStats, referencedColumns)); + + stats.addToColumnStats(emptyStats); } else { List colStats = aggrStats.getColStats(); if (colStats.size() != neededColumns.size()) { @@ -780,6 +861,86 @@ public static ColStatistics getColStatistics(ColumnStatisticsObj cso, String tab return cs; } + private static ColStatistics estimateColStats(long numRows, String colName, HiveConf conf, + List schema) { + ColumnInfo cinfo = getColumnInfoForColumn(colName, schema); + ColStatistics cs = new ColStatistics(colName, cinfo.getTypeName()); + + String colTypeLowerCase = cinfo.getTypeName().toLowerCase(); + double avgColLenString = 5; + + long ndvPercent = Math.min(100L, HiveConf.getLongVar(conf, ConfVars.HIVE_STATS_NDV_ESTIMATE_PERC)); + long nullPercent = Math.min(100L, HiveConf.getLongVar(conf, ConfVars.HIVE_STATS_NUM_NULLS_ESTIMATE_PERC)); + + cs.setCountDistint(Math.max(1, (long)(numRows * ndvPercent/100.00))); + cs.setNumNulls(Math.min(numRows, (long)(numRows * nullPercent/100.00))); + + if (colTypeLowerCase.equals(serdeConstants.TINYINT_TYPE_NAME) + || colTypeLowerCase.equals(serdeConstants.SMALLINT_TYPE_NAME) + || colTypeLowerCase.equals(serdeConstants.INT_TYPE_NAME)) { + cs.setAvgColLen(JavaDataModel.get().primitive1()); + cs.setRange(Integer.MIN_VALUE, Integer.MAX_VALUE); + } else if (colTypeLowerCase.equals(serdeConstants.BIGINT_TYPE_NAME)) { + cs.setAvgColLen(JavaDataModel.get().primitive2()); + cs.setRange(Integer.MIN_VALUE, Integer.MAX_VALUE); + } else if (colTypeLowerCase.equals(serdeConstants.FLOAT_TYPE_NAME)) { + cs.setAvgColLen(JavaDataModel.get().primitive1()); + cs.setRange(Float.MIN_VALUE, Float.MAX_VALUE); + } else if (colTypeLowerCase.equals(serdeConstants.DOUBLE_TYPE_NAME)) { + cs.setAvgColLen(JavaDataModel.get().primitive2()); + cs.setRange(Double.MIN_VALUE, Double.MAX_VALUE); + } else if (colTypeLowerCase.equals(serdeConstants.STRING_TYPE_NAME) + || colTypeLowerCase.startsWith(serdeConstants.CHAR_TYPE_NAME) + || colTypeLowerCase.startsWith(serdeConstants.VARCHAR_TYPE_NAME)) { + cs.setAvgColLen(avgColLenString); + } else if (colTypeLowerCase.equals(serdeConstants.BOOLEAN_TYPE_NAME)) { + cs.setCountDistint(2); + cs.setNumTrues(Math.max(1, (long)numRows/2)); + cs.setNumFalses(Math.max(1, (long)numRows/2)); + cs.setAvgColLen(JavaDataModel.get().primitive1()); + } else if (colTypeLowerCase.equals(serdeConstants.BINARY_TYPE_NAME)) { + cs.setAvgColLen(avgColLenString); + } else if (colTypeLowerCase.equals(serdeConstants.TIMESTAMP_TYPE_NAME) || + colTypeLowerCase.equals(serdeConstants.TIMESTAMPTZ_TYPE_NAME)) { + cs.setAvgColLen(JavaDataModel.get().lengthOfTimestamp()); + } else if (colTypeLowerCase.startsWith(serdeConstants.DECIMAL_TYPE_NAME)) { + cs.setAvgColLen(JavaDataModel.get().lengthOfDecimal()); + cs.setRange(Float.MIN_VALUE, Float.MAX_VALUE); + } else if (colTypeLowerCase.equals(serdeConstants.DATE_TYPE_NAME)) { + cs.setAvgColLen(JavaDataModel.get().lengthOfDate()); + cs.setRange(null, null); + } else { + // Columns statistics for complex datatypes are not supported yet + return null; + } + return cs; + } + + private static List estimateStats(Table table, List schema, + List neededColumns, HiveConf conf, long nr) { + + List stats = new ArrayList(neededColumns.size()); + + for (int i = 0; i < neededColumns.size(); i++) { + ColStatistics cs = estimateColStats(nr, neededColumns.get(i), conf, schema); + stats.add(cs); + } + return stats; + } + + public static List getTableColumnStats( + Table table, List schema, List neededColumns, + HiveConf hiveconf) { + List stats = null; + stats = getTableColumnStats(table, schema, neededColumns); + + if(stats.isEmpty() ) { + long ds = getDataSize(hiveconf, table) ; + long nr = getNumRows(hiveconf, schema, neededColumns, table,ds); + stats = estimateStats(table, schema, neededColumns, hiveconf, nr); + } + return stats; + } /** * Get table level column statistics from metastore for needed columns * @param table @@ -803,6 +964,7 @@ public static ColStatistics getColStatistics(ColumnStatisticsObj cso, String tab try { List colStat = Hive.get().getTableColumnStatistics( dbName, tabName, neededColsInTable); + stats = convertColStats(colStat, tabName); } catch (HiveException e) { LOG.error("Failed to retrieve table statistics: ", e); diff --git a/ql/src/test/queries/clientpositive/join_reordering_no_stats.q b/ql/src/test/queries/clientpositive/join_reordering_no_stats.q new file mode 100644 index 0000000000..157d8de7a3 --- /dev/null +++ b/ql/src/test/queries/clientpositive/join_reordering_no_stats.q @@ -0,0 +1,56 @@ +set hive.stats.autogather=false; + +create table supplier (S_SUPPKEY INT, S_NAME STRING, S_ADDRESS STRING, S_NATIONKEY INT, +S_PHONE STRING, S_ACCTBAL DOUBLE, S_COMMENT STRING); + +CREATE TABLE lineitem_nostats (L_ORDERKEY INT, + L_PARTKEY INT, + L_SUPPKEY INT, + L_LINENUMBER INT, + L_QUANTITY DOUBLE, + L_EXTENDEDPRICE DOUBLE, + L_DISCOUNT DOUBLE, + L_TAX DOUBLE, + L_RETURNFLAG STRING, + L_LINESTATUS STRING, + l_shipdate STRING, + L_COMMITDATE STRING, + L_RECEIPTDATE STRING, + L_SHIPINSTRUCT STRING, + L_SHIPMODE STRING, + L_COMMENT STRING) +ROW FORMAT DELIMITED +FIELDS TERMINATED BY '|'; + +CREATE TABLE part_nostats( + p_partkey INT, + p_name STRING, + p_mfgr STRING, + p_brand STRING, + p_type STRING, + p_size INT, + p_container STRING, + p_retailprice DOUBLE, + p_comment STRING +); + +-- should not have cross join +explain select count(1) from part,supplier,lineitem where p_partkey = l_partkey and s_suppkey = l_suppkey; + +CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double, country string) +row format delimited fields terminated by '|' stored as textfile; + +LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='USA'); +LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='UK'); +LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='USA'); +LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='4000.0', country='USA'); +LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3500.0', country='UK'); +LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='UK'); + +-- partitioned table +explain select count(1) from Employee_Part,supplier,lineitem where employeeID= l_partkey and s_suppkey = l_suppkey; + +drop table Employee_Part; +drop table supplier; +drop table lineitem_nostats; +drop table part_nostats; diff --git a/ql/src/test/results/clientpositive/annotate_stats_part.q.out b/ql/src/test/results/clientpositive/annotate_stats_part.q.out index 866d30a8ea..b87bfd6c22 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_part.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_part.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: insert overwrite table loc_orc partition(year) select * from loc_staging @@ -90,11 +90,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 6 Data size: 1884 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 2490 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1710 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: analyze table loc_orc partition(year='2001') compute statistics @@ -121,11 +121,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 3 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), '__HIVE_DEFAULT_PARTITION__' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 633 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from loc_orc @@ -142,11 +142,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 7 Data size: 1966 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 7 Data size: 2673 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 7 Data size: 1288 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 7 Data size: 1995 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from loc_orc where year='2001' @@ -163,11 +163,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 7 Data size: 734 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 1385 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), '2001' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 7 Data size: 734 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 1323 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: analyze table loc_orc partition(year) compute statistics @@ -196,11 +196,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 197 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), '__HIVE_DEFAULT_PARTITION__' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 211 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from loc_orc @@ -217,11 +217,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 2246 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 3054 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 1472 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 2280 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from loc_orc where year='2001' or year='__HIVE_DEFAULT_PARTITION__' @@ -238,11 +238,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 2246 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 3054 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 1472 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 2280 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from loc_orc where year='2001' and year='__HIVE_DEFAULT_PARTITION__' @@ -259,14 +259,14 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: analyze table loc_orc partition(year='2001') compute statistics for columns state,locid @@ -293,11 +293,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 838 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 838 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: zip (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 8 Data size: 838 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select state from loc_orc @@ -398,11 +398,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 189 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from loc_orc diff --git a/ql/src/test/results/clientpositive/auto_join_reordering_values.q.out b/ql/src/test/results/clientpositive/auto_join_reordering_values.q.out index 156be41502..ba8d16c0fc 100644 --- a/ql/src/test/results/clientpositive/auto_join_reordering_values.q.out +++ b/ql/src/test/results/clientpositive/auto_join_reordering_values.q.out @@ -182,7 +182,7 @@ STAGE PLANS: name: default.orderpayment_small name: default.orderpayment_small Truncated Path -> Alias: - /orderpayment_small [$hdt$_0:orderpayment, $hdt$_1:dim_pay_date] + /orderpayment_small [$hdt$_1:orderpayment, $hdt$_2:dim_pay_date] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -318,7 +318,7 @@ STAGE PLANS: name: default.orderpayment_small name: default.orderpayment_small Truncated Path -> Alias: - /orderpayment_small [$hdt$_2:deal] + /orderpayment_small [$hdt$_3:deal] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -455,7 +455,7 @@ STAGE PLANS: name: default.orderpayment_small name: default.orderpayment_small Truncated Path -> Alias: - /orderpayment_small [$hdt$_3:order_city] + /orderpayment_small [$hdt$_4:order_city] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -592,7 +592,7 @@ STAGE PLANS: name: default.user_small name: default.user_small Truncated Path -> Alias: - /user_small [$hdt$_4:user] + /user_small [$hdt$_0:user] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: diff --git a/ql/src/test/results/clientpositive/auto_join_stats.q.out b/ql/src/test/results/clientpositive/auto_join_stats.q.out index e80af96fcb..cb21718b56 100644 --- a/ql/src/test/results/clientpositive/auto_join_stats.q.out +++ b/ql/src/test/results/clientpositive/auto_join_stats.q.out @@ -305,11 +305,11 @@ STAGE PLANS: Stage: Stage-11 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:src2 + $hdt$_2:src2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:src2 + $hdt$_2:src2 TableScan alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -358,14 +358,14 @@ STAGE PLANS: Stage: Stage-10 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_2:smalltable + $hdt$_0:smalltable Fetch Operator limit: -1 $hdt$_3:smalltable2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_2:smalltable + $hdt$_0:smalltable TableScan alias: smalltable Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -410,26 +410,30 @@ STAGE PLANS: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) 1 UDFToDouble(_col0) (type: double) 2 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work Stage: Stage-12 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:src1 + $hdt$_1:src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:src1 + $hdt$_1:src1 TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/auto_join_stats2.q.out b/ql/src/test/results/clientpositive/auto_join_stats2.q.out index 6ea5afa920..1a3caa639f 100644 --- a/ql/src/test/results/clientpositive/auto_join_stats2.q.out +++ b/ql/src/test/results/clientpositive/auto_join_stats2.q.out @@ -14,6 +14,7 @@ POSTHOOK: query: load data local inpath '../../data/files/T1.txt' into table sma POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@smalltable +Warning: Map Join MAPJOIN[24][bigTable=?] in task 'Stage-5:MAPRED' is a cross product PREHOOK: query: explain select src1.key, src2.key, smalltable.key from src src1 JOIN src src2 ON (src1.key = src2.key) JOIN smalltable ON (src1.key + src2.key = smalltable.key) PREHOOK: type: QUERY POSTHOOK: query: explain select src1.key, src2.key, smalltable.key from src src1 JOIN src src2 ON (src1.key = src2.key) JOIN smalltable ON (src1.key + src2.key = smalltable.key) @@ -62,8 +63,8 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) + 0 + 1 Stage: Stage-5 Map Reduce @@ -82,25 +83,32 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 + 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 20812 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 550 Data size: 22893 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(_col2) + UDFToDouble(_col0)) = UDFToDouble(_col1)) (type: boolean) + Statistics: Num rows: 275 Data size: 11446 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: string), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 275 Data size: 11446 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 11446 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -110,6 +118,7 @@ STAGE PLANS: Processor Tree: ListSink +Warning: Map Join MAPJOIN[24][bigTable=?] in task 'Stage-5:MAPRED' is a cross product PREHOOK: query: select src1.key, src2.key, smalltable.key from src src1 JOIN src src2 ON (src1.key = src2.key) JOIN smalltable ON (src1.key + src2.key = smalltable.key) PREHOOK: type: QUERY PREHOOK: Input: default@smalltable @@ -159,47 +168,47 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:src1 + $hdt$_0:smalltable Fetch Operator limit: -1 - $hdt$_2:smalltable + $hdt$_1:src1 Fetch Operator limit: -1 $hdt$_3:smalltable2 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:src1 + $hdt$_0:smalltable TableScan - alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: smalltable + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_2:smalltable + 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) + 1 UDFToDouble(_col0) (type: double) + 2 UDFToDouble(_col0) (type: double) + $hdt$_1:src1 TableScan - alias: smalltable - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + alias: src1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - 2 UDFToDouble(_col0) (type: double) + 0 _col0 (type: string) + 1 _col0 (type: string) $hdt$_3:smalltable2 TableScan alias: smalltable2 @@ -246,15 +255,19 @@ STAGE PLANS: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) 1 UDFToDouble(_col0) (type: double) 2 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out index d129807f55..7875e9693a 100644 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out +++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out @@ -148,7 +148,7 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:a + $hdt$_1:a Fetch Operator limit: -1 Partition Description: @@ -200,7 +200,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucket_small name: default.bucket_small - $hdt$_1:b + $hdt$_2:b Fetch Operator limit: -1 Partition Description: @@ -305,7 +305,7 @@ STAGE PLANS: name: default.bucket_medium name: default.bucket_medium Alias -> Map Local Operator Tree: - $hdt$_0:a + $hdt$_1:a TableScan alias: a Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE @@ -324,7 +324,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) Position of Big Table: 2 - $hdt$_1:b + $hdt$_2:b TableScan alias: b Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE @@ -603,8 +603,8 @@ STAGE PLANS: name: default.bucket_small name: default.bucket_small Truncated Path -> Alias: - /bucket_big/ds=2008-04-08 [$hdt$_2:c] - /bucket_big/ds=2008-04-09 [$hdt$_2:c] + /bucket_big/ds=2008-04-08 [$hdt$_0:c] + /bucket_big/ds=2008-04-09 [$hdt$_0:c] Needs Tagging: false Reduce Operator Tree: Group By Operator diff --git a/ql/src/test/results/clientpositive/explain_rearrange.q.out b/ql/src/test/results/clientpositive/explain_rearrange.q.out index 2e5f9e4626..7d9434b93e 100644 --- a/ql/src/test/results/clientpositive/explain_rearrange.q.out +++ b/ql/src/test/results/clientpositive/explain_rearrange.q.out @@ -135,7 +135,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false @@ -190,7 +190,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false @@ -225,7 +225,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false @@ -404,7 +404,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false @@ -459,7 +459,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false @@ -494,7 +494,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false @@ -716,7 +716,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false @@ -753,7 +753,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false @@ -788,7 +788,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false @@ -1011,7 +1011,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false @@ -1032,7 +1032,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false @@ -1055,7 +1055,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false diff --git a/ql/src/test/results/clientpositive/filter_join_breaktask.q.out b/ql/src/test/results/clientpositive/filter_join_breaktask.q.out index 8f9b6363f4..9d00ce6786 100644 --- a/ql/src/test/results/clientpositive/filter_join_breaktask.q.out +++ b/ql/src/test/results/clientpositive/filter_join_breaktask.q.out @@ -38,22 +38,22 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: f + alias: g Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) + predicate: (value <> '') (type: boolean) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) + expressions: value (type: string) outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col0 (type: string) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false @@ -70,13 +70,13 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -129,16 +129,16 @@ STAGE PLANS: name: default.filter_join_breaktask name: default.filter_join_breaktask Truncated Path -> Alias: - /filter_join_breaktask/ds=2008-04-08 [$hdt$_0:f, $hdt$_1:m] + /filter_join_breaktask/ds=2008-04-08 [$hdt$_0:g, $hdt$_1:m] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col3 + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 27 Data size: 232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -150,8 +150,8 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col3 - columns.types int,string + columns _col0,_col2 + columns.types string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -165,31 +165,31 @@ STAGE PLANS: TableScan GatherStats: false Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: _col2 (type: int) null sort order: a sort order: + - Map-reduce partition columns: _col3 (type: string) + Map-reduce partition columns: _col2 (type: int) Statistics: Num rows: 27 Data size: 232 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col0 (type: int) + value expressions: _col0 (type: string) auto parallelism: false TableScan - alias: g + alias: f Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (value <> '') (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) + expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col0 (type: int) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE tag: 1 auto parallelism: false @@ -203,8 +203,8 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col3 - columns.types int,string + columns _col0,_col2 + columns.types string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -213,8 +213,8 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col3 - columns.types int,string + columns _col0,_col2 + columns.types string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -266,7 +266,7 @@ STAGE PLANS: name: default.filter_join_breaktask name: default.filter_join_breaktask Truncated Path -> Alias: - /filter_join_breaktask/ds=2008-04-08 [$hdt$_2:g] + /filter_join_breaktask/ds=2008-04-08 [$hdt$_2:f] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -274,12 +274,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 _col0 (type: string) + 0 _col2 (type: int) + 1 _col0 (type: int) outputColumnNames: _col0, _col5 Statistics: Num rows: 29 Data size: 255 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col5 (type: string) + expressions: _col5 (type: int), _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 29 Data size: 255 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/join19.q.out b/ql/src/test/results/clientpositive/join19.q.out index dd167ecabf..e83c776c61 100644 --- a/ql/src/test/results/clientpositive/join19.q.out +++ b/ql/src/test/results/clientpositive/join19.q.out @@ -120,8 +120,10 @@ ON (t66.subject=t55.object) POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 + Stage-2 depends on stages: Stage-1, Stage-5 + Stage-3 depends on stages: Stage-2, Stage-7 + Stage-5 is a root stage + Stage-7 is a root stage Stage-0 depends on stages: Stage-3 STAGE PLANS: @@ -129,22 +131,23 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: t1 + alias: t5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Citation') and subject is not null) (type: boolean) + predicate: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_to') and subject is not null and object is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: subject (type: string) - outputColumnNames: _col0 + expressions: subject (type: string), object (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: string) TableScan - alias: t2 + alias: t6 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__LABEL_REL') and subject is not null) (type: boolean) @@ -159,33 +162,48 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: TableScan - alias: t3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Filter Operator - predicate: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_from') and object is not null and subject is not null) (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: subject (type: string), object (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string) + value expressions: _col1 (type: string), _col3 (type: string) + TableScan + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col1 (type: string) - outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + 1 _col2 (type: string) + outputColumnNames: _col1, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false table: @@ -193,58 +211,87 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: _col5 (type: string) sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col2 (type: string) + Map-reduce partition columns: _col5 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string) TableScan - alias: t4 + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col5 (type: string) + 1 _col2 (type: string) + outputColumnNames: _col1, _col3, _col4, _col8, _col9 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col9 (type: string), _col8 (type: string), _col4 (type: string), _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + alias: t3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Author') and subject is not null) (type: boolean) + predicate: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_from') and object is not null and subject is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: subject (type: string) - outputColumnNames: _col0 + expressions: subject (type: string), object (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string) TableScan - alias: t5 + alias: t4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_to') and subject is not null and object is not null) (type: boolean) + predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Author') and subject is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: subject (type: string), object (type: string) - outputColumnNames: _col0, _col1 + expressions: subject (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 keys: - 0 _col3 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3, _col7 - Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: NONE + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false table: @@ -252,18 +299,11 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-3 + Stage: Stage-7 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - key expressions: _col7 (type: string) - sort order: + - Map-reduce partition columns: _col7 (type: string) - Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string) - TableScan - alias: t6 + alias: t2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__LABEL_REL') and subject is not null) (type: boolean) @@ -278,26 +318,36 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) + TableScan + alias: t1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Citation') and subject is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: subject (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col7 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3, _col7, _col9 - Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col7 (type: string), _col9 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col1, _col2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/join42.q.out b/ql/src/test/results/clientpositive/join42.q.out index 0cd31c6d66..11851a9c88 100644 --- a/ql/src/test/results/clientpositive/join42.q.out +++ b/ql/src/test/results/clientpositive/join42.q.out @@ -86,7 +86,7 @@ POSTHOOK: Output: default@acct POSTHOOK: Lineage: acct.acc_n EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col2, type:string, comment:), ] POSTHOOK: Lineage: acct.aid EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] POSTHOOK: Lineage: acct.brn EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col3, type:string, comment:), ] -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[28][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select acct.ACC_N, acct.brn @@ -115,15 +115,30 @@ WHERE POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 + Stage-2 depends on stages: Stage-1, Stage-6 + Stage-5 is a root stage + Stage-6 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan + alias: acct + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (aid is not null and brn is not null) (type: boolean) + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: aid (type: int), acc_n (type: int), brn (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + TableScan alias: l Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -135,20 +150,6 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan - alias: la - Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((4436 = loan_id) and aid is not null and pi_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: aid (type: int), pi_id (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) - TableScan alias: fr Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -168,8 +169,8 @@ STAGE PLANS: 0 1 2 - outputColumnNames: _col2, _col3 - Statistics: Num rows: 1 Data size: 23 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 3 Data size: 58 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -182,11 +183,57 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col2 (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 23 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int) + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 3 Data size: 58 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int) + TableScan + Reduce Output Operator + key expressions: _col3 (type: int) + sort order: + + Map-reduce partition columns: _col3 (type: int) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col2 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + alias: la + Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((4436 = loan_id) and aid is not null and pi_id is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: aid (type: int), pi_id (type: int) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int) TableScan alias: a Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE @@ -202,33 +249,15 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: acct - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (aid is not null and brn is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: aid (type: int), acc_n (type: int), brn (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col3, _col7, _col8 - Statistics: Num rows: 6 Data size: 68 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -236,16 +265,16 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-3 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col3 (type: int) + key expressions: _col2 (type: int) sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 6 Data size: 68 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: int), _col8 (type: int) + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: int) TableScan alias: pi Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE @@ -266,21 +295,16 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col7, _col8 - Statistics: Num rows: 6 Data size: 74 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col7 (type: int), _col8 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 74 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 74 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -288,7 +312,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[28][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select acct.ACC_N, acct.brn diff --git a/ql/src/test/results/clientpositive/join43.q.out b/ql/src/test/results/clientpositive/join43.q.out index 24168ca4fe..fac8a8cb2d 100644 --- a/ql/src/test/results/clientpositive/join43.q.out +++ b/ql/src/test/results/clientpositive/join43.q.out @@ -209,46 +209,46 @@ from ( ) list POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 + Stage-2 is a root stage Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: purchase_history - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + alias: cart_history + Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s is not null (type: boolean) - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), time (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) TableScan - alias: cart_history - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + alias: purchase_history + Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s is not null (type: boolean) - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), time (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -257,14 +257,14 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 39 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 > _col3) (type: boolean) + predicate: (_col3 > _col1) (type: boolean) Statistics: Num rows: 2 Data size: 13 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col3) - keys: _col0 (type: string), _col1 (type: int) + aggregations: max(_col1) + keys: _col2 (type: string), _col3 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 13 Basic stats: COMPLETE Column stats: NONE @@ -275,7 +275,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -306,16 +306,10 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-3 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col2 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - TableScan alias: events Statistics: Num rows: 6 Data size: 79 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -330,22 +324,32 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 6 Data size: 79 Basic stats: COMPLETE Column stats: NONE + TableScan + Reduce Output Operator + key expressions: _col0 (type: string), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col2 (type: int) + Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col2 (type: int) - 1 _col0 (type: string), _col1 (type: int) - outputColumnNames: _col0 + 0 _col0 (type: string), _col1 (type: int) + 1 _col0 (type: string), _col2 (type: int) + outputColumnNames: _col2 Statistics: Num rows: 6 Data size: 86 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col2 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 86 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 86 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -427,46 +431,46 @@ from ( ) list POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 + Stage-2 is a root stage Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: purchase_history - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + alias: cart_history + Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s is not null (type: boolean) - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), time (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) TableScan - alias: cart_history - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + alias: purchase_history + Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s is not null (type: boolean) - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), time (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -475,14 +479,14 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 39 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 > _col3) (type: boolean) + predicate: (_col3 > _col1) (type: boolean) Statistics: Num rows: 2 Data size: 13 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col3) - keys: _col0 (type: string), _col1 (type: int) + aggregations: max(_col1) + keys: _col2 (type: string), _col3 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 13 Basic stats: COMPLETE Column stats: NONE @@ -493,7 +497,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan @@ -520,17 +524,10 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-3 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col2 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) - TableScan alias: events Statistics: Num rows: 6 Data size: 79 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -546,17 +543,24 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string), _col3 (type: int) Statistics: Num rows: 6 Data size: 79 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: int) + TableScan + Reduce Output Operator + key expressions: _col0 (type: string), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col2 (type: int) + Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col2 (type: int) - 1 _col0 (type: string), _col3 (type: int) - outputColumnNames: _col0, _col1, _col2, _col4, _col5 + 0 _col0 (type: string), _col3 (type: int) + 1 _col0 (type: string), _col2 (type: int) + outputColumnNames: _col1, _col2, _col4, _col5, _col6 Statistics: Num rows: 6 Data size: 86 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col4 (type: string), _col5 (type: int) + expressions: _col4 (type: string), _col5 (type: int), _col6 (type: int), _col1 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 6 Data size: 86 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out index f77c75c232..74f45e58c0 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out @@ -69,22 +69,6 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -116,24 +100,44 @@ STAGE PLANS: Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 keys: 0 _col1 (type: string) 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -156,22 +160,6 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -203,24 +191,44 @@ STAGE PLANS: Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 keys: 0 _col1 (type: string) 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -228,7 +236,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select * from part p1 join part2 p2 join part3 p3 on p2_partkey + p_partkey = p1.p_partkey and p3_name = p2_name PREHOOK: type: QUERY @@ -245,17 +253,6 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -266,38 +263,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col9 + _col0) = _col0) (type: boolean) - Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col10 (type: string) - sort order: + - Map-reduce partition columns: _col10 (type: string) - Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -319,17 +289,59 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: string) + 0 _col1 (type: string) 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 14 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 14 Data size: 1744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col0 + _col18) = _col18) (type: boolean) + Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 + Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -337,7 +349,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select * from part p1 join part2 p2 join part3 p3 on p2_partkey = 1 and p3_name = p2_name PREHOOK: type: QUERY @@ -354,16 +366,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + alias: p3 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: p3_name is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -375,18 +392,20 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 + 0 _col1 (type: string) + 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false table: @@ -399,43 +418,36 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col10 (type: string) - sort order: + - Map-reduce partition columns: _col10 (type: string) - Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) - TableScan - alias: p3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Filter Operator - predicate: p3_name is not null (type: boolean) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: string) - 1 _col1 (type: string) + 0 + 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string) + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 28 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual2.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual2.q.out index f04519f8c5..71e16dd2b5 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual2.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual2.q.out @@ -69,22 +69,6 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -117,6 +101,22 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + TableScan alias: p4 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -136,8 +136,8 @@ STAGE PLANS: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 - Inner Join 0 to 3 + Inner Join 0 to 2 + Inner Join 2 to 3 keys: 0 _col1 (type: string) 1 _col1 (type: string) @@ -145,13 +145,17 @@ STAGE PLANS: 3 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 Statistics: Num rows: 85 Data size: 10385 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 Statistics: Num rows: 85 Data size: 10385 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 85 Data size: 10385 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out index f15d536945..b8d9b408d7 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out @@ -71,22 +71,6 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -118,24 +102,44 @@ STAGE PLANS: Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 keys: 0 _col1 (type: string) 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -160,22 +164,6 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -207,24 +195,44 @@ STAGE PLANS: Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 keys: 0 _col1 (type: string) 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -232,7 +240,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select * from part p1 join part2 p2 join part3 p3 where p2_partkey + p1.p_partkey = p1.p_partkey and p3_name = p2_name @@ -251,17 +259,6 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -272,38 +269,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col9 + _col0) = _col0) (type: boolean) - Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col10 (type: string) - sort order: + - Map-reduce partition columns: _col10 (type: string) - Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -325,17 +295,59 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: string) + 0 _col1 (type: string) 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 14 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 14 Data size: 1744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col0 + _col18) = _col18) (type: boolean) + Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 + Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -343,7 +355,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select * from part p1 join part2 p2 join part3 p3 where p2_partkey = 1 and p3_name = p2_name @@ -362,16 +374,21 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + alias: p3 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: p3_name is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -383,18 +400,20 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 + 0 _col1 (type: string) + 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false table: @@ -407,43 +426,36 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col10 (type: string) - sort order: + - Map-reduce partition columns: _col10 (type: string) - Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) - TableScan - alias: p3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Filter Operator - predicate: p3_name is not null (type: boolean) + sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: string) - 1 _col1 (type: string) + 0 + 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string) + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 28 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual4.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual4.q.out index 1ec5dc415c..d79d1044de 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual4.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual4.q.out @@ -71,22 +71,6 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -119,6 +103,22 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + TableScan alias: p4 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -138,8 +138,8 @@ STAGE PLANS: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 - Inner Join 0 to 3 + Inner Join 0 to 2 + Inner Join 2 to 3 keys: 0 _col1 (type: string) 1 _col1 (type: string) @@ -147,13 +147,17 @@ STAGE PLANS: 3 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 Statistics: Num rows: 85 Data size: 10385 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 Statistics: Num rows: 85 Data size: 10385 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 85 Data size: 10385 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/join_hive_626.q.out b/ql/src/test/results/clientpositive/join_hive_626.q.out index 33a5fbd628..d5b772d63c 100644 --- a/ql/src/test/results/clientpositive/join_hive_626.q.out +++ b/ql/src/test/results/clientpositive/join_hive_626.q.out @@ -74,22 +74,6 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: hive_foo - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: foo_id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: foo_id (type: int), foo_name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan alias: hive_bar Statistics: Num rows: 1 Data size: 23 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -105,15 +89,31 @@ STAGE PLANS: Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 1 Data size: 23 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string) + TableScan + alias: hive_foo + Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: foo_id is not null (type: boolean) + Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: foo_id (type: int), foo_name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col4 + Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -126,11 +126,11 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col2 (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col4 (type: string) + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string), _col4 (type: string) TableScan alias: hive_count Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE @@ -152,17 +152,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col4, _col6 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col2, _col4, _col6 + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col4 (type: string), _col6 (type: int) + expressions: _col4 (type: string), _col2 (type: string), _col6 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_star.q.out b/ql/src/test/results/clientpositive/join_star.q.out index 261fb53bf9..cbb7a03d6a 100644 --- a/ql/src/test/results/clientpositive/join_star.q.out +++ b/ql/src/test/results/clientpositive/join_star.q.out @@ -355,13 +355,28 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:dim1 + $hdt$_0:fact Fetch Operator limit: -1 - $hdt$_2:dim2 + $hdt$_1:dim1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: + $hdt$_0:fact + TableScan + alias: fact + Statistics: Num rows: 8 Data size: 98 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: d1 is not null (type: boolean) + Statistics: Num rows: 8 Data size: 98 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: m1 (type: int), m2 (type: int), d1 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 8 Data size: 98 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col2 (type: int) $hdt$_1:dim1 TableScan alias: dim1 @@ -375,9 +390,12 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - $hdt$_2:dim2 + + Stage: Stage-5 + Map Reduce + Map Operator Tree: TableScan alias: dim2 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -388,47 +406,29 @@ STAGE PLANS: expressions: f3 (type: int), f4 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col4 (type: int) - 1 _col0 (type: int) - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: fact - Statistics: Num rows: 8 Data size: 98 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: d1 is not null (type: boolean) - Statistics: Num rows: 8 Data size: 98 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: m1 (type: int), m2 (type: int), d1 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 8 Data size: 98 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 8 Data size: 107 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col4 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col4, _col6 - Statistics: Num rows: 8 Data size: 117 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: int) + 1 _col2 (type: int) + outputColumnNames: _col1, _col3, _col4, _col5 + Statistics: Num rows: 8 Data size: 107 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col4 (type: int), _col6 (type: int) + expressions: _col4 (type: int), _col5 (type: int), _col1 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 117 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 107 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 117 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 107 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -598,12 +598,12 @@ POSTHOOK: query: explain Select m1, m2, f2, f4, f6, f8, f10, f12, f14 Left outer Join dim7 on dim6.f12 = dim7.f13 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-20 is a root stage - Stage-14 depends on stages: Stage-20 - Stage-0 depends on stages: Stage-14 + Stage-22 is a root stage + Stage-15 depends on stages: Stage-22 + Stage-0 depends on stages: Stage-15 STAGE PLANS: - Stage: Stage-20 + Stage: Stage-22 Map Reduce Local Work Alias -> Map Local Tables: $hdt$_1:dim1 @@ -676,7 +676,6 @@ STAGE PLANS: keys: 0 _col9 (type: int) 1 _col0 (type: int) - 2 _col0 (type: int) $hdt$_5:dim5 TableScan alias: dim5 @@ -701,7 +700,6 @@ STAGE PLANS: keys: 0 _col9 (type: int) 1 _col0 (type: int) - 2 _col0 (type: int) $hdt$_7:dim7 TableScan alias: dim7 @@ -712,10 +710,10 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col13 (type: int) + 0 _col15 (type: int) 1 _col0 (type: int) - Stage: Stage-14 + Stage: Stage-15 Map Reduce Map Operator Tree: TableScan @@ -752,40 +750,46 @@ STAGE PLANS: Map Join Operator condition map: Left Outer Join 0 to 1 - Left Outer Join 0 to 2 keys: 0 _col9 (type: int) 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13 - Statistics: Num rows: 13 Data size: 281 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11 + Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 keys: 0 _col11 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13, _col15 - Statistics: Num rows: 14 Data size: 309 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13 + Statistics: Num rows: 6 Data size: 154 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 keys: - 0 _col13 (type: int) + 0 _col9 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13, _col15, _col17 - Statistics: Num rows: 15 Data size: 339 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col7 (type: int), _col9 (type: int), _col11 (type: int), _col15 (type: int), _col13 (type: int), _col17 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 15 Data size: 339 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 15 Data size: 339 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13, _col15 + Statistics: Num rows: 6 Data size: 169 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col15 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13, _col15, _col17 + Statistics: Num rows: 6 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col7 (type: int), _col9 (type: int), _col11 (type: int), _col13 (type: int), _col15 (type: int), _col17 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 6 Data size: 185 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 185 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out index 8bc280cedd..20747a2cd9 100644 --- a/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out @@ -64,40 +64,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -107,10 +107,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -174,25 +174,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -200,17 +200,17 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap Reducer 2 Execution mode: llap @@ -219,17 +219,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -238,10 +238,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -330,25 +330,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -356,43 +356,43 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap Map 5 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -400,18 +400,18 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap Reducer 2 @@ -422,12 +422,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap @@ -439,14 +439,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -459,12 +459,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -547,40 +547,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -590,10 +590,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -664,40 +664,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -707,10 +707,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -805,40 +805,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -848,10 +848,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -934,40 +934,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -977,10 +977,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1042,38 +1042,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (key + 1) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (key + 1) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1085,15 +1085,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -1102,10 +1102,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1162,40 +1162,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -1205,10 +1205,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1271,36 +1271,36 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -1309,15 +1309,15 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -1327,10 +1327,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1409,40 +1409,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -1452,10 +1452,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1545,25 +1545,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -1571,18 +1571,18 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4650 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4650 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1590,7 +1590,7 @@ STAGE PLANS: name: default.dest1 File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9100 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1762,25 +1762,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -1788,10 +1788,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4650 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4650 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1800,18 +1800,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4650 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap Reducer 2 @@ -1822,14 +1822,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_11.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_11.q.out index 7e3fe4c862..81d6b446c2 100644 --- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_11.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_11.q.out @@ -118,22 +118,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 203 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: true Execution mode: llap @@ -195,16 +195,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 21592 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 9523 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 9523 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -215,16 +215,16 @@ STAGE PLANS: input vertices: 0 Map 1 Position of Big Table: 1 - Statistics: Num rows: 127 Data size: 13807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false @@ -340,13 +340,13 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -408,22 +408,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 203 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: true Execution mode: llap @@ -485,16 +485,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 21592 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 9523 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 9523 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -505,16 +505,16 @@ STAGE PLANS: input vertices: 0 Map 1 Position of Big Table: 1 - Statistics: Num rows: 127 Data size: 13807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false @@ -630,13 +630,13 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -698,18 +698,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 203 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) null sort order: a sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: true Execution mode: llap @@ -771,12 +771,12 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 21592 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 9523 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -787,16 +787,16 @@ STAGE PLANS: input vertices: 0 Map 1 Position of Big Table: 1 - Statistics: Num rows: 127 Data size: 13807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false @@ -912,13 +912,13 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -980,18 +980,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 203 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) null sort order: a sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: true Execution mode: llap @@ -1053,17 +1053,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 21592 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 9523 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 - Estimated key counts: Map 1 => 1, Map 4 => 116 + Estimated key counts: Map 1 => 1, Map 4 => 111 keys: 0 key (type: string) 1 key (type: string) @@ -1072,16 +1072,16 @@ STAGE PLANS: 0 Map 1 2 Map 4 Position of Big Table: 1 - Statistics: Num rows: 255 Data size: 27614 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 23 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false @@ -1193,18 +1193,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: c - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 21592 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 9523 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) null sort order: a sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 116 Data size: 12552 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 9523 Basic stats: COMPLETE Column stats: COMPLETE tag: 2 auto parallelism: true Execution mode: llap @@ -1319,13 +1319,13 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out index 278c55b3e4..a380df365f 100644 --- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out @@ -65,14 +65,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -81,15 +81,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -97,19 +97,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -119,10 +119,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -180,14 +180,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -197,18 +197,18 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -216,19 +216,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -239,10 +239,10 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -316,14 +316,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -333,36 +333,36 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -372,17 +372,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -391,10 +391,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -483,14 +483,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -500,24 +500,24 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -525,19 +525,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -548,7 +548,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -558,14 +558,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 1 Reducer 3 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -578,12 +578,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -667,14 +667,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -683,15 +683,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -699,19 +699,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -721,10 +721,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -796,14 +796,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -812,15 +812,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -828,19 +828,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -850,10 +850,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -949,14 +949,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -965,15 +965,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -981,19 +981,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1003,10 +1003,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1090,14 +1090,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1106,15 +1106,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1122,19 +1122,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1144,10 +1144,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1209,14 +1209,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (key + 1) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1225,15 +1225,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1241,19 +1241,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (key + 1) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1263,10 +1263,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1324,14 +1324,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1340,15 +1340,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1356,19 +1356,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1378,10 +1378,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1437,14 +1437,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1453,15 +1453,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1469,19 +1469,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1491,10 +1491,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1560,14 +1560,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1579,15 +1579,15 @@ STAGE PLANS: input vertices: 1 Map 3 2 Map 4 - Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1595,38 +1595,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1636,10 +1636,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1719,14 +1719,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1735,15 +1735,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1751,19 +1751,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1773,10 +1773,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1846,14 +1846,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1862,15 +1862,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1878,19 +1878,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1900,10 +1900,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1961,14 +1961,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1978,18 +1978,18 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1997,19 +1997,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -2020,10 +2020,10 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2097,14 +2097,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -2114,36 +2114,36 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -2153,17 +2153,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -2172,10 +2172,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2264,14 +2264,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -2281,24 +2281,24 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -2306,19 +2306,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -2329,7 +2329,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -2339,14 +2339,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 1 Reducer 3 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2359,12 +2359,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -2448,14 +2448,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -2464,15 +2464,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -2480,19 +2480,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -2502,10 +2502,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2577,14 +2577,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -2593,15 +2593,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -2609,19 +2609,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -2631,10 +2631,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2730,14 +2730,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -2746,15 +2746,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -2762,19 +2762,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -2784,10 +2784,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2871,14 +2871,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -2887,15 +2887,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -2903,19 +2903,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -2925,10 +2925,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2986,14 +2986,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -3002,15 +3002,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -3018,19 +3018,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -3040,10 +3040,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3099,14 +3099,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -3115,15 +3115,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -3131,19 +3131,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -3153,10 +3153,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3222,14 +3222,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -3241,15 +3241,15 @@ STAGE PLANS: input vertices: 1 Map 3 2 Map 4 - Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -3257,38 +3257,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -3298,10 +3298,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3381,14 +3381,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -3397,15 +3397,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -3413,19 +3413,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -3435,10 +3435,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out index 649afb502a..47b6c609c9 100644 --- a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out @@ -132,19 +132,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 24049 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -152,14 +152,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -169,14 +169,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 206323 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 206323 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 206323 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -217,39 +217,39 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tab_part - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: int), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 237 Data size: 21018 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 237 Data size: 21018 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -259,11 +259,11 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 237 Data size: 21018 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 237 Data size: 21018 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -272,15 +272,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 4 - Statistics: Num rows: 275 Data size: 5121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 573 Data size: 4584 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -289,10 +289,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -346,101 +346,105 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 2 <- Map 1 (CUSTOM_EDGE), Map 4 (CUSTOM_EDGE) - Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) + Map 1 <- Map 3 (CUSTOM_EDGE), Map 4 (CUSTOM_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + alias: b + Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + input vertices: + 1 Map 3 + Statistics: Num rows: 1150 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1150 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 4 + Statistics: Num rows: 5750 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs - Map 2 + Map 3 Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + alias: a + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 0 Map 1 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 4 - Statistics: Num rows: 605 Data size: 11267 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: d - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Reducer 3 + Reducer 2 Execution mode: llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -498,101 +502,105 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 3 <- Map 1 (CUSTOM_EDGE), Map 2 (CUSTOM_EDGE) - Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) + Map 1 <- Map 3 (CUSTOM_EDGE), Map 4 (CUSTOM_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: d - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + alias: b + Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + input vertices: + 1 Map 3 + Statistics: Num rows: 1150 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1150 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 4 + Statistics: Num rows: 5750 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs - Map 2 + Map 3 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 3 + Map 4 Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + alias: d + Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 0 Map 2 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - input vertices: - 0 Map 1 - Statistics: Num rows: 605 Data size: 11267 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Reducer 4 + Reducer 2 Execution mode: llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -654,25 +662,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcbucket_mapjoin - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5319 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2418 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2418 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: llap LLAP IO: no inputs @@ -680,14 +688,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 24049 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -697,14 +705,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Reducer 2 - Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 1635 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 1635 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 1635 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -719,16 +727,16 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: double), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double) Stage: Stage-0 @@ -756,22 +764,58 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Map 3 (CUSTOM_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (CUSTOM_SIMPLE_EDGE) + Map 1 <- Reducer 3 (CUSTOM_EDGE) + Map 2 <- Map 4 (CUSTOM_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan + alias: b + Statistics: Num rows: 242 Data size: 24049 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Reducer 3 + Statistics: Num rows: 230 Data size: 22300 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col2 (type: double), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 230 Data size: 22300 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 230 Data size: 22300 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan alias: tab_part - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -780,53 +824,47 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2 input vertices: - 1 Map 3 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + 1 Map 4 + Statistics: Num rows: 1150 Data size: 106020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), substr(_col2, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 106020 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 47 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 47 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: llap LLAP IO: no inputs - Map 3 + Map 4 Map Operator Tree: TableScan alias: tab - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 24049 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs - Reducer 2 + Reducer 3 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -834,32 +872,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 5121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: double), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 5121 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 - input vertices: - 1 Map 3 - Statistics: Num rows: 302 Data size: 5633 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 302 Data size: 5633 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 302 Data size: 5633 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 46 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 46 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double) Stage: Stage-0 Fetch Operator @@ -886,22 +909,58 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Map 3 (CUSTOM_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (CUSTOM_SIMPLE_EDGE) + Map 1 <- Reducer 3 (CUSTOM_EDGE) + Map 2 <- Map 4 (CUSTOM_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan + alias: b + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Reducer 3 + Statistics: Num rows: 230 Data size: 21183 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col3 (type: int), _col2 (type: double), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 230 Data size: 21183 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 230 Data size: 21183 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan alias: x - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 24049 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -910,66 +969,46 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 input vertices: - 1 Map 3 - Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE + 1 Map 4 + Statistics: Num rows: 1150 Data size: 106020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), substr(_col1, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 106020 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 47 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 47 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: llap LLAP IO: no inputs - Map 3 + Map 4 Map Operator Tree: TableScan alias: y - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE - Execution mode: llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Reducer 2 + Reducer 3 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -977,32 +1016,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 2476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: double), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 2476 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 - input vertices: - 1 Map 4 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 46 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 46 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double) Stage: Stage-0 Fetch Operator @@ -1034,14 +1058,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1050,18 +1074,18 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: _col0, _col1, _col4 input vertices: 1 Map 2 2 Map 3 - Statistics: Num rows: 1100 Data size: 20486 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5750 Data size: 1043471 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) + expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1100 Data size: 20486 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5750 Data size: 1043471 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 20486 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5750 Data size: 1043471 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1071,40 +1095,40 @@ STAGE PLANS: Map 2 Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + alias: c + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 3 Map Operator Tree: TableScan - alias: c - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + alias: b + Statistics: Num rows: 242 Data size: 24049 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -1131,21 +1155,22 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Map 2 (CUSTOM_EDGE), Map 3 (CUSTOM_EDGE) + Map 1 <- Map 3 (CUSTOM_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1154,70 +1179,77 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 input vertices: - 1 Map 2 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 - input vertices: - 1 Map 3 - Statistics: Num rows: 605 Data size: 11267 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 11267 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 605 Data size: 11267 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 1 Map 3 + Statistics: Num rows: 1150 Data size: 104811 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1150 Data size: 104811 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs - Map 2 + Map 3 Map Operator Tree: TableScan alias: y - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 3 + Map 4 Map Operator Tree: TableScan alias: c - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 24049 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 5750 Data size: 1043471 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5750 Data size: 1043471 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 5750 Data size: 1043471 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1252,25 +1284,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcbucket_mapjoin - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5319 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2418 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2418 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: llap LLAP IO: no inputs @@ -1278,14 +1310,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1295,14 +1327,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Reducer 2 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 478 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 478 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 478 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1317,12 +1349,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Stage: Stage-0 @@ -1358,19 +1390,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcbucket_mapjoin - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5319 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2418 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2418 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2418 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -1378,14 +1410,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1395,14 +1427,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Reducer 2 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 983 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 983 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 983 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1417,12 +1449,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Stage: Stage-0 @@ -1448,60 +1480,66 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 24049 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 2 + Map 3 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47676 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 40228 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - input vertices: - 0 Map 1 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 475 Data size: 40228 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 475 Data size: 40228 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1150 Data size: 206323 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1150 Data size: 206323 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1555,19 +1593,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 21483 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -1575,14 +1613,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1592,14 +1630,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 206323 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 206323 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 206323 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1626,93 +1664,95 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Map 2 (CUSTOM_EDGE), Map 3 (BROADCAST_EDGE) + Map 1 <- Map 3 (CUSTOM_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + alias: c + Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + predicate: key is not null (type: boolean) + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col2 input vertices: - 1 Map 2 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 - input vertices: - 1 Map 3 - Statistics: Num rows: 605 Data size: 11267 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col3 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 11267 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 605 Data size: 11267 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 1 Map 3 + Statistics: Num rows: 2255 Data size: 207669 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 2255 Data size: 207669 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int) Execution mode: llap LLAP IO: no inputs - Map 2 + Map 3 Map Operator Tree: TableScan - alias: c - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + alias: a + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 451 Data size: 39897 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 451 Data size: 39897 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE - Execution mode: llap - LLAP IO: no inputs - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 451 Data size: 39897 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col1, _col3 + Statistics: Num rows: 11275 Data size: 90020 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int), _col3 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 11275 Data size: 90020 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 11275 Data size: 90020 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1737,79 +1777,86 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 47094 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 242 Data size: 68577 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 44528 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 230 Data size: 62780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 242 Data size: 44528 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 230 Data size: 62780 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col2 (type: string) - Statistics: Num rows: 242 Data size: 44528 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 230 Data size: 62780 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 141580 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 475 Data size: 129436 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 475 Data size: 129436 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col2 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col2 (type: string) + Statistics: Num rows: 475 Data size: 129436 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Select Operator expressions: _col2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 44528 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 475 Data size: 129436 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 237 Data size: 64626 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) - Target Input: b + Target Input: a Partition key expr: ds - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL - Target Vertex: Map 2 + Statistics: Num rows: 237 Data size: 64626 Basic stats: COMPLETE Column stats: COMPLETE + Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs - Map 2 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 97312 Basic stats: COMPLETE Column stats: PARTIAL - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: PARTIAL - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: PARTIAL - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int), _col2 (type: string) - 1 _col0 (type: int), _col2 (type: string) - outputColumnNames: _col0, _col1, _col4 - input vertices: - 0 Map 1 - Statistics: Num rows: 60500 Data size: 12826000 Basic stats: COMPLETE Column stats: PARTIAL - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60500 Data size: 484000 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 60500 Data size: 484000 Basic stats: COMPLETE Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 2 Execution mode: llap - LLAP IO: no inputs + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col2 (type: string) + 1 _col0 (type: int), _col2 (type: string) + outputColumnNames: _col0, _col1, _col4 + Statistics: Num rows: 1150 Data size: 206323 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1150 Data size: 206323 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1150 Data size: 206323 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1856,14 +1903,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1872,29 +1919,29 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 3 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1904,10 +1951,10 @@ STAGE PLANS: aggregations: count() mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1975,14 +2022,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1991,29 +2038,29 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 3 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -2023,10 +2070,10 @@ STAGE PLANS: aggregations: count() mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/bucketmapjoin1.q.out b/ql/src/test/results/clientpositive/llap/bucketmapjoin1.q.out index feb3bbcfc4..75810c148b 100644 --- a/ql/src/test/results/clientpositive/llap/bucketmapjoin1.q.out +++ b/ql/src/test/results/clientpositive/llap/bucketmapjoin1.q.out @@ -48,22 +48,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: true @@ -73,22 +73,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: true @@ -106,17 +106,17 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Position of Big Table: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -180,22 +180,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: true @@ -205,22 +205,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: true @@ -238,17 +238,17 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Position of Big Table: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -406,22 +406,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2418 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2325 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2325 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2325 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: true @@ -482,22 +482,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10834 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53 Data size: 4836 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53 Data size: 9818 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53 Data size: 9818 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: true @@ -568,17 +568,17 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Position of Big Table: 1 - Statistics: Num rows: 60 Data size: 6877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 21751 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60 Data size: 6877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 43351 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 60 Data size: 6877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 43351 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -772,22 +772,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2418 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2325 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2325 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2325 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: true @@ -848,22 +848,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10834 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53 Data size: 4836 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53 Data size: 9818 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 55 Data size: 6252 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53 Data size: 9818 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: true @@ -934,17 +934,17 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Position of Big Table: 1 - Statistics: Num rows: 60 Data size: 6877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 21751 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60 Data size: 6877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 43351 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 60 Data size: 6877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 43351 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat diff --git a/ql/src/test/results/clientpositive/llap/bucketpruning1.q.out b/ql/src/test/results/clientpositive/llap/bucketpruning1.q.out index 922f23a29e..2c76ea2bd9 100644 --- a/ql/src/test/results/clientpositive/llap/bucketpruning1.q.out +++ b/ql/src/test/results/clientpositive/llap/bucketpruning1.q.out @@ -35,22 +35,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: (key = 1) (type: boolean) buckets included: [1,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -97,22 +97,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: (key = 16) (type: boolean) buckets included: [0,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = 16) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 16 (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -159,22 +159,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: (key = 17) (type: boolean) buckets included: [1,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = 17) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 17 (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -221,22 +221,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: (key = 17) (type: boolean) buckets included: [1,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = 17) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 17 (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -283,22 +283,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: (key = 11) (type: boolean) buckets included: [11,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = 11) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 11 (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -345,22 +345,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: ((key = 1) and (ds = '2008-04-08')) (type: boolean) buckets included: [1,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = 1) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int), value (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -407,22 +407,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: ((key = 1) and (ds = '2008-04-08') and (value = 'One')) (type: boolean) buckets included: [1,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = 1) and (ds = '2008-04-08') and (value = 'One')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int), 'One' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -469,22 +469,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: ((value = 'One') and (key = 1) and (ds = '2008-04-08')) (type: boolean) buckets included: [1,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((value = 'One') and (key = 1) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int), 'One' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -531,22 +531,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: (key) IN (2, 3) (type: boolean) buckets included: [2,3,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key) IN (2, 3) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -593,22 +593,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: ((key) IN (2, 3) and (ds = '2008-04-08')) (type: boolean) buckets included: [2,3,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key) IN (2, 3) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -655,22 +655,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: ((key) IN (2, 3) and (ds = '2008-04-08') and (value = 'One')) (type: boolean) buckets included: [2,3,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key) IN (2, 3) and (ds = '2008-04-08') and (value = 'One')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), 'One' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -717,22 +717,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: ((key) IN (2, 3) and (value = 'One') and (ds = '2008-04-08')) (type: boolean) buckets included: [2,3,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key) IN (2, 3) and (value = 'One') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), 'One' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -778,22 +778,22 @@ STAGE PLANS: TableScan alias: srcbucket_pruned filterExpr: (((key = 1) or (key = 2)) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (((key = 1) or (key = 2)) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -839,22 +839,22 @@ STAGE PLANS: TableScan alias: srcbucket_pruned filterExpr: (((key = 1) or (key = 2)) and (value = 'One') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (((key = 1) or (key = 2)) and (value = 'One') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), 'One' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -901,22 +901,22 @@ STAGE PLANS: alias: srcbucket_pruned filterExpr: (key = -15) (type: boolean) buckets included: [1,15,] of 16 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = -15) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: -15 (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -962,22 +962,22 @@ STAGE PLANS: TableScan alias: srcbucket_pruned filterExpr: (key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1023,22 +1023,22 @@ STAGE PLANS: TableScan alias: srcbucket_pruned filterExpr: ((key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1084,22 +1084,22 @@ STAGE PLANS: TableScan alias: srcbucket_pruned filterExpr: ((key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) and (ds = '2008-04-08') and (value = 'One')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) and (ds = '2008-04-08') and (value = 'One')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), 'One' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1145,22 +1145,22 @@ STAGE PLANS: TableScan alias: srcbucket_pruned filterExpr: ((key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) and (value = 'One') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17) and (value = 'One') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), 'One' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 181 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1206,22 +1206,22 @@ STAGE PLANS: TableScan alias: srcbucket_pruned filterExpr: (((key = 1) and (ds = '2008-04-08')) or (key = 2)) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (((key = 1) and (ds = '2008-04-08')) or (key = 2)) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1267,22 +1267,22 @@ STAGE PLANS: TableScan alias: srcbucket_pruned filterExpr: ((key = 1) and (ds = '2008-04-08') and ((value = 'One') or (value = 'Two'))) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = 1) and (ds = '2008-04-08') and ((value = 'One') or (value = 'Two'))) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int), value (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1328,22 +1328,22 @@ STAGE PLANS: TableScan alias: srcbucket_pruned filterExpr: ((key = 1) or (value = 'One') or ((key = 2) and (value = 'Two'))) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = 1) or (value = 'One') or ((key = 2) and (value = 'Two'))) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1388,22 +1388,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcbucket_pruned - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1449,22 +1449,22 @@ STAGE PLANS: TableScan alias: srcbucket_pruned filterExpr: ((key = 1) or (value = 'One')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = 1) or (value = 'One')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1510,22 +1510,22 @@ STAGE PLANS: TableScan alias: srcbucket_pruned filterExpr: ((key = 1) or (value = 'One') or (key = 2)) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = 1) or (value = 'One') or (key = 2)) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1571,22 +1571,22 @@ STAGE PLANS: TableScan alias: srcbucket_unpruned filterExpr: (key) IN (3, 5) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key) IN (3, 5) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1632,22 +1632,22 @@ STAGE PLANS: TableScan alias: srcbucket_unpruned filterExpr: (key = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out index 8691d0d34e..7cd4c4f7ed 100644 --- a/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out +++ b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out @@ -85,19 +85,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -105,14 +105,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8269 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -122,16 +122,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col4 input vertices: 0 Map 1 - Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), concat(_col1, _col4) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9400 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -141,10 +141,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9400 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9400 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -268,19 +268,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table1 - Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -288,14 +288,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table2 - Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8269 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -305,16 +305,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), concat(_col1, _col3) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9400 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -324,10 +324,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9400 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9400 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -457,19 +457,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table1 - Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 8) and ((key = 0) or (key = 5))) (type: boolean) - Statistics: Num rows: 2 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -477,14 +477,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table2 - Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8269 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 8) and ((key = 0) or (key = 5))) (type: boolean) - Statistics: Num rows: 28 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -494,16 +494,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 30 Data size: 515 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 2730 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), concat(_col1, _col3) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 30 Data size: 515 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 2820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 30 Data size: 515 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 2820 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -513,10 +513,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 30 Data size: 515 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 2820 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 515 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 2820 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/columnStatsUpdateForStatsOptimizer_1.q.out b/ql/src/test/results/clientpositive/llap/columnStatsUpdateForStatsOptimizer_1.q.out index 6d941fd4f2..865e54da23 100644 --- a/ql/src/test/results/clientpositive/llap/columnStatsUpdateForStatsOptimizer_1.q.out +++ b/ql/src/test/results/clientpositive/llap/columnStatsUpdateForStatsOptimizer_1.q.out @@ -130,19 +130,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: calendar - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: year (type: int) outputColumnNames: year - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(year) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs @@ -153,10 +153,10 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -707,19 +707,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: calendarp - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: year (type: int) outputColumnNames: year - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(year) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs @@ -730,10 +730,10 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/column_access_stats.q.out b/ql/src/test/results/clientpositive/llap/column_access_stats.q.out index c56c818617..8a24f28e99 100644 --- a/ql/src/test/results/clientpositive/llap/column_access_stats.q.out +++ b/ql/src/test/results/clientpositive/llap/column_access_stats.q.out @@ -185,14 +185,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -203,14 +203,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -273,14 +273,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -291,14 +291,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -387,38 +387,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 3 Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -431,10 +431,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -518,19 +518,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(val) = 3.0) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -538,19 +538,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(val) = 3.0) and key is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -564,10 +564,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -620,38 +620,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) = 5.0) and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 3 Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) = 6.0) and val is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -664,10 +664,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -733,58 +733,58 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + alias: t2 + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan - alias: t2 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + alias: t1 + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 5 Map Operator Tree: TableScan alias: t3 - Statistics: Num rows: 5 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -797,13 +797,17 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col1 + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -814,10 +818,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 6675 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 6675 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -850,10 +854,10 @@ PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 PREHOOK: Input: default@t3 #### A masked pattern was here #### -Table:default@t1 +Table:default@t2 Columns:key -Table:default@t2 +Table:default@t1 Columns:key Table:default@t3 diff --git a/ql/src/test/results/clientpositive/llap/column_table_stats.q.out b/ql/src/test/results/clientpositive/llap/column_table_stats.q.out index c7726fec30..4eaebf6c1d 100644 --- a/ql/src/test/results/clientpositive/llap/column_table_stats.q.out +++ b/ql/src/test/results/clientpositive/llap/column_table_stats.q.out @@ -73,22 +73,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 5162 Basic stats: COMPLETE Column stats: COMPLETE Statistics Aggregation Key Prefix: default.s/ GatherStats: true Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 5162 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -151,13 +151,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -332,13 +332,13 @@ STAGE PLANS: Map Operator Tree: TableScan alias: spart - Statistics: Num rows: 58 Data size: 32968 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 58 Data size: 43114 Basic stats: COMPLETE Column stats: PARTIAL Statistics Aggregation Key Prefix: default.spart/ GatherStats: true Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 58 Data size: 32968 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 58 Data size: 43114 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) @@ -749,13 +749,13 @@ STAGE PLANS: Map Operator Tree: TableScan alias: spart - Statistics: Num rows: 58 Data size: 32968 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 58 Data size: 43114 Basic stats: COMPLETE Column stats: PARTIAL Statistics Aggregation Key Prefix: default.spart/ GatherStats: true Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 58 Data size: 32968 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 58 Data size: 43114 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) @@ -1166,13 +1166,13 @@ STAGE PLANS: Map Operator Tree: TableScan alias: spart - Statistics: Num rows: 29 Data size: 11148 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 29 Data size: 16310 Basic stats: COMPLETE Column stats: PARTIAL Statistics Aggregation Key Prefix: default.spart/ GatherStats: true Select Operator expressions: key (type: string), value (type: string), ds (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 29 Data size: 11148 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 29 Data size: 16310 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), '11' (type: string) diff --git a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out index 3de40ce871..9c6223f3bb 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out @@ -237,33 +237,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -276,15 +276,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -293,10 +293,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -366,19 +366,19 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -390,15 +390,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -407,10 +407,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -493,33 +493,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: day(_col0) (type: int) sort order: + Map-reduce partition columns: day(_col0) (type: int) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: day(_col0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: day(ds) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -532,15 +532,15 @@ STAGE PLANS: keys: 0 day(_col0) (type: int) 1 day(_col0) (type: int) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 129 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -549,10 +549,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -622,19 +622,19 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: day(_col0) (type: int) sort order: + Map-reduce partition columns: day(_col0) (type: int) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -646,15 +646,15 @@ STAGE PLANS: keys: 0 day(_col0) (type: int) 1 day(_col0) (type: int) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 129 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -663,10 +663,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -739,33 +739,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -774,33 +774,33 @@ STAGE PLANS: TableScan alias: srcpart_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -814,12 +814,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -829,15 +829,15 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2420 Data size: 890560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: llap @@ -846,10 +846,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -927,19 +927,19 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 6 @@ -947,19 +947,19 @@ STAGE PLANS: TableScan alias: srcpart_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -972,12 +972,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -987,15 +987,15 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2420 Data size: 890560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: llap @@ -1004,10 +1004,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1091,48 +1091,48 @@ STAGE PLANS: TableScan alias: srcpart_date_hour filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Select Operator expressions: _col2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -1145,15 +1145,15 @@ STAGE PLANS: keys: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -1162,10 +1162,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1235,19 +1235,19 @@ STAGE PLANS: TableScan alias: srcpart_date_hour filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1259,15 +1259,15 @@ STAGE PLANS: keys: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -1276,10 +1276,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1360,33 +1360,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -1399,15 +1399,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -1416,10 +1416,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1489,19 +1489,19 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1513,15 +1513,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -1530,10 +1530,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1612,33 +1612,33 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -1651,15 +1651,15 @@ STAGE PLANS: keys: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -1668,10 +1668,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1741,33 +1741,33 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: (UDFToDouble(hr) * 2.0) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -1780,15 +1780,15 @@ STAGE PLANS: keys: 0 (UDFToDouble(_col0) * 2.0) (type: double) 1 _col0 (type: double) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -1797,10 +1797,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1870,19 +1870,19 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1894,15 +1894,15 @@ STAGE PLANS: keys: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -1911,10 +1911,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1984,19 +1984,19 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -2008,15 +2008,15 @@ STAGE PLANS: keys: 0 (UDFToDouble(_col0) * 2.0) (type: double) 1 _col0 (type: double) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -2025,10 +2025,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2111,33 +2111,33 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToString(_col0) (type: string) sort order: + Map-reduce partition columns: UDFToString(_col0) (type: string) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToString(_col0) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: UDFToString((UDFToDouble(hr) * 2.0)) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -2150,15 +2150,15 @@ STAGE PLANS: keys: 0 UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) 1 UDFToString(_col0) (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -2167,10 +2167,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2375,17 +2375,17 @@ STAGE PLANS: TableScan alias: srcpart_date_hour filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) - Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -2400,17 +2400,17 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col4 residual filter predicates: {((_col0 = _col2) or (_col1 = _col4))} - Statistics: Num rows: 2000 Data size: 792000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4000 Data size: 2184000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 2000 Data size: 792000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4000 Data size: 2184000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -2419,10 +2419,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2492,48 +2492,48 @@ STAGE PLANS: TableScan alias: srcpart_date_hour filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Select Operator expressions: _col2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -2546,15 +2546,15 @@ STAGE PLANS: keys: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -2563,10 +2563,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2636,33 +2636,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -2675,15 +2675,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -2692,10 +2692,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2729,33 +2729,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 4 Execution mode: llap LLAP IO: no inputs @@ -2784,15 +2784,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -2801,10 +2801,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2854,33 +2854,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -2893,15 +2893,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap @@ -2910,10 +2910,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2967,33 +2967,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -3002,33 +3002,33 @@ STAGE PLANS: TableScan alias: srcpart_hour filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -3042,12 +3042,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 1100 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1100 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -3057,15 +3057,15 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1210 Data size: 445280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: llap @@ -3074,10 +3074,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3123,14 +3123,36 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Map 7 <- Reducer 5 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan + alias: srcpart_hour + filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean) + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(hr) = 13.0) (type: boolean) + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan alias: srcpart filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE @@ -3142,51 +3164,31 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + value expressions: _col0 (type: string) Execution mode: llap LLAP IO: unknown - Map 5 + Map 7 Map Operator Tree: TableScan alias: srcpart_date - filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + filterExpr: ((date = '2008-04-08') and ds is not null and (ds BETWEEN DynamicValue(RS_12_srcpart_ds_min) AND DynamicValue(RS_12_srcpart_ds_max) and in_bloom_filter(ds, DynamicValue(RS_12_srcpart_ds_bloom_filter)))) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + predicate: ((date = '2008-04-08') and ds is not null and (ds BETWEEN DynamicValue(RS_12_srcpart_ds_min) AND DynamicValue(RS_12_srcpart_ds_max) and in_bloom_filter(ds, DynamicValue(RS_12_srcpart_ds_bloom_filter)))) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Execution mode: llap - LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: srcpart_hour - filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) = 13.0) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -3197,14 +3199,27 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: string) - 1 _col0 (type: string) + 1 _col1 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=2) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -3214,15 +3229,15 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: llap @@ -3231,14 +3246,26 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=2) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) Stage: Stage-0 Fetch Operator @@ -3988,15 +4015,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -4005,33 +4032,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -4042,10 +4069,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4124,15 +4151,15 @@ STAGE PLANS: 1 day(_col0) (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 129 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -4141,33 +4168,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: day(_col0) (type: int) sort order: + Map-reduce partition columns: day(_col0) (type: int) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: day(_col0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: day(ds) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -4178,10 +4205,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4249,7 +4276,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -4258,15 +4285,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 1 Map 4 - Statistics: Num rows: 2420 Data size: 890560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -4275,33 +4302,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -4310,33 +4337,33 @@ STAGE PLANS: TableScan alias: srcpart_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -4347,10 +4374,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4430,15 +4457,15 @@ STAGE PLANS: 1 _col0 (type: string), _col2 (type: string) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -4447,48 +4474,48 @@ STAGE PLANS: TableScan alias: srcpart_date_hour filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Select Operator expressions: _col2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -4499,10 +4526,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4579,15 +4606,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -4596,33 +4623,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -4633,10 +4660,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4702,15 +4729,15 @@ STAGE PLANS: 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -4719,33 +4746,33 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -4756,10 +4783,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4825,15 +4852,15 @@ STAGE PLANS: 1 _col0 (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -4842,33 +4869,33 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: (UDFToDouble(hr) * 2.0) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -4879,10 +4906,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5089,15 +5116,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -5106,33 +5133,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -5143,10 +5170,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5180,14 +5207,14 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -5196,15 +5223,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -5231,10 +5258,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5284,14 +5311,14 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -5300,15 +5327,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 0 Map 1 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -5319,10 +5346,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5371,7 +5398,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 3 - Statistics: Num rows: 1100 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -5380,15 +5407,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 1 Map 4 - Statistics: Num rows: 1210 Data size: 445280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -5397,33 +5424,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -5432,33 +5459,33 @@ STAGE PLANS: TableScan alias: srcpart_hour filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -5469,10 +5496,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5518,13 +5545,44 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 2 <- Map 1 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) - Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) + Map 1 <- Map 2 (BROADCAST_EDGE) + Map 3 <- Map 1 (BROADCAST_EDGE) + Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan + alias: srcpart_hour + filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean) + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(hr) = 13.0) (type: boolean) + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col1 + input vertices: + 1 Map 2 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan alias: srcpart filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE @@ -5536,87 +5594,57 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + value expressions: _col0 (type: string) Execution mode: llap LLAP IO: unknown - Map 2 + Map 3 Map Operator Tree: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) - outputColumnNames: _col1 input vertices: 0 Map 1 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - input vertices: - 1 Map 4 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: srcpart_hour - filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) = 13.0) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs - Reducer 3 + Reducer 4 Execution mode: llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5917,15 +5945,15 @@ STAGE PLANS: 1 _col0 (type: string), UDFToDouble(_col2) (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 413600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: all inputs @@ -5934,48 +5962,48 @@ STAGE PLANS: TableScan alias: srcpart_date_hour filterExpr: (((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), UDFToDouble(_col2) (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: string), UDFToDouble(_col2) (type: double) - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart_orc Partition key expr: ds - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Select Operator expressions: UDFToDouble(_col2) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (int) Target Input: srcpart_orc Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -5986,10 +6014,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out index e78429fc7f..91a8c47448 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out @@ -166,11 +166,11 @@ STAGE PLANS: TableScan alias: agg filterExpr: dim_shops_id is not null (type: boolean) - Statistics: Num rows: 9 Data size: 63 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 1071 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: amount (type: decimal(10,0)), dim_shops_id (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 1044 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -180,18 +180,18 @@ STAGE PLANS: outputColumnNames: _col0, _col3 input vertices: 1 Map 4 - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1809 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(_col0) keys: _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0)) Execution mode: llap LLAP IO: no inputs @@ -200,34 +200,34 @@ STAGE PLANS: TableScan alias: d1 filterExpr: ((label) IN ('foo', 'bar') and id is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((label) IN ('foo', 'bar') and id is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int), label (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: dim_shops_id (int) Target Input: agg Partition key expr: dim_shops_id - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -239,11 +239,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0)) Reducer 3 Execution mode: llap @@ -251,10 +251,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: decimal(20,0)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -335,11 +335,11 @@ STAGE PLANS: TableScan alias: agg filterExpr: dim_shops_id is not null (type: boolean) - Statistics: Num rows: 9 Data size: 63 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 1071 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: amount (type: decimal(10,0)), dim_shops_id (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 1044 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -349,18 +349,18 @@ STAGE PLANS: outputColumnNames: _col0, _col3 input vertices: 1 Map 4 - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1809 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(_col0) keys: _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0)) Execution mode: llap LLAP IO: no inputs @@ -369,19 +369,19 @@ STAGE PLANS: TableScan alias: d1 filterExpr: ((label) IN ('foo', 'bar') and id is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((label) IN ('foo', 'bar') and id is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int), label (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -393,11 +393,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0)) Reducer 3 Execution mode: llap @@ -405,10 +405,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: decimal(20,0)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -493,14 +493,14 @@ STAGE PLANS: outputColumnNames: _col2 input vertices: 1 Map 2 - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 801 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 801 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 801 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -512,19 +512,19 @@ STAGE PLANS: TableScan alias: d1 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int), label (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -566,7 +566,7 @@ bar baz baz baz -Warning: Map Join MAPJOIN[13][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[13][bigTable=?] in task 'Map 2' is a cross product PREHOOK: query: EXPLAIN SELECT agg.amount FROM agg_01 agg, dim_shops d1 @@ -588,7 +588,7 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Map 2 (BROADCAST_EDGE) + Map 2 <- Map 1 (BROADCAST_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -596,28 +596,15 @@ STAGE PLANS: TableScan alias: agg filterExpr: (dim_shops_id = 1) (type: boolean) - Statistics: Num rows: 3 Data size: 33 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 345 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: amount (type: decimal(10,0)) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - input vertices: - 1 Map 2 - Statistics: Num rows: 3 Data size: 51 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 51 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(10,0)) Execution mode: llap LLAP IO: no inputs Map 2 @@ -625,15 +612,29 @@ STAGE PLANS: TableScan alias: d1 filterExpr: (1 = id) (type: boolean) - Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (1 = id) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0 + input vertices: + 0 Map 1 + Statistics: Num rows: 9 Data size: 1008 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 1008 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: llap LLAP IO: no inputs @@ -643,7 +644,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[13][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[13][bigTable=?] in task 'Map 2' is a cross product PREHOOK: query: SELECT agg.amount FROM agg_01 agg, dim_shops d1 @@ -665,8 +666,8 @@ POSTHOOK: Input: default@agg_01@dim_shops_id=1 POSTHOOK: Input: default@dim_shops #### A masked pattern was here #### 1 -2 3 +2 PREHOOK: query: EXPLAIN SELECT d1.label, count(*), sum(agg.amount) FROM agg_01 agg, dim_shops d1 @@ -704,11 +705,11 @@ STAGE PLANS: TableScan alias: agg filterExpr: dim_shops_id is not null (type: boolean) - Statistics: Num rows: 9 Data size: 63 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 1071 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: amount (type: decimal(10,0)), dim_shops_id (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 1044 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -718,18 +719,18 @@ STAGE PLANS: outputColumnNames: _col0, _col3 input vertices: 1 Map 4 - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1809 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(_col0) keys: _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0)) Execution mode: llap LLAP IO: no inputs @@ -738,34 +739,34 @@ STAGE PLANS: TableScan alias: d1 filterExpr: ((label) IN ('foo', 'bar') and id is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((label) IN ('foo', 'bar') and id is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int), label (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: dim_shops_id (int) Target Input: agg Partition key expr: dim_shops_id - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -777,11 +778,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0)) Reducer 3 Execution mode: llap @@ -789,10 +790,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: decimal(20,0)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 209 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -864,11 +865,11 @@ STAGE PLANS: TableScan alias: agg_01 filterExpr: dim_shops_id is not null (type: boolean) - Statistics: Num rows: 9 Data size: 63 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 1071 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: amount (type: decimal(10,0)), dim_shops_id (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 1044 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -878,10 +879,10 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1008 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18 Data size: 2016 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -893,33 +894,33 @@ STAGE PLANS: TableScan alias: dim_shops filterExpr: ((label = 'foo') and id is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((label = 'foo') and id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: dim_shops_id (int) Target Input: agg_01 Partition key expr: dim_shops_id - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs @@ -928,11 +929,11 @@ STAGE PLANS: TableScan alias: agg_01 filterExpr: dim_shops_id is not null (type: boolean) - Statistics: Num rows: 9 Data size: 63 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 1071 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: amount (type: decimal(10,0)), dim_shops_id (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 1044 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -942,10 +943,10 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 9 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1008 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18 Data size: 2016 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -957,33 +958,33 @@ STAGE PLANS: TableScan alias: dim_shops filterExpr: ((label = 'bar') and id is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((label = 'bar') and id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: dim_shops_id (int) Target Input: agg_01 Partition key expr: dim_shops_id - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 4 Execution mode: llap LLAP IO: no inputs diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out index 1dc9ed5a8c..39fa681ac4 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out @@ -130,19 +130,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: tinyint) sort order: + Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: llap LLAP IO: no inputs @@ -152,11 +152,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -205,20 +205,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) Execution mode: llap @@ -229,15 +229,15 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: tinyint) sort order: + Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Reducer 3 Execution mode: llap @@ -245,11 +245,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -297,19 +297,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: llap LLAP IO: no inputs @@ -319,11 +319,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 27454 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 27454 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -370,19 +370,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -392,11 +392,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 27454 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 27454 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -511,19 +511,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: tinyint) sort order: + Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: llap LLAP IO: no inputs @@ -533,11 +533,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -586,20 +586,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) Execution mode: llap @@ -610,15 +610,15 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: tinyint) sort order: + Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Reducer 3 Execution mode: llap @@ -626,11 +626,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -678,19 +678,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: llap LLAP IO: no inputs @@ -700,11 +700,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 27454 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 27454 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -751,19 +751,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -773,11 +773,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 27454 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 27454 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1294,18 +1294,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) Execution mode: llap LLAP IO: no inputs @@ -1315,10 +1315,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col1 (type: bigint), VALUE._col2 (type: float), VALUE._col3 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1366,19 +1366,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: tinyint), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col2 (type: bigint), _col3 (type: float) Execution mode: llap LLAP IO: no inputs @@ -1388,11 +1388,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), KEY._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1441,15 +1441,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int) sort order: + - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float) Execution mode: llap @@ -1460,22 +1460,22 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 is null or (_col0 = 27)) (type: boolean) - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: tinyint) sort order: + Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Reducer 3 Execution mode: llap @@ -1483,11 +1483,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1535,20 +1535,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) sort order: +++++ Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1558,14 +1558,14 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1613,20 +1613,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) sort order: +++++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1636,15 +1636,15 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2004,19 +2004,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: float) sort order: + Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col4 (type: tinyint) Execution mode: llap LLAP IO: no inputs @@ -2026,10 +2026,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY.reducesinkkey0 (type: float), VALUE._col3 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2076,19 +2076,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 5208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -2098,11 +2098,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 27454 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 227 Data size: 27454 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2451,19 +2451,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 859 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 859 Data size: 92434 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s = 'foo') (type: boolean) - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), b (type: bigint), f (type: float), 'foo' (type: string), t (type: tinyint), i (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: tinyint), _col5 (type: int) sort order: +++ Map-reduce partition columns: _col3 (type: string), _col4 (type: tinyint), _col5 (type: int) - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: bigint), _col2 (type: float) Execution mode: llap LLAP IO: no inputs @@ -2473,11 +2473,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: bigint), VALUE._col2 (type: float), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2526,19 +2526,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 859 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 859 Data size: 92434 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t = 27) (type: boolean) - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), b (type: bigint), f (type: float), s (type: string), 27 (type: tinyint), i (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: tinyint), _col5 (type: int) sort order: +++ Map-reduce partition columns: _col3 (type: string), _col4 (type: tinyint), _col5 (type: int) - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: bigint), _col2 (type: float) Execution mode: llap LLAP IO: no inputs @@ -2548,11 +2548,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: bigint), VALUE._col2 (type: float), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2601,19 +2601,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 859 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 859 Data size: 92434 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i = 100) (type: boolean) - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), b (type: bigint), f (type: float), s (type: string), t (type: tinyint), 100 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: tinyint), _col5 (type: int) sort order: +++ Map-reduce partition columns: _col3 (type: string), _col4 (type: tinyint), _col5 (type: int) - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: bigint), _col2 (type: float) Execution mode: llap LLAP IO: no inputs @@ -2623,11 +2623,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: bigint), VALUE._col2 (type: float), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 429 Data size: 53255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2676,19 +2676,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 859 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 859 Data size: 92434 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i = 100) and (t = 27)) (type: boolean) - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), b (type: bigint), f (type: float), s (type: string), 27 (type: tinyint), 100 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: tinyint), _col5 (type: int) sort order: +++ Map-reduce partition columns: _col3 (type: string), _col4 (type: tinyint), _col5 (type: int) - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: bigint), _col2 (type: float) Execution mode: llap LLAP IO: no inputs @@ -2698,11 +2698,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: bigint), VALUE._col2 (type: float), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2751,19 +2751,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 859 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 859 Data size: 92434 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i = 100) and (s = 'foo')) (type: boolean) - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), b (type: bigint), f (type: float), 'foo' (type: string), t (type: tinyint), 100 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: tinyint), _col5 (type: int) sort order: +++ Map-reduce partition columns: _col3 (type: string), _col4 (type: tinyint), _col5 (type: int) - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: bigint), _col2 (type: float) Execution mode: llap LLAP IO: no inputs @@ -2773,11 +2773,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: bigint), VALUE._col2 (type: float), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2826,19 +2826,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 859 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 859 Data size: 92434 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t = 27) and (s = 'foo')) (type: boolean) - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), b (type: bigint), f (type: float), 'foo' (type: string), 27 (type: tinyint), i (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: tinyint), _col5 (type: int) sort order: +++ Map-reduce partition columns: _col3 (type: string), _col4 (type: tinyint), _col5 (type: int) - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: bigint), _col2 (type: float) Execution mode: llap LLAP IO: no inputs @@ -2848,11 +2848,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: bigint), VALUE._col2 (type: float), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 214 Data size: 26565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2898,17 +2898,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1k - Statistics: Num rows: 859 Data size: 106636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 859 Data size: 92434 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i = 100) and (t = 27) and (s = 'foo')) (type: boolean) - Statistics: Num rows: 107 Data size: 13282 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), b (type: bigint), f (type: float), 'foo' (type: string), 27 (type: tinyint), 100 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 107 Data size: 13282 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 107 Data size: 13282 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 555 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out index 90756c6776..9765596499 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out @@ -90,20 +90,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ss - Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) sort order: +++ Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -113,15 +113,15 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -333,19 +333,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ss - Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) Execution mode: llap LLAP IO: no inputs @@ -355,11 +355,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -571,20 +571,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ss - Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) sort order: +++ Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -594,14 +594,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -813,18 +813,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ss - Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) Execution mode: llap LLAP IO: no inputs @@ -834,10 +834,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1104,20 +1104,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ss_orc - Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) sort order: +++ Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -1127,14 +1127,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1346,18 +1346,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ss_orc - Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs @@ -1367,10 +1367,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out index 788854aa04..2860ed005b 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out @@ -92,19 +92,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_part - Statistics: Num rows: 1600 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1600 Data size: 153369 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct) outputColumnNames: _col0 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -113,10 +113,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -185,19 +185,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_part - Statistics: Num rows: 1600 Data size: 312400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1600 Data size: 447769 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 147200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct), ds (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 800 Data size: 347200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 800 Data size: 347200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col3 (type: string) Execution mode: llap LLAP IO: may be used (ACID table) @@ -207,10 +207,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), 'foo' (type: string), 'bar' (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 800 Data size: 347200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 800 Data size: 347200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -372,19 +372,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_part_sdpo - Statistics: Num rows: 1600 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1600 Data size: 153369 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct) outputColumnNames: _col0 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -393,10 +393,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1720 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -465,19 +465,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_part_sdpo - Statistics: Num rows: 1600 Data size: 312400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1600 Data size: 447769 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 147200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct), ds (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 800 Data size: 347200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col3 (type: string), '_bucket_number' (type: string), _col0 (type: struct) sort order: +++ Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 800 Data size: 347200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -486,11 +486,11 @@ STAGE PLANS: Select Operator expressions: KEY._col0 (type: struct), 'foo' (type: string), 'bar' (type: string), KEY._col3 (type: string), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, '_bucket_number' - Statistics: Num rows: 800 Data size: 286400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1790 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 800 Data size: 286400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1790 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -661,19 +661,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part - Statistics: Num rows: 1600 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1600 Data size: 153369 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct) outputColumnNames: _col0 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -682,10 +682,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), 11 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -755,19 +755,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part - Statistics: Num rows: 3200 Data size: 48800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 3200 Data size: 319449 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 1600 Data size: 6400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct), hr (type: int) outputColumnNames: _col0, _col4 - Statistics: Num rows: 1600 Data size: 556800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 1600 Data size: 556800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col4 (type: int) Execution mode: llap LLAP IO: may be used (ACID table) @@ -777,10 +777,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), VALUE._col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1600 Data size: 556800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1600 Data size: 556800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -879,19 +879,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part - Statistics: Num rows: 3200 Data size: 637600 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 3200 Data size: 908249 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (value = 'bar') (type: boolean) - Statistics: Num rows: 1600 Data size: 300800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1385 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct), ds (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1600 Data size: 422400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 1600 Data size: 422400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), _col2 (type: int) Execution mode: llap LLAP IO: may be used (ACID table) @@ -901,10 +901,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: string), VALUE._col1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1600 Data size: 422400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1600 Data size: 422400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1073,19 +1073,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part_sdpo - Statistics: Num rows: 1600 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1600 Data size: 153369 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct) outputColumnNames: _col0 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -1094,10 +1094,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), 11 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1167,19 +1167,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part_sdpo - Statistics: Num rows: 3200 Data size: 48800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 3200 Data size: 319449 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 1600 Data size: 6400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct), hr (type: int) outputColumnNames: _col0, _col4 - Statistics: Num rows: 1600 Data size: 556800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: '2008-04-08' (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct) sort order: ++++ Map-reduce partition columns: '2008-04-08' (type: string), _col4 (type: int) - Statistics: Num rows: 1600 Data size: 556800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -1188,11 +1188,11 @@ STAGE PLANS: Select Operator expressions: KEY._col0 (type: struct), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 1600 Data size: 435200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1360 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 1600 Data size: 435200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1360 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1291,19 +1291,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part_sdpo - Statistics: Num rows: 3200 Data size: 637600 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 3200 Data size: 908249 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (value = 'bar') (type: boolean) - Statistics: Num rows: 1600 Data size: 300800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1385 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct), ds (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1600 Data size: 422400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: int), '_bucket_number' (type: string), _col0 (type: struct) sort order: ++++ Map-reduce partition columns: _col1 (type: string), _col2 (type: int) - Statistics: Num rows: 1600 Data size: 422400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -1312,11 +1312,11 @@ STAGE PLANS: Select Operator expressions: KEY._col0 (type: struct), KEY._col1 (type: string), KEY._col2 (type: int), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, '_bucket_number' - Statistics: Num rows: 1600 Data size: 579200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1810 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 1600 Data size: 579200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1810 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1485,19 +1485,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part_sdpo_no_cp - Statistics: Num rows: 1600 Data size: 318800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1600 Data size: 454169 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 150400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1385 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct), key (type: string), ds (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 800 Data size: 280800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2200 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct) sort order: ++++ Map-reduce partition columns: _col3 (type: string), _col4 (type: int) - Statistics: Num rows: 800 Data size: 280800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2200 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), 'bar' (type: string) Execution mode: llap LLAP IO: may be used (ACID table) @@ -1507,11 +1507,11 @@ STAGE PLANS: Select Operator expressions: KEY._col0 (type: struct), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 800 Data size: 359200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2690 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 800 Data size: 359200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2690 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1581,19 +1581,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part_sdpo_no_cp - Statistics: Num rows: 3200 Data size: 637600 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 3200 Data size: 908249 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 1600 Data size: 300800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1385 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct), key (type: string), ds (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 1600 Data size: 561600 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2200 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct) sort order: ++++ Map-reduce partition columns: _col3 (type: string), _col4 (type: int) - Statistics: Num rows: 1600 Data size: 561600 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2200 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), 'bar' (type: string) Execution mode: llap LLAP IO: may be used (ACID table) @@ -1603,11 +1603,11 @@ STAGE PLANS: Select Operator expressions: KEY._col0 (type: struct), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 1600 Data size: 718400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2690 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 1600 Data size: 718400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2690 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out index b36fe2a83f..03796198c5 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out @@ -137,10 +137,10 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_5] Group By Operator [GBY_4] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(_col0)","sum(_col1)"] - Select Operator [SEL_2] (rows=500 width=102) + Select Operator [SEL_2] (rows=500 width=182) Output:["_col0","_col1"] - TableScan [TS_0] (rows=500 width=102) - default@src_orc_merge_test_part,src_orc_merge_test_part,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_0] (rows=500 width=182) + default@src_orc_merge_test_part,src_orc_merge_test_part,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: alter table src_orc_merge_test_part partition (ds='2012-01-03', ts='2012-01-03+14:46:31') concatenate PREHOOK: type: ALTER_PARTITION_MERGE @@ -196,10 +196,10 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_5] Group By Operator [GBY_4] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(_col0)","sum(_col1)"] - Select Operator [SEL_2] (rows=500 width=102) + Select Operator [SEL_2] (rows=500 width=182) Output:["_col0","_col1"] - TableScan [TS_0] (rows=500 width=102) - default@src_orc_merge_test_part,src_orc_merge_test_part,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_0] (rows=500 width=182) + default@src_orc_merge_test_part,src_orc_merge_test_part,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: drop table src_orc_merge_test_part PREHOOK: type: DROPTABLE @@ -2883,17 +2883,17 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Group By Operator [GBY_4] (rows=2 width=19) + Group By Operator [GBY_4] (rows=1 width=28) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT KEY._col1:0._col0)","count(DISTINCT KEY._col1:1._col0)","sum(VALUE._col2)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:_col0 - Group By Operator [GBY_2] (rows=4 width=19) + Group By Operator [GBY_2] (rows=1 width=36) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(DISTINCT b)","count(DISTINCT c)","sum(d)"],keys:a, b, c - Select Operator [SEL_1] (rows=4 width=19) + Select Operator [SEL_1] (rows=4 width=16) Output:["a","b","c","d"] - TableScan [TS_0] (rows=4 width=19) - default@abcd,abcd,Tbl:COMPLETE,Col:NONE,Output:["a","b","c","d"] + TableScan [TS_0] (rows=4 width=16) + default@abcd,abcd,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b","c","d"] PREHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a PREHOOK: type: QUERY @@ -2910,15 +2910,15 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_5] - Group By Operator [GBY_3] (rows=2 width=19) + Group By Operator [GBY_3] (rows=1 width=28) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT KEY._col1:0._col0)","count(DISTINCT KEY._col1:1._col0)","sum(VALUE._col0)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:a - Select Operator [SEL_1] (rows=4 width=19) + Select Operator [SEL_1] (rows=4 width=16) Output:["a","b","c","d"] - TableScan [TS_0] (rows=4 width=19) - default@abcd,abcd,Tbl:COMPLETE,Col:NONE,Output:["a","b","c","d"] + TableScan [TS_0] (rows=4 width=16) + default@abcd,abcd,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b","c","d"] PREHOOK: query: explain create table src_rc_merge_test(key int, value string) stored as rcfile PREHOOK: type: CREATETABLE @@ -3029,10 +3029,10 @@ Stage-0 Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_3] - Select Operator [SEL_1] (rows=5 width=6) + Select Operator [SEL_1] (rows=5 width=93) Output:["_col0","_col1"] - TableScan [TS_0] (rows=5 width=6) - default@tgt_rc_merge_test,tgt_rc_merge_test,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_0] (rows=5 width=93) + default@tgt_rc_merge_test,tgt_rc_merge_test,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: alter table tgt_rc_merge_test concatenate PREHOOK: type: ALTER_TABLE_MERGE @@ -3101,10 +3101,10 @@ Stage-0 Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_3] - Select Operator [SEL_1] (rows=5 width=6) + Select Operator [SEL_1] (rows=5 width=93) Output:["_col0","_col1"] - TableScan [TS_0] (rows=5 width=6) - default@tgt_rc_merge_test,tgt_rc_merge_test,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_0] (rows=5 width=93) + default@tgt_rc_merge_test,tgt_rc_merge_test,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: drop table src_rc_merge_test PREHOOK: type: DROPTABLE @@ -3380,20 +3380,20 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=3 width=9) + Select Operator [SEL_5] (rows=9 width=16) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=3 width=9) + Merge Join Operator [MERGEJOIN_7] (rows=9 width=16) Conds:RS_2.key=RS_3.value(Inner),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key TableScan [TS_0] (rows=3 width=8) - default@myinput1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:value TableScan [TS_1] (rows=3 width=8) - default@myinput1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value join myinput1 c on a.key=c.key PREHOOK: type: QUERY @@ -3410,9 +3410,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_11] - Select Operator [SEL_10] (rows=6 width=9) + Select Operator [SEL_10] (rows=27 width=24) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_21] (rows=6 width=9) + Merge Join Operator [MERGEJOIN_21] (rows=27 width=24) Conds:RS_4.key=RS_6.value(Inner),RS_4.key=RS_8.key(Inner),Output:["_col0","_col1","_col5","_col6","_col10","_col11"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_4] @@ -3420,21 +3420,21 @@ Stage-0 Filter Operator [FIL_18] (rows=3 width=8) predicate:key is not null TableScan [TS_0] (rows=3 width=8) - default@myinput1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_6] PartitionCols:value Filter Operator [FIL_19] (rows=3 width=8) predicate:value is not null TableScan [TS_1] (rows=3 width=8) - default@myinput1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 4 [SIMPLE_EDGE] llap SHUFFLE [RS_8] PartitionCols:key Filter Operator [FIL_20] (rows=3 width=8) predicate:key is not null TableScan [TS_2] (rows=3 width=8) - default@myinput1,c,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,c,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value join myinput1 c on a.key<=>c.key PREHOOK: type: QUERY @@ -3451,25 +3451,25 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_8] - Select Operator [SEL_7] (rows=6 width=9) + Select Operator [SEL_7] (rows=27 width=24) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_9] (rows=6 width=9) + Merge Join Operator [MERGEJOIN_9] (rows=27 width=24) Conds:RS_3.key=RS_4.value(Inner),RS_3.key=RS_5.key(Inner),Output:["_col0","_col1","_col5","_col6","_col10","_col11"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:key TableScan [TS_0] (rows=3 width=8) - default@myinput1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_4] PartitionCols:value TableScan [TS_1] (rows=3 width=8) - default@myinput1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 4 [SIMPLE_EDGE] llap SHUFFLE [RS_5] PartitionCols:key TableScan [TS_2] (rows=3 width=8) - default@myinput1,c,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,c,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value AND a.value=b.key join myinput1 c on a.key<=>c.key AND a.value=c.value PREHOOK: type: QUERY @@ -3486,9 +3486,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_11] - Select Operator [SEL_10] (rows=6 width=9) + Select Operator [SEL_10] (rows=27 width=24) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_15] (rows=6 width=9) + Merge Join Operator [MERGEJOIN_15] (rows=27 width=24) Conds:RS_4.key, value=RS_6.value, key(Inner),RS_4.key, value=RS_8.key, value(Inner),Output:["_col0","_col1","_col5","_col6","_col10","_col11"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_4] @@ -3496,21 +3496,21 @@ Stage-0 Filter Operator [FIL_12] (rows=3 width=8) predicate:value is not null TableScan [TS_0] (rows=3 width=8) - default@myinput1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_6] PartitionCols:value, key Filter Operator [FIL_13] (rows=3 width=8) predicate:key is not null TableScan [TS_1] (rows=3 width=8) - default@myinput1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 4 [SIMPLE_EDGE] llap SHUFFLE [RS_8] PartitionCols:key, value Filter Operator [FIL_14] (rows=3 width=8) predicate:value is not null TableScan [TS_2] (rows=3 width=8) - default@myinput1,c,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,c,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value AND a.value<=>b.key join myinput1 c on a.key<=>c.key AND a.value<=>c.value PREHOOK: type: QUERY @@ -3527,25 +3527,25 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_8] - Select Operator [SEL_7] (rows=6 width=9) + Select Operator [SEL_7] (rows=27 width=24) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_9] (rows=6 width=9) + Merge Join Operator [MERGEJOIN_9] (rows=27 width=24) Conds:RS_3.key, value=RS_4.value, key(Inner),RS_3.key, value=RS_5.key, value(Inner),Output:["_col0","_col1","_col5","_col6","_col10","_col11"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:key, value TableScan [TS_0] (rows=3 width=8) - default@myinput1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_4] PartitionCols:value, key TableScan [TS_1] (rows=3 width=8) - default@myinput1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 4 [SIMPLE_EDGE] llap SHUFFLE [RS_5] PartitionCols:key, value TableScan [TS_2] (rows=3 width=8) - default@myinput1,c,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,c,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: explain select * FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.key<=>b.value PREHOOK: type: QUERY @@ -3562,20 +3562,20 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=3 width=9) + Select Operator [SEL_5] (rows=9 width=16) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=3 width=9) + Merge Join Operator [MERGEJOIN_7] (rows=9 width=16) Conds:RS_2.key=RS_3.value(Left Outer),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key TableScan [TS_0] (rows=3 width=8) - default@myinput1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:value TableScan [TS_1] (rows=3 width=8) - default@myinput1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: explain select * FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.key<=>b.value PREHOOK: type: QUERY @@ -3592,20 +3592,20 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=3 width=9) + Select Operator [SEL_5] (rows=9 width=16) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=3 width=9) + Merge Join Operator [MERGEJOIN_7] (rows=9 width=16) Conds:RS_2.key=RS_3.value(Right Outer),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key TableScan [TS_0] (rows=3 width=8) - default@myinput1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:value TableScan [TS_1] (rows=3 width=8) - default@myinput1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: explain select * FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.key<=>b.value PREHOOK: type: QUERY @@ -3622,20 +3622,20 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=3 width=9) + Select Operator [SEL_5] (rows=9 width=16) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=3 width=9) + Merge Join Operator [MERGEJOIN_7] (rows=9 width=16) Conds:RS_2.key=RS_3.value(Outer),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key TableScan [TS_0] (rows=3 width=8) - default@myinput1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:value TableScan [TS_1] (rows=3 width=8) - default@myinput1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM myinput1 a JOIN myinput1 b ON a.key<=>b.value PREHOOK: type: QUERY @@ -3652,20 +3652,20 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=3 width=9) + Select Operator [SEL_5] (rows=9 width=16) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=3 width=9) + Merge Join Operator [MERGEJOIN_7] (rows=9 width=16) Conds:RS_2.key=RS_3.value(Inner),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key TableScan [TS_0] (rows=3 width=8) - default@myinput1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:value TableScan [TS_1] (rows=3 width=8) - default@myinput1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + default@myinput1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: CREATE TABLE smb_input(key int, value int) PREHOOK: type: CREATETABLE @@ -3748,20 +3748,20 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=28 width=7) + Select Operator [SEL_5] (rows=135 width=16) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=28 width=7) + Merge Join Operator [MERGEJOIN_7] (rows=135 width=16) Conds:RS_2.key=RS_3.key(Inner),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key - TableScan [TS_0] (rows=26 width=7) - default@smb_input1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_0] (rows=26 width=8) + default@smb_input1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:key - TableScan [TS_1] (rows=26 width=7) - default@smb_input1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_1] (rows=26 width=8) + default@smb_input1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key AND a.value <=> b.value PREHOOK: type: QUERY @@ -3778,20 +3778,20 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=28 width=7) + Select Operator [SEL_5] (rows=27 width=16) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=28 width=7) + Merge Join Operator [MERGEJOIN_7] (rows=27 width=16) Conds:RS_2.key, value=RS_3.key, value(Inner),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key, value - TableScan [TS_0] (rows=26 width=7) - default@smb_input1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_0] (rows=26 width=8) + default@smb_input1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:key, value - TableScan [TS_1] (rows=26 width=7) - default@smb_input1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_1] (rows=26 width=8) + default@smb_input1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a RIGHT OUTER JOIN smb_input1 b ON a.key <=> b.key PREHOOK: type: QUERY @@ -3808,20 +3808,20 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=28 width=7) + Select Operator [SEL_5] (rows=135 width=16) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=28 width=7) + Merge Join Operator [MERGEJOIN_7] (rows=135 width=16) Conds:RS_2.key=RS_3.key(Right Outer),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key - TableScan [TS_0] (rows=26 width=7) - default@smb_input1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_0] (rows=26 width=8) + default@smb_input1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:key - TableScan [TS_1] (rows=26 width=7) - default@smb_input1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_1] (rows=26 width=8) + default@smb_input1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key PREHOOK: type: QUERY @@ -3838,20 +3838,20 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=28 width=7) + Select Operator [SEL_5] (rows=135 width=16) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=28 width=7) + Merge Join Operator [MERGEJOIN_7] (rows=135 width=16) Conds:RS_2.key=RS_3.key(Inner),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key - TableScan [TS_0] (rows=26 width=7) - default@smb_input1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_0] (rows=26 width=8) + default@smb_input1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:key - TableScan [TS_1] (rows=26 width=7) - default@smb_input1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_1] (rows=26 width=8) + default@smb_input1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a LEFT OUTER JOIN smb_input1 b ON a.key <=> b.key PREHOOK: type: QUERY @@ -3868,20 +3868,20 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=28 width=7) + Select Operator [SEL_5] (rows=135 width=16) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=28 width=7) + Merge Join Operator [MERGEJOIN_7] (rows=135 width=16) Conds:RS_2.key=RS_3.key(Left Outer),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key - TableScan [TS_0] (rows=26 width=7) - default@smb_input1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_0] (rows=26 width=8) + default@smb_input1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:key - TableScan [TS_1] (rows=26 width=7) - default@smb_input1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_1] (rows=26 width=8) + default@smb_input1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: drop table sales PREHOOK: type: DROPTABLE @@ -3952,28 +3952,28 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=2 width=15) + Merge Join Operator [MERGEJOIN_17] (rows=1 width=93) Conds:RS_8._col1=RS_9._col0(Left Semi),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] PartitionCols:_col1 - Select Operator [SEL_2] (rows=1 width=13) + Select Operator [SEL_2] (rows=1 width=93) Output:["_col0","_col1"] - Filter Operator [FIL_15] (rows=1 width=13) + Filter Operator [FIL_15] (rows=1 width=93) predicate:id is not null - TableScan [TS_0] (rows=1 width=13) - default@sales,sales,Tbl:COMPLETE,Col:NONE,Output:["name","id"] + TableScan [TS_0] (rows=1 width=93) + default@sales,sales,Tbl:COMPLETE,Col:COMPLETE,Output:["name","id"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_9] PartitionCols:_col0 - Group By Operator [GBY_7] (rows=2 width=14) + Group By Operator [GBY_7] (rows=1 width=4) Output:["_col0"],keys:_col0 - Select Operator [SEL_5] (rows=2 width=14) + Select Operator [SEL_5] (rows=2 width=4) Output:["_col0"] - Filter Operator [FIL_16] (rows=2 width=14) + Filter Operator [FIL_16] (rows=2 width=4) predicate:id is not null - TableScan [TS_3] (rows=2 width=14) - default@things,things,Tbl:COMPLETE,Col:NONE,Output:["id"] + TableScan [TS_3] (rows=2 width=10) + default@things,things,Tbl:COMPLETE,Col:COMPLETE,Output:["id"] PREHOOK: query: drop table sales PREHOOK: type: DROPTABLE @@ -5307,49 +5307,51 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) +Map 3 <- Map 1 (BROADCAST_EDGE), Map 2 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Map 1 llap - File Output Operator [FS_18] - Map Join Operator [MAPJOIN_35] (rows=3 width=33) - Conds:SEL_2._col0=RS_13._col0(Inner),RS_13._col0=RS_14._col0(Inner),RS_14._col0=RS_15._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 2 [BROADCAST_EDGE] llap - BROADCAST [RS_13] + Map 3 llap + File Output Operator [FS_21] + Map Join Operator [MAPJOIN_37] (rows=1 width=712) + Conds:RS_16._col0=RS_17._col0(Inner),RS_17._col0=MAPJOIN_36._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 1 [BROADCAST_EDGE] llap + BROADCAST [RS_16] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1 width=30) + Select Operator [SEL_2] (rows=1 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_32] (rows=1 width=30) + Filter Operator [FIL_32] (rows=1 width=178) predicate:key is not null - TableScan [TS_3] (rows=1 width=30) - default@t2,b,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Map 3 [BROADCAST_EDGE] llap - BROADCAST [RS_14] + TableScan [TS_0] (rows=1 width=178) + default@t1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] + <-Map 2 [BROADCAST_EDGE] llap + BROADCAST [RS_17] PartitionCols:_col0 - Select Operator [SEL_8] (rows=1 width=20) + Select Operator [SEL_5] (rows=1 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_33] (rows=1 width=20) + Filter Operator [FIL_33] (rows=1 width=178) predicate:key is not null - TableScan [TS_6] (rows=1 width=20) - default@t3,c,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Map 4 [BROADCAST_EDGE] llap - BROADCAST [RS_15] - PartitionCols:_col0 - Select Operator [SEL_11] (rows=1 width=30) + TableScan [TS_3] (rows=1 width=178) + default@t2,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] + <-Map Join Operator [MAPJOIN_36] (rows=1 width=356) + Conds:SEL_8._col0=RS_13._col0(Inner),Output:["_col0","_col1","_col2","_col3"] + <-Map 4 [BROADCAST_EDGE] llap + BROADCAST [RS_13] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=1 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_35] (rows=1 width=178) + predicate:key is not null + TableScan [TS_9] (rows=1 width=178) + default@t4,d,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] + <-Select Operator [SEL_8] (rows=1 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_34] (rows=1 width=30) + Filter Operator [FIL_34] (rows=1 width=178) predicate:key is not null - TableScan [TS_9] (rows=1 width=30) - default@t4,d,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Select Operator [SEL_2] (rows=1 width=30) - Output:["_col0","_col1"] - Filter Operator [FIL_31] (rows=1 width=30) - predicate:key is not null - TableScan [TS_0] (rows=1 width=30) - default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + TableScan [TS_6] (rows=1 width=178) + default@t3,c,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] PREHOOK: query: explain select /*+ STREAMTABLE(a,c) */ * @@ -5366,49 +5368,51 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) +Map 3 <- Map 1 (BROADCAST_EDGE), Map 2 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Map 1 llap - File Output Operator [FS_18] - Map Join Operator [MAPJOIN_35] (rows=3 width=33) - Conds:SEL_2._col0=RS_13._col0(Inner),RS_13._col0=RS_14._col0(Inner),RS_14._col0=RS_15._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 2 [BROADCAST_EDGE] llap - BROADCAST [RS_13] + Map 3 llap + File Output Operator [FS_21] + Map Join Operator [MAPJOIN_37] (rows=1 width=712) + Conds:RS_16._col0=RS_17._col0(Inner),RS_17._col0=MAPJOIN_36._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 1 [BROADCAST_EDGE] llap + BROADCAST [RS_16] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1 width=30) + Select Operator [SEL_2] (rows=1 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_32] (rows=1 width=30) + Filter Operator [FIL_32] (rows=1 width=178) predicate:key is not null - TableScan [TS_3] (rows=1 width=30) - default@t2,b,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Map 3 [BROADCAST_EDGE] llap - BROADCAST [RS_14] + TableScan [TS_0] (rows=1 width=178) + default@t1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] + <-Map 2 [BROADCAST_EDGE] llap + BROADCAST [RS_17] PartitionCols:_col0 - Select Operator [SEL_8] (rows=1 width=20) + Select Operator [SEL_5] (rows=1 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_33] (rows=1 width=20) + Filter Operator [FIL_33] (rows=1 width=178) predicate:key is not null - TableScan [TS_6] (rows=1 width=20) - default@t3,c,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Map 4 [BROADCAST_EDGE] llap - BROADCAST [RS_15] - PartitionCols:_col0 - Select Operator [SEL_11] (rows=1 width=30) + TableScan [TS_3] (rows=1 width=178) + default@t2,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] + <-Map Join Operator [MAPJOIN_36] (rows=1 width=356) + Conds:SEL_8._col0=RS_13._col0(Inner),Output:["_col0","_col1","_col2","_col3"] + <-Map 4 [BROADCAST_EDGE] llap + BROADCAST [RS_13] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=1 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_35] (rows=1 width=178) + predicate:key is not null + TableScan [TS_9] (rows=1 width=178) + default@t4,d,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] + <-Select Operator [SEL_8] (rows=1 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_34] (rows=1 width=30) + Filter Operator [FIL_34] (rows=1 width=178) predicate:key is not null - TableScan [TS_9] (rows=1 width=30) - default@t4,d,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Select Operator [SEL_2] (rows=1 width=30) - Output:["_col0","_col1"] - Filter Operator [FIL_31] (rows=1 width=30) - predicate:key is not null - TableScan [TS_0] (rows=1 width=30) - default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + TableScan [TS_6] (rows=1 width=178) + default@t3,c,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] PREHOOK: query: explain FROM T1 a JOIN src c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) PREHOOK: type: QUERY @@ -5436,19 +5440,19 @@ Stage-0 <-Map 2 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_11] PartitionCols:rand() - Select Operator [SEL_9] (rows=550 width=87) + Select Operator [SEL_9] (rows=1 width=265) Output:["_col0","_col1","_col2"] - Map Join Operator [MAPJOIN_21] (rows=550 width=87) + Map Join Operator [MAPJOIN_21] (rows=1 width=265) Conds:RS_6.UDFToDouble(_col0)=SEL_5.(UDFToDouble(_col0) + 1.0)(Inner),Output:["_col0","_col1","_col2"] <-Map 1 [BROADCAST_EDGE] llap BROADCAST [RS_6] PartitionCols:UDFToDouble(_col0) - Select Operator [SEL_2] (rows=1 width=30) + Select Operator [SEL_2] (rows=1 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_19] (rows=1 width=30) + Filter Operator [FIL_19] (rows=1 width=178) predicate:key is not null - TableScan [TS_0] (rows=1 width=30) - default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + TableScan [TS_0] (rows=1 width=178) + default@t1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] <-Select Operator [SEL_5] (rows=500 width=87) Output:["_col0"] Filter Operator [FIL_20] (rows=500 width=87) @@ -5539,25 +5543,25 @@ Stage-0 <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_11] PartitionCols:rand() - Select Operator [SEL_9] (rows=1 width=33) + Select Operator [SEL_9] (rows=1 width=178) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_21] (rows=1 width=33) + Map Join Operator [MAPJOIN_21] (rows=1 width=178) Conds:SEL_2._col0=RS_7._col0(Inner),Output:["_col0","_col1"] <-Map 4 [BROADCAST_EDGE] llap BROADCAST [RS_7] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1 width=30) + Select Operator [SEL_5] (rows=1 width=89) Output:["_col0"] - Filter Operator [FIL_20] (rows=1 width=30) + Filter Operator [FIL_20] (rows=1 width=89) predicate:val is not null - TableScan [TS_3] (rows=1 width=30) - default@t1,v,Tbl:COMPLETE,Col:NONE,Output:["val"] - <-Select Operator [SEL_2] (rows=1 width=30) + TableScan [TS_3] (rows=1 width=89) + default@t1,v,Tbl:COMPLETE,Col:COMPLETE,Output:["val"] + <-Select Operator [SEL_2] (rows=1 width=89) Output:["_col0"] - Filter Operator [FIL_19] (rows=1 width=30) + Filter Operator [FIL_19] (rows=1 width=89) predicate:key is not null - TableScan [TS_0] (rows=1 width=30) - default@t1,k,Tbl:COMPLETE,Col:NONE,Output:["key"] + TableScan [TS_0] (rows=1 width=89) + default@t1,k,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] PREHOOK: query: explain select sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key PREHOOK: type: QUERY @@ -5566,44 +5570,44 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Map 4 (BROADCAST_EDGE) -Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Map 2 <- Map 1 (BROADCAST_EDGE) +Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 3 llap + Reducer 4 llap File Output Operator [FS_16] Group By Operator [GBY_14] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] llap + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_13] Group By Operator [GBY_12] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] llap + <-Map 2 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_11] PartitionCols:rand() - Select Operator [SEL_9] (rows=1 width=33) + Select Operator [SEL_9] (rows=1 width=178) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_21] (rows=1 width=33) - Conds:SEL_2._col0=RS_7._col0(Inner),Output:["_col0","_col2"] - <-Map 4 [BROADCAST_EDGE] llap - BROADCAST [RS_7] + Map Join Operator [MAPJOIN_21] (rows=1 width=178) + Conds:RS_6._col0=SEL_5._col0(Inner),Output:["_col0","_col2"] + <-Map 1 [BROADCAST_EDGE] llap + BROADCAST [RS_6] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1 width=30) - Output:["_col0","_col1"] - Filter Operator [FIL_20] (rows=1 width=30) + Select Operator [SEL_2] (rows=1 width=89) + Output:["_col0"] + Filter Operator [FIL_19] (rows=1 width=89) predicate:key is not null - TableScan [TS_3] (rows=1 width=30) - default@t1,v,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Select Operator [SEL_2] (rows=1 width=30) - Output:["_col0"] - Filter Operator [FIL_19] (rows=1 width=30) + TableScan [TS_0] (rows=1 width=89) + default@t1,k,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] + <-Select Operator [SEL_5] (rows=1 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_20] (rows=1 width=178) predicate:key is not null - TableScan [TS_0] (rows=1 width=30) - default@t1,k,Tbl:COMPLETE,Col:NONE,Output:["key"] + TableScan [TS_3] (rows=1 width=178) + default@t1,v,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] PREHOOK: query: explain select count(1) from T1 a join T1 b on a.key = b.key PREHOOK: type: QUERY @@ -5631,23 +5635,23 @@ Stage-0 <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_10] PartitionCols:rand() - Map Join Operator [MAPJOIN_20] (rows=1 width=33) + Map Join Operator [MAPJOIN_20] (rows=1 width=8) Conds:SEL_2._col0=RS_7._col0(Inner) <-Map 4 [BROADCAST_EDGE] llap BROADCAST [RS_7] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1 width=30) + Select Operator [SEL_5] (rows=1 width=89) Output:["_col0"] - Filter Operator [FIL_19] (rows=1 width=30) + Filter Operator [FIL_19] (rows=1 width=89) predicate:key is not null - TableScan [TS_3] (rows=1 width=30) - default@t1,b,Tbl:COMPLETE,Col:NONE,Output:["key"] - <-Select Operator [SEL_2] (rows=1 width=30) + TableScan [TS_3] (rows=1 width=89) + default@t1,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] + <-Select Operator [SEL_2] (rows=1 width=89) Output:["_col0"] - Filter Operator [FIL_18] (rows=1 width=30) + Filter Operator [FIL_18] (rows=1 width=89) predicate:key is not null - TableScan [TS_0] (rows=1 width=30) - default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key"] + TableScan [TS_0] (rows=1 width=89) + default@t1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] PREHOOK: query: explain FROM T1 a LEFT OUTER JOIN T2 c ON c.key+1=a.key select sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) PREHOOK: type: QUERY @@ -5675,21 +5679,21 @@ Stage-0 <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_9] PartitionCols:rand() - Select Operator [SEL_7] (rows=1 width=33) + Select Operator [SEL_7] (rows=1 width=267) Output:["_col0","_col1","_col2"] - Map Join Operator [MAPJOIN_17] (rows=1 width=33) + Map Join Operator [MAPJOIN_17] (rows=1 width=267) Conds:SEL_1.UDFToDouble(_col0)=RS_5.(UDFToDouble(_col0) + 1.0)(Left Outer),Output:["_col0","_col1","_col2"] <-Map 4 [BROADCAST_EDGE] llap BROADCAST [RS_5] PartitionCols:(UDFToDouble(_col0) + 1.0) - Select Operator [SEL_3] (rows=1 width=30) + Select Operator [SEL_3] (rows=1 width=89) Output:["_col0"] - TableScan [TS_2] (rows=1 width=30) - default@t2,c,Tbl:COMPLETE,Col:NONE,Output:["key"] - <-Select Operator [SEL_1] (rows=1 width=30) + TableScan [TS_2] (rows=1 width=89) + default@t2,c,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] + <-Select Operator [SEL_1] (rows=1 width=178) Output:["_col0","_col1"] - TableScan [TS_0] (rows=1 width=30) - default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + TableScan [TS_0] (rows=1 width=178) + default@t1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] PREHOOK: query: explain FROM T1 a RIGHT OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) PREHOOK: type: QUERY @@ -5717,21 +5721,21 @@ Stage-0 <-Map 2 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_9] PartitionCols:rand() - Select Operator [SEL_7] (rows=1 width=33) + Select Operator [SEL_7] (rows=1 width=267) Output:["_col0","_col1","_col2"] - Map Join Operator [MAPJOIN_17] (rows=1 width=33) + Map Join Operator [MAPJOIN_17] (rows=1 width=267) Conds:RS_4.UDFToDouble(_col0)=SEL_3.(UDFToDouble(_col0) + 1.0)(Right Outer),Output:["_col0","_col1","_col2"] <-Map 1 [BROADCAST_EDGE] llap BROADCAST [RS_4] PartitionCols:UDFToDouble(_col0) - Select Operator [SEL_1] (rows=1 width=30) + Select Operator [SEL_1] (rows=1 width=178) Output:["_col0","_col1"] - TableScan [TS_0] (rows=1 width=30) - default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Select Operator [SEL_3] (rows=1 width=30) + TableScan [TS_0] (rows=1 width=178) + default@t1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] + <-Select Operator [SEL_3] (rows=1 width=89) Output:["_col0"] - TableScan [TS_2] (rows=1 width=30) - default@t2,c,Tbl:COMPLETE,Col:NONE,Output:["key"] + TableScan [TS_2] (rows=1 width=89) + default@t2,c,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] PREHOOK: query: explain FROM T1 a FULL OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) PREHOOK: type: QUERY @@ -5759,24 +5763,24 @@ Stage-0 <-Reducer 2 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_9] PartitionCols:rand() - Select Operator [SEL_7] (rows=1 width=33) + Select Operator [SEL_7] (rows=2 width=267) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_15] (rows=1 width=33) + Merge Join Operator [MERGEJOIN_15] (rows=2 width=267) Conds:RS_4.UDFToDouble(_col0)=RS_5.(UDFToDouble(_col0) + 1.0)(Outer),Output:["_col0","_col1","_col2"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_4] PartitionCols:UDFToDouble(_col0) - Select Operator [SEL_1] (rows=1 width=30) + Select Operator [SEL_1] (rows=1 width=178) Output:["_col0","_col1"] - TableScan [TS_0] (rows=1 width=30) - default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + TableScan [TS_0] (rows=1 width=178) + default@t1,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] <-Map 5 [SIMPLE_EDGE] llap SHUFFLE [RS_5] PartitionCols:(UDFToDouble(_col0) + 1.0) - Select Operator [SEL_3] (rows=1 width=30) + Select Operator [SEL_3] (rows=1 width=89) Output:["_col0"] - TableScan [TS_2] (rows=1 width=30) - default@t2,c,Tbl:COMPLETE,Col:NONE,Output:["key"] + TableScan [TS_2] (rows=1 width=89) + default@t2,c,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] PREHOOK: query: explain select /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k left outer join T1 v on k.key+1=v.key PREHOOK: type: QUERY @@ -5804,19 +5808,19 @@ Stage-0 <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_9] PartitionCols:rand() - Select Operator [SEL_7] (rows=1 width=33) + Select Operator [SEL_7] (rows=1 width=178) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_17] (rows=1 width=33) + Map Join Operator [MAPJOIN_17] (rows=1 width=178) Conds:SEL_1.(UDFToDouble(_col0) + 1.0)=RS_5.UDFToDouble(_col0)(Left Outer),Output:["_col0","_col2"] <-Map 4 [BROADCAST_EDGE] llap BROADCAST [RS_5] PartitionCols:UDFToDouble(_col0) - Select Operator [SEL_3] (rows=1 width=30) + Select Operator [SEL_3] (rows=1 width=178) Output:["_col0","_col1"] - TableScan [TS_2] (rows=1 width=30) - default@t1,v,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Select Operator [SEL_1] (rows=1 width=30) + TableScan [TS_2] (rows=1 width=178) + default@t1,v,Tbl:COMPLETE,Col:COMPLETE,Output:["key","val"] + <-Select Operator [SEL_1] (rows=1 width=89) Output:["_col0"] - TableScan [TS_0] (rows=1 width=30) - default@t1,k,Tbl:COMPLETE,Col:NONE,Output:["key"] + TableScan [TS_0] (rows=1 width=89) + default@t1,k,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] diff --git a/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out b/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out index c5cdb77afc..1c3bf80f73 100644 --- a/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out +++ b/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out @@ -44,23 +44,23 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: f - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE + alias: g + Statistics: Num rows: 25 Data size: 2436 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE + predicate: (value <> '') (type: boolean) + Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: key (type: int) + expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col0 (type: string) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: true Execution mode: llap @@ -116,29 +116,29 @@ STAGE PLANS: name: default.filter_join_breaktask name: default.filter_join_breaktask Truncated Path -> Alias: - /filter_join_breaktask/ds=2008-04-08 [f] + /filter_join_breaktask/ds=2008-04-08 [g] Map 4 Map Operator Tree: TableScan alias: m - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2536 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((value <> '') and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4488 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 24 Data size: 4488 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) auto parallelism: true Execution mode: llap LLAP IO: no inputs @@ -197,23 +197,23 @@ STAGE PLANS: Map 5 Map Operator Tree: TableScan - alias: g - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE + alias: f + Statistics: Num rows: 25 Data size: 311 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false - predicate: (value <> '') (type: boolean) - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE + predicate: key is not null (type: boolean) + Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: value (type: string) + expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 2352 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col0 (type: int) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 24 Data size: 2352 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 auto parallelism: true Execution mode: llap @@ -269,7 +269,7 @@ STAGE PLANS: name: default.filter_join_breaktask name: default.filter_join_breaktask Truncated Path -> Alias: - /filter_join_breaktask/ds=2008-04-08 [g] + /filter_join_breaktask/ds=2008-04-08 [f] Reducer 2 Execution mode: llap Needs Tagging: false @@ -278,19 +278,19 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col3 + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 Position of Big Table: 0 - Statistics: Num rows: 27 Data size: 452 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 11160 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: _col2 (type: int) null sort order: a sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 27 Data size: 452 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 120 Data size: 11160 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 - value expressions: _col0 (type: int) + value expressions: _col0 (type: string) auto parallelism: true Reducer 3 Execution mode: llap @@ -300,21 +300,21 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 _col0 (type: string) + 0 _col2 (type: int) + 1 _col0 (type: int) outputColumnNames: _col0, _col5 Position of Big Table: 0 - Statistics: Num rows: 29 Data size: 497 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 576 Data size: 53568 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col5 (type: string) + expressions: _col5 (type: int), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 497 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 576 Data size: 53568 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 29 Data size: 497 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 576 Data size: 53568 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/llap/join_reordering_no_stats.q.out b/ql/src/test/results/clientpositive/llap/join_reordering_no_stats.q.out new file mode 100644 index 0000000000..c41ef9a733 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/join_reordering_no_stats.q.out @@ -0,0 +1,442 @@ +PREHOOK: query: create table supplier (S_SUPPKEY INT, S_NAME STRING, S_ADDRESS STRING, S_NATIONKEY INT, +S_PHONE STRING, S_ACCTBAL DOUBLE, S_COMMENT STRING) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@supplier +POSTHOOK: query: create table supplier (S_SUPPKEY INT, S_NAME STRING, S_ADDRESS STRING, S_NATIONKEY INT, +S_PHONE STRING, S_ACCTBAL DOUBLE, S_COMMENT STRING) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@supplier +PREHOOK: query: CREATE TABLE lineitem_nostats (L_ORDERKEY INT, + L_PARTKEY INT, + L_SUPPKEY INT, + L_LINENUMBER INT, + L_QUANTITY DOUBLE, + L_EXTENDEDPRICE DOUBLE, + L_DISCOUNT DOUBLE, + L_TAX DOUBLE, + L_RETURNFLAG STRING, + L_LINESTATUS STRING, + l_shipdate STRING, + L_COMMITDATE STRING, + L_RECEIPTDATE STRING, + L_SHIPINSTRUCT STRING, + L_SHIPMODE STRING, + L_COMMENT STRING) +ROW FORMAT DELIMITED +FIELDS TERMINATED BY '|' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@lineitem_nostats +POSTHOOK: query: CREATE TABLE lineitem_nostats (L_ORDERKEY INT, + L_PARTKEY INT, + L_SUPPKEY INT, + L_LINENUMBER INT, + L_QUANTITY DOUBLE, + L_EXTENDEDPRICE DOUBLE, + L_DISCOUNT DOUBLE, + L_TAX DOUBLE, + L_RETURNFLAG STRING, + L_LINESTATUS STRING, + l_shipdate STRING, + L_COMMITDATE STRING, + L_RECEIPTDATE STRING, + L_SHIPINSTRUCT STRING, + L_SHIPMODE STRING, + L_COMMENT STRING) +ROW FORMAT DELIMITED +FIELDS TERMINATED BY '|' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@lineitem_nostats +PREHOOK: query: CREATE TABLE part_nostats( + p_partkey INT, + p_name STRING, + p_mfgr STRING, + p_brand STRING, + p_type STRING, + p_size INT, + p_container STRING, + p_retailprice DOUBLE, + p_comment STRING +) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@part_nostats +POSTHOOK: query: CREATE TABLE part_nostats( + p_partkey INT, + p_name STRING, + p_mfgr STRING, + p_brand STRING, + p_type STRING, + p_size INT, + p_container STRING, + p_retailprice DOUBLE, + p_comment STRING +) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@part_nostats +PREHOOK: query: explain select count(1) from part,supplier,lineitem where p_partkey = l_partkey and s_suppkey = l_suppkey +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(1) from part,supplier,lineitem where p_partkey = l_partkey and s_suppkey = l_suppkey +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: lineitem + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (l_partkey is not null and l_suppkey is not null) (type: boolean) + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: l_partkey (type: int), l_suppkey (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: supplier + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: s_suppkey is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: s_suppkey (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Execution mode: llap + LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: part + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: p_partkey is not null (type: boolean) + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: p_partkey (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 110 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 110 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 121 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double, country string) +row format delimited fields terminated by '|' stored as textfile +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@Employee_Part +POSTHOOK: query: CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double, country string) +row format delimited fields terminated by '|' stored as textfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@Employee_Part +PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='USA') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@employee_part +POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='USA') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@employee_part +POSTHOOK: Output: default@employee_part@employeesalary=2000.0/country=USA +PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='UK') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@employee_part +POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='UK') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@employee_part +POSTHOOK: Output: default@employee_part@employeesalary=2000.0/country=UK +PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='USA') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@employee_part +POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='USA') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@employee_part +POSTHOOK: Output: default@employee_part@employeesalary=3000.0/country=USA +PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='4000.0', country='USA') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@employee_part +POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='4000.0', country='USA') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@employee_part +POSTHOOK: Output: default@employee_part@employeesalary=4000.0/country=USA +PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3500.0', country='UK') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@employee_part +POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3500.0', country='UK') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@employee_part +POSTHOOK: Output: default@employee_part@employeesalary=3500.0/country=UK +PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='UK') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@employee_part +POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='UK') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@employee_part +POSTHOOK: Output: default@employee_part@employeesalary=3000.0/country=UK +PREHOOK: query: explain select count(1) from Employee_Part,supplier,lineitem where employeeID= l_partkey and s_suppkey = l_suppkey +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(1) from Employee_Part,supplier,lineitem where employeeID= l_partkey and s_suppkey = l_suppkey +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: lineitem + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (l_partkey is not null and l_suppkey is not null) (type: boolean) + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: l_partkey (type: int), l_suppkey (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: supplier + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: s_suppkey is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: s_suppkey (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Execution mode: llap + LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: employee_part + Statistics: Num rows: 116 Data size: 1394 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: employeeid is not null (type: boolean) + Statistics: Num rows: 116 Data size: 1394 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: employeeid (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 116 Data size: 1394 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 116 Data size: 1394 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 110 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 110 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 127 Data size: 1533 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: drop table Employee_Part +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@employee_part +PREHOOK: Output: default@employee_part +POSTHOOK: query: drop table Employee_Part +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@employee_part +POSTHOOK: Output: default@employee_part +PREHOOK: query: drop table supplier +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@supplier +PREHOOK: Output: default@supplier +POSTHOOK: query: drop table supplier +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@supplier +POSTHOOK: Output: default@supplier +PREHOOK: query: drop table lineitem_nostats +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@lineitem_nostats +PREHOOK: Output: default@lineitem_nostats +POSTHOOK: query: drop table lineitem_nostats +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@lineitem_nostats +POSTHOOK: Output: default@lineitem_nostats +PREHOOK: query: drop table part_nostats +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@part_nostats +PREHOOK: Output: default@part_nostats +POSTHOOK: query: drop table part_nostats +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@part_nostats +POSTHOOK: Output: default@part_nostats diff --git a/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out b/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out index d35501e82b..95bb69affa 100644 --- a/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out +++ b/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out @@ -1630,7 +1630,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: oft - Statistics: Num rows: 12288 Data size: 5280746 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 12288 Data size: 7405596 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1640,14 +1640,14 @@ STAGE PLANS: outputColumnNames: _col1, _col6, _col7, _col10 input vertices: 1 Map 2 - Statistics: Num rows: 960 Data size: 497280 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 960 Data size: 66994 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col10 (type: tinyint), _col1 (type: int), _col6 (type: char(255)), _col7 (type: varchar(255)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 960 Data size: 3840 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 960 Data size: 66994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 960 Data size: 3840 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 960 Data size: 66994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/mergejoin.q.out b/ql/src/test/results/clientpositive/llap/mergejoin.q.out index 9df5e42df2..44e0791b68 100644 --- a/ql/src/test/results/clientpositive/llap/mergejoin.q.out +++ b/ql/src/test/results/clientpositive/llap/mergejoin.q.out @@ -293,19 +293,19 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 4 @@ -313,19 +313,19 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -337,15 +337,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 550 Data size: 56100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -354,10 +354,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1382,32 +1382,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 4 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -1419,15 +1419,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 550 Data size: 56100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 9680 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1436,10 +1436,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1493,32 +1493,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 4 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -1530,15 +1530,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 550 Data size: 56100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 9680 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1547,10 +1547,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1604,32 +1604,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 4 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -1641,15 +1641,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 550 Data size: 56100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 9680 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1658,10 +1658,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1704,9 +1704,11 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Map 1 <- Reducer 7 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Map 8 <- Reducer 5 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: @@ -1714,41 +1716,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - filterExpr: (key is not null and value is not null and (value BETWEEN DynamicValue(RS_13_c_value_min) AND DynamicValue(RS_13_c_value_max) and in_bloom_filter(value, DynamicValue(RS_13_c_value_bloom_filter)))) (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + filterExpr: (key is not null and value is not null and (value BETWEEN DynamicValue(RS_10_c_value_min) AND DynamicValue(RS_10_c_value_max) and in_bloom_filter(value, DynamicValue(RS_10_c_value_bloom_filter)))) (type: boolean) + Statistics: Num rows: 242 Data size: 44231 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (key is not null and value is not null and (value BETWEEN DynamicValue(RS_13_c_value_min) AND DynamicValue(RS_13_c_value_max) and in_bloom_filter(value, DynamicValue(RS_13_c_value_bloom_filter)))) (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and value is not null and (value BETWEEN DynamicValue(RS_10_c_value_min) AND DynamicValue(RS_10_c_value_max) and in_bloom_filter(value, DynamicValue(RS_10_c_value_bloom_filter)))) (type: boolean) + Statistics: Num rows: 219 Data size: 19437 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 219 Data size: 19437 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map 5 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 219 Data size: 19437 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs Map 6 @@ -1784,6 +1766,26 @@ STAGE PLANS: value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) Execution mode: vectorized, llap LLAP IO: no inputs + Map 8 + Map Operator Tree: + TableScan + alias: b + filterExpr: (key is not null and (key BETWEEN DynamicValue(RS_12_a_key_min) AND DynamicValue(RS_12_a_key_max) and in_bloom_filter(key, DynamicValue(RS_12_a_key_bloom_filter)))) (type: boolean) + Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and (key BETWEEN DynamicValue(RS_12_a_key_min) AND DynamicValue(RS_12_a_key_max) and in_bloom_filter(key, DynamicValue(RS_12_a_key_bloom_filter)))) (type: boolean) + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -1791,15 +1793,28 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 56100 Basic stats: COMPLETE Column stats: NONE + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 124 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 550 Data size: 56100 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 124 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 124 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=50) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1807,17 +1822,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 605 Data size: 61710 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 620 Data size: 4960 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -1826,14 +1841,26 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=50) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) Reducer 7 Execution mode: vectorized, llap Reduce Operator Tree: @@ -1892,19 +1919,19 @@ STAGE PLANS: TableScan alias: a filterExpr: value is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 43307 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col1 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 4 @@ -1912,19 +1939,19 @@ STAGE PLANS: TableScan alias: b filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89364 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 40228 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col1 - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 40228 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 40228 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -1936,15 +1963,15 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col1 (type: string) - Statistics: Num rows: 550 Data size: 56100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1953,10 +1980,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2015,19 +2042,19 @@ STAGE PLANS: TableScan alias: s1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 6 @@ -2035,19 +2062,19 @@ STAGE PLANS: TableScan alias: s3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 7 @@ -2055,19 +2082,19 @@ STAGE PLANS: TableScan alias: s2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 508 Data size: 51836 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1380 Data size: 5440 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 8 @@ -2075,19 +2102,19 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -2100,12 +2127,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 266 Data size: 27152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 508 Data size: 51836 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1380 Data size: 5440 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: @@ -2115,15 +2142,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 558 Data size: 57019 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6900 Data size: 55200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 5 Execution mode: vectorized, llap @@ -2132,10 +2159,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2171,19 +2198,19 @@ STAGE PLANS: TableScan alias: a filterExpr: value is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 43307 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col1 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 4 @@ -2191,19 +2218,19 @@ STAGE PLANS: TableScan alias: b filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89364 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 40228 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col1 - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 40228 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 40228 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -2215,15 +2242,15 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col1 (type: string) - Statistics: Num rows: 550 Data size: 56100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2232,10 +2259,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2276,9 +2303,11 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Map 1 <- Reducer 7 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Map 8 <- Reducer 5 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: @@ -2286,41 +2315,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - filterExpr: (key is not null and value is not null and (value BETWEEN DynamicValue(RS_13_c_value_min) AND DynamicValue(RS_13_c_value_max) and in_bloom_filter(value, DynamicValue(RS_13_c_value_bloom_filter)))) (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + filterExpr: (key is not null and value is not null and (value BETWEEN DynamicValue(RS_10_c_value_min) AND DynamicValue(RS_10_c_value_max) and in_bloom_filter(value, DynamicValue(RS_10_c_value_bloom_filter)))) (type: boolean) + Statistics: Num rows: 242 Data size: 44231 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (key is not null and value is not null and (value BETWEEN DynamicValue(RS_13_c_value_min) AND DynamicValue(RS_13_c_value_max) and in_bloom_filter(value, DynamicValue(RS_13_c_value_bloom_filter)))) (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and value is not null and (value BETWEEN DynamicValue(RS_10_c_value_min) AND DynamicValue(RS_10_c_value_max) and in_bloom_filter(value, DynamicValue(RS_10_c_value_bloom_filter)))) (type: boolean) + Statistics: Num rows: 219 Data size: 19437 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 219 Data size: 19437 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map 5 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 219 Data size: 19437 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs Map 6 @@ -2356,6 +2365,26 @@ STAGE PLANS: value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) Execution mode: vectorized, llap LLAP IO: no inputs + Map 8 + Map Operator Tree: + TableScan + alias: b + filterExpr: (key is not null and (key BETWEEN DynamicValue(RS_12_a_key_min) AND DynamicValue(RS_12_a_key_max) and in_bloom_filter(key, DynamicValue(RS_12_a_key_bloom_filter)))) (type: boolean) + Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and (key BETWEEN DynamicValue(RS_12_a_key_min) AND DynamicValue(RS_12_a_key_max) and in_bloom_filter(key, DynamicValue(RS_12_a_key_bloom_filter)))) (type: boolean) + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -2363,15 +2392,28 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 56100 Basic stats: COMPLETE Column stats: NONE + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 124 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 550 Data size: 56100 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 124 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 124 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=50) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -2379,17 +2421,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 605 Data size: 61710 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 620 Data size: 4960 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -2398,14 +2440,26 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=50) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) Reducer 7 Execution mode: vectorized, llap Reduce Operator Tree: @@ -2474,19 +2528,19 @@ STAGE PLANS: TableScan alias: s1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 6 @@ -2494,19 +2548,19 @@ STAGE PLANS: TableScan alias: s3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 7 @@ -2514,19 +2568,19 @@ STAGE PLANS: TableScan alias: s2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 508 Data size: 51836 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1380 Data size: 5440 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 8 @@ -2534,19 +2588,19 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -2559,12 +2613,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 266 Data size: 27152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 508 Data size: 51836 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1380 Data size: 5440 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: @@ -2574,15 +2628,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 558 Data size: 57019 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6900 Data size: 55200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 5 Execution mode: vectorized, llap @@ -2591,10 +2645,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2646,18 +2700,18 @@ STAGE PLANS: TableScan alias: t1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 44231 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map 5 @@ -2665,18 +2719,18 @@ STAGE PLANS: TableScan alias: t2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 91268 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -2685,12 +2739,12 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 24684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -2700,15 +2754,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 550 Data size: 56100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -2717,10 +2771,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2731,12 +2785,12 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 51000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/llap/metadata_only_queries.q.out b/ql/src/test/results/clientpositive/llap/metadata_only_queries.q.out index 594e7e7fd6..2c97dcf223 100644 --- a/ql/src/test/results/clientpositive/llap/metadata_only_queries.q.out +++ b/ql/src/test/results/clientpositive/llap/metadata_only_queries.q.out @@ -198,19 +198,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_tbl - Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9999 Data size: 1491657 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9999 Data size: 1491657 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -221,14 +221,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col0 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -262,19 +262,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_tbl_part - Statistics: Num rows: 9489 Data size: 1054697 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9489 Data size: 2394297 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 9489 Data size: 1054697 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9489 Data size: 2394297 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -285,14 +285,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col0 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -326,19 +326,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_tbl - Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9999 Data size: 1491657 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9999 Data size: 1491657 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -349,14 +349,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col0 (type: bigint), _col3 (type: bigint), 7 (type: decimal(2,0)), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 381 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 381 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -390,19 +390,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_tbl_part - Statistics: Num rows: 9489 Data size: 1054697 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9489 Data size: 2394297 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 9489 Data size: 1054697 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9489 Data size: 2394297 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -413,14 +413,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col0 (type: bigint), _col3 (type: bigint), 7 (type: decimal(2,0)), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 381 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 381 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -654,19 +654,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_tbl_part - Statistics: Num rows: 9489 Data size: 1054697 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9489 Data size: 1339425 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ts (type: timestamp) outputColumnNames: ts - Statistics: Num rows: 9489 Data size: 1054697 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9489 Data size: 1339425 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(ts) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -677,10 +677,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/partition_shared_scan.q.out b/ql/src/test/results/clientpositive/llap/partition_shared_scan.q.out index bd3d247d48..84f6db3d00 100644 --- a/ql/src/test/results/clientpositive/llap/partition_shared_scan.q.out +++ b/ql/src/test/results/clientpositive/llap/partition_shared_scan.q.out @@ -58,59 +58,59 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: f1 - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE + alias: p1 + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: i is not null (type: boolean) - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE + predicate: p_partkey is not null (type: boolean) + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: i (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + alias: f1 + Statistics: Num rows: 10 Data size: 130 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + predicate: i is not null (type: boolean) + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + expressions: i (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 5 Map Operator Tree: TableScan alias: f2 - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 130 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i is not null (type: boolean) - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -122,14 +122,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 10 Data size: 6230 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col9 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: string), _col9 (type: double), _col10 (type: string) + Map-reduce partition columns: _col9 (type: int) + Statistics: Num rows: 10 Data size: 6230 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -137,17 +137,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col9 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 30 Data size: 19473 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col11 + Statistics: Num rows: 50 Data size: 31350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), 'foo' (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: string), _col9 (type: double), _col10 (type: string), _col11 (type: int), 'bar' (type: string) + expressions: _col9 (type: int), 'foo' (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: int), 'bar' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 30 Data size: 19473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 40050 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 19473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 40050 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -183,51 +183,51 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: f1 - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE + alias: p1 + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: i is not null (type: boolean) - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE + predicate: p_partkey is not null (type: boolean) + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: i (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + alias: f1 + Statistics: Num rows: 10 Data size: 130 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + predicate: i is not null (type: boolean) + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + expressions: i (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -239,14 +239,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 10 Data size: 6230 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col9 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: string), _col9 (type: double), _col10 (type: string) + Map-reduce partition columns: _col9 (type: int) + Statistics: Num rows: 10 Data size: 6230 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -254,17 +254,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col9 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 30 Data size: 19473 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col11 + Statistics: Num rows: 50 Data size: 31350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), 'foo' (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: string), _col9 (type: double), _col10 (type: string), _col11 (type: int), 'foo' (type: string) + expressions: _col9 (type: int), 'foo' (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: int), 'foo' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 30 Data size: 19473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 40050 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 19473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 40050 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/ppd_union_view.q.out b/ql/src/test/results/clientpositive/llap/ppd_union_view.q.out index 543d17630a..87624f4369 100644 --- a/ql/src/test/results/clientpositive/llap/ppd_union_view.q.out +++ b/ql/src/test/results/clientpositive/llap/ppd_union_view.q.out @@ -153,26 +153,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_new - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (ds = '2011-10-13') (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), '2011-10-13' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 544 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 544 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -197,22 +197,22 @@ STAGE PLANS: alias: t1_old properties: insideView TRUE - Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: keymap is not null (type: boolean) - Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: keymap (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: true @@ -276,22 +276,22 @@ STAGE PLANS: alias: t1_mapping properties: insideView TRUE - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: keymap is not null (type: boolean) - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), keymap (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: string) auto parallelism: true @@ -361,21 +361,21 @@ STAGE PLANS: 1 _col1 (type: string) outputColumnNames: _col1, _col3 Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), '2011-10-13' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 544 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 544 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -462,22 +462,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_new - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 189 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), '2011-10-15' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 544 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 544 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -554,22 +554,22 @@ STAGE PLANS: alias: t1_old properties: insideView TRUE - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((ds = '2011-10-15') and keymap is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: keymap (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: true @@ -581,22 +581,22 @@ STAGE PLANS: alias: t1_mapping properties: insideView TRUE - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (('2011-10-15' = ds) and keymap is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), keymap (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: string) auto parallelism: true @@ -614,21 +614,21 @@ STAGE PLANS: 1 _col1 (type: string) outputColumnNames: _col1, _col3 Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), '2011-10-15' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 544 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 544 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/llap/reduce_deduplicate.q.out b/ql/src/test/results/clientpositive/llap/reduce_deduplicate.q.out index d74e4c7c78..7794b9ff97 100644 --- a/ql/src/test/results/clientpositive/llap/reduce_deduplicate.q.out +++ b/ql/src/test/results/clientpositive/llap/reduce_deduplicate.q.out @@ -274,16 +274,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: complex_tbl_2 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (ds = '2010-03-29') (type: boolean) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: aet (type: string), aes (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: @@ -296,13 +296,13 @@ STAGE PLANS: serialization.format 9 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: bigint), _col5 (type: string), _col6 (type: string) auto parallelism: true @@ -312,7 +312,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), VALUE._col4 (type: bigint), VALUE._col5 (type: string), VALUE._col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: @@ -325,14 +325,14 @@ STAGE PLANS: serialization.format 9 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2010-03-29/ - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat diff --git a/ql/src/test/results/clientpositive/llap/sample10.q.out b/ql/src/test/results/clientpositive/llap/sample10.q.out index a3da78754f..cd0f4b9a6e 100644 --- a/ql/src/test/results/clientpositive/llap/sample10.q.out +++ b/ql/src/test/results/clientpositive/llap/sample10.q.out @@ -56,29 +56,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpartbucket - Statistics: Num rows: 40 Data size: 7600 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 40 Data size: 11071 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 4) = 0) (type: boolean) sampleDesc: BUCKET 1 OUT OF 4 - Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 20 Data size: 5460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: ds - Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 20 Data size: 5460 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: true @@ -301,12 +301,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -317,13 +317,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out index 0ebb378d08..afca5b149c 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out @@ -77,14 +77,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_int_permute_select - Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), a (type: int), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -206,14 +206,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_int_string_permute_select - Statistics: Num rows: 2 Data size: 290 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 484 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), a (type: int), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -393,14 +393,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_string_group_double - Statistics: Num rows: 5 Data size: 2130 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2715 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: double), c2 (type: double), c3 (type: double), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 605 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 605 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -517,14 +517,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_date_group_string_group_date_timestamp - Statistics: Num rows: 6 Data size: 3521 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 9419 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: char(50)), c3 (type: char(15)), c4 (type: varchar(50)), c5 (type: varchar(15)), c6 (type: string), c7 (type: char(50)), c8 (type: char(15)), c9 (type: varchar(50)), c10 (type: varchar(15)), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -710,14 +710,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_numeric_group_string_group_multi_ints_string_group - Statistics: Num rows: 6 Data size: 2903 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 14141 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: string), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(50)), c8 (type: char(50)), c9 (type: char(5)), c10 (type: char(5)), c11 (type: char(5)), c12 (type: char(5)), c13 (type: varchar(50)), c14 (type: varchar(50)), c15 (type: varchar(50)), c16 (type: varchar(50)), c17 (type: varchar(5)), c18 (type: varchar(5)), c19 (type: varchar(5)), c20 (type: varchar(5)), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11262 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11262 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -893,14 +893,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_numeric_group_string_group_floating_string_group - Statistics: Num rows: 6 Data size: 4540 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 13108 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: char(50)), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(7)), c8 (type: char(7)), c9 (type: char(7)), c10 (type: varchar(50)), c11 (type: varchar(50)), c12 (type: varchar(50)), c13 (type: varchar(7)), c14 (type: varchar(7)), c15 (type: varchar(7)), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8592 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8592 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1062,14 +1062,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_string_group_string_group_string - Statistics: Num rows: 6 Data size: 6682 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 12580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: char(50)), c2 (type: char(9)), c3 (type: varchar(50)), c4 (type: char(9)), c5 (type: varchar(50)), c6 (type: varchar(9)), c7 (type: string), c8 (type: char(50)), c9 (type: char(9)), c10 (type: string), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1259,14 +1259,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_lower_to_higher_numeric_group_tinyint_to_bigint - Statistics: Num rows: 6 Data size: 1419 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5169 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: smallint), c2 (type: int), c3 (type: bigint), c4 (type: decimal(38,18)), c5 (type: float), c6 (type: double), c7 (type: int), c8 (type: bigint), c9 (type: decimal(38,18)), c10 (type: float), c11 (type: double), c12 (type: bigint), c13 (type: decimal(38,18)), c14 (type: float), c15 (type: double), c16 (type: decimal(38,18)), c17 (type: float), c18 (type: double), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3774 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3774 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1398,14 +1398,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_lower_to_higher_numeric_group_decimal_to_float - Statistics: Num rows: 6 Data size: 1523 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 2201 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: float), c2 (type: double), c3 (type: double), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out index 22c7745345..e7eddc3821 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out @@ -155,14 +155,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_struct1 - Statistics: Num rows: 6 Data size: 4734 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5292 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: insert_num (type: int), part (type: int), s1 (type: struct), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -431,14 +431,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_various_various_struct2 - Statistics: Num rows: 8 Data size: 4912 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 5656 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: insert_num (type: int), part (type: int), b (type: string), s2 (type: struct) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 776 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 776 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -635,14 +635,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_to_various_various_struct4 - Statistics: Num rows: 4 Data size: 1172 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 1544 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: insert_num (type: int), part (type: int), b (type: string), s3 (type: struct) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out index 4e94322705..786b4dd4dd 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out @@ -266,14 +266,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_boolean_to_bigint - Statistics: Num rows: 10 Data size: 11688 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 15178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: boolean), c2 (type: boolean), c3 (type: boolean), c4 (type: boolean), c5 (type: boolean), c6 (type: boolean), c7 (type: boolean), c8 (type: boolean), c9 (type: boolean), c10 (type: tinyint), c11 (type: tinyint), c12 (type: tinyint), c13 (type: tinyint), c14 (type: tinyint), c15 (type: tinyint), c16 (type: tinyint), c17 (type: tinyint), c18 (type: tinyint), c19 (type: tinyint), c20 (type: tinyint), c21 (type: smallint), c22 (type: smallint), c23 (type: smallint), c24 (type: smallint), c25 (type: smallint), c26 (type: smallint), c27 (type: smallint), c28 (type: smallint), c29 (type: smallint), c30 (type: smallint), c31 (type: smallint), c32 (type: int), c33 (type: int), c34 (type: int), c35 (type: int), c36 (type: int), c37 (type: int), c38 (type: int), c39 (type: int), c40 (type: int), c41 (type: int), c42 (type: int), c43 (type: bigint), c44 (type: bigint), c45 (type: bigint), c46 (type: bigint), c47 (type: bigint), c48 (type: bigint), c49 (type: bigint), c50 (type: bigint), c51 (type: bigint), c52 (type: bigint), c53 (type: bigint), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41, _col42, _col43, _col44, _col45, _col46, _col47, _col48, _col49, _col50, _col51, _col52, _col53, _col54, _col55 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -491,14 +491,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_decimal_to_double - Statistics: Num rows: 6 Data size: 8295 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 17037 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: decimal(38,18)), c2 (type: decimal(38,18)), c3 (type: decimal(38,18)), c4 (type: decimal(38,18)), c5 (type: decimal(38,18)), c6 (type: decimal(38,18)), c7 (type: decimal(38,18)), c8 (type: decimal(38,18)), c9 (type: decimal(38,18)), c10 (type: decimal(38,18)), c11 (type: decimal(38,18)), c12 (type: float), c13 (type: float), c14 (type: float), c15 (type: float), c16 (type: float), c17 (type: float), c18 (type: float), c19 (type: float), c20 (type: float), c21 (type: float), c22 (type: float), c23 (type: double), c24 (type: double), c25 (type: double), c26 (type: double), c27 (type: double), c28 (type: double), c29 (type: double), c30 (type: double), c31 (type: double), c32 (type: double), c33 (type: double), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8766 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8766 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -638,14 +638,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_timestamp - Statistics: Num rows: 6 Data size: 2965 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 6403 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: timestamp), c2 (type: timestamp), c3 (type: timestamp), c4 (type: timestamp), c5 (type: timestamp), c6 (type: timestamp), c7 (type: timestamp), c8 (type: timestamp), c9 (type: timestamp), c10 (type: timestamp), c11 (type: timestamp), c12 (type: timestamp), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3462 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3462 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -769,14 +769,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_date - Statistics: Num rows: 6 Data size: 2444 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 4346 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: date), c2 (type: date), c3 (type: date), c4 (type: date), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1926 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1926 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -981,14 +981,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_same_type_different_params - Statistics: Num rows: 13 Data size: 8736 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 17485 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: char(8)), c2 (type: char(32)), c3 (type: varchar(15)), c4 (type: varchar(18)), c5 (type: decimal(10,2)), c6 (type: decimal(25,15)), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 8801 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 8801 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out index c6fc7b5dc6..58e2ce93f0 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out @@ -77,7 +77,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_int_permute_select - Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4] @@ -88,13 +88,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 4, 1, 2] - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -230,7 +230,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_int_string_permute_select - Statistics: Num rows: 2 Data size: 290 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 484 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -241,13 +241,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 5, 1, 2] - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,7 +441,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_string_group_double - Statistics: Num rows: 5 Data size: 2130 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2715 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -452,13 +452,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 5, 1, 2, 3, 4] - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 605 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 605 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -589,7 +589,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_date_group_string_group_date_timestamp - Statistics: Num rows: 6 Data size: 3521 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 9419 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] @@ -600,13 +600,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -806,7 +806,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_numeric_group_string_group_multi_ints_string_group - Statistics: Num rows: 6 Data size: 2903 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 14141 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22] @@ -817,13 +817,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 22, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11262 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11262 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1013,7 +1013,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_numeric_group_string_group_floating_string_group - Statistics: Num rows: 6 Data size: 4540 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 13108 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17] @@ -1024,13 +1024,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 17, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8592 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8592 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1206,7 +1206,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_string_group_string_group_string - Statistics: Num rows: 6 Data size: 6682 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 12580 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] @@ -1217,13 +1217,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1427,7 +1427,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_lower_to_higher_numeric_group_tinyint_to_bigint - Statistics: Num rows: 6 Data size: 1419 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5169 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20] @@ -1438,13 +1438,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 20, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3774 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3774 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1590,7 +1590,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_lower_to_higher_numeric_group_decimal_to_float - Statistics: Num rows: 6 Data size: 1523 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 2201 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -1601,13 +1601,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 5, 1, 2, 3, 4] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out index f57481dcc1..b8dec11983 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out @@ -155,7 +155,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_struct1 - Statistics: Num rows: 6 Data size: 4734 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5292 Basic stats: COMPLETE Column stats: PARTIAL TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3] @@ -166,13 +166,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 3, 1, 2] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -455,7 +455,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_various_various_struct2 - Statistics: Num rows: 8 Data size: 4912 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 5656 Basic stats: COMPLETE Column stats: PARTIAL TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3] @@ -466,13 +466,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 3, 1, 2] - Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 776 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 776 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -683,7 +683,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_to_various_various_struct4 - Statistics: Num rows: 4 Data size: 1172 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 1544 Basic stats: COMPLETE Column stats: PARTIAL TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3] @@ -694,13 +694,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 3, 1, 2] - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out index 3a5232ad2e..2c7f9cdd6d 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out @@ -266,7 +266,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_boolean_to_bigint - Statistics: Num rows: 10 Data size: 11688 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 15178 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55] @@ -277,13 +277,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 55, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -515,7 +515,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_decimal_to_double - Statistics: Num rows: 6 Data size: 8295 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 17037 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35] @@ -526,13 +526,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 35, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8766 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8766 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -686,7 +686,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_timestamp - Statistics: Num rows: 6 Data size: 2965 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 6403 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14] @@ -697,13 +697,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 14, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3462 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3462 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -841,7 +841,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_date - Statistics: Num rows: 6 Data size: 2444 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 4346 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6] @@ -852,13 +852,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 6, 1, 2, 3, 4, 5] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1926 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1926 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1077,7 +1077,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_same_type_different_params - Statistics: Num rows: 13 Data size: 8736 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 17485 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8] @@ -1088,13 +1088,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 8, 1, 2, 3, 4, 5, 6, 7] - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 8801 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 8801 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out index 8daee2883f..4fbbe40334 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out @@ -77,14 +77,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_int_permute_select - Statistics: Num rows: 2 Data size: 33 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 227 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), a (type: int), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -206,14 +206,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_int_string_permute_select - Statistics: Num rows: 2 Data size: 38 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), a (type: int), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -393,14 +393,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_string_group_double - Statistics: Num rows: 5 Data size: 471 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: double), c2 (type: double), c3 (type: double), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 605 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 605 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -517,14 +517,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_date_group_string_group_date_timestamp - Statistics: Num rows: 6 Data size: 1032 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 6930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: char(50)), c3 (type: char(15)), c4 (type: varchar(50)), c5 (type: varchar(15)), c6 (type: string), c7 (type: char(50)), c8 (type: char(15)), c9 (type: varchar(50)), c10 (type: varchar(15)), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -710,14 +710,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_numeric_group_string_group_multi_ints_string_group - Statistics: Num rows: 6 Data size: 1094 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 12332 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: string), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(50)), c8 (type: char(50)), c9 (type: char(5)), c10 (type: char(5)), c11 (type: char(5)), c12 (type: char(5)), c13 (type: varchar(50)), c14 (type: varchar(50)), c15 (type: varchar(50)), c16 (type: varchar(50)), c17 (type: varchar(5)), c18 (type: varchar(5)), c19 (type: varchar(5)), c20 (type: varchar(5)), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11262 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11262 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -893,14 +893,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_numeric_group_string_group_floating_string_group - Statistics: Num rows: 6 Data size: 1521 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 10089 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: char(50)), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(7)), c8 (type: char(7)), c9 (type: char(7)), c10 (type: varchar(50)), c11 (type: varchar(50)), c12 (type: varchar(50)), c13 (type: varchar(7)), c14 (type: varchar(7)), c15 (type: varchar(7)), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8592 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8592 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1062,14 +1062,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_string_group_string_group_string - Statistics: Num rows: 6 Data size: 1205 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 7103 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: char(50)), c2 (type: char(9)), c3 (type: varchar(50)), c4 (type: char(9)), c5 (type: varchar(50)), c6 (type: varchar(9)), c7 (type: string), c8 (type: char(50)), c9 (type: char(9)), c10 (type: string), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1259,14 +1259,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_lower_to_higher_numeric_group_tinyint_to_bigint - Statistics: Num rows: 6 Data size: 860 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 4610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: smallint), c2 (type: int), c3 (type: bigint), c4 (type: decimal(38,18)), c5 (type: float), c6 (type: double), c7 (type: int), c8 (type: bigint), c9 (type: decimal(38,18)), c10 (type: float), c11 (type: double), c12 (type: bigint), c13 (type: decimal(38,18)), c14 (type: float), c15 (type: double), c16 (type: decimal(38,18)), c17 (type: float), c18 (type: double), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3774 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3774 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1398,14 +1398,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_lower_to_higher_numeric_group_decimal_to_float - Statistics: Num rows: 6 Data size: 428 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1106 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: float), c2 (type: double), c3 (type: double), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out index 12c7db4af8..766c5d72b9 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out @@ -155,14 +155,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_struct1 - Statistics: Num rows: 6 Data size: 931 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1489 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: insert_num (type: int), part (type: int), s1 (type: struct), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -431,14 +431,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_various_various_struct2 - Statistics: Num rows: 8 Data size: 939 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 1683 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: insert_num (type: int), part (type: int), b (type: string), s2 (type: struct) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 776 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 776 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -635,14 +635,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_to_various_various_struct4 - Statistics: Num rows: 4 Data size: 353 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 725 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: insert_num (type: int), part (type: int), b (type: string), s3 (type: struct) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out index 757ea3a6c0..207dd2b128 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out @@ -266,14 +266,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_boolean_to_bigint - Statistics: Num rows: 10 Data size: 5126 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 8616 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: boolean), c2 (type: boolean), c3 (type: boolean), c4 (type: boolean), c5 (type: boolean), c6 (type: boolean), c7 (type: boolean), c8 (type: boolean), c9 (type: boolean), c10 (type: tinyint), c11 (type: tinyint), c12 (type: tinyint), c13 (type: tinyint), c14 (type: tinyint), c15 (type: tinyint), c16 (type: tinyint), c17 (type: tinyint), c18 (type: tinyint), c19 (type: tinyint), c20 (type: tinyint), c21 (type: smallint), c22 (type: smallint), c23 (type: smallint), c24 (type: smallint), c25 (type: smallint), c26 (type: smallint), c27 (type: smallint), c28 (type: smallint), c29 (type: smallint), c30 (type: smallint), c31 (type: smallint), c32 (type: int), c33 (type: int), c34 (type: int), c35 (type: int), c36 (type: int), c37 (type: int), c38 (type: int), c39 (type: int), c40 (type: int), c41 (type: int), c42 (type: int), c43 (type: bigint), c44 (type: bigint), c45 (type: bigint), c46 (type: bigint), c47 (type: bigint), c48 (type: bigint), c49 (type: bigint), c50 (type: bigint), c51 (type: bigint), c52 (type: bigint), c53 (type: bigint), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41, _col42, _col43, _col44, _col45, _col46, _col47, _col48, _col49, _col50, _col51, _col52, _col53, _col54, _col55 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -491,14 +491,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_decimal_to_double - Statistics: Num rows: 6 Data size: 2735 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11477 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: decimal(38,18)), c2 (type: decimal(38,18)), c3 (type: decimal(38,18)), c4 (type: decimal(38,18)), c5 (type: decimal(38,18)), c6 (type: decimal(38,18)), c7 (type: decimal(38,18)), c8 (type: decimal(38,18)), c9 (type: decimal(38,18)), c10 (type: decimal(38,18)), c11 (type: decimal(38,18)), c12 (type: float), c13 (type: float), c14 (type: float), c15 (type: float), c16 (type: float), c17 (type: float), c18 (type: float), c19 (type: float), c20 (type: float), c21 (type: float), c22 (type: float), c23 (type: double), c24 (type: double), c25 (type: double), c26 (type: double), c27 (type: double), c28 (type: double), c29 (type: double), c30 (type: double), c31 (type: double), c32 (type: double), c33 (type: double), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8766 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8766 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -638,14 +638,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_timestamp - Statistics: Num rows: 6 Data size: 907 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 4345 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: timestamp), c2 (type: timestamp), c3 (type: timestamp), c4 (type: timestamp), c5 (type: timestamp), c6 (type: timestamp), c7 (type: timestamp), c8 (type: timestamp), c9 (type: timestamp), c10 (type: timestamp), c11 (type: timestamp), c12 (type: timestamp), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3462 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3462 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -769,14 +769,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_date - Statistics: Num rows: 6 Data size: 461 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 2363 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: date), c2 (type: date), c3 (type: date), c4 (type: date), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1926 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1926 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -981,14 +981,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_same_type_different_params - Statistics: Num rows: 13 Data size: 1427 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 10176 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: insert_num (type: int), part (type: int), c1 (type: char(8)), c2 (type: char(32)), c3 (type: varchar(15)), c4 (type: varchar(18)), c5 (type: decimal(10,2)), c6 (type: decimal(25,15)), b (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 8801 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 8801 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part.q.out index 45635eeb4c..6d54a47aac 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part.q.out @@ -77,7 +77,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_int_permute_select - Statistics: Num rows: 2 Data size: 33 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 227 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4] @@ -88,13 +88,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 4, 1, 2] - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -230,7 +230,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_int_string_permute_select - Statistics: Num rows: 2 Data size: 38 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -241,13 +241,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 5, 1, 2] - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,7 +441,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_string_group_double - Statistics: Num rows: 5 Data size: 471 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -452,13 +452,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 5, 1, 2, 3, 4] - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 605 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 605 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -589,7 +589,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_date_group_string_group_date_timestamp - Statistics: Num rows: 6 Data size: 1032 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 6930 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] @@ -600,13 +600,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -806,7 +806,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_numeric_group_string_group_multi_ints_string_group - Statistics: Num rows: 6 Data size: 1094 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 12332 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22] @@ -817,13 +817,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 22, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11262 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11262 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1013,7 +1013,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_numeric_group_string_group_floating_string_group - Statistics: Num rows: 6 Data size: 1521 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 10089 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17] @@ -1024,13 +1024,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 17, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8592 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8592 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1206,7 +1206,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_string_group_string_group_string - Statistics: Num rows: 6 Data size: 1205 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 7103 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] @@ -1217,13 +1217,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1427,7 +1427,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_lower_to_higher_numeric_group_tinyint_to_bigint - Statistics: Num rows: 6 Data size: 860 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 4610 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20] @@ -1438,13 +1438,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 20, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3774 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3774 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1590,7 +1590,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_lower_to_higher_numeric_group_decimal_to_float - Statistics: Num rows: 6 Data size: 428 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1106 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -1601,13 +1601,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 5, 1, 2, 3, 4] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_complex.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_complex.q.out index 5e0c8f709a..580fe9065d 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_complex.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_complex.q.out @@ -155,7 +155,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_struct1 - Statistics: Num rows: 6 Data size: 931 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1489 Basic stats: COMPLETE Column stats: PARTIAL TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3] @@ -166,13 +166,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 3, 1, 2] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -455,7 +455,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_various_various_struct2 - Statistics: Num rows: 8 Data size: 939 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 1683 Basic stats: COMPLETE Column stats: PARTIAL TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3] @@ -466,13 +466,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 3, 1, 2] - Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 776 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 776 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -683,7 +683,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_to_various_various_struct4 - Statistics: Num rows: 4 Data size: 353 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 725 Basic stats: COMPLETE Column stats: PARTIAL TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3] @@ -694,13 +694,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 3, 1, 2] - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive.q.out index 17b078fb0c..e7900bbe64 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive.q.out @@ -266,7 +266,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_boolean_to_bigint - Statistics: Num rows: 10 Data size: 5126 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 8616 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55] @@ -277,13 +277,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 55, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -515,7 +515,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_decimal_to_double - Statistics: Num rows: 6 Data size: 2735 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11477 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35] @@ -526,13 +526,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 35, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8766 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8766 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -686,7 +686,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_timestamp - Statistics: Num rows: 6 Data size: 907 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 4345 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14] @@ -697,13 +697,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 14, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3462 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3462 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -841,7 +841,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_date - Statistics: Num rows: 6 Data size: 461 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 2363 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6] @@ -852,13 +852,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 6, 1, 2, 3, 4, 5] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1926 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1926 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1077,7 +1077,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_same_type_different_params - Statistics: Num rows: 13 Data size: 1427 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 10176 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8] @@ -1088,13 +1088,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 8, 1, 2, 3, 4, 5, 6, 7] - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 8801 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 8801 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part.q.out index d687506241..49ae9b7334 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part.q.out @@ -77,7 +77,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_int_permute_select - Statistics: Num rows: 2 Data size: 33 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 227 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4] @@ -88,13 +88,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 4, 1, 2] - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -230,7 +230,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_int_string_permute_select - Statistics: Num rows: 2 Data size: 38 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -241,13 +241,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 5, 1, 2] - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,7 +441,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_string_group_double - Statistics: Num rows: 5 Data size: 471 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -452,13 +452,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 5, 1, 2, 3, 4] - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 605 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 605 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -589,7 +589,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_date_group_string_group_date_timestamp - Statistics: Num rows: 6 Data size: 1032 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 6930 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] @@ -600,13 +600,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -806,7 +806,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_numeric_group_string_group_multi_ints_string_group - Statistics: Num rows: 6 Data size: 1094 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 12332 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22] @@ -817,13 +817,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 22, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11262 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11262 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1013,7 +1013,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_numeric_group_string_group_floating_string_group - Statistics: Num rows: 6 Data size: 1521 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 10089 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17] @@ -1024,13 +1024,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 17, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8592 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8592 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1206,7 +1206,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_string_group_string_group_string - Statistics: Num rows: 6 Data size: 1205 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 7103 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] @@ -1217,13 +1217,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 5922 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1427,7 +1427,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_lower_to_higher_numeric_group_tinyint_to_bigint - Statistics: Num rows: 6 Data size: 860 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 4610 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20] @@ -1438,13 +1438,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 20, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3774 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3774 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1590,7 +1590,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_lower_to_higher_numeric_group_decimal_to_float - Statistics: Num rows: 6 Data size: 428 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1106 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -1601,13 +1601,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 5, 1, 2, 3, 4] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_complex.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_complex.q.out index afaf69faf3..a67d228370 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_complex.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_complex.q.out @@ -155,7 +155,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_struct1 - Statistics: Num rows: 6 Data size: 931 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1489 Basic stats: COMPLETE Column stats: PARTIAL TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3] @@ -166,13 +166,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 3, 1, 2] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -455,7 +455,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_various_various_struct2 - Statistics: Num rows: 8 Data size: 939 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 1683 Basic stats: COMPLETE Column stats: PARTIAL TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3] @@ -466,13 +466,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 3, 1, 2] - Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 776 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 776 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -683,7 +683,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_add_to_various_various_struct4 - Statistics: Num rows: 4 Data size: 353 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 725 Basic stats: COMPLETE Column stats: PARTIAL TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3] @@ -694,13 +694,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 3, 1, 2] - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out index 59d6797d63..266c659b7d 100644 --- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out +++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out @@ -266,7 +266,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_boolean_to_bigint - Statistics: Num rows: 10 Data size: 5126 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 8616 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55] @@ -277,13 +277,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 55, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54] - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -515,7 +515,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_decimal_to_double - Statistics: Num rows: 6 Data size: 2735 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 11477 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35] @@ -526,13 +526,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 35, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8766 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 8766 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -686,7 +686,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_timestamp - Statistics: Num rows: 6 Data size: 907 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 4345 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14] @@ -697,13 +697,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 14, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3462 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 3462 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -841,7 +841,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_various_various_date - Statistics: Num rows: 6 Data size: 461 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 2363 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6] @@ -852,13 +852,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 6, 1, 2, 3, 4, 5] - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1926 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 6 Data size: 1926 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1077,7 +1077,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_change_same_type_different_params - Statistics: Num rows: 13 Data size: 1427 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 10176 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8] @@ -1088,13 +1088,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 8, 1, 2, 3, 4, 5, 6, 7] - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 8801 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 8801 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/smb_mapjoin_18.q.out b/ql/src/test/results/clientpositive/llap/smb_mapjoin_18.q.out index e2d5e4e4c2..8750fe91da 100644 --- a/ql/src/test/results/clientpositive/llap/smb_mapjoin_18.q.out +++ b/ql/src/test/results/clientpositive/llap/smb_mapjoin_18.q.out @@ -53,14 +53,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 44268 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 44268 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -233,19 +233,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 238) (type: boolean) - Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 238 (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -255,10 +255,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -373,14 +373,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 2 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/smb_mapjoin_19.q.out b/ql/src/test/results/clientpositive/llap/smb_mapjoin_19.q.out index c3b29ea2bd..6038c35d8b 100644 --- a/ql/src/test/results/clientpositive/llap/smb_mapjoin_19.q.out +++ b/ql/src/test/results/clientpositive/llap/smb_mapjoin_19.q.out @@ -53,14 +53,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 44268 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 44268 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/stats_only_null.q.out b/ql/src/test/results/clientpositive/llap/stats_only_null.q.out index ab91ea738c..ae9502739c 100644 --- a/ql/src/test/results/clientpositive/llap/stats_only_null.q.out +++ b/ql/src/test/results/clientpositive/llap/stats_only_null.q.out @@ -88,19 +88,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_null - Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1050 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) outputColumnNames: a, b, c, d - Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1050 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -111,10 +111,10 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -148,19 +148,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_null_part - Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) outputColumnNames: a, b, c, d - Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1170 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -171,10 +171,10 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/table_access_keys_stats.q.out b/ql/src/test/results/clientpositive/llap/table_access_keys_stats.q.out index 85459229f5..140397a8db 100644 --- a/ql/src/test/results/clientpositive/llap/table_access_keys_stats.q.out +++ b/ql/src/test/results/clientpositive/llap/table_access_keys_stats.q.out @@ -496,7 +496,7 @@ Keys:val 13.0 1 17.0 1 46.0 1 -Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: SELECT * FROM ( @@ -519,11 +519,11 @@ PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 PREHOOK: Input: default@t3 #### A masked pattern was here #### -Operator:JOIN_8 -Table:default@t1 -Keys:key +Operator:JOIN_11 Table:default@t2 Keys:key +Table:default@t1 +Keys:key PREHOOK: query: SELECT * FROM T1 JOIN T2 diff --git a/ql/src/test/results/clientpositive/llap/tez_dml.q.out b/ql/src/test/results/clientpositive/llap/tez_dml.q.out index ece6946fb8..cb5560ff28 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dml.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dml.q.out @@ -448,14 +448,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tmp_src - Statistics: Num rows: 309 Data size: 2718 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28615 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), cnt (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 2718 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28615 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 2718 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28615 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_smb_empty.q.out b/ql/src/test/results/clientpositive/llap/tez_smb_empty.q.out index e4c246afec..50bfa63305 100644 --- a/ql/src/test/results/clientpositive/llap/tez_smb_empty.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_smb_empty.q.out @@ -138,40 +138,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s3 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -181,10 +181,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -228,19 +228,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s3 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 277 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 242 Data size: 47094 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 242 Data size: 68577 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 242 Data size: 44528 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 242 Data size: 66011 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Left Outer Join 0 to 1 @@ -248,10 +248,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 242 Data size: 117312 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 242 Data size: 67673 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 242 Data size: 117312 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 242 Data size: 67673 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -540,36 +540,36 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s2 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: s3 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Left Outer Join 0 to 1 @@ -578,15 +578,15 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Statistics: Num rows: 532 Data size: 9904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -596,10 +596,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -646,36 +646,36 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: s3 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Left Outer Join 0 to 1 @@ -684,15 +684,15 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Statistics: Num rows: 532 Data size: 9904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -702,10 +702,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -752,40 +752,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s3 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -795,10 +795,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -841,40 +841,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s3 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -884,10 +884,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_smb_main.q.out b/ql/src/test/results/clientpositive/llap/tez_smb_main.q.out index e5f6940e48..b8142d9f50 100644 --- a/ql/src/test/results/clientpositive/llap/tez_smb_main.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_smb_main.q.out @@ -263,33 +263,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 2 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -298,15 +298,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 0 Map 1 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -317,10 +317,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -374,33 +374,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 2 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -409,15 +409,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 0 Map 1 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -428,10 +428,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -584,11 +584,12 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 2 <- Map 4 (BROADCAST_EDGE) - Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) + Map 1 <- Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: - Map 2 + Map 1 Map Operator Tree: TableScan alias: a @@ -600,44 +601,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator + Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - input vertices: - 1 Map 4 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Map 4 + Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE Execution mode: llap + LLAP IO: no inputs Map 4 Map Operator Tree: TableScan @@ -657,6 +637,44 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -692,11 +710,12 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 2 <- Map 4 (BROADCAST_EDGE) - Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) + Map 1 <- Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: - Map 2 + Map 1 Map Operator Tree: TableScan alias: a @@ -708,44 +727,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator + Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - input vertices: - 1 Map 4 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Map 4 + Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE Execution mode: llap + LLAP IO: no inputs Map 4 Map Operator Tree: TableScan @@ -765,6 +763,44 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1364,8 +1400,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 2 <- Map 1 (CUSTOM_EDGE), Map 4 (BROADCAST_EDGE) - Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) + Map 1 <- Map 2 (BROADCAST_EDGE) + Map 3 <- Map 1 (CUSTOM_EDGE) + Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1380,15 +1417,43 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Map 2 + Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs - Map 2 + Map 3 Map Operator Tree: TableScan alias: b @@ -1406,50 +1471,21 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1 input vertices: 0 Map 1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - input vertices: - 1 Map 4 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs - Reducer 3 + Reducer 4 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -1484,8 +1520,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 2 <- Map 1 (CUSTOM_EDGE), Map 4 (BROADCAST_EDGE) - Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) + Map 1 <- Map 2 (BROADCAST_EDGE) + Map 3 <- Map 1 (CUSTOM_EDGE) + Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1500,15 +1537,43 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Map 2 + Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs - Map 2 + Map 3 Map Operator Tree: TableScan alias: b @@ -1526,50 +1591,21 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1 input vertices: 0 Map 1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - input vertices: - 1 Map 4 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs - Reducer 3 + Reducer 4 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -1638,14 +1674,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1655,7 +1691,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1664,15 +1700,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 6 - Statistics: Num rows: 558 Data size: 10399 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6900 Data size: 55200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1680,33 +1716,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s3 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 5 Map Operator Tree: TableScan alias: s2 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1715,15 +1751,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 6 - Statistics: Num rows: 558 Data size: 10399 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6900 Data size: 55200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1731,24 +1767,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 7216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -1758,10 +1794,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1811,36 +1847,36 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 24049 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 20460 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 3 Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 42036 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1849,19 +1885,19 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 230 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1870,15 +1906,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 0 Reducer 2 - Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 5 Execution mode: llap @@ -1887,10 +1923,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_union_group_by.q.out b/ql/src/test/results/clientpositive/llap/tez_union_group_by.q.out index 67cd110a61..85873f1d23 100644 --- a/ql/src/test/results/clientpositive/llap/tez_union_group_by.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_union_group_by.q.out @@ -160,25 +160,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: x - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date < '2014-09-02') and (u <> 0)) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: u (type: bigint), date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col1) keys: _col0 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: unknown @@ -186,40 +186,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: v - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: t is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: t (type: string), st (type: string) sort order: ++ Map-reduce partition columns: t (type: string), st (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Map 5 Map Operator Tree: TableScan alias: y - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date < '2014-09-02') and (u <> 0)) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: u (type: bigint), date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col1) keys: _col0 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: unknown @@ -227,25 +227,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: z - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date < '2014-09-02') and (u <> 0)) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: u (type: bigint), date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col1) keys: _col0 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: unknown @@ -253,15 +253,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: x - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t is not null and (date >= '2014-03-04') and (date < '2014-09-03') and (u <> 0)) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: t (type: string), st (type: string) sort order: ++ Map-reduce partition columns: t (type: string), st (type: string) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE value expressions: u (type: bigint) Execution mode: llap LLAP IO: unknown @@ -273,19 +273,19 @@ STAGE PLANS: keys: KEY._col0 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 <= '2014-09-02') (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: @@ -296,14 +296,14 @@ STAGE PLANS: 0 _col0 (type: bigint) 1 _col0 (type: bigint) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: bigint), _col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -319,17 +319,17 @@ STAGE PLANS: 1 t (type: string), st (type: string) nullSafes: [false, true] outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: bigint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reducer 9 Execution mode: llap Reduce Operator Tree: @@ -337,12 +337,12 @@ STAGE PLANS: keys: KEY._col0 (type: bigint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Union 2 Vertex: Union 2 diff --git a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out index 8d97fa4fab..83d3fb5ab5 100644 --- a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out +++ b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out @@ -5684,21 +5684,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 3070 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: astring (type: string) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 3070 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 13 @@ -5752,12 +5752,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: COMPLETE Reducer 7 Execution mode: llap Reduce Operator Tree: @@ -5765,7 +5765,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -6466,35 +6466,35 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Map 1 <- Union 2 (CONTAINS) - Map 4 <- Map 5 (BROADCAST_EDGE), Union 2 (CONTAINS) Reducer 3 <- Union 2 (SIMPLE_EDGE) + Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE), Union 2 (CONTAINS) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: dst_union22_delta - Statistics: Num rows: 500 Data size: 20936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 228756 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(k0) <= 50.0) (type: boolean) - Statistics: Num rows: 166 Data size: 6950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 70755 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: k1 (type: string), k2 (type: string), k3 (type: string), k4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 166 Data size: 6950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 56604 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 348 Data size: 40548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 434 Data size: 150054 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Statistics: Num rows: 348 Data size: 40548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 434 Data size: 150054 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Execution mode: llap @@ -6555,50 +6555,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 103124 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 500 Data size: 187852 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(k1) > 20.0) (type: boolean) - Statistics: Num rows: 166 Data size: 30544 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 166 Data size: 58846 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: k1 (type: string), k2 (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 30544 Basic stats: COMPLETE Column stats: PARTIAL - Map Join Operator - condition map: - Left Outer Join 0 to 1 - filter mappings: - 0 [1, 1] - filter predicates: - 0 {(_col2 = '1')} - 1 - Estimated key counts: Map 5 => 55 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col4, _col5 - input vertices: - 1 Map 5 - Position of Big Table: 0 - Statistics: Num rows: 182 Data size: 33598 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 33598 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 348 Data size: 40548 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: aaaa - sort order: ++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Statistics: Num rows: 348 Data size: 40548 Basic stats: COMPLETE Column stats: NONE - tag: -1 - auto parallelism: true + Statistics: Num rows: 166 Data size: 58846 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 58846 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: true Execution mode: llap LLAP IO: no inputs Path -> Alias: @@ -6653,26 +6628,26 @@ STAGE PLANS: name: default.dst_union22 Truncated Path -> Alias: /dst_union22/ds=1 [a] - Map 5 + Map 6 Map Operator Tree: TableScan alias: dst_union22_delta - Statistics: Num rows: 500 Data size: 20936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 186392 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(k0) > 50.0) and (UDFToDouble(k1) > 20.0)) (type: boolean) - Statistics: Num rows: 55 Data size: 2302 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 18868 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: k1 (type: string), k3 (type: string), k4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 2302 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 14151 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 2302 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 14151 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string), _col2 (type: string) auto parallelism: true @@ -6738,14 +6713,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 174 Data size: 20274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 434 Data size: 150054 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2/ - Statistics: Num rows: 174 Data size: 20274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 434 Data size: 150054 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -6769,6 +6744,41 @@ STAGE PLANS: TotalFiles: 1 GatherStats: true MultiFileSpray: false + Reducer 5 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + filter mappings: + 0 [1, 1] + filter predicates: + 0 {(VALUE._col1 = '1')} + 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col4, _col5 + Position of Big Table: 0 + Statistics: Num rows: 268 Data size: 93806 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 268 Data size: 93806 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 434 Data size: 150054 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: aaaa + sort order: ++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + Statistics: Num rows: 434 Data size: 150054 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: true Union 2 Vertex: Union 2 @@ -7697,27 +7707,27 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28615 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Execution mode: llap @@ -7777,24 +7787,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src5 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 26255 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 8811 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 2134 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 2134 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: true @@ -7855,27 +7865,27 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28615 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Execution mode: llap @@ -7935,27 +7945,27 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src4 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28615 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Execution mode: llap @@ -8020,18 +8030,18 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 51 Data size: 244 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 2134 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 154 Data size: 738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 5828 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 154 Data size: 738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 5828 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Reducer 3 @@ -8042,18 +8052,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Reducer 5 @@ -8064,18 +8074,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 154 Data size: 738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 5828 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 154 Data size: 738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 5828 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Reducer 7 @@ -8086,13 +8096,13 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 77 Data size: 369 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 5828 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 77 Data size: 369 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 5828 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -8189,7 +8199,7 @@ STAGE PLANS: Edges: Map 1 <- Union 2 (CONTAINS) Map 6 <- Union 2 (CONTAINS) - Map 7 <- Map 8 (BROADCAST_EDGE), Union 4 (CONTAINS) + Map 8 <- Map 7 (BROADCAST_EDGE), Union 4 (CONTAINS) Reducer 3 <- Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) Reducer 5 <- Union 4 (SIMPLE_EDGE) #### A masked pattern was here #### @@ -8198,27 +8208,27 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28615 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Execution mode: llap @@ -8278,27 +8288,27 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28615 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Execution mode: llap @@ -8358,45 +8368,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 26255 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 8811 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - Estimated key counts: Map 8 => 103 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - input vertices: - 1 Map 8 - Position of Big Table: 0 - Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: bigint) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 216 Data size: 1037 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: bigint) - null sort order: aa - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 216 Data size: 1037 Basic stats: COMPLETE Column stats: NONE - tag: -1 - auto parallelism: true + Statistics: Num rows: 103 Data size: 8811 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 103 Data size: 8811 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + auto parallelism: true Execution mode: llap LLAP IO: no inputs Path -> Alias: @@ -8454,25 +8443,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28615 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: _col1 (type: bigint) - auto parallelism: true + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Estimated key counts: Map 7 => 103 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2 + input vertices: + 0 Map 7 + Position of Big Table: 1 + Statistics: Num rows: 505 Data size: 48597 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 505 Data size: 48597 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col1 (type: bigint) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 304 Data size: 29100 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: bigint) + null sort order: aa + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) + Statistics: Num rows: 304 Data size: 29100 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: true Execution mode: llap LLAP IO: no inputs Path -> Alias: @@ -8534,18 +8543,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 216 Data size: 1037 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 304 Data size: 29100 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 216 Data size: 1037 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 304 Data size: 29100 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Reducer 5 @@ -8556,13 +8565,13 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 108 Data size: 518 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 304 Data size: 29100 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 108 Data size: 518 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 304 Data size: 29100 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -8661,27 +8670,27 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28615 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Execution mode: llap @@ -8741,27 +8750,27 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28615 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Execution mode: llap @@ -8821,16 +8830,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 26255 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 8811 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 8811 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -8842,19 +8851,19 @@ STAGE PLANS: input vertices: 1 Map 9 Position of Big Table: 0 - Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 505 Data size: 44589 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 2134 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 2134 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: true @@ -8915,22 +8924,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 26255 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 8811 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 8811 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 8811 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 auto parallelism: true Execution mode: llap @@ -8994,18 +9003,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 9603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 159 Data size: 763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 5820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 159 Data size: 763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 5820 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Reducer 5 @@ -9016,13 +9025,13 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 79 Data size: 379 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 5820 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 79 Data size: 379 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 5820 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -9048,18 +9057,18 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 56 Data size: 269 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 2037 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 159 Data size: 763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 5820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 159 Data size: 763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 5820 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Union 2 @@ -9197,54 +9206,54 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 375 Data size: 66750 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 300 Data size: 53820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 375 Data size: 66750 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 300 Data size: 53820 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 90040 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 84728 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 84728 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 84728 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 7 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 90040 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 84728 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 84728 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 84728 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -9254,20 +9263,20 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 375 Data size: 66750 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 300 Data size: 53820 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 375 Data size: 69750 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 300 Data size: 56220 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: bigint), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 375 Data size: 69750 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 300 Data size: 56220 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 375 Data size: 69750 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 300 Data size: 56220 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -9280,30 +9289,30 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 84728 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 84728 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101 Data size: 8633 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101 Data size: 17266 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 375 Data size: 66750 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 300 Data size: 53820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 375 Data size: 66750 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 300 Data size: 53820 Basic stats: COMPLETE Column stats: COMPLETE Union 2 Vertex: Union 2 Union 5 @@ -10647,109 +10656,117 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 2 <- Union 3 (CONTAINS) - Map 5 <- Union 3 (CONTAINS) - Reducer 4 <- Map 1 (BROADCAST_EDGE), Union 3 (SIMPLE_EDGE) + Map 3 <- Union 4 (CONTAINS) + Map 6 <- Union 4 (CONTAINS) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) + Reducer 5 <- Union 4 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 97.0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21182 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21182 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21182 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 2 + Map 3 Map Operator Tree: TableScan alias: dim_pho - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 84728 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 97.0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 5 + Map 6 Map Operator Tree: TableScan alias: jackson_sev_add - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 84728 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 97.0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Reducer 4 + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 1250 Data size: 220364 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1250 Data size: 220364 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1250 Data size: 220364 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 Execution mode: llap Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - input vertices: - 0 Map 1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Union 3 - Vertex: Union 3 + Statistics: Num rows: 250 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Union 4 + Vertex: Union 4 Stage: Stage-0 Fetch Operator @@ -12014,42 +12031,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 5 Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -12059,24 +12076,24 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -12085,18 +12102,18 @@ STAGE PLANS: Select Operator expressions: _col1 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 4 Execution mode: llap @@ -12106,14 +12123,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -12274,22 +12291,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -12297,22 +12314,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -12324,17 +12341,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: @@ -12342,31 +12359,31 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 5 Execution mode: llap Reduce Operator Tree: Forward - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -12377,14 +12394,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -12398,17 +12415,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Union 3 Vertex: Union 3 @@ -12606,22 +12623,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -12629,21 +12646,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 6 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), cnt (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -12654,17 +12671,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: @@ -12672,34 +12689,34 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Reducer 5 Execution mode: llap Reduce Operator Tree: Forward - Statistics: Num rows: 5 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -12710,14 +12727,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -12887,42 +12904,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(key) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(UDFToLong(key)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -12932,10 +12949,10 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -13001,14 +13018,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -13018,61 +13035,61 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(UDFToLong(_col0)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 5 Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(key) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -13082,10 +13099,10 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -13151,35 +13168,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(key) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -13189,40 +13206,40 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(UDFToLong(_col0)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 5 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -13232,10 +13249,10 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -13301,14 +13318,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -13318,61 +13335,61 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 4 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 8900 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(UDFToLong(_col0)) (type: double), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4850 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: double), _col1 (type: string) - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 5 Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(key) (type: double), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: double), _col1 (type: string) - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -13382,10 +13399,10 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -13451,35 +13468,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(key) (type: double), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: double), _col1 (type: string) - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -13489,40 +13506,40 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 5 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 8900 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(UDFToLong(_col0)) (type: double), UDFToString(CAST( _col1 AS varchar(20))) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9600 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: double), _col1 (type: string) - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 5 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -13532,10 +13549,10 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -14059,14 +14076,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src10_1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -14076,78 +14093,78 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 4 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 8900 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 21 Data size: 218 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 21 Data size: 218 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: src10_2 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 5 Map Operator Tree: TableScan alias: src10_3 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 8 Map Operator Tree: TableScan alias: src10_4 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 3 @@ -14157,10 +14174,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 103 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 103 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -14172,17 +14189,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 21 Data size: 218 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 21 Data size: 218 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Union 2 Vertex: Union 2 Union 6 @@ -14260,19 +14277,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src10_1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -14280,61 +14297,61 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src10_2 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 6 Map Operator Tree: TableScan alias: src10_3 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 9 Map Operator Tree: TableScan alias: src10_4 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -14347,17 +14364,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 8900 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 21 Data size: 218 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 21 Data size: 218 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: @@ -14365,10 +14382,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 103 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 103 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -14380,17 +14397,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 21 Data size: 218 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 21 Data size: 218 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Union 3 Vertex: Union 3 Union 7 diff --git a/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out index b4386c8673..a8daa25c60 100644 --- a/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out @@ -68,32 +68,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -104,10 +104,10 @@ STAGE PLANS: projectedOutputColumns: null mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -132,13 +132,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -206,25 +206,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -232,7 +232,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: groupByMode: HASH @@ -243,12 +243,12 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap Reducer 2 Execution mode: vectorized, llap @@ -272,13 +272,13 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator Select Vectorization: className: VectorSelectOperator native: true projectedOutputColumns: [] - Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -291,14 +291,14 @@ STAGE PLANS: projectedOutputColumns: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -322,13 +322,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -421,25 +421,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -447,7 +447,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -459,37 +459,37 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap Map 5 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -497,7 +497,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -509,12 +509,12 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap Reducer 2 @@ -541,7 +541,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -550,7 +550,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap @@ -562,14 +562,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 5 Data size: 511 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 511 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 511 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -598,7 +598,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -607,7 +607,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -694,32 +694,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -730,10 +730,10 @@ STAGE PLANS: projectedOutputColumns: null mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -758,13 +758,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -839,32 +839,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -875,10 +875,10 @@ STAGE PLANS: projectedOutputColumns: null mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -903,13 +903,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1008,32 +1008,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -1044,10 +1044,10 @@ STAGE PLANS: projectedOutputColumns: null mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -1072,13 +1072,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1165,32 +1165,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -1201,10 +1201,10 @@ STAGE PLANS: projectedOutputColumns: null mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -1229,13 +1229,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1301,7 +1301,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1] @@ -1311,7 +1311,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0) -> boolean predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (key + 1) (type: int) outputColumnNames: _col0 @@ -1320,7 +1320,7 @@ STAGE PLANS: native: true projectedOutputColumns: [2] selectExpressions: LongColAddLongScalar(col 0, val 1) -> 2:long - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -1329,7 +1329,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -1344,7 +1344,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1] @@ -1354,7 +1354,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0) -> boolean predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (key + 1) (type: int) outputColumnNames: _col0 @@ -1363,7 +1363,7 @@ STAGE PLANS: native: true projectedOutputColumns: [2] selectExpressions: LongColAddLongScalar(col 0, val 1) -> 2:long - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -1372,7 +1372,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -1392,7 +1392,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -1403,10 +1403,10 @@ STAGE PLANS: projectedOutputColumns: null mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1430,13 +1430,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1497,32 +1497,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -1533,10 +1533,10 @@ STAGE PLANS: projectedOutputColumns: null mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -1561,13 +1561,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1634,36 +1634,36 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -1672,7 +1672,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Statistics: Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -1683,10 +1683,10 @@ STAGE PLANS: projectedOutputColumns: null mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -1711,13 +1711,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1800,32 +1800,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -1836,10 +1836,10 @@ STAGE PLANS: projectedOutputColumns: null mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -1864,13 +1864,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1964,25 +1964,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -1990,18 +1990,18 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4650 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4650 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2009,7 +2009,7 @@ STAGE PLANS: name: default.dest1 File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9100 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2185,25 +2185,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -2211,10 +2211,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4650 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4650 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2223,7 +2223,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4650 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -2235,12 +2235,12 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: llap Reducer 2 @@ -2267,7 +2267,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 @@ -2275,13 +2275,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1] - Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out b/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out index d45a15ffb8..707d66a568 100644 --- a/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out @@ -1252,7 +1252,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: web_sales - Statistics: Num rows: 2000 Data size: 3520000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 3511604 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33] @@ -1263,7 +1263,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [16] - Statistics: Num rows: 2000 Data size: 3520000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 3511604 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -1276,7 +1276,7 @@ STAGE PLANS: keys: ws_order_number (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 3520000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -1285,7 +1285,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2000 Data size: 3520000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -1318,7 +1318,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 1760000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) Group By Vectorization: @@ -1331,14 +1331,14 @@ STAGE PLANS: projectedOutputColumns: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1362,13 +1362,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vector_mr_diff_schema_alias.q.out b/ql/src/test/results/clientpositive/llap/vector_mr_diff_schema_alias.q.out index 03c6d3fe54..0aec7bdd55 100644 --- a/ql/src/test/results/clientpositive/llap/vector_mr_diff_schema_alias.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_mr_diff_schema_alias.q.out @@ -255,20 +255,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: store_sales - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_store_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_store_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: PARTIAL - value expressions: _col0 (type: int) + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int) Execution mode: vectorized, llap LLAP IO: unknown Map Vectorization: @@ -280,21 +280,20 @@ STAGE PLANS: Map 6 Map Operator Tree: TableScan - alias: store - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + alias: date_dim + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_state) IN ('KS', 'AL', 'MN', 'SC', 'VT') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + predicate: d_date_sk is not null (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int), s_state (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -308,20 +307,21 @@ STAGE PLANS: Map 7 Map Operator Tree: TableScan - alias: date_dim - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + alias: store + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: d_date_sk is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + predicate: ((s_state) IN ('KS', 'AL', 'MN', 'SC', 'VT') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + expressions: s_store_sk (type: int), s_state (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -339,16 +339,15 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: string) + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -356,21 +355,21 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col3 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col4 + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - keys: _col3 (type: string) + keys: _col4 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Reducer 4 @@ -388,11 +387,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Reducer 5 @@ -408,13 +407,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vector_partition_diff_num_cols.q.out b/ql/src/test/results/clientpositive/llap/vector_partition_diff_num_cols.q.out index 4683b4bb62..b4a7a5cda2 100644 --- a/ql/src/test/results/clientpositive/llap/vector_partition_diff_num_cols.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_partition_diff_num_cols.q.out @@ -98,7 +98,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inventory_part_0 - Statistics: Num rows: 200 Data size: 4776 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 3940 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4] @@ -109,7 +109,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [3] - Statistics: Num rows: 200 Data size: 4776 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 3940 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(inv_quantity_on_hand) Group By Vectorization: @@ -122,14 +122,14 @@ STAGE PLANS: projectedOutputColumns: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -163,13 +163,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -271,7 +271,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inventory_part_1 - Statistics: Num rows: 200 Data size: 13476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 12640 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -282,7 +282,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [3] - Statistics: Num rows: 200 Data size: 13476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 12640 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(inv_quantity_on_hand) Group By Vectorization: @@ -295,14 +295,14 @@ STAGE PLANS: projectedOutputColumns: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -336,13 +336,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -444,7 +444,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inventory_part_2a - Statistics: Num rows: 200 Data size: 4776 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 3940 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4] @@ -455,7 +455,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [3] - Statistics: Num rows: 200 Data size: 4776 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 3940 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(inv_quantity_on_hand) Group By Vectorization: @@ -468,14 +468,14 @@ STAGE PLANS: projectedOutputColumns: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -509,13 +509,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -604,7 +604,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inventory_part_2b - Statistics: Num rows: 200 Data size: 4776 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 3940 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -615,7 +615,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [3] - Statistics: Num rows: 200 Data size: 4776 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 3940 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(inv_quantity_on_hand) Group By Vectorization: @@ -628,14 +628,14 @@ STAGE PLANS: projectedOutputColumns: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -669,13 +669,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -764,7 +764,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inventory_part_3 - Statistics: Num rows: 200 Data size: 4776 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 3940 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4] @@ -775,7 +775,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [3] - Statistics: Num rows: 200 Data size: 4776 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 3940 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(inv_quantity_on_hand) Group By Vectorization: @@ -788,14 +788,14 @@ STAGE PLANS: projectedOutputColumns: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -829,13 +829,13 @@ STAGE PLANS: projectedOutputColumns: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out index c5f7128d9d..ae2d01dc71 100644 --- a/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out @@ -271,7 +271,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_orc - Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 37224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -282,7 +282,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 37224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: int), _col2 (type: date) sort order: ++ @@ -290,7 +290,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 37224 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: timestamp), _col4 (type: float) Execution mode: vectorized, llap @@ -320,13 +320,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 3, 1, 4, 5, 0] - Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 37224 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: int), _col2 (type: date) sort order: ++ @@ -334,7 +334,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: timestamp), _col4 (type: float) Reducer 3 @@ -354,19 +354,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 3, 1, 4, 5, 0] - Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -437,7 +437,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_orc - Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -448,7 +448,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2] - Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -463,7 +463,7 @@ STAGE PLANS: keys: fl_date (type: date) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 1792 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -472,7 +472,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 1792 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -508,13 +508,13 @@ STAGE PLANS: keys: KEY._col0 (type: date) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 68 Data size: 19584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 1792 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 68 Data size: 19584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 1792 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -948,7 +948,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_orc_partitioned_date - Statistics: Num rows: 137 Data size: 39448 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 69280 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -959,13 +959,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 37504 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 37504 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1183,7 +1183,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_orc_partitioned_date - Statistics: Num rows: 137 Data size: 39448 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 69280 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -1194,7 +1194,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 39448 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 69280 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: date) sort order: ++ @@ -1202,7 +1202,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 137 Data size: 39448 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 69280 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: timestamp), _col3 (type: float) Execution mode: vectorized, llap @@ -1232,13 +1232,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 37504 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 1400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: date) sort order: ++ @@ -1246,7 +1246,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 25 Data size: 1400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: timestamp), _col3 (type: float) Reducer 3 @@ -1266,19 +1266,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 25 Data size: 1400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 1400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 1400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1908,7 +1908,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_orc_partitioned_timestamp - Statistics: Num rows: 137 Data size: 39448 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 71392 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -1919,13 +1919,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 5480 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 37424 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 137 Data size: 5480 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 37424 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2143,7 +2143,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_orc_partitioned_timestamp - Statistics: Num rows: 137 Data size: 39448 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 71392 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -2154,7 +2154,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 39448 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 71392 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: timestamp) sort order: ++ @@ -2162,7 +2162,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 137 Data size: 39448 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 71392 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: date), _col3 (type: float) Execution mode: vectorized, llap @@ -2192,13 +2192,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 137 Data size: 5480 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 37424 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 1000 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: timestamp) sort order: ++ @@ -2206,7 +2206,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 25 Data size: 1000 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: date), _col3 (type: float) Reducer 3 @@ -2226,19 +2226,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 25 Data size: 1000 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 1000 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 1000 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2711,7 +2711,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_parquet - Statistics: Num rows: 137 Data size: 822 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 37224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -2722,7 +2722,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 822 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 37224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: int), _col2 (type: date) sort order: ++ @@ -2730,7 +2730,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 137 Data size: 822 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 37224 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: timestamp), _col4 (type: float) Execution mode: vectorized, llap @@ -2760,13 +2760,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 3, 1, 4, 5, 0] - Statistics: Num rows: 137 Data size: 822 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 37224 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: int), _col2 (type: date) sort order: ++ @@ -2774,7 +2774,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 25 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: timestamp), _col4 (type: float) Reducer 3 @@ -2794,19 +2794,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 3, 1, 4, 5, 0] - Statistics: Num rows: 25 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2877,7 +2877,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_parquet - Statistics: Num rows: 137 Data size: 822 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -2888,7 +2888,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2] - Statistics: Num rows: 137 Data size: 822 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -2903,7 +2903,7 @@ STAGE PLANS: keys: fl_date (type: date) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 822 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 1792 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -2912,7 +2912,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 137 Data size: 822 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 1792 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -2948,13 +2948,13 @@ STAGE PLANS: keys: KEY._col0 (type: date) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 68 Data size: 408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 1792 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 68 Data size: 408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 1792 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3388,7 +3388,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_parquet_partitioned_date - Statistics: Num rows: 137 Data size: 8357 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 38189 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -3399,13 +3399,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 37504 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 37504 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3623,7 +3623,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_parquet_partitioned_date - Statistics: Num rows: 137 Data size: 8357 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 38189 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -3634,7 +3634,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 8357 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 38189 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: date) sort order: ++ @@ -3642,7 +3642,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 137 Data size: 8357 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 38189 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: timestamp), _col3 (type: float) Execution mode: vectorized, llap @@ -3672,13 +3672,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 37504 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 1400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: date) sort order: ++ @@ -3686,7 +3686,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 25 Data size: 1400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: timestamp), _col3 (type: float) Reducer 3 @@ -3706,19 +3706,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 25 Data size: 1400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 1400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 1400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4348,7 +4348,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_parquet_partitioned_timestamp - Statistics: Num rows: 137 Data size: 6165 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 38109 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -4359,13 +4359,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 5480 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 37424 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 137 Data size: 5480 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 37424 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4583,7 +4583,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_parquet_partitioned_timestamp - Statistics: Num rows: 137 Data size: 6165 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 38109 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] @@ -4594,7 +4594,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 6165 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 38109 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: timestamp) sort order: ++ @@ -4602,7 +4602,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 137 Data size: 6165 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 38109 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: date), _col3 (type: float) Execution mode: vectorized, llap @@ -4632,13 +4632,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 137 Data size: 5480 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 37424 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 1000 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: timestamp) sort order: ++ @@ -4646,7 +4646,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 25 Data size: 1000 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: date), _col3 (type: float) Reducer 3 @@ -4666,19 +4666,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 25 Data size: 1000 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 1000 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 1000 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7050 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorized_context.q.out b/ql/src/test/results/clientpositive/llap/vectorized_context.q.out index 855a50f91c..b067cad0c9 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_context.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_context.q.out @@ -109,79 +109,51 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 2 <- Map 1 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE) + Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: store_sales - Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_store_sk is not null and ss_hdemo_sk is not null) (type: boolean) - Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_store_sk (type: int), ss_hdemo_sk (type: int), ss_net_profit (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: double) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Map 2 - Map Operator Tree: - TableScan - alias: store - Statistics: Num rows: 6075 Data size: 615632 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + Statistics: Num rows: 6075 Data size: 23092 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 6075 Data size: 615632 Basic stats: COMPLETE Column stats: NONE + predicate: hd_demo_sk is not null (type: boolean) + Statistics: Num rows: 5772 Data size: 21940 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int), s_city (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6075 Data size: 615632 Basic stats: COMPLETE Column stats: NONE + expressions: hd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 5772 Data size: 21940 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col4 + 1 _col1 (type: int) + outputColumnNames: _col1, _col3 input vertices: - 0 Map 1 - Statistics: Num rows: 6682 Data size: 80009 Basic stats: COMPLETE Column stats: NONE + 1 Map 2 + Statistics: Num rows: 27405 Data size: 325584 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col4 + outputColumnNames: _col3, _col5 input vertices: 1 Map 3 - Statistics: Num rows: 7350 Data size: 88009 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136953 Data size: 13256714 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col4 (type: string), _col2 (type: double) + expressions: _col5 (type: string), _col3 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 7350 Data size: 88009 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136953 Data size: 13256714 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9700 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9700 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -196,23 +168,52 @@ STAGE PLANS: allNative: false usesVectorUDFAdaptor: false vectorized: true + Map 2 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 6075 Data size: 92368 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_store_sk is not null and ss_hdemo_sk is not null) (type: boolean) + Statistics: Num rows: 5484 Data size: 83376 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_store_sk (type: int), ss_hdemo_sk (type: int), ss_net_profit (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5484 Data size: 83376 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 5484 Data size: 83376 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true Map 3 Map Operator Tree: TableScan - alias: household_demographics - Statistics: Num rows: 6075 Data size: 24300 Basic stats: COMPLETE Column stats: NONE + alias: store + Statistics: Num rows: 6075 Data size: 536889 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: hd_demo_sk is not null (type: boolean) - Statistics: Num rows: 6075 Data size: 24300 Basic stats: COMPLETE Column stats: NONE + predicate: s_store_sk is not null (type: boolean) + Statistics: Num rows: 5772 Data size: 510105 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 6075 Data size: 24300 Basic stats: COMPLETE Column stats: NONE + expressions: s_store_sk (type: int), s_city (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5772 Data size: 510105 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6075 Data size: 24300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5772 Data size: 510105 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out index 690cab80d2..fc24bbf0f1 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out @@ -268,33 +268,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -315,15 +315,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -339,10 +339,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -424,19 +424,19 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -456,15 +456,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -480,10 +480,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -581,33 +581,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -624,33 +624,33 @@ STAGE PLANS: TableScan alias: srcpart_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -672,12 +672,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -687,15 +687,15 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2420 Data size: 890560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -711,10 +711,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -804,19 +804,19 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -832,19 +832,19 @@ STAGE PLANS: TableScan alias: srcpart_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -865,12 +865,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -880,15 +880,15 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2420 Data size: 890560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -904,10 +904,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1003,48 +1003,48 @@ STAGE PLANS: TableScan alias: srcpart_date_hour filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Select Operator expressions: _col2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -1065,15 +1065,15 @@ STAGE PLANS: keys: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1089,10 +1089,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1174,19 +1174,19 @@ STAGE PLANS: TableScan alias: srcpart_date_hour filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -1206,15 +1206,15 @@ STAGE PLANS: keys: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1230,10 +1230,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1326,33 +1326,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -1373,15 +1373,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1397,10 +1397,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1482,19 +1482,19 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -1514,15 +1514,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1538,10 +1538,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1632,33 +1632,33 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -1679,15 +1679,15 @@ STAGE PLANS: keys: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1703,10 +1703,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1788,33 +1788,33 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: (UDFToDouble(hr) * 2.0) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -1835,15 +1835,15 @@ STAGE PLANS: keys: 0 (UDFToDouble(_col0) * 2.0) (type: double) 1 _col0 (type: double) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1859,10 +1859,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1944,19 +1944,19 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -1976,15 +1976,15 @@ STAGE PLANS: keys: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2000,10 +2000,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2085,19 +2085,19 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -2117,15 +2117,15 @@ STAGE PLANS: keys: 0 (UDFToDouble(_col0) * 2.0) (type: double) 1 _col0 (type: double) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2141,10 +2141,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2239,33 +2239,33 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToString(_col0) (type: string) sort order: + Map-reduce partition columns: UDFToString(_col0) (type: string) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToString(_col0) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: UDFToString((UDFToDouble(hr) * 2.0)) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -2286,15 +2286,15 @@ STAGE PLANS: keys: 0 UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) 1 UDFToString(_col0) (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2310,10 +2310,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2556,17 +2556,17 @@ STAGE PLANS: TableScan alias: srcpart_date_hour filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2589,17 +2589,17 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col4 residual filter predicates: {((_col0 = _col2) or (_col1 = _col4))} - Statistics: Num rows: 2000 Data size: 1458000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4000 Data size: 2184000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 2000 Data size: 1458000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4000 Data size: 2184000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2615,10 +2615,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2700,48 +2700,48 @@ STAGE PLANS: TableScan alias: srcpart_date_hour filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Select Operator expressions: _col2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -2762,15 +2762,15 @@ STAGE PLANS: keys: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2786,10 +2786,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2871,33 +2871,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -2918,15 +2918,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2942,10 +2942,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2983,33 +2983,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 4 Execution mode: vectorized, llap LLAP IO: all inputs @@ -3054,15 +3054,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -3078,10 +3078,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3143,33 +3143,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -3190,15 +3190,15 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -3214,10 +3214,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3283,33 +3283,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -3326,33 +3326,33 @@ STAGE PLANS: TableScan alias: srcpart_hour filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) - Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -3374,12 +3374,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 1100 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1100 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -3389,15 +3389,15 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1210 Data size: 445280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -3413,10 +3413,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3466,84 +3466,86 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Map 7 <- Reducer 5 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: srcpart - filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE + alias: srcpart_hour + filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean) + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (UDFToDouble(hr) = 13.0) (type: boolean) + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap - LLAP IO: unknown + LLAP IO: all inputs Map Vectorization: enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat allNative: true usesVectorUDFAdaptor: true vectorized: true - Map 5 + Map 6 Map Operator Tree: TableScan - alias: srcpart_date - filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + alias: srcpart + filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) Execution mode: vectorized, llap - LLAP IO: all inputs + LLAP IO: unknown Map Vectorization: enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat allNative: true - usesVectorUDFAdaptor: false + usesVectorUDFAdaptor: true vectorized: true - Map 6 + Map 7 Map Operator Tree: TableScan - alias: srcpart_hour - filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean) - Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE + alias: srcpart_date + filterExpr: ((date = '2008-04-08') and ds is not null and (ds BETWEEN DynamicValue(RS_12_srcpart_ds_min) AND DynamicValue(RS_12_srcpart_ds_max) and in_bloom_filter(ds, DynamicValue(RS_12_srcpart_ds_bloom_filter)))) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (UDFToDouble(hr) = 13.0) (type: boolean) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + predicate: ((date = '2008-04-08') and ds is not null and (ds BETWEEN DynamicValue(RS_12_srcpart_ds_min) AND DynamicValue(RS_12_srcpart_ds_max) and in_bloom_filter(ds, DynamicValue(RS_12_srcpart_ds_bloom_filter)))) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hr (type: string) + expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -3552,7 +3554,7 @@ STAGE PLANS: groupByVectorOutput: true inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat allNative: true - usesVectorUDFAdaptor: true + usesVectorUDFAdaptor: false vectorized: true Reducer 2 Execution mode: llap @@ -3562,14 +3564,27 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: string) - 1 _col0 (type: string) + 1 _col1 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=2) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -3579,15 +3594,15 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -3603,14 +3618,33 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + groupByVectorOutput: true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=2) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) Stage: Stage-0 Fetch Operator @@ -4526,15 +4560,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -4551,33 +4585,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -4603,10 +4637,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4691,7 +4725,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -4700,15 +4734,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 1 Map 4 - Statistics: Num rows: 2420 Data size: 890560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -4725,33 +4759,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -4768,33 +4802,33 @@ STAGE PLANS: TableScan alias: srcpart_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -4820,10 +4854,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4907,15 +4941,15 @@ STAGE PLANS: 1 _col0 (type: string), _col2 (type: string) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -4932,48 +4966,48 @@ STAGE PLANS: TableScan alias: srcpart_date_hour filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Select Operator expressions: _col2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 361 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -4999,10 +5033,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5083,15 +5117,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -5108,33 +5142,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 370 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -5160,10 +5194,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5233,15 +5267,15 @@ STAGE PLANS: 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -5258,33 +5292,33 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -5310,10 +5344,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5383,15 +5417,15 @@ STAGE PLANS: 1 _col0 (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -5408,33 +5442,33 @@ STAGE PLANS: TableScan alias: srcpart_double_hour filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: (UDFToDouble(hr) * 2.0) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -5460,10 +5494,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5708,15 +5742,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -5733,33 +5767,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -5785,10 +5819,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5826,14 +5860,14 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -5842,15 +5876,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -5900,10 +5934,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5965,14 +5999,14 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (date = '2008-04-08') (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -5981,15 +6015,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 0 Map 1 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -6015,10 +6049,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -6071,7 +6105,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 3 - Statistics: Num rows: 1100 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -6080,15 +6114,15 @@ STAGE PLANS: 1 _col0 (type: string) input vertices: 1 Map 4 - Statistics: Num rows: 1210 Data size: 445280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -6105,33 +6139,33 @@ STAGE PLANS: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -6148,33 +6182,33 @@ STAGE PLANS: TableScan alias: srcpart_hour filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) - Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (string) Target Input: srcpart Partition key expr: hr - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -6200,10 +6234,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -6253,13 +6287,52 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 2 <- Map 1 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) - Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) + Map 1 <- Map 2 (BROADCAST_EDGE) + Map 3 <- Map 1 (BROADCAST_EDGE) + Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan + alias: srcpart_hour + filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean) + Statistics: Num rows: 2 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(hr) = 13.0) (type: boolean) + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col1 + input vertices: + 1 Map 2 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + groupByVectorOutput: true + inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + allNative: true + usesVectorUDFAdaptor: true + vectorized: true + Map 2 + Map Operator Tree: + TableScan alias: srcpart filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE @@ -6271,11 +6344,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: unknown Map Vectorization: @@ -6284,47 +6357,37 @@ STAGE PLANS: allNative: true usesVectorUDFAdaptor: true vectorized: true - Map 2 + Map 3 Map Operator Tree: TableScan alias: srcpart_date filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) - outputColumnNames: _col1 input vertices: 0 Map 1 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - input vertices: - 1 Map 4 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -6335,35 +6398,7 @@ STAGE PLANS: allNative: false usesVectorUDFAdaptor: false vectorized: true - Map 4 - Map Operator Tree: - TableScan - alias: srcpart_hour - filterExpr: (UDFToDouble(hr) = 13.0) (type: boolean) - Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) = 13.0) (type: boolean) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: true - vectorized: true - Reducer 3 + Reducer 4 Execution mode: vectorized, llap Reduce Vectorization: enabled: true @@ -6377,10 +6412,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -6734,15 +6769,15 @@ STAGE PLANS: 1 _col0 (type: string), UDFToDouble(_col2) (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 413600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: all inputs @@ -6751,48 +6786,48 @@ STAGE PLANS: TableScan alias: srcpart_date_hour filterExpr: (((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), UDFToDouble(_col2) (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: string), UDFToDouble(_col2) (type: double) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart_orc Partition key expr: ds - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Select Operator expressions: UDFToDouble(_col2) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: hr (int) Target Input: srcpart_orc Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 1 Execution mode: llap LLAP IO: all inputs @@ -6803,10 +6838,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/merge_join_1.q.out b/ql/src/test/results/clientpositive/merge_join_1.q.out index 4d2c4cf0f4..8a2dd1d046 100644 --- a/ql/src/test/results/clientpositive/merge_join_1.q.out +++ b/ql/src/test/results/clientpositive/merge_join_1.q.out @@ -86,34 +86,34 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col0 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col0 (type: string) + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) TableScan - alias: test_join_1 + alias: test_join_2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (a is not null and b is not null) (type: boolean) + predicate: a is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: a (type: string), b (type: string) - outputColumnNames: _col0, _col1 + expressions: a (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: string) - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: string) + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col0 (type: string) - 1 _col1 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -127,42 +127,46 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + key expressions: _col0 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) + value expressions: _col1 (type: string), _col2 (type: string) TableScan - alias: test_join_2 + alias: test_join_1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: a is not null (type: boolean) + predicate: (a is not null and b is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: a (type: string) - outputColumnNames: _col0 + expressions: a (type: string), b (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + key expressions: _col1 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 _col0 (type: string), _col0 (type: string) + 1 _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/mergejoin.q.out b/ql/src/test/results/clientpositive/mergejoin.q.out index 1961d83c68..ff5be66aeb 100644 --- a/ql/src/test/results/clientpositive/mergejoin.q.out +++ b/ql/src/test/results/clientpositive/mergejoin.q.out @@ -1659,36 +1659,36 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 242 Data size: 22748 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 242 Data size: 22748 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE + alias: c + filterExpr: value is not null (type: boolean) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE + predicate: value is not null (type: boolean) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) + expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 51700 Basic stats: COMPLETE Column stats: NONE + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 266 Data size: 25022 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1701,34 +1701,34 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 550 Data size: 51700 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 266 Data size: 25022 Basic stats: COMPLETE Column stats: NONE TableScan - alias: c - filterExpr: value is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) + expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 605 Data size: 56870 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 550 Data size: 51700 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -2195,36 +2195,36 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 242 Data size: 22748 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 242 Data size: 22748 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE + alias: c + filterExpr: value is not null (type: boolean) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE + predicate: value is not null (type: boolean) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) + expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 51700 Basic stats: COMPLETE Column stats: NONE + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 266 Data size: 25022 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2237,34 +2237,34 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 550 Data size: 51700 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 266 Data size: 25022 Basic stats: COMPLETE Column stats: NONE TableScan - alias: c - filterExpr: value is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) + expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 47000 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 605 Data size: 56870 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 550 Data size: 51700 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/mergejoins_mixed.q.out b/ql/src/test/results/clientpositive/mergejoins_mixed.q.out index e1125e9cb8..a5cc23ae9f 100644 --- a/ql/src/test/results/clientpositive/mergejoins_mixed.q.out +++ b/ql/src/test/results/clientpositive/mergejoins_mixed.q.out @@ -420,7 +420,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 @@ -458,33 +459,15 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) - TableScan - alias: d - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Left Outer Join 0 to 2 keys: 0 _col0 (type: string) 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false table: @@ -500,8 +483,8 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) TableScan alias: c Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -522,19 +505,57 @@ STAGE PLANS: keys: 0 _col3 (type: string) 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + TableScan + alias: d + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string), _col4 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -551,7 +572,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 @@ -589,8 +611,34 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: TableScan - alias: d + Reduce Output Operator + key expressions: _col3 (type: string) + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + TableScan + alias: c Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -605,14 +653,12 @@ STAGE PLANS: Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 - Right Outer Join 0 to 2 + Right Outer Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col3 (type: string) 1 _col0 (type: string) - 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false table: @@ -620,18 +666,18 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) TableScan - alias: c + alias: d Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -648,21 +694,17 @@ STAGE PLANS: condition map: Right Outer Join 0 to 1 keys: - 0 _col3 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string), _col4 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -679,7 +721,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 @@ -717,8 +760,34 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: TableScan - alias: d + Reduce Output Operator + key expressions: _col3 (type: string) + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + TableScan + alias: c Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -733,14 +802,12 @@ STAGE PLANS: Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 - Outer Join 0 to 2 + Outer Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col3 (type: string) 1 _col0 (type: string) - 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false table: @@ -748,18 +815,18 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-3 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) TableScan - alias: c + alias: d Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -776,21 +843,17 @@ STAGE PLANS: condition map: Outer Join 0 to 1 keys: - 0 _col3 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string), _col4 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/ppd_join5.q.out b/ql/src/test/results/clientpositive/ppd_join5.q.out index 551769c73a..1cd3a7a423 100644 --- a/ql/src/test/results/clientpositive/ppd_join5.q.out +++ b/ql/src/test/results/clientpositive/ppd_join5.q.out @@ -32,7 +32,7 @@ POSTHOOK: Lineage: t1.id1 SIMPLE [] POSTHOOK: Lineage: t1.id2 SIMPLE [] POSTHOOK: Lineage: t2.d SIMPLE [] POSTHOOK: Lineage: t2.id SIMPLE [] -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select a.*,b.d d1,c.d d2 from t1 a join t2 b on (a.id1 = b.id) @@ -63,35 +63,32 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + sort order: Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) TableScan - alias: b + alias: c Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d <= 1) and id is not null) (type: boolean) + predicate: (d <= 1) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: id (type: string), d (type: int) - outputColumnNames: _col0, _col1 + expressions: d (type: int) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col0 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col0 (type: string) + sort order: Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -104,34 +101,38 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int) + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int) TableScan - alias: c + alias: b Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (d <= 1) (type: boolean) + predicate: ((d <= 1) and id is not null) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: d (type: int) - outputColumnNames: _col0 + expressions: id (type: string), d (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col0 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col0 (type: string) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col3, _col4 + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col4 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int), _col4 (type: int) + expressions: _col0 (type: string), _col1 (type: string), _col4 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -148,7 +149,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from ( select a.*,b.d d1,c.d d2 from @@ -183,35 +184,32 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + sort order: Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) TableScan - alias: b + alias: c Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d <= 1) and id is not null) (type: boolean) + predicate: (d <= 1) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: id (type: string), d (type: int) - outputColumnNames: _col0, _col1 + expressions: d (type: int) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col0 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col0 (type: string) + sort order: Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -224,37 +222,41 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int) + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int) TableScan - alias: c + alias: b Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (d <= 1) (type: boolean) + predicate: ((d <= 1) and id is not null) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: d (type: int) - outputColumnNames: _col0 + expressions: id (type: string), d (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col0 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col0 (type: string) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col3, _col4 + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col4 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col3 > 1) or (_col4 > 1)) (type: boolean) + predicate: ((_col4 > 1) or (_col2 > 1)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int), _col4 (type: int) + expressions: _col0 (type: string), _col1 (type: string), _col4 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -271,7 +273,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select * from ( select a.*,b.d d1,c.d d2 from t1 a join t2 b on (a.id1 = b.id) diff --git a/ql/src/test/results/clientpositive/ppd_outer_join5.q.out b/ql/src/test/results/clientpositive/ppd_outer_join5.q.out index 75b73800ed..84c10828ce 100644 --- a/ql/src/test/results/clientpositive/ppd_outer_join5.q.out +++ b/ql/src/test/results/clientpositive/ppd_outer_join5.q.out @@ -171,27 +171,27 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) TableScan - alias: t2 + alias: t3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (id = 20) (type: boolean) + predicate: (20 = id) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col1, _col2 + expressions: 20 (type: int), key (type: string), value (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: 0 1 - outputColumnNames: _col1, _col2, _col4, _col5 + outputColumnNames: _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -207,32 +207,32 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) TableScan - alias: t3 + alias: t2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (20 = id) (type: boolean) + predicate: (id = 20) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + value expressions: _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Join Operator condition map: - Left Outer Join 0 to 1 + Inner Join 0 to 1 keys: 0 1 - outputColumnNames: _col1, _col2, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col7, _col8 Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 20 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string), _col8 (type: string) + expressions: 20 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col7 (type: string), _col8 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -279,27 +279,27 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) TableScan - alias: t2 + alias: t3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (id = 20) (type: boolean) + predicate: (20 = id) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col1, _col2 + expressions: 20 (type: int), key (type: string), value (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: 0 1 - outputColumnNames: _col1, _col2, _col4, _col5 + outputColumnNames: _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -315,32 +315,32 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) TableScan - alias: t3 + alias: t2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (20 = id) (type: boolean) + predicate: (id = 20) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + value expressions: _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Join Operator condition map: - Left Outer Join 0 to 1 + Inner Join 0 to 1 keys: 0 1 - outputColumnNames: _col1, _col2, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col7, _col8 Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 20 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string), _col8 (type: string) + expressions: 20 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col7 (type: string), _col8 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/ppd_repeated_alias.q.out b/ql/src/test/results/clientpositive/ppd_repeated_alias.q.out index 738424bb5b..c94002f37d 100644 --- a/ql/src/test/results/clientpositive/ppd_repeated_alias.q.out +++ b/ql/src/test/results/clientpositive/ppd_repeated_alias.q.out @@ -257,25 +257,25 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select c.foo, d.bar from (select c.foo, b.bar, c.blah from pokes c left outer join pokes b on c.foo=b.foo) c left outer join pokes d where d.foo=1 and c.bar=2 PREHOOK: type: QUERY POSTHOOK: query: explain select c.foo, d.bar from (select c.foo, b.bar, c.blah from pokes c left outer join pokes b on c.foo=b.foo) c left outer join pokes d where d.foo=1 and c.bar=2 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan - alias: c + alias: b Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: foo is not null (type: boolean) + predicate: ((bar = 2) and foo is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: foo (type: int) @@ -287,10 +287,10 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE TableScan - alias: b + alias: c Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((bar = 2) and foo is not null) (type: boolean) + predicate: foo is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: foo (type: int) @@ -308,24 +308,23 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0 + outputColumnNames: _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col2 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-2 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int) - TableScan alias: d Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -339,6 +338,11 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: int) + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator condition map: @@ -346,10 +350,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col2 + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col2 (type: int) + expressions: _col2 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out b/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out index db98adc55a..c5a95e2d7c 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out @@ -184,15 +184,15 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: smalltable - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + alias: smalltable2 + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -203,15 +203,15 @@ STAGE PLANS: Map 5 Map Operator Tree: TableScan - alias: smalltable2 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + alias: smalltable + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -280,18 +280,22 @@ STAGE PLANS: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) 1 UDFToDouble(_col0) (type: double) 2 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col1, _col3 input vertices: 1 Map 4 2 Map 5 Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out b/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out index 9064cbc4e0..880c9863c3 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out @@ -14,6 +14,7 @@ POSTHOOK: query: load data local inpath '../../data/files/T1.txt' into table sma POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@smalltable +Warning: Map Join MAPJOIN[22][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select src1.key, src2.key, smalltable.key from src src1 JOIN src src2 ON (src1.key = src2.key) JOIN smalltable ON (src1.key + src2.key = smalltable.key) PREHOOK: type: QUERY POSTHOOK: query: explain select src1.key, src2.key, smalltable.key from src src1 JOIN src src2 ON (src1.key = src2.key) JOIN smalltable ON (src1.key + src2.key = smalltable.key) @@ -31,37 +32,37 @@ STAGE PLANS: Map 2 Map Operator Tree: TableScan - alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: smalltable + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 + 1 Local Work: Map Reduce Local Work Map 3 Map Operator Tree: TableScan - alias: smalltable - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + alias: src1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) + 0 _col0 (type: string) + 1 _col0 (type: string) Local Work: Map Reduce Local Work @@ -72,7 +73,7 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) @@ -85,29 +86,36 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 + 1 outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 20812 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 input vertices: 1 Map 3 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 550 Data size: 22893 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(_col2) + UDFToDouble(_col0)) = UDFToDouble(_col1)) (type: boolean) + Statistics: Num rows: 275 Data size: 11446 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: string), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 275 Data size: 11446 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 11446 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -117,6 +125,7 @@ STAGE PLANS: Processor Tree: ListSink +Warning: Map Join MAPJOIN[22][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: select src1.key, src2.key, smalltable.key from src src1 JOIN src src2 ON (src1.key = src2.key) JOIN smalltable ON (src1.key + src2.key = smalltable.key) PREHOOK: type: QUERY PREHOOK: Input: default@smalltable @@ -188,15 +197,15 @@ STAGE PLANS: Map 3 Map Operator Tree: TableScan - alias: smalltable - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + alias: smalltable2 + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -207,15 +216,15 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: smalltable2 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + alias: smalltable + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -258,18 +267,22 @@ STAGE PLANS: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) 1 UDFToDouble(_col0) (type: double) 2 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col1, _col3 input vertices: 1 Map 3 2 Map 4 Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out index 7a2422f528..c26949f13c 100644 --- a/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out @@ -353,7 +353,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out index 8a302b6d0e..4d0476f9ee 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out @@ -504,7 +504,7 @@ STAGE PLANS: 1 Reducer 4 Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2128,7 +2128,7 @@ STAGE PLANS: 1 Reducer 5 Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) + expressions: _col0 (type: int), _col3 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out index 08d115d105..d8a9575857 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out @@ -350,7 +350,7 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 1 + Map 3 Map Operator Tree: TableScan alias: a @@ -390,10 +390,10 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 3 <- Map 2 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 2 + Map 1 Map Operator Tree: TableScan alias: b @@ -411,31 +411,35 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0 + outputColumnNames: _col1 input vertices: - 0 Map 1 + 1 Map 3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 4 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: _col1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 4 + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work - Reducer 3 + Reducer 2 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -503,36 +507,36 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 1 + Map 3 Map Operator Tree: TableScan - alias: d - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + alias: a + Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work - Map 2 + Map 4 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + alias: d + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -543,10 +547,10 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 4 <- Map 3 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 3 + Map 1 Map Operator Tree: TableScan alias: b @@ -564,31 +568,35 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0 + outputColumnNames: _col1 input vertices: - 0 Map 2 + 1 Map 3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - input vertices: - 0 Map 1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: _col1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 4 + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work - Reducer 4 + Reducer 2 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -764,7 +772,7 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 4 + Map 1 Map Operator Tree: TableScan alias: b @@ -778,8 +786,8 @@ STAGE PLANS: Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) - 1 _col0 (type: int) + 0 _col0 (type: int) + 1 _col1 (type: int) Local Work: Map Reduce Local Work @@ -787,7 +795,7 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 3 + Map 4 Map Operator Tree: TableScan alias: tab @@ -809,10 +817,10 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Map 2 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 1 + Map 2 Map Operator Tree: TableScan alias: tab_part @@ -832,7 +840,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2 input vertices: - 1 Map 3 + 1 Map 4 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: int), substr(_col2, 5) (type: string) @@ -852,7 +860,7 @@ STAGE PLANS: value expressions: _col1 (type: double) Local Work: Map Reduce Local Work - Reducer 2 + Reducer 3 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -870,14 +878,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col1, _col2 input vertices: - 1 Map 4 + 0 Map 1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string) + expressions: _col0 (type: int), _col2 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -915,7 +923,7 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 3 + Map 4 Map Operator Tree: TableScan alias: y @@ -937,10 +945,10 @@ STAGE PLANS: Stage: Stage-2 Spark Edges: - Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Map 2 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 1 + Map 2 Map Operator Tree: TableScan alias: x @@ -960,7 +968,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1 input vertices: - 1 Map 3 + 1 Map 4 Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), substr(_col1, 5) (type: string) @@ -980,7 +988,7 @@ STAGE PLANS: value expressions: _col1 (type: double) Local Work: Map Reduce Local Work - Reducer 2 + Reducer 3 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -996,14 +1004,14 @@ STAGE PLANS: Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) - 1 _col0 (type: int) + 0 _col0 (type: int) + 1 _col1 (type: int) Stage: Stage-1 Spark #### A masked pattern was here #### Vertices: - Map 4 + Map 1 Map Operator Tree: TableScan alias: b @@ -1019,14 +1027,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col1, _col2, _col3 input vertices: - 0 Reducer 2 + 1 Reducer 3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string) + expressions: _col3 (type: int), _col2 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1066,14 +1074,14 @@ STAGE PLANS: Map 2 Map Operator Tree: TableScan - alias: b + alias: c Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: int) + outputColumnNames: _col0 Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: @@ -1085,14 +1093,14 @@ STAGE PLANS: Map 3 Map Operator Tree: TableScan - alias: c + alias: b Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: @@ -1126,13 +1134,13 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: _col0, _col1, _col4 input vertices: 1 Map 2 2 Map 3 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) + expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1682,7 +1690,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: string) + 0 _col2 (type: string) 1 _col1 (type: string) Local Work: Map Reduce Local Work @@ -1696,38 +1704,38 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: a + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and value is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) Map 3 Map Operator Tree: TableScan - alias: c + alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Reducer 2 Local Work: Map Reduce Local Work @@ -1738,20 +1746,20 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) + 0 _col2 (type: string) 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + outputColumnNames: _col1, _col3 input vertices: 1 Map 4 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col1 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/spark/column_access_stats.q.out b/ql/src/test/results/clientpositive/spark/column_access_stats.q.out index b1c494cba7..0fdef11025 100644 --- a/ql/src/test/results/clientpositive/spark/column_access_stats.q.out +++ b/ql/src/test/results/clientpositive/spark/column_access_stats.q.out @@ -694,37 +694,37 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + alias: t2 + Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan - alias: t2 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + alias: t1 + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Map 5 Map Operator Tree: TableScan @@ -751,13 +751,17 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0 + outputColumnNames: _col1 Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reducer 3 Reduce Operator Tree: Join Operator @@ -803,10 +807,10 @@ PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 PREHOOK: Input: default@t3 #### A masked pattern was here #### -Table:default@t1 +Table:default@t2 Columns:key -Table:default@t2 +Table:default@t1 Columns:key Table:default@t3 diff --git a/ql/src/test/results/clientpositive/spark/filter_join_breaktask.q.out b/ql/src/test/results/clientpositive/spark/filter_join_breaktask.q.out index 718346f83a..320a52ee3d 100644 --- a/ql/src/test/results/clientpositive/spark/filter_join_breaktask.q.out +++ b/ql/src/test/results/clientpositive/spark/filter_join_breaktask.q.out @@ -43,22 +43,22 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: f + alias: g Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) + predicate: (value <> '') (type: boolean) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) + expressions: value (type: string) outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col0 (type: string) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false @@ -113,7 +113,7 @@ STAGE PLANS: name: default.filter_join_breaktask name: default.filter_join_breaktask Truncated Path -> Alias: - /filter_join_breaktask/ds=2008-04-08 [$hdt$_0:f] + /filter_join_breaktask/ds=2008-04-08 [$hdt$_0:g] Map 4 Map Operator Tree: TableScan @@ -129,13 +129,13 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE tag: 1 - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -192,22 +192,22 @@ STAGE PLANS: Map 5 Map Operator Tree: TableScan - alias: g + alias: f Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (value <> '') (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) + expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col0 (type: int) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE tag: 1 auto parallelism: false @@ -262,7 +262,7 @@ STAGE PLANS: name: default.filter_join_breaktask name: default.filter_join_breaktask Truncated Path -> Alias: - /filter_join_breaktask/ds=2008-04-08 [$hdt$_2:g] + /filter_join_breaktask/ds=2008-04-08 [$hdt$_2:f] Reducer 2 Needs Tagging: true Reduce Operator Tree: @@ -270,18 +270,18 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col3 + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 27 Data size: 232 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: _col2 (type: int) null sort order: a sort order: + - Map-reduce partition columns: _col3 (type: string) + Map-reduce partition columns: _col2 (type: int) Statistics: Num rows: 27 Data size: 232 Basic stats: COMPLETE Column stats: NONE tag: 0 - value expressions: _col0 (type: int) + value expressions: _col0 (type: string) auto parallelism: false Reducer 3 Needs Tagging: true @@ -290,12 +290,12 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: string) - 1 _col0 (type: string) + 0 _col2 (type: int) + 1 _col0 (type: int) outputColumnNames: _col0, _col5 Statistics: Num rows: 29 Data size: 255 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col5 (type: string) + expressions: _col5 (type: int), _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 29 Data size: 255 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/spark/join19.q.out b/ql/src/test/results/clientpositive/spark/join19.q.out index 35d9942cb0..eb55147698 100644 --- a/ql/src/test/results/clientpositive/spark/join19.q.out +++ b/ql/src/test/results/clientpositive/spark/join19.q.out @@ -126,14 +126,34 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2), Map 6 (PARTITION-LEVEL SORT, 2) - Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 2), Map 8 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) - Reducer 4 <- Map 9 (PARTITION-LEVEL SORT, 2), Reducer 3 (PARTITION-LEVEL SORT, 2) + Reducer 10 <- Map 11 (PARTITION-LEVEL SORT, 2), Map 9 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 7 (PARTITION-LEVEL SORT, 2) + Reducer 4 <- Reducer 10 (PARTITION-LEVEL SORT, 2), Reducer 3 (PARTITION-LEVEL SORT, 2) + Reducer 7 <- Map 6 (PARTITION-LEVEL SORT, 2), Map 8 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan + alias: t5 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_to') and subject is not null and object is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: subject (type: string), object (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: string) + Map 11 + Map Operator Tree: + TableScan alias: t1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -151,7 +171,7 @@ STAGE PLANS: Map 5 Map Operator Tree: TableScan - alias: t2 + alias: t6 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__LABEL_REL') and subject is not null) (type: boolean) @@ -179,12 +199,12 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string) - Map 7 + value expressions: _col1 (type: string) + Map 8 Map Operator Tree: TableScan alias: t4 @@ -201,28 +221,10 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Map 8 - Map Operator Tree: - TableScan - alias: t5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Filter Operator - predicate: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_to') and subject is not null and object is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: subject (type: string), object (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string) Map 9 Map Operator Tree: TableScan - alias: t6 + alias: t2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__LABEL_REL') and subject is not null) (type: boolean) @@ -237,63 +239,91 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) - Reducer 2 + Reducer 10 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 _col0 (type: string) 1 _col0 (type: string) - 2 _col1 (type: string) - outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + outputColumnNames: _col1, _col2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col3 (type: string) + key expressions: _col2 (type: string) sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col2 (type: string) - Reducer 3 + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string) + Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 keys: - 0 _col3 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3, _col7 - Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: NONE + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col7 (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col7 (type: string) - Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string) + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string), _col3 (type: string) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col2 (type: string) + outputColumnNames: _col1, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col5 (type: string) + sort order: + + Map-reduce partition columns: _col5 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string) Reducer 4 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col7 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3, _col7, _col9 - Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: NONE + 0 _col5 (type: string) + 1 _col2 (type: string) + outputColumnNames: _col1, _col3, _col4, _col8, _col9 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col7 (type: string), _col9 (type: string) + expressions: _col9 (type: string), _col8 (type: string), _col4 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 7 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out index 40695ef998..dc9b61e39a 100644 --- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out +++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out @@ -74,31 +74,31 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + alias: p2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + predicate: p2_name is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Map 3 Map Operator Tree: TableScan - alias: p2 + alias: p3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p2_name is not null (type: boolean) + predicate: p3_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) + expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator @@ -110,40 +110,44 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: p3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 keys: 0 _col1 (type: string) 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -171,31 +175,31 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + alias: p2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + predicate: p2_name is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Map 3 Map Operator Tree: TableScan - alias: p2 + alias: p3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p2_name is not null (type: boolean) + predicate: p3_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) + expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator @@ -207,40 +211,44 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: p3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 keys: 0 _col1 (type: string) 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -248,7 +256,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from part p1 join part2 p2 join part3 p3 on p2_partkey + p_partkey = p1.p_partkey and p3_name = p2_name PREHOOK: type: QUERY @@ -263,26 +271,13 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - Map 4 - Map Operator Tree: - TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -293,10 +288,12 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - Map 5 + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Map 4 Map Operator Tree: TableScan alias: p3 @@ -314,42 +311,57 @@ STAGE PLANS: Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Map 5 + Map Operator Tree: + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 + 0 _col1 (type: string) + 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col9 + _col0) = _col0) (type: boolean) - Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col10 (type: string) - sort order: + - Map-reduce partition columns: _col10 (type: string) - Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: string) - 1 _col1 (type: string) + 0 + 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 14 Data size: 1744 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 14 Data size: 1744 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col0 + _col18) = _col18) (type: boolean) + Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 + Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -357,7 +369,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from part p1 join part2 p2 join part3 p3 on p2_partkey = 1 and p3_name = p2_name PREHOOK: type: QUERY @@ -372,90 +384,90 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - Map 4 - Map Operator Tree: - TableScan - alias: p2 + alias: p3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((p2_partkey = 1) and p2_name is not null) (type: boolean) + predicate: p3_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - Map 5 + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Map 4 Map Operator Tree: TableScan - alias: p3 + alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p3_name is not null (type: boolean) + predicate: ((p2_partkey = 1) and p2_name is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Map 5 + Map Operator Tree: + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 + 0 _col1 (type: string) + 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col10 (type: string) - sort order: + - Map-reduce partition columns: _col10 (type: string) - Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + sort order: + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: string) - 1 _col1 (type: string) + 0 + 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string) + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 28 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual2.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual2.q.out index df23dbf548..adefd58f0c 100644 --- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual2.q.out +++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual2.q.out @@ -74,31 +74,31 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + alias: p2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + predicate: p2_name is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Map 3 Map Operator Tree: TableScan - alias: p2 + alias: p3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p2_name is not null (type: boolean) + predicate: p3_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) + expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator @@ -110,20 +110,20 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: p3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Map 5 Map Operator Tree: @@ -148,8 +148,8 @@ STAGE PLANS: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 - Inner Join 0 to 3 + Inner Join 0 to 2 + Inner Join 2 to 3 keys: 0 _col1 (type: string) 1 _col1 (type: string) @@ -157,13 +157,17 @@ STAGE PLANS: 3 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 Statistics: Num rows: 85 Data size: 10385 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 Statistics: Num rows: 85 Data size: 10385 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 85 Data size: 10385 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out index 248512a3db..d1b20006b0 100644 --- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out +++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out @@ -76,31 +76,31 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + alias: p2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + predicate: p2_name is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Map 3 Map Operator Tree: TableScan - alias: p2 + alias: p3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p2_name is not null (type: boolean) + predicate: p3_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) + expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator @@ -112,40 +112,44 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: p3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 keys: 0 _col1 (type: string) 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -175,31 +179,31 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + alias: p2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + predicate: p2_name is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Map 3 Map Operator Tree: TableScan - alias: p2 + alias: p3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p2_name is not null (type: boolean) + predicate: p3_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) + expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator @@ -211,40 +215,44 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: p3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 + Inner Join 0 to 2 keys: 0 _col1 (type: string) 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -252,7 +260,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from part p1 join part2 p2 join part3 p3 where p2_partkey + p1.p_partkey = p1.p_partkey and p3_name = p2_name @@ -269,26 +277,13 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - Map 4 - Map Operator Tree: - TableScan alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator @@ -299,10 +294,12 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - Map 5 + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Map 4 Map Operator Tree: TableScan alias: p3 @@ -320,42 +317,57 @@ STAGE PLANS: Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Map 5 + Map Operator Tree: + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 + 0 _col1 (type: string) + 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col9 + _col0) = _col0) (type: boolean) - Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col10 (type: string) - sort order: + - Map-reduce partition columns: _col10 (type: string) - Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: string) - 1 _col1 (type: string) + 0 + 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 14 Data size: 1744 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 14 Data size: 1744 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col0 + _col18) = _col18) (type: boolean) + Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 + Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 13 Data size: 1586 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -363,7 +375,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from part p1 join part2 p2 join part3 p3 where p2_partkey = 1 and p3_name = p2_name @@ -380,90 +392,90 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - Map 4 - Map Operator Tree: - TableScan - alias: p2 + alias: p3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((p2_partkey = 1) and p2_name is not null) (type: boolean) + predicate: p3_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - Map 5 + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Map 4 Map Operator Tree: TableScan - alias: p3 + alias: p2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p3_name is not null (type: boolean) + predicate: ((p2_partkey = 1) and p2_name is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Map 5 + Map Operator Tree: + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 + 0 _col1 (type: string) + 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col10 (type: string) - sort order: + - Map-reduce partition columns: _col10 (type: string) - Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) + sort order: + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: string) - 1 _col1 (type: string) + 0 + 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string) + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 28 Data size: 3490 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3173 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual4.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual4.q.out index cc8d633f2d..2e628fb86f 100644 --- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual4.q.out +++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual4.q.out @@ -76,31 +76,31 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + alias: p2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + predicate: p2_name is not null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Map 3 Map Operator Tree: TableScan - alias: p2 + alias: p3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: p2_name is not null (type: boolean) + predicate: p3_name is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) + expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator @@ -112,20 +112,20 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: p3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + predicate: p_name is not null (type: boolean) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Map 5 Map Operator Tree: @@ -150,8 +150,8 @@ STAGE PLANS: Join Operator condition map: Inner Join 0 to 1 - Inner Join 1 to 2 - Inner Join 0 to 3 + Inner Join 0 to 2 + Inner Join 2 to 3 keys: 0 _col1 (type: string) 1 _col1 (type: string) @@ -159,13 +159,17 @@ STAGE PLANS: 3 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 Statistics: Num rows: 85 Data size: 10385 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 Statistics: Num rows: 85 Data size: 10385 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 85 Data size: 10385 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/spark/join_hive_626.q.out b/ql/src/test/results/clientpositive/spark/join_hive_626.q.out index f304bb9d35..a067d749e4 100644 --- a/ql/src/test/results/clientpositive/spark/join_hive_626.q.out +++ b/ql/src/test/results/clientpositive/spark/join_hive_626.q.out @@ -79,24 +79,6 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: hive_foo - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: foo_id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: foo_id (type: int), foo_name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Map 4 - Map Operator Tree: - TableScan alias: hive_bar Statistics: Num rows: 1 Data size: 23 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -112,6 +94,24 @@ STAGE PLANS: Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 1 Data size: 23 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string) + Map 4 + Map Operator Tree: + TableScan + alias: hive_foo + Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: foo_id is not null (type: boolean) + Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: foo_id (type: int), foo_name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Map 5 Map Operator Tree: TableScan @@ -136,33 +136,33 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col4 + Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col4 (type: string) + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string), _col4 (type: string) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col4, _col6 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col2, _col4, _col6 + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col4 (type: string), _col6 (type: int) + expressions: _col4 (type: string), _col2 (type: string), _col6 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/join_star.q.out b/ql/src/test/results/clientpositive/spark/join_star.q.out index 5d747ec73d..e304225b72 100644 --- a/ql/src/test/results/clientpositive/spark/join_star.q.out +++ b/ql/src/test/results/clientpositive/spark/join_star.q.out @@ -359,49 +359,65 @@ PREHOOK: type: QUERY POSTHOOK: query: explain select m1, m2, f2, f4 from fact join dim1 on fact.d1= dim1.f1 join dim2 on dim1.f2 = dim2.f3 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: Map 2 Map Operator Tree: TableScan - alias: dim1 + alias: dim2 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (f1 is not null and f2 is not null) (type: boolean) + predicate: f3 is not null (type: boolean) Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: f1 (type: int), f2 (type: int) + expressions: f3 (type: int), f4 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work - Map 3 + + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: dim2 + alias: dim1 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: f3 is not null (type: boolean) + predicate: (f1 is not null and f2 is not null) (type: boolean) Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: f3 (type: int), f4 (type: int) + expressions: f1 (type: int), f2 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col4 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3 + input vertices: + 1 Map 2 + Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col2 (type: int) Local Work: Map Reduce Local Work @@ -409,7 +425,7 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 1 + Map 3 Map Operator Tree: TableScan alias: fact @@ -425,33 +441,23 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col4 + 0 _col0 (type: int) + 1 _col2 (type: int) + outputColumnNames: _col1, _col3, _col4, _col5 input vertices: - 1 Map 2 + 0 Map 1 Statistics: Num rows: 8 Data size: 107 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col4 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col4, _col6 - input vertices: - 1 Map 3 - Statistics: Num rows: 8 Data size: 117 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col4 (type: int), _col6 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 117 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 8 Data size: 117 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col4 (type: int), _col5 (type: int), _col1 (type: int), _col3 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 8 Data size: 107 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 107 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work @@ -691,7 +697,6 @@ STAGE PLANS: keys: 0 _col9 (type: int) 1 _col0 (type: int) - 2 _col0 (type: int) Local Work: Map Reduce Local Work Map 6 @@ -722,7 +727,6 @@ STAGE PLANS: keys: 0 _col9 (type: int) 1 _col0 (type: int) - 2 _col0 (type: int) Local Work: Map Reduce Local Work Map 8 @@ -736,7 +740,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col13 (type: int) + 0 _col15 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -787,47 +791,54 @@ STAGE PLANS: Map Join Operator condition map: Left Outer Join 0 to 1 - Left Outer Join 0 to 2 keys: 0 _col9 (type: int) 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13 + outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11 input vertices: 1 Map 5 - 2 Map 7 - Statistics: Num rows: 13 Data size: 281 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 keys: 0 _col11 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13, _col15 + outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13 input vertices: 1 Map 6 - Statistics: Num rows: 14 Data size: 309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 154 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 keys: - 0 _col13 (type: int) + 0 _col9 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13, _col15, _col17 + outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13, _col15 input vertices: - 1 Map 8 - Statistics: Num rows: 15 Data size: 339 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col7 (type: int), _col9 (type: int), _col11 (type: int), _col15 (type: int), _col13 (type: int), _col17 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 15 Data size: 339 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 15 Data size: 339 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 1 Map 7 + Statistics: Num rows: 6 Data size: 169 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col15 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13, _col15, _col17 + input vertices: + 1 Map 8 + Statistics: Num rows: 6 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col7 (type: int), _col9 (type: int), _col11 (type: int), _col13 (type: int), _col15 (type: int), _col17 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 6 Data size: 185 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 185 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/spark/mergejoins_mixed.q.out b/ql/src/test/results/clientpositive/spark/mergejoins_mixed.q.out index 9306718274..c53cd00f34 100644 --- a/ql/src/test/results/clientpositive/spark/mergejoins_mixed.q.out +++ b/ql/src/test/results/clientpositive/spark/mergejoins_mixed.q.out @@ -473,8 +473,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2), Map 6 (PARTITION-LEVEL SORT, 2) - Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Map 6 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 4 <- Map 7 (PARTITION-LEVEL SORT, 2), Reducer 3 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 @@ -495,7 +496,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) - Map 4 + Map 5 Map Operator Tree: TableScan alias: b @@ -513,7 +514,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) - Map 5 + Map 6 Map Operator Tree: TableScan alias: c @@ -528,7 +529,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) - Map 6 + Map 7 Map Operator Tree: TableScan alias: d @@ -551,19 +552,17 @@ STAGE PLANS: Join Operator condition map: Inner Join 0 to 1 - Left Outer Join 0 to 2 keys: 0 _col0 (type: string) 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Reduce Operator Tree: Join Operator @@ -572,19 +571,31 @@ STAGE PLANS: keys: 0 _col3 (type: string) 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string), _col4 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -606,8 +617,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2), Map 6 (PARTITION-LEVEL SORT, 2) - Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Map 6 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 4 <- Map 7 (PARTITION-LEVEL SORT, 2), Reducer 3 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 @@ -628,7 +640,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) - Map 4 + Map 5 Map Operator Tree: TableScan alias: b @@ -646,7 +658,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) - Map 5 + Map 6 Map Operator Tree: TableScan alias: c @@ -661,7 +673,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) - Map 6 + Map 7 Map Operator Tree: TableScan alias: d @@ -681,19 +693,17 @@ STAGE PLANS: Join Operator condition map: Inner Join 0 to 1 - Right Outer Join 0 to 2 keys: 0 _col0 (type: string) 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Reduce Operator Tree: Join Operator @@ -702,19 +712,31 @@ STAGE PLANS: keys: 0 _col3 (type: string) 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Reduce Operator Tree: + Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string), _col4 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -736,8 +758,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2), Map 6 (PARTITION-LEVEL SORT, 2) - Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Map 6 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 4 <- Map 7 (PARTITION-LEVEL SORT, 2), Reducer 3 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 @@ -758,7 +781,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) - Map 4 + Map 5 Map Operator Tree: TableScan alias: b @@ -776,7 +799,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) - Map 5 + Map 6 Map Operator Tree: TableScan alias: c @@ -791,7 +814,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: string) - Map 6 + Map 7 Map Operator Tree: TableScan alias: d @@ -811,19 +834,17 @@ STAGE PLANS: Join Operator condition map: Inner Join 0 to 1 - Outer Join 0 to 2 keys: 0 _col0 (type: string) 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Reduce Operator Tree: Join Operator @@ -832,19 +853,31 @@ STAGE PLANS: keys: 0 _col3 (type: string) 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Reduce Operator Tree: + Join Operator + condition map: + Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string), _col4 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/spark/ppd_join5.q.out b/ql/src/test/results/clientpositive/spark/ppd_join5.q.out index 2b05a1c917..d5624ad7f2 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_join5.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_join5.q.out @@ -32,7 +32,7 @@ POSTHOOK: Lineage: t1.id1 SIMPLE [] POSTHOOK: Lineage: t1.id2 SIMPLE [] POSTHOOK: Lineage: t2.d SIMPLE [] POSTHOOK: Lineage: t2.id SIMPLE [] -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select a.*,b.d d1,c.d d2 from t1 a join t2 b on (a.id1 = b.id) @@ -51,8 +51,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) - Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 @@ -68,70 +68,71 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + sort order: Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Map 4 Map Operator Tree: TableScan - alias: b + alias: c Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d <= 1) and id is not null) (type: boolean) + predicate: (d <= 1) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: id (type: string), d (type: int) - outputColumnNames: _col0, _col1 + expressions: d (type: int) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col0 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col0 (type: string) + sort order: Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + value expressions: _col0 (type: int) Map 5 Map Operator Tree: TableScan - alias: c + alias: b Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (d <= 1) (type: boolean) + predicate: ((d <= 1) and id is not null) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: d (type: int) - outputColumnNames: _col0 + expressions: id (type: string), d (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col0 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col0 (type: string) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col1 (type: int) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int) + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col3, _col4 + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col4 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int), _col4 (type: int) + expressions: _col0 (type: string), _col1 (type: string), _col4 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -148,7 +149,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from ( select a.*,b.d d1,c.d d2 from @@ -171,8 +172,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) - Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 @@ -188,73 +189,74 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + sort order: Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) Map 4 Map Operator Tree: TableScan - alias: b + alias: c Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d <= 1) and id is not null) (type: boolean) + predicate: (d <= 1) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: id (type: string), d (type: int) - outputColumnNames: _col0, _col1 + expressions: d (type: int) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col0 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col0 (type: string) + sort order: Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + value expressions: _col0 (type: int) Map 5 Map Operator Tree: TableScan - alias: c + alias: b Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (d <= 1) (type: boolean) + predicate: ((d <= 1) and id is not null) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: d (type: int) - outputColumnNames: _col0 + expressions: id (type: string), d (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col0 (type: string), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col0 (type: string) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col1 (type: int) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int) + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col3, _col4 + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col4 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col3 > 1) or (_col4 > 1)) (type: boolean) + predicate: ((_col4 > 1) or (_col2 > 1)) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int), _col4 (type: int) + expressions: _col0 (type: string), _col1 (type: string), _col4 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -271,7 +273,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: select * from ( select a.*,b.d d1,c.d d2 from t1 a join t2 b on (a.id1 = b.id) diff --git a/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out b/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out index 0813d6fcb5..e49260aa35 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_outer_join5.q.out @@ -178,61 +178,61 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: t2 + alias: t3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (id = 20) (type: boolean) + predicate: (20 = id) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col1, _col2 + expressions: 20 (type: int), key (type: string), value (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) Map 5 Map Operator Tree: TableScan - alias: t3 + alias: t2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (20 = id) (type: boolean) + predicate: (id = 20) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + value expressions: _col1 (type: string), _col2 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: 0 1 - outputColumnNames: _col1, _col2, _col4, _col5 + outputColumnNames: _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) Reducer 3 Reduce Operator Tree: Join Operator condition map: - Left Outer Join 0 to 1 + Inner Join 0 to 1 keys: 0 1 - outputColumnNames: _col1, _col2, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col7, _col8 Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 20 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string), _col8 (type: string) + expressions: 20 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col7 (type: string), _col8 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -286,61 +286,61 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: t2 + alias: t3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (id = 20) (type: boolean) + predicate: (20 = id) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col1, _col2 + expressions: 20 (type: int), key (type: string), value (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) Map 5 Map Operator Tree: TableScan - alias: t3 + alias: t2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (20 = id) (type: boolean) + predicate: (id = 20) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: key (type: string), value (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + value expressions: _col1 (type: string), _col2 (type: string) Reducer 2 Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: 0 1 - outputColumnNames: _col1, _col2, _col4, _col5 + outputColumnNames: _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) Reducer 3 Reduce Operator Tree: Join Operator condition map: - Left Outer Join 0 to 1 + Inner Join 0 to 1 keys: 0 1 - outputColumnNames: _col1, _col2, _col4, _col5, _col6, _col7, _col8 + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col7, _col8 Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 20 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string), _col8 (type: string) + expressions: 20 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col7 (type: string), _col8 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/spark/stats_only_null.q.out b/ql/src/test/results/clientpositive/spark/stats_only_null.q.out index 94f955c82d..38ed139302 100644 --- a/ql/src/test/results/clientpositive/spark/stats_only_null.q.out +++ b/ql/src/test/results/clientpositive/spark/stats_only_null.q.out @@ -87,19 +87,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_null - Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1050 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) outputColumnNames: a, b, c, d - Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1050 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -107,10 +107,10 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -143,19 +143,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_null_part - Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) outputColumnNames: a, b, c, d - Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1170 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -163,10 +163,10 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out b/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out index 9291c01867..c8261bd17b 100644 --- a/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out +++ b/ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out @@ -496,7 +496,7 @@ Keys:val 13.0 1 17.0 1 46.0 1 -Warning: Shuffle Join JOIN[20][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 4' is a cross product +Warning: Shuffle Join JOIN[20][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: SELECT * FROM ( @@ -519,11 +519,11 @@ PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 PREHOOK: Input: default@t3 #### A masked pattern was here #### -Operator:JOIN_8 -Table:default@t1 -Keys:key +Operator:JOIN_11 Table:default@t2 Keys:key +Table:default@t1 +Keys:key PREHOOK: query: SELECT * FROM T1 JOIN T2 diff --git a/ql/src/test/results/clientpositive/stats_only_null.q.out b/ql/src/test/results/clientpositive/stats_only_null.q.out index de1b017989..ab9b4adec7 100644 --- a/ql/src/test/results/clientpositive/stats_only_null.q.out +++ b/ql/src/test/results/clientpositive/stats_only_null.q.out @@ -82,29 +82,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_null - Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1050 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) outputColumnNames: a, b, c, d - Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1050 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -132,29 +132,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_null_part - Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) outputColumnNames: a, b, c, d - Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1170 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/stats_partial_size.q.out b/ql/src/test/results/clientpositive/stats_partial_size.q.out index c779741314..3f735c1f88 100644 --- a/ql/src/test/results/clientpositive/stats_partial_size.q.out +++ b/ql/src/test/results/clientpositive/stats_partial_size.q.out @@ -47,16 +47,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: sample_partitioned - Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: x (type: int), y (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan alias: sample @@ -81,10 +81,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/stats_ppr_all.q.out b/ql/src/test/results/clientpositive/stats_ppr_all.q.out index d4060c600b..d4cceb0c04 100644 --- a/ql/src/test/results/clientpositive/stats_ppr_all.q.out +++ b/ql/src/test/results/clientpositive/stats_ppr_all.q.out @@ -116,32 +116,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ss - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble((((year * 10000) + (month * 100)) + day)) = 2015010.0) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: order_amount (type: float) outputColumnNames: order_amount - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(order_amount) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out index 9d47066297..dbd388b577 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out @@ -259,10 +259,10 @@ Stage-3 Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] <-Map 1 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=500/500 width=10) + Select Operator [SEL_1] (rows=500/500 width=169) Output:["key","value"] - TableScan [TS_0] (rows=500/500 width=10) - default@src_stats,src_stats,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_0] (rows=500/500 width=169) + default@src_stats,src_stats,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: CREATE TEMPORARY MACRO SIGMOID (x DOUBLE) 1.0 / (1.0 + EXP(-x)) PREHOOK: type: CREATEMACRO @@ -667,12 +667,12 @@ Stage-3 Map 1 File Output Operator [FS_3] table:{"name:":"default.orc_merge5"} - Select Operator [SEL_2] (rows=306/3 width=268) + Select Operator [SEL_2] (rows=306/3 width=245) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_4] (rows=306/3 width=268) + Filter Operator [FIL_4] (rows=306/3 width=245) predicate:(userid <= 13) - TableScan [TS_0] (rows=919/15000 width=268) - default@orc_merge5,orc_merge5,Tbl:COMPLETE,Col:NONE,Output:["userid","string1","subtype","decimal1","ts"] + TableScan [TS_0] (rows=919/15000 width=244) + default@orc_merge5,orc_merge5,Tbl:COMPLETE,Col:COMPLETE,Output:["userid","string1","subtype","decimal1","ts"] Stage-4(CONDITIONAL) File Merge Please refer to the previous Stage-8(CONDITIONAL CHILD TASKS: Stage-5, Stage-4, Stage-6) @@ -827,31 +827,34 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 2 <- Map 1 (BROADCAST_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Map 2 + Reducer 2 File Output Operator [FS_10] - Select Operator [SEL_9] (rows=550/480 width=18) + Select Operator [SEL_9] (rows=1150/480 width=179) Output:["_col0","_col1","_col2"] - Map Join Operator [MAPJOIN_25] (rows=550/480 width=18) - Conds:RS_6._col0=SEL_5._col0(Inner),HybridGraceHashJoin:true,Output:["_col0","_col1","_col3"] - <-Map 1 [BROADCAST_EDGE] - BROADCAST [RS_6] + Merge Join Operator [MERGEJOIN_25] (rows=1150/480 width=179) + Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_6] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=230/242 width=88) + Output:["_col0","_col1"] + Filter Operator [FIL_13] (rows=230/242 width=88) + predicate:key is not null + TableScan [TS_0] (rows=242/242 width=99) + default@tab,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Map 3 [SIMPLE_EDGE] + SHUFFLE [RS_7] PartitionCols:_col0 - Select Operator [SEL_2] (rows=242/242 width=18) + Select Operator [SEL_5] (rows=475/500 width=88) Output:["_col0","_col1"] - Filter Operator [FIL_13] (rows=242/242 width=18) + Filter Operator [FIL_14] (rows=475/500 width=88) predicate:key is not null - TableScan [TS_0] (rows=242/242 width=18) - default@tab,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_5] (rows=500/500 width=18) - Output:["_col0","_col1"] - Filter Operator [FIL_14] (rows=500/500 width=18) - predicate:key is not null - TableScan [TS_3] (rows=500/500 width=18) - default@tab_part,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_3] (rows=500/500 width=99) + default@tab_part,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] diff --git a/ql/src/test/results/clientpositive/tez/explainuser_3.q.out b/ql/src/test/results/clientpositive/tez/explainuser_3.q.out index f70d711fc4..733aa44dc1 100644 --- a/ql/src/test/results/clientpositive/tez/explainuser_3.q.out +++ b/ql/src/test/results/clientpositive/tez/explainuser_3.q.out @@ -41,13 +41,13 @@ Stage-0 Stage-1 Reducer 2 vectorized File Output Operator [FS_8] - Select Operator [SEL_7] (rows=10 width=101) + Select Operator [SEL_7] (rows=10 width=100) Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_6] - Select Operator [SEL_5] (rows=10 width=101) + Select Operator [SEL_5] (rows=10 width=100) Output:["_col0","_col1"] - TableScan [TS_0] (rows=10 width=101) + TableScan [TS_0] (rows=10 width=100) default@acid_vectorized,acid_vectorized, ACID table,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] PREHOOK: query: explain select key, value @@ -511,12 +511,12 @@ Stage-3 Map 1 vectorized File Output Operator [FS_10] table:{"name:":"default.orc_merge5"} - Select Operator [SEL_9] (rows=306 width=268) + Select Operator [SEL_9] (rows=306 width=245) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_8] (rows=306 width=268) + Filter Operator [FIL_8] (rows=306 width=245) predicate:(userid <= 13) - TableScan [TS_0] (rows=919 width=268) - default@orc_merge5,orc_merge5,Tbl:COMPLETE,Col:NONE,Output:["userid","string1","subtype","decimal1","ts"] + TableScan [TS_0] (rows=919 width=244) + default@orc_merge5,orc_merge5,Tbl:COMPLETE,Col:COMPLETE,Output:["userid","string1","subtype","decimal1","ts"] Stage-4(CONDITIONAL) File Merge Please refer to the previous Stage-8(CONDITIONAL CHILD TASKS: Stage-5, Stage-4, Stage-6) @@ -655,31 +655,34 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 2 <- Map 1 (BROADCAST_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Map 2 vectorized - File Output Operator [FS_34] - Select Operator [SEL_33] (rows=550 width=18) + Reducer 2 + File Output Operator [FS_10] + Select Operator [SEL_9] (rows=1150 width=179) Output:["_col0","_col1","_col2"] - Map Join Operator [MAPJOIN_32] (rows=550 width=18) - Conds:RS_29._col0=SEL_31._col0(Inner),HybridGraceHashJoin:true,Output:["_col0","_col1","_col3"] - <-Map 1 [BROADCAST_EDGE] vectorized - BROADCAST [RS_29] + Merge Join Operator [MERGEJOIN_25] (rows=1150 width=179) + Conds:RS_28._col0=RS_31._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_28] PartitionCols:_col0 - Select Operator [SEL_28] (rows=242 width=18) + Select Operator [SEL_27] (rows=230 width=88) Output:["_col0","_col1"] - Filter Operator [FIL_27] (rows=242 width=18) + Filter Operator [FIL_26] (rows=230 width=88) predicate:key is not null - TableScan [TS_0] (rows=242 width=18) - default@tab,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_31] (rows=500 width=18) - Output:["_col0","_col1"] - Filter Operator [FIL_30] (rows=500 width=18) - predicate:key is not null - TableScan [TS_3] (rows=500 width=18) - default@tab_part,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + TableScan [TS_0] (rows=242 width=99) + default@tab,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Map 3 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_31] + PartitionCols:_col0 + Select Operator [SEL_30] (rows=475 width=88) + Output:["_col0","_col1"] + Filter Operator [FIL_29] (rows=475 width=88) + predicate:key is not null + TableScan [TS_3] (rows=500 width=99) + default@tab_part,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] diff --git a/ql/src/test/results/clientpositive/tez/vector_join_part_col_char.q.out b/ql/src/test/results/clientpositive/tez/vector_join_part_col_char.q.out index 2b9882e390..f8d6bc3789 100644 --- a/ql/src/test/results/clientpositive/tez/vector_join_part_col_char.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_join_part_col_char.q.out @@ -110,28 +110,28 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_10] - Merge Join Operator [MERGEJOIN_21] (rows=2 width=431) + Merge Join Operator [MERGEJOIN_21] (rows=2 width=409) Conds:RS_23._col2=RS_28._col2(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_23] PartitionCols:_col2 - Select Operator [SEL_22] (rows=2 width=134) + Select Operator [SEL_22] (rows=2 width=227) Output:["_col0","_col1","_col2"] - TableScan [TS_0] (rows=2 width=236) - default@char_tbl1,c1,Tbl:COMPLETE,Col:PARTIAL,Output:["name","age"] - Dynamic Partitioning Event Operator [EVENT_26] (rows=1 width=134) - Group By Operator [GBY_25] (rows=1 width=134) + TableScan [TS_0] (rows=2 width=329) + default@char_tbl1,c1,Tbl:COMPLETE,Col:COMPLETE,Output:["name","age"] + Dynamic Partitioning Event Operator [EVENT_26] (rows=1 width=227) + Group By Operator [GBY_25] (rows=1 width=227) Output:["_col0"],keys:_col0 - Select Operator [SEL_24] (rows=2 width=134) + Select Operator [SEL_24] (rows=2 width=227) Output:["_col0"] Please refer to the previous Select Operator [SEL_22] <-Map 3 [SIMPLE_EDGE] vectorized SHUFFLE [RS_28] PartitionCols:_col2 - Select Operator [SEL_27] (rows=2 width=89) + Select Operator [SEL_27] (rows=2 width=182) Output:["_col0","_col1","_col2"] - TableScan [TS_3] (rows=2 width=190) - default@char_tbl2,c2,Tbl:COMPLETE,Col:PARTIAL,Output:["name","age"] + TableScan [TS_3] (rows=2 width=283) + default@char_tbl2,c2,Tbl:COMPLETE,Col:COMPLETE,Output:["name","age"] PREHOOK: query: select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa) PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/tez/vector_non_string_partition.q.out b/ql/src/test/results/clientpositive/tez/vector_non_string_partition.q.out index e09cbb91e5..5f7d4699da 100644 --- a/ql/src/test/results/clientpositive/tez/vector_non_string_partition.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_non_string_partition.q.out @@ -51,7 +51,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: non_string_part - Statistics: Num rows: 3073 Data size: 351442 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 3073 Data size: 363126 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4] @@ -61,7 +61,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0, val 0) -> boolean predicate: (cint > 0) (type: boolean) - Statistics: Num rows: 1024 Data size: 4096 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1024 Data size: 7992 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), ctinyint (type: tinyint) outputColumnNames: _col0, _col1 @@ -69,7 +69,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 4] - Statistics: Num rows: 1024 Data size: 4096 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1024 Data size: 7992 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -77,7 +77,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1024 Data size: 4096 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1024 Data size: 7992 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: tinyint) Execution mode: vectorized @@ -106,19 +106,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1] - Statistics: Num rows: 1024 Data size: 4096 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1024 Data size: 7992 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -174,7 +174,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: non_string_part - Statistics: Num rows: 3073 Data size: 363734 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3073 Data size: 610803 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true projectedOutputColumns: [0, 1, 2, 3, 4] @@ -184,7 +184,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0, val 0) -> boolean predicate: (cint > 0) (type: boolean) - Statistics: Num rows: 1024 Data size: 121205 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 90582 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cstring1 (type: string) outputColumnNames: _col0, _col1 @@ -192,7 +192,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1] - Statistics: Num rows: 1024 Data size: 121205 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 90582 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ @@ -200,7 +200,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1024 Data size: 121205 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 90582 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -228,19 +228,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1] - Statistics: Num rows: 1024 Data size: 121205 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 90582 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 1180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 1180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out b/ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out index a659b9e869..725bad3337 100644 --- a/ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out +++ b/ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out @@ -258,27 +258,26 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col1 (type: int) TableScan - alias: store + alias: date_dim Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((s_state) IN ('KS', 'AL', 'MN', 'SC', 'VT') and s_store_sk is not null) (type: boolean) + predicate: d_date_sk is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: s_store_sk (type: int), s_state (type: string) - outputColumnNames: _col0, _col1 + expressions: d_date_sk (type: int) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: string) Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -291,9 +290,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col3 + outputColumnNames: _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -307,26 +306,26 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col3 (type: string) TableScan - alias: date_dim + alias: store Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: d_date_sk is not null (type: boolean) + predicate: ((s_state) IN ('KS', 'AL', 'MN', 'SC', 'VT') and s_store_sk is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 + expressions: s_store_sk (type: int), s_state (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string) Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -339,13 +338,13 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col3 + outputColumnNames: _col4 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() - keys: _col3 (type: string) + keys: _col4 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git a/ql/src/test/results/clientpositive/vector_outer_join6.q.out b/ql/src/test/results/clientpositive/vector_outer_join6.q.out index 75d3fcb240..1b98e15e88 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join6.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join6.q.out @@ -130,7 +130,7 @@ POSTHOOK: query: explain vectorization detail formatted select tj1rnum, tj2rnum, tjoin3.rnum as rnumt3 from (select tjoin1.rnum tj1rnum, tjoin2.rnum tj2rnum, tjoin2.c1 tj2c1 from tjoin1 left outer join tjoin2 on tjoin1.c1 = tjoin2.c1 ) tj left outer join tjoin3 on tj2c1 = tjoin3.c1 POSTHOOK: type: QUERY -{"PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"STAGE DEPENDENCIES":{"Stage-7":{"ROOT STAGE":"TRUE"},"Stage-5":{"DEPENDENT STAGES":"Stage-7"},"Stage-0":{"DEPENDENT STAGES":"Stage-5"}},"STAGE PLANS":{"Stage-7":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_0:$hdt$_1:tjoin2":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_1:tjoin3":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_0:$hdt$_1:tjoin2":{"TableScan":{"alias:":"tjoin2","Statistics:":"Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)"},"OperatorId:":"HASHTABLESINK_21"}}}}}},"$hdt$_1:tjoin3":{"TableScan":{"alias:":"tjoin3","Statistics:":"Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"TS_8","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_9","children":{"HashTable Sink Operator":{"keys:":{"0":"_col2 (type: int)","1":"_col1 (type: int)"},"OperatorId:":"HASHTABLESINK_19"}}}}}}}}},"Stage-5":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"tjoin1","Statistics:":"Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE","TableScan Vectorization:":{"native:":"true","projectedOutputColumns:":"[0, 1, 2]"},"OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumns:":"[0, 1]"},"Statistics:":"Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_23","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)"},"Map Join Vectorization:":{"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col2","_col3"],"Statistics:":"Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_24","children":{"Select Operator":{"expressions:":"_col0 (type: int), _col2 (type: int), _col3 (type: int)","outputColumnNames:":["_col0","_col1","_col2"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumns:":"[0, 1, 2]"},"Statistics:":"Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_25","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col2 (type: int)","1":"_col1 (type: int)"},"Map Join Vectorization:":{"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col1","_col3"],"Statistics:":"Num rows: 4 Data size: 449 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_26","children":{"Select Operator":{"expressions:":"_col0 (type: int), _col1 (type: int), _col3 (type: int)","outputColumnNames:":["_col0","_col1","_col2"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumns:":"[0, 1, 2]"},"Statistics:":"Num rows: 4 Data size: 449 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_27","children":{"File Output Operator":{"compressed:":"false","File Sink Vectorization:":{"className:":"VectorFileSinkOperator","native:":"false"},"Statistics:":"Num rows: 4 Data size: 449 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_28"}}}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"groupByVectorOutput:":"true","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"3","includeColumns:":"[0, 1]","dataColumns:":["rnum:int","c1:int","c2:int"],"partitionColumnCount:":"0","scratchColumnTypeNames:":["bigint","bigint"]}},"Local Work:":{"Map Reduce Local Work":{}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_29"}}}}}} +{"PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"STAGE DEPENDENCIES":{"Stage-7":{"ROOT STAGE":"TRUE"},"Stage-5":{"DEPENDENT STAGES":"Stage-7"},"Stage-0":{"DEPENDENT STAGES":"Stage-5"}},"STAGE PLANS":{"Stage-7":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_0:$hdt$_0:tjoin2":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_1:tjoin3":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_0:$hdt$_0:tjoin2":{"TableScan":{"alias:":"tjoin2","Statistics:":"Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_1","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)"},"OperatorId:":"HASHTABLESINK_21"}}}}}},"$hdt$_1:tjoin3":{"TableScan":{"alias:":"tjoin3","Statistics:":"Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"TS_8","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_9","children":{"HashTable Sink Operator":{"keys:":{"0":"_col2 (type: int)","1":"_col1 (type: int)"},"OperatorId:":"HASHTABLESINK_19"}}}}}}}}},"Stage-5":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"tjoin1","Statistics:":"Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE","TableScan Vectorization:":{"native:":"true","projectedOutputColumns:":"[0, 1, 2]"},"OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumns:":"[0, 1]"},"Statistics:":"Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_23","children":{"Map Join Operator":{"condition map:":[{"":"Right Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)"},"Map Join Vectorization:":{"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col1","_col2"],"Statistics:":"Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_24","children":{"Select Operator":{"expressions:":"_col2 (type: int), _col0 (type: int), _col1 (type: int)","outputColumnNames:":["_col0","_col1","_col2"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumns:":"[2, 0, 1]"},"Statistics:":"Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_25","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col2 (type: int)","1":"_col1 (type: int)"},"Map Join Vectorization:":{"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col1","_col3"],"Statistics:":"Num rows: 4 Data size: 449 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_26","children":{"Select Operator":{"expressions:":"_col0 (type: int), _col1 (type: int), _col3 (type: int)","outputColumnNames:":["_col0","_col1","_col2"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumns:":"[0, 1, 2]"},"Statistics:":"Num rows: 4 Data size: 449 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_27","children":{"File Output Operator":{"compressed:":"false","File Sink Vectorization:":{"className:":"VectorFileSinkOperator","native:":"false"},"Statistics:":"Num rows: 4 Data size: 449 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_28"}}}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"groupByVectorOutput:":"true","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"3","includeColumns:":"[0, 1]","dataColumns:":["rnum:int","c1:int","c2:int"],"partitionColumnCount:":"0","scratchColumnTypeNames:":["bigint","bigint"]}},"Local Work:":{"Map Reduce Local Work":{}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_29"}}}}}} PREHOOK: query: select tj1rnum, tj2rnum, tjoin3.rnum as rnumt3 from (select tjoin1.rnum tj1rnum, tjoin2.rnum tj2rnum, tjoin2.c1 tj2c1 from tjoin1 left outer join tjoin2 on tjoin1.c1 = tjoin2.c1 ) tj left outer join tjoin3 on tj2c1 = tjoin3.c1 PREHOOK: type: QUERY @@ -157,7 +157,7 @@ POSTHOOK: query: explain vectorization detail formatted select tj1rnum, tj2rnum as rnumt3 from (select tjoin1.rnum tj1rnum, tjoin2.rnum tj2rnum, tjoin2.c1 tj2c1 from tjoin1 left outer join tjoin2 on tjoin1.c1 = tjoin2.c1 ) tj left outer join tjoin3 on tj2c1 = tjoin3.c1 POSTHOOK: type: QUERY -{"PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"STAGE DEPENDENCIES":{"Stage-7":{"ROOT STAGE":"TRUE"},"Stage-5":{"DEPENDENT STAGES":"Stage-7"},"Stage-0":{"DEPENDENT STAGES":"Stage-5"}},"STAGE PLANS":{"Stage-7":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_0:$hdt$_1:tjoin2":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_1:tjoin3":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_0:$hdt$_1:tjoin2":{"TableScan":{"alias:":"tjoin2","Statistics:":"Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)"},"OperatorId:":"HASHTABLESINK_21"}}}}}},"$hdt$_1:tjoin3":{"TableScan":{"alias:":"tjoin3","Statistics:":"Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"TS_8","children":{"Select Operator":{"expressions:":"c1 (type: int)","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_9","children":{"HashTable Sink Operator":{"keys:":{"0":"_col2 (type: int)","1":"_col0 (type: int)"},"OperatorId:":"HASHTABLESINK_19"}}}}}}}}},"Stage-5":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"tjoin1","Statistics:":"Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE","TableScan Vectorization:":{"native:":"true","projectedOutputColumns:":"[0, 1, 2]"},"OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumns:":"[0, 1]"},"Statistics:":"Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_23","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)"},"Map Join Vectorization:":{"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col2","_col3"],"Statistics:":"Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_24","children":{"Select Operator":{"expressions:":"_col0 (type: int), _col2 (type: int), _col3 (type: int)","outputColumnNames:":["_col0","_col1","_col2"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumns:":"[0, 1, 2]"},"Statistics:":"Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_25","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col2 (type: int)","1":"_col0 (type: int)"},"Map Join Vectorization:":{"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 4 Data size: 449 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_26","children":{"File Output Operator":{"compressed:":"false","File Sink Vectorization:":{"className:":"VectorFileSinkOperator","native:":"false"},"Statistics:":"Num rows: 4 Data size: 449 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_27"}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"groupByVectorOutput:":"true","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"3","includeColumns:":"[0, 1]","dataColumns:":["rnum:int","c1:int","c2:int"],"partitionColumnCount:":"0","scratchColumnTypeNames:":["bigint","bigint"]}},"Local Work:":{"Map Reduce Local Work":{}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_28"}}}}}} +{"PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"STAGE DEPENDENCIES":{"Stage-7":{"ROOT STAGE":"TRUE"},"Stage-5":{"DEPENDENT STAGES":"Stage-7"},"Stage-0":{"DEPENDENT STAGES":"Stage-5"}},"STAGE PLANS":{"Stage-7":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_0:$hdt$_0:tjoin2":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_1:tjoin3":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_0:$hdt$_0:tjoin2":{"TableScan":{"alias:":"tjoin2","Statistics:":"Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_1","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)"},"OperatorId:":"HASHTABLESINK_21"}}}}}},"$hdt$_1:tjoin3":{"TableScan":{"alias:":"tjoin3","Statistics:":"Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"TS_8","children":{"Select Operator":{"expressions:":"c1 (type: int)","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_9","children":{"HashTable Sink Operator":{"keys:":{"0":"_col2 (type: int)","1":"_col0 (type: int)"},"OperatorId:":"HASHTABLESINK_19"}}}}}}}}},"Stage-5":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"tjoin1","Statistics:":"Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE","TableScan Vectorization:":{"native:":"true","projectedOutputColumns:":"[0, 1, 2]"},"OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumns:":"[0, 1]"},"Statistics:":"Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_23","children":{"Map Join Operator":{"condition map:":[{"":"Right Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)"},"Map Join Vectorization:":{"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col1","_col2"],"Statistics:":"Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_24","children":{"Select Operator":{"expressions:":"_col2 (type: int), _col0 (type: int), _col1 (type: int)","outputColumnNames:":["_col0","_col1","_col2"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumns:":"[2, 0, 1]"},"Statistics:":"Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_25","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col2 (type: int)","1":"_col0 (type: int)"},"Map Join Vectorization:":{"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 4 Data size: 449 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_26","children":{"File Output Operator":{"compressed:":"false","File Sink Vectorization:":{"className:":"VectorFileSinkOperator","native:":"false"},"Statistics:":"Num rows: 4 Data size: 449 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_27"}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"groupByVectorOutput:":"true","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"3","includeColumns:":"[0, 1]","dataColumns:":["rnum:int","c1:int","c2:int"],"partitionColumnCount:":"0","scratchColumnTypeNames:":["bigint","bigint"]}},"Local Work:":{"Map Reduce Local Work":{}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_28"}}}}}} PREHOOK: query: select tj1rnum, tj2rnum as rnumt3 from (select tjoin1.rnum tj1rnum, tjoin2.rnum tj2rnum, tjoin2.c1 tj2c1 from tjoin1 left outer join tjoin2 on tjoin1.c1 = tjoin2.c1 ) tj left outer join tjoin3 on tj2c1 = tjoin3.c1 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/vectorized_context.q.out b/ql/src/test/results/clientpositive/vectorized_context.q.out index dac9b6b143..9f69e8de90 100644 --- a/ql/src/test/results/clientpositive/vectorized_context.q.out +++ b/ql/src/test/results/clientpositive/vectorized_context.q.out @@ -109,29 +109,14 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:store_sales + $hdt$_0:household_demographics Fetch Operator limit: -1 - $hdt$_2:household_demographics + $hdt$_2:store Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:store_sales - TableScan - alias: store_sales - Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_store_sk is not null and ss_hdemo_sk is not null) (type: boolean) - Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_store_sk (type: int), ss_hdemo_sk (type: int), ss_net_profit (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - $hdt$_2:household_demographics + $hdt$_0:household_demographics TableScan alias: household_demographics Statistics: Num rows: 6075 Data size: 24300 Basic stats: COMPLETE Column stats: NONE @@ -144,12 +129,9 @@ STAGE PLANS: Statistics: Num rows: 6075 Data size: 24300 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - - Stage: Stage-5 - Map Reduce - Map Operator Tree: + 0 _col0 (type: int) + 1 _col1 (type: int) + $hdt$_2:store TableScan alias: store Statistics: Num rows: 6075 Data size: 615632 Basic stats: COMPLETE Column stats: NONE @@ -160,32 +142,50 @@ STAGE PLANS: expressions: s_store_sk (type: int), s_city (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6075 Data size: 615632 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_store_sk is not null and ss_hdemo_sk is not null) (type: boolean) + Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_store_sk (type: int), ss_hdemo_sk (type: int), ss_net_profit (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 6682 Data size: 80009 Basic stats: COMPLETE Column stats: NONE + 1 _col1 (type: int) + outputColumnNames: _col1, _col3 + Statistics: Num rows: 6682 Data size: 26730 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col4 - Statistics: Num rows: 7350 Data size: 88009 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col3, _col5 + Statistics: Num rows: 7350 Data size: 29403 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col4 (type: string), _col2 (type: double) + expressions: _col5 (type: string), _col3 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 7350 Data size: 88009 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7350 Data size: 29403 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat