diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/StatsNoJobTask.java ql/src/java/org/apache/hadoop/hive/ql/exec/StatsNoJobTask.java index f089964..868cf04 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/StatsNoJobTask.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/StatsNoJobTask.java @@ -19,6 +19,7 @@ package org.apache.hadoop.hive.ql.exec; import java.io.Serializable; +import java.util.Collection; import java.util.List; import java.util.Map; import java.util.concurrent.ConcurrentMap; @@ -223,7 +224,12 @@ private int aggregateStats(ExecutorService threadPool) { int ret = 0; try { - List partitions = getPartitionsList(); + Collection partitions = null; + if (work.getPrunedPartitionList() == null) { + partitions = getPartitionsList(); + } else { + partitions = work.getPrunedPartitionList().getPartitions(); + } // non-partitioned table if (partitions == null) { diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRTableScan1.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRTableScan1.java index 0b45e25..0ea81ab 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRTableScan1.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRTableScan1.java @@ -90,16 +90,25 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx opProcCtx, QBParseInfo parseInfo = parseCtx.getQB().getParseInfo(); if (parseInfo.isAnalyzeCommand()) { - boolean partialScan = parseInfo.isPartialScanAnalyzeCommand(); - boolean noScan = parseInfo.isNoScanAnalyzeCommand(); - if (inputFormat.equals(OrcInputFormat.class) && (noScan || partialScan)) { - + if (inputFormat.equals(OrcInputFormat.class)) { + // For ORC, all the following statements are the same + // ANALYZE TABLE T [PARTITION (...)] COMPUTE STATISTICS // ANALYZE TABLE T [PARTITION (...)] COMPUTE STATISTICS partialscan; // ANALYZE TABLE T [PARTITION (...)] COMPUTE STATISTICS noscan; + // There will not be any MR or Tez job above this task StatsNoJobWork snjWork = new StatsNoJobWork(parseCtx.getQB().getParseInfo().getTableSpec()); snjWork.setStatsReliable(parseCtx.getConf().getBoolVar( HiveConf.ConfVars.HIVE_STATS_RELIABLE)); + // If partition is specified, get pruned partition list + Set confirmedParts = GenMapRedUtils.getConfirmedPartitionsForScan(parseInfo); + if (confirmedParts.size() > 0) { + Table source = parseCtx.getQB().getMetaData().getTableForAlias(alias); + List partCols = GenMapRedUtils.getPartitionColumns(parseInfo); + PrunedPartitionList partList = new PrunedPartitionList(source, confirmedParts, + partCols, false); + snjWork.setPrunedPartitionList(partList); + } Task snjTask = TaskFactory.get(snjWork, parseCtx.getConf()); ctx.setCurrTask(snjTask); ctx.setCurrTopOp(null); diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/ProcessAnalyzeTable.java ql/src/java/org/apache/hadoop/hive/ql/parse/ProcessAnalyzeTable.java index 2ecf8a5..61592c1 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/ProcessAnalyzeTable.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/ProcessAnalyzeTable.java @@ -95,16 +95,25 @@ public Object process(Node nd, Stack stack, assert alias != null; TezWork tezWork = context.currentTask.getWork(); - boolean partialScan = parseInfo.isPartialScanAnalyzeCommand(); - boolean noScan = parseInfo.isNoScanAnalyzeCommand(); - if (inputFormat.equals(OrcInputFormat.class) && (noScan || partialScan)) { - + if (inputFormat.equals(OrcInputFormat.class)) { + // For ORC, all the following statements are the same + // ANALYZE TABLE T [PARTITION (...)] COMPUTE STATISTICS // ANALYZE TABLE T [PARTITION (...)] COMPUTE STATISTICS partialscan; // ANALYZE TABLE T [PARTITION (...)] COMPUTE STATISTICS noscan; + // There will not be any Tez job above this task StatsNoJobWork snjWork = new StatsNoJobWork(parseContext.getQB().getParseInfo().getTableSpec()); snjWork.setStatsReliable(parseContext.getConf().getBoolVar( HiveConf.ConfVars.HIVE_STATS_RELIABLE)); + // If partition is specified, get pruned partition list + Set confirmedParts = GenMapRedUtils.getConfirmedPartitionsForScan(parseInfo); + if (confirmedParts.size() > 0) { + Table source = parseContext.getQB().getMetaData().getTableForAlias(alias); + List partCols = GenMapRedUtils.getPartitionColumns(parseInfo); + PrunedPartitionList partList = new PrunedPartitionList(source, confirmedParts, + partCols, false); + snjWork.setPrunedPartitionList(partList); + } Task snjTask = TaskFactory.get(snjWork, parseContext.getConf()); snjTask.setParentTasks(null); context.rootTasks.remove(context.currentTask); diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/StatsNoJobWork.java ql/src/java/org/apache/hadoop/hive/ql/plan/StatsNoJobWork.java index 5487836..3e5a607 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/StatsNoJobWork.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/StatsNoJobWork.java @@ -21,6 +21,7 @@ import java.io.Serializable; import org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.tableSpec; +import org.apache.hadoop.hive.ql.parse.PrunedPartitionList; /** * Client-side stats aggregator task. @@ -31,6 +32,7 @@ private tableSpec tableSpecs; private boolean statsReliable; + private PrunedPartitionList prunedPartitionList; public StatsNoJobWork() { } @@ -54,4 +56,12 @@ public boolean isStatsReliable() { public void setStatsReliable(boolean statsReliable) { this.statsReliable = statsReliable; } + + public void setPrunedPartitionList(PrunedPartitionList prunedPartitionList) { + this.prunedPartitionList = prunedPartitionList; + } + + public PrunedPartitionList getPrunedPartitionList() { + return prunedPartitionList; + } } diff --git ql/src/test/queries/clientpositive/orc_analyze.q ql/src/test/queries/clientpositive/orc_analyze.q index 3621c7a..bd22e6f 100644 --- ql/src/test/queries/clientpositive/orc_analyze.q +++ ql/src/test/queries/clientpositive/orc_analyze.q @@ -30,8 +30,13 @@ STORED AS orc; INSERT OVERWRITE TABLE orc_create_people SELECT * FROM orc_create_people_staging ORDER BY id; set hive.stats.autogather = true; +analyze table orc_create_people compute statistics; +desc formatted orc_create_people; + analyze table orc_create_people compute statistics partialscan; +desc formatted orc_create_people; +analyze table orc_create_people compute statistics noscan; desc formatted orc_create_people; drop table orc_create_people; @@ -70,8 +75,15 @@ INSERT OVERWRITE TABLE orc_create_people PARTITION (state) SELECT * FROM orc_create_people_staging ORDER BY id; set hive.stats.autogather = true; +analyze table orc_create_people partition(state) compute statistics; +desc formatted orc_create_people partition(state="Ca"); +desc formatted orc_create_people partition(state="Or"); + analyze table orc_create_people partition(state) compute statistics partialscan; +desc formatted orc_create_people partition(state="Ca"); +desc formatted orc_create_people partition(state="Or"); +analyze table orc_create_people partition(state) compute statistics noscan; desc formatted orc_create_people partition(state="Ca"); desc formatted orc_create_people partition(state="Or"); @@ -116,8 +128,15 @@ INSERT OVERWRITE TABLE orc_create_people PARTITION (state) SELECT * FROM orc_create_people_staging ORDER BY id; set hive.stats.autogather = true; +analyze table orc_create_people partition(state) compute statistics; +desc formatted orc_create_people partition(state="Ca"); +desc formatted orc_create_people partition(state="Or"); + analyze table orc_create_people partition(state) compute statistics partialscan; +desc formatted orc_create_people partition(state="Ca"); +desc formatted orc_create_people partition(state="Or"); +analyze table orc_create_people partition(state) compute statistics noscan; desc formatted orc_create_people partition(state="Ca"); desc formatted orc_create_people partition(state="Or"); @@ -174,8 +193,15 @@ ALTER TABLE orc_create_people SET SERDE 'org.apache.hadoop.hive.ql.io.orc.OrcSer ALTER TABLE orc_create_people SET FILEFORMAT ORC; set hive.stats.autogather = true; -analyze table orc_create_people partition(state) compute statistics noscan; +analyze table orc_create_people partition(state) compute statistics; +desc formatted orc_create_people partition(state="Ca"); +desc formatted orc_create_people partition(state="OH"); +analyze table orc_create_people partition(state) compute statistics partialscan; +desc formatted orc_create_people partition(state="Ca"); +desc formatted orc_create_people partition(state="OH"); + +analyze table orc_create_people partition(state) compute statistics noscan; desc formatted orc_create_people partition(state="Ca"); desc formatted orc_create_people partition(state="OH"); diff --git ql/src/test/results/clientpositive/annotate_stats_part.q.out ql/src/test/results/clientpositive/annotate_stats_part.q.out index f003576..ddd6465c 100644 --- ql/src/test/results/clientpositive/annotate_stats_part.q.out +++ ql/src/test/results/clientpositive/annotate_stats_part.q.out @@ -109,14 +109,12 @@ PREHOOK: query: -- partition level analyze statistics for specific parition analyze table loc_orc partition(year='2001') compute statistics PREHOOK: type: QUERY PREHOOK: Input: default@loc_orc -PREHOOK: Input: default@loc_orc@year=2001 PREHOOK: Output: default@loc_orc PREHOOK: Output: default@loc_orc@year=2001 POSTHOOK: query: -- partition level analyze statistics for specific parition analyze table loc_orc partition(year='2001') compute statistics POSTHOOK: type: QUERY POSTHOOK: Input: default@loc_orc -POSTHOOK: Input: default@loc_orc@year=2001 POSTHOOK: Output: default@loc_orc POSTHOOK: Output: default@loc_orc@year=2001 PREHOOK: query: -- basicStatState: PARTIAL colStatState: NONE @@ -158,11 +156,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 10 Data size: 767 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 7 Data size: 678 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 7 Data size: 678 Basic stats: PARTIAL Column stats: PARTIAL ListSink PREHOOK: query: -- basicStatState: COMPLETE colStatState: NONE @@ -181,19 +179,17 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 7 Data size: 425 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 678 Basic stats: COMPLETE Column stats: NONE 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: 425 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 678 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: -- partition level analyze statistics for all partitions analyze table loc_orc partition(year) compute statistics PREHOOK: type: QUERY PREHOOK: Input: default@loc_orc -PREHOOK: Input: default@loc_orc@year=2001 -PREHOOK: Input: default@loc_orc@year=__HIVE_DEFAULT_PARTITION__ PREHOOK: Output: default@loc_orc PREHOOK: Output: default@loc_orc@year=2001 PREHOOK: Output: default@loc_orc@year=__HIVE_DEFAULT_PARTITION__ @@ -201,8 +197,6 @@ POSTHOOK: query: -- partition level analyze statistics for all partitions analyze table loc_orc partition(year) compute statistics POSTHOOK: type: QUERY POSTHOOK: Input: default@loc_orc -POSTHOOK: Input: default@loc_orc@year=2001 -POSTHOOK: Input: default@loc_orc@year=__HIVE_DEFAULT_PARTITION__ POSTHOOK: Output: default@loc_orc POSTHOOK: Output: default@loc_orc@year=2001 POSTHOOK: Output: default@loc_orc@year=__HIVE_DEFAULT_PARTITION__ @@ -222,11 +216,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 1 Data size: 342 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE 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: 342 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: -- basicStatState: COMPLETE colStatState: NONE @@ -245,7 +239,7 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 767 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 @@ -268,7 +262,7 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 767 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 @@ -331,11 +325,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 767 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: zip (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 8 Data size: 767 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: -- basicStatState: COMPLETE colStatState: PARTIAL @@ -354,7 +348,7 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 767 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string) outputColumnNames: _col0 @@ -377,7 +371,7 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 767 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: year (type: string) outputColumnNames: _col0 @@ -402,7 +396,7 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 767 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int) outputColumnNames: _col0, _col1 @@ -425,7 +419,7 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 7 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 678 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) outputColumnNames: _col0, _col1 @@ -448,11 +442,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 1 Data size: 342 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: state (type: string), locid (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 342 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: -- basicStatState: COMPLETE colStatState: PARTIAL @@ -471,7 +465,7 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 767 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 @@ -496,7 +490,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: loc_orc - Statistics: Num rows: 7 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 678 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid > 0) (type: boolean) Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -532,7 +526,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: loc_orc - Statistics: Num rows: 7 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 678 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid > 0) (type: boolean) Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -568,7 +562,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: loc_orc - Statistics: Num rows: 7 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 678 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid > 0) (type: boolean) Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/annotate_stats_table.q.out ql/src/test/results/clientpositive/annotate_stats_table.q.out index d89e669..efc4de8 100644 --- ql/src/test/results/clientpositive/annotate_stats_table.q.out +++ ql/src/test/results/clientpositive/annotate_stats_table.q.out @@ -122,11 +122,11 @@ STAGE PLANS: Processor Tree: TableScan alias: emp_orc - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lastname (type: string), deptid (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: -- column level partial statistics @@ -155,7 +155,7 @@ STAGE PLANS: Processor Tree: TableScan alias: emp_orc - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: lastname (type: string), deptid (type: int) outputColumnNames: _col0, _col1 @@ -180,7 +180,7 @@ STAGE PLANS: Processor Tree: TableScan alias: emp_orc - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int) outputColumnNames: _col0 @@ -213,7 +213,7 @@ STAGE PLANS: Processor Tree: TableScan alias: emp_orc - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int) outputColumnNames: _col0, _col1 @@ -236,7 +236,7 @@ STAGE PLANS: Processor Tree: TableScan alias: emp_orc - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string) outputColumnNames: _col0 @@ -259,7 +259,7 @@ STAGE PLANS: Processor Tree: TableScan alias: emp_orc - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptid (type: int) outputColumnNames: _col0 @@ -282,7 +282,7 @@ STAGE PLANS: Processor Tree: TableScan alias: emp_orc - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lastname (type: string), deptid (type: int) outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/limit_pushdown.q.out ql/src/test/results/clientpositive/limit_pushdown.q.out index 7a051f6..c7ab7b3 100644 --- ql/src/test/results/clientpositive/limit_pushdown.q.out +++ ql/src/test/results/clientpositive/limit_pushdown.q.out @@ -352,34 +352,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -435,22 +435,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT _col1) keys: _col0 (type: tinyint), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Reduce Operator Tree: Group By Operator @@ -458,13 +458,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -522,22 +522,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT _col1), count(DISTINCT _col2) keys: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Reduce Operator Tree: Group By Operator @@ -545,13 +545,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/orc_analyze.q.out ql/src/test/results/clientpositive/orc_analyze.q.out index 60a23d4..b0e2ea5 100644 --- ql/src/test/results/clientpositive/orc_analyze.q.out +++ ql/src/test/results/clientpositive/orc_analyze.q.out @@ -71,6 +71,55 @@ POSTHOOK: Lineage: orc_create_people.last_name SIMPLE [(orc_create_people_stagin POSTHOOK: Lineage: orc_create_people.salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] POSTHOOK: Lineage: orc_create_people.start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] POSTHOOK: Lineage: orc_create_people.state SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:state, type:string, comment:null), ] +PREHOOK: query: analyze table orc_create_people compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: analyze table orc_create_people compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: desc formatted orc_create_people +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp +state string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Protect Mode: None +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 100 + rawDataSize 52600 + totalSize 3158 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 PREHOOK: query: analyze table orc_create_people compute statistics partialscan PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people @@ -120,6 +169,55 @@ Bucket Columns: [] Sort Columns: [] Storage Desc Params: serialization.format 1 +PREHOOK: query: analyze table orc_create_people compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: analyze table orc_create_people compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: desc formatted orc_create_people +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp +state string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Protect Mode: None +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 100 + rawDataSize 52600 + totalSize 3158 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 PREHOOK: query: drop table orc_create_people PREHOOK: type: DROPTABLE PREHOOK: Input: default@orc_create_people @@ -269,13 +367,13 @@ POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_ POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] -PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people PREHOOK: Output: default@orc_create_people PREHOOK: Output: default@orc_create_people@state=Ca PREHOOK: Output: default@orc_create_people@state=Or -POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics POSTHOOK: type: QUERY POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people @@ -371,63 +469,18 @@ Bucket Columns: [] Sort Columns: [] Storage Desc Params: serialization.format 1 -PREHOOK: query: drop table orc_create_people -PREHOOK: type: DROPTABLE +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people PREHOOK: Output: default@orc_create_people -POSTHOOK: query: drop table orc_create_people -POSTHOOK: type: DROPTABLE +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: type: QUERY POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people -PREHOOK: query: -- auto stats gather -CREATE TABLE orc_create_people ( - id int, - first_name string, - last_name string, - address string, - salary decimal, - start_date timestamp) -PARTITIONED BY (state string) -STORED AS orc -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: -- auto stats gather -CREATE TABLE orc_create_people ( - id int, - first_name string, - last_name string, - address string, - salary decimal, - start_date timestamp) -PARTITIONED BY (state string) -STORED AS orc -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@orc_create_people -PREHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) - SELECT * FROM orc_create_people_staging ORDER BY id -PREHOOK: type: QUERY -PREHOOK: Input: default@orc_create_people_staging -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) - SELECT * FROM orc_create_people_staging ORDER BY id -POSTHOOK: type: QUERY -POSTHOOK: Input: default@orc_create_people_staging POSTHOOK: Output: default@orc_create_people@state=Ca POSTHOOK: Output: default@orc_create_people@state=Or -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] PREHOOK: query: desc formatted orc_create_people partition(state="Ca") PREHOOK: type: DESCTABLE PREHOOK: Input: default@orc_create_people @@ -518,78 +571,13 @@ Bucket Columns: [] Sort Columns: [] Storage Desc Params: serialization.format 1 -PREHOOK: query: drop table orc_create_people -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@orc_create_people -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: drop table orc_create_people -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@orc_create_people -POSTHOOK: Output: default@orc_create_people -PREHOOK: query: -- partitioned and bucketed table --- partial scan gather -CREATE TABLE orc_create_people ( - id int, - first_name string, - last_name string, - address string, - salary decimal, - start_date timestamp) -PARTITIONED BY (state string) -clustered by (first_name) -sorted by (last_name) -into 4 buckets -STORED AS orc -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: -- partitioned and bucketed table --- partial scan gather -CREATE TABLE orc_create_people ( - id int, - first_name string, - last_name string, - address string, - salary decimal, - start_date timestamp) -PARTITIONED BY (state string) -clustered by (first_name) -sorted by (last_name) -into 4 buckets -STORED AS orc -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@orc_create_people -PREHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) - SELECT * FROM orc_create_people_staging ORDER BY id -PREHOOK: type: QUERY -PREHOOK: Input: default@orc_create_people_staging -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) - SELECT * FROM orc_create_people_staging ORDER BY id -POSTHOOK: type: QUERY -POSTHOOK: Input: default@orc_create_people_staging -POSTHOOK: Output: default@orc_create_people@state=Ca -POSTHOOK: Output: default@orc_create_people@state=Or -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] -PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people PREHOOK: Output: default@orc_create_people PREHOOK: Output: default@orc_create_people@state=Ca PREHOOK: Output: default@orc_create_people@state=Or -POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan POSTHOOK: type: QUERY POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people @@ -635,9 +623,9 @@ SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat Compressed: No -Num Buckets: 4 -Bucket Columns: [first_name] -Sort Columns: [Order(col:last_name, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: desc formatted orc_create_people partition(state="Or") @@ -680,9 +668,9 @@ SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat Compressed: No -Num Buckets: 4 -Bucket Columns: [first_name] -Sort Columns: [Order(col:last_name, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: drop table orc_create_people @@ -702,9 +690,6 @@ CREATE TABLE orc_create_people ( salary decimal, start_date timestamp) PARTITIONED BY (state string) -clustered by (first_name) -sorted by (last_name) -into 4 buckets STORED AS orc PREHOOK: type: CREATETABLE PREHOOK: Output: database:default @@ -718,9 +703,6 @@ CREATE TABLE orc_create_people ( salary decimal, start_date timestamp) PARTITIONED BY (state string) -clustered by (first_name) -sorted by (last_name) -into 4 buckets STORED AS orc POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default @@ -788,9 +770,9 @@ SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat Compressed: No -Num Buckets: 4 -Bucket Columns: [first_name] -Sort Columns: [Order(col:last_name, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: desc formatted orc_create_people partition(state="Or") @@ -833,9 +815,9 @@ SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat Compressed: No -Num Buckets: 4 -Bucket Columns: [first_name] -Sort Columns: [Order(col:last_name, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: drop table orc_create_people @@ -846,10 +828,534 @@ POSTHOOK: query: drop table orc_create_people POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people -PREHOOK: query: -- create table with partitions containing text and ORC files. --- ORC files implements StatsProvidingRecordReader but text files does not. --- So the partition containing text file should not have statistics. -CREATE TABLE orc_create_people ( +PREHOOK: query: -- partitioned and bucketed table +-- partial scan gather +CREATE TABLE orc_create_people ( + id int, + first_name string, + last_name string, + address string, + salary decimal, + start_date timestamp) +PARTITIONED BY (state string) +clustered by (first_name) +sorted by (last_name) +into 4 buckets +STORED AS orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: -- partitioned and bucketed table +-- partial scan gather +CREATE TABLE orc_create_people ( + id int, + first_name string, + last_name string, + address string, + salary decimal, + start_date timestamp) +PARTITIONED BY (state string) +clustered by (first_name) +sorted by (last_name) +into 4 buckets +STORED AS orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) + SELECT * FROM orc_create_people_staging ORDER BY id +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people_staging +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) + SELECT * FROM orc_create_people_staging ORDER BY id +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people_staging +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="Or") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Or") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Or] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 22050 + totalSize 2071 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="Or") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Or") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Or] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 22050 + totalSize 2071 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="Or") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Or") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Or] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 22050 + totalSize 2071 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: drop table orc_create_people +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: drop table orc_create_people +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: -- auto stats gather +CREATE TABLE orc_create_people ( + id int, + first_name string, + last_name string, + address string, + salary decimal, + start_date timestamp) +PARTITIONED BY (state string) +clustered by (first_name) +sorted by (last_name) +into 4 buckets +STORED AS orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: -- auto stats gather +CREATE TABLE orc_create_people ( + id int, + first_name string, + last_name string, + address string, + salary decimal, + start_date timestamp) +PARTITIONED BY (state string) +clustered by (first_name) +sorted by (last_name) +into 4 buckets +STORED AS orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) + SELECT * FROM orc_create_people_staging ORDER BY id +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people_staging +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) + SELECT * FROM orc_create_people_staging ORDER BY id +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people_staging +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="Or") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Or") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Or] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 22050 + totalSize 2071 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: drop table orc_create_people +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: drop table orc_create_people +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: -- create table with partitions containing text and ORC files. +-- ORC files implements StatsProvidingRecordReader but text files does not. +-- So the partition containing text file should not have statistics. +CREATE TABLE orc_create_people ( id int, first_name string, last_name string, @@ -946,6 +1452,214 @@ POSTHOOK: query: ALTER TABLE orc_create_people SET FILEFORMAT ORC POSTHOOK: type: ALTERTABLE_FILEFORMAT POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=OH +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=OH +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="OH") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="OH") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [OH] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE false + numFiles 1 + numRows -1 + rawDataSize -1 + totalSize 5812 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=OH +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=OH +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="OH") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="OH") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [OH] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE false + numFiles 1 + numRows -1 + rawDataSize -1 + totalSize 5812 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 PREHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people diff --git ql/src/test/results/clientpositive/tez/limit_pushdown.q.out ql/src/test/results/clientpositive/tez/limit_pushdown.q.out index 604d33d..952d7ff 100644 --- ql/src/test/results/clientpositive/tez/limit_pushdown.q.out +++ ql/src/test/results/clientpositive/tez/limit_pushdown.q.out @@ -381,21 +381,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Reducer 2 Reduce Operator Tree: @@ -403,13 +403,13 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -470,22 +470,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT _col1) keys: _col0 (type: tinyint), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Reducer 2 Reduce Operator Tree: @@ -494,13 +494,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -563,22 +563,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT _col1), count(DISTINCT _col2) keys: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Reducer 2 Reduce Operator Tree: @@ -587,13 +587,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/tez/orc_analyze.q.out ql/src/test/results/clientpositive/tez/orc_analyze.q.out index 60a23d4..b0e2ea5 100644 --- ql/src/test/results/clientpositive/tez/orc_analyze.q.out +++ ql/src/test/results/clientpositive/tez/orc_analyze.q.out @@ -71,6 +71,55 @@ POSTHOOK: Lineage: orc_create_people.last_name SIMPLE [(orc_create_people_stagin POSTHOOK: Lineage: orc_create_people.salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] POSTHOOK: Lineage: orc_create_people.start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] POSTHOOK: Lineage: orc_create_people.state SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:state, type:string, comment:null), ] +PREHOOK: query: analyze table orc_create_people compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: analyze table orc_create_people compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: desc formatted orc_create_people +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp +state string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Protect Mode: None +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 100 + rawDataSize 52600 + totalSize 3158 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 PREHOOK: query: analyze table orc_create_people compute statistics partialscan PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people @@ -120,6 +169,55 @@ Bucket Columns: [] Sort Columns: [] Storage Desc Params: serialization.format 1 +PREHOOK: query: analyze table orc_create_people compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: analyze table orc_create_people compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: desc formatted orc_create_people +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp +state string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Protect Mode: None +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 100 + rawDataSize 52600 + totalSize 3158 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 PREHOOK: query: drop table orc_create_people PREHOOK: type: DROPTABLE PREHOOK: Input: default@orc_create_people @@ -269,13 +367,13 @@ POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_ POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] -PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people PREHOOK: Output: default@orc_create_people PREHOOK: Output: default@orc_create_people@state=Ca PREHOOK: Output: default@orc_create_people@state=Or -POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics POSTHOOK: type: QUERY POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people @@ -371,63 +469,18 @@ Bucket Columns: [] Sort Columns: [] Storage Desc Params: serialization.format 1 -PREHOOK: query: drop table orc_create_people -PREHOOK: type: DROPTABLE +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people PREHOOK: Output: default@orc_create_people -POSTHOOK: query: drop table orc_create_people -POSTHOOK: type: DROPTABLE +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: type: QUERY POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people -PREHOOK: query: -- auto stats gather -CREATE TABLE orc_create_people ( - id int, - first_name string, - last_name string, - address string, - salary decimal, - start_date timestamp) -PARTITIONED BY (state string) -STORED AS orc -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: -- auto stats gather -CREATE TABLE orc_create_people ( - id int, - first_name string, - last_name string, - address string, - salary decimal, - start_date timestamp) -PARTITIONED BY (state string) -STORED AS orc -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@orc_create_people -PREHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) - SELECT * FROM orc_create_people_staging ORDER BY id -PREHOOK: type: QUERY -PREHOOK: Input: default@orc_create_people_staging -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) - SELECT * FROM orc_create_people_staging ORDER BY id -POSTHOOK: type: QUERY -POSTHOOK: Input: default@orc_create_people_staging POSTHOOK: Output: default@orc_create_people@state=Ca POSTHOOK: Output: default@orc_create_people@state=Or -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] PREHOOK: query: desc formatted orc_create_people partition(state="Ca") PREHOOK: type: DESCTABLE PREHOOK: Input: default@orc_create_people @@ -518,78 +571,13 @@ Bucket Columns: [] Sort Columns: [] Storage Desc Params: serialization.format 1 -PREHOOK: query: drop table orc_create_people -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@orc_create_people -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: drop table orc_create_people -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@orc_create_people -POSTHOOK: Output: default@orc_create_people -PREHOOK: query: -- partitioned and bucketed table --- partial scan gather -CREATE TABLE orc_create_people ( - id int, - first_name string, - last_name string, - address string, - salary decimal, - start_date timestamp) -PARTITIONED BY (state string) -clustered by (first_name) -sorted by (last_name) -into 4 buckets -STORED AS orc -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: -- partitioned and bucketed table --- partial scan gather -CREATE TABLE orc_create_people ( - id int, - first_name string, - last_name string, - address string, - salary decimal, - start_date timestamp) -PARTITIONED BY (state string) -clustered by (first_name) -sorted by (last_name) -into 4 buckets -STORED AS orc -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@orc_create_people -PREHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) - SELECT * FROM orc_create_people_staging ORDER BY id -PREHOOK: type: QUERY -PREHOOK: Input: default@orc_create_people_staging -PREHOOK: Output: default@orc_create_people -POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) - SELECT * FROM orc_create_people_staging ORDER BY id -POSTHOOK: type: QUERY -POSTHOOK: Input: default@orc_create_people_staging -POSTHOOK: Output: default@orc_create_people@state=Ca -POSTHOOK: Output: default@orc_create_people@state=Or -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] -POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] -PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people PREHOOK: Output: default@orc_create_people PREHOOK: Output: default@orc_create_people@state=Ca PREHOOK: Output: default@orc_create_people@state=Or -POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan POSTHOOK: type: QUERY POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people @@ -635,9 +623,9 @@ SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat Compressed: No -Num Buckets: 4 -Bucket Columns: [first_name] -Sort Columns: [Order(col:last_name, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: desc formatted orc_create_people partition(state="Or") @@ -680,9 +668,9 @@ SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat Compressed: No -Num Buckets: 4 -Bucket Columns: [first_name] -Sort Columns: [Order(col:last_name, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: drop table orc_create_people @@ -702,9 +690,6 @@ CREATE TABLE orc_create_people ( salary decimal, start_date timestamp) PARTITIONED BY (state string) -clustered by (first_name) -sorted by (last_name) -into 4 buckets STORED AS orc PREHOOK: type: CREATETABLE PREHOOK: Output: database:default @@ -718,9 +703,6 @@ CREATE TABLE orc_create_people ( salary decimal, start_date timestamp) PARTITIONED BY (state string) -clustered by (first_name) -sorted by (last_name) -into 4 buckets STORED AS orc POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default @@ -788,9 +770,9 @@ SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat Compressed: No -Num Buckets: 4 -Bucket Columns: [first_name] -Sort Columns: [Order(col:last_name, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: desc formatted orc_create_people partition(state="Or") @@ -833,9 +815,9 @@ SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat Compressed: No -Num Buckets: 4 -Bucket Columns: [first_name] -Sort Columns: [Order(col:last_name, order:1)] +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: drop table orc_create_people @@ -846,10 +828,534 @@ POSTHOOK: query: drop table orc_create_people POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people -PREHOOK: query: -- create table with partitions containing text and ORC files. --- ORC files implements StatsProvidingRecordReader but text files does not. --- So the partition containing text file should not have statistics. -CREATE TABLE orc_create_people ( +PREHOOK: query: -- partitioned and bucketed table +-- partial scan gather +CREATE TABLE orc_create_people ( + id int, + first_name string, + last_name string, + address string, + salary decimal, + start_date timestamp) +PARTITIONED BY (state string) +clustered by (first_name) +sorted by (last_name) +into 4 buckets +STORED AS orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: -- partitioned and bucketed table +-- partial scan gather +CREATE TABLE orc_create_people ( + id int, + first_name string, + last_name string, + address string, + salary decimal, + start_date timestamp) +PARTITIONED BY (state string) +clustered by (first_name) +sorted by (last_name) +into 4 buckets +STORED AS orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) + SELECT * FROM orc_create_people_staging ORDER BY id +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people_staging +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) + SELECT * FROM orc_create_people_staging ORDER BY id +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people_staging +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="Or") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Or") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Or] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 22050 + totalSize 2071 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="Or") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Or") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Or] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 22050 + totalSize 2071 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="Or") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Or") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Or] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 22050 + totalSize 2071 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: drop table orc_create_people +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: drop table orc_create_people +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: -- auto stats gather +CREATE TABLE orc_create_people ( + id int, + first_name string, + last_name string, + address string, + salary decimal, + start_date timestamp) +PARTITIONED BY (state string) +clustered by (first_name) +sorted by (last_name) +into 4 buckets +STORED AS orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: -- auto stats gather +CREATE TABLE orc_create_people ( + id int, + first_name string, + last_name string, + address string, + salary decimal, + start_date timestamp) +PARTITIONED BY (state string) +clustered by (first_name) +sorted by (last_name) +into 4 buckets +STORED AS orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) + SELECT * FROM orc_create_people_staging ORDER BY id +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people_staging +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: INSERT OVERWRITE TABLE orc_create_people PARTITION (state) + SELECT * FROM orc_create_people_staging ORDER BY id +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people_staging +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Ca).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).address SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:address, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).first_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:first_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).id SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:id, type:int, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).last_name SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:last_name, type:string, comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).salary SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:salary, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_create_people PARTITION(state=Or).start_date SIMPLE [(orc_create_people_staging)orc_create_people_staging.FieldSchema(name:start_date, type:timestamp, comment:null), ] +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="Or") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Or") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Or] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 22050 + totalSize 2071 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: 4 +Bucket Columns: [first_name] +Sort Columns: [Order(col:last_name, order:1)] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: drop table orc_create_people +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +POSTHOOK: query: drop table orc_create_people +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +PREHOOK: query: -- create table with partitions containing text and ORC files. +-- ORC files implements StatsProvidingRecordReader but text files does not. +-- So the partition containing text file should not have statistics. +CREATE TABLE orc_create_people ( id int, first_name string, last_name string, @@ -946,6 +1452,214 @@ POSTHOOK: query: ALTER TABLE orc_create_people SET FILEFORMAT ORC POSTHOOK: type: ALTERTABLE_FILEFORMAT POSTHOOK: Input: default@orc_create_people POSTHOOK: Output: default@orc_create_people +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=OH +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=OH +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="OH") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="OH") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [OH] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE false + numFiles 1 + numRows -1 + rawDataSize -1 + totalSize 5812 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_create_people +PREHOOK: Output: default@orc_create_people +PREHOOK: Output: default@orc_create_people@state=Ca +PREHOOK: Output: default@orc_create_people@state=OH +PREHOOK: Output: default@orc_create_people@state=Or +POSTHOOK: query: analyze table orc_create_people partition(state) compute statistics partialscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_create_people +POSTHOOK: Output: default@orc_create_people +POSTHOOK: Output: default@orc_create_people@state=Ca +POSTHOOK: Output: default@orc_create_people@state=OH +POSTHOOK: Output: default@orc_create_people@state=Or +PREHOOK: query: desc formatted orc_create_people partition(state="Ca") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="Ca") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [Ca] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 50 + rawDataSize 21950 + totalSize 2055 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted orc_create_people partition(state="OH") +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@orc_create_people +POSTHOOK: query: desc formatted orc_create_people partition(state="OH") +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@orc_create_people +# col_name data_type comment + +id int +first_name string +last_name string +address string +salary decimal(10,0) +start_date timestamp + +# Partition Information +# col_name data_type comment + +state string + +# Detailed Partition Information +Partition Value: [OH] +Database: default +Table: orc_create_people +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE false + numFiles 1 + numRows -1 + rawDataSize -1 + totalSize 5812 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 PREHOOK: query: analyze table orc_create_people partition(state) compute statistics noscan PREHOOK: type: QUERY PREHOOK: Input: default@orc_create_people diff --git ql/src/test/results/clientpositive/tez/vector_char_simple.q.out ql/src/test/results/clientpositive/tez/vector_char_simple.q.out index fe651ca..9c72edb 100644 --- ql/src/test/results/clientpositive/tez/vector_char_simple.q.out +++ ql/src/test/results/clientpositive/tez/vector_char_simple.q.out @@ -271,17 +271,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized Reducer 2 @@ -289,17 +289,17 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( _col0 AS CHAR(12) (type: char(12)) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out index ce6a473..ce722e8 100644 --- ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out +++ ql/src/test/results/clientpositive/tez/vector_left_outer_join.q.out @@ -32,11 +32,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: c - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 @@ -46,7 +46,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - Statistics: Num rows: 13516 Data size: 414960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 @@ -55,7 +55,7 @@ STAGE PLANS: 1 _col0 (type: tinyint) input vertices: 1 Map 4 - Statistics: Num rows: 14867 Data size: 456456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14867 Data size: 3196776 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -70,31 +70,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: c - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 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: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 4 Map Operator Tree: TableScan alias: c - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/tez/vector_varchar_simple.q.out ql/src/test/results/clientpositive/tez/vector_varchar_simple.q.out index f3d9147..e90eefa 100644 --- ql/src/test/results/clientpositive/tez/vector_varchar_simple.q.out +++ ql/src/test/results/clientpositive/tez/vector_varchar_simple.q.out @@ -271,17 +271,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized Reducer 2 @@ -289,17 +289,17 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( _col0 AS varchar(25)) (type: varchar(25)) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git ql/src/test/results/clientpositive/tez/vectorization_0.q.out ql/src/test/results/clientpositive/tez/vectorization_0.q.out index cd03692..250f3d3 100644 --- ql/src/test/results/clientpositive/tez/vectorization_0.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_0.q.out @@ -32,11 +32,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: ctinyint - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(ctinyint), max(ctinyint), count(ctinyint), count() mode: hash @@ -126,11 +126,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) mode: hash @@ -229,11 +229,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: ctinyint - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(ctinyint), variance(ctinyint), var_pop(ctinyint), var_samp(ctinyint), std(ctinyint), stddev(ctinyint), stddev_pop(ctinyint), stddev_samp(ctinyint) mode: hash @@ -338,11 +338,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) outputColumnNames: cbigint - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(cbigint), max(cbigint), count(cbigint), count() mode: hash @@ -432,11 +432,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) mode: hash @@ -535,11 +535,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) outputColumnNames: cbigint - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(cbigint), variance(cbigint), var_pop(cbigint), var_samp(cbigint), std(cbigint), stddev(cbigint), stddev_pop(cbigint), stddev_samp(cbigint) mode: hash @@ -644,11 +644,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) outputColumnNames: cfloat - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(cfloat), max(cfloat), count(cfloat), count() mode: hash @@ -738,11 +738,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) mode: hash @@ -841,11 +841,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) outputColumnNames: cfloat - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(cfloat), variance(cfloat), var_pop(cfloat), var_samp(cfloat), std(cfloat), stddev(cfloat), stddev_pop(cfloat), stddev_samp(cfloat) mode: hash @@ -988,14 +988,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cstring2 like '%b%') or ((79.553 <> UDFToDouble(cint)) or (UDFToDouble(cbigint) < cdouble))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(_col0), stddev_pop(_col0), var_samp(_col0), count(), sum(_col1), min(_col2) mode: hash diff --git ql/src/test/results/clientpositive/tez/vectorization_13.q.out ql/src/test/results/clientpositive/tez/vectorization_13.q.out index e47c2ae..55a68c2 100644 --- ql/src/test/results/clientpositive/tez/vectorization_13.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_13.q.out @@ -80,25 +80,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((UDFToDouble(ctimestamp1) > 11.0) and ((UDFToDouble(ctimestamp2) <> 12.0) and (UDFToDouble(ctinyint) < 9763215.5639)))) (type: boolean) - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized Reducer 2 @@ -108,28 +108,28 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col2 (type: timestamp), _col10 (type: tinyint), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col14, _col15, _col16, _col17, _col18, _col19, _col2, _col20, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), VALUE._col0 (type: tinyint), VALUE._col1 (type: tinyint), VALUE._col2 (type: tinyint), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col5 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: float), VALUE._col13 (type: double), VALUE._col14 (type: tinyint) 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: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -334,25 +334,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((UDFToDouble(ctimestamp1) > -1.388) and ((UDFToDouble(ctimestamp2) <> -1.3359999999999999) and (UDFToDouble(ctinyint) < 9763215.5639)))) (type: boolean) - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized Reducer 2 @@ -362,28 +362,28 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col2 (type: timestamp), _col10 (type: tinyint), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col14, _col15, _col16, _col17, _col18, _col19, _col2, _col20, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), VALUE._col0 (type: tinyint), VALUE._col1 (type: tinyint), VALUE._col2 (type: tinyint), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col5 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: float), VALUE._col13 (type: double), VALUE._col14 (type: tinyint) 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: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/tez/vectorization_14.q.out ql/src/test/results/clientpositive/tez/vectorization_14.q.out index 8ca24aa..cc2b6cc 100644 --- ql/src/test/results/clientpositive/tez/vectorization_14.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_14.q.out @@ -80,25 +80,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((UDFToLong(ctinyint) <= cbigint) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1))) and (cdouble < UDFToDouble(ctinyint))) and ((cbigint > -257) or (cfloat < UDFToFloat(cint)))) (type: boolean) - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28 + cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(_col5), max(_col1), stddev_pop(_col1), count(_col1), var_pop(_col1), var_samp(_col1) keys: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double) sort order: +++++ Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double) - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: struct), _col6 (type: float), _col7 (type: struct), _col8 (type: bigint), _col9 (type: struct), _col10 (type: struct) Execution mode: vectorized Reducer 2 @@ -108,25 +108,25 @@ STAGE PLANS: keys: KEY._col0 (type: timestamp), KEY._col1 (type: float), KEY._col2 (type: string), KEY._col3 (type: boolean), KEY._col4 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double), (-26.28 + _col4) (type: double), (- (-26.28 + _col4)) (type: double), _col5 (type: double), (UDFToDouble(_col1) * -26.28) (type: double), _col6 (type: float), (- _col1) (type: float), (- _col6) (type: float), ((- (-26.28 + _col4)) / 10.175) (type: double), _col7 (type: double), _col8 (type: bigint), (- ((- (-26.28 + _col4)) / 10.175)) (type: double), (-1.389 % _col5) (type: double), (UDFToDouble(_col1) - _col4) (type: double), _col9 (type: double), (_col9 % 10.175) (type: double), _col10 (type: double), (- (UDFToDouble(_col1) - _col4)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp) sort order: ++++ - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/tez/vectorization_15.q.out ql/src/test/results/clientpositive/tez/vectorization_15.q.out index 8140494..779c37f 100644 --- ql/src/test/results/clientpositive/tez/vectorization_15.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_15.q.out @@ -76,25 +76,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cstring2 like '%ss%') or ((cstring1 like '10%') or ((cint >= -75) and ((UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(_col0), min(_col2), stddev_samp(_col4), var_pop(_col4), var_samp(_col5), stddev_pop(_col5) keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) sort order: +++++++ Map-reduce partition columns: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: struct), _col8 (type: double), _col9 (type: struct), _col10 (type: struct), _col11 (type: struct), _col12 (type: struct) Execution mode: vectorized Reducer 2 @@ -104,25 +104,25 @@ STAGE PLANS: keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), _col7 (type: double), (-26.28 - UDFToDouble(_col5)) (type: double), _col8 (type: double), (_col2 * 79.553) (type: double), (33.0 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - UDFToDouble(_col5))) (type: double), _col12 (type: double) 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) sort order: +++++++ - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: double), _col20 (type: double) Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: double), VALUE._col13 (type: double) 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/tez/vectorization_16.q.out ql/src/test/results/clientpositive/tez/vectorization_16.q.out index fe1fc72..bfed7d1 100644 --- ql/src/test/results/clientpositive/tez/vectorization_16.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_16.q.out @@ -57,25 +57,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1), stddev_samp(_col1), min(_col1) keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized Reducer 2 @@ -85,14 +85,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/tez/vectorization_7.q.out ql/src/test/results/clientpositive/tez/vectorization_7.q.out index 1e7019b..34f590d 100644 --- ql/src/test/results/clientpositive/tez/vectorization_7.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_7.q.out @@ -63,20 +63,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or ((UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')))) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > -15.0) and (3569.0 >= cdouble)))) (type: boolean) - Statistics: Num rows: 7281 Data size: 223523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 7281 Data size: 223523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -235,20 +235,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or ((UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')))) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > 7.6850000000000005) and (3569.0 >= cdouble)))) (type: boolean) - Statistics: Num rows: 7281 Data size: 223523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 7281 Data size: 223523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/tez/vectorization_8.q.out ql/src/test/results/clientpositive/tez/vectorization_8.q.out index 3bd5183..912f5a7 100644 --- ql/src/test/results/clientpositive/tez/vectorization_8.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_8.q.out @@ -59,20 +59,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cstring2 is not null and ((UDFToDouble(ctimestamp1) <= 10.0) and (UDFToDouble(ctimestamp2) <> 16.0))) or ((cfloat < -6432.0) or (cboolean1 is not null and (cdouble = 988888.0)))) (type: boolean) - Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15 - cdouble) (type: double), (cdouble * -257.0) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), ((-5638.15 - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -218,20 +218,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cstring2 is not null and ((UDFToDouble(ctimestamp1) <= 12.503) and (UDFToDouble(ctimestamp2) <> 11.998))) or ((cfloat < -6432.0) or (cboolean1 is not null and (cdouble = 988888.0)))) (type: boolean) - Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15 - cdouble) (type: double), (cdouble * -257.0) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), ((-5638.15 - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/tez/vectorization_9.q.out ql/src/test/results/clientpositive/tez/vectorization_9.q.out index be6c6c9..c0e9a3e 100644 --- ql/src/test/results/clientpositive/tez/vectorization_9.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_9.q.out @@ -53,25 +53,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1), stddev_samp(_col1), min(_col1) keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized Reducer 2 @@ -81,14 +81,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/tez/vectorization_div0.q.out ql/src/test/results/clientpositive/tez/vectorization_div0.q.out index fdf82d4..49dc346 100644 --- ql/src/test/results/clientpositive/tez/vectorization_div0.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_div0.q.out @@ -160,18 +160,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cbigint > 0) and (cbigint < 100000000)) (type: boolean) - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cbigint - 988888) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888))) (type: double), (1.2 / UDFToDouble((cbigint - 988888))) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: bigint), _col1 (type: double) sort order: ++ - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: double) Execution mode: vectorized Reducer 2 @@ -179,13 +179,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 3000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 3000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -335,18 +335,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cdouble >= -500.0) and (cdouble < -199.0)) (type: boolean) - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdouble + 200.0) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0)) (type: double), ((cdouble + 200.0) / (cdouble + 200.0)) (type: double), (3.0 / (cdouble + 200.0)) (type: double), (1.2 / (cdouble + 200.0)) (type: double) outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: double) sort order: ++ - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: double), _col4 (type: double), _col5 (type: double) Execution mode: vectorized Reducer 2 @@ -354,13 +354,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 3000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 3000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/tez/vectorization_limit.q.out ql/src/test/results/clientpositive/tez/vectorization_limit.q.out index 6e0edd4..d815938 100644 --- ql/src/test/results/clientpositive/tez/vectorization_limit.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_limit.q.out @@ -63,18 +63,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: smallint) Execution mode: vectorized @@ -83,13 +83,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -153,22 +153,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), (cdouble + 1.0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(_col1) keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 value expressions: _col1 (type: struct) Execution mode: vectorized @@ -179,13 +179,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -248,21 +248,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Reducer 2 @@ -271,13 +271,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -339,22 +339,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT _col1) keys: _col0 (type: tinyint), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Reducer 2 @@ -364,13 +364,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -460,25 +460,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), ctinyint (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1) keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reducer 2 @@ -488,11 +488,11 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: bigint), _col0 (type: double) sort order: ++ - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Reducer 3 @@ -500,13 +500,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: double), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/tez/vectorization_pushdown.q.out ql/src/test/results/clientpositive/tez/vectorization_pushdown.q.out index 25057df..e203bfd 100644 --- ql/src/test/results/clientpositive/tez/vectorization_pushdown.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_pushdown.q.out @@ -19,14 +19,14 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(_col0) mode: hash diff --git ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out index b17ce20..a3c723d 100644 --- ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out +++ ql/src/test/results/clientpositive/tez/vectorization_short_regress.q.out @@ -146,14 +146,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((762 = cbigint) or (((UDFToFloat(csmallint) < cfloat) and ((UDFToDouble(ctimestamp2) > -5.0) and (cdouble <> UDFToDouble(cint)))) or ((cstring1 = 'a') or ((UDFToDouble(cbigint) <= -1.389) and ((cstring2 <> 'a') and ((79.553 <> UDFToDouble(cint)) and (cboolean2 <> cboolean1))))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), csmallint (type: smallint), cfloat (type: float), ctinyint (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(_col0), sum(_col1), stddev_pop(_col0), stddev_samp(_col2), var_samp(_col0), avg(_col3), stddev_samp(_col0), min(_col4), count(_col2) mode: hash @@ -358,14 +358,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((cbigint <= 197) and (UDFToLong(cint) < cbigint)) or (((cdouble >= -26.28) and (UDFToDouble(csmallint) > cdouble)) or (((UDFToFloat(ctinyint) > cfloat) and (cstring1 rlike '.*ss.*')) or ((cfloat > 79.553) and (cstring2 like '10%'))))) (type: boolean) - Statistics: Num rows: 6826 Data size: 209555 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), csmallint (type: smallint), cdouble (type: double), ctinyint (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6826 Data size: 209555 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col0), var_pop(_col1), stddev_pop(_col2), max(_col3), avg(_col4), min(_col0), min(_col3), stddev_samp(_col2), var_samp(_col0) mode: hash @@ -561,14 +561,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((ctimestamp1 = ctimestamp2) or ((762.0 = cfloat) or ((cstring1 = 'ss') or (((UDFToLong(csmallint) <= cbigint) and (1 = cboolean2)) or (cboolean1 is not null and (ctimestamp2 is not null and (cstring2 > 'a'))))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cdouble (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: var_pop(_col0), count(), max(_col1), stddev_pop(_col2), max(_col3), stddev_samp(_col4), count(_col1), avg(_col1) mode: hash @@ -743,14 +743,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((ctimestamp2 <= ctimestamp1) and ((UDFToDouble(cbigint) <> cdouble) and ('ss' <= cstring1))) or (((csmallint < UDFToShort(ctinyint)) and (UDFToDouble(ctimestamp1) >= 0.0)) or (cfloat = 17.0))) (type: boolean) - Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cbigint (type: bigint), cint (type: int), cfloat (type: float) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(_col0), max(_col1), stddev_samp(_col2), var_pop(_col2), var_pop(_col1), max(_col3) mode: hash @@ -933,18 +933,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((cstring1 rlike 'a.*') and (cstring2 like '%ss%')) or (((1 <> cboolean2) and ((UDFToDouble(csmallint) < 79.553) and (-257 <> UDFToInteger(ctinyint)))) or (((cdouble > UDFToDouble(ctinyint)) and (cfloat >= UDFToFloat(cint))) or ((UDFToLong(cint) < cbigint) and (UDFToLong(ctinyint) > cbigint))))) (type: boolean) - Statistics: Num rows: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), ctimestamp2 (type: timestamp), cstring1 (type: string), cboolean2 (type: boolean), ctinyint (type: tinyint), cfloat (type: float), ctimestamp1 (type: timestamp), csmallint (type: smallint), cbigint (type: bigint), (-3728 * cbigint) (type: bigint), (- cint) (type: int), (-863.257 - UDFToDouble(cint)) (type: double), (- csmallint) (type: smallint), (csmallint - (- csmallint)) (type: smallint), ((csmallint - (- csmallint)) + (- csmallint)) (type: smallint), (UDFToDouble(cint) / UDFToDouble(cint)) (type: double), ((-863.257 - UDFToDouble(cint)) - -26.28) (type: double), (- cfloat) (type: float), (cdouble * -89010.0) (type: double), (UDFToDouble(ctinyint) / 988888.0) (type: double), (- ctinyint) (type: tinyint), (79.553 / UDFToDouble(ctinyint)) (type: double) 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: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: timestamp), _col3 (type: string), _col4 (type: boolean), _col5 (type: tinyint), _col6 (type: float), _col7 (type: timestamp), _col8 (type: smallint), _col9 (type: bigint) sort order: ++++++++++ - Statistics: Num rows: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE value expressions: _col10 (type: bigint), _col11 (type: int), _col12 (type: double), _col13 (type: smallint), _col14 (type: smallint), _col15 (type: smallint), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: double), _col21 (type: tinyint), _col22 (type: double) Execution mode: vectorized Reducer 2 @@ -952,13 +952,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: boolean), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: float), KEY.reducesinkkey7 (type: timestamp), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: bigint), VALUE._col0 (type: bigint), VALUE._col1 (type: int), VALUE._col2 (type: double), VALUE._col3 (type: smallint), VALUE._col4 (type: smallint), VALUE._col5 (type: smallint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: float), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: tinyint), VALUE._col12 (type: double) 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: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 - Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1192,18 +1192,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((197.0 > UDFToDouble(ctinyint)) and (UDFToLong(cint) = cbigint)) or ((cbigint = 359) or ((cboolean1 < 0) or ((cstring1 like '%ss') and (cfloat <= UDFToFloat(ctinyint)))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), (UDFToDouble(cint) / UDFToDouble(cbigint)) (type: double), (UDFToDouble(cbigint) % 79.553) (type: double), (- (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (10.175 % UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), (cfloat - (- cfloat)) (type: float), ((cfloat - (- cfloat)) % -6432.0) (type: float), (cdouble * UDFToDouble(csmallint)) (type: double), (- cdouble) (type: double), (- cbigint) (type: bigint), cstring1 (type: string), (UDFToDouble(cfloat) - (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (- csmallint) (type: smallint), (3569 % cbigint) (type: bigint), (359.0 - cdouble) (type: double), cboolean1 (type: boolean), cfloat (type: float), cdouble (type: double), ctimestamp2 (type: timestamp), csmallint (type: smallint), cstring2 (type: string), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col2, _col20, _col21, _col22, _col23, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean), _col4 (type: float), _col5 (type: double), _col6 (type: timestamp), _col7 (type: smallint), _col8 (type: string), _col9 (type: boolean) sort order: ++++++++++ - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: float), _col15 (type: float), _col16 (type: float), _col17 (type: double), _col18 (type: double), _col19 (type: bigint), _col20 (type: double), _col21 (type: smallint), _col22 (type: bigint), _col23 (type: double) Execution mode: vectorized Reducer 2 @@ -1211,13 +1211,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: boolean), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: timestamp), KEY.reducesinkkey7 (type: smallint), KEY.reducesinkkey8 (type: string), KEY.reducesinkkey9 (type: boolean), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: bigint), VALUE._col10 (type: double), VALUE._col11 (type: smallint), VALUE._col12 (type: bigint), VALUE._col13 (type: double), VALUE._col11 (type: smallint) 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 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1400,18 +1400,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((UDFToDouble(csmallint) > -26.28) and (cstring2 like 'ss')) or (((cdouble <= UDFToDouble(cbigint)) and ((cstring1 >= 'ss') and (UDFToDouble(cint) <> cdouble))) or ((UDFToInteger(ctinyint) = -89010) or ((UDFToFloat(cbigint) <= cfloat) and (-26.28 <= UDFToDouble(csmallint)))))) (type: boolean) - Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cstring1 (type: string), cboolean2 (type: boolean), ctimestamp2 (type: timestamp), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), cboolean1 (type: boolean), (cint + UDFToInteger(csmallint)) (type: int), (cbigint - UDFToLong(ctinyint)) (type: bigint), (- cbigint) (type: bigint), (- cfloat) (type: float), ((cbigint - UDFToLong(ctinyint)) + cbigint) (type: bigint), (cdouble / cdouble) (type: double), (- cdouble) (type: double), (UDFToLong((cint + UDFToInteger(csmallint))) * (- cbigint)) (type: bigint), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (-1.389 / UDFToDouble(ctinyint)) (type: double), (UDFToDouble(cbigint) % cdouble) (type: double), (- csmallint) (type: smallint), (UDFToInteger(csmallint) + (cint + UDFToInteger(csmallint))) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: boolean), _col1 (type: string), _col3 (type: timestamp), _col5 (type: float), _col6 (type: bigint), _col1 (type: string), _col4 (type: double), _col0 (type: int), _col7 (type: smallint), _col4 (type: double) sort order: ++++++++++ - Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: boolean), _col9 (type: int), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: float), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: smallint), _col21 (type: int) Execution mode: vectorized Reducer 2 @@ -1419,13 +1419,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey7 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey0 (type: boolean), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: float), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: bigint), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: smallint), VALUE._col13 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 75 - Statistics: Num rows: 75 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75 Data size: 16125 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 75 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75 Data size: 16125 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1666,18 +1666,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((-1.389 >= UDFToDouble(cint)) and ((csmallint < UDFToShort(ctinyint)) and (-6432 > UDFToInteger(csmallint)))) or (((cdouble >= UDFToDouble(cfloat)) and (cstring2 <= 'a')) or ((cstring1 like 'ss%') and (10.175 > UDFToDouble(cbigint))))) (type: boolean) - Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cstring2 (type: string), (cdouble * 10.175) (type: double), (UDFToDouble((-6432.0 * cfloat)) / UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), (cint % UDFToInteger(csmallint)) (type: int), (cdouble * (- cdouble)) (type: double), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), (UDFToDouble(cbigint) / 3569.0) (type: double), (-257 - UDFToInteger(csmallint)) (type: int), (-6432.0 * cfloat) (type: float), (- cdouble) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col15, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col5 (type: smallint), _col1 (type: string), _col2 (type: double) sort order: +++ - Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: timestamp), _col3 (type: float), _col4 (type: bigint), _col6 (type: double), _col7 (type: int), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: float), _col13 (type: int), _col15 (type: double) Execution mode: vectorized Reducer 2 @@ -1685,13 +1685,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: timestamp), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: float), VALUE._col2 (type: bigint), KEY.reducesinkkey0 (type: smallint), VALUE._col3 (type: double), VALUE._col4 (type: int), VALUE._col5 (type: float), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: float), VALUE._col10 (type: int), VALUE._col6 (type: double), VALUE._col11 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 45 - Statistics: Num rows: 45 Data size: 1350 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 45 Data size: 9675 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 45 Data size: 1350 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 45 Data size: 9675 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1874,25 +1874,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToInteger(csmallint) >= -257) and ((-6432 = UDFToInteger(csmallint)) or ((UDFToDouble(cint) >= cdouble) and (UDFToInteger(ctinyint) <= cint)))) (type: boolean) - Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cbigint (type: bigint), ctinyint (type: tinyint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(_col0), sum(_col1), var_pop(_col2), count() keys: _col0 (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct), _col2 (type: bigint), _col3 (type: struct), _col4 (type: bigint) Execution mode: vectorized Reducer 2 @@ -1902,28 +1902,28 @@ STAGE PLANS: keys: KEY._col0 (type: smallint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: smallint), (UDFToInteger(_col0) % -75) (type: int), _col1 (type: double), (-1.389 / UDFToDouble(_col0)) (type: double), _col2 (type: bigint), (UDFToDouble((UDFToInteger(_col0) % -75)) / UDFToDouble(_col2)) (type: double), (- (UDFToInteger(_col0) % -75)) (type: int), _col3 (type: double), (- (- (UDFToInteger(_col0) % -75))) (type: int), _col4 (type: bigint), (_col4 - -89010) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + - Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: int), _col7 (type: double), _col8 (type: int), _col9 (type: bigint), _col10 (type: bigint) Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: smallint), VALUE._col0 (type: int), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: int), VALUE._col6 (type: double), VALUE._col7 (type: int), VALUE._col8 (type: bigint), VALUE._col9 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2082,25 +2082,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and ((UDFToInteger(csmallint) < cint) and (UDFToDouble(cfloat) < -5638.15))) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > UDFToDouble(cbigint))))) (type: boolean) - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) outputColumnNames: _col0, _col1 - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: var_samp(_col0), count(_col1), sum(_col1), var_pop(_col0), stddev_pop(_col0), sum(_col0) keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct), _col2 (type: bigint), _col3 (type: double), _col4 (type: struct), _col5 (type: struct), _col6 (type: double) Execution mode: vectorized Reducer 2 @@ -2110,25 +2110,25 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: double), _col1 (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762.0) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762.0)) (type: double), (2563.58 * _col1) (type: double), (- _col1) (type: double), _col2 (type: bigint), ((2563.58 * _col1) + -5638.15) (type: double), ((- _col1) * ((2563.58 * _col1) + -5638.15)) (type: double), _col3 (type: double), _col4 (type: double), (_col0 - (- _col1)) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double) Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2337,25 +2337,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(ctimestamp1) <> 0.0) and (((-257 <> UDFToInteger(ctinyint)) and (cboolean2 is not null and ((cstring1 rlike '.*ss') and (-3.0 < UDFToDouble(ctimestamp1))))) or ((UDFToDouble(ctimestamp2) = -5.0) or (((UDFToDouble(ctimestamp1) < 0.0) and (cstring2 like '%b%')) or ((cdouble = UDFToDouble(cint)) or (cboolean1 is null and (cfloat < UDFToFloat(cint)))))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cstring1 (type: string), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_pop(_col2), avg(_col3), count(), min(_col4), var_samp(_col3), var_pop(_col5), avg(_col2), var_samp(_col5), avg(_col5), min(_col6), var_pop(_col3), stddev_pop(_col4), sum(_col2) keys: _col0 (type: timestamp), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: string) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: bigint), _col5 (type: tinyint), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct), _col11 (type: double), _col12 (type: struct), _col13 (type: struct), _col14 (type: bigint) Execution mode: vectorized Reducer 2 @@ -2365,28 +2365,28 @@ STAGE PLANS: keys: KEY._col0 (type: timestamp), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: timestamp), _col1 (type: string), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col2 (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (_col2 * 10.175) (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / UDFToDouble((- _col5))) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double), (- _col2) (type: double), _col3 (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col2, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col3, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col38, _col4, _col5, _col7, _col8, _col9 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: string) sort order: ++ - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double), _col11 (type: tinyint), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double), _col22 (type: double), _col23 (type: double), _col24 (type: double), _col25 (type: double), _col26 (type: double), _col27 (type: tinyint), _col28 (type: double), _col29 (type: double), _col30 (type: double), _col31 (type: double), _col32 (type: double), _col33 (type: double), _col34 (type: bigint), _col35 (type: double), _col36 (type: bigint), _col38 (type: double) Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col2 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: bigint), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double), VALUE._col18 (type: double), VALUE._col19 (type: double), VALUE._col20 (type: double), VALUE._col21 (type: double), VALUE._col22 (type: double), VALUE._col23 (type: double), VALUE._col24 (type: tinyint), VALUE._col25 (type: double), VALUE._col26 (type: double), VALUE._col27 (type: double), VALUE._col28 (type: double), VALUE._col29 (type: double), VALUE._col30 (type: double), VALUE._col31 (type: bigint), VALUE._col32 (type: double), VALUE._col33 (type: bigint), VALUE._col5 (type: bigint), VALUE._col34 (type: double) 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 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 - Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2670,25 +2670,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (cboolean1 is not null and (((cdouble < UDFToDouble(csmallint)) and ((cboolean2 = cboolean1) and (UDFToDouble(cbigint) <= -863.257))) or (((cint >= -257) and (cstring1 is not null and (cboolean1 >= 1))) or ((cstring2 rlike 'b') or ((csmallint >= UDFToShort(ctinyint)) and ctimestamp2 is null))))) (type: boolean) - Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cbigint (type: bigint), cint (type: int), cdouble (type: double), ctinyint (type: tinyint), csmallint (type: smallint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col1), sum(_col2), var_samp(_col3), avg(_col4), min(_col2), var_pop(_col2), sum(_col3), stddev_samp(_col5), stddev_pop(_col6), avg(_col3) keys: _col0 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + Map-reduce partition columns: _col0 (type: boolean) - Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: float), _col2 (type: bigint), _col3 (type: struct), _col4 (type: struct), _col5 (type: bigint), _col6 (type: struct), _col7 (type: bigint), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct) Execution mode: vectorized Reducer 2 @@ -2698,25 +2698,25 @@ STAGE PLANS: keys: KEY._col0 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: boolean), _col1 (type: float), ((UDFToDouble(_col2) - 10.175) + _col3) (type: double), _col5 (type: bigint), _col6 (type: double), (- (10.175 + UDFToDouble((- _col1)))) (type: double), (79.553 / _col6) (type: double), (_col3 % (79.553 / _col6)) (type: double), _col7 (type: bigint), _col8 (type: double), (-1.389 * UDFToDouble(_col5)) (type: double), (- _col1) (type: float), (UDFToDouble(_col7) - (-1.389 * UDFToDouble(_col5))) (type: double), _col9 (type: double), (- (UDFToDouble(_col7) - (-1.389 * UDFToDouble(_col5)))) (type: double), _col10 (type: double), (- _col10) (type: double), (_col10 * UDFToDouble(_col7)) (type: double), (-26.28 / UDFToDouble(_col1)) (type: double), _col2 (type: bigint), (UDFToDouble(_col2) - 10.175) (type: double), _col3 (type: double), (_col3 % UDFToDouble(_col1)) (type: double), (10.175 + UDFToDouble((- _col1))) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19, _col2, _col20, _col21, _col22, _col23, _col24, _col25, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: float), _col2 (type: float), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: bigint), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col17 (type: bigint), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double), _col22 (type: double), _col23 (type: double), _col24 (type: double), _col25 (type: double) Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col12 (type: double), VALUE._col15 (type: bigint), VALUE._col16 (type: double), VALUE._col17 (type: double), VALUE._col18 (type: double), VALUE._col19 (type: double), VALUE._col20 (type: double), VALUE._col21 (type: double), VALUE._col22 (type: double), VALUE._col23 (type: double) 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 - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out index 55ecebd..90c9934 100644 --- ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_distinct_gby.q.out @@ -101,21 +101,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(DISTINCT _col0), count(DISTINCT _col0), avg(DISTINCT _col0), std(DISTINCT _col0) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/tez/vectorized_mapjoin.q.out ql/src/test/results/clientpositive/tez/vectorized_mapjoin.q.out index 34c6b88..884d114 100644 --- ql/src/test/results/clientpositive/tez/vectorized_mapjoin.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_mapjoin.q.out @@ -22,14 +22,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -39,11 +39,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) mode: hash @@ -58,19 +58,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/tez/vectorized_nested_mapjoin.q.out ql/src/test/results/clientpositive/tez/vectorized_nested_mapjoin.q.out index c4a0363..7c73f91 100644 --- ql/src/test/results/clientpositive/tez/vectorized_nested_mapjoin.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_nested_mapjoin.q.out @@ -18,33 +18,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: v1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ctinyint is not null and csmallint is not null) (type: boolean) - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cdouble (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: smallint), _col2 (type: double) Execution mode: vectorized Map 2 Map Operator Tree: TableScan alias: v1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -54,11 +54,11 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 0 Map 1 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: smallint), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -68,11 +68,11 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 7433 Data size: 228226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 7433 Data size: 228226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) mode: hash @@ -87,19 +87,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: v1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: csmallint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 3 Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/tez/vectorized_shufflejoin.q.out ql/src/test/results/clientpositive/tez/vectorized_shufflejoin.q.out index 6a0d16a..408d46e 100644 --- ql/src/test/results/clientpositive/tez/vectorized_shufflejoin.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_shufflejoin.q.out @@ -22,37 +22,37 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 4 Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -63,11 +63,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) mode: hash diff --git ql/src/test/results/clientpositive/vector_char_simple.q.out ql/src/test/results/clientpositive/vector_char_simple.q.out index fbe1b40..a61cbc8 100644 --- ql/src/test/results/clientpositive/vector_char_simple.q.out +++ ql/src/test/results/clientpositive/vector_char_simple.q.out @@ -251,34 +251,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( _col0 AS CHAR(12) (type: char(12)) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git ql/src/test/results/clientpositive/vector_coalesce.q.out ql/src/test/results/clientpositive/vector_coalesce.q.out index d532864..096ee22 100644 --- ql/src/test/results/clientpositive/vector_coalesce.q.out +++ ql/src/test/results/clientpositive/vector_coalesce.q.out @@ -16,20 +16,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cdouble is null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: null (type: void), cstring1 (type: string), cint (type: int), cfloat (type: float), csmallint (type: smallint), COALESCE(null,cstring1,cint,cfloat,csmallint) (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -82,20 +82,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ctinyint is null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: null (type: void), cdouble (type: double), cint (type: int), COALESCE((UDFToInteger(null) + 10),(cdouble + log2(cint)),0) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -148,20 +148,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (cfloat is null and cbigint is null) (type: boolean) - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: null (type: void), null (type: void), COALESCE(null,null,0) (type: float) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -214,20 +214,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ctimestamp1 is not null or ctimestamp2 is not null) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), COALESCE(ctimestamp1,ctimestamp2) (type: timestamp) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vector_decimal_cast.q.out ql/src/test/results/clientpositive/vector_decimal_cast.q.out index 2053452..88c09d9 100644 --- ql/src/test/results/clientpositive/vector_decimal_cast.q.out +++ ql/src/test/results/clientpositive/vector_decimal_cast.q.out @@ -12,20 +12,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((cdouble is not null and cint is not null) and cboolean1 is not null) and ctimestamp1 is not null) (type: boolean) - Statistics: Num rows: 768 Data size: 23577 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 768 Data size: 165122 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cint (type: int), cboolean1 (type: boolean), ctimestamp1 (type: timestamp), CAST( cdouble AS decimal(20,10)) (type: decimal(20,10)), CAST( cint AS decimal(23,14)) (type: decimal(23,14)), CAST( cboolean1 AS decimal(5,2)) (type: decimal(5,2)), CAST( ctimestamp1 AS decimal(15,0)) (type: decimal(15,0)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 768 Data size: 23577 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 768 Data size: 165122 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vector_elt.q.out ql/src/test/results/clientpositive/vector_elt.q.out index 917dc31..3a2c1fc 100644 --- ql/src/test/results/clientpositive/vector_elt.q.out +++ ql/src/test/results/clientpositive/vector_elt.q.out @@ -16,20 +16,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ctinyint > 0) (type: boolean) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ((UDFToInteger(ctinyint) % 2) + 1) (type: int), cstring1 (type: string), cint (type: int), elt(((UDFToInteger(ctinyint) % 2) + 1), cstring1, cint) (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -100,7 +100,7 @@ STAGE PLANS: Processor Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'defg' (type: string), 'cc' (type: string), 'abc' (type: string), '2' (type: string), '12345' (type: string), '123456789012' (type: string), '1.25' (type: string), '16.0' (type: string), null (type: void), null (type: void) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 diff --git ql/src/test/results/clientpositive/vector_if_expr.q.out ql/src/test/results/clientpositive/vector_if_expr.q.out index 3a27b52..76f155b 100644 --- ql/src/test/results/clientpositive/vector_if_expr.q.out +++ ql/src/test/results/clientpositive/vector_if_expr.q.out @@ -14,28 +14,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (cboolean1 is not null and cboolean1) (type: boolean) - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), if(cboolean1, 'first', 'second') (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vector_left_outer_join.q.out ql/src/test/results/clientpositive/vector_left_outer_join.q.out index b464b0f..2f986c2 100644 --- ql/src/test/results/clientpositive/vector_left_outer_join.q.out +++ ql/src/test/results/clientpositive/vector_left_outer_join.q.out @@ -35,11 +35,11 @@ STAGE PLANS: $hdt$_0:$hdt$_1:c TableScan alias: c - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -47,11 +47,11 @@ STAGE PLANS: $hdt$_0:$hdt$_2:c TableScan alias: c - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: tinyint) @@ -62,11 +62,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: c - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 @@ -74,14 +74,14 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 13516 Data size: 414960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 keys: 0 _col0 (type: tinyint) 1 _col0 (type: tinyint) - Statistics: Num rows: 14867 Data size: 456456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14867 Data size: 3196776 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git ql/src/test/results/clientpositive/vector_varchar_simple.q.out ql/src/test/results/clientpositive/vector_varchar_simple.q.out index 1c774af..252d45d 100644 --- ql/src/test/results/clientpositive/vector_varchar_simple.q.out +++ ql/src/test/results/clientpositive/vector_varchar_simple.q.out @@ -251,34 +251,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( _col0 AS varchar(25)) (type: varchar(25)) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2150 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git ql/src/test/results/clientpositive/vectorization_0.q.out ql/src/test/results/clientpositive/vectorization_0.q.out index 1e5b553..59d074f 100644 --- ql/src/test/results/clientpositive/vectorization_0.q.out +++ ql/src/test/results/clientpositive/vectorization_0.q.out @@ -27,11 +27,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: ctinyint - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(ctinyint), max(ctinyint), count(ctinyint), count() mode: hash @@ -123,11 +123,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) mode: hash @@ -228,11 +228,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: ctinyint - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(ctinyint), variance(ctinyint), var_pop(ctinyint), var_samp(ctinyint), std(ctinyint), stddev(ctinyint), stddev_pop(ctinyint), stddev_samp(ctinyint) mode: hash @@ -340,11 +340,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) outputColumnNames: cbigint - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(cbigint), max(cbigint), count(cbigint), count() mode: hash @@ -436,11 +436,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) mode: hash @@ -541,11 +541,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) outputColumnNames: cbigint - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(cbigint), variance(cbigint), var_pop(cbigint), var_samp(cbigint), std(cbigint), stddev(cbigint), stddev_pop(cbigint), stddev_samp(cbigint) mode: hash @@ -653,11 +653,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) outputColumnNames: cfloat - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(cfloat), max(cfloat), count(cfloat), count() mode: hash @@ -749,11 +749,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) mode: hash @@ -854,11 +854,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) outputColumnNames: cfloat - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(cfloat), variance(cfloat), var_pop(cfloat), var_samp(cfloat), std(cfloat), stddev(cfloat), stddev_pop(cfloat), stddev_samp(cfloat) mode: hash @@ -1004,14 +1004,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cstring2 like '%b%') or ((79.553 <> UDFToDouble(cint)) or (UDFToDouble(cbigint) < cdouble))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(_col0), stddev_pop(_col0), var_samp(_col0), count(), sum(_col1), min(_col2) mode: hash diff --git ql/src/test/results/clientpositive/vectorization_13.q.out ql/src/test/results/clientpositive/vectorization_13.q.out index 2926bad..7d14581 100644 --- ql/src/test/results/clientpositive/vectorization_13.q.out +++ ql/src/test/results/clientpositive/vectorization_13.q.out @@ -75,25 +75,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((UDFToDouble(ctimestamp1) > 11.0) and ((UDFToDouble(ctimestamp2) <> 12.0) and (UDFToDouble(ctinyint) < 9763215.5639)))) (type: boolean) - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized Reduce Operator Tree: @@ -102,11 +102,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col2 (type: timestamp), _col10 (type: tinyint), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col14, _col15, _col16, _col17, _col18, _col19, _col2, _col20, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -121,19 +121,19 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), VALUE._col0 (type: tinyint), VALUE._col1 (type: tinyint), VALUE._col2 (type: tinyint), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col5 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: float), VALUE._col13 (type: double), VALUE._col14 (type: tinyint) 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: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -332,25 +332,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((cfloat < 3569.0) and ((10.175 >= cdouble) and (cboolean1 <> 1))) or ((UDFToDouble(ctimestamp1) > -1.388) and ((UDFToDouble(ctimestamp2) <> -1.3359999999999999) and (UDFToDouble(ctinyint) < 9763215.5639)))) (type: boolean) - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) - Statistics: Num rows: 2730 Data size: 83809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized Reduce Operator Tree: @@ -359,11 +359,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col2 (type: timestamp), _col10 (type: tinyint), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col14, _col15, _col16, _col17, _col18, _col19, _col2, _col20, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -378,19 +378,19 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), VALUE._col0 (type: tinyint), VALUE._col1 (type: tinyint), VALUE._col2 (type: tinyint), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col5 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: float), VALUE._col13 (type: double), VALUE._col14 (type: tinyint) 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: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorization_14.q.out ql/src/test/results/clientpositive/vectorization_14.q.out index cff0ccd..f1c7975 100644 --- ql/src/test/results/clientpositive/vectorization_14.q.out +++ ql/src/test/results/clientpositive/vectorization_14.q.out @@ -75,25 +75,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((UDFToLong(ctinyint) <= cbigint) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1))) and (cdouble < UDFToDouble(ctinyint))) and ((cbigint > -257) or (cfloat < UDFToFloat(cint)))) (type: boolean) - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28 + cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(_col5), max(_col1), stddev_pop(_col1), count(_col1), var_pop(_col1), var_samp(_col1) keys: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double) sort order: +++++ Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double) - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: struct), _col6 (type: float), _col7 (type: struct), _col8 (type: bigint), _col9 (type: struct), _col10 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -102,11 +102,11 @@ STAGE PLANS: keys: KEY._col0 (type: timestamp), KEY._col1 (type: float), KEY._col2 (type: string), KEY._col3 (type: boolean), KEY._col4 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: timestamp), _col1 (type: float), _col2 (type: string), _col3 (type: boolean), _col4 (type: double), (-26.28 + _col4) (type: double), (- (-26.28 + _col4)) (type: double), _col5 (type: double), (UDFToDouble(_col1) * -26.28) (type: double), _col6 (type: float), (- _col1) (type: float), (- _col6) (type: float), ((- (-26.28 + _col4)) / 10.175) (type: double), _col7 (type: double), _col8 (type: bigint), (- ((- (-26.28 + _col4)) / 10.175)) (type: double), (-1.389 % _col5) (type: double), (UDFToDouble(_col1) - _col4) (type: double), _col9 (type: double), (_col9 % 10.175) (type: double), _col10 (type: double), (- (UDFToDouble(_col1) - _col4)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -121,16 +121,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp) sort order: ++++ - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorization_15.q.out ql/src/test/results/clientpositive/vectorization_15.q.out index 5cc9cb0..da9610f 100644 --- ql/src/test/results/clientpositive/vectorization_15.q.out +++ ql/src/test/results/clientpositive/vectorization_15.q.out @@ -71,25 +71,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cstring2 like '%ss%') or ((cstring1 like '10%') or ((cint >= -75) and ((UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(_col0), min(_col2), stddev_samp(_col4), var_pop(_col4), var_samp(_col5), stddev_pop(_col5) keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) sort order: +++++++ Map-reduce partition columns: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: struct), _col8 (type: double), _col9 (type: struct), _col10 (type: struct), _col11 (type: struct), _col12 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -98,11 +98,11 @@ STAGE PLANS: keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), _col7 (type: double), (-26.28 - UDFToDouble(_col5)) (type: double), _col8 (type: double), (_col2 * 79.553) (type: double), (33.0 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - UDFToDouble(_col5))) (type: double), _col12 (type: double) 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -117,16 +117,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) sort order: +++++++ - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: double), _col20 (type: double) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: double), VALUE._col13 (type: double) 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorization_16.q.out ql/src/test/results/clientpositive/vectorization_16.q.out index 0b3d1e0..6ae3b4e 100644 --- ql/src/test/results/clientpositive/vectorization_16.q.out +++ ql/src/test/results/clientpositive/vectorization_16.q.out @@ -52,25 +52,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1), stddev_samp(_col1), min(_col1) keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -79,14 +79,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorization_7.q.out ql/src/test/results/clientpositive/vectorization_7.q.out index 292da75..c7c096e 100644 --- ql/src/test/results/clientpositive/vectorization_7.q.out +++ ql/src/test/results/clientpositive/vectorization_7.q.out @@ -60,20 +60,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or ((UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')))) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > -15.0) and (3569.0 >= cdouble)))) (type: boolean) - Statistics: Num rows: 7281 Data size: 223523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 7281 Data size: 223523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -229,20 +229,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or ((UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')))) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > 7.6850000000000005) and (3569.0 >= cdouble)))) (type: boolean) - Statistics: Num rows: 7281 Data size: 223523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 7281 Data size: 223523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorization_8.q.out ql/src/test/results/clientpositive/vectorization_8.q.out index feef5b9..456c913 100644 --- ql/src/test/results/clientpositive/vectorization_8.q.out +++ ql/src/test/results/clientpositive/vectorization_8.q.out @@ -56,20 +56,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cstring2 is not null and ((UDFToDouble(ctimestamp1) <= 10.0) and (UDFToDouble(ctimestamp2) <> 16.0))) or ((cfloat < -6432.0) or (cboolean1 is not null and (cdouble = 988888.0)))) (type: boolean) - Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15 - cdouble) (type: double), (cdouble * -257.0) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), ((-5638.15 - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -212,20 +212,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cstring2 is not null and ((UDFToDouble(ctimestamp1) <= 12.503) and (UDFToDouble(ctimestamp2) <> 11.998))) or ((cfloat < -6432.0) or (cboolean1 is not null and (cdouble = 988888.0)))) (type: boolean) - Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15 - cdouble) (type: double), (cdouble * -257.0) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), ((-5638.15 - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorization_9.q.out ql/src/test/results/clientpositive/vectorization_9.q.out index 1ff5d94..65c92df 100644 --- ql/src/test/results/clientpositive/vectorization_9.q.out +++ ql/src/test/results/clientpositive/vectorization_9.q.out @@ -48,25 +48,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1), stddev_samp(_col1), min(_col1) keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -75,14 +75,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorization_div0.q.out ql/src/test/results/clientpositive/vectorization_div0.q.out index 56e9de7..9cd35d3 100644 --- ql/src/test/results/clientpositive/vectorization_div0.q.out +++ ql/src/test/results/clientpositive/vectorization_div0.q.out @@ -16,17 +16,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdouble / 0.0) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 3000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 3000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -171,31 +171,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cbigint > 0) and (cbigint < 100000000)) (type: boolean) - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cbigint - 988888) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888))) (type: double), (1.2 / UDFToDouble((cbigint - 988888))) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: bigint), _col1 (type: double) sort order: ++ - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 3000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 3000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -339,31 +339,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cdouble >= -500.0) and (cdouble < -199.0)) (type: boolean) - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdouble + 200.0) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0)) (type: double), ((cdouble + 200.0) / (cdouble + 200.0)) (type: double), (3.0 / (cdouble + 200.0)) (type: double), (1.2 / (cdouble + 200.0)) (type: double) outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: double) sort order: ++ - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: double), _col4 (type: double), _col5 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 3000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 3000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorization_limit.q.out ql/src/test/results/clientpositive/vectorization_limit.q.out index cf8c72e..7691a4d 100644 --- ql/src/test/results/clientpositive/vectorization_limit.q.out +++ ql/src/test/results/clientpositive/vectorization_limit.q.out @@ -13,20 +13,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 41904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 7 - Statistics: Num rows: 7 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 1505 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 1505 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -75,18 +75,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: smallint) Execution mode: vectorized @@ -94,13 +94,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -158,22 +158,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), (cdouble + 1.0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(_col1) keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 value expressions: _col1 (type: struct) Execution mode: vectorized @@ -183,13 +183,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -247,21 +247,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Reduce Operator Tree: @@ -269,13 +269,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -331,22 +331,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT _col1) keys: _col0 (type: tinyint), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Reduce Operator Tree: @@ -355,13 +355,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -446,25 +446,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), ctinyint (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1) keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -473,7 +473,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -488,19 +488,19 @@ STAGE PLANS: Reduce Output Operator key expressions: _col1 (type: bigint), _col0 (type: double) sort order: ++ - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: double), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorization_pushdown.q.out ql/src/test/results/clientpositive/vectorization_pushdown.q.out index 0debbde..7205376 100644 --- ql/src/test/results/clientpositive/vectorization_pushdown.q.out +++ ql/src/test/results/clientpositive/vectorization_pushdown.q.out @@ -14,14 +14,14 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(_col0) mode: hash diff --git ql/src/test/results/clientpositive/vectorization_short_regress.q.out ql/src/test/results/clientpositive/vectorization_short_regress.q.out index e624de8..b9ab174 100644 --- ql/src/test/results/clientpositive/vectorization_short_regress.q.out +++ ql/src/test/results/clientpositive/vectorization_short_regress.q.out @@ -141,14 +141,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((762 = cbigint) or (((UDFToFloat(csmallint) < cfloat) and ((UDFToDouble(ctimestamp2) > -5.0) and (cdouble <> UDFToDouble(cint)))) or ((cstring1 = 'a') or ((UDFToDouble(cbigint) <= -1.389) and ((cstring2 <> 'a') and ((79.553 <> UDFToDouble(cint)) and (cboolean2 <> cboolean1))))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), csmallint (type: smallint), cfloat (type: float), ctinyint (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(_col0), sum(_col1), stddev_pop(_col0), stddev_samp(_col2), var_samp(_col0), avg(_col3), stddev_samp(_col0), min(_col4), count(_col2) mode: hash @@ -347,14 +347,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((cbigint <= 197) and (UDFToLong(cint) < cbigint)) or (((cdouble >= -26.28) and (UDFToDouble(csmallint) > cdouble)) or (((UDFToFloat(ctinyint) > cfloat) and (cstring1 rlike '.*ss.*')) or ((cfloat > 79.553) and (cstring2 like '10%'))))) (type: boolean) - Statistics: Num rows: 6826 Data size: 209555 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), csmallint (type: smallint), cdouble (type: double), ctinyint (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6826 Data size: 209555 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col0), var_pop(_col1), stddev_pop(_col2), max(_col3), avg(_col4), min(_col0), min(_col3), stddev_samp(_col2), var_samp(_col0) mode: hash @@ -544,14 +544,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((ctimestamp1 = ctimestamp2) or ((762.0 = cfloat) or ((cstring1 = 'ss') or (((UDFToLong(csmallint) <= cbigint) and (1 = cboolean2)) or (cboolean1 is not null and (ctimestamp2 is not null and (cstring2 > 'a'))))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cdouble (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: var_pop(_col0), count(), max(_col1), stddev_pop(_col2), max(_col3), stddev_samp(_col4), count(_col1), avg(_col1) mode: hash @@ -720,14 +720,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((ctimestamp2 <= ctimestamp1) and ((UDFToDouble(cbigint) <> cdouble) and ('ss' <= cstring1))) or (((csmallint < UDFToShort(ctinyint)) and (UDFToDouble(ctimestamp1) >= 0.0)) or (cfloat = 17.0))) (type: boolean) - Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cbigint (type: bigint), cint (type: int), cfloat (type: float) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(_col0), max(_col1), stddev_samp(_col2), var_pop(_col2), var_pop(_col1), max(_col3) mode: hash @@ -904,31 +904,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((cstring1 rlike 'a.*') and (cstring2 like '%ss%')) or (((1 <> cboolean2) and ((UDFToDouble(csmallint) < 79.553) and (-257 <> UDFToInteger(ctinyint)))) or (((cdouble > UDFToDouble(ctinyint)) and (cfloat >= UDFToFloat(cint))) or ((UDFToLong(cint) < cbigint) and (UDFToLong(ctinyint) > cbigint))))) (type: boolean) - Statistics: Num rows: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), ctimestamp2 (type: timestamp), cstring1 (type: string), cboolean2 (type: boolean), ctinyint (type: tinyint), cfloat (type: float), ctimestamp1 (type: timestamp), csmallint (type: smallint), cbigint (type: bigint), (-3728 * cbigint) (type: bigint), (- cint) (type: int), (-863.257 - UDFToDouble(cint)) (type: double), (- csmallint) (type: smallint), (csmallint - (- csmallint)) (type: smallint), ((csmallint - (- csmallint)) + (- csmallint)) (type: smallint), (UDFToDouble(cint) / UDFToDouble(cint)) (type: double), ((-863.257 - UDFToDouble(cint)) - -26.28) (type: double), (- cfloat) (type: float), (cdouble * -89010.0) (type: double), (UDFToDouble(ctinyint) / 988888.0) (type: double), (- ctinyint) (type: tinyint), (79.553 / UDFToDouble(ctinyint)) (type: double) 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: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: timestamp), _col3 (type: string), _col4 (type: boolean), _col5 (type: tinyint), _col6 (type: float), _col7 (type: timestamp), _col8 (type: smallint), _col9 (type: bigint) sort order: ++++++++++ - Statistics: Num rows: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE value expressions: _col10 (type: bigint), _col11 (type: int), _col12 (type: double), _col13 (type: smallint), _col14 (type: smallint), _col15 (type: smallint), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: double), _col21 (type: tinyint), _col22 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: boolean), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: float), KEY.reducesinkkey7 (type: timestamp), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: bigint), VALUE._col0 (type: bigint), VALUE._col1 (type: int), VALUE._col2 (type: double), VALUE._col3 (type: smallint), VALUE._col4 (type: smallint), VALUE._col5 (type: smallint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: float), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: tinyint), VALUE._col12 (type: double) 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: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 - Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1156,31 +1156,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((197.0 > UDFToDouble(ctinyint)) and (UDFToLong(cint) = cbigint)) or ((cbigint = 359) or ((cboolean1 < 0) or ((cstring1 like '%ss') and (cfloat <= UDFToFloat(ctinyint)))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), (UDFToDouble(cint) / UDFToDouble(cbigint)) (type: double), (UDFToDouble(cbigint) % 79.553) (type: double), (- (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (10.175 % UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), (cfloat - (- cfloat)) (type: float), ((cfloat - (- cfloat)) % -6432.0) (type: float), (cdouble * UDFToDouble(csmallint)) (type: double), (- cdouble) (type: double), (- cbigint) (type: bigint), cstring1 (type: string), (UDFToDouble(cfloat) - (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (- csmallint) (type: smallint), (3569 % cbigint) (type: bigint), (359.0 - cdouble) (type: double), cboolean1 (type: boolean), cfloat (type: float), cdouble (type: double), ctimestamp2 (type: timestamp), csmallint (type: smallint), cstring2 (type: string), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col2, _col20, _col21, _col22, _col23, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean), _col4 (type: float), _col5 (type: double), _col6 (type: timestamp), _col7 (type: smallint), _col8 (type: string), _col9 (type: boolean) sort order: ++++++++++ - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: float), _col15 (type: float), _col16 (type: float), _col17 (type: double), _col18 (type: double), _col19 (type: bigint), _col20 (type: double), _col21 (type: smallint), _col22 (type: bigint), _col23 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: boolean), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: timestamp), KEY.reducesinkkey7 (type: smallint), KEY.reducesinkkey8 (type: string), KEY.reducesinkkey9 (type: boolean), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: bigint), VALUE._col10 (type: double), VALUE._col11 (type: smallint), VALUE._col12 (type: bigint), VALUE._col13 (type: double), VALUE._col11 (type: smallint) 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 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1357,31 +1357,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((UDFToDouble(csmallint) > -26.28) and (cstring2 like 'ss')) or (((cdouble <= UDFToDouble(cbigint)) and ((cstring1 >= 'ss') and (UDFToDouble(cint) <> cdouble))) or ((UDFToInteger(ctinyint) = -89010) or ((UDFToFloat(cbigint) <= cfloat) and (-26.28 <= UDFToDouble(csmallint)))))) (type: boolean) - Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cstring1 (type: string), cboolean2 (type: boolean), ctimestamp2 (type: timestamp), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), cboolean1 (type: boolean), (cint + UDFToInteger(csmallint)) (type: int), (cbigint - UDFToLong(ctinyint)) (type: bigint), (- cbigint) (type: bigint), (- cfloat) (type: float), ((cbigint - UDFToLong(ctinyint)) + cbigint) (type: bigint), (cdouble / cdouble) (type: double), (- cdouble) (type: double), (UDFToLong((cint + UDFToInteger(csmallint))) * (- cbigint)) (type: bigint), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (-1.389 / UDFToDouble(ctinyint)) (type: double), (UDFToDouble(cbigint) % cdouble) (type: double), (- csmallint) (type: smallint), (UDFToInteger(csmallint) + (cint + UDFToInteger(csmallint))) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: boolean), _col1 (type: string), _col3 (type: timestamp), _col5 (type: float), _col6 (type: bigint), _col1 (type: string), _col4 (type: double), _col0 (type: int), _col7 (type: smallint), _col4 (type: double) sort order: ++++++++++ - Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: boolean), _col9 (type: int), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: float), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: smallint), _col21 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey7 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey0 (type: boolean), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: float), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: bigint), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: smallint), VALUE._col13 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 75 - Statistics: Num rows: 75 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75 Data size: 16125 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 75 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75 Data size: 16125 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1616,31 +1616,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((-1.389 >= UDFToDouble(cint)) and ((csmallint < UDFToShort(ctinyint)) and (-6432 > UDFToInteger(csmallint)))) or (((cdouble >= UDFToDouble(cfloat)) and (cstring2 <= 'a')) or ((cstring1 like 'ss%') and (10.175 > UDFToDouble(cbigint))))) (type: boolean) - Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cstring2 (type: string), (cdouble * 10.175) (type: double), (UDFToDouble((-6432.0 * cfloat)) / UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), (cint % UDFToInteger(csmallint)) (type: int), (cdouble * (- cdouble)) (type: double), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), (UDFToDouble(cbigint) / 3569.0) (type: double), (-257 - UDFToInteger(csmallint)) (type: int), (-6432.0 * cfloat) (type: float), (- cdouble) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col15, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col5 (type: smallint), _col1 (type: string), _col2 (type: double) sort order: +++ - Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: timestamp), _col3 (type: float), _col4 (type: bigint), _col6 (type: double), _col7 (type: int), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: float), _col13 (type: int), _col15 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: timestamp), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: float), VALUE._col2 (type: bigint), KEY.reducesinkkey0 (type: smallint), VALUE._col3 (type: double), VALUE._col4 (type: int), VALUE._col5 (type: float), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: float), VALUE._col10 (type: int), VALUE._col6 (type: double), VALUE._col11 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 45 - Statistics: Num rows: 45 Data size: 1350 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 45 Data size: 9675 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 45 Data size: 1350 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 45 Data size: 9675 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1817,25 +1817,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToInteger(csmallint) >= -257) and ((-6432 = UDFToInteger(csmallint)) or ((UDFToDouble(cint) >= cdouble) and (UDFToInteger(ctinyint) <= cint)))) (type: boolean) - Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cbigint (type: bigint), ctinyint (type: tinyint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(_col0), sum(_col1), var_pop(_col2), count() keys: _col0 (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct), _col2 (type: bigint), _col3 (type: struct), _col4 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1844,11 +1844,11 @@ STAGE PLANS: keys: KEY._col0 (type: smallint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: smallint), (UDFToInteger(_col0) % -75) (type: int), _col1 (type: double), (-1.389 / UDFToDouble(_col0)) (type: double), _col2 (type: bigint), (UDFToDouble((UDFToInteger(_col0) % -75)) / UDFToDouble(_col2)) (type: double), (- (UDFToInteger(_col0) % -75)) (type: int), _col3 (type: double), (- (- (UDFToInteger(_col0) % -75))) (type: int), _col4 (type: bigint), (_col4 - -89010) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1863,19 +1863,19 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + - Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: int), _col7 (type: double), _col8 (type: int), _col9 (type: bigint), _col10 (type: bigint) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: smallint), VALUE._col0 (type: int), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: int), VALUE._col6 (type: double), VALUE._col7 (type: int), VALUE._col8 (type: bigint), VALUE._col9 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2028,25 +2028,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and ((UDFToInteger(csmallint) < cint) and (UDFToDouble(cfloat) < -5638.15))) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > UDFToDouble(cbigint))))) (type: boolean) - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) outputColumnNames: _col0, _col1 - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: var_samp(_col0), count(_col1), sum(_col1), var_pop(_col0), stddev_pop(_col0), sum(_col0) keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 606 Data size: 18603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct), _col2 (type: bigint), _col3 (type: double), _col4 (type: struct), _col5 (type: struct), _col6 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -2055,11 +2055,11 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: double), _col1 (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762.0) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762.0)) (type: double), (2563.58 * _col1) (type: double), (- _col1) (type: double), _col2 (type: bigint), ((2563.58 * _col1) + -5638.15) (type: double), ((- _col1) * ((2563.58 * _col1) + -5638.15)) (type: double), _col3 (type: double), _col4 (type: double), (_col0 - (- _col1)) (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2074,16 +2074,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 303 Data size: 9301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2286,25 +2286,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(ctimestamp1) <> 0.0) and (((-257 <> UDFToInteger(ctinyint)) and (cboolean2 is not null and ((cstring1 rlike '.*ss') and (-3.0 < UDFToDouble(ctimestamp1))))) or ((UDFToDouble(ctimestamp2) = -5.0) or (((UDFToDouble(ctimestamp1) < 0.0) and (cstring2 like '%b%')) or ((cdouble = UDFToDouble(cint)) or (cboolean1 is null and (cfloat < UDFToFloat(cint)))))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cstring1 (type: string), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_pop(_col2), avg(_col3), count(), min(_col4), var_samp(_col3), var_pop(_col5), avg(_col2), var_samp(_col5), avg(_col5), min(_col6), var_pop(_col3), stddev_pop(_col4), sum(_col2) keys: _col0 (type: timestamp), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: string) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: bigint), _col5 (type: tinyint), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct), _col11 (type: double), _col12 (type: struct), _col13 (type: struct), _col14 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -2313,11 +2313,11 @@ STAGE PLANS: keys: KEY._col0 (type: timestamp), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: timestamp), _col1 (type: string), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col2 (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (_col2 * 10.175) (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / UDFToDouble((- _col5))) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double), (- _col2) (type: double), _col3 (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col2, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col3, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col38, _col4, _col5, _col7, _col8, _col9 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2332,19 +2332,19 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: string) sort order: ++ - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double), _col11 (type: tinyint), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double), _col22 (type: double), _col23 (type: double), _col24 (type: double), _col25 (type: double), _col26 (type: double), _col27 (type: tinyint), _col28 (type: double), _col29 (type: double), _col30 (type: double), _col31 (type: double), _col32 (type: double), _col33 (type: double), _col34 (type: bigint), _col35 (type: double), _col36 (type: bigint), _col38 (type: double) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col2 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: bigint), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double), VALUE._col18 (type: double), VALUE._col19 (type: double), VALUE._col20 (type: double), VALUE._col21 (type: double), VALUE._col22 (type: double), VALUE._col23 (type: double), VALUE._col24 (type: tinyint), VALUE._col25 (type: double), VALUE._col26 (type: double), VALUE._col27 (type: double), VALUE._col28 (type: double), VALUE._col29 (type: double), VALUE._col30 (type: double), VALUE._col31 (type: bigint), VALUE._col32 (type: double), VALUE._col33 (type: bigint), VALUE._col5 (type: bigint), VALUE._col34 (type: double) 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 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 - Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2622,25 +2622,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (cboolean1 is not null and (((cdouble < UDFToDouble(csmallint)) and ((cboolean2 = cboolean1) and (UDFToDouble(cbigint) <= -863.257))) or (((cint >= -257) and (cstring1 is not null and (cboolean1 >= 1))) or ((cstring2 rlike 'b') or ((csmallint >= UDFToShort(ctinyint)) and ctimestamp2 is null))))) (type: boolean) - Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cbigint (type: bigint), cint (type: int), cdouble (type: double), ctinyint (type: tinyint), csmallint (type: smallint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col1), sum(_col2), var_samp(_col3), avg(_col4), min(_col2), var_pop(_col2), sum(_col3), stddev_samp(_col5), stddev_pop(_col6), avg(_col3) keys: _col0 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + Map-reduce partition columns: _col0 (type: boolean) - Statistics: Num rows: 4778 Data size: 146682 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: float), _col2 (type: bigint), _col3 (type: struct), _col4 (type: struct), _col5 (type: bigint), _col6 (type: struct), _col7 (type: bigint), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -2649,11 +2649,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: boolean), _col1 (type: float), ((UDFToDouble(_col2) - 10.175) + _col3) (type: double), _col5 (type: bigint), _col6 (type: double), (- (10.175 + UDFToDouble((- _col1)))) (type: double), (79.553 / _col6) (type: double), (_col3 % (79.553 / _col6)) (type: double), _col7 (type: bigint), _col8 (type: double), (-1.389 * UDFToDouble(_col5)) (type: double), (- _col1) (type: float), (UDFToDouble(_col7) - (-1.389 * UDFToDouble(_col5))) (type: double), _col9 (type: double), (- (UDFToDouble(_col7) - (-1.389 * UDFToDouble(_col5)))) (type: double), _col10 (type: double), (- _col10) (type: double), (_col10 * UDFToDouble(_col7)) (type: double), (-26.28 / UDFToDouble(_col1)) (type: double), _col2 (type: bigint), (UDFToDouble(_col2) - 10.175) (type: double), _col3 (type: double), (_col3 % UDFToDouble(_col1)) (type: double), (10.175 + UDFToDouble((- _col1))) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19, _col2, _col20, _col21, _col22, _col23, _col24, _col25, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2668,16 +2668,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: float), _col2 (type: float), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: bigint), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col17 (type: bigint), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double), _col22 (type: double), _col23 (type: double), _col24 (type: double), _col25 (type: double) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col12 (type: double), VALUE._col15 (type: bigint), VALUE._col16 (type: double), VALUE._col17 (type: double), VALUE._col18 (type: double), VALUE._col19 (type: double), VALUE._col20 (type: double), VALUE._col21 (type: double), VALUE._col22 (type: double), VALUE._col23 (type: double) 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 - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2389 Data size: 73341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2389 Data size: 513643 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorized_case.q.out ql/src/test/results/clientpositive/vectorized_case.q.out index 1aede37..9f547d1 100644 --- ql/src/test/results/clientpositive/vectorized_case.q.out +++ ql/src/test/results/clientpositive/vectorized_case.q.out @@ -44,17 +44,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((csmallint = 418) or ((csmallint = 12205) or (csmallint = 10583))) (type: boolean) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string), CASE (csmallint) WHEN (418) THEN ('a') WHEN (12205) THEN ('b') ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorized_casts.q.out ql/src/test/results/clientpositive/vectorized_casts.q.out index 8de66fb..f915200 100644 --- ql/src/test/results/clientpositive/vectorized_casts.q.out +++ ql/src/test/results/clientpositive/vectorized_casts.q.out @@ -156,17 +156,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cbigint % 250) = 0) (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToBoolean(ctinyint) (type: boolean), UDFToBoolean(csmallint) (type: boolean), UDFToBoolean(cint) (type: boolean), UDFToBoolean(cbigint) (type: boolean), UDFToBoolean(cfloat) (type: boolean), UDFToBoolean(cdouble) (type: boolean), cboolean1 (type: boolean), UDFToBoolean((cbigint * 0)) (type: boolean), UDFToBoolean(ctimestamp1) (type: boolean), UDFToBoolean(cstring1) (type: boolean), UDFToInteger(ctinyint) (type: int), UDFToInteger(csmallint) (type: int), cint (type: int), UDFToInteger(cbigint) (type: int), UDFToInteger(cfloat) (type: int), UDFToInteger(cdouble) (type: int), UDFToInteger(cboolean1) (type: int), UDFToInteger(ctimestamp1) (type: int), UDFToInteger(cstring1) (type: int), UDFToInteger(substr(cstring1, 1, 1)) (type: int), UDFToByte(cfloat) (type: tinyint), UDFToShort(cfloat) (type: smallint), UDFToLong(cfloat) (type: bigint), UDFToDouble(ctinyint) (type: double), UDFToDouble(csmallint) (type: double), UDFToDouble(cint) (type: double), UDFToDouble(cbigint) (type: double), UDFToDouble(cfloat) (type: double), cdouble (type: double), UDFToDouble(cboolean1) (type: double), UDFToDouble(ctimestamp1) (type: double), UDFToDouble(cstring1) (type: double), UDFToDouble(substr(cstring1, 1, 1)) (type: double), UDFToFloat(cint) (type: float), UDFToFloat(cdouble) (type: float), CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp), UDFToString(ctinyint) (type: string), UDFToString(csmallint) (type: string), UDFToString(cint) (type: string), UDFToString(cbigint) (type: string), UDFToString(cfloat) (type: string), UDFToString(cdouble) (type: string), UDFToString(cboolean1) (type: string), UDFToString((cbigint * 0)) (type: string), UDFToString(ctimestamp1) (type: string), cstring1 (type: string), UDFToFloat(UDFToInteger(cfloat)) (type: float), UDFToDouble((cint * 2)) (type: double), UDFToString(sin(cfloat)) (type: string), (UDFToDouble(UDFToFloat(cint)) + UDFToDouble(cboolean1)) (type: double) 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, _col56, _col57, _col58, _col59 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out index 362dcdd..1c684ce 100644 --- ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out +++ ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out @@ -90,21 +90,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(DISTINCT _col0), count(DISTINCT _col0), avg(DISTINCT _col0), std(DISTINCT _col0) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/vectorized_mapjoin.q.out ql/src/test/results/clientpositive/vectorized_mapjoin.q.out index 609b53b..d042ae0 100644 --- ql/src/test/results/clientpositive/vectorized_mapjoin.q.out +++ ql/src/test/results/clientpositive/vectorized_mapjoin.q.out @@ -22,14 +22,14 @@ STAGE PLANS: $hdt$_0:$hdt$_0:t1 TableScan alias: t1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -40,14 +40,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -55,11 +55,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) mode: hash diff --git ql/src/test/results/clientpositive/vectorized_math_funcs.q.out ql/src/test/results/clientpositive/vectorized_math_funcs.q.out index 99deb49..29f80f6 100644 --- ql/src/test/results/clientpositive/vectorized_math_funcs.q.out +++ ql/src/test/results/clientpositive/vectorized_math_funcs.q.out @@ -116,17 +116,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((cbigint % 500) = 0) and (sin(cfloat) >= -1.0)) (type: boolean) - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), round(cdouble, 2) (type: double), floor(cdouble) (type: bigint), ceil(cdouble) (type: bigint), rand() (type: double), rand(98007) (type: double), exp(ln(cdouble)) (type: double), ln(cdouble) (type: double), ln(cfloat) (type: double), log10(cdouble) (type: double), log2(cdouble) (type: double), log2((cdouble - 15601.0)) (type: double), log2(cfloat) (type: double), log2(cbigint) (type: double), log2(cint) (type: double), log2(csmallint) (type: double), log2(ctinyint) (type: double), log(2.0, cdouble) (type: double), power(log2(cdouble), 2.0) (type: double), power(log2(cdouble), 2.0) (type: double), sqrt(cdouble) (type: double), sqrt(cbigint) (type: double), bin(cbigint) (type: string), hex(cdouble) (type: string), conv(cbigint, 10, 16) (type: string), abs(cdouble) (type: double), abs(ctinyint) (type: int), (cint pmod 3) (type: int), sin(cdouble) (type: double), asin(cdouble) (type: double), cos(cdouble) (type: double), acos(cdouble) (type: double), atan(cdouble) (type: double), degrees(cdouble) (type: double), radians(cdouble) (type: double), cdouble (type: double), cbigint (type: bigint), (- cdouble) (type: double), sign(cdouble) (type: double), sign(cbigint) (type: double), cos(((- sin(log(cdouble))) + 3.14159)) (type: double) 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 - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 62872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out index d3768c1..c92dcf9 100644 --- ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out +++ ql/src/test/results/clientpositive/vectorized_nested_mapjoin.q.out @@ -21,14 +21,14 @@ STAGE PLANS: $hdt$_0:$hdt$_0:$hdt$_0:v1 TableScan alias: v1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ctinyint is not null and csmallint is not null) (type: boolean) - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cdouble (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: tinyint) @@ -36,14 +36,14 @@ STAGE PLANS: $hdt$_0:$hdt$_1:v1 TableScan alias: v1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: csmallint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: smallint) @@ -54,14 +54,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: v1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -69,11 +69,11 @@ STAGE PLANS: 0 _col0 (type: tinyint) 1 _col0 (type: tinyint) outputColumnNames: _col1, _col2 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: smallint), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -81,11 +81,11 @@ STAGE PLANS: 0 _col0 (type: smallint) 1 _col0 (type: smallint) outputColumnNames: _col1 - Statistics: Num rows: 7433 Data size: 228226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 7433 Data size: 228226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) mode: hash diff --git ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out index 23f12f4..99962bb 100644 --- ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out +++ ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out @@ -17,34 +17,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE TableScan alias: t1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Join Operator @@ -54,11 +54,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 207479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) mode: hash diff --git ql/src/test/results/clientpositive/vectorized_string_funcs.q.out ql/src/test/results/clientpositive/vectorized_string_funcs.q.out index 9ab5c1e..8a5925e 100644 --- ql/src/test/results/clientpositive/vectorized_string_funcs.q.out +++ ql/src/test/results/clientpositive/vectorized_string_funcs.q.out @@ -56,17 +56,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((cbigint % 237) = 0) and (length(substr(cstring1, 1, 2)) <= 2)) and (cstring1 like '%')) (type: boolean) - Statistics: Num rows: 1024 Data size: 31436 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(cstring1, 1, 2) (type: string), substr(cstring1, 2) (type: string), lower(cstring1) (type: string), upper(cstring1) (type: string), upper(cstring1) (type: string), length(cstring1) (type: int), trim(cstring1) (type: string), ltrim(cstring1) (type: string), rtrim(cstring1) (type: string), concat(cstring1, cstring2) (type: string), concat('>', cstring1) (type: string), concat(cstring1, '<') (type: string), concat(substr(cstring1, 1, 2), substr(cstring2, 1, 2)) (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1024 Data size: 31436 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1024 Data size: 31436 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 220163 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/windowing_streaming.q.out ql/src/test/results/clientpositive/windowing_streaming.q.out index ac9e180..d45646a 100644 --- ql/src/test/results/clientpositive/windowing_streaming.q.out +++ ql/src/test/results/clientpositive/windowing_streaming.q.out @@ -273,34 +273,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.8 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE PTF Operator - Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_wcol0 < 5) (type: boolean) - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: tinyint), _col1 (type: double), _wcol0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4096 Data size: 125745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat