diff --git data/files/dynpart_test.txt data/files/dynpart_test.txt new file mode 100644 index 0000000..ab6cd4a --- /dev/null +++ data/files/dynpart_test.txt @@ -0,0 +1,24 @@ +24526172.99-11.32 +245261710022.633952.8 +24526172.1-2026.3 +2452617552.96-1363.84 +24526171765.07-4648.8 +2452617879.07-2185.76 +24526177412.832071.68 +245261785.825.61 +2452617565.92196.48 +24526175362.01-600.28 +24526173423.95-3164.07 +24526384133.98-775.72 +245263810171.1660.48 +2452638317.87-3775.38 +2452638156.67-4626.56 +24526381327.0857.97 +24526381971.35-488.25 +2452638181.03-207.24 +2452638267.01-3266.36 +24526380.15-241.22 +24526381524.33494.37 +2452638150.39-162.12 +24526381413.19178.08 +24526384329.49-4000.51 diff --git itests/src/test/resources/testconfiguration.properties itests/src/test/resources/testconfiguration.properties index 536e418..5593e09 100644 --- itests/src/test/resources/testconfiguration.properties +++ itests/src/test/resources/testconfiguration.properties @@ -74,6 +74,7 @@ minitez.query.files.shared=alter_merge_2_orc.q,\ disable_merge_for_bucketing.q,\ dynpart_sort_opt_vectorization.q,\ dynpart_sort_optimization.q,\ + dynpart_sort_optimization2.q,\ enforce_order.q,\ filter_join_breaktask.q,\ filter_join_breaktask2.q,\ diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/FileSinkOperator.java ql/src/java/org/apache/hadoop/hive/ql/exec/FileSinkOperator.java index 3ff0782..1088a64 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/FileSinkOperator.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/FileSinkOperator.java @@ -99,6 +99,7 @@ protected transient boolean statsCollectRawDataSize; protected transient boolean[] statsFromRecordWriter; protected transient boolean isCollectRWStats; + protected transient boolean firstRowInGroup; private transient FSPaths prevFsp; private transient FSPaths fpaths; private transient ObjectInspector keyOI; @@ -326,7 +327,7 @@ protected void initializeOp(Configuration hconf) throws HiveException { parent = Utilities.toTempPath(conf.getDirName()); statsCollectRawDataSize = conf.isStatsCollectRawDataSize(); statsFromRecordWriter = new boolean[numFiles]; - + firstRowInGroup = true; serializer = (Serializer) conf.getTableInfo().getDeserializerClass().newInstance(); serializer.initialize(null, conf.getTableInfo().getProperties()); outputClass = serializer.getSerializedClass(); @@ -607,30 +608,53 @@ public void processOp(Object row, int tag) throws HiveException { assert inputObjInspectors[0].getCategory() == ObjectInspector.Category.STRUCT : "input object inspector is not struct"; if (bDynParts) { - // copy the DP column values from the input row to dpVals - dpVals.clear(); - dpWritables.clear(); - ObjectInspectorUtils.partialCopyToStandardObject(dpWritables, row, dpStartCol, numDynParts, - (StructObjectInspector) inputObjInspectors[0], ObjectInspectorCopyOption.WRITABLE); - // get a set of RecordWriter based on the DP column values - // pass the null value along to the escaping process to determine what the dir should be - for (Object o : dpWritables) { - if (o == null || o.toString().length() == 0) { - dpVals.add(dpCtx.getDefaultPartitionName()); - } else { - dpVals.add(o.toString()); - } - } - // use SubStructObjectInspector to serialize the non-partitioning columns in the input row - recordValue = serializer.serialize(row, subSetOI); - // when dynamic partition sorting is not used, the DPSortState will be NONE - // in which we will fall back to old method of file system path creation - // i.e, having as many record writers as distinct values in partition column + // when dynamic partition sorting is not enabled, we really don't care + // about the key as partition columns are last columns in value and + // bucket numbers are computed before writing each rows. When dynamic + // partition sorting is enabled, we look for key which contains + // partition column values and bucket number (is part of key). if (conf.getDpSortState().equals(DPSortState.NONE)) { + // copy the DP column values from the input row to dpVals + dpVals.clear(); + dpWritables.clear(); + ObjectInspectorUtils + .partialCopyToStandardObject(dpWritables, row, dpStartCol, + numDynParts, + (StructObjectInspector) inputObjInspectors[0], + ObjectInspectorCopyOption.WRITABLE); + // get a set of RecordWriter based on the DP column values + // pass the null value along to the escaping process to determine what the dir should be + for (Object o : dpWritables) { + if (o == null || o.toString().length() == 0) { + dpVals.add(dpCtx.getDefaultPartitionName()); + } else { + dpVals.add(o.toString()); + } + } + fpaths = getDynOutPaths(dpVals, lbDirName); + } else { + // copy the DP column values from the group key + keys.clear(); + keyWritables.clear(); + ObjectInspectorUtils.partialCopyToStandardObject(keyWritables, + getGroupKeyObject(), 0, numKeyColToRead, + (StructObjectInspector) keyOI, ObjectInspectorCopyOption.WRITABLE); + + for (Object o : keyWritables) { + if (o == null || o.toString().length() == 0) { + keys.add(dpCtx.getDefaultPartitionName()); + } else { + keys.add(o.toString()); + } + } + + fpaths = getDynOutPaths(keys, null); } + // use SubStructObjectInspector to serialize the non-partitioning columns in the input row + recordValue = serializer.serialize(row, subSetOI); } else { if (lbDirName != null) { fpaths = lookupListBucketingPaths(lbDirName); @@ -919,21 +943,11 @@ private String getDynPartDirectory(List row, List dpColNames) { @Override public void startGroup() throws HiveException { - if (!conf.getDpSortState().equals(DPSortState.NONE)) { + // key object inspectors are never going to change, so we need to get it + // only once + if (!conf.getDpSortState().equals(DPSortState.NONE) && firstRowInGroup) { keyOI = getGroupKeyObjectInspector(); - keys.clear(); - keyWritables.clear(); - ObjectInspectorUtils.partialCopyToStandardObject(keyWritables, getGroupKeyObject(), 0, - numKeyColToRead, (StructObjectInspector) keyOI, ObjectInspectorCopyOption.WRITABLE); - - for (Object o : keyWritables) { - if (o == null || o.toString().length() == 0) { - keys.add(dpCtx.getDefaultPartitionName()); - } else { - keys.add(o.toString()); - } - } - fpaths = getDynOutPaths(keys, null); + firstRowInGroup = false; } } diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/GroupByOperator.java ql/src/java/org/apache/hadoop/hive/ql/exec/GroupByOperator.java index 792d87f..b31b36b 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/GroupByOperator.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/GroupByOperator.java @@ -32,8 +32,6 @@ import java.util.Map; import java.util.Set; -import javolution.util.FastBitSet; - import org.apache.commons.logging.Log; import org.apache.commons.logging.LogFactory; import org.apache.hadoop.conf.Configuration; @@ -69,6 +67,8 @@ import org.apache.hadoop.io.BytesWritable; import org.apache.hadoop.io.Text; +import javolution.util.FastBitSet; + /** * GroupBy operator implementation. */ @@ -872,6 +872,15 @@ private void processAggr(Object row, // Partial aggregation is performed on the mapper, and the // reducer gets 1 row (partial result) per mapper. if (!conf.isDontResetAggrsDistinct()) { + // When sort-based aggregation happens in the reducer, rows with same group + // key gets buffered up and aggregated. When there is change in group key the + // aggregated output of the previous row is forwarded. This is inconsistent + // as group key points to newly changed key but the row forwarded is based on + // previous key. To make it consistent this method updates the group key of + // all the child operators to point to the key of forwarded row. This is + // required for FS to work properly when hive.optimize.sort.dynamic.partition + // is enabled. + updateGroupKeyObject(currentKeys.getKeyArray()); forward(currentKeys.getKeyArray(), aggregations); countAfterReport = 0; } @@ -1086,6 +1095,7 @@ public void flush() throws HiveException{ } else if (aggregations != null) { // sort-based aggregations if (currentKeys != null) { + updateGroupKeyObject(currentKeys.getKeyArray()); forward(currentKeys.getKeyArray(), aggregations); } currentKeys = null; @@ -1100,6 +1110,22 @@ public void flush() throws HiveException{ } } + private void updateGroupKeyObject(Object[] keyArray) { + updateGroupKeyObjectOfChild(this, keyArray); + } + + private void updateGroupKeyObjectOfChild(Operator op, + Object[] keyArray) { + if (op.childOperators == null || op.childOperators.isEmpty()) { + return; + } + + for (Operator child : op.childOperators) { + updateGroupKeyObjectOfChild(child, keyArray); + child.setGroupKeyObject(keyArray); + } + } + /** * We need to forward all the aggregations to children. * diff --git ql/src/test/queries/clientpositive/dynpart_sort_optimization2.q ql/src/test/queries/clientpositive/dynpart_sort_optimization2.q new file mode 100644 index 0000000..adba1d2 --- /dev/null +++ ql/src/test/queries/clientpositive/dynpart_sort_optimization2.q @@ -0,0 +1,200 @@ +set hive.optimize.sort.dynamic.partition=true; +set hive.exec.dynamic.partition=true; +set hive.exec.max.dynamic.partitions=1000; +set hive.exec.max.dynamic.partitions.pernode=1000; +set hive.exec.dynamic.partition.mode=nonstrict; +set hive.enforce.bucketing=false; +set hive.enforce.sorting=false; +set hive.exec.submitviachild=true; +set hive.exec.submit.local.task.via.child=true; + +drop table ss; +drop table ss_orc; +drop table ss_part; +drop table ss_part_orc; + +create table ss ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float); + +create table ss_part ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int); + +load data local inpath '../../data/files/dynpart_test.txt' overwrite into table ss; + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk; + +insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk; + +desc formatted ss_part partition(ss_sold_date_sk=2452617); +select * from ss_part where ss_sold_date_sk=2452617; + +desc formatted ss_part partition(ss_sold_date_sk=2452638); +select * from ss_part where ss_sold_date_sk=2452638; + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk; + +insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk; + +desc formatted ss_part partition(ss_sold_date_sk=2452617); +select * from ss_part where ss_sold_date_sk=2452617; + +desc formatted ss_part partition(ss_sold_date_sk=2452638); +select * from ss_part where ss_sold_date_sk=2452638; + +set hive.optimize.sort.dynamic.partition=false; +-- SORT DYNAMIC PARTITION DISABLED + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk; + +insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk; + +desc formatted ss_part partition(ss_sold_date_sk=2452617); +select * from ss_part where ss_sold_date_sk=2452617; + +desc formatted ss_part partition(ss_sold_date_sk=2452638); +select * from ss_part where ss_sold_date_sk=2452638; + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk; + +insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk; + +desc formatted ss_part partition(ss_sold_date_sk=2452617); +select * from ss_part where ss_sold_date_sk=2452617; + +desc formatted ss_part partition(ss_sold_date_sk=2452638); +select * from ss_part where ss_sold_date_sk=2452638; + +set hive.vectorized.execution.enabled=true; +-- VECTORIZATION IS ENABLED + +create table ss_orc ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) stored as orc; + +create table ss_part_orc ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) stored as orc; + +insert overwrite table ss_orc select * from ss; + +drop table ss; +drop table ss_part; + +explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk; + +insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk; + +desc formatted ss_part_orc partition(ss_sold_date_sk=2452617); +select * from ss_part_orc where ss_sold_date_sk=2452617; + +desc formatted ss_part_orc partition(ss_sold_date_sk=2452638); +select * from ss_part_orc where ss_sold_date_sk=2452638; + +explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk; + +insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk; + +desc formatted ss_part_orc partition(ss_sold_date_sk=2452617); +select * from ss_part_orc where ss_sold_date_sk=2452617; + +desc formatted ss_part_orc partition(ss_sold_date_sk=2452638); +select * from ss_part_orc where ss_sold_date_sk=2452638; + +drop table ss_orc; +drop table ss_part_orc; \ No newline at end of file diff --git ql/src/test/results/clientpositive/dynpart_sort_optimization2.q.out ql/src/test/results/clientpositive/dynpart_sort_optimization2.q.out new file mode 100644 index 0000000..f08fe32 --- /dev/null +++ ql/src/test/results/clientpositive/dynpart_sort_optimization2.q.out @@ -0,0 +1,1520 @@ +PREHOOK: query: drop table ss +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table ss_orc +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss_orc +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table ss_part +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss_part +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table ss_part_orc +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss_part_orc +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table ss ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss +POSTHOOK: query: create table ss ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss +PREHOOK: query: create table ss_part ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss_part +POSTHOOK: query: create table ss_part ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss_part +PREHOOK: query: load data local inpath '../../data/files/dynpart_test.txt' overwrite into table ss +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@ss +POSTHOOK: query: load data local inpath '../../data/files/dynpart_test.txt' overwrite into table ss +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@ss +PREHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +2.1 -2026.3 2452617 +2.99 -11.32 2452617 +85.8 25.61 2452617 +552.96 -1363.84 2452617 +565.92 196.48 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +7412.83 2071.68 2452617 +10022.63 3952.8 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +0.15 -241.22 2452638 +150.39 -162.12 2452638 +156.67 -4626.56 2452638 +181.03 -207.24 2452638 +267.01 -3266.36 2452638 +317.87 -3775.38 2452638 +1327.08 57.97 2452638 +1413.19 178.08 2452638 +1524.33 494.37 2452638 +1971.35 -488.25 2452638 +4133.98 -775.72 2452638 +4329.49 -4000.51 2452638 +10171.1 660.48 2452638 +PREHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +10022.63 3952.8 2452617 +2.99 -11.32 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +565.92 196.48 2452617 +85.8 25.61 2452617 +7412.83 2071.68 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +552.96 -1363.84 2452617 +2.1 -2026.3 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +4329.49 -4000.51 2452638 +1413.19 178.08 2452638 +150.39 -162.12 2452638 +1524.33 494.37 2452638 +0.15 -241.22 2452638 +267.01 -3266.36 2452638 +181.03 -207.24 2452638 +1971.35 -488.25 2452638 +1327.08 57.97 2452638 +156.67 -4626.56 2452638 +317.87 -3775.38 2452638 +10171.1 660.48 2452638 +4133.98 -775.72 2452638 +PREHOOK: query: -- SORT DYNAMIC PARTITION DISABLED + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: -- SORT DYNAMIC PARTITION DISABLED + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +2.1 -2026.3 2452617 +2.99 -11.32 2452617 +85.8 25.61 2452617 +552.96 -1363.84 2452617 +565.92 196.48 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +7412.83 2071.68 2452617 +10022.63 3952.8 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +0.15 -241.22 2452638 +150.39 -162.12 2452638 +156.67 -4626.56 2452638 +181.03 -207.24 2452638 +267.01 -3266.36 2452638 +317.87 -3775.38 2452638 +1327.08 57.97 2452638 +1413.19 178.08 2452638 +1524.33 494.37 2452638 +1971.35 -488.25 2452638 +4133.98 -775.72 2452638 +4329.49 -4000.51 2452638 +10171.1 660.48 2452638 +PREHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +565.92 196.48 2452617 +85.8 25.61 2452617 +7412.83 2071.68 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +552.96 -1363.84 2452617 +2.1 -2026.3 2452617 +10022.63 3952.8 2452617 +2.99 -11.32 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +4329.49 -4000.51 2452638 +1413.19 178.08 2452638 +150.39 -162.12 2452638 +1524.33 494.37 2452638 +0.15 -241.22 2452638 +267.01 -3266.36 2452638 +181.03 -207.24 2452638 +1971.35 -488.25 2452638 +1327.08 57.97 2452638 +156.67 -4626.56 2452638 +317.87 -3775.38 2452638 +10171.1 660.48 2452638 +4133.98 -775.72 2452638 +PREHOOK: query: -- VECTORIZATION IS ENABLED + +create table ss_orc ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss_orc +POSTHOOK: query: -- VECTORIZATION IS ENABLED + +create table ss_orc ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss_orc +PREHOOK: query: create table ss_part_orc ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: create table ss_part_orc ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss_part_orc +PREHOOK: query: insert overwrite table ss_orc select * from ss +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_orc +POSTHOOK: query: insert overwrite table ss_orc select * from ss +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_orc +POSTHOOK: Lineage: ss_orc.ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_orc.ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_orc.ss_sold_date_sk SIMPLE [(ss)ss.FieldSchema(name:ss_sold_date_sk, type:int, comment:null), ] +PREHOOK: query: drop table ss +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss +POSTHOOK: query: drop table ss +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss +PREHOOK: query: drop table ss_part +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss_part +PREHOOK: Output: default@ss_part +POSTHOOK: query: drop table ss_part +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss_part +POSTHOOK: Output: default@ss_part +PREHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: ss_orc + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 12 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 + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_orc +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_orc +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 88 + totalSize 417 +#### 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: select * from ss_part_orc where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +2.1 -2026.3 2452617 +2.99 -11.32 2452617 +85.8 25.61 2452617 +552.96 -1363.84 2452617 +565.92 196.48 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +7412.83 2071.68 2452617 +10022.63 3952.8 2452617 +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 104 + totalSize 440 +#### 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: select * from ss_part_orc where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +0.15 -241.22 2452638 +150.39 -162.12 2452638 +156.67 -4626.56 2452638 +181.03 -207.24 2452638 +267.01 -3266.36 2452638 +317.87 -3775.38 2452638 +1327.08 57.97 2452638 +1413.19 178.08 2452638 +1524.33 494.37 2452638 +1971.35 -488.25 2452638 +4133.98 -775.72 2452638 +4329.49 -4000.51 2452638 +10171.1 660.48 2452638 +PREHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: ss_orc + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) + Execution mode: vectorized + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 24 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 + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_orc +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_orc +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 88 + totalSize 417 +#### 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: select * from ss_part_orc where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +565.92 196.48 2452617 +85.8 25.61 2452617 +7412.83 2071.68 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +552.96 -1363.84 2452617 +2.1 -2026.3 2452617 +10022.63 3952.8 2452617 +2.99 -11.32 2452617 +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 104 + totalSize 440 +#### 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: select * from ss_part_orc where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +4329.49 -4000.51 2452638 +1413.19 178.08 2452638 +150.39 -162.12 2452638 +1524.33 494.37 2452638 +0.15 -241.22 2452638 +267.01 -3266.36 2452638 +181.03 -207.24 2452638 +1971.35 -488.25 2452638 +1327.08 57.97 2452638 +156.67 -4626.56 2452638 +317.87 -3775.38 2452638 +10171.1 660.48 2452638 +4133.98 -775.72 2452638 +PREHOOK: query: drop table ss_orc +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss_orc +PREHOOK: Output: default@ss_orc +POSTHOOK: query: drop table ss_orc +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss_orc +POSTHOOK: Output: default@ss_orc +PREHOOK: query: drop table ss_part_orc +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss_part_orc +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: drop table ss_part_orc +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Output: default@ss_part_orc diff --git ql/src/test/results/clientpositive/tez/dynpart_sort_optimization2.q.out ql/src/test/results/clientpositive/tez/dynpart_sort_optimization2.q.out new file mode 100644 index 0000000..1050f7f --- /dev/null +++ ql/src/test/results/clientpositive/tez/dynpart_sort_optimization2.q.out @@ -0,0 +1,1580 @@ +PREHOOK: query: drop table ss +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table ss_orc +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss_orc +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table ss_part +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss_part +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table ss_part_orc +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss_part_orc +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table ss ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss +POSTHOOK: query: create table ss ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss +PREHOOK: query: create table ss_part ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss_part +POSTHOOK: query: create table ss_part ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss_part +PREHOOK: query: load data local inpath '../../data/files/dynpart_test.txt' overwrite into table ss +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@ss +POSTHOOK: query: load data local inpath '../../data/files/dynpart_test.txt' overwrite into table ss +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@ss +PREHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +2.1 -2026.3 2452617 +2.99 -11.32 2452617 +85.8 25.61 2452617 +552.96 -1363.84 2452617 +565.92 196.48 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +7412.83 2071.68 2452617 +10022.63 3952.8 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +0.15 -241.22 2452638 +150.39 -162.12 2452638 +156.67 -4626.56 2452638 +181.03 -207.24 2452638 +267.01 -3266.36 2452638 +317.87 -3775.38 2452638 +1327.08 57.97 2452638 +1413.19 178.08 2452638 +1524.33 494.37 2452638 +1971.35 -488.25 2452638 +4133.98 -775.72 2452638 +4329.49 -4000.51 2452638 +10171.1 660.48 2452638 +PREHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) + Reducer 2 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +10022.63 3952.8 2452617 +2.99 -11.32 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +565.92 196.48 2452617 +85.8 25.61 2452617 +7412.83 2071.68 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +552.96 -1363.84 2452617 +2.1 -2026.3 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +4329.49 -4000.51 2452638 +1413.19 178.08 2452638 +150.39 -162.12 2452638 +1524.33 494.37 2452638 +0.15 -241.22 2452638 +267.01 -3266.36 2452638 +181.03 -207.24 2452638 +1971.35 -488.25 2452638 +1327.08 57.97 2452638 +156.67 -4626.56 2452638 +317.87 -3775.38 2452638 +10171.1 660.48 2452638 +4133.98 -775.72 2452638 +PREHOOK: query: -- SORT DYNAMIC PARTITION DISABLED + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: -- SORT DYNAMIC PARTITION DISABLED + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +2.1 -2026.3 2452617 +2.99 -11.32 2452617 +85.8 25.61 2452617 +552.96 -1363.84 2452617 +565.92 196.48 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +7412.83 2071.68 2452617 +10022.63 3952.8 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +0.15 -241.22 2452638 +150.39 -162.12 2452638 +156.67 -4626.56 2452638 +181.03 -207.24 2452638 +267.01 -3266.36 2452638 +317.87 -3775.38 2452638 +1327.08 57.97 2452638 +1413.19 178.08 2452638 +1524.33 494.37 2452638 +1971.35 -488.25 2452638 +4133.98 -775.72 2452638 +4329.49 -4000.51 2452638 +10171.1 660.48 2452638 +PREHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) + Reducer 2 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +565.92 196.48 2452617 +85.8 25.61 2452617 +7412.83 2071.68 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +552.96 -1363.84 2452617 +2.1 -2026.3 2452617 +10022.63 3952.8 2452617 +2.99 -11.32 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### 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.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +4329.49 -4000.51 2452638 +1413.19 178.08 2452638 +150.39 -162.12 2452638 +1524.33 494.37 2452638 +0.15 -241.22 2452638 +267.01 -3266.36 2452638 +181.03 -207.24 2452638 +1971.35 -488.25 2452638 +1327.08 57.97 2452638 +156.67 -4626.56 2452638 +317.87 -3775.38 2452638 +10171.1 660.48 2452638 +4133.98 -775.72 2452638 +PREHOOK: query: -- VECTORIZATION IS ENABLED + +create table ss_orc ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss_orc +POSTHOOK: query: -- VECTORIZATION IS ENABLED + +create table ss_orc ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss_orc +PREHOOK: query: create table ss_part_orc ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: create table ss_part_orc ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss_part_orc +PREHOOK: query: insert overwrite table ss_orc select * from ss +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_orc +POSTHOOK: query: insert overwrite table ss_orc select * from ss +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_orc +POSTHOOK: Lineage: ss_orc.ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_orc.ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_orc.ss_sold_date_sk SIMPLE [(ss)ss.FieldSchema(name:ss_sold_date_sk, type:int, comment:null), ] +PREHOOK: query: drop table ss +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss +POSTHOOK: query: drop table ss +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss +PREHOOK: query: drop table ss_part +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss_part +PREHOOK: Output: default@ss_part +POSTHOOK: query: drop table ss_part +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss_part +POSTHOOK: Output: default@ss_part +PREHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss_orc + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 12 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 + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_orc +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_orc +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 88 + totalSize 417 +#### 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: select * from ss_part_orc where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +2.1 -2026.3 2452617 +2.99 -11.32 2452617 +85.8 25.61 2452617 +552.96 -1363.84 2452617 +565.92 196.48 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +7412.83 2071.68 2452617 +10022.63 3952.8 2452617 +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 104 + totalSize 440 +#### 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: select * from ss_part_orc where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +0.15 -241.22 2452638 +150.39 -162.12 2452638 +156.67 -4626.56 2452638 +181.03 -207.24 2452638 +267.01 -3266.36 2452638 +317.87 -3775.38 2452638 +1327.08 57.97 2452638 +1413.19 178.08 2452638 +1524.33 494.37 2452638 +1971.35 -488.25 2452638 +4133.98 -775.72 2452638 +4329.49 -4000.51 2452638 +10171.1 660.48 2452638 +PREHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss_orc + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) + Execution mode: vectorized + Reducer 2 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 24 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 + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_orc +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_orc +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 88 + totalSize 417 +#### 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: select * from ss_part_orc where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +565.92 196.48 2452617 +85.8 25.61 2452617 +7412.83 2071.68 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +552.96 -1363.84 2452617 +2.1 -2026.3 2452617 +10022.63 3952.8 2452617 +2.99 -11.32 2452617 +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 104 + totalSize 440 +#### 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: select * from ss_part_orc where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +4329.49 -4000.51 2452638 +1413.19 178.08 2452638 +150.39 -162.12 2452638 +1524.33 494.37 2452638 +0.15 -241.22 2452638 +267.01 -3266.36 2452638 +181.03 -207.24 2452638 +1971.35 -488.25 2452638 +1327.08 57.97 2452638 +156.67 -4626.56 2452638 +317.87 -3775.38 2452638 +10171.1 660.48 2452638 +4133.98 -775.72 2452638 +PREHOOK: query: drop table ss_orc +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss_orc +PREHOOK: Output: default@ss_orc +POSTHOOK: query: drop table ss_orc +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss_orc +POSTHOOK: Output: default@ss_orc +PREHOOK: query: drop table ss_part_orc +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss_part_orc +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: drop table ss_part_orc +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Output: default@ss_part_orc