diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/AnnotateStatsProcCtx.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/AnnotateStatsProcCtx.java index 0b7f14f957..187ec254a7 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/AnnotateStatsProcCtx.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/AnnotateStatsProcCtx.java @@ -77,6 +77,10 @@ public void addAffectedColumn(ExprNodeColumnDesc column) { affectedColumns.add(column.getColumn()); } + public void addAffectedColumns(Set columns) { + affectedColumns.addAll(columns); + } + public Set getAffectedColumns() { return affectedColumns; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/StatsRulesProcFactory.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/StatsRulesProcFactory.java index 0258e36738..4fc73620fe 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/StatsRulesProcFactory.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/StatsRulesProcFactory.java @@ -334,13 +334,14 @@ protected long evaluateExpression(Statistics stats, ExprNodeDesc pred, // for AND condition cascadingly update stats if (udf instanceof GenericUDFOPAnd) { + Set affectedColumns = new HashSet<>(); andStats = stats.clone(); aspCtx.setAndExprStats(andStats); + aspCtx.clearAffectedColumns(); // evaluate children long evaluatedRowCount = currNumRows; for (ExprNodeDesc child : genFunc.getChildren()) { - aspCtx.clearAffectedColumns(); evaluatedRowCount = evaluateChildExpr(aspCtx.getAndExprStats(), child, aspCtx, neededCols, op, evaluatedRowCount); newNumRows = evaluatedRowCount; @@ -353,7 +354,10 @@ protected long evaluateExpression(Statistics stats, ExprNodeDesc pred, } else { StatsUtils.updateStats(aspCtx.getAndExprStats(), newNumRows, false, op); } + affectedColumns.addAll(aspCtx.getAffectedColumns()); + aspCtx.clearAffectedColumns(); } + aspCtx.addAffectedColumns(affectedColumns); } else if (udf instanceof GenericUDFOPOr) { // for OR condition independently compute and update stats. for (ExprNodeDesc child : genFunc.getChildren()) { diff --git a/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out b/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out index 64b97ee5aa..709de139ca 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out @@ -1380,14 +1380,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col2 - Statistics: Num rows: 223 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 241 Data size: 964 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 223 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 241 Data size: 964 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 223 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 241 Data size: 964 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/correlationoptimizer9.q.out b/ql/src/test/results/clientpositive/correlationoptimizer9.q.out index 0c2f78fe48..506fbe1365 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer9.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer9.q.out @@ -443,14 +443,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 57 Data size: 11742 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 94 Data size: 19364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 57 Data size: 11742 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 94 Data size: 19364 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 11742 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 94 Data size: 19364 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/filter_join_breaktask.q.out b/ql/src/test/results/clientpositive/filter_join_breaktask.q.out index 9fb11d6236..ec5d4a14e1 100644 --- a/ql/src/test/results/clientpositive/filter_join_breaktask.q.out +++ b/ql/src/test/results/clientpositive/filter_join_breaktask.q.out @@ -158,7 +158,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 15 Data size: 1375 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2305 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -188,7 +188,7 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 15 Data size: 1375 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2305 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col0 (type: int) auto parallelism: false @@ -298,17 +298,17 @@ STAGE PLANS: 0 _col2 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 19 Data size: 1747 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 32 Data size: 2956 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 19 Data size: 1747 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 32 Data size: 2956 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 19 Data size: 1747 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 32 Data size: 2956 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/llap/auto_join29.q.out b/ql/src/test/results/clientpositive/llap/auto_join29.q.out index b5f16f3eba..964bfd9932 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join29.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join29.q.out @@ -672,15 +672,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 input vertices: 1 Map 4 - Statistics: Num rows: 762 Data size: 318086 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1204 Data size: 554114 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 762 Data size: 318086 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1204 Data size: 554114 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 762 Data size: 318086 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1204 Data size: 554114 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 3 @@ -723,10 +723,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 762 Data size: 318086 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1204 Data size: 554114 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 762 Data size: 318086 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1204 Data size: 554114 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1313,15 +1313,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 input vertices: 1 Map 4 - Statistics: Num rows: 762 Data size: 318086 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1204 Data size: 554114 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 762 Data size: 318086 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1204 Data size: 554114 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 762 Data size: 318086 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1204 Data size: 554114 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 4 @@ -1347,10 +1347,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 762 Data size: 318086 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1204 Data size: 554114 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 762 Data size: 318086 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1204 Data size: 554114 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2559,7 +2559,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6 input vertices: 1 Map 3 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -2569,15 +2569,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 input vertices: 1 Map 4 - Statistics: Num rows: 110 Data size: 49128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 221 Data size: 102884 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 110 Data size: 49128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 221 Data size: 102884 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 110 Data size: 49128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 221 Data size: 102884 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 3 @@ -2620,10 +2620,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 110 Data size: 49128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 221 Data size: 102884 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 110 Data size: 49128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 221 Data size: 102884 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2685,12 +2685,12 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6 input vertices: 1 Map 2 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: string) sort order: + Map-reduce partition columns: _col5 (type: string) - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs @@ -2728,15 +2728,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 input vertices: 0 Map 1 - Statistics: Num rows: 587 Data size: 135814 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 636 Data size: 161980 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 587 Data size: 135814 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 636 Data size: 161980 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 587 Data size: 135814 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 636 Data size: 161980 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 4 @@ -2745,10 +2745,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 587 Data size: 135814 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 636 Data size: 161980 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 587 Data size: 135814 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 636 Data size: 161980 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3321,15 +3321,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 input vertices: 1 Map 4 - Statistics: Num rows: 254 Data size: 106088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 401 Data size: 184586 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 254 Data size: 106088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 401 Data size: 184586 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 254 Data size: 106088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 401 Data size: 184586 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 3 @@ -3372,10 +3372,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 254 Data size: 106088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 401 Data size: 184586 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 254 Data size: 106088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 401 Data size: 184586 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3456,7 +3456,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6 input vertices: 0 Map 1 - Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -3466,15 +3466,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 input vertices: 1 Map 4 - Statistics: Num rows: 166 Data size: 88644 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 166 Data size: 88644 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 166 Data size: 88644 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 4 @@ -3500,10 +3500,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 166 Data size: 88644 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 88644 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3587,12 +3587,12 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6 input vertices: 1 Map 2 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: string) sort order: + Map-reduce partition columns: _col5 (type: string) - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs @@ -3631,15 +3631,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 input vertices: 0 Map 1 - Statistics: Num rows: 55 Data size: 29370 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 55 Data size: 29370 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 55 Data size: 29370 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 4 @@ -3648,10 +3648,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 55 Data size: 29370 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 29370 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out index 2e2303fe24..ce49b5f5c2 100644 --- a/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out @@ -611,10 +611,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -737,10 +737,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -885,10 +885,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1023,10 +1023,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1269,10 +1269,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1389,12 +1389,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap Map 5 Map Operator Tree: @@ -1425,10 +1425,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.8333333 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1558,10 +1558,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_10.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_10.q.out index 2697fc9d60..7c95815758 100644 --- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_10.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_10.q.out @@ -152,10 +152,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.8333333 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -273,7 +273,7 @@ STAGE PLANS: keys: key (type: int) mode: final outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out index 838087d71e..6ef947bd99 100644 --- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out @@ -737,10 +737,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -863,10 +863,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1011,10 +1011,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1149,10 +1149,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1395,10 +1395,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1505,10 +1505,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1627,12 +1627,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap Map 5 Map Operator Tree: @@ -1663,10 +1663,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.8333333 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1796,10 +1796,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -2560,10 +2560,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -2686,10 +2686,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -2834,10 +2834,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -2972,10 +2972,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -3084,10 +3084,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -3194,10 +3194,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -3316,12 +3316,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap Map 5 Map Operator Tree: @@ -3352,10 +3352,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.8333333 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -3485,10 +3485,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out index aadd8e2868..d78171aa96 100644 --- a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out @@ -712,10 +712,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -773,10 +773,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 166 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -884,10 +884,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 332 Data size: 1996 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 332 Data size: 1996 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -945,10 +945,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 332 Data size: 1996 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 332 Data size: 1996 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1056,10 +1056,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 332 Data size: 1996 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 332 Data size: 1996 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1137,10 +1137,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Map 1 - Statistics: Num rows: 332 Data size: 1996 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 332 Data size: 1996 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/convert_decimal64_to_decimal.q.out b/ql/src/test/results/clientpositive/llap/convert_decimal64_to_decimal.q.out index 31d812705c..2570aed11b 100644 --- a/ql/src/test/results/clientpositive/llap/convert_decimal64_to_decimal.q.out +++ b/ql/src/test/results/clientpositive/llap/convert_decimal64_to_decimal.q.out @@ -196,7 +196,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 3 - Statistics: Num rows: 894 Data size: 3224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 958 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) Group By Vectorization: @@ -412,7 +412,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 3 - Statistics: Num rows: 894 Data size: 3224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 958 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out index 5aea1fafaa..ee50efdf16 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out @@ -465,7 +465,7 @@ Stage-0 <-Reducer 2 [ONE_TO_ONE_EDGE] llap FORWARD [RS_20] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_63] (rows=5 width=104) + Merge Join Operator [MERGEJOIN_63] (rows=2 width=105) Conds:RS_17._col0=RS_18._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"],residual filter predicates:{((_col4 > 0) or _col2)} <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_17] @@ -479,9 +479,9 @@ Stage-0 <-Reducer 7 [SIMPLE_EDGE] llap SHUFFLE [RS_18] PartitionCols:_col0 - Select Operator [SEL_9] (rows=2 width=97) + Select Operator [SEL_9] (rows=1 width=97) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_8] (rows=2 width=101) + Group By Operator [GBY_8] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Map 6 [SIMPLE_EDGE] llap SHUFFLE [RS_7] @@ -1349,9 +1349,9 @@ Stage-0 Stage-1 Reducer 3 llap File Output Operator [FS_16] - Select Operator [SEL_15] (rows=24 width=100) + Select Operator [SEL_15] (rows=39 width=100) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_49] (rows=24 width=104) + Merge Join Operator [MERGEJOIN_49] (rows=39 width=104) Conds:RS_12._col0=RS_13._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7"],residual filter predicates:{((_col1 > 0) or _col7)} {((_col1 > 0) or (_col6 >= 0))} <-Map 5 [SIMPLE_EDGE] llap SHUFFLE [RS_13] @@ -1365,7 +1365,7 @@ Stage-0 <-Reducer 2 [ONE_TO_ONE_EDGE] llap FORWARD [RS_12] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_48] (rows=8 width=182) + Merge Join Operator [MERGEJOIN_48] (rows=13 width=182) Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4"],residual filter predicates:{((_col1 + _col4) = 2)} <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_9] @@ -1414,9 +1414,9 @@ Stage-0 Stage-1 Reducer 3 llap File Output Operator [FS_16] - Select Operator [SEL_15] (rows=24 width=100) + Select Operator [SEL_15] (rows=39 width=100) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_49] (rows=24 width=104) + Merge Join Operator [MERGEJOIN_49] (rows=39 width=104) Conds:RS_12._col0=RS_13._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7"],residual filter predicates:{((_col1 > 0) or _col7)} {((_col1 > 0) or (_col6 >= 0))} <-Map 5 [SIMPLE_EDGE] llap SHUFFLE [RS_13] @@ -1430,7 +1430,7 @@ Stage-0 <-Reducer 2 [ONE_TO_ONE_EDGE] llap FORWARD [RS_12] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_48] (rows=8 width=182) + Merge Join Operator [MERGEJOIN_48] (rows=13 width=182) Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4"],residual filter predicates:{((_col1 + _col4) = 2)} <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_9] @@ -2234,7 +2234,7 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_37] (rows=83 width=178) + Merge Join Operator [MERGEJOIN_37] (rows=131 width=178) Conds:RS_8._col0, _col1=RS_9._col0, _col1(Left Semi),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] @@ -2290,7 +2290,7 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_37] (rows=83 width=178) + Merge Join Operator [MERGEJOIN_37] (rows=131 width=178) Conds:RS_8._col0, _col1=RS_9._col0, _col1(Left Semi),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] @@ -2336,7 +2336,7 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_27] (rows=83 width=178) + Merge Join Operator [MERGEJOIN_27] (rows=131 width=178) Conds:RS_8._col0=RS_9._col0(Left Semi),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] @@ -2385,9 +2385,9 @@ Stage-0 Stage-1 Reducer 3 llap File Output Operator [FS_21] - Select Operator [SEL_20] (rows=1 width=8) + Select Operator [SEL_20] (rows=3 width=8) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_51] (rows=1 width=8) + Merge Join Operator [MERGEJOIN_51] (rows=3 width=8) Conds:RS_17._col1, _col4=RS_18._col0, _col1(Left Semi),Output:["_col0","_col3"] <-Map 5 [SIMPLE_EDGE] llap SHUFFLE [RS_18] @@ -2464,16 +2464,16 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] llap SHUFFLE [RS_29] PartitionCols:_col2 - Filter Operator [FIL_39] (rows=41 width=186) + Filter Operator [FIL_39] (rows=65 width=186) predicate:_col2 is not null - Group By Operator [GBY_16] (rows=41 width=186) + Group By Operator [GBY_16] (rows=65 width=186) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 3 [SIMPLE_EDGE] llap SHUFFLE [RS_15] PartitionCols:_col0, _col1 - Group By Operator [GBY_14] (rows=41 width=186) + Group By Operator [GBY_14] (rows=65 width=186) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col2 - Merge Join Operator [MERGEJOIN_55] (rows=83 width=178) + Merge Join Operator [MERGEJOIN_55] (rows=131 width=178) Conds:RS_10._col0=RS_11._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] llap SHUFFLE [RS_11] @@ -2704,16 +2704,16 @@ Stage-0 Stage-1 Reducer 3 llap File Output Operator [FS_24] - Select Operator [SEL_23] (rows=38 width=223) + Select Operator [SEL_23] (rows=41 width=223) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_22] (rows=38 width=234) + Filter Operator [FIL_22] (rows=41 width=229) predicate:((_col8 is null or (_col4 = 0L) or _col4 is null) and ((_col5 < _col4) is not true or (_col4 = 0L) or _col4 is null or _col8 is not null or _col0 is null) and (_col0 is not null or (_col4 = 0L) or _col4 is null or _col8 is not null)) - Merge Join Operator [MERGEJOIN_45] (rows=38 width=234) + Merge Join Operator [MERGEJOIN_45] (rows=41 width=229) Conds:RS_19._col0, _col1=RS_20._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col8"] <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_19] PartitionCols:_col0, _col1 - Merge Join Operator [MERGEJOIN_44] (rows=33 width=233) + Merge Join Operator [MERGEJOIN_44] (rows=36 width=227) Conds:RS_16._col1=RS_17._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_16] @@ -2725,12 +2725,12 @@ Stage-0 <-Reducer 4 [ONE_TO_ONE_EDGE] llap FORWARD [RS_17] PartitionCols:_col0 - Group By Operator [GBY_7] (rows=4 width=114) + Group By Operator [GBY_7] (rows=2 width=114) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] PartitionCols:_col0 - Group By Operator [GBY_5] (rows=4 width=114) + Group By Operator [GBY_5] (rows=2 width=114) Output:["_col0","_col1","_col2"],aggregations:["count()","count(p_name)"],keys:p_mfgr Select Operator [SEL_4] (rows=8 width=223) Output:["p_name","p_mfgr"] diff --git a/ql/src/test/results/clientpositive/llap/explainuser_4.q.out b/ql/src/test/results/clientpositive/llap/explainuser_4.q.out index a2e11f93e3..d7edf0ae11 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_4.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_4.q.out @@ -30,11 +30,11 @@ Stage-0 Stage-1 Reducer 3 vectorized, llap File Output Operator [FS_35] - Select Operator [SEL_34] (rows=1019 width=484) + Select Operator [SEL_34] (rows=2048 width=552) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_27] (rows=1019 width=484) + Merge Join Operator [MERGEJOIN_27] (rows=2048 width=552) Conds:RS_30._col2=RS_33._col2(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_30] @@ -119,7 +119,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_11] Group By Operator [GBY_10] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_29] (rows=1019 width=8) + Merge Join Operator [MERGEJOIN_29] (rows=2048 width=8) Conds:RS_32._col0=RS_35._col0(Inner) <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_32] @@ -192,18 +192,18 @@ Stage-0 Stage-1 Reducer 4 vectorized, llap File Output Operator [FS_41] - Select Operator [SEL_40] (rows=509 width=10) + Select Operator [SEL_40] (rows=1024 width=11) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_39] - Group By Operator [GBY_38] (rows=509 width=10) + Group By Operator [GBY_38] (rows=1024 width=11) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_11] PartitionCols:_col0 - Group By Operator [GBY_10] (rows=509 width=10) + Group By Operator [GBY_10] (rows=1024 width=11) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Merge Join Operator [MERGEJOIN_31] (rows=1019 width=2) + Merge Join Operator [MERGEJOIN_31] (rows=2048 width=3) Conds:RS_34._col1=RS_37._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_34] diff --git a/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out b/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out index c9133d3e8a..a2ef96bce0 100644 --- a/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out +++ b/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out @@ -304,13 +304,13 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col2 Position of Big Table: 1 - Statistics: Num rows: 15 Data size: 1375 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2305 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 15 Data size: 1375 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2305 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col0 (type: int) auto parallelism: true @@ -325,18 +325,18 @@ STAGE PLANS: 0 _col2 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col3 - Position of Big Table: 1 - Statistics: Num rows: 19 Data size: 1747 Basic stats: COMPLETE Column stats: COMPLETE + Position of Big Table: 0 + Statistics: Num rows: 32 Data size: 2956 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 19 Data size: 1747 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 32 Data size: 2956 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 19 Data size: 1747 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 32 Data size: 2956 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out index 3f6a78609a..f39dc2b781 100644 --- a/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out @@ -315,7 +315,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 13785 Data size: 110280 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() minReductionHashAggr: 0.99 @@ -439,7 +439,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 13785 Data size: 110280 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() minReductionHashAggr: 0.99 @@ -559,7 +559,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18466 Data size: 147728 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21560 Data size: 172480 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() minReductionHashAggr: 0.99 @@ -679,7 +679,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18466 Data size: 147728 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21560 Data size: 172480 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() minReductionHashAggr: 0.99 diff --git a/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_2.q.out index 9eac2555fd..1ddc1ea1ec 100644 --- a/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_2.q.out @@ -1401,7 +1401,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Map 1 - Statistics: Num rows: 4 Data size: 700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1411,7 +1411,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1421,7 +1421,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 5 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 114 Data size: 10146 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1430,10 +1430,10 @@ STAGE PLANS: 1 value (type: string) input vertices: 1 Map 6 - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 185 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1632,7 +1632,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Map 1 - Statistics: Num rows: 4 Data size: 700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1642,7 +1642,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1652,7 +1652,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 5 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 114 Data size: 10146 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1661,10 +1661,10 @@ STAGE PLANS: 1 value (type: string) input vertices: 1 Map 6 - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 185 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/join46.q.out b/ql/src/test/results/clientpositive/llap/join46.q.out index 85fd4c5656..485573aa73 100644 --- a/ql/src/test/results/clientpositive/llap/join46.q.out +++ b/ql/src/test/results/clientpositive/llap/join46.q.out @@ -475,10 +475,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 7 Data size: 1237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 1237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1665,14 +1665,14 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col6)} - Statistics: Num rows: 7 Data size: 1265 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 7 Data size: 1237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 1237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2310,14 +2310,14 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 residual filter predicates: {(_col4 BETWEEN 100 AND 102 or _col3)} - Statistics: Num rows: 7 Data size: 1261 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: int), _col5 (type: int), _col6 (type: string), _col0 (type: int), _col1 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 7 Data size: 1233 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 7 Data size: 1233 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) Reducer 3 Execution mode: llap @@ -2330,10 +2330,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 residual filter predicates: {(_col1 is null or (_col10 is null and (_col7 <> _col4)))} - Statistics: Num rows: 63 Data size: 23764 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 72 Data size: 27306 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 63 Data size: 23764 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 72 Data size: 27306 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/mapjoin46.q.out b/ql/src/test/results/clientpositive/llap/mapjoin46.q.out index 3715be62a8..1610bf7000 100644 --- a/ql/src/test/results/clientpositive/llap/mapjoin46.q.out +++ b/ql/src/test/results/clientpositive/llap/mapjoin46.q.out @@ -447,10 +447,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 input vertices: 0 Map 1 - Statistics: Num rows: 7 Data size: 1237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 1237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1472,14 +1472,14 @@ STAGE PLANS: input vertices: 0 Map 1 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col6)} - Statistics: Num rows: 7 Data size: 1265 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 7 Data size: 1237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 1237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2538,14 +2538,14 @@ STAGE PLANS: input vertices: 1 Map 3 residual filter predicates: {(_col4 BETWEEN 100 AND 102 or _col3)} - Statistics: Num rows: 7 Data size: 1261 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: int), _col5 (type: int), _col6 (type: string), _col0 (type: int), _col1 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 7 Data size: 1233 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 7 Data size: 1233 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) Execution mode: llap LLAP IO: no inputs @@ -2624,10 +2624,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 residual filter predicates: {(_col1 is null or (_col10 is null and (_col7 <> _col4)))} - Statistics: Num rows: 63 Data size: 23764 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 72 Data size: 27306 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 63 Data size: 23764 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 72 Data size: 27306 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2784,14 +2784,14 @@ STAGE PLANS: input vertices: 1 Map 3 residual filter predicates: {(_col4 BETWEEN 100 AND 102 or _col3)} - Statistics: Num rows: 7 Data size: 1261 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: int), _col5 (type: int), _col6 (type: string), _col0 (type: int), _col1 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 7 Data size: 1233 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 7 Data size: 1233 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) Execution mode: llap LLAP IO: no inputs @@ -2870,10 +2870,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 residual filter predicates: {(_col1 is null or (_col10 is null and (_col7 <> _col4)))} - Statistics: Num rows: 63 Data size: 23764 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 72 Data size: 27306 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 63 Data size: 23764 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 72 Data size: 27306 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/orc_llap.q.out b/ql/src/test/results/clientpositive/llap/orc_llap.q.out index 4f805b0a23..b9c5b06025 100644 --- a/ql/src/test/results/clientpositive/llap/orc_llap.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_llap.q.out @@ -640,11 +640,11 @@ STAGE PLANS: outputColumnNames: _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 159130 Data size: 26936864 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 285509 Data size: 50948874 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col1,_col3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 159130 Data size: 26936864 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 285509 Data size: 50948874 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) minReductionHashAggr: 0.99 @@ -1124,11 +1124,11 @@ STAGE PLANS: outputColumnNames: _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 636522 Data size: 114343414 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1142036 Data size: 210391074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col1,_col3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 636522 Data size: 114343414 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1142036 Data size: 210391074 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) minReductionHashAggr: 0.99 diff --git a/ql/src/test/results/clientpositive/llap/semijoin6.q.out b/ql/src/test/results/clientpositive/llap/semijoin6.q.out index 18c46a7dae..4b8fcf7979 100644 --- a/ql/src/test/results/clientpositive/llap/semijoin6.q.out +++ b/ql/src/test/results/clientpositive/llap/semijoin6.q.out @@ -115,10 +115,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -432,14 +432,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 residual filter predicates: {(_col1 <> _col3)} - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/semijoin7.q.out b/ql/src/test/results/clientpositive/llap/semijoin7.q.out index 5c4446f144..3ff5faab21 100644 --- a/ql/src/test/results/clientpositive/llap/semijoin7.q.out +++ b/ql/src/test/results/clientpositive/llap/semijoin7.q.out @@ -111,10 +111,10 @@ STAGE PLANS: 0 a (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -420,14 +420,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col6 residual filter predicates: {(_col1 <> _col6)} - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/skewjoin.q.out b/ql/src/test/results/clientpositive/llap/skewjoin.q.out index d2f9456f54..3baa24f942 100644 --- a/ql/src/test/results/clientpositive/llap/skewjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/skewjoin.q.out @@ -1091,12 +1091,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 15308 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 15308 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string) Reducer 3 Execution mode: llap @@ -1108,10 +1108,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0)), sum(hash(_col3)) - minReductionHashAggr: 0.9818182 + minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out index 49bda58d1e..1aebec391f 100644 --- a/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out +++ b/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out @@ -503,10 +503,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -629,10 +629,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -777,10 +777,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -915,10 +915,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1161,10 +1161,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1269,10 +1269,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1389,12 +1389,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap Map 5 Map Operator Tree: @@ -1425,10 +1425,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.8333333 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1558,10 +1558,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.75 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/subquery_in.q.out b/ql/src/test/results/clientpositive/llap/subquery_in.q.out index 98bb91f629..c888a877fd 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_in.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_in.q.out @@ -81,10 +81,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -209,10 +209,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -723,10 +723,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1151,15 +1151,15 @@ STAGE PLANS: Statistics: Num rows: 14 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) - minReductionHashAggr: 0.5 + minReductionHashAggr: 0.71428573 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -1189,14 +1189,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 14 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 14 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 14 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3637,7 +3637,7 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) - minReductionHashAggr: 0.0 + minReductionHashAggr: 0.375 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out b/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out index 9e75c759e7..3d96385c5d 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out @@ -653,19 +653,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string), _col2 (type: string) minReductionHashAggr: 0.0 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -675,15 +675,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: bigint) sort order: + Map-reduce partition columns: _col2 (type: bigint) - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reducer 5 Execution mode: llap @@ -864,19 +864,19 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 0 Reducer 2 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string), _col2 (type: string) minReductionHashAggr: 0.0 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -932,10 +932,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Semi Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out index cddbe791b3..f9cb4958c6 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out @@ -5673,19 +5673,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string), _col2 (type: string) minReductionHashAggr: 0.0 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -5695,13 +5695,13 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) Reducer 5 Execution mode: llap @@ -5714,14 +5714,14 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {(_col2 > _col3)} - Statistics: Num rows: 13 Data size: 2522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 4074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 2418 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 3906 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 2418 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 3906 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out index f959d71c2a..d83b7c93ff 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out @@ -359,7 +359,7 @@ STAGE PLANS: Group By Operator aggregations: count() keys: _col0 (type: smallint) - minReductionHashAggr: 0.49950933 + minReductionHashAggr: 0.49951172 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out index 87c47cd58e..483609f718 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out @@ -102,12 +102,12 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 500 Data size: 40234 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 500 Data size: 40234 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -119,11 +119,11 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 4 Execution mode: vectorized, llap @@ -131,10 +131,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -307,12 +307,12 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 500 Data size: 40234 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 500 Data size: 40234 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -324,11 +324,11 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 4 Execution mode: vectorized, llap @@ -336,10 +336,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -512,12 +512,12 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 500 Data size: 40234 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 500 Data size: 40234 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -529,11 +529,11 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 4 Execution mode: vectorized, llap @@ -541,10 +541,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out index 17f646723b..a7bd2b68ed 100644 --- a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out @@ -359,7 +359,7 @@ STAGE PLANS: Group By Operator aggregations: count() keys: _col0 (type: smallint) - minReductionHashAggr: 0.49950933 + minReductionHashAggr: 0.49951172 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out index 87c47cd58e..483609f718 100644 --- a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out @@ -102,12 +102,12 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 500 Data size: 40234 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 500 Data size: 40234 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -119,11 +119,11 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 4 Execution mode: vectorized, llap @@ -131,10 +131,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -307,12 +307,12 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 500 Data size: 40234 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 500 Data size: 40234 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -324,11 +324,11 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 4 Execution mode: vectorized, llap @@ -336,10 +336,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -512,12 +512,12 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 500 Data size: 40234 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 500 Data size: 40234 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -529,11 +529,11 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 4 Execution mode: vectorized, llap @@ -541,10 +541,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 791 Data size: 130440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out b/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out index b667632714..190647ea65 100644 --- a/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out @@ -55,7 +55,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - Statistics: Num rows: 18466 Data size: 61408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21560 Data size: 73784 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -64,7 +64,7 @@ STAGE PLANS: 1 _col0 (type: tinyint) input vertices: 1 Map 4 - Statistics: Num rows: 1302989 Data size: 10423912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1528346 Data size: 12226768 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() minReductionHashAggr: 0.99 diff --git a/ql/src/test/results/clientpositive/llap/vector_nullsafe_join.q.out b/ql/src/test/results/clientpositive/llap/vector_nullsafe_join.q.out index 4b8c4b8c98..7103755f81 100644 --- a/ql/src/test/results/clientpositive/llap/vector_nullsafe_join.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_nullsafe_join.q.out @@ -214,7 +214,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6 input vertices: 1 Map 2 - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -231,7 +231,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 @@ -239,13 +239,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1312,7 +1312,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6 input vertices: 1 Map 2 - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1327,7 +1327,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 input vertices: 1 Map 3 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 @@ -1335,13 +1335,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 0, 4] - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vector_outer_join0.q.out b/ql/src/test/results/clientpositive/llap/vector_outer_join0.q.out index 8395b7d36f..6899a90b42 100644 --- a/ql/src/test/results/clientpositive/llap/vector_outer_join0.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_outer_join0.q.out @@ -126,13 +126,13 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 1 Map 2 - Statistics: Num rows: 9 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1484 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1484 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -347,13 +347,13 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 9 Data size: 1484 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 1763 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9 Data size: 1484 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 1763 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vector_outer_join1.q.out b/ql/src/test/results/clientpositive/llap/vector_outer_join1.q.out index 9c35295d90..97814adcdf 100644 --- a/ql/src/test/results/clientpositive/llap/vector_outer_join1.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_outer_join1.q.out @@ -284,13 +284,13 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 input vertices: 1 Map 2 - Statistics: Num rows: 18 Data size: 9762 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 33 Data size: 14459 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 18 Data size: 9762 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 33 Data size: 14459 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -749,7 +749,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - Statistics: Num rows: 18 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 22 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -768,7 +768,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - Statistics: Num rows: 180 Data size: 704 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 220 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(_col0) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vector_outer_join2.q.out b/ql/src/test/results/clientpositive/llap/vector_outer_join2.q.out index cf9af78659..996816f5b5 100644 --- a/ql/src/test/results/clientpositive/llap/vector_outer_join2.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_outer_join2.q.out @@ -299,7 +299,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 3 - Statistics: Num rows: 25 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 45 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -318,7 +318,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 25 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 90 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(_col1) Group By Vectorization: @@ -328,7 +328,7 @@ STAGE PLANS: native: false vectorProcessingMode: HASH projectedOutputColumnNums: [0, 1] - minReductionHashAggr: 0.96 + minReductionHashAggr: 0.98888886 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/vector_windowing_gby.q.out b/ql/src/test/results/clientpositive/llap/vector_windowing_gby.q.out index 6d0eb35bc0..5fad93167c 100644 --- a/ql/src/test/results/clientpositive/llap/vector_windowing_gby.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_windowing_gby.q.out @@ -151,11 +151,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col1 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 27 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 36 Data size: 284 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3), sum(_col1) keys: _col2 (type: boolean) - minReductionHashAggr: 0.9259259 + minReductionHashAggr: 0.9444444 mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/vector_windowing_gby2.q.out b/ql/src/test/results/clientpositive/llap/vector_windowing_gby2.q.out index 593012772a..769e8ab665 100644 --- a/ql/src/test/results/clientpositive/llap/vector_windowing_gby2.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_windowing_gby2.q.out @@ -1005,11 +1005,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col1 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 27 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 36 Data size: 284 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3), sum(_col1) keys: _col2 (type: boolean) - minReductionHashAggr: 0.9259259 + minReductionHashAggr: 0.9444444 mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out index 263b3d8aa3..2eadb1f899 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out @@ -2537,10 +2537,10 @@ STAGE PLANS: vectorProcessingMode: HASH projectedOutputColumnNums: [0, 1, 2, 3, 4] keys: _col0 (type: double) - minReductionHashAggr: 0.49980026 + minReductionHashAggr: 0.5497403 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1251 Data size: 57520 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 51824 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -2549,7 +2549,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1251 Data size: 57520 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 51824 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2584,7 +2584,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1251 Data size: 57520 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 51824 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END) (type: double), (2563.58D * ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) (type: double), (- ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) (type: double), _col4 (type: bigint), ((2563.58D * ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) + -5638.15D) (type: double), ((- ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) * ((2563.58D * ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) + -5638.15D)) (type: double), _col5 (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / _col3) (type: double), (_col0 - (- ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END))) (type: double), power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5) (type: double), (_col0 + ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) (type: double), (_col0 * 762.0D) (type: double), _col2 (type: double), (-863.257D % (_col0 * 762.0D)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -2593,7 +2593,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 12, 20, 28, 4, 37, 55, 5, 59, 68, 73, 81, 82, 2, 84] selectExpressions: DoubleColDivideLongColumn(col 8:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 7:double)(children: DoubleColDivideLongColumn(col 6:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 6:double) -> 7:double) -> 8:double, IfExprNullCondExpr(col 9:boolean, null, col 10:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 9:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 10:bigint) -> 11:bigint) -> 12:double, DoubleScalarMultiplyDoubleColumn(val 2563.58, col 19:double)(children: DoubleColDivideLongColumn(col 15:double, col 18:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 14:double)(children: DoubleColDivideLongColumn(col 13:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 13:double) -> 14:double) -> 15:double, IfExprNullCondExpr(col 16:boolean, null, col 17:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 16:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 17:bigint) -> 18:bigint) -> 19:double) -> 20:double, DoubleColUnaryMinus(col 27:double)(children: DoubleColDivideLongColumn(col 23:double, col 26:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 22:double)(children: DoubleColDivideLongColumn(col 21:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 21:double) -> 22:double) -> 23:double, IfExprNullCondExpr(col 24:boolean, null, col 25:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 24:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 25:bigint) -> 26:bigint) -> 27:double) -> 28:double, DoubleColAddDoubleScalar(col 36:double, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 35:double)(children: DoubleColDivideLongColumn(col 31:double, col 34:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 30:double)(children: DoubleColDivideLongColumn(col 29:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 29:double) -> 30:double) -> 31:double, IfExprNullCondExpr(col 32:boolean, null, col 33:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 32:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 33:bigint) -> 34:bigint) -> 35:double) -> 36:double) -> 37:double, DoubleColMultiplyDoubleColumn(col 45:double, col 54:double)(children: DoubleColUnaryMinus(col 44:double)(children: DoubleColDivideLongColumn(col 40:double, col 43:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 39:double)(children: DoubleColDivideLongColumn(col 38:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 38:double) -> 39:double) -> 40:double, IfExprNullCondExpr(col 41:boolean, null, col 42:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 41:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 42:bigint) -> 43:bigint) -> 44:double) -> 45:double, DoubleColAddDoubleScalar(col 53:double, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 52:double)(children: DoubleColDivideLongColumn(col 48:double, col 51:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 47:double)(children: DoubleColDivideLongColumn(col 46:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 46:double) -> 47:double) -> 48:double, IfExprNullCondExpr(col 49:boolean, null, col 50:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 49:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 50:bigint) -> 51:bigint) -> 52:double) -> 53:double) -> 54:double) -> 55:double, DoubleColDivideLongColumn(col 58:double, col 3:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 57:double)(children: DoubleColDivideLongColumn(col 56:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 56:double) -> 57:double) -> 58:double) -> 59:double, DoubleColSubtractDoubleColumn(col 0:double, col 67:double)(children: DoubleColUnaryMinus(col 66:double)(children: DoubleColDivideLongColumn(col 62:double, col 65:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 61:double)(children: DoubleColDivideLongColumn(col 60:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 60:double) -> 61:double) -> 62:double, IfExprNullCondExpr(col 63:boolean, null, col 64:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 63:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 64:bigint) -> 65:bigint) -> 66:double) -> 67:double) -> 68:double, FuncPowerDoubleToDouble(col 72:double)(children: DoubleColDivideLongColumn(col 71:double, col 3:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 70:double)(children: DoubleColDivideLongColumn(col 69:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 69:double) -> 70:double) -> 71:double) -> 72:double) -> 73:double, DoubleColAddDoubleColumn(col 0:double, col 80:double)(children: DoubleColDivideLongColumn(col 76:double, col 79:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 75:double)(children: DoubleColDivideLongColumn(col 74:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 74:double) -> 75:double) -> 76:double, IfExprNullCondExpr(col 77:boolean, null, col 78:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 77:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 78:bigint) -> 79:bigint) -> 80:double) -> 81:double, DoubleColMultiplyDoubleScalar(col 0:double, val 762.0) -> 82:double, DoubleScalarModuloDoubleColumn(val -863.257, col 83:double)(children: DoubleColMultiplyDoubleScalar(col 0:double, val 762.0) -> 83:double) -> 84:double - Statistics: Num rows: 1251 Data size: 157600 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -2601,7 +2601,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1251 Data size: 157600 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double) Reducer 3 Execution mode: vectorized, llap @@ -2619,13 +2619,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 13] - Statistics: Num rows: 1251 Data size: 157600 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1251 Data size: 157600 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3275,7 +3275,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18 - Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + @@ -3284,7 +3284,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: float), _col2 (type: bigint), _col3 (type: double), _col4 (type: double), _col5 (type: bigint), _col6 (type: double), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: double), _col10 (type: double), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: double), _col14 (type: double), _col15 (type: bigint), _col16 (type: double), _col17 (type: double), _col18 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -3319,7 +3319,7 @@ STAGE PLANS: keys: KEY._col0 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18 - Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: float), (- _col1) (type: float), (-26.28D / UDFToDouble(_col1)) (type: double), _col2 (type: bigint), (CAST( _col2 AS decimal(19,0)) - 10.175) (type: decimal(23,3)), ((_col3 - ((_col4 * _col4) / _col5)) / CASE WHEN ((_col5 = 1L)) THEN (null) ELSE ((_col5 - 1)) END) (type: double), (((_col3 - ((_col4 * _col4) / _col5)) / CASE WHEN ((_col5 = 1L)) THEN (null) ELSE ((_col5 - 1)) END) % UDFToDouble(_col1)) (type: double), (10.175 + (- _col1)) (type: float), (_col6 / _col7) (type: double), (UDFToDouble((CAST( _col2 AS decimal(19,0)) - 10.175)) + ((_col3 - ((_col4 * _col4) / _col5)) / CASE WHEN ((_col5 = 1L)) THEN (null) ELSE ((_col5 - 1)) END)) (type: double), _col8 (type: bigint), ((_col9 - ((_col10 * _col10) / _col11)) / _col11) (type: double), (- (10.175 + (- _col1))) (type: float), (79.553D / ((_col9 - ((_col10 * _col10) / _col11)) / _col11)) (type: double), (((_col3 - ((_col4 * _col4) / _col5)) / CASE WHEN ((_col5 = 1L)) THEN (null) ELSE ((_col5 - 1)) END) % (79.553D / ((_col9 - ((_col10 * _col10) / _col11)) / _col11))) (type: double), _col12 (type: bigint), power(((_col13 - ((_col14 * _col14) / _col15)) / CASE WHEN ((_col15 = 1L)) THEN (null) ELSE ((_col15 - 1)) END), 0.5) (type: double), (-1.389 * CAST( _col8 AS decimal(19,0))) (type: decimal(24,3)), (CAST( _col12 AS decimal(19,0)) - (-1.389 * CAST( _col8 AS decimal(19,0)))) (type: decimal(25,3)), power(((_col16 - ((_col17 * _col17) / _col18)) / _col18), 0.5) (type: double), (- (CAST( _col12 AS decimal(19,0)) - (-1.389 * CAST( _col8 AS decimal(19,0))))) (type: decimal(25,3)), (UDFToDouble(_col12) / _col5) (type: double), (- (UDFToDouble(_col12) / _col5)) (type: double), ((UDFToDouble(_col12) / _col5) * UDFToDouble(_col12)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25 @@ -3328,7 +3328,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 19, 20, 2, 22, 29, 37, 39, 40, 51, 8, 55, 58, 63, 76, 12, 84, 86, 90, 95, 100, 102, 105, 109] selectExpressions: DoubleColUnaryMinus(col 1:float) -> 19:float, DoubleScalarDivideDoubleColumn(val -26.28, col 1:double)(children: col 1:float) -> 20:double, DecimalColSubtractDecimalScalar(col 21:decimal(19,0), val 10.175)(children: CastLongToDecimal(col 2:bigint) -> 21:decimal(19,0)) -> 22:decimal(23,3), DoubleColDivideLongColumn(col 25:double, col 28:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 24:double)(children: DoubleColDivideLongColumn(col 23:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 23:double) -> 24:double) -> 25:double, IfExprNullCondExpr(col 26:boolean, null, col 27:bigint)(children: LongColEqualLongScalar(col 5:bigint, val 1) -> 26:boolean, LongColSubtractLongScalar(col 5:bigint, val 1) -> 27:bigint) -> 28:bigint) -> 29:double, DoubleColModuloDoubleColumn(col 36:double, col 1:double)(children: DoubleColDivideLongColumn(col 32:double, col 35:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 31:double)(children: DoubleColDivideLongColumn(col 30:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 30:double) -> 31:double) -> 32:double, IfExprNullCondExpr(col 33:boolean, null, col 34:bigint)(children: LongColEqualLongScalar(col 5:bigint, val 1) -> 33:boolean, LongColSubtractLongScalar(col 5:bigint, val 1) -> 34:bigint) -> 35:bigint) -> 36:double, col 1:float) -> 37:double, DoubleScalarAddDoubleColumn(val 10.175000190734863, col 38:float)(children: DoubleColUnaryMinus(col 1:float) -> 38:float) -> 39:float, DoubleColDivideLongColumn(col 6:double, col 7:bigint) -> 40:double, DoubleColAddDoubleColumn(col 43:double, col 50:double)(children: CastDecimalToDouble(col 42:decimal(23,3))(children: DecimalColSubtractDecimalScalar(col 41:decimal(19,0), val 10.175)(children: CastLongToDecimal(col 2:bigint) -> 41:decimal(19,0)) -> 42:decimal(23,3)) -> 43:double, DoubleColDivideLongColumn(col 46:double, col 49:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 45:double)(children: DoubleColDivideLongColumn(col 44:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 44:double) -> 45:double) -> 46:double, IfExprNullCondExpr(col 47:boolean, null, col 48:bigint)(children: LongColEqualLongScalar(col 5:bigint, val 1) -> 47:boolean, LongColSubtractLongScalar(col 5:bigint, val 1) -> 48:bigint) -> 49:bigint) -> 50:double) -> 51:double, DoubleColDivideLongColumn(col 54:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 53:double)(children: DoubleColDivideLongColumn(col 52:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 52:double) -> 53:double) -> 54:double) -> 55:double, DoubleColUnaryMinus(col 57:float)(children: DoubleScalarAddDoubleColumn(val 10.175000190734863, col 56:float)(children: DoubleColUnaryMinus(col 1:float) -> 56:float) -> 57:float) -> 58:float, DoubleScalarDivideDoubleColumn(val 79.553, col 62:double)(children: DoubleColDivideLongColumn(col 61:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 60:double)(children: DoubleColDivideLongColumn(col 59:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 59:double) -> 60:double) -> 61:double) -> 62:double) -> 63:double, DoubleColModuloDoubleColumn(col 70:double, col 75:double)(children: DoubleColDivideLongColumn(col 66:double, col 69:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 65:double)(children: DoubleColDivideLongColumn(col 64:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 64:double) -> 65:double) -> 66:double, IfExprNullCondExpr(col 67:boolean, null, col 68:bigint)(children: LongColEqualLongScalar(col 5:bigint, val 1) -> 67:boolean, LongColSubtractLongScalar(col 5:bigint, val 1) -> 68:bigint) -> 69:bigint) -> 70:double, DoubleScalarDivideDoubleColumn(val 79.553, col 74:double)(children: DoubleColDivideLongColumn(col 73:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 72:double)(children: DoubleColDivideLongColumn(col 71:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 71:double) -> 72:double) -> 73:double) -> 74:double) -> 75:double) -> 76:double, FuncPowerDoubleToDouble(col 83:double)(children: DoubleColDivideLongColumn(col 79:double, col 82:bigint)(children: DoubleColSubtractDoubleColumn(col 13:double, col 78:double)(children: DoubleColDivideLongColumn(col 77:double, col 15:bigint)(children: DoubleColMultiplyDoubleColumn(col 14:double, col 14:double) -> 77:double) -> 78:double) -> 79:double, IfExprNullCondExpr(col 80:boolean, null, col 81:bigint)(children: LongColEqualLongScalar(col 15:bigint, val 1) -> 80:boolean, LongColSubtractLongScalar(col 15:bigint, val 1) -> 81:bigint) -> 82:bigint) -> 83:double) -> 84:double, DecimalScalarMultiplyDecimalColumn(val -1.389, col 85:decimal(19,0))(children: CastLongToDecimal(col 8:bigint) -> 85:decimal(19,0)) -> 86:decimal(24,3), DecimalColSubtractDecimalColumn(col 87:decimal(19,0), col 89:decimal(24,3))(children: CastLongToDecimal(col 12:bigint) -> 87:decimal(19,0), DecimalScalarMultiplyDecimalColumn(val -1.389, col 88:decimal(19,0))(children: CastLongToDecimal(col 8:bigint) -> 88:decimal(19,0)) -> 89:decimal(24,3)) -> 90:decimal(25,3), FuncPowerDoubleToDouble(col 94:double)(children: DoubleColDivideLongColumn(col 93:double, col 18:bigint)(children: DoubleColSubtractDoubleColumn(col 16:double, col 92:double)(children: DoubleColDivideLongColumn(col 91:double, col 18:bigint)(children: DoubleColMultiplyDoubleColumn(col 17:double, col 17:double) -> 91:double) -> 92:double) -> 93:double) -> 94:double) -> 95:double, FuncNegateDecimalToDecimal(col 99:decimal(25,3))(children: DecimalColSubtractDecimalColumn(col 96:decimal(19,0), col 98:decimal(24,3))(children: CastLongToDecimal(col 12:bigint) -> 96:decimal(19,0), DecimalScalarMultiplyDecimalColumn(val -1.389, col 97:decimal(19,0))(children: CastLongToDecimal(col 8:bigint) -> 97:decimal(19,0)) -> 98:decimal(24,3)) -> 99:decimal(25,3)) -> 100:decimal(25,3), DoubleColDivideLongColumn(col 101:double, col 5:bigint)(children: CastLongToDouble(col 12:bigint) -> 101:double) -> 102:double, DoubleColUnaryMinus(col 104:double)(children: DoubleColDivideLongColumn(col 103:double, col 5:bigint)(children: CastLongToDouble(col 12:bigint) -> 103:double) -> 104:double) -> 105:double, DoubleColMultiplyDoubleColumn(col 107:double, col 108:double)(children: DoubleColDivideLongColumn(col 106:double, col 5:bigint)(children: CastLongToDouble(col 12:bigint) -> 106:double) -> 107:double, CastLongToDouble(col 12:bigint) -> 108:double) -> 109:double - Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + @@ -3336,7 +3336,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: float), _col2 (type: float), _col3 (type: double), _col4 (type: bigint), _col5 (type: decimal(23,3)), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint), _col12 (type: double), _col13 (type: float), _col14 (type: double), _col15 (type: double), _col17 (type: bigint), _col18 (type: double), _col19 (type: decimal(24,3)), _col20 (type: decimal(25,3)), _col21 (type: double), _col22 (type: decimal(25,3)), _col23 (type: double), _col24 (type: double), _col25 (type: double) Reducer 3 Execution mode: vectorized, llap @@ -3354,13 +3354,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 13, 16, 17, 18, 19, 20, 21, 22, 23, 24] - Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorized_join46.q.out b/ql/src/test/results/clientpositive/llap/vectorized_join46.q.out index 83be1e974b..e72c5de3cb 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_join46.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_join46.q.out @@ -637,13 +637,13 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 input vertices: 0 Map 1 - Statistics: Num rows: 7 Data size: 1237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 7 Data size: 1237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1964,14 +1964,14 @@ STAGE PLANS: input vertices: 0 Map 1 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col6)} - Statistics: Num rows: 7 Data size: 1265 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 7 Data size: 1237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 1237 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out index 90cc453940..2f95f26bd3 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out @@ -64,7 +64,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 13785 Data size: 91688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 @@ -73,7 +73,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 2, 13] selectExpressions: LongColAddLongColumn(col 2:int, col 2:int) -> 13:int - Statistics: Num rows: 13785 Data size: 91688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), sum(_col2), count(_col2) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out index 6f8e9930c6..8d2ac81d4c 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out @@ -45,7 +45,7 @@ STAGE PLANS: outputColumnNames: _col1, _col3 input vertices: 1 Map 3 - Statistics: Num rows: 11087 Data size: 112232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 14848 Data size: 157364 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -55,7 +55,7 @@ STAGE PLANS: outputColumnNames: _col3 input vertices: 1 Map 4 - Statistics: Num rows: 782315 Data size: 6244648 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1389803 Data size: 11104552 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3) minReductionHashAggr: 0.99 diff --git a/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out index 1804cae06f..d217764e69 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out @@ -123,11 +123,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 13785 Data size: 91688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13785 Data size: 91688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), sum(_col2), count(_col2) minReductionHashAggr: 0.99 diff --git a/ql/src/test/results/clientpositive/llap/windowing_gby.q.out b/ql/src/test/results/clientpositive/llap/windowing_gby.q.out index 721066f4ec..f8a0d18927 100644 --- a/ql/src/test/results/clientpositive/llap/windowing_gby.q.out +++ b/ql/src/test/results/clientpositive/llap/windowing_gby.q.out @@ -47,7 +47,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=3 width=20) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)","sum(_col1)"],keys:_col2 - Merge Join Operator [MERGEJOIN_34] (rows=27 width=7) + Merge Join Operator [MERGEJOIN_34] (rows=36 width=7) Conds:RS_37._col0=RS_40._col1(Inner),Output:["_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_37] diff --git a/ql/src/test/results/clientpositive/masking_12.q.out b/ql/src/test/results/clientpositive/masking_12.q.out index a3b4eb25d6..6140a980ee 100644 --- a/ql/src/test/results/clientpositive/masking_12.q.out +++ b/ql/src/test/results/clientpositive/masking_12.q.out @@ -460,14 +460,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 4 Data size: 736 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 736 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 736 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query1.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query1.q.out index 346a55ce5e..453e6e3f97 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query1.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query1.q.out @@ -76,13 +76,13 @@ Stage-0 File Output Operator [FS_164] Limit [LIM_163] (rows=100 width=100) Number of rows:100 - Select Operator [SEL_162] (rows=816091 width=100) + Select Operator [SEL_162] (rows=663970 width=100) Output:["_col0"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_51] - Select Operator [SEL_50] (rows=816091 width=100) + Select Operator [SEL_50] (rows=663970 width=100) Output:["_col0"] - Merge Join Operator [MERGEJOIN_136] (rows=816091 width=100) + Merge Join Operator [MERGEJOIN_136] (rows=663970 width=100) Conds:RS_47._col1=RS_161._col0(Inner),Output:["_col7"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_161] @@ -94,22 +94,22 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_47] PartitionCols:_col1 - Filter Operator [FIL_46] (rows=816091 width=225) + Filter Operator [FIL_46] (rows=663970 width=225) predicate:(_col3 > _col4) - Merge Join Operator [MERGEJOIN_135] (rows=2448274 width=225) + Merge Join Operator [MERGEJOIN_135] (rows=1991910 width=225) Conds:RS_43._col2=RS_159._col1(Inner),Output:["_col1","_col3","_col4"] <-Reducer 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_159] PartitionCols:_col1 - Select Operator [SEL_158] (rows=31 width=115) + Select Operator [SEL_158] (rows=29 width=115) Output:["_col0","_col1"] - Filter Operator [FIL_157] (rows=31 width=123) + Filter Operator [FIL_157] (rows=29 width=123) predicate:(_col1 is not null and _col2 is not null) - Group By Operator [GBY_156] (rows=31 width=123) + Group By Operator [GBY_156] (rows=29 width=123) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1 - Select Operator [SEL_155] (rows=14291868 width=119) + Select Operator [SEL_155] (rows=13369812 width=119) Output:["_col1","_col2"] - Group By Operator [GBY_154] (rows=14291868 width=119) + Group By Operator [GBY_154] (rows=13369812 width=119) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_29] @@ -139,7 +139,7 @@ Stage-0 <-Reducer 2 [ONE_TO_ONE_EDGE] FORWARD [RS_43] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_133] (rows=2369298 width=114) + Merge Join Operator [MERGEJOIN_133] (rows=1923224 width=114) Conds:RS_139._col0=RS_153._col1(Inner),Output:["_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_139] @@ -153,11 +153,11 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_153] PartitionCols:_col1 - Select Operator [SEL_152] (rows=14291868 width=119) + Select Operator [SEL_152] (rows=11601100 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_151] (rows=14291868 width=119) + Filter Operator [FIL_151] (rows=11601100 width=119) predicate:_col2 is not null - Group By Operator [GBY_150] (rows=14291868 width=119) + Group By Operator [GBY_150] (rows=11601100 width=119) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_14] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query10.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query10.q.out index bd19a4f1d5..4602033a7b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query10.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query10.q.out @@ -173,28 +173,28 @@ Stage-0 PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Group By Operator [GBY_65] (rows=1 width=379) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["count()"],keys:_col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Top N Key Operator [TNK_102] (rows=58 width=379) + Top N Key Operator [TNK_102] (rows=52 width=379) keys:_col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13,sort order:++++++++,top n:100 - Select Operator [SEL_64] (rows=58 width=379) + Select Operator [SEL_64] (rows=52 width=379) Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - Filter Operator [FIL_63] (rows=58 width=379) + Filter Operator [FIL_63] (rows=52 width=379) predicate:(_col15 is not null or _col17 is not null) - Merge Join Operator [MERGEJOIN_180] (rows=58 width=379) + Merge Join Operator [MERGEJOIN_180] (rows=52 width=379) Conds:RS_60._col0=RS_217._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col15","_col17"] <-Reducer 5 [ONE_TO_ONE_EDGE] PARTITION_ONLY_SHUFFLE [RS_60] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_179] (rows=58 width=379) + Merge Join Operator [MERGEJOIN_179] (rows=53 width=379) Conds:RS_57._col0=RS_209._col0(Left Outer),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col15"] <-Reducer 4 [ONE_TO_ONE_EDGE] FORWARD [RS_57] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_178] (rows=22703 width=375) + Merge Join Operator [MERGEJOIN_178] (rows=20705 width=375) Conds:RS_54._col0=RS_55._col0(Left Semi),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col0 - Group By Operator [GBY_53] (rows=155827 width=2) + Group By Operator [GBY_53] (rows=142119 width=2) Output:["_col0"],keys:_col0 Select Operator [SEL_17] (rows=57825495 width=2) Output:["_col0"] @@ -267,14 +267,14 @@ Stage-0 <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_209] PartitionCols:_col0 - Select Operator [SEL_208] (rows=155827 width=7) + Select Operator [SEL_208] (rows=155749 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_207] (rows=155827 width=3) + Group By Operator [GBY_207] (rows=155749 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col0 - Group By Operator [GBY_28] (rows=155827 width=3) + Group By Operator [GBY_28] (rows=155749 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_176] (rows=15843227 width=3) Conds:RS_206._col0=RS_193._col0(Inner),Output:["_col1"] @@ -299,20 +299,20 @@ Stage-0 FORWARD [RS_150] Group By Operator [GBY_149] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_148] (rows=22703 width=4) + Select Operator [SEL_148] (rows=20705 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_178] <-Reducer 20 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_217] PartitionCols:_col0 - Select Operator [SEL_216] (rows=154725 width=7) + Select Operator [SEL_216] (rows=153181 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_215] (rows=154725 width=3) + Group By Operator [GBY_215] (rows=153181 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:_col0 - Group By Operator [GBY_42] (rows=154725 width=3) + Group By Operator [GBY_42] (rows=153181 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_177] (rows=31162251 width=3) Conds:RS_214._col0=RS_194._col0(Inner),Output:["_col1"] @@ -337,7 +337,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_165] Group By Operator [GBY_164] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_163] (rows=58 width=4) + Select Operator [SEL_163] (rows=53 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_179] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query14.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query14.q.out index d6861eeba3..51cfb310cf 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query14.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query14.q.out @@ -385,7 +385,7 @@ Stage-0 <-Reducer 34 [SIMPLE_EDGE] SHUFFLE [RS_230] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_1169] (rows=724 width=4) + Merge Join Operator [MERGEJOIN_1169] (rows=729 width=4) Conds:RS_1347._col1, _col2, _col3=RS_1370._col0, _col1, _col2(Inner),Output:["_col0"] <-Map 65 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1347] @@ -402,20 +402,20 @@ Stage-0 Output:["_col0","_col1","_col2"] Filter Operator [FIL_1368] (rows=1 width=20) predicate:(_col3 = 3L) - Group By Operator [GBY_1367] (rows=121728 width=19) + Group By Operator [GBY_1367] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 32 [SIMPLE_EDGE] <-Reducer 31 [CONTAINS] vectorized Reduce Output Operator [RS_1424] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1423] (rows=121728 width=19) + Group By Operator [GBY_1423] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1422] (rows=121728 width=19) + Group By Operator [GBY_1422] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_169] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_25] (rows=121728 width=19) + Group By Operator [GBY_25] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 Merge Join Operator [MERGEJOIN_1151] (rows=14628613 width=11) Conds:RS_21._col1=RS_1344._col0(Inner),Output:["_col4","_col5","_col6"] @@ -464,14 +464,14 @@ Stage-0 <-Reducer 44 [CONTAINS] vectorized Reduce Output Operator [RS_1438] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1437] (rows=121728 width=19) + Group By Operator [GBY_1437] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1436] (rows=121728 width=19) + Group By Operator [GBY_1436] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 42 [SIMPLE_EDGE] SHUFFLE [RS_189] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_45] (rows=121728 width=19) + Group By Operator [GBY_45] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 Merge Join Operator [MERGEJOIN_1153] (rows=7620440 width=11) Conds:RS_41._col1=RS_1345._col0(Inner),Output:["_col4","_col5","_col6"] @@ -515,14 +515,14 @@ Stage-0 <-Reducer 50 [CONTAINS] vectorized Reduce Output Operator [RS_1452] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1451] (rows=121728 width=19) + Group By Operator [GBY_1451] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1450] (rows=121728 width=19) + Group By Operator [GBY_1450] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 48 [SIMPLE_EDGE] SHUFFLE [RS_210] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_66] (rows=121728 width=19) + Group By Operator [GBY_66] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 Merge Join Operator [MERGEJOIN_1155] (rows=3828623 width=11) Conds:RS_62._col1=RS_1346._col0(Inner),Output:["_col4","_col5","_col6"] @@ -755,7 +755,7 @@ Stage-0 <-Reducer 38 [SIMPLE_EDGE] SHUFFLE [RS_374] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_1182] (rows=724 width=4) + Merge Join Operator [MERGEJOIN_1182] (rows=729 width=4) Conds:RS_1348._col1, _col2, _col3=RS_1386._col0, _col1, _col2(Inner),Output:["_col0"] <-Map 65 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1348] @@ -772,15 +772,15 @@ Stage-0 Output:["_col0","_col1","_col2"] Filter Operator [FIL_1384] (rows=1 width=20) predicate:(_col3 = 3L) - Group By Operator [GBY_1383] (rows=121728 width=19) + Group By Operator [GBY_1383] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 36 [SIMPLE_EDGE] <-Reducer 35 [CONTAINS] vectorized Reduce Output Operator [RS_1427] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1426] (rows=121728 width=19) + Group By Operator [GBY_1426] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1425] (rows=121728 width=19) + Group By Operator [GBY_1425] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_313] @@ -789,9 +789,9 @@ Stage-0 <-Reducer 45 [CONTAINS] vectorized Reduce Output Operator [RS_1441] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1440] (rows=121728 width=19) + Group By Operator [GBY_1440] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1439] (rows=121728 width=19) + Group By Operator [GBY_1439] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 42 [SIMPLE_EDGE] SHUFFLE [RS_333] @@ -800,9 +800,9 @@ Stage-0 <-Reducer 51 [CONTAINS] vectorized Reduce Output Operator [RS_1455] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1454] (rows=121728 width=19) + Group By Operator [GBY_1454] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1453] (rows=121728 width=19) + Group By Operator [GBY_1453] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 48 [SIMPLE_EDGE] SHUFFLE [RS_354] @@ -942,7 +942,7 @@ Stage-0 <-Reducer 30 [SIMPLE_EDGE] SHUFFLE [RS_87] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_1156] (rows=724 width=4) + Merge Join Operator [MERGEJOIN_1156] (rows=729 width=4) Conds:RS_1343._col1, _col2, _col3=RS_1324._col0, _col1, _col2(Inner),Output:["_col0"] <-Map 65 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1343] @@ -959,15 +959,15 @@ Stage-0 Output:["_col0","_col1","_col2"] Filter Operator [FIL_1322] (rows=1 width=20) predicate:(_col3 = 3L) - Group By Operator [GBY_1321] (rows=121728 width=19) + Group By Operator [GBY_1321] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 28 [SIMPLE_EDGE] <-Reducer 27 [CONTAINS] vectorized Reduce Output Operator [RS_1421] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1420] (rows=121728 width=19) + Group By Operator [GBY_1420] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1419] (rows=121728 width=19) + Group By Operator [GBY_1419] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_26] @@ -976,9 +976,9 @@ Stage-0 <-Reducer 43 [CONTAINS] vectorized Reduce Output Operator [RS_1435] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1434] (rows=121728 width=19) + Group By Operator [GBY_1434] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1433] (rows=121728 width=19) + Group By Operator [GBY_1433] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 42 [SIMPLE_EDGE] SHUFFLE [RS_46] @@ -987,9 +987,9 @@ Stage-0 <-Reducer 49 [CONTAINS] vectorized Reduce Output Operator [RS_1449] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1448] (rows=121728 width=19) + Group By Operator [GBY_1448] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1447] (rows=121728 width=19) + Group By Operator [GBY_1447] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 48 [SIMPLE_EDGE] SHUFFLE [RS_67] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query17.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query17.q.out index 0b459e0958..07b6748d8d 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query17.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query17.q.out @@ -125,24 +125,24 @@ Stage-0 File Output Operator [FS_248] Limit [LIM_247] (rows=100 width=466) Number of rows:100 - Select Operator [SEL_246] (rows=8581091679 width=466) + Select Operator [SEL_246] (rows=8667503740 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_245] - Select Operator [SEL_244] (rows=8581091679 width=466) + Select Operator [SEL_244] (rows=8667503740 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - Group By Operator [GBY_243] (rows=8581091679 width=466) + Group By Operator [GBY_243] (rows=8667503740 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","count(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)","sum(VALUE._col7)","count(VALUE._col8)","sum(VALUE._col9)","sum(VALUE._col10)","sum(VALUE._col11)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_48] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_47] (rows=8581091679 width=466) + Group By Operator [GBY_47] (rows=8667503740 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"],aggregations:["count(_col3)","sum(_col3)","sum(_col7)","sum(_col6)","count(_col4)","sum(_col4)","sum(_col9)","sum(_col8)","count(_col5)","sum(_col5)","sum(_col11)","sum(_col10)"],keys:_col0, _col1, _col2 - Top N Key Operator [TNK_94] (rows=8581091679 width=381) + Top N Key Operator [TNK_94] (rows=8667503740 width=381) keys:_col0, _col1, _col2,sort order:+++,top n:100 - Select Operator [SEL_45] (rows=8581091679 width=381) + Select Operator [SEL_45] (rows=8667503740 width=381) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Merge Join Operator [MERGEJOIN_210] (rows=8581091679 width=381) + Merge Join Operator [MERGEJOIN_210] (rows=8667503740 width=381) Conds:RS_42._col6=RS_242._col0(Inner),Output:["_col3","_col10","_col16","_col19","_col21","_col22"] <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_242] @@ -154,7 +154,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col6 - Merge Join Operator [MERGEJOIN_209] (rows=8581091679 width=101) + Merge Join Operator [MERGEJOIN_209] (rows=8667503740 width=101) Conds:RS_39._col8=RS_240._col0(Inner),Output:["_col3","_col6","_col10","_col16","_col19"] <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_240] @@ -166,7 +166,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_39] PartitionCols:_col8 - Merge Join Operator [MERGEJOIN_208] (rows=8581091679 width=19) + Merge Join Operator [MERGEJOIN_208] (rows=8667503740 width=19) Conds:RS_36._col1, _col2=RS_37._col9, _col8(Inner),Output:["_col3","_col6","_col8","_col10","_col16"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_37] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query18.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query18.q.out index 786f2eabaf..133971d977 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query18.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query18.q.out @@ -100,20 +100,20 @@ Stage-0 File Output Operator [FS_174] Limit [LIM_173] (rows=100 width=1165) Number of rows:100 - Select Operator [SEL_172] (rows=11124280 width=1165) + Select Operator [SEL_172] (rows=11292800 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_171] - Select Operator [SEL_170] (rows=11124280 width=1165) + Select Operator [SEL_170] (rows=11292800 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Group By Operator [GBY_169] (rows=11124280 width=1229) + Group By Operator [GBY_169] (rows=11292800 width=1229) Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)","sum(VALUE._col8)","count(VALUE._col9)","sum(VALUE._col10)","count(VALUE._col11)","sum(VALUE._col12)","count(VALUE._col13)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_40] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_39] (rows=11124280 width=1229) + Group By Operator [GBY_39] (rows=11292800 width=1229) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(_col12)","count(_col12)","sum(_col13)","count(_col13)","sum(_col14)","count(_col14)","sum(_col15)","count(_col15)","sum(_col16)","count(_col16)","sum(_col3)","count(_col3)","sum(_col19)","count(_col19)"],keys:_col21, _col5, _col6, _col7, 0L - Merge Join Operator [MERGEJOIN_144] (rows=2224856 width=816) + Merge Join Operator [MERGEJOIN_144] (rows=2258560 width=821) Conds:RS_35._col1=RS_168._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col19","_col21"] <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_168] @@ -125,7 +125,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_143] (rows=2193833 width=813) + Merge Join Operator [MERGEJOIN_143] (rows=2227067 width=818) Conds:RS_32._col11=RS_166._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col19","_col21"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_166] @@ -137,12 +137,12 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col11 - Merge Join Operator [MERGEJOIN_142] (rows=2193833 width=717) + Merge Join Operator [MERGEJOIN_142] (rows=2227067 width=722) Conds:RS_29._col0=RS_30._col1(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col11","_col12","_col13","_col14","_col15","_col16","_col19"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_141] (rows=15983636 width=639) + Merge Join Operator [MERGEJOIN_141] (rows=16225774 width=640) Conds:RS_18._col2=RS_164._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col11"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_164] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query23.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query23.q.out index 34bfd53e7c..60293bc351 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query23.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query23.q.out @@ -211,18 +211,18 @@ Stage-0 <-Reducer 24 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_456] PartitionCols:_col0 - Group By Operator [GBY_455] (rows=235937 width=3) + Group By Operator [GBY_455] (rows=225322 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 23 [SIMPLE_EDGE] SHUFFLE [RS_120] PartitionCols:_col0 - Group By Operator [GBY_119] (rows=235937 width=3) + Group By Operator [GBY_119] (rows=225322 width=3) Output:["_col0"],keys:_col0 - Select Operator [SEL_118] (rows=471875 width=227) + Select Operator [SEL_118] (rows=450644 width=227) Output:["_col0"] - Filter Operator [FIL_117] (rows=471875 width=227) + Filter Operator [FIL_117] (rows=450644 width=227) predicate:(_col1 > _col2) - Merge Join Operator [MERGEJOIN_360] (rows=1415626 width=227) + Merge Join Operator [MERGEJOIN_360] (rows=1351934 width=227) Conds:(Inner),Output:["_col0","_col1","_col2"] <-Reducer 22 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_417] @@ -236,14 +236,14 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_412] Group By Operator [GBY_411] (rows=1 width=112) Output:["_col0"],aggregations:["max(_col1)"] - Select Operator [SEL_410] (rows=50562 width=112) + Select Operator [SEL_410] (rows=46114 width=112) Output:["_col1"] - Group By Operator [GBY_409] (rows=50562 width=112) + Group By Operator [GBY_409] (rows=46114 width=112) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 20 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0 - Group By Operator [GBY_25] (rows=455058 width=112) + Group By Operator [GBY_25] (rows=415026 width=112) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col1 Merge Join Operator [MERGEJOIN_351] (rows=18762463 width=112) Conds:RS_408._col0=RS_400._col0(Inner),Output:["_col1","_col2"] @@ -278,9 +278,9 @@ Stage-0 Please refer to the previous Select Operator [SEL_399] <-Reducer 37 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_454] - Filter Operator [FIL_453] (rows=1415626 width=115) + Filter Operator [FIL_453] (rows=1351934 width=115) predicate:_col1 is not null - Group By Operator [GBY_452] (rows=1415626 width=115) + Group By Operator [GBY_452] (rows=1351934 width=115) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Map 36 [SIMPLE_EDGE] vectorized SHUFFLE [RS_451] @@ -410,27 +410,27 @@ Stage-0 <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_419] PartitionCols:_col0 - Group By Operator [GBY_418] (rows=235937 width=3) + Group By Operator [GBY_418] (rows=225322 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0 - Group By Operator [GBY_41] (rows=235937 width=3) + Group By Operator [GBY_41] (rows=225322 width=3) Output:["_col0"],keys:_col0 - Select Operator [SEL_40] (rows=471875 width=227) + Select Operator [SEL_40] (rows=450644 width=227) Output:["_col0"] - Filter Operator [FIL_39] (rows=471875 width=227) + Filter Operator [FIL_39] (rows=450644 width=227) predicate:(_col1 > _col2) - Merge Join Operator [MERGEJOIN_358] (rows=1415626 width=227) + Merge Join Operator [MERGEJOIN_358] (rows=1351934 width=227) Conds:(Inner),Output:["_col0","_col1","_col2"] <-Reducer 22 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_416] Please refer to the previous Select Operator [SEL_415] <-Reducer 16 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_397] - Filter Operator [FIL_396] (rows=1415626 width=115) + Filter Operator [FIL_396] (rows=1351934 width=115) predicate:_col1 is not null - Group By Operator [GBY_395] (rows=1415626 width=115) + Group By Operator [GBY_395] (rows=1351934 width=115) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_394] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query25.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query25.q.out index efa3b9839d..ab95fb821b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query25.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query25.q.out @@ -131,20 +131,20 @@ Stage-0 File Output Operator [FS_246] Limit [LIM_245] (rows=100 width=808) Number of rows:100 - Select Operator [SEL_244] (rows=4248052730 width=808) + Select Operator [SEL_244] (rows=4290851668 width=808) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_243] - Group By Operator [GBY_242] (rows=4248052730 width=808) + Group By Operator [GBY_242] (rows=4290851668 width=808) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_47] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_46] (rows=4248052730 width=808) + Group By Operator [GBY_46] (rows=4290851668 width=808) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col10)","sum(_col16)","sum(_col3)"],keys:_col22, _col23, _col19, _col20 - Top N Key Operator [TNK_93] (rows=4248052730 width=807) + Top N Key Operator [TNK_93] (rows=4290851668 width=807) keys:_col22, _col23, _col19, _col20,sort order:++++,top n:100 - Merge Join Operator [MERGEJOIN_209] (rows=4248052730 width=807) + Merge Join Operator [MERGEJOIN_209] (rows=4290851668 width=807) Conds:RS_42._col6=RS_241._col0(Inner),Output:["_col3","_col10","_col16","_col19","_col20","_col22","_col23"] <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_241] @@ -156,7 +156,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col6 - Merge Join Operator [MERGEJOIN_208] (rows=4248052730 width=527) + Merge Join Operator [MERGEJOIN_208] (rows=4290851668 width=527) Conds:RS_39._col8=RS_239._col0(Inner),Output:["_col3","_col6","_col10","_col16","_col19","_col20"] <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_239] @@ -168,7 +168,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_39] PartitionCols:_col8 - Merge Join Operator [MERGEJOIN_207] (rows=4248052730 width=343) + Merge Join Operator [MERGEJOIN_207] (rows=4290851668 width=343) Conds:RS_36._col1, _col2=RS_37._col9, _col8(Inner),Output:["_col3","_col6","_col8","_col10","_col16"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_37] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query26.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query26.q.out index 2dd8b8a4b4..2b0ba1c818 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query26.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query26.q.out @@ -83,9 +83,9 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_27] (rows=462000 width=476) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col12 - Top N Key Operator [TNK_54] (rows=809521 width=100) + Top N Key Operator [TNK_54] (rows=821787 width=100) keys:_col12,sort order:+,top n:100 - Merge Join Operator [MERGEJOIN_98] (rows=809521 width=100) + Merge Join Operator [MERGEJOIN_98] (rows=821787 width=100) Conds:RS_23._col2=RS_117._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col12"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_117] @@ -97,7 +97,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_23] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_97] (rows=809521 width=4) + Merge Join Operator [MERGEJOIN_97] (rows=821787 width=4) Conds:RS_20._col3=RS_115._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_115] @@ -111,7 +111,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_20] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_96] (rows=809521 width=4) + Merge Join Operator [MERGEJOIN_96] (rows=821787 width=4) Conds:RS_17._col0=RS_112._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_112] @@ -125,7 +125,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_95] (rows=2283326 width=135) + Merge Join Operator [MERGEJOIN_95] (rows=2317924 width=139) Conds:RS_109._col1=RS_101._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_101] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query27.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query27.q.out index c84ad206f3..2a3711fceb 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query27.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query27.q.out @@ -74,24 +74,24 @@ Stage-0 File Output Operator [FS_124] Limit [LIM_123] (rows=100 width=538) Number of rows:100 - Select Operator [SEL_122] (rows=4281825 width=538) + Select Operator [SEL_122] (rows=4916010 width=538) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_121] - Select Operator [SEL_120] (rows=4281825 width=538) + Select Operator [SEL_120] (rows=4916010 width=538) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Group By Operator [GBY_119] (rows=4281825 width=570) + Group By Operator [GBY_119] (rows=4916010 width=570) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_28] (rows=4281825 width=570) + Group By Operator [GBY_28] (rows=4916010 width=570) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col2)","count(_col2)","sum(_col3)","count(_col3)","sum(_col4)","count(_col4)","sum(_col5)","count(_col5)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_55] (rows=1427275 width=186) + Top N Key Operator [TNK_55] (rows=1638670 width=186) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_26] (rows=1427275 width=186) + Select Operator [SEL_26] (rows=1638670 width=186) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_99] (rows=1427275 width=186) + Merge Join Operator [MERGEJOIN_99] (rows=1638670 width=186) Conds:RS_23._col1=RS_118._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col11","_col13"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_118] @@ -103,7 +103,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_23] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_98] (rows=1427275 width=90) + Merge Join Operator [MERGEJOIN_98] (rows=1638670 width=90) Conds:RS_20._col3=RS_116._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col11"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_116] @@ -117,7 +117,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_20] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_97] (rows=1441779 width=4) + Merge Join Operator [MERGEJOIN_97] (rows=1655322 width=4) Conds:RS_17._col0=RS_113._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_113] @@ -131,7 +131,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_96] (rows=4037920 width=4) + Merge Join Operator [MERGEJOIN_96] (rows=4635978 width=4) Conds:RS_110._col2=RS_102._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_102] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query29.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query29.q.out index 74f63908f3..3e1c9d6c81 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query29.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query29.q.out @@ -129,20 +129,20 @@ Stage-0 File Output Operator [FS_246] Limit [LIM_245] (rows=100 width=496) Number of rows:100 - Select Operator [SEL_244] (rows=4156223234 width=496) + Select Operator [SEL_244] (rows=4290826997 width=496) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_243] - Group By Operator [GBY_242] (rows=4156223234 width=496) + Group By Operator [GBY_242] (rows=4290826997 width=496) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_47] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_46] (rows=4156223234 width=496) + Group By Operator [GBY_46] (rows=4290826997 width=496) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col10)","sum(_col16)","sum(_col3)"],keys:_col22, _col23, _col19, _col20 - Top N Key Operator [TNK_93] (rows=4156223234 width=483) + Top N Key Operator [TNK_93] (rows=4290826997 width=483) keys:_col22, _col23, _col19, _col20,sort order:++++,top n:100 - Merge Join Operator [MERGEJOIN_209] (rows=4156223234 width=483) + Merge Join Operator [MERGEJOIN_209] (rows=4290826997 width=483) Conds:RS_42._col6=RS_241._col0(Inner),Output:["_col3","_col10","_col16","_col19","_col20","_col22","_col23"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_241] @@ -154,7 +154,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col6 - Merge Join Operator [MERGEJOIN_208] (rows=4156223234 width=203) + Merge Join Operator [MERGEJOIN_208] (rows=4290826997 width=203) Conds:RS_39._col8=RS_239._col0(Inner),Output:["_col3","_col6","_col10","_col16","_col19","_col20"] <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_239] @@ -166,7 +166,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_39] PartitionCols:_col8 - Merge Join Operator [MERGEJOIN_207] (rows=4156223234 width=19) + Merge Join Operator [MERGEJOIN_207] (rows=4290826997 width=19) Conds:RS_36._col1, _col2=RS_37._col9, _col8(Inner),Output:["_col3","_col6","_col8","_col10","_col16"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_37] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query30.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query30.q.out index 183105f988..f3b3229892 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query30.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query30.q.out @@ -90,13 +90,13 @@ Stage-0 File Output Operator [FS_215] Limit [LIM_214] (rows=100 width=942) Number of rows:100 - Select Operator [SEL_213] (rows=691171 width=942) + Select Operator [SEL_213] (rows=601923 width=942) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_66] - Select Operator [SEL_65] (rows=691171 width=942) + Select Operator [SEL_65] (rows=601923 width=942) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - Merge Join Operator [MERGEJOIN_180] (rows=691171 width=942) + Merge Join Operator [MERGEJOIN_180] (rows=601923 width=942) Conds:RS_62._col0=RS_63._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col17"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_62] @@ -124,11 +124,11 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col0 - Select Operator [SEL_58] (rows=704993 width=227) + Select Operator [SEL_58] (rows=613960 width=227) Output:["_col0","_col2"] - Filter Operator [FIL_57] (rows=704993 width=227) + Filter Operator [FIL_57] (rows=613960 width=227) predicate:(_col2 > _col3) - Merge Join Operator [MERGEJOIN_179] (rows=2114980 width=227) + Merge Join Operator [MERGEJOIN_179] (rows=1841880 width=227) Conds:RS_206._col1=RS_212._col1(Inner),Output:["_col0","_col2","_col3"] <-Reducer 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_212] @@ -184,11 +184,11 @@ Stage-0 <-Reducer 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_206] PartitionCols:_col1 - Filter Operator [FIL_205] (rows=2114980 width=201) + Filter Operator [FIL_205] (rows=1841880 width=201) predicate:_col2 is not null - Select Operator [SEL_204] (rows=2114980 width=201) + Select Operator [SEL_204] (rows=1841880 width=201) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_203] (rows=2114980 width=201) + Group By Operator [GBY_203] (rows=1841880 width=201) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_23] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query33.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query33.q.out index f23ae020ae..acd2c04f82 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query33.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query33.q.out @@ -192,33 +192,33 @@ Stage-0 Stage-1 Reducer 7 vectorized File Output Operator [FS_357] - Limit [LIM_356] (rows=59 width=115) + Limit [LIM_356] (rows=2 width=114) Number of rows:100 - Select Operator [SEL_355] (rows=59 width=115) + Select Operator [SEL_355] (rows=2 width=114) Output:["_col0","_col1"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_354] - Group By Operator [GBY_353] (rows=59 width=115) + Group By Operator [GBY_353] (rows=2 width=114) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Union 5 [SIMPLE_EDGE] <-Reducer 11 [CONTAINS] vectorized Reduce Output Operator [RS_373] PartitionCols:_col0 - Group By Operator [GBY_372] (rows=59 width=115) + Group By Operator [GBY_372] (rows=2 width=114) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_371] (rows=19 width=115) + Group By Operator [GBY_371] (rows=2 width=114) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_109] PartitionCols:_col0 - Group By Operator [GBY_108] (rows=19 width=115) + Group By Operator [GBY_108] (rows=2 width=114) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_304] (rows=11364 width=3) + Merge Join Operator [MERGEJOIN_304] (rows=1134 width=0) Conds:RS_104._col0=RS_105._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_104] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_293] (rows=461514 width=7) + Merge Join Operator [MERGEJOIN_293] (rows=46084 width=7) Conds:RS_319._col1=RS_325._col0(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_319] @@ -232,12 +232,12 @@ Stage-0 <-Reducer 13 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_325] PartitionCols:_col0 - Group By Operator [GBY_324] (rows=692 width=3) + Group By Operator [GBY_324] (rows=69 width=4) Output:["_col0"],keys:KEY._col0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_323] PartitionCols:_col0 - Group By Operator [GBY_322] (rows=692 width=3) + Group By Operator [GBY_322] (rows=70 width=4) Output:["_col0"],keys:i_manufact_id Select Operator [SEL_321] (rows=46085 width=93) Output:["i_manufact_id"] @@ -298,16 +298,16 @@ Stage-0 <-Reducer 4 [CONTAINS] vectorized Reduce Output Operator [RS_352] PartitionCols:_col0 - Group By Operator [GBY_351] (rows=59 width=115) + Group By Operator [GBY_351] (rows=2 width=114) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_350] (rows=64 width=115) + Group By Operator [GBY_350] (rows=2 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col0 - Group By Operator [GBY_33] (rows=64 width=115) + Group By Operator [GBY_33] (rows=2 width=116) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_302] (rows=41476 width=3) + Merge Join Operator [MERGEJOIN_302] (rows=4136 width=2) Conds:RS_29._col0=RS_30._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_29] @@ -356,16 +356,16 @@ Stage-0 <-Reducer 9 [CONTAINS] vectorized Reduce Output Operator [RS_365] PartitionCols:_col0 - Group By Operator [GBY_364] (rows=59 width=115) + Group By Operator [GBY_364] (rows=2 width=114) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_363] (rows=35 width=115) + Group By Operator [GBY_363] (rows=2 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_71] PartitionCols:_col0 - Group By Operator [GBY_70] (rows=35 width=115) + Group By Operator [GBY_70] (rows=2 width=116) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_303] (rows=22352 width=3) + Merge Join Operator [MERGEJOIN_303] (rows=2229 width=1) Conds:RS_66._col0=RS_67._col3(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_66] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query35.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query35.q.out index 9adeaa9479..85fdceb020 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query35.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query35.q.out @@ -169,28 +169,28 @@ Stage-0 PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 Group By Operator [GBY_65] (rows=1 width=336) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count()","sum(_col8)","count(_col8)","max(_col8)","sum(_col9)","count(_col9)","max(_col9)","sum(_col10)","count(_col10)","max(_col10)"],keys:_col4, _col6, _col7, _col8, _col9, _col10 - Top N Key Operator [TNK_103] (rows=67 width=276) + Top N Key Operator [TNK_103] (rows=61 width=276) keys:_col4, _col6, _col7, _col8, _col9, _col10,sort order:++++++,top n:100 - Select Operator [SEL_64] (rows=67 width=276) + Select Operator [SEL_64] (rows=61 width=276) Output:["_col4","_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_63] (rows=67 width=276) + Filter Operator [FIL_63] (rows=61 width=276) predicate:(_col12 is not null or _col14 is not null) - Merge Join Operator [MERGEJOIN_181] (rows=67 width=276) + Merge Join Operator [MERGEJOIN_181] (rows=61 width=276) Conds:RS_60._col0=RS_217._col0(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col12","_col14"] <-Reducer 5 [ONE_TO_ONE_EDGE] PARTITION_ONLY_SHUFFLE [RS_60] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_180] (rows=68 width=276) + Merge Join Operator [MERGEJOIN_180] (rows=62 width=276) Conds:RS_57._col0=RS_209._col0(Left Outer),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10","_col12"] <-Reducer 4 [ONE_TO_ONE_EDGE] FORWARD [RS_57] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_179] (rows=162346 width=272) + Merge Join Operator [MERGEJOIN_179] (rows=148065 width=272) Conds:RS_54._col0=RS_55._col0(Left Semi),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col0 - Group By Operator [GBY_53] (rows=168231 width=2) + Group By Operator [GBY_53] (rows=153432 width=2) Output:["_col0"],keys:_col0 Select Operator [SEL_23] (rows=62428523 width=2) Output:["_col0"] @@ -263,14 +263,14 @@ Stage-0 <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_209] PartitionCols:_col0 - Select Operator [SEL_208] (rows=168231 width=7) + Select Operator [SEL_208] (rows=168147 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_207] (rows=168231 width=3) + Group By Operator [GBY_207] (rows=168147 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col0 - Group By Operator [GBY_34] (rows=168231 width=3) + Group By Operator [GBY_34] (rows=168147 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_177] (rows=17104380 width=3) Conds:RS_206._col0=RS_193._col0(Inner),Output:["_col1"] @@ -295,20 +295,20 @@ Stage-0 FORWARD [RS_151] Group By Operator [GBY_150] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_149] (rows=162346 width=4) + Select Operator [SEL_149] (rows=148065 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_179] <-Reducer 20 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_217] PartitionCols:_col0 - Select Operator [SEL_216] (rows=167041 width=7) + Select Operator [SEL_216] (rows=165374 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_215] (rows=167041 width=3) + Group By Operator [GBY_215] (rows=165374 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0 - Group By Operator [GBY_48] (rows=167041 width=3) + Group By Operator [GBY_48] (rows=165374 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_178] (rows=33642830 width=3) Conds:RS_214._col0=RS_194._col0(Inner),Output:["_col1"] @@ -333,7 +333,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_166] Group By Operator [GBY_165] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_164] (rows=68 width=4) + Select Operator [SEL_164] (rows=62 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_180] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query47.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query47.q.out index fb98cbed17..8450bbd5fc 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query47.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query47.q.out @@ -132,29 +132,29 @@ Stage-0 File Output Operator [FS_321] Limit [LIM_320] (rows=100 width=658) Number of rows:100 - Select Operator [SEL_319] (rows=241454 width=658) + Select Operator [SEL_319] (rows=301730 width=658) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_110] - Select Operator [SEL_109] (rows=241454 width=658) + Select Operator [SEL_109] (rows=301730 width=658) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_278] (rows=241454 width=546) + Merge Join Operator [MERGEJOIN_278] (rows=301730 width=546) Conds:RS_106._col6, _col7, _col8, _col9, _col14=RS_306._col0, _col1, _col2, _col3, _col5(Inner),Output:["_col4","_col6","_col10","_col11","_col12","_col13","_col19"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_306] PartitionCols:_col0, _col1, _col2, _col3, _col5 - Select Operator [SEL_304] (rows=162257387 width=485) + Select Operator [SEL_304] (rows=1810380 width=485) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_302] (rows=162257387 width=489) + Filter Operator [FIL_302] (rows=1810380 width=489) predicate:rank_window_0 is not null - PTF Operator [PTF_300] (rows=162257387 width=489) + PTF Operator [PTF_300] (rows=1810380 width=489) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS LAST, _col1 ASC NULLS LAST","partition by:":"_col5, _col4, _col2, _col3"}] - Select Operator [SEL_299] (rows=162257387 width=489) + Select Operator [SEL_299] (rows=1810380 width=489) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_297] PartitionCols:_col5, _col4, _col2, _col3 - Group By Operator [GBY_296] (rows=162257387 width=489) + Group By Operator [GBY_296] (rows=1810380 width=489) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_93] @@ -223,41 +223,41 @@ Stage-0 <-Reducer 9 [ONE_TO_ONE_EDGE] FORWARD [RS_106] PartitionCols:_col6, _col7, _col8, _col9, _col14 - Merge Join Operator [MERGEJOIN_277] (rows=241454 width=717) + Merge Join Operator [MERGEJOIN_277] (rows=301730 width=717) Conds:RS_307._col0, _col1, _col2, _col3, _col5=RS_318._col0, _col1, _col2, _col3, _col8(Inner),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_307] PartitionCols:_col0, _col1, _col2, _col3, _col5 - Select Operator [SEL_305] (rows=162257387 width=485) + Select Operator [SEL_305] (rows=1810380 width=485) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_303] (rows=162257387 width=489) + Filter Operator [FIL_303] (rows=1810380 width=489) predicate:rank_window_0 is not null - PTF Operator [PTF_301] (rows=162257387 width=489) + PTF Operator [PTF_301] (rows=1810380 width=489) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS LAST, _col1 ASC NULLS LAST","partition by:":"_col5, _col4, _col2, _col3"}] Please refer to the previous Select Operator [SEL_299] <-Reducer 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_318] PartitionCols:_col0, _col1, _col2, _col3, _col8 - Select Operator [SEL_317] (rows=241454 width=605) + Select Operator [SEL_317] (rows=301730 width=605) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_316] (rows=241454 width=605) + Filter Operator [FIL_316] (rows=301730 width=605) predicate:CASE WHEN ((_col0 > 0)) THEN (((abs((_col7 - _col0)) / _col0) > 0.1)) ELSE (false) END - Select Operator [SEL_315] (rows=482909 width=601) + Select Operator [SEL_315] (rows=603460 width=601) Output:["rank_window_1","_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_314] (rows=482909 width=601) + Filter Operator [FIL_314] (rows=603460 width=601) predicate:((_col0 > 0) and rank_window_1 is not null and (_col1 = 2000)) - PTF Operator [PTF_313] (rows=162257387 width=601) + PTF Operator [PTF_313] (rows=1810380 width=601) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS LAST, _col2 ASC NULLS LAST","partition by:":"_col6, _col5, _col3, _col4"}] - Select Operator [SEL_312] (rows=162257387 width=601) + Select Operator [SEL_312] (rows=1810380 width=601) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_311] PartitionCols:_col5, _col4, _col2, _col3 - Select Operator [SEL_310] (rows=162257387 width=489) + Select Operator [SEL_310] (rows=1810380 width=489) Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_309] (rows=162257387 width=489) + PTF Operator [PTF_309] (rows=1810380 width=489) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col5 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col2 ASC NULLS FIRST, _col3 ASC NULLS FIRST, _col0 ASC NULLS FIRST","partition by:":"_col5, _col4, _col2, _col3, _col0"}] - Select Operator [SEL_308] (rows=162257387 width=489) + Select Operator [SEL_308] (rows=1810380 width=489) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_298] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query48.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query48.q.out index 9d3505f8e7..ceba5a43dc 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query48.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query48.q.out @@ -162,11 +162,11 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_24] Group By Operator [GBY_23] (rows=1 width=8) Output:["_col0"],aggregations:["sum(_col3)"] - Select Operator [SEL_22] (rows=170127 width=24) + Select Operator [SEL_22] (rows=613581 width=24) Output:["_col3"] - Filter Operator [FIL_21] (rows=170127 width=24) + Filter Operator [FIL_21] (rows=613581 width=24) predicate:((_col10 and _col4) or (_col11 and _col5) or (_col12 and _col6)) - Merge Join Operator [MERGEJOIN_73] (rows=226838 width=24) + Merge Join Operator [MERGEJOIN_73] (rows=818111 width=24) Conds:RS_18._col2=RS_90._col0(Inner),Output:["_col3","_col4","_col5","_col6","_col10","_col11","_col12"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_90] @@ -180,7 +180,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_72] (rows=2570826 width=12) + Merge Join Operator [MERGEJOIN_72] (rows=9271916 width=13) Conds:RS_15._col1=RS_87._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6"] <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_87] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query57.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query57.q.out index b62de39fda..a77f2d4c24 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query57.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query57.q.out @@ -126,29 +126,29 @@ Stage-0 File Output Operator [FS_321] Limit [LIM_320] (rows=100 width=758) Number of rows:100 - Select Operator [SEL_319] (rows=130121 width=758) + Select Operator [SEL_319] (rows=397735 width=758) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_110] - Select Operator [SEL_109] (rows=130121 width=758) + Select Operator [SEL_109] (rows=397735 width=758) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_278] (rows=130121 width=646) + Merge Join Operator [MERGEJOIN_278] (rows=397735 width=646) Conds:RS_106._col5, _col6, _col12, _col7=RS_306._col0, _col1, _col4, _col2(Inner),Output:["_col3","_col5","_col6","_col8","_col9","_col10","_col11","_col16"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_306] PartitionCols:_col0, _col1, _col4, _col2 - Select Operator [SEL_304] (rows=87441185 width=404) + Select Operator [SEL_304] (rows=2386410 width=404) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_302] (rows=87441185 width=408) + Filter Operator [FIL_302] (rows=2386410 width=408) predicate:rank_window_0 is not null - PTF Operator [PTF_300] (rows=87441185 width=408) + PTF Operator [PTF_300] (rows=2386410 width=408) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS LAST, _col1 ASC NULLS LAST","partition by:":"_col4, _col3, _col2"}] - Select Operator [SEL_299] (rows=87441185 width=408) + Select Operator [SEL_299] (rows=2386410 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_297] PartitionCols:_col4, _col3, _col2 - Group By Operator [GBY_296] (rows=87441185 width=408) + Group By Operator [GBY_296] (rows=2386410 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_93] @@ -217,41 +217,41 @@ Stage-0 <-Reducer 9 [ONE_TO_ONE_EDGE] FORWARD [RS_106] PartitionCols:_col5, _col6, _col12, _col7 - Merge Join Operator [MERGEJOIN_277] (rows=130121 width=636) + Merge Join Operator [MERGEJOIN_277] (rows=397735 width=636) Conds:RS_307._col0, _col1, _col4, _col2=RS_318._col0, _col1, _col7, _col2(Inner),Output:["_col3","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_307] PartitionCols:_col0, _col1, _col4, _col2 - Select Operator [SEL_305] (rows=87441185 width=404) + Select Operator [SEL_305] (rows=2386410 width=404) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_303] (rows=87441185 width=408) + Filter Operator [FIL_303] (rows=2386410 width=408) predicate:rank_window_0 is not null - PTF Operator [PTF_301] (rows=87441185 width=408) + PTF Operator [PTF_301] (rows=2386410 width=408) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS LAST, _col1 ASC NULLS LAST","partition by:":"_col4, _col3, _col2"}] Please refer to the previous Select Operator [SEL_299] <-Reducer 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_318] PartitionCols:_col0, _col1, _col7, _col2 - Select Operator [SEL_317] (rows=130121 width=524) + Select Operator [SEL_317] (rows=397735 width=524) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_316] (rows=130121 width=524) + Filter Operator [FIL_316] (rows=397735 width=524) predicate:CASE WHEN ((_col0 > 0)) THEN (((abs((_col6 - _col0)) / _col0) > 0.1)) ELSE (false) END - Select Operator [SEL_315] (rows=260242 width=520) + Select Operator [SEL_315] (rows=795470 width=520) Output:["rank_window_1","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_314] (rows=260242 width=520) + Filter Operator [FIL_314] (rows=795470 width=520) predicate:((_col0 > 0) and rank_window_1 is not null and (_col1 = 2000)) - PTF Operator [PTF_313] (rows=87441185 width=520) + PTF Operator [PTF_313] (rows=2386410 width=520) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS LAST, _col2 ASC NULLS LAST","partition by:":"_col5, _col4, _col3"}] - Select Operator [SEL_312] (rows=87441185 width=520) + Select Operator [SEL_312] (rows=2386410 width=520) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_311] PartitionCols:_col4, _col3, _col2 - Select Operator [SEL_310] (rows=87441185 width=408) + Select Operator [SEL_310] (rows=2386410 width=408) Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5"] - PTF Operator [PTF_309] (rows=87441185 width=408) + PTF Operator [PTF_309] (rows=2386410 width=408) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col4 ASC NULLS FIRST, _col3 ASC NULLS FIRST, _col2 ASC NULLS FIRST, _col0 ASC NULLS FIRST","partition by:":"_col4, _col3, _col2, _col0"}] - Select Operator [SEL_308] (rows=87441185 width=408) + Select Operator [SEL_308] (rows=2386410 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_298] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query59.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query59.q.out index 805fce4de7..82148531bc 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query59.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query59.q.out @@ -114,20 +114,20 @@ Stage-0 File Output Operator [FS_207] Limit [LIM_206] (rows=100 width=976) Number of rows:100 - Select Operator [SEL_205] (rows=1012347 width=976) + Select Operator [SEL_205] (rows=862591 width=976) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_57] - Select Operator [SEL_56] (rows=1012347 width=976) + Select Operator [SEL_56] (rows=862591 width=976) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Merge Join Operator [MERGEJOIN_181] (rows=1012347 width=1648) + Merge Join Operator [MERGEJOIN_181] (rows=862591 width=1648) Conds:RS_53._col11, _col0=RS_54._col1, (_col0 - 52)(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col11","_col12","_col15","_col16","_col17","_col18","_col19","_col20"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_54] PartitionCols:_col1, (_col0 - 52) - Select Operator [SEL_46] (rows=28847 width=776) + Select Operator [SEL_46] (rows=26628 width=776) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_180] (rows=28847 width=776) + Merge Join Operator [MERGEJOIN_180] (rows=26628 width=776) Conds:RS_43._col1=RS_204._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col10"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_204] @@ -139,7 +139,7 @@ Stage-0 <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_179] (rows=28847 width=676) + Merge Join Operator [MERGEJOIN_179] (rows=26628 width=676) Conds:RS_202._col0=RS_198._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_198] @@ -153,7 +153,7 @@ Stage-0 <-Reducer 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_202] PartitionCols:_col0 - Group By Operator [GBY_201] (rows=1196832 width=679) + Group By Operator [GBY_201] (rows=1104768 width=679) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)"],keys:KEY._col0, KEY._col1 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_32] @@ -185,7 +185,7 @@ Stage-0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_53] PartitionCols:_col11, _col0 - Merge Join Operator [MERGEJOIN_177] (rows=28847 width=976) + Merge Join Operator [MERGEJOIN_177] (rows=26628 width=976) Conds:RS_50._col1=RS_200._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col11","_col12"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_200] @@ -197,7 +197,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_50] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_176] (rows=28847 width=788) + Merge Join Operator [MERGEJOIN_176] (rows=26628 width=788) Conds:RS_192._col0=RS_197._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_197] @@ -210,7 +210,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] vectorized SHUFFLE [RS_192] PartitionCols:_col0 - Group By Operator [GBY_191] (rows=1196832 width=791) + Group By Operator [GBY_191] (rows=1104768 width=791) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query65.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query65.q.out index a3f63e6ca9..dca20cf95c 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query65.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query65.q.out @@ -85,13 +85,13 @@ Stage-0 File Output Operator [FS_164] Limit [LIM_163] (rows=100 width=705) Number of rows:100 - Select Operator [SEL_162] (rows=65392 width=704) + Select Operator [SEL_162] (rows=61787 width=703) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_51] - Select Operator [SEL_50] (rows=65392 width=704) + Select Operator [SEL_50] (rows=61787 width=703) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_137] (rows=65392 width=704) + Merge Join Operator [MERGEJOIN_137] (rows=61787 width=703) Conds:RS_47._col1=RS_161._col0(Inner),Output:["_col2","_col6","_col8","_col9","_col10","_col11"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_161] @@ -103,7 +103,7 @@ Stage-0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_47] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_136] (rows=65392 width=204) + Merge Join Operator [MERGEJOIN_136] (rows=61787 width=204) Conds:RS_44._col0=RS_159._col0(Inner),Output:["_col1","_col2","_col6"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_159] @@ -115,21 +115,21 @@ Stage-0 <-Reducer 4 [ONE_TO_ONE_EDGE] FORWARD [RS_44] PartitionCols:_col0 - Filter Operator [FIL_43] (rows=65392 width=231) + Filter Operator [FIL_43] (rows=61787 width=231) predicate:(_col2 <= _col4) - Merge Join Operator [MERGEJOIN_135] (rows=196176 width=231) + Merge Join Operator [MERGEJOIN_135] (rows=185361 width=231) Conds:RS_151._col0=RS_157._col0(Inner),Output:["_col0","_col1","_col2","_col4"] <-Reducer 3 [SIMPLE_EDGE] vectorized SHUFFLE [RS_151] PartitionCols:_col0 - Filter Operator [FIL_150] (rows=184637 width=118) + Filter Operator [FIL_150] (rows=173776 width=118) predicate:_col2 is not null - Group By Operator [GBY_149] (rows=184637 width=118) + Group By Operator [GBY_149] (rows=173776 width=118) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_11] PartitionCols:_col0, _col1 - Group By Operator [GBY_10] (rows=6093021 width=118) + Group By Operator [GBY_10] (rows=5734608 width=118) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1 Merge Join Operator [MERGEJOIN_133] (rows=91197860 width=89) Conds:RS_148._col0=RS_140._col0(Inner),Output:["_col1","_col2","_col3"] @@ -165,15 +165,15 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_157] PartitionCols:_col0 - Select Operator [SEL_156] (rows=17 width=115) + Select Operator [SEL_156] (rows=16 width=115) Output:["_col0","_col1"] - Filter Operator [FIL_155] (rows=17 width=123) + Filter Operator [FIL_155] (rows=16 width=123) predicate:(_col1 is not null and _col2 is not null) - Group By Operator [GBY_154] (rows=17 width=123) + Group By Operator [GBY_154] (rows=16 width=123) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1 - Select Operator [SEL_153] (rows=184637 width=118) + Select Operator [SEL_153] (rows=173776 width=118) Output:["_col1","_col2"] - Group By Operator [GBY_152] (rows=184637 width=118) + Group By Operator [GBY_152] (rows=173776 width=118) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_27] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query69.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query69.q.out index 68d2d41318..b7cbd87c3d 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query69.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query69.q.out @@ -164,17 +164,17 @@ Stage-0 Output:["_col0","_col6","_col7","_col8","_col9","_col10"] Filter Operator [FIL_46] (rows=1 width=367) predicate:_col12 is null - Merge Join Operator [MERGEJOIN_182] (rows=33 width=367) + Merge Join Operator [MERGEJOIN_182] (rows=30 width=367) Conds:RS_43._col0=RS_212._col0(Left Outer),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col12"] <-Reducer 4 [ONE_TO_ONE_EDGE] FORWARD [RS_43] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_181] (rows=6841 width=363) + Merge Join Operator [MERGEJOIN_181] (rows=6239 width=363) Conds:RS_40._col0=RS_41._col0(Left Semi),Output:["_col0","_col6","_col7","_col8","_col9","_col10"] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col0 - Group By Operator [GBY_39] (rows=116289 width=1) + Group By Operator [GBY_39] (rows=106060 width=1) Output:["_col0"],keys:_col0 Select Operator [SEL_17] (rows=43153353 width=1) Output:["_col0"] @@ -247,14 +247,14 @@ Stage-0 <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_212] PartitionCols:_col0 - Select Operator [SEL_211] (rows=116289 width=7) + Select Operator [SEL_211] (rows=116231 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_210] (rows=116289 width=3) + Group By Operator [GBY_210] (rows=116231 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col0 - Group By Operator [GBY_28] (rows=116289 width=3) + Group By Operator [GBY_28] (rows=116231 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_179] (rows=11823304 width=3) Conds:RS_209._col0=RS_196._col0(Inner),Output:["_col1"] @@ -279,20 +279,20 @@ Stage-0 FORWARD [RS_152] Group By Operator [GBY_151] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_150] (rows=6841 width=4) + Select Operator [SEL_150] (rows=6239 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_181] <-Reducer 20 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_220] PartitionCols:_col0 - Select Operator [SEL_219] (rows=115467 width=7) + Select Operator [SEL_219] (rows=114314 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_218] (rows=115467 width=3) + Group By Operator [GBY_218] (rows=114314 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_59] PartitionCols:_col0 - Group By Operator [GBY_58] (rows=115467 width=3) + Group By Operator [GBY_58] (rows=114314 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_180] (rows=23255411 width=3) Conds:RS_217._col0=RS_197._col0(Inner),Output:["_col1"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query7.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query7.q.out index 58ed4cc27e..ed01a9eecb 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query7.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query7.q.out @@ -83,9 +83,9 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_27] (rows=462000 width=476) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col12 - Top N Key Operator [TNK_54] (rows=1441769 width=100) + Top N Key Operator [TNK_54] (rows=1655321 width=100) keys:_col12,sort order:+,top n:100 - Merge Join Operator [MERGEJOIN_98] (rows=1441769 width=100) + Merge Join Operator [MERGEJOIN_98] (rows=1655321 width=100) Conds:RS_23._col1=RS_117._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col12"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_117] @@ -97,7 +97,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_23] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_97] (rows=1441769 width=4) + Merge Join Operator [MERGEJOIN_97] (rows=1655321 width=4) Conds:RS_20._col3=RS_115._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_115] @@ -111,7 +111,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_20] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_96] (rows=1441769 width=4) + Merge Join Operator [MERGEJOIN_96] (rows=1655321 width=4) Conds:RS_17._col0=RS_112._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_112] @@ -125,7 +125,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_95] (rows=4037893 width=4) + Merge Join Operator [MERGEJOIN_95] (rows=4635977 width=4) Conds:RS_109._col2=RS_101._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_101] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query72.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query72.q.out index 5d99aa4b6c..145d406853 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query72.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query72.q.out @@ -104,20 +104,20 @@ Stage-0 File Output Operator [FS_283] Limit [LIM_282] (rows=100 width=312) Number of rows:100 - Select Operator [SEL_281] (rows=182953402 width=312) + Select Operator [SEL_281] (rows=187595238 width=312) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_280] - Group By Operator [GBY_279] (rows=182953402 width=312) + Group By Operator [GBY_279] (rows=187595238 width=312) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_66] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_65] (rows=182953402 width=312) + Group By Operator [GBY_65] (rows=187595238 width=312) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(_col3)","count(_col4)","count()"],keys:_col0, _col1, _col2 - Select Operator [SEL_63] (rows=471834849 width=292) + Select Operator [SEL_63] (rows=483806094 width=292) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_247] (rows=471834849 width=292) + Merge Join Operator [MERGEJOIN_247] (rows=483806094 width=292) Conds:RS_60._col4, _col6=RS_278._col0, _col1(Left Outer),Output:["_col13","_col15","_col19","_col25"] <-Map 24 [SIMPLE_EDGE] vectorized SHUFFLE [RS_278] @@ -129,9 +129,9 @@ Stage-0 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_60] PartitionCols:_col4, _col6 - Select Operator [SEL_57] (rows=182953402 width=300) + Select Operator [SEL_57] (rows=187595238 width=300) Output:["_col4","_col6","_col13","_col15","_col19","_col25"] - Merge Join Operator [MERGEJOIN_246] (rows=182953402 width=300) + Merge Join Operator [MERGEJOIN_246] (rows=187595238 width=300) Conds:RS_54._col4=RS_276._col0(Inner),Output:["_col4","_col6","_col13","_col20","_col21","_col25"] <-Map 23 [SIMPLE_EDGE] vectorized SHUFFLE [RS_276] @@ -143,9 +143,9 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_54] PartitionCols:_col4 - Filter Operator [FIL_53] (rows=182953402 width=132) + Filter Operator [FIL_53] (rows=187595238 width=132) predicate:(_col23 > _col14) - Merge Join Operator [MERGEJOIN_245] (rows=548860207 width=132) + Merge Join Operator [MERGEJOIN_245] (rows=562785714 width=132) Conds:RS_50._col1=RS_274._col0(Inner),Output:["_col4","_col6","_col13","_col14","_col20","_col21","_col23"] <-Map 22 [SIMPLE_EDGE] vectorized SHUFFLE [RS_274] @@ -159,7 +159,7 @@ Stage-0 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_50] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_244] (rows=548860207 width=127) + Merge Join Operator [MERGEJOIN_244] (rows=562785714 width=127) Conds:RS_47._col5=RS_271._col0(Left Outer),Output:["_col1","_col4","_col6","_col13","_col14","_col20","_col21"] <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_271] @@ -171,7 +171,7 @@ Stage-0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_47] PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_243] (rows=548860207 width=127) + Merge Join Operator [MERGEJOIN_243] (rows=562785714 width=127) Conds:RS_44._col17=RS_269._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col13","_col14","_col20"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_269] @@ -183,9 +183,9 @@ Stage-0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col17 - Filter Operator [FIL_43] (rows=548860207 width=39) + Filter Operator [FIL_43] (rows=562785714 width=39) predicate:(_col18 < _col7) - Merge Join Operator [MERGEJOIN_242] (rows=1646580622 width=39) + Merge Join Operator [MERGEJOIN_242] (rows=1688357142 width=39) Conds:RS_40._col10, _col4=RS_267._col0, _col1(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col13","_col14","_col17","_col18"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_267] @@ -199,7 +199,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_40] PartitionCols:_col10, _col4 - Merge Join Operator [MERGEJOIN_241] (rows=2885264 width=30) + Merge Join Operator [MERGEJOIN_241] (rows=2958468 width=30) Conds:RS_37._col0=RS_38._col2(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col10","_col13","_col14"] <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_38] @@ -227,7 +227,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_239] (rows=8138146 width=21) + Merge Join Operator [MERGEJOIN_239] (rows=8344625 width=21) Conds:RS_34._col3=RS_264._col0(Inner),Output:["_col0","_col1","_col4","_col5","_col6","_col7"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_264] @@ -241,7 +241,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_238] (rows=40690727 width=27) + Merge Join Operator [MERGEJOIN_238] (rows=41723124 width=27) Conds:RS_258._col2=RS_261._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_258] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query75.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query75.q.out index 082dd7805f..5b9f90d4e8 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query75.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query75.q.out @@ -204,20 +204,20 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] Limit [LIM_609] (rows=100 width=152) Number of rows:100 - Select Operator [SEL_608] (rows=3422897230256 width=151) + Select Operator [SEL_608] (rows=7853634 width=152) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_169] - Select Operator [SEL_168] (rows=3422897230256 width=151) + Select Operator [SEL_168] (rows=7853634 width=152) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_167] (rows=3422897230256 width=255) + Filter Operator [FIL_167] (rows=7853634 width=256) predicate:((CAST( _col10 AS decimal(17,2)) / CAST( _col4 AS decimal(17,2))) < 0.9) - Merge Join Operator [MERGEJOIN_512] (rows=10268691690770 width=255) + Merge Join Operator [MERGEJOIN_512] (rows=23560904 width=256) Conds:RS_604._col0, _col1, _col2, _col3=RS_607._col0, _col1, _col2, _col3(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col10","_col11"] <-Reducer 27 [SIMPLE_EDGE] vectorized SHUFFLE [RS_607] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_606] (rows=84235776 width=135) + Group By Operator [GBY_606] (rows=40320 width=136) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 Group By Operator [GBY_605] (rows=736356923 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 @@ -413,7 +413,7 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_604] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_603] (rows=84235776 width=135) + Group By Operator [GBY_603] (rows=40320 width=136) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 Group By Operator [GBY_602] (rows=736356923 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query77.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query77.q.out index ac83e8e2b0..47ffd16222 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query77.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query77.q.out @@ -264,23 +264,23 @@ Stage-0 Stage-1 Reducer 7 vectorized File Output Operator [FS_271] - Limit [LIM_270] (rows=58 width=437) + Limit [LIM_270] (rows=66 width=437) Number of rows:100 - Select Operator [SEL_269] (rows=58 width=437) + Select Operator [SEL_269] (rows=66 width=437) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_268] - Select Operator [SEL_267] (rows=58 width=437) + Select Operator [SEL_267] (rows=66 width=437) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_266] (rows=58 width=445) + Group By Operator [GBY_266] (rows=66 width=445) Output:["_col0","_col1","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 5 [SIMPLE_EDGE] <-Reducer 14 [CONTAINS] Reduce Output Operator [RS_230] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_229] (rows=58 width=445) + Group By Operator [GBY_229] (rows=66 width=445) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_228] (rows=39 width=435) + Top N Key Operator [TNK_228] (rows=60 width=435) keys:_col0, _col1, 0L,sort order:+++,top n:100 Select Operator [SEL_226] (rows=2 width=439) Output:["_col0","_col1","_col2","_col3","_col4"] @@ -352,13 +352,13 @@ Stage-0 <-Reducer 20 [CONTAINS] Reduce Output Operator [RS_236] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_235] (rows=58 width=445) + Group By Operator [GBY_235] (rows=66 width=445) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_234] (rows=39 width=435) + Top N Key Operator [TNK_234] (rows=60 width=435) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_232] (rows=25 width=435) + Select Operator [SEL_232] (rows=46 width=435) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_231] (rows=25 width=452) + Merge Join Operator [MERGEJOIN_231] (rows=46 width=340) Conds:RS_290._col0=RS_295._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"] <-Reducer 19 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_290] @@ -401,12 +401,12 @@ Stage-0 <-Reducer 23 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_295] PartitionCols:_col0 - Group By Operator [GBY_294] (rows=24 width=226) + Group By Operator [GBY_294] (rows=22 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_94] PartitionCols:_col0 - Group By Operator [GBY_93] (rows=24 width=226) + Group By Operator [GBY_93] (rows=22 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","sum(_col2)"],keys:_col0 Select Operator [SEL_91] (rows=1458758 width=135) Output:["_col0","_col1","_col2"] @@ -428,9 +428,9 @@ Stage-0 <-Reducer 4 [CONTAINS] Reduce Output Operator [RS_224] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_223] (rows=58 width=445) + Group By Operator [GBY_223] (rows=66 width=445) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_222] (rows=39 width=435) + Top N Key Operator [TNK_222] (rows=60 width=435) keys:_col0, _col1, 0L,sort order:+++,top n:100 Select Operator [SEL_220] (rows=12 width=436) Output:["_col0","_col1","_col2","_col3","_col4"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query78.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query78.q.out index 578addda51..9bd5f3bdb6 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query78.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query78.q.out @@ -158,13 +158,13 @@ Stage-0 File Output Operator [FS_269] Limit [LIM_268] (rows=100 width=484) Number of rows:100 - Select Operator [SEL_267] (rows=1831943309558 width=483) + Select Operator [SEL_267] (rows=1864495018545 width=483) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_73] - Select Operator [SEL_72] (rows=1831943309558 width=719) + Select Operator [SEL_72] (rows=1864495018545 width=719) Output:["_col0","_col1","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - Merge Join Operator [MERGEJOIN_220] (rows=1831943309558 width=703) + Merge Join Operator [MERGEJOIN_220] (rows=1864495018545 width=703) Conds:RS_69._col0, _col1=RS_266._col0, _col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col11","_col12","_col13"] <-Reducer 12 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_266] @@ -228,7 +228,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_69] PartitionCols:_col0, _col1 - Merge Join Operator [MERGEJOIN_219] (rows=22841150061 width=471) + Merge Join Operator [MERGEJOIN_219] (rows=23235469441 width=471) Conds:RS_244._col1=RS_256._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col8"] <-Reducer 3 [SIMPLE_EDGE] vectorized SHUFFLE [RS_244] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query81.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query81.q.out index 8f62fdea3b..ee8f0aa7dd 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query81.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query81.q.out @@ -88,26 +88,26 @@ Stage-0 Stage-1 Reducer 4 vectorized File Output Operator [FS_215] - Select Operator [SEL_214] (rows=100 width=1506) + Select Operator [SEL_214] (rows=100 width=1504) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] - Limit [LIM_213] (rows=100 width=1420) + Limit [LIM_213] (rows=100 width=1418) Number of rows:100 - Select Operator [SEL_212] (rows=1577696 width=1418) + Select Operator [SEL_212] (rows=1515166 width=1418) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_66] - Select Operator [SEL_65] (rows=1577696 width=1418) + Select Operator [SEL_65] (rows=1515166 width=1418) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] - Merge Join Operator [MERGEJOIN_181] (rows=1577696 width=1418) + Merge Join Operator [MERGEJOIN_181] (rows=1515166 width=1418) Conds:RS_62._col0=RS_63._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col19"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col0 - Select Operator [SEL_58] (rows=1609248 width=227) + Select Operator [SEL_58] (rows=1545467 width=227) Output:["_col0","_col2"] - Filter Operator [FIL_57] (rows=1609248 width=227) + Filter Operator [FIL_57] (rows=1545467 width=227) predicate:(_col2 > _col3) - Merge Join Operator [MERGEJOIN_180] (rows=4827746 width=227) + Merge Join Operator [MERGEJOIN_180] (rows=4636401 width=227) Conds:RS_205._col1=RS_211._col1(Inner),Output:["_col0","_col2","_col3"] <-Reducer 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_211] @@ -164,11 +164,11 @@ Stage-0 <-Reducer 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_205] PartitionCols:_col1 - Filter Operator [FIL_204] (rows=4827746 width=201) + Filter Operator [FIL_204] (rows=4636401 width=201) predicate:_col2 is not null - Select Operator [SEL_203] (rows=4827746 width=201) + Select Operator [SEL_203] (rows=4636401 width=201) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_202] (rows=4827746 width=201) + Group By Operator [GBY_202] (rows=4636401 width=201) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_23] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query84.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query84.q.out index d13dfdbd83..ec1467efba 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query84.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query84.q.out @@ -70,13 +70,13 @@ Stage-0 File Output Operator [FS_139] Limit [LIM_138] (rows=100 width=384) Number of rows:100 - Select Operator [SEL_137] (rows=255280 width=384) + Select Operator [SEL_137] (rows=264528 width=384) Output:["_col0","_col1"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_35] - Select Operator [SEL_34] (rows=255280 width=384) + Select Operator [SEL_34] (rows=264528 width=384) Output:["_col1","_col2"] - Merge Join Operator [MERGEJOIN_119] (rows=255280 width=284) + Merge Join Operator [MERGEJOIN_119] (rows=264528 width=284) Conds:RS_31._col4=RS_32._col0(Inner),Output:["_col2","_col6"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_32] @@ -104,7 +104,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_118] (rows=2552796 width=287) + Merge Join Operator [MERGEJOIN_118] (rows=2645278 width=287) Conds:RS_28._col1=RS_29._col1(Inner),Output:["_col2","_col4","_col6"] <-Reducer 2 [ONE_TO_ONE_EDGE] FORWARD [RS_28] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query89.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query89.q.out index 6cd97eec97..fa314f9482 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query89.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query89.q.out @@ -82,29 +82,29 @@ Stage-0 File Output Operator [FS_110] Limit [LIM_109] (rows=100 width=801) Number of rows:100 - Select Operator [SEL_108] (rows=4804228 width=801) + Select Operator [SEL_108] (rows=32461 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_107] - Select Operator [SEL_106] (rows=4804228 width=801) + Select Operator [SEL_106] (rows=32461 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_105] (rows=4804228 width=689) + Filter Operator [FIL_105] (rows=32461 width=689) predicate:CASE WHEN ((avg_window_0 <> 0)) THEN (((abs((_col6 - avg_window_0)) / avg_window_0) > 0.1)) ELSE (false) END - Select Operator [SEL_104] (rows=9608456 width=577) + Select Operator [SEL_104] (rows=64922 width=577) Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_103] (rows=9608456 width=577) + PTF Operator [PTF_103] (rows=64922 width=577) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS FIRST, _col0 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST","partition by:":"_col2, _col0, _col4, _col5"}] - Select Operator [SEL_102] (rows=9608456 width=577) + Select Operator [SEL_102] (rows=64922 width=577) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_101] PartitionCols:_col2, _col0, _col4, _col5 - Group By Operator [GBY_100] (rows=9608456 width=577) + Group By Operator [GBY_100] (rows=64922 width=577) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_21] (rows=27308180 width=577) + Group By Operator [GBY_21] (rows=3375944 width=577) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)"],keys:_col5, _col6, _col7, _col9, _col11, _col12 Merge Join Operator [MERGEJOIN_83] (rows=27308180 width=480) Conds:RS_17._col2=RS_99._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col9","_col11","_col12"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query91.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query91.q.out index 5e9c1e042f..76a9301f58 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query91.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query91.q.out @@ -92,18 +92,18 @@ Stage-0 Stage-1 Reducer 8 vectorized File Output Operator [FS_170] - Select Operator [SEL_169] (rows=115978 width=406) + Select Operator [SEL_169] (rows=40890 width=406) Output:["_col0","_col1","_col2","_col3"] <-Reducer 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_168] - Select Operator [SEL_167] (rows=115978 width=518) + Select Operator [SEL_167] (rows=40890 width=518) Output:["_col0","_col1","_col2","_col4"] - Group By Operator [GBY_166] (rows=115978 width=585) + Group By Operator [GBY_166] (rows=40890 width=585) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_40] (rows=115978 width=585) + Group By Operator [GBY_40] (rows=40890 width=585) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col11)"],keys:_col5, _col6, _col15, _col16, _col17 Merge Join Operator [MERGEJOIN_145] (rows=231957 width=473) Conds:RS_36._col10=RS_165._col0(Inner),Output:["_col5","_col6","_col11","_col15","_col16","_col17"] @@ -159,7 +159,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_141] (rows=213205 width=183) + Merge Join Operator [MERGEJOIN_141] (rows=228944 width=183) Conds:RS_27._col3=RS_154._col0(Inner),Output:["_col0","_col2","_col5","_col6"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_154] @@ -173,7 +173,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_140] (rows=1066023 width=187) + Merge Join Operator [MERGEJOIN_140] (rows=1144719 width=187) Conds:RS_148._col1=RS_151._col0(Inner),Output:["_col0","_col2","_col3","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_148] diff --git a/ql/src/test/results/clientpositive/perf/tez/query1.q.out b/ql/src/test/results/clientpositive/perf/tez/query1.q.out index efccffea0e..9dd2939b90 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query1.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query1.q.out @@ -76,28 +76,28 @@ Stage-0 File Output Operator [FS_165] Limit [LIM_164] (rows=100 width=100) Number of rows:100 - Select Operator [SEL_163] (rows=816091 width=100) + Select Operator [SEL_163] (rows=663970 width=100) Output:["_col0"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_52] - Select Operator [SEL_51] (rows=816091 width=100) + Select Operator [SEL_51] (rows=663970 width=100) Output:["_col0"] - Filter Operator [FIL_50] (rows=816091 width=324) + Filter Operator [FIL_50] (rows=663970 width=324) predicate:(_col3 > _col6) - Merge Join Operator [MERGEJOIN_136] (rows=2448274 width=324) + Merge Join Operator [MERGEJOIN_136] (rows=1991910 width=324) Conds:RS_47._col2=RS_162._col1(Inner),Output:["_col3","_col5","_col6"] <-Reducer 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_162] PartitionCols:_col1 - Select Operator [SEL_161] (rows=31 width=115) + Select Operator [SEL_161] (rows=29 width=115) Output:["_col0","_col1"] - Filter Operator [FIL_160] (rows=31 width=123) + Filter Operator [FIL_160] (rows=29 width=123) predicate:(_col1 is not null and _col2 is not null) - Group By Operator [GBY_159] (rows=31 width=123) + Group By Operator [GBY_159] (rows=29 width=123) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1 - Select Operator [SEL_158] (rows=14291868 width=119) + Select Operator [SEL_158] (rows=13369812 width=119) Output:["_col1","_col2"] - Group By Operator [GBY_157] (rows=14291868 width=119) + Group By Operator [GBY_157] (rows=13369812 width=119) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_32] @@ -127,7 +127,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_47] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_134] (rows=2369298 width=213) + Merge Join Operator [MERGEJOIN_134] (rows=1923224 width=213) Conds:RS_44._col1=RS_156._col0(Inner),Output:["_col2","_col3","_col5"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_156] @@ -141,7 +141,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_133] (rows=2369298 width=114) + Merge Join Operator [MERGEJOIN_133] (rows=1923224 width=114) Conds:RS_139._col0=RS_153._col1(Inner),Output:["_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_139] @@ -155,11 +155,11 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_153] PartitionCols:_col1 - Select Operator [SEL_152] (rows=14291868 width=119) + Select Operator [SEL_152] (rows=11601100 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_151] (rows=14291868 width=119) + Filter Operator [FIL_151] (rows=11601100 width=119) predicate:_col2 is not null - Group By Operator [GBY_150] (rows=14291868 width=119) + Group By Operator [GBY_150] (rows=11601100 width=119) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_14] diff --git a/ql/src/test/results/clientpositive/perf/tez/query10.q.out b/ql/src/test/results/clientpositive/perf/tez/query10.q.out index 6943d08577..7c5e00e526 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query10.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query10.q.out @@ -173,28 +173,28 @@ Stage-0 PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Group By Operator [GBY_66] (rows=1 width=379) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["count()"],keys:_col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Top N Key Operator [TNK_103] (rows=58 width=379) + Top N Key Operator [TNK_103] (rows=52 width=379) keys:_col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13,sort order:++++++++,top n:100 - Select Operator [SEL_65] (rows=58 width=379) + Select Operator [SEL_65] (rows=52 width=379) Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - Filter Operator [FIL_64] (rows=58 width=379) + Filter Operator [FIL_64] (rows=52 width=379) predicate:(_col15 is not null or _col17 is not null) - Merge Join Operator [MERGEJOIN_181] (rows=58 width=379) + Merge Join Operator [MERGEJOIN_181] (rows=52 width=379) Conds:RS_61._col0=RS_219._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col15","_col17"] <-Reducer 5 [ONE_TO_ONE_EDGE] PARTITION_ONLY_SHUFFLE [RS_61] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_180] (rows=58 width=379) + Merge Join Operator [MERGEJOIN_180] (rows=53 width=379) Conds:RS_58._col0=RS_211._col0(Left Outer),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col15"] <-Reducer 4 [ONE_TO_ONE_EDGE] FORWARD [RS_58] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_179] (rows=22703 width=375) + Merge Join Operator [MERGEJOIN_179] (rows=20705 width=375) Conds:RS_55._col0=RS_56._col0(Left Semi),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col0 - Group By Operator [GBY_54] (rows=155827 width=2) + Group By Operator [GBY_54] (rows=142119 width=2) Output:["_col0"],keys:_col0 Select Operator [SEL_18] (rows=57825495 width=2) Output:["_col0"] @@ -269,14 +269,14 @@ Stage-0 <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_211] PartitionCols:_col0 - Select Operator [SEL_210] (rows=155827 width=7) + Select Operator [SEL_210] (rows=155749 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_209] (rows=155827 width=3) + Group By Operator [GBY_209] (rows=155749 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0 - Group By Operator [GBY_29] (rows=155827 width=3) + Group By Operator [GBY_29] (rows=155749 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_177] (rows=15843227 width=3) Conds:RS_208._col0=RS_195._col0(Inner),Output:["_col1"] @@ -301,20 +301,20 @@ Stage-0 FORWARD [RS_151] Group By Operator [GBY_150] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_149] (rows=22703 width=4) + Select Operator [SEL_149] (rows=20705 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_179] <-Reducer 20 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_219] PartitionCols:_col0 - Select Operator [SEL_218] (rows=154725 width=7) + Select Operator [SEL_218] (rows=153181 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_217] (rows=154725 width=3) + Group By Operator [GBY_217] (rows=153181 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col0 - Group By Operator [GBY_43] (rows=154725 width=3) + Group By Operator [GBY_43] (rows=153181 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_178] (rows=31162251 width=3) Conds:RS_216._col0=RS_196._col0(Inner),Output:["_col1"] @@ -339,7 +339,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_166] Group By Operator [GBY_165] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_164] (rows=58 width=4) + Select Operator [SEL_164] (rows=53 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_180] diff --git a/ql/src/test/results/clientpositive/perf/tez/query14.q.out b/ql/src/test/results/clientpositive/perf/tez/query14.q.out index 022256722f..a887c504da 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query14.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query14.q.out @@ -387,9 +387,9 @@ Stage-0 <-Reducer 33 [SIMPLE_EDGE] SHUFFLE [RS_239] PartitionCols:_col0 - Group By Operator [GBY_237] (rows=362 width=4) + Group By Operator [GBY_237] (rows=364 width=4) Output:["_col0"],keys:_col0 - Merge Join Operator [MERGEJOIN_1151] (rows=724 width=4) + Merge Join Operator [MERGEJOIN_1151] (rows=729 width=4) Conds:RS_1327._col1, _col2, _col3=RS_1355._col0, _col1, _col2(Inner),Output:["_col0"] <-Map 24 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1327] @@ -406,20 +406,20 @@ Stage-0 Output:["_col0","_col1","_col2"] Filter Operator [FIL_1353] (rows=1 width=20) predicate:(_col3 = 3L) - Group By Operator [GBY_1352] (rows=121728 width=19) + Group By Operator [GBY_1352] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 31 [SIMPLE_EDGE] <-Reducer 30 [CONTAINS] vectorized Reduce Output Operator [RS_1409] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1408] (rows=121728 width=19) + Group By Operator [GBY_1408] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1407] (rows=121728 width=19) + Group By Operator [GBY_1407] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_175] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_28] (rows=121728 width=19) + Group By Operator [GBY_28] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 Merge Join Operator [MERGEJOIN_1134] (rows=14628613 width=11) Conds:RS_24._col1=RS_1323._col0(Inner),Output:["_col4","_col5","_col6"] @@ -468,14 +468,14 @@ Stage-0 <-Reducer 40 [CONTAINS] vectorized Reduce Output Operator [RS_1423] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1422] (rows=121728 width=19) + Group By Operator [GBY_1422] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1421] (rows=121728 width=19) + Group By Operator [GBY_1421] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 38 [SIMPLE_EDGE] SHUFFLE [RS_195] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_48] (rows=121728 width=19) + Group By Operator [GBY_48] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 Merge Join Operator [MERGEJOIN_1136] (rows=7620440 width=11) Conds:RS_44._col1=RS_1324._col0(Inner),Output:["_col4","_col5","_col6"] @@ -519,14 +519,14 @@ Stage-0 <-Reducer 44 [CONTAINS] vectorized Reduce Output Operator [RS_1437] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1436] (rows=121728 width=19) + Group By Operator [GBY_1436] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1435] (rows=121728 width=19) + Group By Operator [GBY_1435] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 42 [SIMPLE_EDGE] SHUFFLE [RS_216] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_69] (rows=121728 width=19) + Group By Operator [GBY_69] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6 Merge Join Operator [MERGEJOIN_1138] (rows=3828623 width=11) Conds:RS_65._col1=RS_1325._col0(Inner),Output:["_col4","_col5","_col6"] @@ -761,9 +761,9 @@ Stage-0 <-Reducer 37 [SIMPLE_EDGE] SHUFFLE [RS_386] PartitionCols:_col0 - Group By Operator [GBY_384] (rows=362 width=4) + Group By Operator [GBY_384] (rows=364 width=4) Output:["_col0"],keys:_col0 - Merge Join Operator [MERGEJOIN_1163] (rows=724 width=4) + Merge Join Operator [MERGEJOIN_1163] (rows=729 width=4) Conds:RS_1329._col1, _col2, _col3=RS_1371._col0, _col1, _col2(Inner),Output:["_col0"] <-Map 24 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1329] @@ -780,15 +780,15 @@ Stage-0 Output:["_col0","_col1","_col2"] Filter Operator [FIL_1369] (rows=1 width=20) predicate:(_col3 = 3L) - Group By Operator [GBY_1368] (rows=121728 width=19) + Group By Operator [GBY_1368] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 35 [SIMPLE_EDGE] <-Reducer 34 [CONTAINS] vectorized Reduce Output Operator [RS_1412] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1411] (rows=121728 width=19) + Group By Operator [GBY_1411] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1410] (rows=121728 width=19) + Group By Operator [GBY_1410] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_322] @@ -797,9 +797,9 @@ Stage-0 <-Reducer 41 [CONTAINS] vectorized Reduce Output Operator [RS_1426] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1425] (rows=121728 width=19) + Group By Operator [GBY_1425] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1424] (rows=121728 width=19) + Group By Operator [GBY_1424] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 38 [SIMPLE_EDGE] SHUFFLE [RS_342] @@ -808,9 +808,9 @@ Stage-0 <-Reducer 45 [CONTAINS] vectorized Reduce Output Operator [RS_1440] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1439] (rows=121728 width=19) + Group By Operator [GBY_1439] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1438] (rows=121728 width=19) + Group By Operator [GBY_1438] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 42 [SIMPLE_EDGE] SHUFFLE [RS_363] @@ -910,9 +910,9 @@ Stage-0 <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_93] PartitionCols:_col0 - Group By Operator [GBY_91] (rows=362 width=4) + Group By Operator [GBY_91] (rows=364 width=4) Output:["_col0"],keys:_col0 - Merge Join Operator [MERGEJOIN_1139] (rows=724 width=4) + Merge Join Operator [MERGEJOIN_1139] (rows=729 width=4) Conds:RS_1322._col1, _col2, _col3=RS_1333._col0, _col1, _col2(Inner),Output:["_col0"] <-Map 24 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1322] @@ -929,15 +929,15 @@ Stage-0 Output:["_col0","_col1","_col2"] Filter Operator [FIL_1331] (rows=1 width=20) predicate:(_col3 = 3L) - Group By Operator [GBY_1330] (rows=121728 width=19) + Group By Operator [GBY_1330] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 28 [SIMPLE_EDGE] <-Reducer 27 [CONTAINS] vectorized Reduce Output Operator [RS_1406] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1405] (rows=121728 width=19) + Group By Operator [GBY_1405] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1404] (rows=121728 width=19) + Group By Operator [GBY_1404] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_29] @@ -946,9 +946,9 @@ Stage-0 <-Reducer 39 [CONTAINS] vectorized Reduce Output Operator [RS_1420] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1419] (rows=121728 width=19) + Group By Operator [GBY_1419] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1418] (rows=121728 width=19) + Group By Operator [GBY_1418] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 38 [SIMPLE_EDGE] SHUFFLE [RS_49] @@ -957,9 +957,9 @@ Stage-0 <-Reducer 43 [CONTAINS] vectorized Reduce Output Operator [RS_1434] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1433] (rows=121728 width=19) + Group By Operator [GBY_1433] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1432] (rows=121728 width=19) + Group By Operator [GBY_1432] (rows=120960 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 42 [SIMPLE_EDGE] SHUFFLE [RS_70] diff --git a/ql/src/test/results/clientpositive/perf/tez/query17.q.out b/ql/src/test/results/clientpositive/perf/tez/query17.q.out index a89d995d38..9fca15ec04 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query17.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query17.q.out @@ -125,24 +125,24 @@ Stage-0 File Output Operator [FS_253] Limit [LIM_252] (rows=100 width=466) Number of rows:100 - Select Operator [SEL_251] (rows=8581091759 width=466) + Select Operator [SEL_251] (rows=9307320243 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_250] - Select Operator [SEL_249] (rows=8581091759 width=466) + Select Operator [SEL_249] (rows=9307320243 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - Group By Operator [GBY_248] (rows=8581091759 width=466) + Group By Operator [GBY_248] (rows=9307320243 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","count(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)","sum(VALUE._col7)","count(VALUE._col8)","sum(VALUE._col9)","sum(VALUE._col10)","sum(VALUE._col11)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_50] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_49] (rows=8581091759 width=466) + Group By Operator [GBY_49] (rows=9307320243 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"],aggregations:["count(_col3)","sum(_col3)","sum(_col7)","sum(_col6)","count(_col4)","sum(_col4)","sum(_col9)","sum(_col8)","count(_col5)","sum(_col5)","sum(_col11)","sum(_col10)"],keys:_col0, _col1, _col2 - Top N Key Operator [TNK_93] (rows=8581091759 width=381) + Top N Key Operator [TNK_93] (rows=9307320243 width=381) keys:_col0, _col1, _col2,sort order:+++,top n:100 - Select Operator [SEL_47] (rows=8581091759 width=381) + Select Operator [SEL_47] (rows=9307320243 width=381) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Merge Join Operator [MERGEJOIN_213] (rows=8581091759 width=381) + Merge Join Operator [MERGEJOIN_213] (rows=9307320243 width=381) Conds:RS_44._col3=RS_247._col0(Inner),Output:["_col5","_col8","_col9","_col13","_col19","_col22"] <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_247] @@ -156,12 +156,12 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_212] (rows=8581091759 width=299) + Merge Join Operator [MERGEJOIN_212] (rows=9307320243 width=299) Conds:RS_41._col1, _col2, _col4=RS_42._col6, _col7, _col8(Inner),Output:["_col3","_col5","_col8","_col9","_col13","_col19"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col6, _col7, _col8 - Merge Join Operator [MERGEJOIN_211] (rows=1640229377 width=19) + Merge Join Operator [MERGEJOIN_211] (rows=1656746576 width=19) Conds:RS_28._col2, _col1=RS_29._col1, _col2(Inner),Output:["_col3","_col6","_col7","_col8","_col9"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_28] diff --git a/ql/src/test/results/clientpositive/perf/tez/query18.q.out b/ql/src/test/results/clientpositive/perf/tez/query18.q.out index c6d4d1a76b..5b494ee211 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query18.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query18.q.out @@ -100,27 +100,27 @@ Stage-0 File Output Operator [FS_174] Limit [LIM_173] (rows=100 width=1165) Number of rows:100 - Select Operator [SEL_172] (rows=10969165 width=1165) + Select Operator [SEL_172] (rows=11135335 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_171] - Select Operator [SEL_170] (rows=10969165 width=1165) + Select Operator [SEL_170] (rows=11135335 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Group By Operator [GBY_169] (rows=10969165 width=1229) + Group By Operator [GBY_169] (rows=11135335 width=1229) Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)","sum(VALUE._col8)","count(VALUE._col9)","sum(VALUE._col10)","count(VALUE._col11)","sum(VALUE._col12)","count(VALUE._col13)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_41] (rows=10969165 width=1229) + Group By Operator [GBY_41] (rows=11135335 width=1229) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(_col15)","count(_col15)","sum(_col16)","count(_col16)","sum(_col17)","count(_col17)","sum(_col18)","count(_col18)","sum(_col19)","count(_col19)","sum(_col3)","count(_col3)","sum(_col22)","count(_col22)"],keys:_col5, _col6, _col7, _col10, 0L - Merge Join Operator [MERGEJOIN_142] (rows=2193833 width=811) + Merge Join Operator [MERGEJOIN_142] (rows=2227067 width=817) Conds:RS_37._col0=RS_38._col3(Inner),Output:["_col3","_col5","_col6","_col7","_col10","_col15","_col16","_col17","_col18","_col19","_col22"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col3 - Select Operator [SEL_30] (rows=15983636 width=735) + Select Operator [SEL_30] (rows=16225774 width=736) Output:["_col1","_col3","_col6","_col7","_col8","_col9","_col10","_col13"] - Merge Join Operator [MERGEJOIN_141] (rows=15983636 width=735) + Merge Join Operator [MERGEJOIN_141] (rows=16225774 width=736) Conds:RS_27._col3=RS_168._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col11","_col13"] <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_168] @@ -134,7 +134,7 @@ Stage-0 <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_140] (rows=15983636 width=639) + Merge Join Operator [MERGEJOIN_140] (rows=16225774 width=640) Conds:RS_24._col2=RS_165._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col11"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_165] diff --git a/ql/src/test/results/clientpositive/perf/tez/query23.q.out b/ql/src/test/results/clientpositive/perf/tez/query23.q.out index 75d7e434ef..fa9df26bc8 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query23.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query23.q.out @@ -165,19 +165,19 @@ Stage-0 Reduce Output Operator [RS_467] Group By Operator [GBY_466] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_464] (rows=4 width=112) + Select Operator [SEL_464] (rows=3 width=112) Output:["_col0"] - Merge Join Operator [MERGEJOIN_463] (rows=4 width=29) + Merge Join Operator [MERGEJOIN_463] (rows=3 width=38) Conds:RS_178._col2=RS_179._col0(Left Semi),Output:["_col3","_col4"] <-Reducer 11 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_178] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_453] (rows=155 width=0) + Merge Join Operator [MERGEJOIN_453] (rows=148 width=0) Conds:RS_173._col1=RS_503._col0(Inner),Output:["_col2","_col3","_col4"] <-Reducer 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_503] PartitionCols:_col0 - Group By Operator [GBY_501] (rows=2235 width=4) + Group By Operator [GBY_501] (rows=2134 width=4) Output:["_col0"],keys:_col1 Select Operator [SEL_500] (rows=6548799 width=290) Output:["_col1"] @@ -274,13 +274,13 @@ Stage-0 <-Reducer 30 [SIMPLE_EDGE] SHUFFLE [RS_179] PartitionCols:_col0 - Group By Operator [GBY_177] (rows=235937 width=4) + Group By Operator [GBY_177] (rows=225322 width=4) Output:["_col0"],keys:_col0 - Select Operator [SEL_169] (rows=471875 width=4) + Select Operator [SEL_169] (rows=450644 width=4) Output:["_col0"] - Filter Operator [FIL_168] (rows=471875 width=228) + Filter Operator [FIL_168] (rows=450644 width=228) predicate:(_col1 > _col2) - Merge Join Operator [MERGEJOIN_456] (rows=1415625 width=228) + Merge Join Operator [MERGEJOIN_456] (rows=1351933 width=228) Conds:(Inner),Output:["_col0","_col1","_col2"] <-Reducer 29 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_536] @@ -294,14 +294,14 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_531] Group By Operator [GBY_530] (rows=1 width=112) Output:["_col0"],aggregations:["max(_col1)"] - Select Operator [SEL_529] (rows=11859 width=116) + Select Operator [SEL_529] (rows=10815 width=116) Output:["_col1"] - Group By Operator [GBY_528] (rows=11859 width=116) + Group By Operator [GBY_528] (rows=10815 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 27 [SIMPLE_EDGE] SHUFFLE [RS_64] PartitionCols:_col0 - Group By Operator [GBY_63] (rows=106731 width=116) + Group By Operator [GBY_63] (rows=97335 width=116) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 Merge Join Operator [MERGEJOIN_445] (rows=18762463 width=116) Conds:RS_59._col1=RS_512._col0(Inner),Output:["_col2","_col4"] @@ -350,9 +350,9 @@ Stage-0 Please refer to the previous Select Operator [SEL_518] <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_551] - Filter Operator [FIL_550] (rows=1415625 width=116) + Filter Operator [FIL_550] (rows=1351933 width=116) predicate:_col1 is not null - Group By Operator [GBY_549] (rows=1415625 width=116) + Group By Operator [GBY_549] (rows=1351933 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 31 [SIMPLE_EDGE] SHUFFLE [RS_134] @@ -382,21 +382,21 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_415] Group By Operator [GBY_414] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_413] (rows=155 width=0) + Select Operator [SEL_413] (rows=148 width=0) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_453] <-Reducer 4 [CONTAINS] Reduce Output Operator [RS_462] Group By Operator [GBY_461] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_459] (rows=7 width=112) + Select Operator [SEL_459] (rows=6 width=112) Output:["_col0"] - Merge Join Operator [MERGEJOIN_458] (rows=7 width=16) + Merge Join Operator [MERGEJOIN_458] (rows=6 width=19) Conds:RS_87._col1=RS_88._col0(Left Semi),Output:["_col3","_col4"] <-Reducer 3 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_87] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_452] (rows=304 width=0) + Merge Join Operator [MERGEJOIN_452] (rows=290 width=0) Conds:RS_82._col2=RS_502._col0(Inner),Output:["_col1","_col3","_col4"] <-Reducer 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_502] @@ -434,22 +434,22 @@ Stage-0 <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_88] PartitionCols:_col0 - Group By Operator [GBY_86] (rows=235937 width=4) + Group By Operator [GBY_86] (rows=225322 width=4) Output:["_col0"],keys:_col0 - Select Operator [SEL_78] (rows=471875 width=4) + Select Operator [SEL_78] (rows=450644 width=4) Output:["_col0"] - Filter Operator [FIL_77] (rows=471875 width=228) + Filter Operator [FIL_77] (rows=450644 width=228) predicate:(_col1 > _col2) - Merge Join Operator [MERGEJOIN_454] (rows=1415625 width=228) + Merge Join Operator [MERGEJOIN_454] (rows=1351933 width=228) Conds:(Inner),Output:["_col0","_col1","_col2"] <-Reducer 29 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_535] Please refer to the previous Select Operator [SEL_534] <-Reducer 24 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_516] - Filter Operator [FIL_515] (rows=1415625 width=116) + Filter Operator [FIL_515] (rows=1351933 width=116) predicate:_col1 is not null - Group By Operator [GBY_514] (rows=1415625 width=116) + Group By Operator [GBY_514] (rows=1351933 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 23 [SIMPLE_EDGE] SHUFFLE [RS_43] @@ -479,7 +479,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_329] Group By Operator [GBY_328] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_327] (rows=304 width=0) + Select Operator [SEL_327] (rows=290 width=0) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_452] diff --git a/ql/src/test/results/clientpositive/perf/tez/query25.q.out b/ql/src/test/results/clientpositive/perf/tez/query25.q.out index b72cef636f..7004eae83f 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query25.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query25.q.out @@ -131,20 +131,20 @@ Stage-0 File Output Operator [FS_253] Limit [LIM_252] (rows=100 width=808) Number of rows:100 - Select Operator [SEL_251] (rows=4248052806 width=808) + Select Operator [SEL_251] (rows=4607593224 width=808) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_250] - Group By Operator [GBY_249] (rows=4248052806 width=808) + Group By Operator [GBY_249] (rows=4607593224 width=808) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_48] (rows=4248052806 width=808) + Group By Operator [GBY_48] (rows=4607593224 width=808) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col5)","sum(_col16)","sum(_col10)"],keys:_col19, _col20, _col22, _col23 - Top N Key Operator [TNK_95] (rows=4248052806 width=807) + Top N Key Operator [TNK_95] (rows=4607593224 width=807) keys:_col19, _col20, _col22, _col23,sort order:++++,top n:100 - Merge Join Operator [MERGEJOIN_214] (rows=4248052806 width=807) + Merge Join Operator [MERGEJOIN_214] (rows=4607593224 width=807) Conds:RS_44._col3=RS_248._col0(Inner),Output:["_col5","_col10","_col16","_col19","_col20","_col22","_col23"] <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_248] @@ -158,7 +158,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_213] (rows=4248052806 width=623) + Merge Join Operator [MERGEJOIN_213] (rows=4607593224 width=623) Conds:RS_41._col1=RS_245._col0(Inner),Output:["_col3","_col5","_col10","_col16","_col19","_col20"] <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_245] @@ -172,12 +172,12 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_212] (rows=4248052806 width=343) + Merge Join Operator [MERGEJOIN_212] (rows=4607593224 width=343) Conds:RS_38._col1, _col2, _col4=RS_39._col6, _col7, _col8(Inner),Output:["_col1","_col3","_col5","_col10","_col16"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_39] PartitionCols:_col6, _col7, _col8 - Merge Join Operator [MERGEJOIN_211] (rows=1893811716 width=235) + Merge Join Operator [MERGEJOIN_211] (rows=1912891783 width=235) Conds:RS_25._col2, _col1=RS_26._col1, _col2(Inner),Output:["_col3","_col6","_col7","_col8","_col9"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_25] diff --git a/ql/src/test/results/clientpositive/perf/tez/query26.q.out b/ql/src/test/results/clientpositive/perf/tez/query26.q.out index 798942fa50..3c5c7a9845 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query26.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query26.q.out @@ -83,9 +83,9 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_28] (rows=462000 width=476) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col12 - Top N Key Operator [TNK_55] (rows=809521 width=100) + Top N Key Operator [TNK_55] (rows=821787 width=100) keys:_col12,sort order:+,top n:100 - Merge Join Operator [MERGEJOIN_99] (rows=809521 width=100) + Merge Join Operator [MERGEJOIN_99] (rows=821787 width=100) Conds:RS_24._col2=RS_119._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col12"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_119] @@ -99,7 +99,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_98] (rows=809521 width=4) + Merge Join Operator [MERGEJOIN_98] (rows=821787 width=4) Conds:RS_21._col3=RS_116._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_116] @@ -113,7 +113,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_97] (rows=809521 width=4) + Merge Join Operator [MERGEJOIN_97] (rows=821787 width=4) Conds:RS_18._col0=RS_113._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_113] @@ -127,7 +127,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_96] (rows=2283326 width=135) + Merge Join Operator [MERGEJOIN_96] (rows=2317924 width=139) Conds:RS_110._col1=RS_102._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_102] diff --git a/ql/src/test/results/clientpositive/perf/tez/query27.q.out b/ql/src/test/results/clientpositive/perf/tez/query27.q.out index 44ddef0401..e715634186 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query27.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query27.q.out @@ -74,24 +74,24 @@ Stage-0 File Output Operator [FS_126] Limit [LIM_125] (rows=100 width=538) Number of rows:100 - Select Operator [SEL_124] (rows=4281825 width=538) + Select Operator [SEL_124] (rows=4916010 width=538) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_123] - Select Operator [SEL_122] (rows=4281825 width=538) + Select Operator [SEL_122] (rows=4916010 width=538) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Group By Operator [GBY_121] (rows=4281825 width=570) + Group By Operator [GBY_121] (rows=4916010 width=570) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_29] (rows=4281825 width=570) + Group By Operator [GBY_29] (rows=4916010 width=570) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col2)","count(_col2)","sum(_col3)","count(_col3)","sum(_col4)","count(_col4)","sum(_col5)","count(_col5)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_56] (rows=1427275 width=186) + Top N Key Operator [TNK_56] (rows=1638670 width=186) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_27] (rows=1427275 width=186) + Select Operator [SEL_27] (rows=1638670 width=186) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_100] (rows=1427275 width=186) + Merge Join Operator [MERGEJOIN_100] (rows=1638670 width=186) Conds:RS_24._col1=RS_120._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col11","_col13"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_120] @@ -105,7 +105,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_99] (rows=1427275 width=90) + Merge Join Operator [MERGEJOIN_99] (rows=1638670 width=90) Conds:RS_21._col3=RS_117._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col11"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_117] @@ -119,7 +119,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_98] (rows=1441779 width=4) + Merge Join Operator [MERGEJOIN_98] (rows=1655322 width=4) Conds:RS_18._col0=RS_114._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_114] @@ -133,7 +133,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_97] (rows=4037920 width=4) + Merge Join Operator [MERGEJOIN_97] (rows=4635978 width=4) Conds:RS_111._col2=RS_103._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_103] diff --git a/ql/src/test/results/clientpositive/perf/tez/query29.q.out b/ql/src/test/results/clientpositive/perf/tez/query29.q.out index f5e6c59970..5bffe371cf 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query29.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query29.q.out @@ -129,27 +129,27 @@ Stage-0 File Output Operator [FS_244] Limit [LIM_243] (rows=100 width=496) Number of rows:100 - Select Operator [SEL_242] (rows=21091879 width=496) + Select Operator [SEL_242] (rows=22648840 width=496) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_241] - Group By Operator [GBY_240] (rows=21091879 width=496) + Group By Operator [GBY_240] (rows=22648840 width=496) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_48] (rows=21091879 width=496) + Group By Operator [GBY_48] (rows=22648840 width=496) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col13)","sum(_col19)","sum(_col3)"],keys:_col6, _col7, _col22, _col23 - Top N Key Operator [TNK_93] (rows=4156223234 width=483) + Top N Key Operator [TNK_93] (rows=4607567401 width=483) keys:_col6, _col7, _col22, _col23,sort order:++++,top n:100 - Merge Join Operator [MERGEJOIN_205] (rows=4156223234 width=483) + Merge Join Operator [MERGEJOIN_205] (rows=4607567401 width=483) Conds:RS_44._col2, _col1=RS_45._col11, _col12(Inner),Output:["_col3","_col6","_col7","_col13","_col19","_col22","_col23"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_45] PartitionCols:_col11, _col12 - Select Operator [SEL_40] (rows=21091879 width=484) + Select Operator [SEL_40] (rows=22648840 width=484) Output:["_col1","_col2","_col8","_col11","_col12","_col14","_col17","_col18"] - Merge Join Operator [MERGEJOIN_204] (rows=21091879 width=484) + Merge Join Operator [MERGEJOIN_204] (rows=22648840 width=484) Conds:RS_37._col3=RS_239._col0(Inner),Output:["_col5","_col8","_col9","_col11","_col14","_col15","_col17","_col18"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_239] @@ -163,7 +163,7 @@ Stage-0 <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_203] (rows=21091879 width=298) + Merge Join Operator [MERGEJOIN_203] (rows=22648840 width=298) Conds:RS_34._col1=RS_236._col0(Inner),Output:["_col3","_col5","_col8","_col9","_col11","_col14","_col15"] <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_236] @@ -177,7 +177,7 @@ Stage-0 <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_202] (rows=21091879 width=18) + Merge Join Operator [MERGEJOIN_202] (rows=22648840 width=18) Conds:RS_31._col1, _col2, _col4=RS_32._col1, _col2, _col3(Inner),Output:["_col1","_col3","_col5","_col8","_col9","_col11"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_32] diff --git a/ql/src/test/results/clientpositive/perf/tez/query30.q.out b/ql/src/test/results/clientpositive/perf/tez/query30.q.out index 42c09533d3..e2c814e5e7 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query30.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query30.q.out @@ -90,13 +90,13 @@ Stage-0 File Output Operator [FS_215] Limit [LIM_214] (rows=100 width=942) Number of rows:100 - Select Operator [SEL_213] (rows=691171 width=942) + Select Operator [SEL_213] (rows=601923 width=942) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_66] - Select Operator [SEL_65] (rows=691171 width=942) + Select Operator [SEL_65] (rows=601923 width=942) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - Merge Join Operator [MERGEJOIN_180] (rows=691171 width=942) + Merge Join Operator [MERGEJOIN_180] (rows=601923 width=942) Conds:RS_62._col0=RS_63._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col17"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_62] @@ -124,11 +124,11 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col0 - Select Operator [SEL_58] (rows=704993 width=227) + Select Operator [SEL_58] (rows=613960 width=227) Output:["_col0","_col2"] - Filter Operator [FIL_57] (rows=704993 width=227) + Filter Operator [FIL_57] (rows=613960 width=227) predicate:(_col2 > _col3) - Merge Join Operator [MERGEJOIN_179] (rows=2114980 width=227) + Merge Join Operator [MERGEJOIN_179] (rows=1841880 width=227) Conds:RS_206._col1=RS_212._col1(Inner),Output:["_col0","_col2","_col3"] <-Reducer 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_212] @@ -184,11 +184,11 @@ Stage-0 <-Reducer 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_206] PartitionCols:_col1 - Filter Operator [FIL_205] (rows=2114980 width=201) + Filter Operator [FIL_205] (rows=1841880 width=201) predicate:_col2 is not null - Select Operator [SEL_204] (rows=2114980 width=201) + Select Operator [SEL_204] (rows=1841880 width=201) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_203] (rows=2114980 width=201) + Group By Operator [GBY_203] (rows=1841880 width=201) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_23] diff --git a/ql/src/test/results/clientpositive/perf/tez/query33.q.out b/ql/src/test/results/clientpositive/perf/tez/query33.q.out index af1e288366..b0f0d86027 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query33.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query33.q.out @@ -192,33 +192,33 @@ Stage-0 Stage-1 Reducer 7 vectorized File Output Operator [FS_357] - Limit [LIM_356] (rows=59 width=115) + Limit [LIM_356] (rows=2 width=114) Number of rows:100 - Select Operator [SEL_355] (rows=59 width=115) + Select Operator [SEL_355] (rows=2 width=114) Output:["_col0","_col1"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_354] - Group By Operator [GBY_353] (rows=59 width=115) + Group By Operator [GBY_353] (rows=2 width=114) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Union 5 [SIMPLE_EDGE] <-Reducer 11 [CONTAINS] vectorized Reduce Output Operator [RS_373] PartitionCols:_col0 - Group By Operator [GBY_372] (rows=59 width=115) + Group By Operator [GBY_372] (rows=2 width=114) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_371] (rows=19 width=115) + Group By Operator [GBY_371] (rows=2 width=114) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_109] PartitionCols:_col0 - Group By Operator [GBY_108] (rows=19 width=115) + Group By Operator [GBY_108] (rows=2 width=114) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_304] (rows=11364 width=3) + Merge Join Operator [MERGEJOIN_304] (rows=1134 width=0) Conds:RS_104._col0=RS_105._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_104] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_293] (rows=461514 width=7) + Merge Join Operator [MERGEJOIN_293] (rows=46084 width=7) Conds:RS_319._col1=RS_325._col0(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_319] @@ -232,12 +232,12 @@ Stage-0 <-Reducer 13 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_325] PartitionCols:_col0 - Group By Operator [GBY_324] (rows=692 width=3) + Group By Operator [GBY_324] (rows=69 width=4) Output:["_col0"],keys:KEY._col0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_323] PartitionCols:_col0 - Group By Operator [GBY_322] (rows=692 width=3) + Group By Operator [GBY_322] (rows=70 width=4) Output:["_col0"],keys:i_manufact_id Select Operator [SEL_321] (rows=46085 width=93) Output:["i_manufact_id"] @@ -298,16 +298,16 @@ Stage-0 <-Reducer 4 [CONTAINS] vectorized Reduce Output Operator [RS_352] PartitionCols:_col0 - Group By Operator [GBY_351] (rows=59 width=115) + Group By Operator [GBY_351] (rows=2 width=114) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_350] (rows=64 width=115) + Group By Operator [GBY_350] (rows=2 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col0 - Group By Operator [GBY_33] (rows=64 width=115) + Group By Operator [GBY_33] (rows=2 width=116) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_302] (rows=41476 width=3) + Merge Join Operator [MERGEJOIN_302] (rows=4136 width=2) Conds:RS_29._col0=RS_30._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_29] @@ -356,16 +356,16 @@ Stage-0 <-Reducer 9 [CONTAINS] vectorized Reduce Output Operator [RS_365] PartitionCols:_col0 - Group By Operator [GBY_364] (rows=59 width=115) + Group By Operator [GBY_364] (rows=2 width=114) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_363] (rows=35 width=115) + Group By Operator [GBY_363] (rows=2 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_71] PartitionCols:_col0 - Group By Operator [GBY_70] (rows=35 width=115) + Group By Operator [GBY_70] (rows=2 width=116) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_303] (rows=22352 width=3) + Merge Join Operator [MERGEJOIN_303] (rows=2229 width=1) Conds:RS_66._col0=RS_67._col3(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_66] diff --git a/ql/src/test/results/clientpositive/perf/tez/query35.q.out b/ql/src/test/results/clientpositive/perf/tez/query35.q.out index 9c8a4f61d9..ad929535fd 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query35.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query35.q.out @@ -169,28 +169,28 @@ Stage-0 PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 Group By Operator [GBY_66] (rows=1 width=336) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count()","sum(_col8)","count(_col8)","max(_col8)","sum(_col9)","count(_col9)","max(_col9)","sum(_col10)","count(_col10)","max(_col10)"],keys:_col4, _col6, _col7, _col8, _col9, _col10 - Top N Key Operator [TNK_104] (rows=67 width=276) + Top N Key Operator [TNK_104] (rows=61 width=276) keys:_col4, _col6, _col7, _col8, _col9, _col10,sort order:++++++,top n:100 - Select Operator [SEL_65] (rows=67 width=276) + Select Operator [SEL_65] (rows=61 width=276) Output:["_col4","_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_64] (rows=67 width=276) + Filter Operator [FIL_64] (rows=61 width=276) predicate:(_col12 is not null or _col14 is not null) - Merge Join Operator [MERGEJOIN_182] (rows=67 width=276) + Merge Join Operator [MERGEJOIN_182] (rows=61 width=276) Conds:RS_61._col0=RS_220._col0(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col12","_col14"] <-Reducer 5 [ONE_TO_ONE_EDGE] PARTITION_ONLY_SHUFFLE [RS_61] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_181] (rows=68 width=276) + Merge Join Operator [MERGEJOIN_181] (rows=62 width=276) Conds:RS_58._col0=RS_212._col0(Left Outer),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10","_col12"] <-Reducer 4 [ONE_TO_ONE_EDGE] FORWARD [RS_58] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_180] (rows=162346 width=272) + Merge Join Operator [MERGEJOIN_180] (rows=148065 width=272) Conds:RS_55._col0=RS_56._col0(Left Semi),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col0 - Group By Operator [GBY_54] (rows=168231 width=2) + Group By Operator [GBY_54] (rows=153432 width=2) Output:["_col0"],keys:_col0 Select Operator [SEL_18] (rows=62428523 width=2) Output:["_col0"] @@ -265,14 +265,14 @@ Stage-0 <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_212] PartitionCols:_col0 - Select Operator [SEL_211] (rows=168231 width=7) + Select Operator [SEL_211] (rows=168147 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_210] (rows=168231 width=3) + Group By Operator [GBY_210] (rows=168147 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0 - Group By Operator [GBY_29] (rows=168231 width=3) + Group By Operator [GBY_29] (rows=168147 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_178] (rows=17104380 width=3) Conds:RS_209._col0=RS_196._col0(Inner),Output:["_col1"] @@ -297,20 +297,20 @@ Stage-0 FORWARD [RS_152] Group By Operator [GBY_151] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_150] (rows=162346 width=4) + Select Operator [SEL_150] (rows=148065 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_180] <-Reducer 20 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_220] PartitionCols:_col0 - Select Operator [SEL_219] (rows=167041 width=7) + Select Operator [SEL_219] (rows=165374 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_218] (rows=167041 width=3) + Group By Operator [GBY_218] (rows=165374 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col0 - Group By Operator [GBY_43] (rows=167041 width=3) + Group By Operator [GBY_43] (rows=165374 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_179] (rows=33642830 width=3) Conds:RS_217._col0=RS_197._col0(Inner),Output:["_col1"] @@ -335,7 +335,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_167] Group By Operator [GBY_166] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_165] (rows=68 width=4) + Select Operator [SEL_165] (rows=62 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_181] diff --git a/ql/src/test/results/clientpositive/perf/tez/query47.q.out b/ql/src/test/results/clientpositive/perf/tez/query47.q.out index 68f7bb600e..1c81d1e1a7 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query47.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query47.q.out @@ -132,29 +132,29 @@ Stage-0 File Output Operator [FS_321] Limit [LIM_320] (rows=100 width=658) Number of rows:100 - Select Operator [SEL_319] (rows=241454 width=658) + Select Operator [SEL_319] (rows=301730 width=658) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_110] - Select Operator [SEL_109] (rows=241454 width=658) + Select Operator [SEL_109] (rows=301730 width=658) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_278] (rows=241454 width=546) + Merge Join Operator [MERGEJOIN_278] (rows=301730 width=546) Conds:RS_106._col6, _col7, _col8, _col9, _col14=RS_306._col0, _col1, _col2, _col3, _col5(Inner),Output:["_col4","_col6","_col10","_col11","_col12","_col13","_col19"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_306] PartitionCols:_col0, _col1, _col2, _col3, _col5 - Select Operator [SEL_304] (rows=162257387 width=485) + Select Operator [SEL_304] (rows=1810380 width=485) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_302] (rows=162257387 width=489) + Filter Operator [FIL_302] (rows=1810380 width=489) predicate:rank_window_0 is not null - PTF Operator [PTF_300] (rows=162257387 width=489) + PTF Operator [PTF_300] (rows=1810380 width=489) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS LAST, _col3 ASC NULLS LAST","partition by:":"_col1, _col0, _col4, _col5"}] - Select Operator [SEL_299] (rows=162257387 width=489) + Select Operator [SEL_299] (rows=1810380 width=489) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_297] PartitionCols:_col1, _col0, _col4, _col5 - Group By Operator [GBY_296] (rows=162257387 width=489) + Group By Operator [GBY_296] (rows=1810380 width=489) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_93] @@ -223,41 +223,41 @@ Stage-0 <-Reducer 9 [ONE_TO_ONE_EDGE] FORWARD [RS_106] PartitionCols:_col6, _col7, _col8, _col9, _col14 - Merge Join Operator [MERGEJOIN_277] (rows=241454 width=717) + Merge Join Operator [MERGEJOIN_277] (rows=301730 width=717) Conds:RS_307._col0, _col1, _col2, _col3, _col5=RS_318._col0, _col1, _col2, _col3, _col8(Inner),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_307] PartitionCols:_col0, _col1, _col2, _col3, _col5 - Select Operator [SEL_305] (rows=162257387 width=485) + Select Operator [SEL_305] (rows=1810380 width=485) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_303] (rows=162257387 width=489) + Filter Operator [FIL_303] (rows=1810380 width=489) predicate:rank_window_0 is not null - PTF Operator [PTF_301] (rows=162257387 width=489) + PTF Operator [PTF_301] (rows=1810380 width=489) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS LAST, _col3 ASC NULLS LAST","partition by:":"_col1, _col0, _col4, _col5"}] Please refer to the previous Select Operator [SEL_299] <-Reducer 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_318] PartitionCols:_col0, _col1, _col2, _col3, _col8 - Select Operator [SEL_317] (rows=241454 width=605) + Select Operator [SEL_317] (rows=301730 width=605) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_316] (rows=241454 width=605) + Filter Operator [FIL_316] (rows=301730 width=605) predicate:CASE WHEN ((_col0 > 0)) THEN (((abs((_col7 - _col0)) / _col0) > 0.1)) ELSE (false) END - Select Operator [SEL_315] (rows=482909 width=601) + Select Operator [SEL_315] (rows=603460 width=601) Output:["rank_window_1","_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_314] (rows=482909 width=601) + Filter Operator [FIL_314] (rows=603460 width=601) predicate:((_col0 > 0) and rank_window_1 is not null and (_col3 = 2000)) - PTF Operator [PTF_313] (rows=162257387 width=601) + PTF Operator [PTF_313] (rows=1810380 width=601) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col3 ASC NULLS LAST, _col4 ASC NULLS LAST","partition by:":"_col2, _col1, _col5, _col6"}] - Select Operator [SEL_312] (rows=162257387 width=601) + Select Operator [SEL_312] (rows=1810380 width=601) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_311] PartitionCols:_col1, _col0, _col4, _col5 - Select Operator [SEL_310] (rows=162257387 width=489) + Select Operator [SEL_310] (rows=1810380 width=489) Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_309] (rows=162257387 width=489) + PTF Operator [PTF_309] (rows=1810380 width=489) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST, _col0 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST, _col2 ASC NULLS FIRST","partition by:":"_col1, _col0, _col4, _col5, _col2"}] - Select Operator [SEL_308] (rows=162257387 width=489) + Select Operator [SEL_308] (rows=1810380 width=489) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_298] diff --git a/ql/src/test/results/clientpositive/perf/tez/query48.q.out b/ql/src/test/results/clientpositive/perf/tez/query48.q.out index c232f1713a..a44ffda9bf 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query48.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query48.q.out @@ -163,7 +163,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_30] Group By Operator [GBY_29] (rows=1 width=8) Output:["_col0"],aggregations:["sum(_col4)"] - Merge Join Operator [MERGEJOIN_96] (rows=170127 width=0) + Merge Join Operator [MERGEJOIN_96] (rows=613581 width=0) Conds:RS_25._col3=RS_116._col0(Inner),Output:["_col4"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_116] @@ -177,9 +177,9 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col3 - Filter Operator [FIL_24] (rows=170127 width=24) + Filter Operator [FIL_24] (rows=613581 width=24) predicate:((_col11 and _col5) or (_col12 and _col6) or (_col13 and _col7)) - Merge Join Operator [MERGEJOIN_95] (rows=226838 width=24) + Merge Join Operator [MERGEJOIN_95] (rows=818111 width=24) Conds:RS_21._col2=RS_113._col0(Inner),Output:["_col3","_col4","_col5","_col6","_col7","_col11","_col12","_col13"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_113] @@ -193,7 +193,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_94] (rows=2570826 width=12) + Merge Join Operator [MERGEJOIN_94] (rows=9271916 width=14) Conds:RS_18._col1=RS_110._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_110] diff --git a/ql/src/test/results/clientpositive/perf/tez/query57.q.out b/ql/src/test/results/clientpositive/perf/tez/query57.q.out index 95792263f2..95dd5840a6 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query57.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query57.q.out @@ -126,29 +126,29 @@ Stage-0 File Output Operator [FS_321] Limit [LIM_320] (rows=100 width=758) Number of rows:100 - Select Operator [SEL_319] (rows=130121 width=758) + Select Operator [SEL_319] (rows=397735 width=758) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_110] - Select Operator [SEL_109] (rows=130121 width=758) + Select Operator [SEL_109] (rows=397735 width=758) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_278] (rows=130121 width=646) + Merge Join Operator [MERGEJOIN_278] (rows=397735 width=646) Conds:RS_106._col5, _col6, _col12, _col7=RS_306._col0, _col1, _col4, _col2(Inner),Output:["_col3","_col5","_col6","_col8","_col9","_col10","_col11","_col16"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_306] PartitionCols:_col0, _col1, _col4, _col2 - Select Operator [SEL_304] (rows=87441185 width=404) + Select Operator [SEL_304] (rows=2386410 width=404) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_302] (rows=87441185 width=408) + Filter Operator [FIL_302] (rows=2386410 width=408) predicate:rank_window_0 is not null - PTF Operator [PTF_300] (rows=87441185 width=408) + PTF Operator [PTF_300] (rows=2386410 width=408) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS LAST, _col3 ASC NULLS LAST","partition by:":"_col1, _col0, _col4"}] - Select Operator [SEL_299] (rows=87441185 width=408) + Select Operator [SEL_299] (rows=2386410 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_297] PartitionCols:_col1, _col0, _col4 - Group By Operator [GBY_296] (rows=87441185 width=408) + Group By Operator [GBY_296] (rows=2386410 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_93] @@ -217,41 +217,41 @@ Stage-0 <-Reducer 9 [ONE_TO_ONE_EDGE] FORWARD [RS_106] PartitionCols:_col5, _col6, _col12, _col7 - Merge Join Operator [MERGEJOIN_277] (rows=130121 width=636) + Merge Join Operator [MERGEJOIN_277] (rows=397735 width=636) Conds:RS_307._col0, _col1, _col4, _col2=RS_318._col0, _col1, _col7, _col2(Inner),Output:["_col3","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_307] PartitionCols:_col0, _col1, _col4, _col2 - Select Operator [SEL_305] (rows=87441185 width=404) + Select Operator [SEL_305] (rows=2386410 width=404) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_303] (rows=87441185 width=408) + Filter Operator [FIL_303] (rows=2386410 width=408) predicate:rank_window_0 is not null - PTF Operator [PTF_301] (rows=87441185 width=408) + PTF Operator [PTF_301] (rows=2386410 width=408) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS LAST, _col3 ASC NULLS LAST","partition by:":"_col1, _col0, _col4"}] Please refer to the previous Select Operator [SEL_299] <-Reducer 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_318] PartitionCols:_col0, _col1, _col7, _col2 - Select Operator [SEL_317] (rows=130121 width=524) + Select Operator [SEL_317] (rows=397735 width=524) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_316] (rows=130121 width=524) + Filter Operator [FIL_316] (rows=397735 width=524) predicate:CASE WHEN ((_col0 > 0)) THEN (((abs((_col6 - _col0)) / _col0) > 0.1)) ELSE (false) END - Select Operator [SEL_315] (rows=260242 width=520) + Select Operator [SEL_315] (rows=795470 width=520) Output:["rank_window_1","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_314] (rows=260242 width=520) + Filter Operator [FIL_314] (rows=795470 width=520) predicate:((_col0 > 0) and rank_window_1 is not null and (_col3 = 2000)) - PTF Operator [PTF_313] (rows=87441185 width=520) + PTF Operator [PTF_313] (rows=2386410 width=520) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col3 ASC NULLS LAST, _col4 ASC NULLS LAST","partition by:":"_col2, _col1, _col5"}] - Select Operator [SEL_312] (rows=87441185 width=520) + Select Operator [SEL_312] (rows=2386410 width=520) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_311] PartitionCols:_col1, _col0, _col4 - Select Operator [SEL_310] (rows=87441185 width=408) + Select Operator [SEL_310] (rows=2386410 width=408) Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5"] - PTF Operator [PTF_309] (rows=87441185 width=408) + PTF Operator [PTF_309] (rows=2386410 width=408) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST, _col0 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col2 ASC NULLS FIRST","partition by:":"_col1, _col0, _col4, _col2"}] - Select Operator [SEL_308] (rows=87441185 width=408) + Select Operator [SEL_308] (rows=2386410 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_298] diff --git a/ql/src/test/results/clientpositive/perf/tez/query59.q.out b/ql/src/test/results/clientpositive/perf/tez/query59.q.out index 3c3cd2dc78..566f888d40 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query59.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query59.q.out @@ -114,20 +114,20 @@ Stage-0 File Output Operator [FS_211] Limit [LIM_210] (rows=100 width=976) Number of rows:100 - Select Operator [SEL_209] (rows=1012347 width=976) + Select Operator [SEL_209] (rows=862591 width=976) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_59] - Select Operator [SEL_58] (rows=1012347 width=976) + Select Operator [SEL_58] (rows=862591 width=976) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Merge Join Operator [MERGEJOIN_183] (rows=1012347 width=1648) + Merge Join Operator [MERGEJOIN_183] (rows=862591 width=1648) Conds:RS_55._col11, _col0=RS_56._col1, (_col0 - 52)(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col11","_col12","_col15","_col16","_col17","_col18","_col19","_col20"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col1, (_col0 - 52) - Select Operator [SEL_48] (rows=28847 width=776) + Select Operator [SEL_48] (rows=26628 width=776) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_182] (rows=28847 width=776) + Merge Join Operator [MERGEJOIN_182] (rows=26628 width=776) Conds:RS_45._col1=RS_208._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col10"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_208] @@ -141,7 +141,7 @@ Stage-0 <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_45] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_181] (rows=28847 width=676) + Merge Join Operator [MERGEJOIN_181] (rows=26628 width=676) Conds:RS_205._col0=RS_200._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_200] @@ -155,7 +155,7 @@ Stage-0 <-Reducer 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_205] PartitionCols:_col0 - Group By Operator [GBY_204] (rows=1196832 width=679) + Group By Operator [GBY_204] (rows=1104768 width=679) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)"],keys:KEY._col0, KEY._col1 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_33] @@ -187,7 +187,7 @@ Stage-0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col11, _col0 - Merge Join Operator [MERGEJOIN_179] (rows=28847 width=976) + Merge Join Operator [MERGEJOIN_179] (rows=26628 width=976) Conds:RS_52._col1=RS_203._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col11","_col12"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_203] @@ -201,7 +201,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_52] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_178] (rows=28847 width=788) + Merge Join Operator [MERGEJOIN_178] (rows=26628 width=788) Conds:RS_194._col0=RS_199._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_199] @@ -214,7 +214,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] vectorized SHUFFLE [RS_194] PartitionCols:_col0 - Group By Operator [GBY_193] (rows=1196832 width=791) + Group By Operator [GBY_193] (rows=1104768 width=791) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] diff --git a/ql/src/test/results/clientpositive/perf/tez/query65.q.out b/ql/src/test/results/clientpositive/perf/tez/query65.q.out index f389c5ed9a..69b12f6947 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query65.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query65.q.out @@ -86,13 +86,13 @@ Stage-0 File Output Operator [FS_172] Limit [LIM_171] (rows=100 width=705) Number of rows:100 - Select Operator [SEL_170] (rows=65392 width=704) + Select Operator [SEL_170] (rows=56354 width=703) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_53] - Select Operator [SEL_52] (rows=65392 width=704) + Select Operator [SEL_52] (rows=56354 width=703) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_139] (rows=65392 width=704) + Merge Join Operator [MERGEJOIN_139] (rows=56354 width=703) Conds:RS_49._col1=RS_169._col0(Inner),Output:["_col2","_col6","_col8","_col9","_col10","_col11"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_169] @@ -106,7 +106,7 @@ Stage-0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_138] (rows=65392 width=204) + Merge Join Operator [MERGEJOIN_138] (rows=56354 width=204) Conds:RS_46._col0=RS_166._col0(Inner),Output:["_col1","_col2","_col6"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_166] @@ -120,21 +120,21 @@ Stage-0 <-Reducer 4 [ONE_TO_ONE_EDGE] FORWARD [RS_46] PartitionCols:_col0 - Filter Operator [FIL_45] (rows=65392 width=231) + Filter Operator [FIL_45] (rows=56354 width=231) predicate:(_col2 <= _col4) - Merge Join Operator [MERGEJOIN_137] (rows=196176 width=231) + Merge Join Operator [MERGEJOIN_137] (rows=169062 width=231) Conds:RS_157._col0=RS_163._col0(Inner),Output:["_col0","_col1","_col2","_col4"] <-Reducer 3 [SIMPLE_EDGE] vectorized SHUFFLE [RS_157] PartitionCols:_col0 - Filter Operator [FIL_156] (rows=184637 width=118) + Filter Operator [FIL_156] (rows=158496 width=118) predicate:_col2 is not null - Group By Operator [GBY_155] (rows=184637 width=118) + Group By Operator [GBY_155] (rows=158496 width=118) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_11] PartitionCols:_col0, _col1 - Group By Operator [GBY_10] (rows=6093021 width=118) + Group By Operator [GBY_10] (rows=5230368 width=118) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1 Merge Join Operator [MERGEJOIN_135] (rows=91197860 width=89) Conds:RS_153._col0=RS_142._col0(Inner),Output:["_col1","_col2","_col3"] @@ -170,20 +170,20 @@ Stage-0 <-Reducer 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_163] PartitionCols:_col0 - Select Operator [SEL_162] (rows=17 width=115) + Select Operator [SEL_162] (rows=16 width=115) Output:["_col0","_col1"] - Filter Operator [FIL_161] (rows=17 width=123) + Filter Operator [FIL_161] (rows=16 width=123) predicate:(_col1 is not null and _col2 is not null) - Group By Operator [GBY_160] (rows=17 width=123) + Group By Operator [GBY_160] (rows=16 width=123) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1 - Select Operator [SEL_159] (rows=184637 width=118) + Select Operator [SEL_159] (rows=173776 width=118) Output:["_col1","_col2"] - Group By Operator [GBY_158] (rows=184637 width=118) + Group By Operator [GBY_158] (rows=173776 width=118) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col0 - Group By Operator [GBY_26] (rows=6093021 width=118) + Group By Operator [GBY_26] (rows=5734608 width=118) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1 Merge Join Operator [MERGEJOIN_136] (rows=91197860 width=89) Conds:RS_154._col0=RS_144._col0(Inner),Output:["_col1","_col2","_col3"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query69.q.out b/ql/src/test/results/clientpositive/perf/tez/query69.q.out index 2a9bc81f43..abe5e61d29 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query69.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query69.q.out @@ -164,17 +164,17 @@ Stage-0 Output:["_col0","_col6","_col7","_col8","_col9","_col10"] Filter Operator [FIL_47] (rows=1 width=367) predicate:_col12 is null - Merge Join Operator [MERGEJOIN_183] (rows=33 width=367) + Merge Join Operator [MERGEJOIN_183] (rows=30 width=367) Conds:RS_44._col0=RS_214._col0(Left Outer),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col12"] <-Reducer 4 [ONE_TO_ONE_EDGE] FORWARD [RS_44] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_182] (rows=6841 width=363) + Merge Join Operator [MERGEJOIN_182] (rows=6239 width=363) Conds:RS_41._col0=RS_42._col0(Left Semi),Output:["_col0","_col6","_col7","_col8","_col9","_col10"] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0 - Group By Operator [GBY_40] (rows=116289 width=1) + Group By Operator [GBY_40] (rows=106060 width=1) Output:["_col0"],keys:_col0 Select Operator [SEL_18] (rows=43153353 width=1) Output:["_col0"] @@ -249,14 +249,14 @@ Stage-0 <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_214] PartitionCols:_col0 - Select Operator [SEL_213] (rows=116289 width=7) + Select Operator [SEL_213] (rows=116231 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_212] (rows=116289 width=3) + Group By Operator [GBY_212] (rows=116231 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0 - Group By Operator [GBY_29] (rows=116289 width=3) + Group By Operator [GBY_29] (rows=116231 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_180] (rows=11823304 width=3) Conds:RS_211._col0=RS_198._col0(Inner),Output:["_col1"] @@ -281,20 +281,20 @@ Stage-0 FORWARD [RS_153] Group By Operator [GBY_152] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_151] (rows=6841 width=4) + Select Operator [SEL_151] (rows=6239 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_182] <-Reducer 20 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_222] PartitionCols:_col0 - Select Operator [SEL_221] (rows=115467 width=7) + Select Operator [SEL_221] (rows=114314 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_220] (rows=115467 width=3) + Group By Operator [GBY_220] (rows=114314 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_60] PartitionCols:_col0 - Group By Operator [GBY_59] (rows=115467 width=3) + Group By Operator [GBY_59] (rows=114314 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_181] (rows=23255411 width=3) Conds:RS_219._col0=RS_199._col0(Inner),Output:["_col1"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query7.q.out b/ql/src/test/results/clientpositive/perf/tez/query7.q.out index b8e0ce7b7d..8638ea0e99 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query7.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query7.q.out @@ -83,9 +83,9 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_28] (rows=462000 width=476) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col12 - Top N Key Operator [TNK_55] (rows=1441769 width=100) + Top N Key Operator [TNK_55] (rows=1655321 width=100) keys:_col12,sort order:+,top n:100 - Merge Join Operator [MERGEJOIN_99] (rows=1441769 width=100) + Merge Join Operator [MERGEJOIN_99] (rows=1655321 width=100) Conds:RS_24._col1=RS_119._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col12"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_119] @@ -99,7 +99,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_98] (rows=1441769 width=4) + Merge Join Operator [MERGEJOIN_98] (rows=1655321 width=4) Conds:RS_21._col3=RS_116._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_116] @@ -113,7 +113,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_97] (rows=1441769 width=4) + Merge Join Operator [MERGEJOIN_97] (rows=1655321 width=4) Conds:RS_18._col0=RS_113._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_113] @@ -127,7 +127,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_96] (rows=4037893 width=4) + Merge Join Operator [MERGEJOIN_96] (rows=4635977 width=4) Conds:RS_110._col2=RS_102._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_102] diff --git a/ql/src/test/results/clientpositive/perf/tez/query72.q.out b/ql/src/test/results/clientpositive/perf/tez/query72.q.out index 2cc0b395d8..f90f6d77ef 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query72.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query72.q.out @@ -104,20 +104,20 @@ Stage-0 File Output Operator [FS_295] Limit [LIM_294] (rows=100 width=312) Number of rows:100 - Select Operator [SEL_293] (rows=384313734 width=312) + Select Operator [SEL_293] (rows=78286131 width=312) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_292] - Group By Operator [GBY_291] (rows=384313734 width=312) + Group By Operator [GBY_291] (rows=78286131 width=312) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_70] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_69] (rows=576990095 width=312) + Group By Operator [GBY_69] (rows=622787354 width=312) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(_col3)","count(_col4)","count()"],keys:_col0, _col1, _col2 - Select Operator [SEL_67] (rows=1488051228 width=292) + Select Operator [SEL_67] (rows=1606161864 width=292) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_252] (rows=1488051228 width=292) + Merge Join Operator [MERGEJOIN_252] (rows=1606161864 width=292) Conds:RS_64._col4, _col6=RS_290._col0, _col1(Left Outer),Output:["_col13","_col15","_col19","_col25"] <-Map 24 [SIMPLE_EDGE] vectorized SHUFFLE [RS_290] @@ -131,9 +131,9 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_64] PartitionCols:_col4, _col6 - Select Operator [SEL_60] (rows=576990095 width=300) + Select Operator [SEL_60] (rows=622787354 width=300) Output:["_col4","_col6","_col13","_col15","_col19","_col25"] - Merge Join Operator [MERGEJOIN_251] (rows=576990095 width=300) + Merge Join Operator [MERGEJOIN_251] (rows=622787354 width=300) Conds:RS_57._col0, _col19=RS_287._col0, _col1(Inner),Output:["_col5","_col9","_col14","_col16","_col19","_col23"] <-Map 23 [SIMPLE_EDGE] vectorized SHUFFLE [RS_287] @@ -147,18 +147,18 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_57] PartitionCols:_col0, _col19 - Filter Operator [FIL_56] (rows=516036043 width=311) + Filter Operator [FIL_56] (rows=556995215 width=311) predicate:(_col3 < _col17) - Merge Join Operator [MERGEJOIN_250] (rows=1548108131 width=311) + Merge Join Operator [MERGEJOIN_250] (rows=1670985646 width=311) Conds:RS_53._col1=RS_54._col8(Inner),Output:["_col0","_col3","_col5","_col9","_col14","_col16","_col17","_col19","_col23"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_54] PartitionCols:_col8 - Select Operator [SEL_46] (rows=2712713 width=219) + Select Operator [SEL_46] (rows=2781538 width=219) Output:["_col3","_col8","_col10","_col11","_col13","_col17"] - Filter Operator [FIL_45] (rows=2712713 width=219) + Filter Operator [FIL_45] (rows=2781538 width=219) predicate:(_col17 > _col10) - Merge Join Operator [MERGEJOIN_249] (rows=8138139 width=219) + Merge Join Operator [MERGEJOIN_249] (rows=8344616 width=219) Conds:RS_42._col1=RS_284._col0(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col13","_col15","_col17"] <-Map 22 [SIMPLE_EDGE] vectorized SHUFFLE [RS_284] @@ -172,7 +172,7 @@ Stage-0 <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_248] (rows=8138139 width=214) + Merge Join Operator [MERGEJOIN_248] (rows=8344616 width=214) Conds:RS_39._col4=RS_281._col0(Inner),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col13","_col15"] <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_281] @@ -186,7 +186,7 @@ Stage-0 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_39] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_247] (rows=8138139 width=30) + Merge Join Operator [MERGEJOIN_247] (rows=8344616 width=30) Conds:RS_36._col5=RS_278._col0(Left Outer),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col13"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_278] @@ -200,7 +200,7 @@ Stage-0 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_36] PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_246] (rows=8138139 width=29) + Merge Join Operator [MERGEJOIN_246] (rows=8344616 width=29) Conds:RS_33._col3=RS_275._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col9","_col10"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_275] @@ -214,7 +214,7 @@ Stage-0 <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_33] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_245] (rows=40690691 width=35) + Merge Join Operator [MERGEJOIN_245] (rows=41723078 width=35) Conds:RS_30._col2=RS_272._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col9","_col10"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_272] diff --git a/ql/src/test/results/clientpositive/perf/tez/query75.q.out b/ql/src/test/results/clientpositive/perf/tez/query75.q.out index aa97bdcf8c..4b923a09f3 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query75.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query75.q.out @@ -204,20 +204,20 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] Limit [LIM_616] (rows=100 width=152) Number of rows:100 - Select Operator [SEL_615] (rows=3422897230256 width=151) + Select Operator [SEL_615] (rows=7853634 width=152) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_175] - Select Operator [SEL_174] (rows=3422897230256 width=151) + Select Operator [SEL_174] (rows=7853634 width=152) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_173] (rows=3422897230256 width=255) + Filter Operator [FIL_173] (rows=7853634 width=256) predicate:((CAST( _col10 AS decimal(17,2)) / CAST( _col4 AS decimal(17,2))) < 0.9) - Merge Join Operator [MERGEJOIN_518] (rows=10268691690770 width=255) + Merge Join Operator [MERGEJOIN_518] (rows=23560904 width=256) Conds:RS_611._col0, _col1, _col2, _col3=RS_614._col0, _col1, _col2, _col3(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col10","_col11"] <-Reducer 27 [SIMPLE_EDGE] vectorized SHUFFLE [RS_614] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_613] (rows=84235776 width=135) + Group By Operator [GBY_613] (rows=40320 width=136) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 Group By Operator [GBY_612] (rows=736356923 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 @@ -419,7 +419,7 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_611] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_610] (rows=84235776 width=135) + Group By Operator [GBY_610] (rows=40320 width=136) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 Group By Operator [GBY_609] (rows=736356923 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 diff --git a/ql/src/test/results/clientpositive/perf/tez/query77.q.out b/ql/src/test/results/clientpositive/perf/tez/query77.q.out index b3086e93ed..6fb5cbb6f9 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query77.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query77.q.out @@ -268,23 +268,23 @@ Stage-0 Stage-1 Reducer 8 vectorized File Output Operator [FS_367] - Limit [LIM_366] (rows=52 width=439) + Limit [LIM_366] (rows=63 width=439) Number of rows:100 - Select Operator [SEL_365] (rows=52 width=439) + Select Operator [SEL_365] (rows=63 width=439) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_364] - Select Operator [SEL_363] (rows=52 width=439) + Select Operator [SEL_363] (rows=63 width=439) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_362] (rows=52 width=447) + Group By Operator [GBY_362] (rows=63 width=447) Output:["_col0","_col1","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 6 [SIMPLE_EDGE] <-Reducer 16 [CONTAINS] Reduce Output Operator [RS_322] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_321] (rows=52 width=447) + Group By Operator [GBY_321] (rows=63 width=447) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_320] (rows=35 width=435) + Top N Key Operator [TNK_320] (rows=56 width=435) keys:_col0, _col1, 0L,sort order:+++,top n:100 Select Operator [SEL_318] (rows=2 width=439) Output:["_col0","_col1","_col2","_col3","_col4"] @@ -356,13 +356,13 @@ Stage-0 <-Reducer 23 [CONTAINS] Reduce Output Operator [RS_328] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_327] (rows=52 width=447) + Group By Operator [GBY_327] (rows=63 width=447) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_326] (rows=35 width=435) + Top N Key Operator [TNK_326] (rows=56 width=435) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_324] (rows=23 width=435) + Select Operator [SEL_324] (rows=44 width=435) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_323] (rows=23 width=452) + Merge Join Operator [MERGEJOIN_323] (rows=44 width=340) Conds:RS_390._col0=RS_395._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"] <-Reducer 22 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_390] @@ -417,12 +417,12 @@ Stage-0 <-Reducer 27 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_395] PartitionCols:_col0 - Group By Operator [GBY_394] (rows=23 width=228) + Group By Operator [GBY_394] (rows=21 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_114] PartitionCols:_col0 - Group By Operator [GBY_113] (rows=23 width=228) + Group By Operator [GBY_113] (rows=21 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col5 Merge Join Operator [MERGEJOIN_307] (rows=1458758 width=137) Conds:RS_109._col1=RS_388._col0(Inner),Output:["_col2","_col3","_col5"] @@ -451,9 +451,9 @@ Stage-0 <-Reducer 5 [CONTAINS] Reduce Output Operator [RS_316] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_315] (rows=52 width=447) + Group By Operator [GBY_315] (rows=63 width=447) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_314] (rows=35 width=435) + Top N Key Operator [TNK_314] (rows=56 width=435) keys:_col0, _col1, 0L,sort order:+++,top n:100 Select Operator [SEL_312] (rows=10 width=437) Output:["_col0","_col1","_col2","_col3","_col4"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query78.q.out b/ql/src/test/results/clientpositive/perf/tez/query78.q.out index 6ff50df3e6..85cebfd8fc 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query78.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query78.q.out @@ -158,13 +158,13 @@ Stage-0 File Output Operator [FS_276] Limit [LIM_275] (rows=100 width=484) Number of rows:100 - Select Operator [SEL_274] (rows=1831943309424 width=483) + Select Operator [SEL_274] (rows=1864495018431 width=483) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_76] - Select Operator [SEL_75] (rows=1831943309424 width=719) + Select Operator [SEL_75] (rows=1864495018431 width=719) Output:["_col0","_col1","_col2","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - Merge Join Operator [MERGEJOIN_223] (rows=1831943309424 width=715) + Merge Join Operator [MERGEJOIN_223] (rows=1864495018431 width=715) Conds:RS_72._col1=RS_273._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col11","_col12","_col13","_col14","_col15"] <-Reducer 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_273] @@ -234,7 +234,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_72] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_222] (rows=9160455599 width=471) + Merge Join Operator [MERGEJOIN_222] (rows=9165006707 width=471) Conds:RS_248._col1, _col0=RS_260._col1, _col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col7","_col8","_col9"] <-Reducer 3 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_248] diff --git a/ql/src/test/results/clientpositive/perf/tez/query81.q.out b/ql/src/test/results/clientpositive/perf/tez/query81.q.out index fd239220ed..52d1106cd3 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query81.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query81.q.out @@ -88,26 +88,26 @@ Stage-0 Stage-1 Reducer 4 vectorized File Output Operator [FS_215] - Select Operator [SEL_214] (rows=100 width=1506) + Select Operator [SEL_214] (rows=100 width=1504) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] - Limit [LIM_213] (rows=100 width=1420) + Limit [LIM_213] (rows=100 width=1418) Number of rows:100 - Select Operator [SEL_212] (rows=1577696 width=1418) + Select Operator [SEL_212] (rows=1515166 width=1418) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_66] - Select Operator [SEL_65] (rows=1577696 width=1418) + Select Operator [SEL_65] (rows=1515166 width=1418) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] - Merge Join Operator [MERGEJOIN_181] (rows=1577696 width=1418) + Merge Join Operator [MERGEJOIN_181] (rows=1515166 width=1418) Conds:RS_62._col0=RS_63._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col19"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col0 - Select Operator [SEL_58] (rows=1609248 width=227) + Select Operator [SEL_58] (rows=1545467 width=227) Output:["_col0","_col2"] - Filter Operator [FIL_57] (rows=1609248 width=227) + Filter Operator [FIL_57] (rows=1545467 width=227) predicate:(_col2 > _col3) - Merge Join Operator [MERGEJOIN_180] (rows=4827746 width=227) + Merge Join Operator [MERGEJOIN_180] (rows=4636401 width=227) Conds:RS_205._col1=RS_211._col1(Inner),Output:["_col0","_col2","_col3"] <-Reducer 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_211] @@ -164,11 +164,11 @@ Stage-0 <-Reducer 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_205] PartitionCols:_col1 - Filter Operator [FIL_204] (rows=4827746 width=201) + Filter Operator [FIL_204] (rows=4636401 width=201) predicate:_col2 is not null - Select Operator [SEL_203] (rows=4827746 width=201) + Select Operator [SEL_203] (rows=4636401 width=201) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_202] (rows=4827746 width=201) + Group By Operator [GBY_202] (rows=4636401 width=201) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_23] diff --git a/ql/src/test/results/clientpositive/perf/tez/query84.q.out b/ql/src/test/results/clientpositive/perf/tez/query84.q.out index 35cf670285..ef41408f19 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query84.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query84.q.out @@ -70,13 +70,13 @@ Stage-0 File Output Operator [FS_141] Limit [LIM_140] (rows=100 width=384) Number of rows:100 - Select Operator [SEL_139] (rows=255285 width=384) + Select Operator [SEL_139] (rows=264534 width=384) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_36] - Select Operator [SEL_35] (rows=255285 width=384) + Select Operator [SEL_35] (rows=264534 width=384) Output:["_col1","_col2"] - Merge Join Operator [MERGEJOIN_120] (rows=255285 width=284) + Merge Join Operator [MERGEJOIN_120] (rows=264534 width=284) Conds:RS_32._col1=RS_33._col1(Inner),Output:["_col2","_col6"] <-Reducer 2 [ONE_TO_ONE_EDGE] FORWARD [RS_32] diff --git a/ql/src/test/results/clientpositive/perf/tez/query89.q.out b/ql/src/test/results/clientpositive/perf/tez/query89.q.out index 6cd118365c..b9fdaab398 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query89.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query89.q.out @@ -82,29 +82,29 @@ Stage-0 File Output Operator [FS_112] Limit [LIM_111] (rows=100 width=801) Number of rows:100 - Select Operator [SEL_110] (rows=4804228 width=801) + Select Operator [SEL_110] (rows=32461 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_109] - Select Operator [SEL_108] (rows=4804228 width=801) + Select Operator [SEL_108] (rows=32461 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_107] (rows=4804228 width=689) + Filter Operator [FIL_107] (rows=32461 width=689) predicate:CASE WHEN ((avg_window_0 <> 0)) THEN (((abs((_col6 - avg_window_0)) / avg_window_0) > 0.1)) ELSE (false) END - Select Operator [SEL_106] (rows=9608456 width=577) + Select Operator [SEL_106] (rows=64922 width=577) Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_105] (rows=9608456 width=577) + PTF Operator [PTF_105] (rows=64922 width=577) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS FIRST, _col0 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST","partition by:":"_col2, _col0, _col4, _col5"}] - Select Operator [SEL_104] (rows=9608456 width=577) + Select Operator [SEL_104] (rows=64922 width=577) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_103] PartitionCols:_col2, _col0, _col4, _col5 - Group By Operator [GBY_102] (rows=9608456 width=577) + Group By Operator [GBY_102] (rows=64922 width=577) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_23] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_22] (rows=27308180 width=577) + Group By Operator [GBY_22] (rows=3375944 width=577) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)"],keys:_col5, _col6, _col7, _col9, _col11, _col12 Merge Join Operator [MERGEJOIN_84] (rows=27308180 width=480) Conds:RS_18._col2=RS_101._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col9","_col11","_col12"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query91.q.out b/ql/src/test/results/clientpositive/perf/tez/query91.q.out index 6bd534b21b..a92b7417a2 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query91.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query91.q.out @@ -92,18 +92,18 @@ Stage-0 Stage-1 Reducer 7 vectorized File Output Operator [FS_170] - Select Operator [SEL_169] (rows=9504 width=406) + Select Operator [SEL_169] (rows=2376 width=406) Output:["_col0","_col1","_col2","_col3"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_168] - Select Operator [SEL_167] (rows=9504 width=518) + Select Operator [SEL_167] (rows=2376 width=518) Output:["_col0","_col1","_col2","_col4"] - Group By Operator [GBY_166] (rows=9504 width=585) + Group By Operator [GBY_166] (rows=2376 width=585) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_41] (rows=9504 width=585) + Group By Operator [GBY_41] (rows=2376 width=585) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col11)"],keys:_col5, _col6, _col14, _col15, _col16 Merge Join Operator [MERGEJOIN_144] (rows=231957 width=473) Conds:RS_37._col2=RS_165._col0(Inner),Output:["_col5","_col6","_col11","_col14","_col15","_col16"] @@ -161,7 +161,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_140] (rows=213205 width=183) + Merge Join Operator [MERGEJOIN_140] (rows=228944 width=183) Conds:RS_31._col3=RS_153._col0(Inner),Output:["_col0","_col2","_col5","_col6"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_153] @@ -175,7 +175,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_139] (rows=1066023 width=187) + Merge Join Operator [MERGEJOIN_139] (rows=1144719 width=187) Conds:RS_147._col1=RS_150._col0(Inner),Output:["_col0","_col2","_col3","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_147] diff --git a/ql/src/test/results/clientpositive/ppd_gby_join.q.out b/ql/src/test/results/clientpositive/ppd_gby_join.q.out index eba3c9b342..20740772ee 100644 --- a/ql/src/test/results/clientpositive/ppd_gby_join.q.out +++ b/ql/src/test/results/clientpositive/ppd_gby_join.q.out @@ -71,14 +71,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 56 Data size: 4872 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 1710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -94,7 +94,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 18 Data size: 1710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -103,10 +103,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 1710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 1710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -342,14 +342,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 56 Data size: 4872 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 1710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -365,7 +365,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 18 Data size: 1710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -374,10 +374,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 1710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 1710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join.q.out b/ql/src/test/results/clientpositive/ppd_join.q.out index c45867799f..282924c00d 100644 --- a/ql/src/test/results/clientpositive/ppd_join.q.out +++ b/ql/src/test/results/clientpositive/ppd_join.q.out @@ -69,14 +69,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -597,14 +597,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join2.q.out b/ql/src/test/results/clientpositive/ppd_join2.q.out index cf3457e970..8a7d6f7b5d 100644 --- a/ql/src/test/results/clientpositive/ppd_join2.q.out +++ b/ql/src/test/results/clientpositive/ppd_join2.q.out @@ -77,10 +77,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean) - Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -96,7 +96,7 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: src @@ -122,14 +122,14 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1764,10 +1764,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean) - Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1783,7 +1783,7 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: src @@ -1809,14 +1809,14 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join3.q.out b/ql/src/test/results/clientpositive/ppd_join3.q.out index a7820aa0b5..950ac90d51 100644 --- a/ql/src/test/results/clientpositive/ppd_join3.q.out +++ b/ql/src/test/results/clientpositive/ppd_join3.q.out @@ -75,7 +75,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 7482 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -91,7 +91,7 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 7482 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '12') and (key <> '11') and (key <> '13')) (type: boolean) @@ -117,17 +117,17 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 35775 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 > '10') or (_col1 <> '10')) (type: boolean) - Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 35775 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1817,7 +1817,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 7482 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1833,7 +1833,7 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 7482 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '12') and (key <> '11') and (key <> '13')) (type: boolean) @@ -1859,17 +1859,17 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 35775 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 > '10') or (_col1 <> '10')) (type: boolean) - Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 35775 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_outer_join4.q.out b/ql/src/test/results/clientpositive/ppd_outer_join4.q.out index f0fe2c24f8..7c90cdd352 100644 --- a/ql/src/test/results/clientpositive/ppd_outer_join4.q.out +++ b/ql/src/test/results/clientpositive/ppd_outer_join4.q.out @@ -76,7 +76,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 22790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -92,7 +92,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 22790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: b @@ -119,14 +119,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 55 Data size: 24365 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 55 Data size: 24365 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 24365 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -472,7 +472,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 22790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -488,7 +488,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 86 Data size: 22790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: b @@ -515,14 +515,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 55 Data size: 24365 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 55 Data size: 24365 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 24365 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out index e5e2568e72..24640b5f47 100644 --- a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out @@ -1252,11 +1252,11 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_17] - Select Operator [SEL_16] (rows=30 width=101) + Select Operator [SEL_16] (rows=40 width=101) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_13] (rows=30 width=105) + Filter Operator [FIL_13] (rows=40 width=105) predicate:(((_col1 > 0) or (_col6 >= 0)) and ((_col1 > 0) or _col7) and ((_col1 + _col4) = 2)) - Join Operator [JOIN_12] (rows=60 width=104) + Join Operator [JOIN_12] (rows=81 width=104) Output:["_col1","_col2","_col3","_col4","_col6","_col7"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"},{"":"{\"type\":\"Inner\",\"left\":0,\"right\":2}"}],keys:{"0":"_col0","1":"_col0","2":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_9] @@ -1313,11 +1313,11 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_17] - Select Operator [SEL_16] (rows=30 width=101) + Select Operator [SEL_16] (rows=40 width=101) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_13] (rows=30 width=105) + Filter Operator [FIL_13] (rows=40 width=105) predicate:(((_col1 > 0) or (_col6 >= 0)) and ((_col1 > 0) or _col7) and ((_col1 + _col4) = 2)) - Join Operator [JOIN_12] (rows=60 width=104) + Join Operator [JOIN_12] (rows=81 width=104) Output:["_col1","_col2","_col3","_col4","_col6","_col7"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"},{"":"{\"type\":\"Inner\",\"left\":0,\"right\":2}"}],keys:{"0":"_col0","1":"_col0","2":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_9] @@ -1698,9 +1698,9 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_18] - Select Operator [SEL_17] (rows=10 width=93) + Select Operator [SEL_17] (rows=14 width=93) Output:["_col0","_col1","_col2"] - Join Operator [JOIN_16] (rows=10 width=93) + Join Operator [JOIN_16] (rows=14 width=93) Output:["_col0","_col1","_col2"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"},{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":2}"}],keys:{"0":"_col0","1":"_col0","2":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_13] @@ -2119,7 +2119,7 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_12] - Join Operator [JOIN_10] (rows=83 width=178) + Join Operator [JOIN_10] (rows=131 width=178) Output:["_col0","_col1"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0, _col1","1":"_col0, _col1"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_8] @@ -2175,7 +2175,7 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_12] - Join Operator [JOIN_10] (rows=83 width=178) + Join Operator [JOIN_10] (rows=131 width=178) Output:["_col0","_col1"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0, _col1","1":"_col0, _col1"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_8] diff --git a/ql/src/test/results/clientpositive/subquery_exists.q.out b/ql/src/test/results/clientpositive/subquery_exists.q.out index 658a445d00..9a65531e22 100644 --- a/ql/src/test/results/clientpositive/subquery_exists.q.out +++ b/ql/src/test/results/clientpositive/subquery_exists.q.out @@ -74,10 +74,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out index 462b22dac6..d567dc1d6a 100644 --- a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out +++ b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out @@ -175,10 +175,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -266,10 +266,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out index 7f3ad53bac..ff908245ff 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out @@ -48,11 +48,11 @@ Stage-0 Stage-1 Reducer 3 File Output Operator [FS_12] - Select Operator [SEL_11] (rows=1019/10 width=484) + Select Operator [SEL_11] (rows=2048/10 width=552) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_27] (rows=1019/10 width=484) + Merge Join Operator [MERGEJOIN_27] (rows=2048/10 width=552) Conds:RS_6._col2=RS_7._col2(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -151,7 +151,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_28] (rows=1019/10 width=8) + Merge Join Operator [MERGEJOIN_28] (rows=2048/10 width=8) Conds:RS_6._col0=RS_7._col0(Inner) <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -244,16 +244,16 @@ Stage-0 Stage-1 Reducer 4 File Output Operator [FS_15] - Select Operator [SEL_14] (rows=1019/5 width=10) + Select Operator [SEL_14] (rows=1366/5 width=11) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_13] - Group By Operator [GBY_11] (rows=1019/5 width=10) + Group By Operator [GBY_11] (rows=1366/5 width=11) Output:["_col0","_col1"],aggregations:["count()"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_10] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_30] (rows=1019/10 width=2) + Merge Join Operator [MERGEJOIN_30] (rows=2048/10 width=3) Conds:RS_6._col1=RS_7._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] diff --git a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out index afabf4be5c..d9078b5111 100644 --- a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out @@ -312,7 +312,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 13785 Data size: 110280 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() minReductionHashAggr: 0.99 @@ -434,7 +434,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 13785 Data size: 110280 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -553,7 +553,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18466 Data size: 147728 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21560 Data size: 172480 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() minReductionHashAggr: 0.99 @@ -671,7 +671,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18466 Data size: 147728 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21560 Data size: 172480 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() diff --git a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out index 9ba9a1f684..d3ba4538fe 100644 --- a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out @@ -1383,7 +1383,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Map 1 - Statistics: Num rows: 4 Data size: 700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1393,7 +1393,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1403,7 +1403,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 5 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 114 Data size: 10146 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1412,10 +1412,10 @@ STAGE PLANS: 1 value (type: string) input vertices: 1 Map 6 - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 185 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1609,7 +1609,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Map 1 - Statistics: Num rows: 4 Data size: 700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Map Join Operator condition map: @@ -1620,7 +1620,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Map Join Operator condition map: @@ -1631,7 +1631,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 5 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 114 Data size: 10146 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Map Join Operator condition map: @@ -1641,11 +1641,11 @@ STAGE PLANS: 1 value (type: string) input vertices: 1 Map 6 - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 185 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1721,6 +1721,76 @@ STAGE PLANS: Processor Tree: ListSink +PREHOOK: query: SELECT COUNT(*) +FROM src1 x +JOIN srcpart z1 ON (x.key = z1.key) +JOIN src y1 ON (x.key = y1.key) +JOIN srcpart z2 ON (x.value = z2.value) +JOIN src y2 ON (x.value = y2.value) +WHERE z1.key < 'zzzzzzzz' AND z2.key < 'zzzzzzzzzz' + AND y1.value < 'zzzzzzzz' AND y2.value < 'zzzzzzzzzz' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +PREHOOK: Output: hdfs://### HDFS PATH ### +Status: Failed +Vertex failed, vertexName=Map 2, vertexId=vertex_#ID#, diagnostics=[Task failed, taskId=task_#ID#, diagnostics=[TaskAttempt 0 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: java.lang.OutOfMemoryError: Java heap space +#### A masked pattern was here #### + at com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:108) + at com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:41) + at com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:77) +#### A masked pattern was here #### +], TaskAttempt 1 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: java.lang.OutOfMemoryError: Java heap space +#### A masked pattern was here #### + at com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:108) + at com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:41) + at com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:77) +#### A masked pattern was here #### +], TaskAttempt 2 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: java.lang.OutOfMemoryError: Java heap space +#### A masked pattern was here #### + at com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:108) + at com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:41) + at com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:77) +#### A masked pattern was here #### +], TaskAttempt 3 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: java.lang.OutOfMemoryError: Java heap space +#### A masked pattern was here #### + at com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:108) + at com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:41) + at com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:77) +#### A masked pattern was here #### +]], Vertex did not succeed due to OWN_TASK_FAILURE, failedTasks:1 killedTasks:0, Vertex vertex_#ID# [Map 2] killed/failed due to:OWN_TASK_FAILURE] +Vertex killed, vertexName=Reducer 3, vertexId=vertex_#ID#, diagnostics=[Vertex received Kill while in RUNNING state., Vertex did not succeed due to OTHER_VERTEX_FAILURE, failedTasks:0 killedTasks:1, Vertex vertex_#ID# [Reducer 3] killed/failed due to:OTHER_VERTEX_FAILURE] +DAG did not succeed due to VERTEX_FAILURE. failedVertices:1 killedVertices:1 +FAILED: Execution Error, return code 2 from org.apache.hadoop.hive.ql.exec.tez.TezTask. Vertex failed, vertexName=Map 2, vertexId=vertex_#ID#, diagnostics=[Task failed, taskId=task_#ID#, diagnostics=[TaskAttempt 0 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: java.lang.OutOfMemoryError: Java heap space +#### A masked pattern was here #### + at com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:108) + at com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:41) + at com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:77) +#### A masked pattern was here #### +], TaskAttempt 1 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: java.lang.OutOfMemoryError: Java heap space +#### A masked pattern was here #### + at com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:108) + at com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:41) + at com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:77) +#### A masked pattern was here #### +], TaskAttempt 2 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: java.lang.OutOfMemoryError: Java heap space +#### A masked pattern was here #### + at com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:108) + at com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:41) + at com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:77) +#### A masked pattern was here #### +], TaskAttempt 3 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: java.lang.OutOfMemoryError: Java heap space +#### A masked pattern was here #### + at com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:108) + at com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:41) + at com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:77) +#### A masked pattern was here #### +]], Vertex did not succeed due to OWN_TASK_FAILURE, failedTasks:1 killedTasks:0, Vertex vertex_#ID# [Map 2] killed/failed due to:OWN_TASK_FAILURE]Vertex killed, vertexName=Reducer 3, vertexId=vertex_#ID#, diagnostics=[Vertex received Kill while in RUNNING state., Vertex did not succeed due to OTHER_VERTEX_FAILURE, failedTasks:0 killedTasks:1, Vertex vertex_#ID# [Reducer 3] killed/failed due to:OTHER_VERTEX_FAILURE]DAG did not succeed due to VERTEX_FAILURE. failedVertices:1 killedVertices:1 PREHOOK: query: SELECT COUNT(*) FROM src1 x JOIN srcpart z1 ON (x.key = z1.key) @@ -1755,4 +1825,4 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 POSTHOOK: Output: hdfs://### HDFS PATH ### -18256 +0 diff --git a/ql/src/test/results/clientpositive/vector_outer_join3.q.out b/ql/src/test/results/clientpositive/vector_outer_join3.q.out index f88492df5c..0640aeec75 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join3.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join3.q.out @@ -336,7 +336,7 @@ left outer join small_alltypesorc_a_n1 hd POSTHOOK: type: QUERY POSTHOOK: Input: default@small_alltypesorc_a_n1 #### A masked pattern was here #### -{"CBOPlan":"{\n \"rels\": [\n {\n \"id\": \"0\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveTableScan\",\n \"table\": [\n \"default\",\n \"small_alltypesorc_a_n1\"\n ],\n \"table:alias\": \"c\",\n \"inputs\": [],\n \"rowCount\": 20.0,\n \"avgRowSize\": 26.75,\n \"rowType\": [\n {\n \"type\": \"TINYINT\",\n \"nullable\": true,\n \"name\": \"ctinyint\"\n },\n {\n \"type\": \"SMALLINT\",\n \"nullable\": true,\n \"name\": \"csmallint\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"cint\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"cbigint\"\n },\n {\n \"type\": \"FLOAT\",\n \"nullable\": true,\n \"name\": \"cfloat\"\n },\n {\n \"type\": \"DOUBLE\",\n \"nullable\": true,\n \"name\": \"cdouble\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"cstring1\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"cstring2\"\n },\n {\n \"type\": \"TIMESTAMP\",\n \"nullable\": true,\n \"precision\": 9,\n \"name\": \"ctimestamp1\"\n },\n {\n \"type\": \"TIMESTAMP\",\n \"nullable\": true,\n \"precision\": 9,\n \"name\": \"ctimestamp2\"\n },\n {\n \"type\": \"BOOLEAN\",\n \"nullable\": true,\n \"name\": \"cboolean1\"\n },\n {\n \"type\": \"BOOLEAN\",\n \"nullable\": true,\n \"name\": \"cboolean2\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"BLOCK__OFFSET__INSIDE__FILE\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"INPUT__FILE__NAME\"\n },\n {\n \"fields\": [\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"writeid\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"bucketid\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"rowid\"\n }\n ],\n \"name\": \"ROW__ID\"\n }\n ],\n \"colStats\": [\n {\n \"name\": \"cint\",\n \"ndv\": 8,\n \"minValue\": -738306196,\n \"maxValue\": 626923679\n },\n {\n \"name\": \"cbigint\",\n \"ndv\": 15,\n \"minValue\": -1970551565,\n \"maxValue\": 1086455747\n },\n {\n \"name\": \"cstring1\",\n \"ndv\": 8\n },\n {\n \"name\": \"cstring2\",\n \"ndv\": 15\n },\n {\n \"name\": \"ctinyint\",\n \"ndv\": 2,\n \"minValue\": -64,\n \"maxValue\": -51\n },\n {\n \"name\": \"csmallint\",\n \"ndv\": 6,\n \"minValue\": -15920,\n \"maxValue\": -6907\n },\n {\n \"name\": \"cfloat\",\n \"ndv\": 2,\n \"minValue\": -64.0,\n \"maxValue\": -51.0\n },\n {\n \"name\": \"cdouble\",\n \"ndv\": 6,\n \"minValue\": -15920.0,\n \"maxValue\": -6907.0\n },\n {\n \"name\": \"ctimestamp1\",\n \"ndv\": 0\n },\n {\n \"name\": \"ctimestamp2\",\n \"ndv\": 0\n },\n {\n \"name\": \"cboolean1\",\n \"ndv\": 2\n },\n {\n \"name\": \"cboolean2\",\n \"ndv\": 2\n }\n ]\n },\n {\n \"id\": \"1\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject\",\n \"fields\": [\n \"cint\",\n \"cbigint\",\n \"cstring1\",\n \"cstring2\"\n ],\n \"exprs\": [\n {\n \"input\": 2,\n \"name\": \"$2\"\n },\n {\n \"input\": 3,\n \"name\": \"$3\"\n },\n {\n \"input\": 6,\n \"name\": \"$6\"\n },\n {\n \"input\": 7,\n \"name\": \"$7\"\n }\n ],\n \"rowCount\": 20.0\n },\n {\n \"id\": \"2\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveTableScan\",\n \"table\": [\n \"default\",\n \"small_alltypesorc_a_n1\"\n ],\n \"table:alias\": \"cd\",\n \"inputs\": [],\n \"rowCount\": 20.0,\n \"avgRowSize\": 16.75,\n \"rowType\": [\n {\n \"type\": \"TINYINT\",\n \"nullable\": true,\n \"name\": \"ctinyint\"\n },\n {\n \"type\": \"SMALLINT\",\n \"nullable\": true,\n \"name\": \"csmallint\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"cint\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"cbigint\"\n },\n {\n \"type\": \"FLOAT\",\n \"nullable\": true,\n \"name\": \"cfloat\"\n },\n {\n \"type\": \"DOUBLE\",\n \"nullable\": true,\n \"name\": \"cdouble\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"cstring1\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"cstring2\"\n },\n {\n \"type\": \"TIMESTAMP\",\n \"nullable\": true,\n \"precision\": 9,\n \"name\": \"ctimestamp1\"\n },\n {\n \"type\": \"TIMESTAMP\",\n \"nullable\": true,\n \"precision\": 9,\n \"name\": \"ctimestamp2\"\n },\n {\n \"type\": \"BOOLEAN\",\n \"nullable\": true,\n \"name\": \"cboolean1\"\n },\n {\n \"type\": \"BOOLEAN\",\n \"nullable\": true,\n \"name\": \"cboolean2\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"BLOCK__OFFSET__INSIDE__FILE\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"INPUT__FILE__NAME\"\n },\n {\n \"fields\": [\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"writeid\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"bucketid\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"rowid\"\n }\n ],\n \"name\": \"ROW__ID\"\n }\n ],\n \"colStats\": [\n {\n \"name\": \"cbigint\",\n \"ndv\": 15,\n \"minValue\": -1970551565,\n \"maxValue\": 1086455747\n },\n {\n \"name\": \"cstring2\",\n \"ndv\": 15\n },\n {\n \"name\": \"ctinyint\",\n \"ndv\": 2,\n \"minValue\": -64,\n \"maxValue\": -51\n },\n {\n \"name\": \"csmallint\",\n \"ndv\": 6,\n \"minValue\": -15920,\n \"maxValue\": -6907\n },\n {\n \"name\": \"cint\",\n \"ndv\": 8,\n \"minValue\": -738306196,\n \"maxValue\": 626923679\n },\n {\n \"name\": \"cfloat\",\n \"ndv\": 2,\n \"minValue\": -64.0,\n \"maxValue\": -51.0\n },\n {\n \"name\": \"cdouble\",\n \"ndv\": 6,\n \"minValue\": -15920.0,\n \"maxValue\": -6907.0\n },\n {\n \"name\": \"cstring1\",\n \"ndv\": 8\n },\n {\n \"name\": \"ctimestamp1\",\n \"ndv\": 0\n },\n {\n \"name\": \"ctimestamp2\",\n \"ndv\": 0\n },\n {\n \"name\": \"cboolean1\",\n \"ndv\": 2\n },\n {\n \"name\": \"cboolean2\",\n \"ndv\": 2\n }\n ]\n },\n {\n \"id\": \"3\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveFilter\",\n \"condition\": {\n \"op\": \"AND\",\n \"operands\": [\n {\n \"op\": \"IS NOT NULL\",\n \"operands\": [\n {\n \"input\": 3,\n \"name\": \"$3\"\n }\n ]\n },\n {\n \"op\": \"IS NOT NULL\",\n \"operands\": [\n {\n \"input\": 7,\n \"name\": \"$7\"\n }\n ]\n }\n ]\n },\n \"rowCount\": 11.25\n },\n {\n \"id\": \"4\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject\",\n \"fields\": [\n \"cbigint\",\n \"cstring2\"\n ],\n \"exprs\": [\n {\n \"input\": 3,\n \"name\": \"$3\"\n },\n {\n \"input\": 7,\n \"name\": \"$7\"\n }\n ],\n \"rowCount\": 11.25\n },\n {\n \"id\": \"5\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveJoin\",\n \"condition\": {\n \"op\": \"AND\",\n \"operands\": [\n {\n \"op\": \"=\",\n \"operands\": [\n {\n \"input\": 5,\n \"name\": \"$5\"\n },\n {\n \"input\": 3,\n \"name\": \"$3\"\n }\n ]\n },\n {\n \"op\": \"=\",\n \"operands\": [\n {\n \"input\": 4,\n \"name\": \"$4\"\n },\n {\n \"input\": 1,\n \"name\": \"$1\"\n }\n ]\n }\n ]\n },\n \"joinType\": \"left\",\n \"algorithm\": \"none\",\n \"cost\": \"not available\",\n \"inputs\": [\n \"1\",\n \"4\"\n ],\n \"rowCount\": 20.0\n },\n {\n \"id\": \"6\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveTableScan\",\n \"table\": [\n \"default\",\n \"small_alltypesorc_a_n1\"\n ],\n \"table:alias\": \"hd\",\n \"inputs\": [],\n \"rowCount\": 20.0,\n \"avgRowSize\": 10.0,\n \"rowType\": [\n {\n \"type\": \"TINYINT\",\n \"nullable\": true,\n \"name\": \"ctinyint\"\n },\n {\n \"type\": \"SMALLINT\",\n \"nullable\": true,\n \"name\": \"csmallint\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"cint\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"cbigint\"\n },\n {\n \"type\": \"FLOAT\",\n \"nullable\": true,\n \"name\": \"cfloat\"\n },\n {\n \"type\": \"DOUBLE\",\n \"nullable\": true,\n \"name\": \"cdouble\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"cstring1\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"cstring2\"\n },\n {\n \"type\": \"TIMESTAMP\",\n \"nullable\": true,\n \"precision\": 9,\n \"name\": \"ctimestamp1\"\n },\n {\n \"type\": \"TIMESTAMP\",\n \"nullable\": true,\n \"precision\": 9,\n \"name\": \"ctimestamp2\"\n },\n {\n \"type\": \"BOOLEAN\",\n \"nullable\": true,\n \"name\": \"cboolean1\"\n },\n {\n \"type\": \"BOOLEAN\",\n \"nullable\": true,\n \"name\": \"cboolean2\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"BLOCK__OFFSET__INSIDE__FILE\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"INPUT__FILE__NAME\"\n },\n {\n \"fields\": [\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"writeid\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"bucketid\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"rowid\"\n }\n ],\n \"name\": \"ROW__ID\"\n }\n ],\n \"colStats\": [\n {\n \"name\": \"cint\",\n \"ndv\": 8,\n \"minValue\": -738306196,\n \"maxValue\": 626923679\n },\n {\n \"name\": \"cstring1\",\n \"ndv\": 8\n },\n {\n \"name\": \"ctinyint\",\n \"ndv\": 2,\n \"minValue\": -64,\n \"maxValue\": -51\n },\n {\n \"name\": \"csmallint\",\n \"ndv\": 6,\n \"minValue\": -15920,\n \"maxValue\": -6907\n },\n {\n \"name\": \"cbigint\",\n \"ndv\": 15,\n \"minValue\": -1970551565,\n \"maxValue\": 1086455747\n },\n {\n \"name\": \"cfloat\",\n \"ndv\": 2,\n \"minValue\": -64.0,\n \"maxValue\": -51.0\n },\n {\n \"name\": \"cdouble\",\n \"ndv\": 6,\n \"minValue\": -15920.0,\n \"maxValue\": -6907.0\n },\n {\n \"name\": \"cstring2\",\n \"ndv\": 15\n },\n {\n \"name\": \"ctimestamp1\",\n \"ndv\": 0\n },\n {\n \"name\": \"ctimestamp2\",\n \"ndv\": 0\n },\n {\n \"name\": \"cboolean1\",\n \"ndv\": 2\n },\n {\n \"name\": \"cboolean2\",\n \"ndv\": 2\n }\n ]\n },\n {\n \"id\": \"7\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveFilter\",\n \"condition\": {\n \"op\": \"AND\",\n \"operands\": [\n {\n \"op\": \"IS NOT NULL\",\n \"operands\": [\n {\n \"input\": 2,\n \"name\": \"$2\"\n }\n ]\n },\n {\n \"op\": \"IS NOT NULL\",\n \"operands\": [\n {\n \"input\": 6,\n \"name\": \"$6\"\n }\n ]\n }\n ]\n },\n \"rowCount\": 5.0\n },\n {\n \"id\": \"8\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject\",\n \"fields\": [\n \"cint\",\n \"cstring1\"\n ],\n \"exprs\": [\n {\n \"input\": 2,\n \"name\": \"$2\"\n },\n {\n \"input\": 6,\n \"name\": \"$6\"\n }\n ],\n \"rowCount\": 5.0\n },\n {\n \"id\": \"9\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveJoin\",\n \"condition\": {\n \"op\": \"AND\",\n \"operands\": [\n {\n \"op\": \"=\",\n \"operands\": [\n {\n \"input\": 7,\n \"name\": \"$7\"\n },\n {\n \"input\": 2,\n \"name\": \"$2\"\n }\n ]\n },\n {\n \"op\": \"=\",\n \"operands\": [\n {\n \"input\": 6,\n \"name\": \"$6\"\n },\n {\n \"input\": 0,\n \"name\": \"$0\"\n }\n ]\n }\n ]\n },\n \"joinType\": \"left\",\n \"algorithm\": \"none\",\n \"cost\": \"not available\",\n \"inputs\": [\n \"5\",\n \"8\"\n ],\n \"rowCount\": 20.0\n },\n {\n \"id\": \"10\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveAggregate\",\n \"group\": [],\n \"aggs\": [\n {\n \"agg\": \"count\",\n \"type\": {\n \"type\": \"BIGINT\",\n \"nullable\": true\n },\n \"distinct\": false,\n \"operands\": []\n }\n ],\n \"rowCount\": 1.0\n }\n ]\n}","optimizedSQL":"SELECT COUNT(*) AS `$f0`\nFROM (SELECT `cint`, `cbigint`, `cstring1`, `cstring2`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t`\nLEFT JOIN (SELECT `cbigint`, `cstring2`\nFROM `default`.`small_alltypesorc_a_n1`\nWHERE `cbigint` IS NOT NULL AND `cstring2` IS NOT NULL) AS `t1` ON `t`.`cstring2` = `t1`.`cstring2` AND `t`.`cbigint` = `t1`.`cbigint`\nLEFT JOIN (SELECT `cint`, `cstring1`\nFROM `default`.`small_alltypesorc_a_n1`\nWHERE `cint` IS NOT NULL AND `cstring1` IS NOT NULL) AS `t3` ON `t`.`cstring1` = `t3`.`cstring1` AND `t`.`cint` = `t3`.`cint`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-8":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-8"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-8":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:cd":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:hd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:cd":{"TableScan":{"alias:":"cd","columns:":["cbigint","cstring2"],"database:":"default","filterExpr:":"(cbigint is not null and cstring2 is not null) (type: boolean)","Statistics:":"Num rows: 20 Data size: 1616 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_2","children":{"Filter Operator":{"predicate:":"(cbigint is not null and cstring2 is not null) (type: boolean)","Statistics:":"Num rows: 11 Data size: 909 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"FIL_20","children":{"Select Operator":{"expressions:":"cbigint (type: bigint), cstring2 (type: string)","columnExprMap:":{"_col0":"cbigint","_col1":"cstring2"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 11 Data size: 909 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_4","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: bigint), _col3 (type: string)","1":"_col0 (type: bigint), _col1 (type: string)"},"OperatorId:":"HASHTABLESINK_30"}}}}}}}},"$hdt$_2:hd":{"TableScan":{"alias:":"hd","columns:":["cint","cstring1"],"database:":"default","filterExpr:":"(cint is not null and cstring1 is not null) (type: boolean)","Statistics:":"Num rows: 20 Data size: 1034 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_5","children":{"Filter Operator":{"predicate:":"(cint is not null and cstring1 is not null) (type: boolean)","Statistics:":"Num rows: 5 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"FIL_21","children":{"Select Operator":{"expressions:":"cint (type: int), cstring1 (type: string)","columnExprMap:":{"_col0":"cint","_col1":"cstring1"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 5 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_7","children":{"HashTable Sink Operator":{"keys:":{"0":"_col0 (type: int), _col2 (type: string)","1":"_col0 (type: int), _col1 (type: string)"},"OperatorId:":"HASHTABLESINK_28"}}}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["cint","cbigint","cstring1","cstring2"],"database:":"default","Statistics:":"Num rows: 20 Data size: 2650 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"cint (type: int), cbigint (type: bigint), cstring1 (type: string), cstring2 (type: string)","columnExprMap:":{"_col0":"cint","_col1":"cbigint","_col2":"cstring1","_col3":"cstring2"},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[2, 3, 6, 7]"},"Statistics:":"Num rows: 20 Data size: 2650 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_32","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0","_col2":"0:_col2"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: bigint), _col3 (type: string)","1":"_col0 (type: bigint), _col1 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 3:bigint","col 7:string"],"bigTableValueExpressions:":["col 2:int","col 6:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col2"],"Statistics:":"Num rows: 20 Data size: 1034 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_33","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col0 (type: int), _col2 (type: string)","1":"_col0 (type: int), _col1 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 0:int","col 1:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_34","children":{"Group By Operator":{"aggregations:":["count()"],"Group By Vectorization:":{"aggregators:":["VectorUDAFCountStar(*) -> bigint"],"className:":"VectorGroupByOperator","groupByMode:":"HASH","native:":"false","vectorProcessingMode:":"HASH","projectedOutputColumnNums:":"[0]"},"minReductionHashAggr:":"0.99","mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"GBY_35","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0"},"sort order:":"","Reduce Sink Vectorization:":{"className:":"VectorReduceSinkOperator","native:":"false","nativeConditionsMet:":["hive.vectorized.execution.reducesink.new.enabled IS true","No PTF TopN IS true","No DISTINCT columns IS true","BinarySortableSerDe for keys IS true","LazyBinarySerDe for values IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: bigint)","OperatorId:":"RS_36"}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[2, 3, 6, 7]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[]"}},"Local Work:":{"Map Reduce Local Work":{}},"Reduce Vectorization:":{"enabled:":"false","enableConditionsMet:":["hive.vectorized.execution.reduce.enabled IS true"],"enableConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"GBY_17","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_19"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_37"}}}}}} +{"CBOPlan":"{\n \"rels\": [\n {\n \"id\": \"0\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveTableScan\",\n \"table\": [\n \"default\",\n \"small_alltypesorc_a_n1\"\n ],\n \"table:alias\": \"c\",\n \"inputs\": [],\n \"rowCount\": 20.0,\n \"avgRowSize\": 26.75,\n \"rowType\": [\n {\n \"type\": \"TINYINT\",\n \"nullable\": true,\n \"name\": \"ctinyint\"\n },\n {\n \"type\": \"SMALLINT\",\n \"nullable\": true,\n \"name\": \"csmallint\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"cint\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"cbigint\"\n },\n {\n \"type\": \"FLOAT\",\n \"nullable\": true,\n \"name\": \"cfloat\"\n },\n {\n \"type\": \"DOUBLE\",\n \"nullable\": true,\n \"name\": \"cdouble\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"cstring1\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"cstring2\"\n },\n {\n \"type\": \"TIMESTAMP\",\n \"nullable\": true,\n \"precision\": 9,\n \"name\": \"ctimestamp1\"\n },\n {\n \"type\": \"TIMESTAMP\",\n \"nullable\": true,\n \"precision\": 9,\n \"name\": \"ctimestamp2\"\n },\n {\n \"type\": \"BOOLEAN\",\n \"nullable\": true,\n \"name\": \"cboolean1\"\n },\n {\n \"type\": \"BOOLEAN\",\n \"nullable\": true,\n \"name\": \"cboolean2\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"BLOCK__OFFSET__INSIDE__FILE\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"INPUT__FILE__NAME\"\n },\n {\n \"fields\": [\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"writeid\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"bucketid\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"rowid\"\n }\n ],\n \"name\": \"ROW__ID\"\n }\n ],\n \"colStats\": [\n {\n \"name\": \"cint\",\n \"ndv\": 8,\n \"minValue\": -738306196,\n \"maxValue\": 626923679\n },\n {\n \"name\": \"cbigint\",\n \"ndv\": 15,\n \"minValue\": -1970551565,\n \"maxValue\": 1086455747\n },\n {\n \"name\": \"cstring1\",\n \"ndv\": 8\n },\n {\n \"name\": \"cstring2\",\n \"ndv\": 15\n },\n {\n \"name\": \"ctinyint\",\n \"ndv\": 2,\n \"minValue\": -64,\n \"maxValue\": -51\n },\n {\n \"name\": \"csmallint\",\n \"ndv\": 6,\n \"minValue\": -15920,\n \"maxValue\": -6907\n },\n {\n \"name\": \"cfloat\",\n \"ndv\": 2,\n \"minValue\": -64.0,\n \"maxValue\": -51.0\n },\n {\n \"name\": \"cdouble\",\n \"ndv\": 6,\n \"minValue\": -15920.0,\n \"maxValue\": -6907.0\n },\n {\n \"name\": \"ctimestamp1\",\n \"ndv\": 0\n },\n {\n \"name\": \"ctimestamp2\",\n \"ndv\": 0\n },\n {\n \"name\": \"cboolean1\",\n \"ndv\": 2\n },\n {\n \"name\": \"cboolean2\",\n \"ndv\": 2\n }\n ]\n },\n {\n \"id\": \"1\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject\",\n \"fields\": [\n \"cint\",\n \"cbigint\",\n \"cstring1\",\n \"cstring2\"\n ],\n \"exprs\": [\n {\n \"input\": 2,\n \"name\": \"$2\"\n },\n {\n \"input\": 3,\n \"name\": \"$3\"\n },\n {\n \"input\": 6,\n \"name\": \"$6\"\n },\n {\n \"input\": 7,\n \"name\": \"$7\"\n }\n ],\n \"rowCount\": 20.0\n },\n {\n \"id\": \"2\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveTableScan\",\n \"table\": [\n \"default\",\n \"small_alltypesorc_a_n1\"\n ],\n \"table:alias\": \"cd\",\n \"inputs\": [],\n \"rowCount\": 20.0,\n \"avgRowSize\": 16.75,\n \"rowType\": [\n {\n \"type\": \"TINYINT\",\n \"nullable\": true,\n \"name\": \"ctinyint\"\n },\n {\n \"type\": \"SMALLINT\",\n \"nullable\": true,\n \"name\": \"csmallint\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"cint\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"cbigint\"\n },\n {\n \"type\": \"FLOAT\",\n \"nullable\": true,\n \"name\": \"cfloat\"\n },\n {\n \"type\": \"DOUBLE\",\n \"nullable\": true,\n \"name\": \"cdouble\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"cstring1\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"cstring2\"\n },\n {\n \"type\": \"TIMESTAMP\",\n \"nullable\": true,\n \"precision\": 9,\n \"name\": \"ctimestamp1\"\n },\n {\n \"type\": \"TIMESTAMP\",\n \"nullable\": true,\n \"precision\": 9,\n \"name\": \"ctimestamp2\"\n },\n {\n \"type\": \"BOOLEAN\",\n \"nullable\": true,\n \"name\": \"cboolean1\"\n },\n {\n \"type\": \"BOOLEAN\",\n \"nullable\": true,\n \"name\": \"cboolean2\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"BLOCK__OFFSET__INSIDE__FILE\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"INPUT__FILE__NAME\"\n },\n {\n \"fields\": [\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"writeid\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"bucketid\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"rowid\"\n }\n ],\n \"name\": \"ROW__ID\"\n }\n ],\n \"colStats\": [\n {\n \"name\": \"cbigint\",\n \"ndv\": 15,\n \"minValue\": -1970551565,\n \"maxValue\": 1086455747\n },\n {\n \"name\": \"cstring2\",\n \"ndv\": 15\n },\n {\n \"name\": \"ctinyint\",\n \"ndv\": 2,\n \"minValue\": -64,\n \"maxValue\": -51\n },\n {\n \"name\": \"csmallint\",\n \"ndv\": 6,\n \"minValue\": -15920,\n \"maxValue\": -6907\n },\n {\n \"name\": \"cint\",\n \"ndv\": 8,\n \"minValue\": -738306196,\n \"maxValue\": 626923679\n },\n {\n \"name\": \"cfloat\",\n \"ndv\": 2,\n \"minValue\": -64.0,\n \"maxValue\": -51.0\n },\n {\n \"name\": \"cdouble\",\n \"ndv\": 6,\n \"minValue\": -15920.0,\n \"maxValue\": -6907.0\n },\n {\n \"name\": \"cstring1\",\n \"ndv\": 8\n },\n {\n \"name\": \"ctimestamp1\",\n \"ndv\": 0\n },\n {\n \"name\": \"ctimestamp2\",\n \"ndv\": 0\n },\n {\n \"name\": \"cboolean1\",\n \"ndv\": 2\n },\n {\n \"name\": \"cboolean2\",\n \"ndv\": 2\n }\n ]\n },\n {\n \"id\": \"3\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveFilter\",\n \"condition\": {\n \"op\": \"AND\",\n \"operands\": [\n {\n \"op\": \"IS NOT NULL\",\n \"operands\": [\n {\n \"input\": 3,\n \"name\": \"$3\"\n }\n ]\n },\n {\n \"op\": \"IS NOT NULL\",\n \"operands\": [\n {\n \"input\": 7,\n \"name\": \"$7\"\n }\n ]\n }\n ]\n },\n \"rowCount\": 11.25\n },\n {\n \"id\": \"4\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject\",\n \"fields\": [\n \"cbigint\",\n \"cstring2\"\n ],\n \"exprs\": [\n {\n \"input\": 3,\n \"name\": \"$3\"\n },\n {\n \"input\": 7,\n \"name\": \"$7\"\n }\n ],\n \"rowCount\": 11.25\n },\n {\n \"id\": \"5\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveJoin\",\n \"condition\": {\n \"op\": \"AND\",\n \"operands\": [\n {\n \"op\": \"=\",\n \"operands\": [\n {\n \"input\": 5,\n \"name\": \"$5\"\n },\n {\n \"input\": 3,\n \"name\": \"$3\"\n }\n ]\n },\n {\n \"op\": \"=\",\n \"operands\": [\n {\n \"input\": 4,\n \"name\": \"$4\"\n },\n {\n \"input\": 1,\n \"name\": \"$1\"\n }\n ]\n }\n ]\n },\n \"joinType\": \"left\",\n \"algorithm\": \"none\",\n \"cost\": \"not available\",\n \"inputs\": [\n \"1\",\n \"4\"\n ],\n \"rowCount\": 20.0\n },\n {\n \"id\": \"6\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveTableScan\",\n \"table\": [\n \"default\",\n \"small_alltypesorc_a_n1\"\n ],\n \"table:alias\": \"hd\",\n \"inputs\": [],\n \"rowCount\": 20.0,\n \"avgRowSize\": 10.0,\n \"rowType\": [\n {\n \"type\": \"TINYINT\",\n \"nullable\": true,\n \"name\": \"ctinyint\"\n },\n {\n \"type\": \"SMALLINT\",\n \"nullable\": true,\n \"name\": \"csmallint\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"cint\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"cbigint\"\n },\n {\n \"type\": \"FLOAT\",\n \"nullable\": true,\n \"name\": \"cfloat\"\n },\n {\n \"type\": \"DOUBLE\",\n \"nullable\": true,\n \"name\": \"cdouble\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"cstring1\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"cstring2\"\n },\n {\n \"type\": \"TIMESTAMP\",\n \"nullable\": true,\n \"precision\": 9,\n \"name\": \"ctimestamp1\"\n },\n {\n \"type\": \"TIMESTAMP\",\n \"nullable\": true,\n \"precision\": 9,\n \"name\": \"ctimestamp2\"\n },\n {\n \"type\": \"BOOLEAN\",\n \"nullable\": true,\n \"name\": \"cboolean1\"\n },\n {\n \"type\": \"BOOLEAN\",\n \"nullable\": true,\n \"name\": \"cboolean2\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"BLOCK__OFFSET__INSIDE__FILE\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"INPUT__FILE__NAME\"\n },\n {\n \"fields\": [\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"writeid\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"bucketid\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"rowid\"\n }\n ],\n \"name\": \"ROW__ID\"\n }\n ],\n \"colStats\": [\n {\n \"name\": \"cint\",\n \"ndv\": 8,\n \"minValue\": -738306196,\n \"maxValue\": 626923679\n },\n {\n \"name\": \"cstring1\",\n \"ndv\": 8\n },\n {\n \"name\": \"ctinyint\",\n \"ndv\": 2,\n \"minValue\": -64,\n \"maxValue\": -51\n },\n {\n \"name\": \"csmallint\",\n \"ndv\": 6,\n \"minValue\": -15920,\n \"maxValue\": -6907\n },\n {\n \"name\": \"cbigint\",\n \"ndv\": 15,\n \"minValue\": -1970551565,\n \"maxValue\": 1086455747\n },\n {\n \"name\": \"cfloat\",\n \"ndv\": 2,\n \"minValue\": -64.0,\n \"maxValue\": -51.0\n },\n {\n \"name\": \"cdouble\",\n \"ndv\": 6,\n \"minValue\": -15920.0,\n \"maxValue\": -6907.0\n },\n {\n \"name\": \"cstring2\",\n \"ndv\": 15\n },\n {\n \"name\": \"ctimestamp1\",\n \"ndv\": 0\n },\n {\n \"name\": \"ctimestamp2\",\n \"ndv\": 0\n },\n {\n \"name\": \"cboolean1\",\n \"ndv\": 2\n },\n {\n \"name\": \"cboolean2\",\n \"ndv\": 2\n }\n ]\n },\n {\n \"id\": \"7\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveFilter\",\n \"condition\": {\n \"op\": \"AND\",\n \"operands\": [\n {\n \"op\": \"IS NOT NULL\",\n \"operands\": [\n {\n \"input\": 2,\n \"name\": \"$2\"\n }\n ]\n },\n {\n \"op\": \"IS NOT NULL\",\n \"operands\": [\n {\n \"input\": 6,\n \"name\": \"$6\"\n }\n ]\n }\n ]\n },\n \"rowCount\": 5.0\n },\n {\n \"id\": \"8\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject\",\n \"fields\": [\n \"cint\",\n \"cstring1\"\n ],\n \"exprs\": [\n {\n \"input\": 2,\n \"name\": \"$2\"\n },\n {\n \"input\": 6,\n \"name\": \"$6\"\n }\n ],\n \"rowCount\": 5.0\n },\n {\n \"id\": \"9\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveJoin\",\n \"condition\": {\n \"op\": \"AND\",\n \"operands\": [\n {\n \"op\": \"=\",\n \"operands\": [\n {\n \"input\": 7,\n \"name\": \"$7\"\n },\n {\n \"input\": 2,\n \"name\": \"$2\"\n }\n ]\n },\n {\n \"op\": \"=\",\n \"operands\": [\n {\n \"input\": 6,\n \"name\": \"$6\"\n },\n {\n \"input\": 0,\n \"name\": \"$0\"\n }\n ]\n }\n ]\n },\n \"joinType\": \"left\",\n \"algorithm\": \"none\",\n \"cost\": \"not available\",\n \"inputs\": [\n \"5\",\n \"8\"\n ],\n \"rowCount\": 20.0\n },\n {\n \"id\": \"10\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveAggregate\",\n \"group\": [],\n \"aggs\": [\n {\n \"agg\": \"count\",\n \"type\": {\n \"type\": \"BIGINT\",\n \"nullable\": true\n },\n \"distinct\": false,\n \"operands\": []\n }\n ],\n \"rowCount\": 1.0\n }\n ]\n}","optimizedSQL":"SELECT COUNT(*) AS `$f0`\nFROM (SELECT `cint`, `cbigint`, `cstring1`, `cstring2`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t`\nLEFT JOIN (SELECT `cbigint`, `cstring2`\nFROM `default`.`small_alltypesorc_a_n1`\nWHERE `cbigint` IS NOT NULL AND `cstring2` IS NOT NULL) AS `t1` ON `t`.`cstring2` = `t1`.`cstring2` AND `t`.`cbigint` = `t1`.`cbigint`\nLEFT JOIN (SELECT `cint`, `cstring1`\nFROM `default`.`small_alltypesorc_a_n1`\nWHERE `cint` IS NOT NULL AND `cstring1` IS NOT NULL) AS `t3` ON `t`.`cstring1` = `t3`.`cstring1` AND `t`.`cint` = `t3`.`cint`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-8":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-8"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-8":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:cd":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:hd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:cd":{"TableScan":{"alias:":"cd","columns:":["cbigint","cstring2"],"database:":"default","filterExpr:":"(cbigint is not null and cstring2 is not null) (type: boolean)","Statistics:":"Num rows: 20 Data size: 1616 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_2","children":{"Filter Operator":{"predicate:":"(cbigint is not null and cstring2 is not null) (type: boolean)","Statistics:":"Num rows: 11 Data size: 909 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"FIL_20","children":{"Select Operator":{"expressions:":"cbigint (type: bigint), cstring2 (type: string)","columnExprMap:":{"_col0":"cbigint","_col1":"cstring2"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 11 Data size: 909 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_4","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: bigint), _col3 (type: string)","1":"_col0 (type: bigint), _col1 (type: string)"},"OperatorId:":"HASHTABLESINK_30"}}}}}}}},"$hdt$_2:hd":{"TableScan":{"alias:":"hd","columns:":["cint","cstring1"],"database:":"default","filterExpr:":"(cint is not null and cstring1 is not null) (type: boolean)","Statistics:":"Num rows: 20 Data size: 1034 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_5","children":{"Filter Operator":{"predicate:":"(cint is not null and cstring1 is not null) (type: boolean)","Statistics:":"Num rows: 5 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"FIL_21","children":{"Select Operator":{"expressions:":"cint (type: int), cstring1 (type: string)","columnExprMap:":{"_col0":"cint","_col1":"cstring1"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 5 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_7","children":{"HashTable Sink Operator":{"keys:":{"0":"_col0 (type: int), _col2 (type: string)","1":"_col0 (type: int), _col1 (type: string)"},"OperatorId:":"HASHTABLESINK_28"}}}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["cint","cbigint","cstring1","cstring2"],"database:":"default","Statistics:":"Num rows: 20 Data size: 2650 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"cint (type: int), cbigint (type: bigint), cstring1 (type: string), cstring2 (type: string)","columnExprMap:":{"_col0":"cint","_col1":"cbigint","_col2":"cstring1","_col3":"cstring2"},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[2, 3, 6, 7]"},"Statistics:":"Num rows: 20 Data size: 2650 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_32","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0","_col2":"0:_col2"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: bigint), _col3 (type: string)","1":"_col0 (type: bigint), _col1 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 3:bigint","col 7:string"],"bigTableValueExpressions:":["col 2:int","col 6:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col2"],"Statistics:":"Num rows: 26 Data size: 1598 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_33","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col0 (type: int), _col2 (type: string)","1":"_col0 (type: int), _col1 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 0:int","col 1:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 42 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_34","children":{"Group By Operator":{"aggregations:":["count()"],"Group By Vectorization:":{"aggregators:":["VectorUDAFCountStar(*) -> bigint"],"className:":"VectorGroupByOperator","groupByMode:":"HASH","native:":"false","vectorProcessingMode:":"HASH","projectedOutputColumnNums:":"[0]"},"minReductionHashAggr:":"0.99","mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"GBY_35","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0"},"sort order:":"","Reduce Sink Vectorization:":{"className:":"VectorReduceSinkOperator","native:":"false","nativeConditionsMet:":["hive.vectorized.execution.reducesink.new.enabled IS true","No PTF TopN IS true","No DISTINCT columns IS true","BinarySortableSerDe for keys IS true","LazyBinarySerDe for values IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: bigint)","OperatorId:":"RS_36"}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[2, 3, 6, 7]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[]"}},"Local Work:":{"Map Reduce Local Work":{}},"Reduce Vectorization:":{"enabled:":"false","enableConditionsMet:":["hive.vectorized.execution.reduce.enabled IS true"],"enableConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"GBY_17","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_19"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_37"}}}}}} PREHOOK: query: select count(*) from (select c.cstring1 from small_alltypesorc_a_n1 c left outer join small_alltypesorc_a_n1 cd