diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/TopNKeyDesc.java ql/src/java/org/apache/hadoop/hive/ql/plan/TopNKeyDesc.java index a9e2a527df..f752967a96 100644 --- ql/src/java/org/apache/hadoop/hive/ql/plan/TopNKeyDesc.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/TopNKeyDesc.java @@ -46,9 +46,23 @@ public TopNKeyDesc( final List keyColumns) { this.topN = topN; - this.columnSortOrder = columnSortOrder; - this.nullOrder = nullOrder; - this.keyColumns = keyColumns; + + this.keyColumns = new ArrayList<>(keyColumns.size()); + StringBuilder sortOrder = new StringBuilder(columnSortOrder.length()); + StringBuilder nullSortOrder = new StringBuilder(nullOrder.length()); + + for (int i = 0; i < keyColumns.size(); ++i) { + ExprNodeDesc keyExpression = keyColumns.get(i); + if (keyExpression instanceof ExprNodeConstantDesc) { + continue; + } + this.keyColumns.add(keyExpression); + sortOrder.append(columnSortOrder.charAt(i)); + nullSortOrder.append(nullOrder.charAt(i)); + } + + this.columnSortOrder = sortOrder.toString(); + this.nullOrder = nullSortOrder.toString(); } @Explain(displayName = "top n", explainLevels = { Level.DEFAULT, Level.EXTENDED, Level.USER }) diff --git ql/src/test/results/clientpositive/llap/topnkey_grouping_sets.q.out ql/src/test/results/clientpositive/llap/topnkey_grouping_sets.q.out index b1ec8d8847..1015ebf481 100644 --- ql/src/test/results/clientpositive/llap/topnkey_grouping_sets.q.out +++ ql/src/test/results/clientpositive/llap/topnkey_grouping_sets.q.out @@ -72,34 +72,28 @@ STAGE PLANS: alias: t_test_grouping_sets Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Top N Key Operator - sort order: + - keys: a (type: int) - null sort order: z + sort order: ++ + keys: a (type: int), b (type: int) + null sort order: za Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE top n: 3 Select Operator expressions: a (type: int), b (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: +++ + Group By Operator keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint) - null sort order: zaa - Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - top n: 3 - Group By Operator - keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint) - minReductionHashAggr: 0.15384614 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - null sort order: zaa - sort order: +++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + minReductionHashAggr: 0.15384614 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + null sort order: zaa + sort order: +++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -109,16 +103,16 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), grouping(_col2, 1L) (type: bigint), grouping(_col2, 0L) (type: bigint), grouping(_col2, 1L, 0L) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 26 Data size: 632 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: z sort order: + - Statistics: Num rows: 26 Data size: 632 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint) Reducer 3 @@ -127,13 +121,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 26 Data size: 632 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 3 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -196,34 +190,28 @@ STAGE PLANS: alias: t_test_grouping_sets Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Top N Key Operator - sort order: + - keys: a (type: int) - null sort order: z + sort order: ++ + keys: a (type: int), b (type: int) + null sort order: za Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE top n: 10 Select Operator expressions: a (type: int), b (type: int) outputColumnNames: a, b Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: +++ + Group By Operator keys: a (type: int), b (type: int), 0L (type: bigint) - null sort order: zaa - Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - top n: 10 - Group By Operator - keys: a (type: int), b (type: int), 0L (type: bigint) - minReductionHashAggr: 0.15384614 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - null sort order: zaa - sort order: +++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + minReductionHashAggr: 0.15384614 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + null sort order: zaa + sort order: +++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -233,13 +221,13 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Reduce Output Operator key expressions: _col0 (type: int) null sort order: z sort order: + - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int) Reducer 3 @@ -248,13 +236,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -686,25 +674,19 @@ STAGE PLANS: expressions: a (type: int), b (type: int) outputColumnNames: a, b Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: -++ + Group By Operator keys: a (type: int), b (type: int), 0L (type: bigint) - null sort order: zza - Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - top n: 7 - Group By Operator - keys: a (type: int), b (type: int), 0L (type: bigint) - minReductionHashAggr: 0.15384614 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - null sort order: zza - sort order: -++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + minReductionHashAggr: 0.15384614 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + null sort order: zza + sort order: -++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -714,13 +696,13 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: -+ - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: llap @@ -728,13 +710,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 7 - Statistics: Num rows: 7 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 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 @@ -814,25 +796,19 @@ STAGE PLANS: expressions: a (type: int), b (type: int) outputColumnNames: a, b Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: -++ + Group By Operator keys: a (type: int), b (type: int), 0L (type: bigint) - null sort order: zza - Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - top n: 7 - Group By Operator - keys: a (type: int), b (type: int), 0L (type: bigint) - minReductionHashAggr: 0.15384614 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - null sort order: zza - sort order: -++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + minReductionHashAggr: 0.15384614 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + null sort order: zza + sort order: -++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -842,13 +818,13 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: -+ - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: llap @@ -856,13 +832,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 7 - Statistics: Num rows: 7 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 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 @@ -942,25 +918,19 @@ STAGE PLANS: expressions: a (type: int), b (type: int) outputColumnNames: a, b Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: -++ + Group By Operator keys: a (type: int), b (type: int), 0L (type: bigint) - null sort order: zza - Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - top n: 7 - Group By Operator - keys: a (type: int), b (type: int), 0L (type: bigint) - minReductionHashAggr: 0.15384614 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - null sort order: zza - sort order: -++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + minReductionHashAggr: 0.15384614 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + null sort order: zza + sort order: -++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -970,13 +940,13 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: -+ - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: llap @@ -984,13 +954,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 7 - Statistics: Num rows: 7 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 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 @@ -1070,25 +1040,19 @@ STAGE PLANS: expressions: a (type: int), b (type: int) outputColumnNames: a, b Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: -++ + Group By Operator keys: a (type: int), b (type: int), 0L (type: bigint) - null sort order: zza - Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - top n: 7 - Group By Operator - keys: a (type: int), b (type: int), 0L (type: bigint) - minReductionHashAggr: 0.15384614 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - null sort order: zza - sort order: -++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + minReductionHashAggr: 0.15384614 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + null sort order: zza + sort order: -++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1098,13 +1062,13 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: -+ - Statistics: Num rows: 13 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: llap @@ -1112,13 +1076,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 7 - Statistics: Num rows: 7 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 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 @@ -1225,27 +1189,21 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: -++ + Group By Operator + aggregations: max(_col2) keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint) - null sort order: zza - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - top n: 7 - Group By Operator - aggregations: max(_col2) - keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint) - minReductionHashAggr: 0.0 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - null sort order: zza - sort order: -++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 6 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col3 (type: int) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + null sort order: zza + sort order: -++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: int) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1254,17 +1212,17 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 6 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: -+ - Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: int) Reducer 4 @@ -1273,13 +1231,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 7 - Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 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 ql/src/test/results/clientpositive/llap/topnkey_grouping_sets_functions.q.out ql/src/test/results/clientpositive/llap/topnkey_grouping_sets_functions.q.out index 0ec6e6de43..84657327ec 100644 --- ql/src/test/results/clientpositive/llap/topnkey_grouping_sets_functions.q.out +++ ql/src/test/results/clientpositive/llap/topnkey_grouping_sets_functions.q.out @@ -284,8 +284,8 @@ NULL 1 2 5 2 3 NULL 2 1 6 2 1 -7 8 4 NULL 8 4 +7 8 4 PREHOOK: query: SELECT a, b, min(c) FROM t_test_grouping_sets GROUP BY a,b GROUPING SETS ((b,a), (a), (b), ()) ORDER BY b LIMIT 7 PREHOOK: type: QUERY PREHOOK: Input: default@t_test_grouping_sets @@ -413,8 +413,8 @@ NULL 1 2 5 2 3 NULL 2 3 6 2 1 -NULL 8 4 7 8 4 +NULL 8 4 PREHOOK: query: SELECT a, b, max(c) FROM t_test_grouping_sets GROUP BY a,b GROUPING SETS ((a,b), (a), (b), ()) ORDER BY b LIMIT 7 PREHOOK: type: QUERY PREHOOK: Input: default@t_test_grouping_sets diff --git ql/src/test/results/clientpositive/llap/topnkey_grouping_sets_order.q.out ql/src/test/results/clientpositive/llap/topnkey_grouping_sets_order.q.out index d3ff1a6256..598d86b11c 100644 --- ql/src/test/results/clientpositive/llap/topnkey_grouping_sets_order.q.out +++ ql/src/test/results/clientpositive/llap/topnkey_grouping_sets_order.q.out @@ -146,8 +146,8 @@ POSTHOOK: Input: default@t_test_grouping_sets NULL NULL 5 NULL 6 NULL -10 NULL 7 NULL +10 NULL NULL NULL NULL NULL PREHOOK: query: SELECT a, b FROM t_test_grouping_sets GROUP BY a,b GROUPING SETS ((a,b), (a), (b), ()) ORDER BY b NULLS FIRST LIMIT 7 @@ -270,8 +270,8 @@ NULL 1 5 2 NULL 2 6 2 -NULL 8 7 8 +NULL 8 PREHOOK: query: SELECT a, b FROM t_test_grouping_sets GROUP BY a,b GROUPING SETS ((a,b), (a), (b), ()) ORDER BY b NULLS LAST LIMIT 7 PREHOOK: type: QUERY PREHOOK: Input: default@t_test_grouping_sets @@ -285,8 +285,8 @@ NULL 1 5 2 NULL 2 6 2 -NULL 8 7 8 +NULL 8 PREHOOK: query: EXPLAIN SELECT a, b FROM t_test_grouping_sets GROUP BY a,b GROUPING SETS ((a,b), (a), (b), ()) ORDER BY a DESC, b ASC LIMIT 7 PREHOOK: type: QUERY @@ -325,25 +325,19 @@ STAGE PLANS: expressions: a (type: int), b (type: int) outputColumnNames: a, b Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: -++ + Group By Operator keys: a (type: int), b (type: int), 0L (type: bigint) - null sort order: zza - Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - top n: 7 - Group By Operator - keys: a (type: int), b (type: int), 0L (type: bigint) - minReductionHashAggr: 0.15384614 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - null sort order: zza - sort order: -++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + minReductionHashAggr: 0.15384614 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + null sort order: zza + sort order: -++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -353,13 +347,13 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: zz sort order: -+ - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: llap @@ -367,13 +361,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 7 - Statistics: Num rows: 7 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 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 @@ -453,25 +447,19 @@ STAGE PLANS: expressions: a (type: int), b (type: int) outputColumnNames: a, b Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: -++ + Group By Operator keys: a (type: int), b (type: int), 0L (type: bigint) - null sort order: aaa - Statistics: Num rows: 13 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - top n: 7 - Group By Operator - keys: a (type: int), b (type: int), 0L (type: bigint) - minReductionHashAggr: 0.15384614 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - null sort order: aaa - sort order: -++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + minReductionHashAggr: 0.15384614 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + null sort order: aaa + sort order: -++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -481,13 +469,13 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) null sort order: aa sort order: -+ - Statistics: Num rows: 26 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: llap @@ -495,13 +483,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 7 - Statistics: Num rows: 7 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 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 ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_limit.q.out ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_limit.q.out index 3addfb9a88..d36b590104 100644 --- ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_limit.q.out +++ ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_limit.q.out @@ -82,45 +82,35 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1] Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: +++ - keys: a (type: string), b (type: string), 0L (type: bigint) - null sort order: zza - Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE - top n: 10 - Top N Key Vectorization: - className: VectorTopNKeyOperator + Group By Operator + aggregations: count() + Group By Vectorization: + aggregators: VectorUDAFCountStar(*) -> bigint + className: VectorGroupByOperator + groupByMode: HASH keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 4:bigint - native: true - Group By Operator - aggregations: count() - Group By Vectorization: - aggregators: VectorUDAFCountStar(*) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 5:bigint - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0] - keys: a (type: string), b (type: string), 0L (type: bigint) - minReductionHashAggr: 0.0 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0] + keys: a (type: string), b (type: string), 0L (type: bigint) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + null sort order: zza + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + keyColumns: 0:string, 1:string, 2:bigint + 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 + valueColumns: 3:bigint Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - null sort order: zza - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Reduce Sink Vectorization: - className: VectorReduceSinkMultiKeyOperator - keyColumns: 0:string, 1:string, 2:bigint - 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 - valueColumns: 3:bigint - Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col3 (type: bigint) + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -137,7 +127,7 @@ STAGE PLANS: includeColumns: [0, 1] dataColumns: a:string, b:string, c:string partitionColumnCount: 0 - scratchColumnTypeNames: [bigint, bigint] + scratchColumnTypeNames: [bigint] Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: @@ -310,45 +300,35 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1] Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: +++ - keys: a (type: string), b (type: string), 0L (type: bigint) - null sort order: zza - Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE - top n: 10 - Top N Key Vectorization: - className: VectorTopNKeyOperator + Group By Operator + aggregations: count() + Group By Vectorization: + aggregators: VectorUDAFCountStar(*) -> bigint + className: VectorGroupByOperator + groupByMode: HASH keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 4:bigint - native: true - Group By Operator - aggregations: count() - Group By Vectorization: - aggregators: VectorUDAFCountStar(*) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 5:bigint - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0] - keys: a (type: string), b (type: string), 0L (type: bigint) - minReductionHashAggr: 0.0 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0] + keys: a (type: string), b (type: string), 0L (type: bigint) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + null sort order: zza + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + keyColumns: 0:string, 1:string, 2:bigint + 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 + valueColumns: 3:bigint Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - null sort order: zza - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Reduce Sink Vectorization: - className: VectorReduceSinkMultiKeyOperator - keyColumns: 0:string, 1:string, 2:bigint - 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 - valueColumns: 3:bigint - Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col3 (type: bigint) + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -365,7 +345,7 @@ STAGE PLANS: includeColumns: [0, 1] dataColumns: a:string, b:string, c:string partitionColumnCount: 0 - scratchColumnTypeNames: [bigint, bigint] + scratchColumnTypeNames: [bigint] Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: @@ -538,45 +518,35 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1] Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: +++ - keys: a (type: string), b (type: string), 0L (type: bigint) - null sort order: zza - Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE - top n: 10 - Top N Key Vectorization: - className: VectorTopNKeyOperator + Group By Operator + aggregations: count() + Group By Vectorization: + aggregators: VectorUDAFCountStar(*) -> bigint + className: VectorGroupByOperator + groupByMode: HASH keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 4:bigint - native: true - Group By Operator - aggregations: count() - Group By Vectorization: - aggregators: VectorUDAFCountStar(*) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 5:bigint - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0] - keys: a (type: string), b (type: string), 0L (type: bigint) - minReductionHashAggr: 0.0 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0] + keys: a (type: string), b (type: string), 0L (type: bigint) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + null sort order: zza + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + keyColumns: 0:string, 1:string, 2:bigint + 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 + valueColumns: 3:bigint Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - null sort order: zza - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Reduce Sink Vectorization: - className: VectorReduceSinkMultiKeyOperator - keyColumns: 0:string, 1:string, 2:bigint - 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 - valueColumns: 3:bigint - Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col3 (type: bigint) + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -593,7 +563,7 @@ STAGE PLANS: includeColumns: [0, 1] dataColumns: a:string, b:string, c:string partitionColumnCount: 0 - scratchColumnTypeNames: [bigint, bigint] + scratchColumnTypeNames: [bigint] Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: @@ -749,14 +719,14 @@ STAGE PLANS: native: true vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct] Top N Key Operator - sort order: + - keys: a (type: string) - null sort order: z + sort order: +++ + keys: a (type: string), b (type: string), c (type: string) + null sort order: zaa Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE top n: 10 Top N Key Vectorization: className: VectorTopNKeyOperator - keyExpressions: col 0:string + keyExpressions: col 0:string, col 1:string, col 2:string native: true Select Operator expressions: a (type: string), b (type: string), c (type: string) @@ -766,41 +736,31 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 2] Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: ++++ - keys: a (type: string), b (type: string), c (type: string), 0L (type: bigint) - null sort order: zaaa - Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE - top n: 10 - Top N Key Vectorization: - className: VectorTopNKeyOperator + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + groupByMode: HASH keyExpressions: col 0:string, col 1:string, col 2:string, ConstantVectorExpression(val 0) -> 4:bigint - native: true - Group By Operator - Group By Vectorization: - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 0:string, col 1:string, col 2:string, ConstantVectorExpression(val 0) -> 5:bigint - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [] - keys: a (type: string), b (type: string), c (type: string), 0L (type: bigint) - minReductionHashAggr: 0.0 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [] + keys: a (type: string), b (type: string), c (type: string), 0L (type: bigint) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 9 Data size: 2367 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) + null sort order: zaaa + sort order: ++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + keyColumns: 0:string, 1:string, 2:string, 3:bigint + 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: 9 Data size: 2367 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - null sort order: zaaa - sort order: ++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - Reduce Sink Vectorization: - className: VectorReduceSinkMultiKeyOperator - keyColumns: 0:string, 1:string, 2:string, 3:bigint - 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: 9 Data size: 2367 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -817,7 +777,7 @@ STAGE PLANS: includeColumns: [0, 1, 2] dataColumns: a:string, b:string, c:string partitionColumnCount: 0 - scratchColumnTypeNames: [bigint, bigint] + scratchColumnTypeNames: [bigint] Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: diff --git ql/src/test/results/clientpositive/perf/tez/constraints/query14.q.out ql/src/test/results/clientpositive/perf/tez/constraints/query14.q.out index 44da18ad40..4f811c01ce 100644 --- ql/src/test/results/clientpositive/perf/tez/constraints/query14.q.out +++ ql/src/test/results/clientpositive/perf/tez/constraints/query14.q.out @@ -314,7 +314,7 @@ Stage-0 Group By Operator [GBY_1208] (rows=304320 width=231) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0L Top N Key Operator [TNK_1207] (rows=121728 width=221) - keys:_col0, _col1, _col2, _col3, 0L,top n:100 + keys:_col0, _col1, _col2, _col3,top n:100 Select Operator [SEL_1205] (rows=40576 width=223) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_1204] (rows=40576 width=244) @@ -690,7 +690,7 @@ Stage-0 Group By Operator [GBY_1215] (rows=304320 width=231) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0L Top N Key Operator [TNK_1214] (rows=121728 width=221) - keys:_col0, _col1, _col2, _col3, 0L,top n:100 + keys:_col0, _col1, _col2, _col3,top n:100 Select Operator [SEL_1212] (rows=40576 width=219) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_1211] (rows=40576 width=244) @@ -877,7 +877,7 @@ Stage-0 Group By Operator [GBY_1201] (rows=304320 width=231) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0L Top N Key Operator [TNK_1200] (rows=121728 width=221) - keys:_col0, _col1, _col2, _col3, 0L,top n:100 + keys:_col0, _col1, _col2, _col3,top n:100 Select Operator [SEL_1198] (rows=40576 width=221) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_1197] (rows=40576 width=244) diff --git ql/src/test/results/clientpositive/perf/tez/constraints/query27.q.out ql/src/test/results/clientpositive/perf/tez/constraints/query27.q.out index 4eb41168bc..957f883ffd 100644 --- ql/src/test/results/clientpositive/perf/tez/constraints/query27.q.out +++ ql/src/test/results/clientpositive/perf/tez/constraints/query27.q.out @@ -87,81 +87,79 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_28] (rows=13907934 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_60] (rows=4635978 width=186) - keys:_col0, _col1, 0L,top n:100 - Select Operator [SEL_26] (rows=4635978 width=186) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Top N Key Operator [TNK_58] (rows=4635978 width=186) - keys:_col13, _col11,top n:100 - Merge Join Operator [MERGEJOIN_104] (rows=4635978 width=186) - Conds:RS_23._col1=RS_123._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col11","_col13"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_123] - PartitionCols:_col0 - Select Operator [SEL_122] (rows=462000 width=104) - Output:["_col0","_col1"] - TableScan [TS_12] (rows=462000 width=104) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_23] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_103] (rows=4635978 width=90) - Conds:RS_20._col3=RS_121._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col11"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_121] - PartitionCols:_col0 - Select Operator [SEL_120] (rows=209 width=90) - Output:["_col0","_col1"] - Filter Operator [FIL_119] (rows=209 width=90) - predicate:(s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') - TableScan [TS_9] (rows=1704 width=90) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_20] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_102] (rows=4635978 width=4) - Conds:RS_17._col0=RS_118._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_118] - PartitionCols:_col0 - Select Operator [SEL_117] (rows=652 width=4) - Output:["_col0"] - Filter Operator [FIL_116] (rows=652 width=8) - predicate:(d_year = 2001) - TableScan [TS_6] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_17] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_101] (rows=4635978 width=4) - Conds:RS_115._col2=RS_107._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_107] - PartitionCols:_col0 - Select Operator [SEL_106] (rows=14776 width=4) - Output:["_col0"] - Filter Operator [FIL_105] (rows=14776 width=268) - predicate:((cd_marital_status = 'U') and (cd_education_status = '2 yr Degree') and (cd_gender = 'M')) - TableScan [TS_3] (rows=1861800 width=268) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_115] - PartitionCols:_col2 - Select Operator [SEL_114] (rows=501690006 width=340) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_113] (rows=501690006 width=340) - predicate:(ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_cdemo_sk BETWEEN DynamicValue(RS_15_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_15_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_15_customer_demographics_cd_demo_sk_bloom_filter))) - TableScan [TS_0] (rows=575995635 width=340) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_cdemo_sk","ss_store_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_112] - Group By Operator [GBY_111] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_110] - Group By Operator [GBY_109] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_108] (rows=14776 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_106] + Select Operator [SEL_26] (rows=4635978 width=186) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Top N Key Operator [TNK_58] (rows=4635978 width=186) + keys:_col13, _col11,top n:100 + Merge Join Operator [MERGEJOIN_104] (rows=4635978 width=186) + Conds:RS_23._col1=RS_123._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col11","_col13"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_123] + PartitionCols:_col0 + Select Operator [SEL_122] (rows=462000 width=104) + Output:["_col0","_col1"] + TableScan [TS_12] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_23] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_103] (rows=4635978 width=90) + Conds:RS_20._col3=RS_121._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col11"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_121] + PartitionCols:_col0 + Select Operator [SEL_120] (rows=209 width=90) + Output:["_col0","_col1"] + Filter Operator [FIL_119] (rows=209 width=90) + predicate:(s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') + TableScan [TS_9] (rows=1704 width=90) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_20] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_102] (rows=4635978 width=4) + Conds:RS_17._col0=RS_118._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_118] + PartitionCols:_col0 + Select Operator [SEL_117] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_116] (rows=652 width=8) + predicate:(d_year = 2001) + TableScan [TS_6] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_17] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_101] (rows=4635978 width=4) + Conds:RS_115._col2=RS_107._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_107] + PartitionCols:_col0 + Select Operator [SEL_106] (rows=14776 width=4) + Output:["_col0"] + Filter Operator [FIL_105] (rows=14776 width=268) + predicate:((cd_marital_status = 'U') and (cd_education_status = '2 yr Degree') and (cd_gender = 'M')) + TableScan [TS_3] (rows=1861800 width=268) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_115] + PartitionCols:_col2 + Select Operator [SEL_114] (rows=501690006 width=340) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_113] (rows=501690006 width=340) + predicate:(ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_cdemo_sk BETWEEN DynamicValue(RS_15_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_15_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_15_customer_demographics_cd_demo_sk_bloom_filter))) + TableScan [TS_0] (rows=575995635 width=340) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_cdemo_sk","ss_store_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_112] + Group By Operator [GBY_111] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_110] + Group By Operator [GBY_109] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_108] (rows=14776 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_106] diff --git ql/src/test/results/clientpositive/perf/tez/constraints/query5.q.out ql/src/test/results/clientpositive/perf/tez/constraints/query5.q.out index f78b2faf7c..6f2bb83581 100644 --- ql/src/test/results/clientpositive/perf/tez/constraints/query5.q.out +++ ql/src/test/results/clientpositive/perf/tez/constraints/query5.q.out @@ -321,7 +321,7 @@ Stage-0 Group By Operator [GBY_314] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_313] (rows=39721 width=618) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_312] (rows=38846 width=619) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_311] (rows=38846 width=548) @@ -390,7 +390,7 @@ Stage-0 Group By Operator [GBY_321] (rows=59581 width=627) 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=39721 width=618) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_319] (rows=53 width=615) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_318] (rows=53 width=548) @@ -470,7 +470,7 @@ Stage-0 Group By Operator [GBY_298] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_297] (rows=39721 width=618) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_296] (rows=822 width=617) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_295] (rows=822 width=548) diff --git ql/src/test/results/clientpositive/perf/tez/constraints/query77.q.out ql/src/test/results/clientpositive/perf/tez/constraints/query77.q.out index 40810d45dc..e8cfe33f2d 100644 --- ql/src/test/results/clientpositive/perf/tez/constraints/query77.q.out +++ ql/src/test/results/clientpositive/perf/tez/constraints/query77.q.out @@ -281,7 +281,7 @@ Stage-0 Group By Operator [GBY_234] (rows=564 width=446) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_233] (rows=531 width=435) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_231] (rows=10 width=439) Output:["_col0","_col1","_col2","_col3","_col4"] Merge Join Operator [MERGEJOIN_230] (rows=10 width=452) @@ -355,7 +355,7 @@ Stage-0 Group By Operator [GBY_240] (rows=564 width=446) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_239] (rows=531 width=435) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_237] (rows=394 width=435) Output:["_col0","_col1","_col2","_col3","_col4"] Merge Join Operator [MERGEJOIN_236] (rows=394 width=335) @@ -431,7 +431,7 @@ Stage-0 Group By Operator [GBY_228] (rows=564 width=446) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_227] (rows=531 width=435) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_225] (rows=127 width=436) Output:["_col0","_col1","_col2","_col3","_col4"] Merge Join Operator [MERGEJOIN_224] (rows=127 width=379) diff --git ql/src/test/results/clientpositive/perf/tez/constraints/query80.q.out ql/src/test/results/clientpositive/perf/tez/constraints/query80.q.out index 462eed8942..9c82167a01 100644 --- ql/src/test/results/clientpositive/perf/tez/constraints/query80.q.out +++ ql/src/test/results/clientpositive/perf/tez/constraints/query80.q.out @@ -267,7 +267,7 @@ Stage-0 Group By Operator [GBY_448] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_447] (rows=39721 width=618) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_446] (rows=38846 width=619) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_445] (rows=38846 width=436) @@ -368,7 +368,7 @@ Stage-0 Group By Operator [GBY_462] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_461] (rows=39721 width=618) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_460] (rows=53 width=615) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_459] (rows=53 width=436) @@ -454,7 +454,7 @@ Stage-0 Group By Operator [GBY_428] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_427] (rows=39721 width=618) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_426] (rows=822 width=617) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_425] (rows=822 width=436) diff --git ql/src/test/results/clientpositive/perf/tez/query14.q.out ql/src/test/results/clientpositive/perf/tez/query14.q.out index da6b74d147..bf96850291 100644 --- ql/src/test/results/clientpositive/perf/tez/query14.q.out +++ ql/src/test/results/clientpositive/perf/tez/query14.q.out @@ -314,7 +314,7 @@ Stage-0 Group By Operator [GBY_1190] (rows=304320 width=231) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0L Top N Key Operator [TNK_1189] (rows=121728 width=221) - keys:_col0, _col1, _col2, _col3, 0L,top n:100 + keys:_col0, _col1, _col2, _col3,top n:100 Select Operator [SEL_1187] (rows=40576 width=223) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_1186] (rows=40576 width=244) @@ -694,7 +694,7 @@ Stage-0 Group By Operator [GBY_1197] (rows=304320 width=231) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0L Top N Key Operator [TNK_1196] (rows=121728 width=221) - keys:_col0, _col1, _col2, _col3, 0L,top n:100 + keys:_col0, _col1, _col2, _col3,top n:100 Select Operator [SEL_1194] (rows=40576 width=219) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_1193] (rows=40576 width=244) @@ -885,7 +885,7 @@ Stage-0 Group By Operator [GBY_1183] (rows=304320 width=231) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0L Top N Key Operator [TNK_1182] (rows=121728 width=221) - keys:_col0, _col1, _col2, _col3, 0L,top n:100 + keys:_col0, _col1, _col2, _col3,top n:100 Select Operator [SEL_1180] (rows=40576 width=221) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Filter Operator [FIL_1179] (rows=40576 width=244) diff --git ql/src/test/results/clientpositive/perf/tez/query27.q.out ql/src/test/results/clientpositive/perf/tez/query27.q.out index 62fbeda71e..cfc5823e6d 100644 --- ql/src/test/results/clientpositive/perf/tez/query27.q.out +++ ql/src/test/results/clientpositive/perf/tez/query27.q.out @@ -87,83 +87,81 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_29] (rows=13907934 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_61] (rows=4635978 width=186) - keys:_col0, _col1, 0L,top n:100 - Select Operator [SEL_27] (rows=4635978 width=186) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Top N Key Operator [TNK_59] (rows=4635978 width=186) - keys:_col13, _col11,top n:100 - Merge Join Operator [MERGEJOIN_105] (rows=4635978 width=186) - Conds:RS_24._col1=RS_125._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col11","_col13"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_125] - PartitionCols:_col0 - Select Operator [SEL_124] (rows=462000 width=104) - Output:["_col0","_col1"] - Filter Operator [FIL_123] (rows=462000 width=104) - predicate:i_item_sk is not null - TableScan [TS_12] (rows=462000 width=104) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_24] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_104] (rows=4635978 width=90) - Conds:RS_21._col3=RS_122._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col11"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_122] - PartitionCols:_col0 - Select Operator [SEL_121] (rows=209 width=90) - Output:["_col0","_col1"] - Filter Operator [FIL_120] (rows=209 width=90) - predicate:((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') and s_store_sk is not null) - TableScan [TS_9] (rows=1704 width=90) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_21] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_103] (rows=4635978 width=4) - Conds:RS_18._col0=RS_119._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_119] - PartitionCols:_col0 - Select Operator [SEL_118] (rows=652 width=4) - Output:["_col0"] - Filter Operator [FIL_117] (rows=652 width=8) - predicate:((d_year = 2001) and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_18] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_102] (rows=4635978 width=4) - Conds:RS_116._col2=RS_108._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_108] - PartitionCols:_col0 - Select Operator [SEL_107] (rows=14776 width=4) - Output:["_col0"] - Filter Operator [FIL_106] (rows=14776 width=268) - predicate:((cd_marital_status = 'U') and (cd_education_status = '2 yr Degree') and (cd_gender = 'M') and cd_demo_sk is not null) - TableScan [TS_3] (rows=1861800 width=268) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_116] - PartitionCols:_col2 - Select Operator [SEL_115] (rows=501690006 width=340) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_114] (rows=501690006 width=340) - predicate:(ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_item_sk is not null and ss_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) - TableScan [TS_0] (rows=575995635 width=340) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_cdemo_sk","ss_store_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_113] - Group By Operator [GBY_112] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_111] - Group By Operator [GBY_110] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_109] (rows=14776 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_107] + Select Operator [SEL_27] (rows=4635978 width=186) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Top N Key Operator [TNK_59] (rows=4635978 width=186) + keys:_col13, _col11,top n:100 + Merge Join Operator [MERGEJOIN_105] (rows=4635978 width=186) + Conds:RS_24._col1=RS_125._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col11","_col13"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_125] + PartitionCols:_col0 + Select Operator [SEL_124] (rows=462000 width=104) + Output:["_col0","_col1"] + Filter Operator [FIL_123] (rows=462000 width=104) + predicate:i_item_sk is not null + TableScan [TS_12] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_24] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_104] (rows=4635978 width=90) + Conds:RS_21._col3=RS_122._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col11"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_122] + PartitionCols:_col0 + Select Operator [SEL_121] (rows=209 width=90) + Output:["_col0","_col1"] + Filter Operator [FIL_120] (rows=209 width=90) + predicate:((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') and s_store_sk is not null) + TableScan [TS_9] (rows=1704 width=90) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_21] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_103] (rows=4635978 width=4) + Conds:RS_18._col0=RS_119._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_119] + PartitionCols:_col0 + Select Operator [SEL_118] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_117] (rows=652 width=8) + predicate:((d_year = 2001) and d_date_sk is not null) + TableScan [TS_6] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_102] (rows=4635978 width=4) + Conds:RS_116._col2=RS_108._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_108] + PartitionCols:_col0 + Select Operator [SEL_107] (rows=14776 width=4) + Output:["_col0"] + Filter Operator [FIL_106] (rows=14776 width=268) + predicate:((cd_marital_status = 'U') and (cd_education_status = '2 yr Degree') and (cd_gender = 'M') and cd_demo_sk is not null) + TableScan [TS_3] (rows=1861800 width=268) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_116] + PartitionCols:_col2 + Select Operator [SEL_115] (rows=501690006 width=340) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_114] (rows=501690006 width=340) + predicate:(ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_item_sk is not null and ss_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) + TableScan [TS_0] (rows=575995635 width=340) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_cdemo_sk","ss_store_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_113] + Group By Operator [GBY_112] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_111] + Group By Operator [GBY_110] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_109] (rows=14776 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_107] diff --git ql/src/test/results/clientpositive/perf/tez/query5.q.out ql/src/test/results/clientpositive/perf/tez/query5.q.out index 34bbb51ef9..af29b3e4f9 100644 --- ql/src/test/results/clientpositive/perf/tez/query5.q.out +++ ql/src/test/results/clientpositive/perf/tez/query5.q.out @@ -321,7 +321,7 @@ Stage-0 Group By Operator [GBY_319] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_318] (rows=39721 width=618) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_317] (rows=38846 width=619) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_316] (rows=38846 width=548) @@ -392,7 +392,7 @@ Stage-0 Group By Operator [GBY_327] (rows=59581 width=627) 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=39721 width=618) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_325] (rows=53 width=615) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_324] (rows=53 width=548) @@ -474,7 +474,7 @@ Stage-0 Group By Operator [GBY_302] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_301] (rows=39721 width=618) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_300] (rows=822 width=617) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_299] (rows=822 width=548) diff --git ql/src/test/results/clientpositive/perf/tez/query77.q.out ql/src/test/results/clientpositive/perf/tez/query77.q.out index 6b9c5b4e16..4efb3eeb09 100644 --- ql/src/test/results/clientpositive/perf/tez/query77.q.out +++ ql/src/test/results/clientpositive/perf/tez/query77.q.out @@ -285,7 +285,7 @@ Stage-0 Group By Operator [GBY_326] (rows=561 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_325] (rows=526 width=435) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_323] (rows=10 width=439) Output:["_col0","_col1","_col2","_col3","_col4"] Merge Join Operator [MERGEJOIN_322] (rows=10 width=452) @@ -359,7 +359,7 @@ Stage-0 Group By Operator [GBY_332] (rows=561 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_331] (rows=526 width=435) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_329] (rows=392 width=435) Output:["_col0","_col1","_col2","_col3","_col4"] Merge Join Operator [MERGEJOIN_328] (rows=392 width=335) @@ -454,7 +454,7 @@ Stage-0 Group By Operator [GBY_320] (rows=561 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_319] (rows=526 width=435) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_317] (rows=124 width=437) Output:["_col0","_col1","_col2","_col3","_col4"] Merge Join Operator [MERGEJOIN_316] (rows=124 width=379) diff --git ql/src/test/results/clientpositive/perf/tez/query80.q.out ql/src/test/results/clientpositive/perf/tez/query80.q.out index 30f77de916..82e986d764 100644 --- ql/src/test/results/clientpositive/perf/tez/query80.q.out +++ ql/src/test/results/clientpositive/perf/tez/query80.q.out @@ -267,7 +267,7 @@ Stage-0 Group By Operator [GBY_458] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_457] (rows=39721 width=618) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_456] (rows=38846 width=619) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_455] (rows=38846 width=436) @@ -372,7 +372,7 @@ Stage-0 Group By Operator [GBY_474] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_473] (rows=39721 width=618) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_472] (rows=53 width=615) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_471] (rows=53 width=436) @@ -462,7 +462,7 @@ Stage-0 Group By Operator [GBY_436] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L Top N Key Operator [TNK_435] (rows=39721 width=618) - keys:_col0, _col1, 0L,top n:100 + keys:_col0, _col1,top n:100 Select Operator [SEL_434] (rows=822 width=617) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_433] (rows=822 width=436)