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 7682791f4d..f71e34cb19 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 @@ -1696,12 +1696,17 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, } List distinctVals = Lists.newArrayList(); + + // these ndvs are later used to compuate dangling rows and num of nulls for outer joins + List ndvsDangling= Lists.newArrayList(); long denom = 1; + long denomDangling = 1; if (inferredRowCount == -1) { // failed to infer PK-FK relationship for row count estimation fall-back on default logic // compute denominator max(V(R,y1), V(S,y1)) * max(V(R,y2), V(S,y2)) // in case of multi-attribute join List perAttrDVs = Lists.newArrayList(); + // go over each predicate for (int idx = 0; idx < numAttr; idx++) { for (Integer i : joinKeys.keySet()) { String col = joinKeys.get(i).get(idx); @@ -1711,19 +1716,27 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, } } distinctVals.add(getDenominator(perAttrDVs)); + ndvsDangling.add(getDenominatorForDanglingRows(perAttrDVs)); perAttrDVs.clear(); } if (numAttr > 1 && conf.getBoolVar(HiveConf.ConfVars.HIVE_STATS_CORRELATED_MULTI_KEY_JOINS)) { denom = Collections.max(distinctVals); + denomDangling = denom - ndvsDangling.get(distinctVals.indexOf(denom)); } else if (numAttr > numParent) { // To avoid denominator getting larger and aggressively reducing // number of rows, we will ease out denominator. denom = StatsUtils.addWithExpDecay(distinctVals); + denomDangling = denom - StatsUtils.addWithExpDecay(ndvsDangling); } else { for (Long l : distinctVals) { denom = StatsUtils.safeMult(denom, l); } + long tempDenom = 1; + for (Long l : ndvsDangling) { + tempDenom = StatsUtils.safeMult(tempDenom, l); + } + denomDangling = denom - tempDenom; } } @@ -1754,15 +1767,18 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, // update join statistics stats.setColumnStats(outColStats); - // reason we compute interim row count, where join type isn't considered, is because later - // it will be used to estimate num nulls long interimRowCount = inferredRowCount != -1 ? inferredRowCount : computeRowCountAssumingInnerJoin(rowCounts, denom, jop); // final row computation will consider join type long joinRowCount = inferredRowCount != -1 ? inferredRowCount : computeFinalRowCount(rowCounts, interimRowCount, jop); - updateColStats(conf, stats, interimRowCount, joinRowCount, jop, rowCountParents); + // the idea is to measure dangling rows in outer joins by figuring out how many rows didn't match + // mismatched rows are figured using denomDangling which is the difference of denom used for computing + // join cardinality minus the ndv which wasn't used. This number (mismatched rows) is then subtracted from + /// join cardinality to get the rows which didn't match + long unMatchedRows = Math.abs(computeRowCountAssumingInnerJoin(rowCounts, denomDangling, jop) - joinRowCount); + updateColStats(conf, stats, unMatchedRows, joinRowCount, jop, rowCountParents); // evaluate filter expression and update statistics if (joinRowCount != -1 && jop.getConf().getNoOuterJoin() && @@ -2176,13 +2192,10 @@ private void updateNumNulls(ColStatistics colStats, long interimNumRows, long ne //if this column is coming from right input only then we update num nulls if (pos == joinCond.getRight() && interimNumRows != newNumRows) { - // interim row count can not be less due to containment - // assumption in join cardinality computation - assert (newNumRows > interimNumRows); if (isJoinKey(colStats.getColumnName(), jop.getConf().getJoinKeys())) { - newNumNulls = Math.min(newNumRows, (newNumRows - interimNumRows)); + newNumNulls = Math.min(newNumRows, (interimNumRows)); } else { - newNumNulls = Math.min(newNumRows, oldNumNulls + (newNumRows - interimNumRows)); + newNumNulls = Math.min(newNumRows, oldNumNulls + (interimNumRows)); } } break; @@ -2190,24 +2203,19 @@ private void updateNumNulls(ColStatistics colStats, long interimNumRows, long ne if (pos == joinCond.getLeft() && interimNumRows != newNumRows) { - // interim row count can not be less due to containment - // assumption in join cardinality computation - // interimNumRows represent number of matches for join keys on two sides. - // newNumRows-interimNumRows represent number of non-matches. - assert (newNumRows > interimNumRows); - if (isJoinKey(colStats.getColumnName(), jop.getConf().getJoinKeys())) { - newNumNulls = Math.min(newNumRows, (newNumRows - interimNumRows)); + newNumNulls = Math.min(newNumRows, ( interimNumRows)); } else { - newNumNulls = Math.min(newNumRows, oldNumNulls + (newNumRows - interimNumRows)); + // TODO: oldNumNulls should be scaled instead of taken as it is + newNumNulls = Math.min(newNumRows, oldNumNulls + (interimNumRows)); } } break; case JoinDesc.FULL_OUTER_JOIN: if (isJoinKey(colStats.getColumnName(), jop.getConf().getJoinKeys())) { - newNumNulls = Math.min(newNumRows, (newNumRows - interimNumRows)); + newNumNulls = Math.min(newNumRows, (interimNumRows)); } else { - newNumNulls = Math.min(newNumRows, oldNumNulls + (newNumRows - interimNumRows)); + newNumNulls = Math.min(newNumRows, oldNumNulls + (interimNumRows)); } break; @@ -2379,6 +2387,39 @@ private void updateJoinColumnsNDV(Map> joinKeys, } } + private long getDenominatorForDanglingRows(List distinctVals) { + + if (distinctVals.isEmpty()) { + return 2; + } + + // simple join from 2 relations: denom = min(v1, v2) + if (distinctVals.size() <= 2) { + return Collections.min(distinctVals); + } else { + + // remember max value and ignore it from the denominator + long maxNDV = distinctVals.get(0); + int maxIdx = 0; + + for (int i = 1; i < distinctVals.size(); i++) { + if (distinctVals.get(i) > maxNDV) { + maxNDV = distinctVals.get(i); + maxIdx = i; + } + } + + // join from multiple relations: + // denom = Product of all NDVs except the greatest of all + long denom = 1; + for (int i = 0; i < distinctVals.size(); i++) { + if (i != maxIdx) { + denom = StatsUtils.safeMult(denom, distinctVals.get(i)); + } + } + return denom; + } + } private long getDenominator(List distinctVals) { if (distinctVals.isEmpty()) { diff --git a/ql/src/test/results/clientpositive/annotate_stats_join.q.out b/ql/src/test/results/clientpositive/annotate_stats_join.q.out index b0d2b05ab0..1cc4772f1e 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_join.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_join.q.out @@ -705,10 +705,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: int) 1 _col1 (type: string), _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 48 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4847 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 48 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4847 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -838,10 +838,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: int) 1 _col1 (type: string), _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 48 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4659 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 48 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4659 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -898,10 +898,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: int) 1 _col1 (type: string), _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 54 Data size: 9506 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 54 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 54 Data size: 9506 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 54 Data size: 194 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_join30.q.out b/ql/src/test/results/clientpositive/llap/auto_join30.q.out index 874511a112..b41eff02db 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join30.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join30.q.out @@ -169,7 +169,7 @@ STAGE PLANS: outputColumnNames: _col2, _col3 input vertices: 1 Map 3 - Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash 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 205cd444b2..4f042cee50 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 @@ -856,10 +856,10 @@ 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: 166 Data size: 668 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: 166 Data size: 668 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -911,10 +911,10 @@ 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: 166 Data size: 668 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: 166 Data size: 668 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1016,10 +1016,10 @@ 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: 166 Data size: 668 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: 166 Data size: 668 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1091,10 +1091,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Map 1 - Statistics: Num rows: 166 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 166 Data size: 668 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: 166 Data size: 668 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/check_constraint.q.out b/ql/src/test/results/clientpositive/llap/check_constraint.q.out index ec1ed64fe8..be1084b1f2 100644 --- a/ql/src/test/results/clientpositive/llap/check_constraint.q.out +++ b/ql/src/test/results/clientpositive/llap/check_constraint.q.out @@ -1537,7 +1537,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 262 Data size: 69430 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 262 Data size: 46723 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col2 AS decimal(5,2)) (type: decimal(5,2)), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 diff --git a/ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out b/ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out index 21b07b2c80..0edeef947e 100644 --- a/ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out +++ b/ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out @@ -1104,18 +1104,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3306 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1246,18 +1246,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3306 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1385,7 +1385,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 39 Data size: 6903 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6812 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col3 (type: string) @@ -1516,7 +1516,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 39 Data size: 6903 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6812 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col3 (type: string) @@ -1934,7 +1934,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 3612 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2076,7 +2076,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 3612 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2218,7 +2218,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 525 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 525 Data size: 3612 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2360,7 +2360,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 525 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 525 Data size: 3612 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) 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 a98191653f..0d3bcebb2a 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out @@ -957,9 +957,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_8] - Select Operator [SEL_7] (rows=80 width=7) + Select Operator [SEL_7] (rows=80 width=4) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_16] (rows=80 width=7) + Merge Join Operator [MERGEJOIN_16] (rows=80 width=4) Conds:RS_4._col0=RS_5._col0(Left Outer),Output:["_col1","_col3"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_4] @@ -991,9 +991,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_8] - Select Operator [SEL_7] (rows=80 width=7) + Select Operator [SEL_7] (rows=80 width=0) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_9] (rows=80 width=7) + Merge Join Operator [MERGEJOIN_9] (rows=80 width=0) Conds:RS_4._col0=RS_5._col0(Outer),Output:["_col1","_col3"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_4] @@ -1715,9 +1715,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_19] - Select Operator [SEL_18] (rows=365 width=178) + Select Operator [SEL_18] (rows=315 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_17] (rows=365 width=179) + Filter Operator [FIL_17] (rows=315 width=179) predicate:_col3 is null Merge Join Operator [MERGEJOIN_27] (rows=500 width=179) Conds:RS_14._col1=RS_15._col0(Left Outer),Output:["_col0","_col1","_col3"] @@ -1777,11 +1777,11 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_18] - Select Operator [SEL_17] (rows=167 width=178) + Select Operator [SEL_17] (rows=126 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_16] (rows=167 width=179) + Filter Operator [FIL_16] (rows=126 width=180) predicate:_col4 is null - Merge Join Operator [MERGEJOIN_31] (rows=250 width=179) + Merge Join Operator [MERGEJOIN_31] (rows=250 width=180) Conds:GBY_4._col0, _col1=SEL_12._col0, _col1(Left Outer),Output:["_col0","_col1","_col4"] <-Select Operator [SEL_12] (rows=83 width=182) Output:["_col0","_col1","_col2"] @@ -2287,14 +2287,14 @@ Stage-0 File Output Operator [FS_24] Select Operator [SEL_23] (rows=13 width=223) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_22] (rows=13 width=237) + Filter Operator [FIL_22] (rows=13 width=225) predicate:CASE WHEN ((_col4 = 0L)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END - Merge Join Operator [MERGEJOIN_45] (rows=26 width=236) + Merge Join Operator [MERGEJOIN_45] (rows=26 width=224) 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=26 width=235) + Merge Join Operator [MERGEJOIN_44] (rows=26 width=223) Conds:RS_16._col1=RS_17._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_16] @@ -3819,9 +3819,9 @@ Stage-0 Stage-1 Map 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=48 width=15) + Select Operator [SEL_5] (rows=48 width=7) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=48 width=15) + Merge Join Operator [MERGEJOIN_7] (rows=48 width=7) Conds:TS_0.key=TS_1.key(Right Outer),Output:["_col0","_col1","_col5","_col6"] <-TableScan [TS_0] (rows=26 width=7) default@smb_input1_n2,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] @@ -3861,9 +3861,9 @@ Stage-0 Stage-1 Map 1 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=48 width=15) + Select Operator [SEL_5] (rows=48 width=7) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=48 width=15) + Merge Join Operator [MERGEJOIN_7] (rows=48 width=7) Conds:TS_0.key=TS_1.key(Left Outer),Output:["_col0","_col1","_col5","_col6"] <-TableScan [TS_1] (rows=26 width=7) default@smb_input1_n2,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] diff --git a/ql/src/test/results/clientpositive/llap/insert_into_default_keyword.q.out b/ql/src/test/results/clientpositive/llap/insert_into_default_keyword.q.out index 1a61c0e592..f604443d8c 100644 --- a/ql/src/test/results/clientpositive/llap/insert_into_default_keyword.q.out +++ b/ql/src/test/results/clientpositive/llap/insert_into_default_keyword.q.out @@ -2601,7 +2601,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col2, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 = _col6) and (_col6 < 3)) (type: boolean) Statistics: Num rows: 1 Data size: 261 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 b6ef9b184e..07c4a6234e 100644 --- a/ql/src/test/results/clientpositive/llap/join46.q.out +++ b/ql/src/test/results/clientpositive/llap/join46.q.out @@ -106,10 +106,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -220,10 +220,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 857 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 952 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 857 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 952 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -435,10 +435,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -981,10 +981,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1533,10 +1533,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1976,10 +1976,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 10 Data size: 1711 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1711 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2138,10 +2138,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 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 @@ -2154,10 +2154,10 @@ 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: 64 Data size: 24440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 23107 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 64 Data size: 24440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 23107 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2173,10 +2173,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 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) Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/llap/join_emit_interval.q.out b/ql/src/test/results/clientpositive/llap/join_emit_interval.q.out index 9484b7ae0a..b5d5bd7bf4 100644 --- a/ql/src/test/results/clientpositive/llap/join_emit_interval.q.out +++ b/ql/src/test/results/clientpositive/llap/join_emit_interval.q.out @@ -109,10 +109,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 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/limit_join_transpose.q.out b/ql/src/test/results/clientpositive/llap/limit_join_transpose.q.out index f8ce1ce93e..5b87588eea 100644 --- a/ql/src/test/results/clientpositive/llap/limit_join_transpose.q.out +++ b/ql/src/test/results/clientpositive/llap/limit_join_transpose.q.out @@ -66,7 +66,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140976 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE @@ -167,7 +167,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140976 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE @@ -954,7 +954,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140976 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Offset of rows: 1 @@ -1056,7 +1056,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140976 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Offset of rows: 1 diff --git a/ql/src/test/results/clientpositive/llap/mapjoin3.q.out b/ql/src/test/results/clientpositive/llap/mapjoin3.q.out index 7aa7318896..53d98ed5b2 100644 --- a/ql/src/test/results/clientpositive/llap/mapjoin3.q.out +++ b/ql/src/test/results/clientpositive/llap/mapjoin3.q.out @@ -123,14 +123,14 @@ STAGE PLANS: outputColumnNames: _col0, _col2, _col3 input vertices: 1 Map 2 - Statistics: Num rows: 3 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), _col2 (type: varchar(100)), _col3 (type: varchar(100)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 196 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 204e7755e5..52eb609414 100644 --- a/ql/src/test/results/clientpositive/llap/mapjoin46.q.out +++ b/ql/src/test/results/clientpositive/llap/mapjoin46.q.out @@ -80,10 +80,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 input vertices: 1 Map 2 - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -183,10 +183,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 input vertices: 1 Map 2 - Statistics: Num rows: 6 Data size: 857 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 952 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 857 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 952 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -407,10 +407,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 input vertices: 0 Map 1 - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -909,10 +909,10 @@ STAGE PLANS: input vertices: 1 Map 2 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1346,10 +1346,10 @@ STAGE PLANS: input vertices: 0 Map 1 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1791,10 +1791,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 10 Data size: 1711 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1711 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1917,10 +1917,10 @@ STAGE PLANS: input vertices: 1 Map 4 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 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 @@ -1943,10 +1943,10 @@ STAGE PLANS: input vertices: 0 Map 1 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 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 @@ -1978,10 +1978,10 @@ 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: 64 Data size: 24440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 23107 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 64 Data size: 24440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 23107 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/mapjoin_emit_interval.q.out b/ql/src/test/results/clientpositive/llap/mapjoin_emit_interval.q.out index f6a1a6ee41..b6678729dc 100644 --- a/ql/src/test/results/clientpositive/llap/mapjoin_emit_interval.q.out +++ b/ql/src/test/results/clientpositive/llap/mapjoin_emit_interval.q.out @@ -83,10 +83,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 input vertices: 1 Map 2 - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 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/skewjoinopt15.q.out b/ql/src/test/results/clientpositive/llap/skewjoinopt15.q.out index cd20c3ab17..bd30c24ade 100644 --- a/ql/src/test/results/clientpositive/llap/skewjoinopt15.q.out +++ b/ql/src/test/results/clientpositive/llap/skewjoinopt15.q.out @@ -231,10 +231,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 7 Data size: 1260 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 1260 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 720 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/subquery_in.q.out b/ql/src/test/results/clientpositive/llap/subquery_in.q.out index a045b12dc6..57ab9e7dfc 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_in.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_in.q.out @@ -4391,10 +4391,10 @@ STAGE PLANS: 0 _col4 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 - Statistics: Num rows: 26 Data size: 16214 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16278 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sq_count_check(CASE WHEN (_col10 is null) THEN (0) ELSE (_col10) END, true) > 0) (type: boolean) - Statistics: Num rows: 8 Data size: 4992 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 5016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -4898,10 +4898,10 @@ STAGE PLANS: 0 _col4 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 - Statistics: Num rows: 26 Data size: 16214 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16278 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sq_count_check(CASE WHEN (_col10 is null) THEN (0) ELSE (_col10) END, true) > 0) (type: boolean) - Statistics: Num rows: 8 Data size: 4992 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 5016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -4922,12 +4922,12 @@ STAGE PLANS: 0 _col4 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11 - Statistics: Num rows: 8 Data size: 5080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 4968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: string), UDFToLong(_col5) (type: bigint) sort order: ++ Map-reduce partition columns: _col4 (type: string), UDFToLong(_col5) (type: bigint) - Statistics: Num rows: 8 Data size: 5080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 4968 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: bigint), _col11 (type: bigint) Reducer 4 Execution mode: llap @@ -4939,10 +4939,10 @@ STAGE PLANS: 0 _col4 (type: string), UDFToLong(_col5) (type: bigint) 1 _col1 (type: string), _col0 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col14 - Statistics: Num rows: 8 Data size: 5112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col10 = 0L)) THEN (true) WHEN (_col10 is null) THEN (true) WHEN (_col14 is not null) THEN (false) WHEN (_col5 is null) THEN (null) WHEN ((_col11 < _col10)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 4 Data size: 2556 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -5153,10 +5153,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 - Statistics: Num rows: 26 Data size: 16206 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16294 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sq_count_check(CASE WHEN (_col10 is null) THEN (0) ELSE (_col10) END, true) > 0) (type: boolean) - Statistics: Num rows: 8 Data size: 4992 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 5016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -5177,12 +5177,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11 - Statistics: Num rows: 8 Data size: 5080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 4968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), UDFToDouble(_col5) (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: int), UDFToDouble(_col5) (type: double) - Statistics: Num rows: 8 Data size: 5080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 4968 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: bigint), _col11 (type: bigint) Reducer 4 Execution mode: llap @@ -5194,10 +5194,10 @@ STAGE PLANS: 0 _col0 (type: int), UDFToDouble(_col5) (type: double) 1 _col1 (type: int), _col0 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col14 - Statistics: Num rows: 8 Data size: 5112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col10 = 0L)) THEN (true) WHEN (_col10 is null) THEN (true) WHEN (_col14 is not null) THEN (false) WHEN (_col5 is null) THEN (null) WHEN ((_col11 < _col10)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 4 Data size: 2556 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 diff --git a/ql/src/test/results/clientpositive/llap/subquery_multi.q.out b/ql/src/test/results/clientpositive/llap/subquery_multi.q.out index a865ee9259..0f9e2702ce 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_multi.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_multi.q.out @@ -4164,10 +4164,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 500 Data size: 50028 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 50216 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 50028 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 50216 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: bigint), _col4 (type: boolean) Reducer 4 Execution mode: llap @@ -4179,12 +4179,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col2, _col4, _col5 - Statistics: Num rows: 500 Data size: 52028 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 52216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col4 is not null and (_col2 <> 0L)) or _col1 is not null or _col5 is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 52028 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 52216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 52028 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 52216 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out index f5f5f36aa3..3795effc5e 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out @@ -105,10 +105,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 500 Data size: 97528 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97716 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 97528 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97716 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 @@ -373,12 +373,12 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 26 Data size: 6134 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 5814 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: 26 Data size: 6134 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 5814 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col4 (type: bigint), _col5 (type: bigint) Reducer 3 Execution mode: llap @@ -390,10 +390,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col8 - Statistics: Num rows: 26 Data size: 6154 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 5834 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col4 = 0L)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 13 Data size: 3087 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 2927 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2 @@ -932,10 +932,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 26 Data size: 5966 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 5806 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sq_count_check(CASE WHEN (_col4 is null) THEN (0) ELSE (_col4) END, true) > 0) (type: boolean) - Statistics: Num rows: 8 Data size: 1840 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1792 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2 @@ -956,12 +956,12 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 8 Data size: 1912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: int) sort order: ++ Map-reduce partition columns: _col1 (type: string), _col2 (type: int) - Statistics: Num rows: 8 Data size: 1912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col4 (type: bigint), _col5 (type: bigint) Reducer 4 Execution mode: llap @@ -973,10 +973,10 @@ STAGE PLANS: 0 _col1 (type: string), _col2 (type: int) 1 _col1 (type: string), _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col8 - Statistics: Num rows: 8 Data size: 1932 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 1832 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col4 = 0L)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col2 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 4 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 924 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2 @@ -1518,10 +1518,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 166 Data size: 17358 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 166 Data size: 17526 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col1 = 0L) or (_col4 is null and _col0 is not null and (_col2 >= _col1))) (type: boolean) - Statistics: Num rows: 166 Data size: 17358 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 166 Data size: 17526 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 @@ -1679,12 +1679,12 @@ STAGE PLANS: 0 _col4 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11 - Statistics: Num rows: 26 Data size: 16334 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16462 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: string), _col5 (type: int) sort order: ++ Map-reduce partition columns: _col4 (type: string), _col5 (type: int) - Statistics: Num rows: 26 Data size: 16334 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16462 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: bigint), _col11 (type: bigint) Reducer 3 Execution mode: llap @@ -1696,10 +1696,10 @@ STAGE PLANS: 0 _col4 (type: string), _col5 (type: int) 1 _col1 (type: string), _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col14 - Statistics: Num rows: 26 Data size: 16402 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16506 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col10 = 0L)) THEN (true) WHEN (_col10 is null) THEN (true) WHEN (_col14 is not null) THEN (false) WHEN (_col5 is null) THEN (null) WHEN ((_col11 < _col10)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 13 Data size: 8211 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 8263 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -1869,10 +1869,10 @@ STAGE PLANS: 0 (_col5 - 1) (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 - Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16554 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col12 is null and _col5 is not null and (_col10 >= _col9)) or (_col9 = 0L)) (type: boolean) - Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16554 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -2076,10 +2076,10 @@ STAGE PLANS: 0 (_col0 * _col5) (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 - Statistics: Num rows: 26 Data size: 16538 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col12 is null and _col0 is not null and _col5 is not null and (_col10 >= _col9)) or (_col9 = 0L)) (type: boolean) - Statistics: Num rows: 26 Data size: 16538 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -2314,12 +2314,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 26 Data size: 3474 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 3650 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 26 Data size: 3474 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 3650 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 3 Execution mode: llap @@ -2331,12 +2331,12 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: int) 1 _col1 (type: string), _col3 (type: int) outputColumnNames: _col1, _col3, _col4, _col7 - Statistics: Num rows: 26 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 548 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col3 = 0L)) THEN (true) WHEN (_col3 is null) THEN (true) WHEN (_col7 is not null) THEN (false) WHEN ((_col1 + 100) is null) THEN (null) WHEN ((_col4 < _col3)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 13 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 13 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 284 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -2513,10 +2513,10 @@ STAGE PLANS: 0 floor(_col7) (type: bigint) 1 _col0 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 - Statistics: Num rows: 26 Data size: 16538 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16546 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col12 is null and _col7 is not null and (_col10 >= _col9)) or (_col9 = 0L)) (type: boolean) - Statistics: Num rows: 26 Data size: 16538 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16546 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -2737,12 +2737,12 @@ STAGE PLANS: 0 _col5 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11 - Statistics: Num rows: 26 Data size: 16222 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16270 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col5 (type: int) sort order: ++ Map-reduce partition columns: _col1 (type: string), _col5 (type: int) - Statistics: Num rows: 26 Data size: 16222 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16270 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: bigint), _col11 (type: bigint) Reducer 3 Execution mode: llap @@ -2754,10 +2754,10 @@ STAGE PLANS: 0 _col1 (type: string), _col5 (type: int) 1 _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col14 - Statistics: Num rows: 26 Data size: 16250 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16306 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col10 = 0L)) THEN (true) WHEN (_col10 is null) THEN (true) WHEN (_col14 is not null) THEN (false) WHEN (_col1 is null) THEN (null) WHEN ((_col11 < _col10)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 13 Data size: 8127 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 8163 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -2967,12 +2967,12 @@ STAGE PLANS: 0 _col0 (type: int), _col5 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12 - Statistics: Num rows: 26 Data size: 16318 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16494 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col5 (type: int) - Statistics: Num rows: 26 Data size: 16318 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16494 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: bigint), _col12 (type: bigint) Reducer 3 Execution mode: llap @@ -2984,10 +2984,10 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string), _col5 (type: int) 1 _col1 (type: int), _col0 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12, _col16 - Statistics: Num rows: 26 Data size: 16374 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16594 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col11 = 0L)) THEN (true) WHEN (_col11 is null) THEN (true) WHEN (_col16 is not null) THEN (false) WHEN (_col1 is null) THEN (null) WHEN ((_col12 < _col11)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 13 Data size: 8187 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 8307 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -3137,12 +3137,12 @@ STAGE PLANS: 0 _col2 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 26 Data size: 8594 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 8258 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col1) (type: double), _col2 (type: string) sort order: ++ Map-reduce partition columns: UDFToDouble(_col1) (type: double), _col2 (type: string) - Statistics: Num rows: 26 Data size: 8594 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 8258 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col4 (type: bigint), _col5 (type: bigint) Reducer 3 Execution mode: llap @@ -3154,10 +3154,10 @@ STAGE PLANS: 0 UDFToDouble(_col1) (type: double), _col2 (type: string) 1 _col0 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col4, _col5, _col8 - Statistics: Num rows: 26 Data size: 6262 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 5958 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col4 = 0L)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col1 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 13 Data size: 3133 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 2989 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 @@ -3369,12 +3369,12 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 26 Data size: 6114 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6226 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: int) sort order: ++ Map-reduce partition columns: _col1 (type: string), _col2 (type: int) - Statistics: Num rows: 26 Data size: 6114 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6226 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col4 (type: bigint), _col5 (type: bigint) Reducer 3 Execution mode: llap @@ -3386,10 +3386,10 @@ STAGE PLANS: 0 _col1 (type: string), _col2 (type: int) 1 _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1, _col4, _col5, _col8 - Statistics: Num rows: 26 Data size: 6046 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6178 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col4 = 0L)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col1 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 13 Data size: 3025 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 3097 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 @@ -3631,14 +3631,14 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 500 Data size: 98632 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97004 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0L) or (_col5 is null and _col1 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 98632 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97004 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 98632 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97004 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -3904,12 +3904,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 500 Data size: 95336 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 89016 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 95336 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 89016 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 3 Execution mode: llap @@ -3921,14 +3921,14 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4, _col7 - Statistics: Num rows: 500 Data size: 96968 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 89020 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col3 = 0L)) THEN (true) WHEN (_col3 is null) THEN (true) WHEN (_col7 is not null) THEN (false) WHEN (_col1 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 250 Data size: 48484 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 44520 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 48484 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 44520 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -4173,10 +4173,10 @@ STAGE PLANS: 0 (_col5 - 1) (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 - Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16554 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col12 is null and _col5 is not null and (_col10 >= _col9)) or (_col9 = 0L)) (type: boolean) - Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16554 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -4381,10 +4381,10 @@ STAGE PLANS: 0 (_col5 - 1) (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 - Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16554 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col12 is null and _col5 is not null and (_col10 >= _col9)) or (_col9 = 0L)) (type: boolean) - Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16554 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -4660,10 +4660,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 500 Data size: 97160 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97172 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 97160 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97172 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 @@ -5329,12 +5329,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 26 Data size: 2848 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 2512 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 26 Data size: 2848 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 2512 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 3 Execution mode: llap @@ -5346,12 +5346,12 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: int) 1 _col1 (type: string), _col3 (type: int) outputColumnNames: _col1, _col3, _col4, _col7 - Statistics: Num rows: 26 Data size: 524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 164 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col3 = 0L)) THEN (true) WHEN (_col3 is null) THEN (true) WHEN (_col7 is not null) THEN (false) WHEN ((_col1 + 100) is null) THEN (null) WHEN ((_col4 < _col3)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 13 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 13 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -5569,10 +5569,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 4 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col1 = 0L) or (_col4 is null and _col0 is not null and (_col2 >= _col1))) (type: boolean) - Statistics: Num rows: 4 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 @@ -5722,12 +5722,12 @@ STAGE PLANS: 0 _col1 (type: char(100)) 1 _col0 (type: char(100)) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 4 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: char(100)) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: char(100)) - Statistics: Num rows: 4 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 3 Execution mode: llap @@ -5739,10 +5739,10 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: char(100)) 1 _col0 (type: int), _col1 (type: char(100)) outputColumnNames: _col0, _col3, _col4, _col7 - Statistics: Num rows: 4 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col3 = 0L)) THEN (true) WHEN (_col3 is null) THEN (true) WHEN (_col7 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 2 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 @@ -6627,12 +6627,12 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 3 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 3 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 3 Execution mode: llap @@ -6644,7 +6644,7 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col3, _col4, _col7 - Statistics: Num rows: 3 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col3 = 0L)) THEN (true) WHEN (_col3 is null) THEN (true) WHEN (_col7 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (false) ELSE (true) END (type: boolean) Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE @@ -7115,12 +7115,12 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 500 Data size: 95528 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 89016 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: 500 Data size: 95528 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 89016 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col3 (type: bigint), _col4 (type: bigint) Reducer 3 Execution mode: llap @@ -7133,10 +7133,10 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4, _col6, _col7 residual filter predicates: {(_col1 > _col6)} - Statistics: Num rows: 500 Data size: 108068 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 106021 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col3 = 0L)) THEN (true) WHEN (_col3 is null) THEN (true) WHEN (_col7 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 250 Data size: 54034 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 53066 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 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 4423aec8a2..202b88ac78 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out @@ -2327,10 +2327,10 @@ STAGE PLANS: 0 _col0 (type: int), _col5 (type: int) 1 _col2 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 26 Data size: 16262 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16394 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN (_col10 is null) THEN ((UDFToLong(_col5) <> 0)) ELSE ((UDFToLong(_col5) <> _col9)) END (type: boolean) - Statistics: Num rows: 13 Data size: 8131 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 8203 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -5948,10 +5948,10 @@ STAGE PLANS: 0 _col4 (type: string) 1 _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 26 Data size: 16274 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 16370 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN (_col10 is null) THEN ((UDFToLong(_col5) <> 0)) ELSE ((UDFToLong(_col5) <> _col9)) END (type: boolean) - Statistics: Num rows: 13 Data size: 8143 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 8191 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 diff --git a/ql/src/test/results/clientpositive/llap/subquery_select.q.out b/ql/src/test/results/clientpositive/llap/subquery_select.q.out index cf3d60f4b3..172c98970a 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_select.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_select.q.out @@ -263,12 +263,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 26 Data size: 3048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 3176 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 26 Data size: 3048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 3176 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 3 Execution mode: llap @@ -280,7 +280,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: int) 1 _col1 (type: string), _col0 (type: int) outputColumnNames: _col1, _col3, _col4, _col7 - Statistics: Num rows: 26 Data size: 412 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), CASE WHEN ((_col3 = 0L)) THEN (false) WHEN (_col3 is null) THEN (false) WHEN (_col7 is not null) THEN (true) WHEN (_col1 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (null) ELSE (false) END (type: boolean) outputColumnNames: _col0, _col1 @@ -668,10 +668,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 26 Data size: 2928 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 2992 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sq_count_check(CASE WHEN (_col3 is null) THEN (0) ELSE (_col3) END, true) > 0) (type: boolean) - Statistics: Num rows: 8 Data size: 904 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 @@ -692,12 +692,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 8 Data size: 992 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 8 Data size: 992 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 4 Execution mode: llap @@ -709,7 +709,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: int) 1 _col1 (type: string), _col0 (type: int) outputColumnNames: _col1, _col3, _col4, _col7 - Statistics: Num rows: 8 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), CASE WHEN ((_col3 = 0L)) THEN (true) WHEN (_col3 is null) THEN (true) WHEN (_col7 is not null) THEN (false) WHEN (_col1 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (null) ELSE (true) END (type: boolean) outputColumnNames: _col0, _col1 @@ -1028,7 +1028,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col3 - Statistics: Num rows: 26 Data size: 164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col3 is not null (type: boolean) outputColumnNames: _col0, _col1 @@ -1300,7 +1300,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col3 - Statistics: Num rows: 26 Data size: 164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col3 is null (type: boolean) outputColumnNames: _col0, _col1 @@ -1440,7 +1440,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col2 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 26 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 404 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), CASE WHEN (_col3 is null) THEN (0) ELSE (_col2) END (type: bigint) outputColumnNames: _col0, _col1 @@ -1579,7 +1579,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col2 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 26 Data size: 2736 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 4804 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END (type: string) outputColumnNames: _col0, _col1 @@ -2657,7 +2657,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col2 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 26 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), (1 + CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END) (type: int) outputColumnNames: _col0, _col1 @@ -2792,7 +2792,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col2 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 26 Data size: 284 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), CASE WHEN (_col3 is null) THEN (false) ELSE (_col2 is null) END (type: boolean) outputColumnNames: _col0, _col1 @@ -3195,12 +3195,12 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 26 Data size: 6194 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6322 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: int) sort order: ++ Map-reduce partition columns: _col1 (type: string), _col2 (type: int) - Statistics: Num rows: 26 Data size: 6194 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6322 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col4 (type: bigint), _col5 (type: bigint) Reducer 3 Execution mode: llap @@ -3212,10 +3212,10 @@ STAGE PLANS: 0 _col1 (type: string), _col2 (type: int) 1 _col1 (type: string), _col0 (type: int) outputColumnNames: _col0, _col2, _col4, _col5, _col8 - Statistics: Num rows: 26 Data size: 3558 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 3662 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3558 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 3662 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: int), _col4 (type: bigint), _col5 (type: bigint), _col8 (type: boolean) Reducer 4 Execution mode: llap @@ -3227,12 +3227,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col2, _col4, _col5, _col8, _col9, _col10 - Statistics: Num rows: 26 Data size: 3974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 4078 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: 26 Data size: 3974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 4078 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col4 (type: bigint), _col5 (type: bigint), _col8 (type: boolean), _col9 (type: bigint), _col10 (type: bigint) Reducer 5 Execution mode: llap @@ -3244,7 +3244,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2, _col4, _col5, _col8, _col9, _col10, _col12 - Statistics: Num rows: 26 Data size: 3982 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 4086 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: int), (CASE WHEN ((_col4 = 0L)) THEN (false) WHEN (_col4 is null) THEN (false) WHEN (_col8 is not null) THEN (true) WHEN (_col2 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (null) ELSE (false) END and CASE WHEN ((_col9 = 0L)) THEN (false) WHEN (_col12 is not null) THEN (true) WHEN (_col0 is null) THEN (null) WHEN ((_col10 < _col9)) THEN (null) ELSE (false) END) (type: boolean) outputColumnNames: _col0, _col1 @@ -3414,7 +3414,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col3 - Statistics: Num rows: 26 Data size: 164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col3 is null (type: boolean) outputColumnNames: _col0, _col1 @@ -5503,7 +5503,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col2 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 26 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), exp(CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END) (type: double) outputColumnNames: _col0, _col1 diff --git a/ql/src/test/results/clientpositive/llap/tez_join_tests.q.out b/ql/src/test/results/clientpositive/llap/tez_join_tests.q.out index bf2f5a8548..5f55446a28 100644 --- a/ql/src/test/results/clientpositive/llap/tez_join_tests.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_join_tests.q.out @@ -71,12 +71,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6764 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6764 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 3 Execution mode: llap @@ -88,11 +88,11 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 101108 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 101108 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Reducer 4 Execution mode: vectorized, llap @@ -100,10 +100,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 101108 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 101108 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_joins_explain.q.out b/ql/src/test/results/clientpositive/llap/tez_joins_explain.q.out index 72b84a0106..81df0f29e4 100644 --- a/ql/src/test/results/clientpositive/llap/tez_joins_explain.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_joins_explain.q.out @@ -71,12 +71,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6764 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6764 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 3 Execution mode: llap @@ -88,11 +88,11 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 101108 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 101108 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Reducer 4 Execution mode: vectorized, llap @@ -100,10 +100,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 101108 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 101108 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_union.q.out b/ql/src/test/results/clientpositive/llap/tez_union.q.out index 914ed47859..d8da4e25b3 100644 --- a/ql/src/test/results/clientpositive/llap/tez_union.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_union.q.out @@ -1207,10 +1207,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 1 Map 4 - Statistics: Num rows: 1582 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 281774 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1582 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 281774 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1235,10 +1235,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 1 Map 4 - Statistics: Num rows: 1582 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 281774 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1582 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 281774 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1351,10 +1351,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Union 2 - Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 137721 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 137721 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/unionDistinct_1.q.out b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out index f006e37b56..78817b4e16 100644 --- a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out +++ b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out @@ -3804,13 +3804,13 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 332 Data size: 98612 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 103418 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Statistics: Num rows: 332 Data size: 98612 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 103418 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Execution mode: vectorized @@ -4037,14 +4037,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 332 Data size: 98612 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 103418 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 directory: hdfs://### HDFS PATH ### NumFilesPerFileSink: 1 Static Partition Specification: ds=2/ - Statistics: Num rows: 332 Data size: 98612 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 103418 Basic stats: COMPLETE Column stats: COMPLETE Stats Publishing Key Prefix: hdfs://### HDFS PATH ### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -4073,7 +4073,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), '2' (type: string) outputColumnNames: k1, k2, k3, k4, ds - Statistics: Num rows: 332 Data size: 126832 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 131638 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll'), compute_stats(k3, 'hll'), compute_stats(k4, 'hll') keys: ds (type: string) @@ -4141,22 +4141,22 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col4, _col5 Position of Big Table: 0 - Statistics: Num rows: 166 Data size: 39516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 166 Data size: 44322 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 166 Data size: 39516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 166 Data size: 44322 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 332 Data size: 98612 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 103418 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Statistics: Num rows: 332 Data size: 98612 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 103418 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Union 2 diff --git a/ql/src/test/results/clientpositive/llap/vector_coalesce_3.q.out b/ql/src/test/results/clientpositive/llap/vector_coalesce_3.q.out index d05dd70206..2fda57048e 100644 --- a/ql/src/test/results/clientpositive/llap/vector_coalesce_3.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_coalesce_3.q.out @@ -110,7 +110,7 @@ STAGE PLANS: outputColumnNames: _col0, _col2 input vertices: 1 Map 2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), CASE WHEN ((COALESCE(_col2,5) > 1)) THEN (_col2) ELSE (null) END (type: bigint) outputColumnNames: _col0, _col1 diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out index 6443678f89..c7f38bdbf7 100644 --- a/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out @@ -74,14 +74,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col5 input vertices: 1 Reducer 5 - Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97004 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator Filter Vectorization: className: VectorFilterOperator native: true predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 3:bigint, val 0), FilterExprAndExpr(children: SelectColumnIsNull(col 5:boolean), SelectColumnIsNotNull(col 0:string), FilterLongColGreaterEqualLongColumn(col 4:bigint, col 3:bigint))) predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97004 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 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 19e98f3f4a..aa0a46fa3e 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 @@ -119,13 +119,13 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 1 Map 2 - Statistics: Num rows: 9 Data size: 1666 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 926 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9 Data size: 1666 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 926 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -317,13 +317,13 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 9 Data size: 1666 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 926 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9 Data size: 1666 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 926 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 c74a588993..470389198d 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 @@ -279,13 +279,13 @@ 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: 28 Data size: 15376 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 28 Data size: 7995 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 28 Data size: 15376 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 28 Data size: 7995 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 e03948f8b0..6b25672237 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_join46.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_join46.q.out @@ -80,10 +80,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 input vertices: 1 Map 2 - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -183,10 +183,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 input vertices: 1 Map 2 - Statistics: Num rows: 6 Data size: 857 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 952 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 857 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 952 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -407,10 +407,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 input vertices: 0 Map 1 - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -909,10 +909,10 @@ STAGE PLANS: input vertices: 1 Map 2 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1346,10 +1346,10 @@ STAGE PLANS: input vertices: 0 Map 1 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1791,10 +1791,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 10 Data size: 1711 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1711 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10 Data size: 191 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/annotate_stats_join.q.out b/ql/src/test/results/clientpositive/spark/annotate_stats_join.q.out index 7d45328d41..76916201c5 100644 --- a/ql/src/test/results/clientpositive/spark/annotate_stats_join.q.out +++ b/ql/src/test/results/clientpositive/spark/annotate_stats_join.q.out @@ -794,10 +794,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: int) 1 _col1 (type: string), _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 48 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4847 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 48 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4847 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -947,10 +947,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: int) 1 _col1 (type: string), _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 48 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4659 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 48 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 48 Data size: 4659 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1017,10 +1017,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: int) 1 _col1 (type: string), _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 54 Data size: 9506 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 54 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 54 Data size: 9506 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 54 Data size: 194 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 00f5d7ef11..1a8ee5bdbe 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 @@ -903,9 +903,9 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_8] - Select Operator [SEL_7] (rows=80 width=7) + Select Operator [SEL_7] (rows=80 width=4) Output:["_col0","_col1"] - Join Operator [JOIN_6] (rows=80 width=7) + Join Operator [JOIN_6] (rows=80 width=4) Output:["_col1","_col3"],condition map:[{"":"{\"type\":\"Left Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_4] @@ -937,9 +937,9 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_8] - Select Operator [SEL_7] (rows=80 width=7) + Select Operator [SEL_7] (rows=80 width=0) Output:["_col0","_col1"] - Join Operator [JOIN_6] (rows=80 width=7) + Join Operator [JOIN_6] (rows=80 width=0) Output:["_col1","_col3"],condition map:[{"":"{\"type\":\"Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_4] @@ -1665,9 +1665,9 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_19] - Select Operator [SEL_18] (rows=365 width=178) + Select Operator [SEL_18] (rows=315 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_17] (rows=365 width=179) + Filter Operator [FIL_17] (rows=315 width=179) predicate:_col3 is null Join Operator [JOIN_16] (rows=500 width=179) Output:["_col0","_col1","_col3"],condition map:[{"":"{\"type\":\"Left Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col1","1":"_col0"} @@ -1730,11 +1730,11 @@ Stage-0 Stage-1 Reducer 3 File Output Operator [FS_18] - Select Operator [SEL_17] (rows=167 width=178) + Select Operator [SEL_17] (rows=126 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_16] (rows=167 width=179) + Filter Operator [FIL_16] (rows=126 width=180) predicate:_col4 is null - Join Operator [JOIN_15] (rows=250 width=179) + Join Operator [JOIN_15] (rows=250 width=180) Output:["_col0","_col1","_col4"],condition map:[{"":"{\"type\":\"Left Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0, _col1","1":"_col0, _col1"} <-Reducer 2 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_13] @@ -2248,14 +2248,14 @@ Stage-0 File Output Operator [FS_24] Select Operator [SEL_23] (rows=13 width=223) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_22] (rows=13 width=231) + Filter Operator [FIL_22] (rows=13 width=235) predicate:CASE WHEN ((_col4 = 0L)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END - Join Operator [JOIN_21] (rows=26 width=230) + Join Operator [JOIN_21] (rows=26 width=234) Output:["_col0","_col1","_col2","_col4","_col5","_col8"],condition map:[{"":"{\"type\":\"Left Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0, _col1","1":"_col0, _col1"} <-Reducer 2 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_19] PartitionCols:_col0, _col1 - Join Operator [JOIN_18] (rows=26 width=229) + Join Operator [JOIN_18] (rows=26 width=234) Output:["_col0","_col1","_col2","_col4","_col5"],condition map:[{"":"{\"type\":\"Left Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col1","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_16]