diff --git a/data/files/filterCard.txt b/data/files/filterCard.txt new file mode 100644 index 0000000000..6246bfb86e --- /dev/null +++ b/data/files/filterCard.txt @@ -0,0 +1,101 @@ +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +10,10,10 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 +20,20,20 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 423913b56b..cac8a4ab0f 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 @@ -280,7 +280,7 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, // evaluate filter expression and update statistics long newNumRows = evaluateExpression(parentStats, pred, aspCtx, - neededCols, fop, 0); + neededCols, fop, parentStats.getNumRows()); Statistics st = parentStats.clone(); if (satisfyPrecondition(parentStats)) { @@ -318,13 +318,13 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, protected long evaluateExpression(Statistics stats, ExprNodeDesc pred, AnnotateStatsProcCtx aspCtx, List neededCols, - Operator op, long evaluatedRowCount) throws CloneNotSupportedException, SemanticException { + Operator op, long currNumRows) throws CloneNotSupportedException, SemanticException { long newNumRows = 0; Statistics andStats = null; - if (stats.getNumRows() <= 1 || stats.getDataSize() <= 0) { + if (currNumRows <= 1 || stats.getDataSize() <= 0) { if (LOG.isDebugEnabled()) { - LOG.debug("Estimating row count for " + pred + " Original num rows: " + stats.getNumRows() + + LOG.debug("Estimating row count for " + pred + " Original num rows: " + currNumRows + " Original data size: " + stats.getDataSize() + " New num rows: 1"); } return 1; @@ -340,41 +340,41 @@ protected long evaluateExpression(Statistics stats, ExprNodeDesc pred, aspCtx.setAndExprStats(andStats); // evaluate children + long evaluatedRowCount = currNumRows; for (ExprNodeDesc child : genFunc.getChildren()) { - newNumRows = evaluateChildExpr(aspCtx.getAndExprStats(), child, + evaluatedRowCount = evaluateChildExpr(aspCtx.getAndExprStats(), child, aspCtx, neededCols, op, evaluatedRowCount); - if (satisfyPrecondition(aspCtx.getAndExprStats())) { - updateStats(aspCtx.getAndExprStats(), newNumRows, true, op); - } else { - updateStats(aspCtx.getAndExprStats(), newNumRows, false, op); - } + } + newNumRows = evaluatedRowCount; + if (satisfyPrecondition(aspCtx.getAndExprStats())) { + updateStats(aspCtx.getAndExprStats(), newNumRows, true, op); + } else { + updateStats(aspCtx.getAndExprStats(), newNumRows, false, op); } } else if (udf instanceof GenericUDFOPOr) { // for OR condition independently compute and update stats. for (ExprNodeDesc child : genFunc.getChildren()) { // early exit if OR evaluation yields more rows than input rows - if (evaluatedRowCount >= stats.getNumRows()) { - evaluatedRowCount = stats.getNumRows(); - } else { newNumRows = StatsUtils.safeAdd( - evaluateChildExpr(stats, child, aspCtx, neededCols, op, evaluatedRowCount), + evaluateChildExpr(stats, child, aspCtx, neededCols, op, currNumRows), newNumRows); - evaluatedRowCount = newNumRows; - } + } + if(newNumRows > currNumRows) { + newNumRows = currNumRows; } } else if (udf instanceof GenericUDFIn) { // for IN clause - newNumRows = evaluateInExpr(stats, pred, aspCtx, neededCols, op); + newNumRows = evaluateInExpr(stats, pred, currNumRows, aspCtx, neededCols, op); } else if (udf instanceof GenericUDFBetween) { // for BETWEEN clause - newNumRows = evaluateBetweenExpr(stats, pred, aspCtx, neededCols, op); + newNumRows = evaluateBetweenExpr(stats, pred, currNumRows, aspCtx, neededCols, op); } else if (udf instanceof GenericUDFOPNot) { - newNumRows = evaluateNotExpr(stats, pred, aspCtx, neededCols, op); + newNumRows = evaluateNotExpr(stats, pred, currNumRows, aspCtx, neededCols, op); } else if (udf instanceof GenericUDFOPNotNull) { - return evaluateNotNullExpr(stats, genFunc); + return evaluateNotNullExpr(stats, genFunc, currNumRows); } else { // single predicate condition - newNumRows = evaluateChildExpr(stats, pred, aspCtx, neededCols, op, evaluatedRowCount); + newNumRows = evaluateChildExpr(stats, pred, aspCtx, neededCols, op,currNumRows); } } else if (pred instanceof ExprNodeColumnDesc) { @@ -413,10 +413,10 @@ protected long evaluateExpression(Statistics stats, ExprNodeDesc pred, return newNumRows; } - private long evaluateInExpr(Statistics stats, ExprNodeDesc pred, AnnotateStatsProcCtx aspCtx, + private long evaluateInExpr(Statistics stats, ExprNodeDesc pred, long currNumRows, AnnotateStatsProcCtx aspCtx, List neededCols, Operator op) throws SemanticException { - long numRows = stats.getNumRows(); + long numRows = currNumRows; ExprNodeGenericFuncDesc fd = (ExprNodeGenericFuncDesc) pred; @@ -503,7 +503,7 @@ private long evaluateInExpr(Statistics stats, ExprNodeDesc pred, AnnotateStatsPr return Math.round( (double) numRows * factor * inFactor); } - private long evaluateBetweenExpr(Statistics stats, ExprNodeDesc pred, AnnotateStatsProcCtx aspCtx, + private long evaluateBetweenExpr(Statistics stats, ExprNodeDesc pred, long currNumRows, AnnotateStatsProcCtx aspCtx, List neededCols, Operator op) throws SemanticException, CloneNotSupportedException { final ExprNodeGenericFuncDesc fd = (ExprNodeGenericFuncDesc) pred; final boolean invert = Boolean.TRUE.equals( @@ -515,7 +515,7 @@ private long evaluateBetweenExpr(Statistics stats, ExprNodeDesc pred, AnnotateSt // Short circuit and return the current number of rows if this is a // synthetic predicate with dynamic values if (leftExpression instanceof ExprNodeDynamicValueDesc) { - return stats.getNumRows(); + return currNumRows; } // We transform the BETWEEN clause to AND clause (with NOT on top in invert is true). @@ -532,14 +532,14 @@ private long evaluateBetweenExpr(Statistics stats, ExprNodeDesc pred, AnnotateSt new GenericUDFOPNot(), Lists.newArrayList(newExpression)); } - return evaluateExpression(stats, newExpression, aspCtx, neededCols, op, 0); + return evaluateExpression(stats, newExpression, aspCtx, neededCols, op, currNumRows); } - private long evaluateNotExpr(Statistics stats, ExprNodeDesc pred, + private long evaluateNotExpr(Statistics stats, ExprNodeDesc pred, long currNumRows, AnnotateStatsProcCtx aspCtx, List neededCols, Operator op) throws CloneNotSupportedException, SemanticException { - long numRows = stats.getNumRows(); + long numRows = currNumRows; // if the evaluate yields true then pass all rows else pass 0 rows if (pred instanceof ExprNodeGenericFuncDesc) { @@ -551,7 +551,7 @@ private long evaluateNotExpr(Statistics stats, ExprNodeDesc pred, long newNumRows = 0; for (ExprNodeDesc child : genFunc.getChildren()) { newNumRows = evaluateChildExpr(stats, child, aspCtx, neededCols, - op, 0); + op, numRows); } return numRows - newNumRows; } else if (leaf instanceof ExprNodeConstantDesc) { @@ -583,9 +583,9 @@ private long evaluateNotExpr(Statistics stats, ExprNodeDesc pred, return numRows / 2; } - private long evaluateColEqualsNullExpr(Statistics stats, ExprNodeDesc pred) { + private long evaluateColEqualsNullExpr(Statistics stats, ExprNodeDesc pred, long currNumRows) { - long numRows = stats.getNumRows(); + long numRows = currNumRows; if (pred instanceof ExprNodeGenericFuncDesc) { @@ -607,9 +607,9 @@ private long evaluateColEqualsNullExpr(Statistics stats, ExprNodeDesc pred) { return numRows / 2; } - private long evaluateNotNullExpr(Statistics parentStats, ExprNodeGenericFuncDesc pred) { + private long evaluateNotNullExpr(Statistics parentStats, ExprNodeGenericFuncDesc pred, long currNumRows) { long noOfNulls = getMaxNulls(parentStats, pred); - long parentCardinality = parentStats.getNumRows(); + long parentCardinality = currNumRows; long newPredCardinality = parentCardinality; if (parentCardinality > noOfNulls) { @@ -659,8 +659,8 @@ private long getMaxNulls(Statistics stats, ExprNodeDesc pred) { return maxNoNulls; } - private long evaluateComparator(Statistics stats, ExprNodeGenericFuncDesc genFunc) { - long numRows = stats.getNumRows(); + private long evaluateComparator(Statistics stats, ExprNodeGenericFuncDesc genFunc, long currNumRows) { + long numRows = currNumRows; GenericUDF udf = genFunc.getGenericUDF(); ExprNodeColumnDesc columnDesc; @@ -836,9 +836,9 @@ private long evaluateComparator(Statistics stats, ExprNodeGenericFuncDesc genFun private long evaluateChildExpr(Statistics stats, ExprNodeDesc child, AnnotateStatsProcCtx aspCtx, List neededCols, - Operator op, long evaluatedRowCount) throws CloneNotSupportedException, SemanticException { + Operator op, long currNumRows) throws CloneNotSupportedException, SemanticException { - long numRows = stats.getNumRows(); + long numRows = currNumRows; if (child instanceof ExprNodeGenericFuncDesc) { @@ -915,15 +915,15 @@ private long evaluateChildExpr(Statistics stats, ExprNodeDesc child, || udf instanceof GenericUDFOPEqualOrLessThan || udf instanceof GenericUDFOPGreaterThan || udf instanceof GenericUDFOPLessThan) { - return evaluateComparator(stats, genFunc); + return evaluateComparator(stats, genFunc, numRows); } else if (udf instanceof GenericUDFOPNotNull) { - return evaluateNotNullExpr(stats, genFunc); + return evaluateNotNullExpr(stats, genFunc, numRows); } else if (udf instanceof GenericUDFOPNull) { - return evaluateColEqualsNullExpr(stats, genFunc); + return evaluateColEqualsNullExpr(stats, genFunc, numRows); } else if (udf instanceof GenericUDFOPAnd || udf instanceof GenericUDFOPOr || udf instanceof GenericUDFIn || udf instanceof GenericUDFBetween || udf instanceof GenericUDFOPNot) { - return evaluateExpression(stats, genFunc, aspCtx, neededCols, op, evaluatedRowCount); + return evaluateExpression(stats, genFunc, aspCtx, neededCols, op, numRows); } else if (udf instanceof GenericUDFInBloomFilter) { if (genFunc.getChildren().get(1) instanceof ExprNodeDynamicValueDesc) { // Synthetic predicates from semijoin opt should not affect stats. @@ -934,7 +934,7 @@ private long evaluateChildExpr(Statistics stats, ExprNodeDesc child, if (Boolean.FALSE.equals(((ExprNodeConstantDesc) child).getValue())) { return 0; } else { - return stats.getNumRows(); + return numRows; } } @@ -1582,7 +1582,7 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, // evaluate filter expression and update statistics try { newNumRows = evaluateExpression(stats, pred, - aspCtx, jop.getSchema().getColumnNames(), jop, 0); + aspCtx, jop.getSchema().getColumnNames(), jop, stats.getNumRows()); } catch (CloneNotSupportedException e) { throw new SemanticException(ErrorMsg.STATISTICS_CLONING_FAILED.getMsg()); } diff --git a/ql/src/test/queries/clientpositive/filter_cardinality.q b/ql/src/test/queries/clientpositive/filter_cardinality.q new file mode 100644 index 0000000000..2dfd2462c6 --- /dev/null +++ b/ql/src/test/queries/clientpositive/filter_cardinality.q @@ -0,0 +1,21 @@ +-- to test cardinality of filter in physical planning +set hive.stats.fetch.column.stats=true; +set hive.explain.user=false; + +CREATE TABLE mytable +( +num1 INT, +num2 INT, +num3 INT +) +ROW FORMAT DELIMITED FIELDS TERMINATED BY ","; + +LOAD DATA LOCAL inpath "../../data/files/filterCard.txt" into table mytable; + +ANALYZE table mytable compute statistics for columns; + +explain select * from mytable where num1=4; +explain select * from mytable where num1=4 and num2=8; +explain select * from mytable where num1=4 and num2=8 and num3=7; + +drop table mytable; diff --git a/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out b/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out index 6e2975e671..4d25644a3b 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_deep_filters.q.out @@ -121,9 +121,9 @@ STAGE PLANS: Statistics: Num rows: 2098 Data size: 16744 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((t = 1) and (si = 2)) or ((t = 2) and (si = 3)) or ((t = 3) and (si = 4)) or ((t = 4) and (si = 5)) or ((t = 5) and (si = 6)) or ((t = 6) and (si = 7)) or ((t = 7) and (si = 8)) or ((t = 9) and (si = 10)) or ((t = 10) and (si = 11)) or ((t = 11) and (si = 12)) or ((t = 12) and (si = 13)) or ((t = 13) and (si = 14)) or ((t = 14) and (si = 15)) or ((t = 15) and (si = 16)) or ((t = 16) and (si = 17)) or ((t = 17) and (si = 18)) or ((t = 27) and (si = 28)) or ((t = 37) and (si = 38)) or ((t = 47) and (si = 48)) or ((t = 52) and (si = 53))) (type: boolean) - Statistics: Num rows: 160 Data size: 1280 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 160 Data size: 1280 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -210,9 +210,9 @@ STAGE PLANS: Statistics: Num rows: 2098 Data size: 211174 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((t = 1) and (si = 2)) or ((t = 2) and (si = 3)) or ((t = 3) and (si = 4)) or ((t = 4) and (si = 5)) or ((t = 5) and (si = 6)) or ((t = 6) and (si = 7)) or ((t = 7) and (si = 8)) or ((t = 9) and (si = 10)) or ((t = 10) and (si = 11)) or ((t = 11) and (si = 12)) or ((t = 12) and (si = 13)) or ((t = 13) and (si = 14)) or ((t = 14) and (si = 15)) or ((t = 15) and (si = 16)) or ((t = 16) and (si = 17)) or ((t = 17) and (si = 18)) or ((t = 27) and (si = 28)) or ((t = 37) and (si = 38)) or ((t = 47) and (si = 48)) or ((t = 52) and (si = 53))) (type: boolean) - Statistics: Num rows: 2098 Data size: 211174 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 201 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 2098 Data size: 211174 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 201 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/annotate_stats_filter.q.out b/ql/src/test/results/clientpositive/annotate_stats_filter.q.out index b2f983606e..b019a0707a 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_filter.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_filter.q.out @@ -629,14 +629,14 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((state = 'OH') or (state = 'CA')) (type: boolean) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -737,14 +737,14 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((year = 2001) and year is null) or (state = 'CA')) (type: boolean) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 102 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/annotate_stats_join_pkfk.q.out b/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out index e04c1c6bc5..d88819a1ec 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out @@ -577,16 +577,16 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 7676 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 321 Data size: 2468 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 2284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 321 Data size: 2468 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 2284 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 321 Data size: 2468 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 2284 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -595,10 +595,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 131 Data size: 524 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 122 Data size: 488 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 131 Data size: 524 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 122 Data size: 488 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -707,16 +707,16 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 7676 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 321 Data size: 2468 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 2284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 321 Data size: 2468 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 2284 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 321 Data size: 2468 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 2284 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -725,10 +725,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 1188 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 1188 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1015,16 +1015,16 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 7676 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 321 Data size: 2468 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 2284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 321 Data size: 2468 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 2284 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 321 Data size: 2468 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 2284 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE @@ -1065,14 +1065,14 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col2 - Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 1188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 1188 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 297 Data size: 1188 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1102,16 +1102,16 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 7664 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_store_sk is not null and ss_addr_sk is not null) (type: boolean) - Statistics: Num rows: 916 Data size: 7020 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 914 Data size: 7004 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_addr_sk (type: int), ss_store_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 916 Data size: 7020 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 914 Data size: 7004 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 916 Data size: 7020 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 914 Data size: 7004 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan alias: s @@ -1136,7 +1136,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 916 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 914 Data size: 7132 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1152,7 +1152,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 916 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 914 Data size: 7132 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int) TableScan alias: ca @@ -1177,14 +1177,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col2 - Statistics: Num rows: 241 Data size: 964 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 243 Data size: 972 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 241 Data size: 964 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 243 Data size: 972 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 241 Data size: 964 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 243 Data size: 972 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/correlationoptimizer8.q.out b/ql/src/test/results/clientpositive/correlationoptimizer8.q.out index f3cb988a03..c541a7ba48 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer8.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer8.q.out @@ -84,16 +84,16 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -259,30 +259,30 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 348 Data size: 3648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 3533 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 174 Data size: 1824 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1761 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 348 Data size: 3648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 3522 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 696 Data size: 7296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 665 Data size: 7055 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 @@ -307,11 +307,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 174 Data size: 1824 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1761 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 348 Data size: 3648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 3522 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 696 Data size: 7296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 665 Data size: 7055 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 @@ -332,7 +332,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 696 Data size: 7296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 665 Data size: 7055 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 @@ -902,16 +902,16 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator diff --git a/ql/src/test/results/clientpositive/filter_cardinality.q.out b/ql/src/test/results/clientpositive/filter_cardinality.q.out new file mode 100644 index 0000000000..de41578adc --- /dev/null +++ b/ql/src/test/results/clientpositive/filter_cardinality.q.out @@ -0,0 +1,152 @@ +PREHOOK: query: CREATE TABLE mytable +( +num1 INT, +num2 INT, +num3 INT +) +ROW FORMAT DELIMITED FIELDS TERMINATED BY "," +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@mytable +POSTHOOK: query: CREATE TABLE mytable +( +num1 INT, +num2 INT, +num3 INT +) +ROW FORMAT DELIMITED FIELDS TERMINATED BY "," +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@mytable +PREHOOK: query: LOAD DATA LOCAL inpath "../../data/files/filterCard.txt" into table mytable +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@mytable +POSTHOOK: query: LOAD DATA LOCAL inpath "../../data/files/filterCard.txt" into table mytable +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@mytable +PREHOOK: query: ANALYZE table mytable compute statistics for columns +PREHOOK: type: QUERY +PREHOOK: Input: default@mytable +#### A masked pattern was here #### +POSTHOOK: query: ANALYZE table mytable compute statistics for columns +POSTHOOK: type: QUERY +POSTHOOK: Input: default@mytable +#### A masked pattern was here #### +PREHOOK: query: explain select * from mytable where num1=4 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from mytable where num1=4 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: mytable + Statistics: Num rows: 75 Data size: 900 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (num1 = 4) (type: boolean) + Statistics: Num rows: 38 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 4 (type: int), num2 (type: int), num3 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 38 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 38 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select * from mytable where num1=4 and num2=8 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from mytable where num1=4 and num2=8 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: mytable + Statistics: Num rows: 75 Data size: 900 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((num1 = 4) and (num2 = 8)) (type: boolean) + Statistics: Num rows: 19 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 4 (type: int), 8 (type: int), num3 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 19 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 19 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select * from mytable where num1=4 and num2=8 and num3=7 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from mytable where num1=4 and num2=8 and num3=7 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: mytable + Statistics: Num rows: 75 Data size: 900 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((num1 = 4) and (num2 = 8) and (num3 = 7)) (type: boolean) + Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 4 (type: int), 8 (type: int), 7 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: drop table mytable +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@mytable +PREHOOK: Output: default@mytable +POSTHOOK: query: drop table mytable +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@mytable +POSTHOOK: Output: default@mytable diff --git a/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out b/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out index d986120357..d9e88f3d5a 100644 --- a/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out +++ b/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out @@ -38,16 +38,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((value = '2008-04-08') or (value = '2008-04-09')) and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -60,7 +60,7 @@ STAGE PLANS: Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((_col3 = '2008-04-08') and (_col1 = '2008-04-08')) or (_col3 = '2008-04-09')) (type: boolean) - Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -76,7 +76,7 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: string) TableScan alias: g @@ -160,16 +160,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((value) IN ('2008-04-08', '2008-04-10') or (value = '2008-04-09')) and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -182,7 +182,7 @@ STAGE PLANS: Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((_col3) IN ('2008-04-08', '2008-04-10') and (_col1 = '2008-04-08')) or (_col3 = '2008-04-09')) (type: boolean) - Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -198,7 +198,7 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: string) TableScan alias: g @@ -314,11 +314,11 @@ STAGE PLANS: Statistics: Num rows: 11 Data size: 144 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((_col2 + _col4) > 2) or ((_col1 + 1) > 2)) (type: boolean) - Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -349,7 +349,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -412,16 +412,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((value <> '') and ((value = '2008-04-10') or (value = '2008-04-08')) and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -434,14 +434,14 @@ STAGE PLANS: Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((_col1) IN ('2008-04-08', '2008-04-10') and (_col1) IN ('2008-04-08', '2008-04-09') and (_col3 = '2008-04-10')) or (_col3 = '2008-04-08')) (type: boolean) - Statistics: Num rows: 344 Data size: 3654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 344 Data size: 3654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 344 Data size: 3654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE 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/fold_eq_with_case_when.q.out b/ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out index 4de8d01473..192e871bac 100644 --- a/ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out +++ b/ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out @@ -138,14 +138,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '238') or (key = '94')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE 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/folder_predicate.q.out b/ql/src/test/results/clientpositive/folder_predicate.q.out index 0dd73473c5..913fc46080 100644 --- a/ql/src/test/results/clientpositive/folder_predicate.q.out +++ b/ql/src/test/results/clientpositive/folder_predicate.q.out @@ -36,14 +36,14 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value is null or (value <> 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -87,14 +87,14 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value is null or (value < 3)) (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -136,14 +136,14 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value is null or (value > 3)) (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -185,14 +185,14 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value is null or (value <= 3)) (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -235,14 +235,14 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value is null or (value >= 3)) (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -285,14 +285,14 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value is null or (value = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -333,14 +333,14 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value is null or (value <= 1) or (value > 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE 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/groupby_grouping_sets_grouping.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets_grouping.q.out index 39dd731f34..c493b37e35 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets_grouping.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets_grouping.q.out @@ -315,11 +315,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((grouping(_col2, 1) = 1) or (grouping(_col2, 0) = 1)) (type: boolean) - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), (grouping(_col2, 1) + grouping(_col2, 0)) (type: int), CASE WHEN (((grouping(_col2, 1) + grouping(_col2, 0)) = 1)) THEN (_col0) ELSE (null) END (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -334,16 +334,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col2 (type: int), _col3 (type: int) sort order: -+ - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -668,22 +668,22 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((grouping(_col2, 1) = 1) or (grouping(_col2, 0) = 1)) (type: boolean) - Statistics: Num rows: 12 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 12 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), (grouping(_col2, 1) + grouping(_col2, 0)) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -698,16 +698,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col2 (type: int), CASE WHEN ((_col2 = 1)) THEN (_col0) END (type: int) sort order: -+ - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE 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/groupby_multi_single_reducer3.q.out b/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out index e41d9ef021..0c8d0855a8 100644 --- a/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out +++ b/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out @@ -52,32 +52,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((value) IN ('val_400', 'val_500') and (key) IN (400, 450)) or ((value) IN ('val_100', 'val_200', 'val_300') and (key) IN (100, 150, 200))) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE value expressions: value (type: string) Reduce Operator Tree: Forward - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((VALUE._col0) IN ('val_100', 'val_200', 'val_300') and (KEY._col0) IN (100, 150, 200)) (type: boolean) - Statistics: Num rows: 63 Data size: 669 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -85,20 +85,20 @@ STAGE PLANS: name: default.e1 Filter Operator predicate: ((VALUE._col0) IN ('val_400', 'val_500') and (KEY._col0) IN (400, 450)) (type: boolean) - Statistics: Num rows: 63 Data size: 669 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -218,32 +218,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key + key) = 400) or (((key - 100) = 500) and value is not null)) or (((key + key) = 200) or ((key - 100) = 100) or ((key = 300) and value is not null))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: value (type: string) sort order: + Map-reduce partition columns: value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string) Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((VALUE._col0 + VALUE._col0) = 200) or ((VALUE._col0 - 100) = 100) or ((VALUE._col0 = 300) and KEY._col0 is not null)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -251,20 +251,20 @@ STAGE PLANS: name: default.e1 Filter Operator predicate: (((VALUE._col0 + VALUE._col0) = 400) or (((VALUE._col0 - 100) = 500) and KEY._col0 is not null)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -384,32 +384,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((value) IN ('val_400', 'val_500') and (key) IN (400, 450)) or ((value) IN ('val_100', 'val_200', 'val_300') and (key) IN (100, 150, 200))) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE value expressions: value (type: string) Reduce Operator Tree: Forward - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((VALUE._col0) IN ('val_100', 'val_200', 'val_300') and (KEY._col0) IN (100, 150, 200)) (type: boolean) - Statistics: Num rows: 63 Data size: 669 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -417,20 +417,20 @@ STAGE PLANS: name: default.e1 Filter Operator predicate: ((VALUE._col0) IN ('val_400', 'val_500') and (KEY._col0) IN (400, 450)) (type: boolean) - Statistics: Num rows: 63 Data size: 669 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -550,32 +550,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key + key) = 400) or (((key - 100) = 500) and value is not null)) or (((key + key) = 200) or ((key - 100) = 100) or ((key = 300) and value is not null))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: value (type: string) sort order: + Map-reduce partition columns: value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string) Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((VALUE._col0 + VALUE._col0) = 200) or ((VALUE._col0 - 100) = 100) or ((VALUE._col0 = 300) and KEY._col0 is not null)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -583,20 +583,20 @@ STAGE PLANS: name: default.e1 Filter Operator predicate: (((VALUE._col0 + VALUE._col0) = 400) or (((VALUE._col0 - 100) = 500) and KEY._col0 is not null)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/index_auto_unused.q.out b/ql/src/test/results/clientpositive/index_auto_unused.q.out index cff53137cd..be3fb6f24e 100644 --- a/ql/src/test/results/clientpositive/index_auto_unused.q.out +++ b/ql/src/test/results/clientpositive/index_auto_unused.q.out @@ -162,14 +162,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) < 10.0) or (UDFToDouble(key) > 480.0)) (type: boolean) - Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE 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/join34.q.out b/ql/src/test/results/clientpositive/join34.q.out index 67599bc991..b023c59cfa 100644 --- a/ql/src/test/results/clientpositive/join34.q.out +++ b/ql/src/test/results/clientpositive/join34.q.out @@ -48,11 +48,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) diff --git a/ql/src/test/results/clientpositive/join35.q.out b/ql/src/test/results/clientpositive/join35.q.out index ade6646caa..6b92ec2dc7 100644 --- a/ql/src/test/results/clientpositive/join35.q.out +++ b/ql/src/test/results/clientpositive/join35.q.out @@ -154,11 +154,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) diff --git a/ql/src/test/results/clientpositive/join45.q.out b/ql/src/test/results/clientpositive/join45.q.out index 3c373e64a4..362cac68aa 100644 --- a/ql/src/test/results/clientpositive/join45.q.out +++ b/ql/src/test/results/clientpositive/join45.q.out @@ -362,13 +362,13 @@ STAGE PLANS: Statistics: Num rows: 12500 Data size: 240800 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col0 = _col2) or UDFToDouble(_col1) BETWEEN 100.0 AND 102.0 or UDFToDouble(_col3) BETWEEN 100.0 AND 102.0) (type: boolean) - Statistics: Num rows: 9026 Data size: 173876 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 38 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 38 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 38 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -566,13 +566,13 @@ STAGE PLANS: Statistics: Num rows: 12500 Data size: 240800 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0) or ((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0)) (type: boolean) - Statistics: Num rows: 8332 Data size: 160507 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1680,17 +1680,17 @@ STAGE PLANS: Statistics: Num rows: 176000 Data size: 9396800 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((_col0 = _col24) or ((_col1 = _col25) and (_col26 = _col20))) and ((_col12 = _col24) or ((_col27 = _col15) and (_col13 = _col25))) and ((_col6 = _col24) or ((_col28 = _col16) and (_col8 = 42)))) (type: boolean) - Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: string), _col19 (type: string), _col20 (type: int), _col21 (type: float), _col22 (type: boolean), _col23 (type: string), _col24 (type: string), _col25 (type: string), _col26 (type: int), _col27 (type: float), _col28 (type: boolean), _col29 (type: string), _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: float), _col16 (type: boolean), _col17 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: float), _col10 (type: boolean), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE 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/join47.q.out b/ql/src/test/results/clientpositive/join47.q.out index 20dce5d3bb..1fca7475be 100644 --- a/ql/src/test/results/clientpositive/join47.q.out +++ b/ql/src/test/results/clientpositive/join47.q.out @@ -360,13 +360,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((_col0 = _col2) or UDFToDouble(_col1) BETWEEN 100.0 AND 102.0 or UDFToDouble(_col3) BETWEEN 100.0 AND 102.0)} - Statistics: Num rows: 9026 Data size: 173876 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -463,13 +463,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0)} {((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0)} - Statistics: Num rows: 1388 Data size: 26738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -560,13 +560,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {(((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0) or ((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0))} - Statistics: Num rows: 8332 Data size: 160507 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -659,13 +659,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {(struct(_col0,_col2)) IN (const struct(100,100), const struct(101,101), const struct(102,102))} - Statistics: Num rows: 3125 Data size: 60200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -788,17 +788,17 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) >= 100.0)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -933,13 +933,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1035,7 +1035,7 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((UDFToDouble(_col2) + UDFToDouble(_col0)) >= 100.0)} - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1051,7 +1051,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b @@ -1074,13 +1074,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4582 Data size: 88278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1215,13 +1215,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1307,7 +1307,7 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((UDFToDouble(_col2) + UDFToDouble(_col0)) >= 100.0)} - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1323,7 +1323,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b @@ -1346,13 +1346,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4582 Data size: 88278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1487,13 +1487,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1658,17 +1658,17 @@ STAGE PLANS: 3 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 residual filter predicates: {((_col6 = _col24) or ((_col28 = _col16) and (_col8 = 42)))} {((_col12 = _col24) or ((_col27 = _col15) and (_col13 = _col25)))} {((_col0 = _col24) or ((_col1 = _col25) and (_col26 = _col20)))} - Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: string), _col19 (type: string), _col20 (type: int), _col21 (type: float), _col22 (type: boolean), _col23 (type: string), _col24 (type: string), _col25 (type: string), _col26 (type: int), _col27 (type: float), _col28 (type: boolean), _col29 (type: string), _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: float), _col16 (type: boolean), _col17 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: float), _col10 (type: boolean), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE 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/bucketsortoptimize_insert_7.q.out b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out index 62ed4c8a64..41b477d70b 100644 --- a/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out +++ b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out @@ -88,16 +88,16 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -108,11 +108,11 @@ STAGE PLANS: Statistics: Num rows: 84 Data size: 15964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -122,16 +122,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col4 input vertices: 0 Map 1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), concat(_col1, _col4) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -141,10 +141,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -271,16 +271,16 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -291,11 +291,11 @@ STAGE PLANS: Statistics: Num rows: 84 Data size: 15964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -305,16 +305,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), concat(_col1, _col3) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -324,10 +324,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -460,16 +460,16 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < 8) and ((key = 0) or (key = 5))) (type: boolean) - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -480,11 +480,11 @@ STAGE PLANS: Statistics: Num rows: 84 Data size: 15964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < 8) and ((key = 0) or (key = 5))) (type: boolean) - Statistics: Num rows: 10 Data size: 1900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 1900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -494,16 +494,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), concat(_col1, _col3) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -513,10 +513,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out index ffc39575d1..7cabdb12f3 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out @@ -2400,9 +2400,9 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col4 residual filter predicates: {((_col0 = _col2) or (_col1 = _col4))} - Statistics: Num rows: 4000 Data size: 4420000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1105 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 4000 Data size: 4420000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1105 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -5938,45 +5938,45 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 2944 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), UDFToDouble(_col2) (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: string), UDFToDouble(_col2) (type: double) - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart_orc Partition key expr: ds - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Target Vertex: Map 1 Select Operator expressions: UDFToDouble(_col2) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Dynamic Partitioning Event Operator Target column: hr (int) Target Input: srcpart_orc Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Target Vertex: Map 1 Execution mode: llap LLAP IO: no inputs diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out index fe86a60974..63ed5c79d4 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out @@ -176,16 +176,16 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), _col0 (type: smallint) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: vectorized, llap LLAP IO: all inputs @@ -195,11 +195,11 @@ STAGE PLANS: Select Operator expressions: KEY._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -251,11 +251,11 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE @@ -343,16 +343,16 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: vectorized, llap LLAP IO: all inputs @@ -362,11 +362,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -416,16 +416,16 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -435,11 +435,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -557,16 +557,16 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), _col0 (type: smallint) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: vectorized, llap LLAP IO: all inputs @@ -576,11 +576,11 @@ STAGE PLANS: Select Operator expressions: KEY._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -632,11 +632,11 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE @@ -724,16 +724,16 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: vectorized, llap LLAP IO: all inputs @@ -743,11 +743,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -797,16 +797,16 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -816,11 +816,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1340,15 +1340,15 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -1358,10 +1358,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col1 (type: bigint), VALUE._col2 (type: float), VALUE._col3 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1412,16 +1412,16 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col2 (type: bigint), _col3 (type: float) Execution mode: vectorized, llap LLAP IO: all inputs @@ -1431,11 +1431,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), KEY._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1509,16 +1509,16 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col0 is null or (_col0 = 27)) (type: boolean) - Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint) sort order: + Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Reducer 3 Execution mode: vectorized, llap @@ -1526,11 +1526,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1581,17 +1581,17 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) sort order: +++++ Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -1601,14 +1601,14 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 28 Data size: 639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 593 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 28 Data size: 639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 593 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 28 Data size: 639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 593 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1659,17 +1659,17 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) sort order: +++++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -1679,15 +1679,15 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 28 Data size: 639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 593 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 28 Data size: 639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 593 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 28 Data size: 639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 593 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2050,16 +2050,16 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col3 (type: float) sort order: + Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col4 (type: tinyint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2069,10 +2069,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY.reducesinkkey0 (type: float), VALUE._col3 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2122,16 +2122,16 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 23952 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2141,11 +2141,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 57 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1187 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out index 36898ceed9..bfb9a5d9ff 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out @@ -133,16 +133,16 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint) sort order: + Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: llap LLAP IO: no inputs @@ -152,11 +152,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -208,11 +208,11 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE @@ -300,16 +300,16 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: llap LLAP IO: no inputs @@ -319,11 +319,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -373,16 +373,16 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -392,11 +392,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -514,16 +514,16 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint) sort order: + Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: llap LLAP IO: no inputs @@ -533,11 +533,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -589,11 +589,11 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE @@ -681,16 +681,16 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: llap LLAP IO: no inputs @@ -700,11 +700,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -754,16 +754,16 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -773,11 +773,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1297,15 +1297,15 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) Execution mode: llap LLAP IO: no inputs @@ -1315,10 +1315,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col1 (type: bigint), VALUE._col2 (type: float), VALUE._col3 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1369,16 +1369,16 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col2 (type: bigint), _col3 (type: float) Execution mode: llap LLAP IO: no inputs @@ -1388,11 +1388,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), KEY._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1466,16 +1466,16 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col0 is null or (_col0 = 27)) (type: boolean) - Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint) sort order: + Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Reducer 3 Execution mode: llap @@ -1483,11 +1483,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 10 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1538,17 +1538,17 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) sort order: +++++ Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1558,14 +1558,14 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 113 Data size: 2577 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 2531 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 113 Data size: 2577 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 2531 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 113 Data size: 2577 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 2531 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1616,17 +1616,17 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) sort order: +++++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1636,15 +1636,15 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 113 Data size: 2577 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 2531 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 113 Data size: 2577 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 2531 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 113 Data size: 2577 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 2531 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2007,16 +2007,16 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col3 (type: float) sort order: + Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col4 (type: tinyint) Execution mode: llap LLAP IO: no inputs @@ -2026,10 +2026,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY.reducesinkkey0 (type: float), VALUE._col3 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2079,16 +2079,16 @@ STAGE PLANS: Statistics: Num rows: 4443 Data size: 101328 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -2098,11 +2098,11 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 227 Data size: 5177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 222 Data size: 5062 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out index 48c02a24ad..7a07b041bc 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out @@ -388,25 +388,25 @@ Stage-0 <-Map 5 [SIMPLE_EDGE] llap SHUFFLE [RS_7] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_6] (rows=2 width=101) + Group By Operator [GBY_6] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float - Filter Operator [FIL_39] (rows=5 width=93) + Filter Operator [FIL_39] (rows=1 width=93) predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and key is not null) TableScan [TS_3] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 8 [SIMPLE_EDGE] llap SHUFFLE [RS_21] PartitionCols:_col0 - Select Operator [SEL_17] (rows=2 width=89) + Select Operator [SEL_17] (rows=1 width=89) Output:["_col0","_col1"] - Group By Operator [GBY_16] (rows=2 width=93) + Group By Operator [GBY_16] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 <-Map 7 [SIMPLE_EDGE] llap SHUFFLE [RS_15] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_14] (rows=2 width=93) + Group By Operator [GBY_14] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float - Filter Operator [FIL_40] (rows=5 width=93) + Filter Operator [FIL_40] (rows=1 width=93) predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and key is not null) TableScan [TS_11] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -468,7 +468,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_6] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float - Filter Operator [FIL_39] (rows=2 width=93) + Filter Operator [FIL_39] (rows=1 width=93) predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null) TableScan [TS_3] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -484,7 +484,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_14] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float - Filter Operator [FIL_40] (rows=2 width=93) + Filter Operator [FIL_40] (rows=1 width=93) predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null) TableScan [TS_11] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -539,7 +539,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_6] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float - Filter Operator [FIL_36] (rows=2 width=93) + Filter Operator [FIL_36] (rows=1 width=93) predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null) TableScan [TS_3] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -555,7 +555,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_14] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float - Filter Operator [FIL_37] (rows=2 width=93) + Filter Operator [FIL_37] (rows=1 width=93) predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null) TableScan [TS_11] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -615,7 +615,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_6] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float - Filter Operator [FIL_38] (rows=2 width=93) + Filter Operator [FIL_38] (rows=1 width=93) predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null) TableScan [TS_3] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -631,7 +631,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_14] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float - Filter Operator [FIL_39] (rows=2 width=93) + Filter Operator [FIL_39] (rows=1 width=93) predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null) TableScan [TS_11] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -686,7 +686,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_6] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float - Filter Operator [FIL_36] (rows=2 width=93) + Filter Operator [FIL_36] (rows=1 width=93) predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null) TableScan [TS_3] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -702,7 +702,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_14] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float - Filter Operator [FIL_37] (rows=2 width=93) + Filter Operator [FIL_37] (rows=1 width=93) predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null) TableScan [TS_11] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -1088,25 +1088,25 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_14] - Select Operator [SEL_13] (rows=40 width=101) + Select Operator [SEL_13] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_24] (rows=40 width=101) + Merge Join Operator [MERGEJOIN_24] (rows=1 width=101) Conds:RS_9._col0=RS_10._col0(Inner),RS_9._col0=RS_11._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6"],residual filter predicates:{((_col1 + _col4) = 2)} {((_col1 > 0) or (_col6 >= 0))} <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_9] PartitionCols:_col0 - Select Operator [SEL_2] (rows=9 width=93) + Select Operator [SEL_2] (rows=1 width=93) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_21] (rows=9 width=93) + Filter Operator [FIL_21] (rows=1 width=93) predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null) TableScan [TS_0] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_10] PartitionCols:_col0 - Select Operator [SEL_5] (rows=9 width=89) + Select Operator [SEL_5] (rows=1 width=89) Output:["_col0","_col1"] - Filter Operator [FIL_22] (rows=9 width=93) + Filter Operator [FIL_22] (rows=1 width=93) predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null) TableScan [TS_3] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -1135,25 +1135,25 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_14] - Select Operator [SEL_13] (rows=40 width=101) + Select Operator [SEL_13] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_24] (rows=40 width=101) + Merge Join Operator [MERGEJOIN_24] (rows=1 width=101) Conds:RS_9._col0=RS_10._col0(Inner),RS_9._col0=RS_11._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6"],residual filter predicates:{((_col1 + _col4) = 2)} {((_col1 > 0) or (_col6 >= 0))} <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_9] PartitionCols:_col0 - Select Operator [SEL_2] (rows=9 width=93) + Select Operator [SEL_2] (rows=1 width=93) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_21] (rows=9 width=93) + Filter Operator [FIL_21] (rows=1 width=93) predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null) TableScan [TS_0] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_10] PartitionCols:_col0 - Select Operator [SEL_5] (rows=9 width=89) + Select Operator [SEL_5] (rows=1 width=89) Output:["_col0","_col1"] - Filter Operator [FIL_22] (rows=9 width=93) + Filter Operator [FIL_22] (rows=1 width=93) predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null) TableScan [TS_3] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -1339,9 +1339,9 @@ Stage-0 PartitionCols:_col0, _col1 Group By Operator [GBY_36] (rows=1 width=20) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col4, _col6 - Select Operator [SEL_35] (rows=2 width=20) + Select Operator [SEL_35] (rows=1 width=20) Output:["_col4","_col6"] - Merge Join Operator [MERGEJOIN_56] (rows=2 width=20) + Merge Join Operator [MERGEJOIN_56] (rows=1 width=20) Conds:RS_31._col0=RS_32._col0(Inner),RS_32._col0=RS_33._col0(Inner),Output:["_col1","_col3","_col4","_col6"],residual filter predicates:{((_col3 + _col1) >= 0)} {((_col3 > 0) or (_col6 >= 0))} <-Map 10 [SIMPLE_EDGE] llap SHUFFLE [RS_33] @@ -1355,48 +1355,48 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] llap SHUFFLE [RS_31] PartitionCols:_col0 - Filter Operator [FIL_12] (rows=2 width=105) + Filter Operator [FIL_12] (rows=1 width=105) predicate:_col0 is not null - Limit [LIM_10] (rows=3 width=105) + Limit [LIM_10] (rows=1 width=105) Number of rows:5 - Select Operator [SEL_9] (rows=3 width=105) + Select Operator [SEL_9] (rows=1 width=105) Output:["_col0","_col1"] <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_8] - Select Operator [SEL_6] (rows=3 width=105) + Select Operator [SEL_6] (rows=1 width=105) Output:["_col0","_col1","_col2","_col5"] - Group By Operator [GBY_5] (rows=3 width=101) + Group By Operator [GBY_5] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_4] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_3] (rows=3 width=101) + Group By Operator [GBY_3] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float - Filter Operator [FIL_52] (rows=6 width=93) + Filter Operator [FIL_52] (rows=1 width=93) predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0))) TableScan [TS_0] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Reducer 9 [SIMPLE_EDGE] llap SHUFFLE [RS_32] PartitionCols:_col0 - Filter Operator [FIL_26] (rows=2 width=97) + Filter Operator [FIL_26] (rows=1 width=97) predicate:_col0 is not null - Limit [LIM_24] (rows=3 width=97) + Limit [LIM_24] (rows=1 width=97) Number of rows:5 - Select Operator [SEL_23] (rows=3 width=97) + Select Operator [SEL_23] (rows=1 width=97) Output:["_col0","_col1","_col2"] <-Reducer 8 [SIMPLE_EDGE] llap SHUFFLE [RS_22] - Select Operator [SEL_20] (rows=3 width=97) + Select Operator [SEL_20] (rows=1 width=97) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_19] (rows=3 width=101) + Group By Operator [GBY_19] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Map 7 [SIMPLE_EDGE] llap SHUFFLE [RS_18] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_17] (rows=3 width=101) + Group By Operator [GBY_17] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float - Filter Operator [FIL_54] (rows=6 width=93) + Filter Operator [FIL_54] (rows=1 width=93) predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0))) TableScan [TS_14] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -1416,16 +1416,16 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Select Operator [SEL_11] (rows=9 width=4) + Select Operator [SEL_11] (rows=1 width=4) Output:["_col0"] - Merge Join Operator [MERGEJOIN_17] (rows=9 width=4) + Merge Join Operator [MERGEJOIN_17] (rows=1 width=4) Conds:RS_8._col0=RS_9._col0(Left Semi),Output:["_col1"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] PartitionCols:_col0 - Select Operator [SEL_2] (rows=9 width=93) + Select Operator [SEL_2] (rows=1 width=93) Output:["_col0","_col1"] - Filter Operator [FIL_15] (rows=9 width=93) + Filter Operator [FIL_15] (rows=1 width=93) predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null) TableScan [TS_0] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -1456,27 +1456,27 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_18] - Select Operator [SEL_17] (rows=14 width=93) + Select Operator [SEL_17] (rows=1 width=93) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_28] (rows=14 width=93) + Merge Join Operator [MERGEJOIN_28] (rows=1 width=93) Conds:RS_13._col0=RS_14._col0(Left Semi),RS_13._col0=RS_15._col0(Left Semi),Output:["_col0","_col1","_col2"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_13] PartitionCols:_col0 - Select Operator [SEL_2] (rows=9 width=93) + Select Operator [SEL_2] (rows=1 width=93) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_25] (rows=9 width=93) + Filter Operator [FIL_25] (rows=1 width=93) predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null) TableScan [TS_0] (rows=20 width=88) default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_14] PartitionCols:_col0 - Group By Operator [GBY_10] (rows=4 width=85) + Group By Operator [GBY_10] (rows=1 width=85) Output:["_col0"],keys:_col0 - Select Operator [SEL_5] (rows=9 width=85) + Select Operator [SEL_5] (rows=1 width=85) Output:["_col0"] - Filter Operator [FIL_26] (rows=9 width=93) + Filter Operator [FIL_26] (rows=1 width=93) predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null) TableScan [TS_3] (rows=20 width=88) default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"] @@ -2176,13 +2176,13 @@ Stage-0 Stage-1 Reducer 4 llap File Output Operator [FS_26] - Select Operator [SEL_25] (rows=500 width=178) + Select Operator [SEL_25] (rows=1 width=178) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] llap SHUFFLE [RS_24] - Select Operator [SEL_23] (rows=500 width=178) + Select Operator [SEL_23] (rows=1 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_22] (rows=500 width=195) + Filter Operator [FIL_22] (rows=1 width=198) predicate:((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) Merge Join Operator [MERGEJOIN_31] (rows=500 width=195) Conds:RS_19._col0=RS_20._col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5"] @@ -2339,13 +2339,13 @@ Stage-0 Stage-1 Reducer 4 llap File Output Operator [FS_31] - Select Operator [SEL_30] (rows=26 width=125) + Select Operator [SEL_30] (rows=1 width=125) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] llap SHUFFLE [RS_29] - Select Operator [SEL_28] (rows=26 width=125) + Select Operator [SEL_28] (rows=1 width=125) Output:["_col0","_col1"] - Filter Operator [FIL_27] (rows=26 width=141) + Filter Operator [FIL_27] (rows=1 width=145) predicate:((_col2 = 0) or (_col5 is null and _col1 is not null and (_col3 >= _col2))) Merge Join Operator [MERGEJOIN_37] (rows=26 width=141) Conds:RS_24.UDFToDouble(_col1)=RS_25._col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5"] diff --git a/ql/src/test/results/clientpositive/llap/multi_insert.q.out b/ql/src/test/results/clientpositive/llap/multi_insert.q.out index 58fc759f26..8d2a3c5f82 100644 --- a/ql/src/test/results/clientpositive/llap/multi_insert.q.out +++ b/ql/src/test/results/clientpositive/llap/multi_insert.q.out @@ -619,30 +619,30 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -650,15 +650,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -773,30 +773,30 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -804,15 +804,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -927,30 +927,30 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -958,15 +958,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1081,30 +1081,30 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1112,15 +1112,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 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 92786f7e80..93c2087f18 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_multi.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_multi.q.out @@ -377,14 +377,14 @@ STAGE PLANS: Statistics: Num rows: 17 Data size: 6877 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col10 = 0) or (_col13 is null and _col3 is not null and (_col11 >= _col10))) (type: boolean) - Statistics: Num rows: 10 Data size: 4045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE 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 - Statistics: Num rows: 10 Data size: 4045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 4045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -585,14 +585,14 @@ STAGE PLANS: Statistics: Num rows: 17 Data size: 6877 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col10 = 0) or (_col13 is null and _col3 is not null and (_col11 >= _col10))) (type: boolean) - Statistics: Num rows: 10 Data size: 4045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE 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 - Statistics: Num rows: 10 Data size: 4045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 4045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -822,14 +822,14 @@ STAGE PLANS: Statistics: Num rows: 17 Data size: 6877 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col10 = 0) or (_col13 is null and _col3 is not null and (_col11 >= _col10))) (type: boolean) - Statistics: Num rows: 10 Data size: 4045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE 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 - Statistics: Num rows: 10 Data size: 4045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 4045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1016,16 +1016,16 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 6726 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col9 = 0) or (_col12 is null and _col1 is not null and (_col10 >= _col9))) (type: boolean) - Statistics: Num rows: 2 Data size: 2690 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1345 Basic stats: COMPLETE Column stats: NONE 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 - Statistics: Num rows: 2 Data size: 2690 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1345 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 2 Data size: 2690 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1345 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 4 Execution mode: llap @@ -3953,14 +3953,14 @@ STAGE PLANS: Statistics: Num rows: 28 Data size: 18304 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col0 = 3) or CASE WHEN ((_col9 = 0)) THEN (true) WHEN (_col12 is not null) THEN (false) WHEN (_col5 is null) THEN (null) WHEN ((_col10 < _col9)) THEN (null) ELSE (true) END) (type: boolean) - Statistics: Num rows: 28 Data size: 18304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 653 Basic stats: COMPLETE Column stats: NONE 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 - Statistics: Num rows: 28 Data size: 18304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 653 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 28 Data size: 18304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 653 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4168,9 +4168,9 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 52040 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col4 is not null and (_col2 <> 0)) or _col1 is not null or _col5 is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 52040 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 52040 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 420 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 ea3c78b21e..ada4598ab8 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out @@ -107,14 +107,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 97540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 97540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -677,14 +677,14 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 3674 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0) or (_col5 is null and _col1 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 26 Data size: 3674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 145 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1563,14 +1563,14 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 17366 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col1 = 0) or (_col4 is null and _col0 is not null and (_col2 >= _col1))) (type: boolean) - Statistics: Num rows: 166 Data size: 17366 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 107 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1922,14 +1922,14 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col9 = 0) or (_col12 is null and _col5 is not null and (_col10 >= _col9))) (type: boolean) - Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 639 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 - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2137,14 +2137,14 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 16538 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col9 = 0) or (_col12 is null and _col0 is not null and _col5 is not null and (_col10 >= _col9))) (type: boolean) - Statistics: Num rows: 26 Data size: 16538 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 639 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 - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2586,14 +2586,14 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 16538 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col9 = 0) or (_col12 is null and floor(_col7) is not null and (_col10 >= _col9))) (type: boolean) - Statistics: Num rows: 26 Data size: 16538 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 639 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 - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3689,22 +3689,22 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0) or (_col5 is null and _col1 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 95 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: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 4 Execution mode: llap @@ -3714,15 +3714,15 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + Map-reduce partition columns: _col1 (type: bigint) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 5 Execution mode: llap @@ -4244,15 +4244,15 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col9 = 0) or (_col12 is null and _col5 is not null and (_col10 >= _col9))) (type: boolean) - Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 639 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 - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 4 Execution mode: llap @@ -4260,10 +4260,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: int), VALUE._col5 (type: string), VALUE._col6 (type: double), VALUE._col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4472,15 +4472,15 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col9 = 0) or (_col12 is null and _col5 is not null and (_col10 >= _col9))) (type: boolean) - Statistics: Num rows: 26 Data size: 16542 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 639 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 - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col0 (type: int) sort order: ++ - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 4 @@ -4489,13 +4489,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: int), VALUE._col4 (type: string), VALUE._col5 (type: double), VALUE._col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 4 - Statistics: Num rows: 4 Data size: 2476 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 2476 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4764,14 +4764,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 97164 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 97164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5661,14 +5661,14 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 110 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col1 = 0) or (_col4 is null and _col0 is not null and (_col2 >= _col1))) (type: boolean) - Statistics: Num rows: 2 Data size: 55 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 55 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 55 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE 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_scalar.q.out b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out index ba5ccad500..1474c31c94 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out @@ -139,14 +139,14 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 residual filter predicates: {(UDFToDouble(_col5) > _col9)} - Statistics: Num rows: 8 Data size: 5600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 700 Basic stats: COMPLETE Column stats: NONE 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 - Statistics: Num rows: 8 Data size: 5600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 700 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 5600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 700 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -282,14 +282,14 @@ STAGE PLANS: 2 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 residual filter predicates: {(UDFToDouble(_col5) > UDFToDouble(_col10))} - Statistics: Num rows: 8 Data size: 5712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 714 Basic stats: COMPLETE Column stats: NONE 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 - Statistics: Num rows: 8 Data size: 5712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 714 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 5712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 714 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1628,14 +1628,14 @@ STAGE PLANS: 1 _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 residual filter predicates: {(UDFToDouble(_col5) > CASE WHEN (_col10 is null) THEN (null) ELSE (_col9) END)} - Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 632 Basic stats: COMPLETE Column stats: NONE 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 - Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 632 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 632 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1961,14 +1961,14 @@ STAGE PLANS: 1 _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 residual filter predicates: {(_col5 >= CASE WHEN (_col10 is null) THEN (null) ELSE (_col9) END)} - Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 632 Basic stats: COMPLETE Column stats: NONE 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 - Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 632 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 632 Basic stats: COMPLETE Column stats: NONE value 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) Reducer 3 Execution mode: llap @@ -1981,14 +1981,14 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 residual filter predicates: {(_col7 <= _col9)} - Statistics: Num rows: 3 Data size: 1947 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 649 Basic stats: COMPLETE Column stats: NONE 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 - Statistics: Num rows: 3 Data size: 1947 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 649 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 1947 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 649 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3459,14 +3459,14 @@ STAGE PLANS: Statistics: Num rows: 14 Data size: 1787 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col10 = 0) or (_col13 is null and _col3 is not null and (_col11 >= _col10))) (type: boolean) - Statistics: Num rows: 9 Data size: 1148 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 127 Basic stats: COMPLETE Column stats: NONE 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 - Statistics: Num rows: 9 Data size: 1148 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 127 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 9 Data size: 1148 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 127 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5170,14 +5170,14 @@ STAGE PLANS: 1 _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 residual filter predicates: {(UDFToLong(_col2) <> CASE WHEN (_col11 is null) THEN (null) ELSE (_col10) END)} - Statistics: Num rows: 5 Data size: 3476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 695 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 5 Data size: 3476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 695 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 3476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 695 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) Reducer 3 Execution mode: llap @@ -6235,22 +6235,22 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 residual filter predicates: {(_col0 <> _col1)} - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 5 Execution mode: llap @@ -6391,22 +6391,22 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2 residual filter predicates: {(_col1 <> _col2)} - Statistics: Num rows: 2 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(_col0) keys: _col2 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct) Reducer 4 Execution mode: llap diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_cast.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_cast.q.out index c45210e562..8fc23c486f 100644 --- a/ql/src/test/results/clientpositive/llap/vector_decimal_cast.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_decimal_cast.q.out @@ -29,7 +29,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 5) -> boolean, SelectColumnIsNotNull(col 2) -> boolean, SelectColumnIsNotNull(col 10) -> boolean, SelectColumnIsNotNull(col 8) -> boolean) -> boolean predicate: (cdouble is not null and cint is not null and cboolean1 is not null and ctimestamp1 is not null) (type: boolean) - Statistics: Num rows: 5112 Data size: 265564 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2945 Data size: 152996 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), cint (type: int), cboolean1 (type: boolean), ctimestamp1 (type: timestamp), CAST( cdouble AS decimal(20,10)) (type: decimal(20,10)), CAST( cint AS decimal(23,14)) (type: decimal(23,14)), CAST( cboolean1 AS decimal(5,2)) (type: decimal(5,2)), CAST( ctimestamp1 AS decimal(15,0)) (type: decimal(15,0)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 @@ -38,7 +38,7 @@ STAGE PLANS: native: true projectedOutputColumns: [5, 2, 10, 8, 12, 13, 14, 15] selectExpressions: CastDoubleToDecimal(col 5) -> 12:decimal(20,10), CastLongToDecimal(col 2) -> 13:decimal(23,14), CastLongToDecimal(col 10) -> 14:decimal(5,2), CastTimestampToDecimal(col 8) -> 15:decimal(15,0) - Statistics: Num rows: 5112 Data size: 2410700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2945 Data size: 1388804 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out index f7d69250d8..ad25261d1e 100644 --- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out @@ -375,15 +375,15 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((grouping(_col2, 1) = 1) or (grouping(_col2, 0) = 1)) (type: boolean) - Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), (grouping(_col2, 1) + grouping(_col2, 0)) (type: int), CASE WHEN (((grouping(_col2, 1) + grouping(_col2, 0)) = 1)) THEN (_col0) ELSE (null) END (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: int), _col3 (type: int) sort order: -+ - Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) Reducer 3 Execution mode: vectorized, llap @@ -391,10 +391,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -763,12 +763,12 @@ STAGE PLANS: Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((grouping(_col2, 1) = 1) or (grouping(_col2, 0) = 1)) (type: boolean) - Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -778,15 +778,15 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), (grouping(_col2, 1) + grouping(_col2, 0)) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: int), CASE WHEN ((_col2 = 1)) THEN (_col0) END (type: int) sort order: -+ - Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) Reducer 3 Execution mode: vectorized, llap @@ -794,10 +794,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE 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_groupby_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out index e43b4d1bb4..0f83f5569c 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 @@ -82,7 +82,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 2, val 0) -> boolean, FilterExprAndExpr(children: SelectColumnIsNull(col 4) -> boolean, SelectColumnIsNotNull(col 0) -> boolean, FilterLongColGreaterEqualLongColumn(col 3, col 2) -> boolean) -> boolean) -> boolean predicate: ((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 @@ -90,7 +90,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1] - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -98,7 +98,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs @@ -196,13 +196,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1] - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 178 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_if_expr.q.out b/ql/src/test/results/clientpositive/llap/vector_if_expr.q.out index 32d100180d..b1e0b14d4d 100644 --- a/ql/src/test/results/clientpositive/llap/vector_if_expr.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_if_expr.q.out @@ -34,7 +34,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsTrue(col 10) -> boolean, SelectColumnIsNotNull(col 10) -> boolean) -> boolean predicate: (cboolean1 and cboolean1 is not null) (type: boolean) - Statistics: Num rows: 4587 Data size: 13704 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3030 Data size: 9052 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), if(cboolean1, 'first', 'second') (type: string) outputColumnNames: _col0, _col1 @@ -43,7 +43,7 @@ STAGE PLANS: native: true projectedOutputColumns: [10, 12] selectExpressions: IfExprStringScalarStringScalar(col 10, val first, val second) -> 12:String - Statistics: Num rows: 4587 Data size: 857712 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3030 Data size: 566572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + @@ -51,7 +51,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 4587 Data size: 857712 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3030 Data size: 566572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs @@ -80,13 +80,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1] - Statistics: Num rows: 4587 Data size: 857712 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3030 Data size: 566572 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4587 Data size: 857712 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3030 Data size: 566572 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/vectorization_0.q.out b/ql/src/test/results/clientpositive/llap/vectorization_0.q.out index db76eaaf1b..8ad6f5b2fa 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_0.q.out @@ -1610,7 +1610,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7, pattern %b%) -> boolean, FilterDecimalScalarNotEqualDecimalColumn(val 79.553, col 12)(children: CastLongToDecimal(col 2) -> 12:decimal(13,3)) -> boolean, FilterDoubleColLessDoubleColumn(col 13, col 5)(children: CastLongToDouble(col 3) -> 13:double) -> boolean, FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 0, col 1)(children: col 0) -> boolean, FilterLongColEqualLongScalar(col 11, val 1) -> boolean, FilterLongScalarEqualLongColumn(val 3569, col 0)(children: col 0) -> boolean) -> boolean) -> boolean predicate: ((cstring2 like '%b%') or (79.553 <> CAST( cint AS decimal(13,3))) or (UDFToDouble(cbigint) < cdouble) or ((UDFToShort(ctinyint) >= csmallint) and (cboolean2 = 1) and (3569 = UDFToInteger(ctinyint)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 1210980 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 132 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cbigint (type: bigint), cfloat (type: float) outputColumnNames: ctinyint, cbigint, cfloat @@ -1618,7 +1618,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 3, 4] - Statistics: Num rows: 12288 Data size: 1210980 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 132 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: avg(cbigint), stddev_pop(cbigint), var_samp(cbigint), count(), sum(cfloat), min(ctinyint) Group By Vectorization: @@ -1802,9 +1802,9 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((cstring1 like 'a%') or (cstring1 like 'b%') or (cstring1 like 'c%') or ((length(cstring1) < 50) and (cstring1 like '%n') and (length(cstring1) > 0))) (type: boolean) - Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -30611,17 +30611,17 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean) - Statistics: Num rows: 6 Data size: 1630 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 6 Data size: 1630 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 1630 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -30841,17 +30841,17 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((cint = 49) or (cfloat = 3.5)) and ((cint = 47) or (cfloat = 2.09)) and ((cint = 45) or (cfloat = 3.02))) (type: boolean) - Statistics: Num rows: 27 Data size: 6990 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 27 Data size: 6990 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 27 Data size: 6990 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorization_10.q.out b/ql/src/test/results/clientpositive/llap/vectorization_10.q.out index f06c2dbcc6..d2ca4536f2 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_10.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_10.q.out @@ -73,7 +73,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7, val 10) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 0) -> 12:double) -> boolean, FilterDecimalScalarGreaterEqualDecimalColumn(val -5638.15, col 13)(children: CastLongToDecimal(col 0) -> 13:decimal(6,2)) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5, val 6981.0) -> boolean, FilterExprOrExpr(children: FilterDecimalColEqualDecimalScalar(col 14, val 9763215.5639)(children: CastLongToDecimal(col 1) -> 14:decimal(11,4)) -> boolean, FilterStringColLikeStringScalar(col 6, pattern %a) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (-5638.15 >= CAST( ctinyint AS decimal(6,2)))) or ((cdouble > 6981.0) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a')))) (type: boolean) - Statistics: Num rows: 5461 Data size: 1107444 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639 - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -82,13 +82,13 @@ STAGE PLANS: native: true projectedOutputColumns: [5, 8, 0, 10, 6, 12, 16, 15, 17, 19, 20, 18, 22, 23, 25] selectExpressions: DoubleColUnaryMinus(col 5) -> 12:double, DoubleColAddDoubleColumn(col 5, col 15)(children: CastLongToDouble(col 1) -> 15:double) -> 16:double, DoubleColModuloDoubleScalar(col 17, val 33.0)(children: DoubleColAddDoubleColumn(col 5, col 15)(children: CastLongToDouble(col 1) -> 15:double) -> 17:double) -> 15:double, DoubleColUnaryMinus(col 5) -> 17:double, DoubleColModuloDoubleColumn(col 18, col 5)(children: CastLongToDouble(col 0) -> 18:double) -> 19:double, LongColModuloLongColumn(col 0, col 1)(children: col 0) -> 20:long, DoubleColUnaryMinus(col 5) -> 18:double, LongColMultiplyLongColumn(col 3, col 21)(children: col 21) -> 22:long, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 24)(children: DoubleColAddDoubleColumn(col 5, col 23)(children: CastLongToDouble(col 1) -> 23:double) -> 24:double) -> 23:double, DoubleColUnaryMinus(col 24)(children: DoubleColUnaryMinus(col 5) -> 24:double) -> 25:double - Statistics: Num rows: 5461 Data size: 1082056 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 452 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5461 Data size: 1082056 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 452 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/vectorization_11.q.out b/ql/src/test/results/clientpositive/llap/vectorization_11.q.out index 2b8c39109f..83bedea904 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_11.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_11.q.out @@ -55,7 +55,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringGroupColumn(col 7, col 6) -> boolean, FilterExprAndExpr(children: SelectColumnIsNull(col 8) -> boolean, FilterStringColLikeStringScalar(col 6, pattern %a) -> boolean) -> boolean) -> boolean predicate: ((cstring2 = cstring1) or (ctimestamp1 is null and (cstring1 like '%a'))) (type: boolean) - Statistics: Num rows: 6144 Data size: 1190792 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 246 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), ctimestamp1 (type: timestamp), (-3728 * UDFToInteger(csmallint)) (type: int), (cdouble - 9763215.5639) (type: double), (- cdouble) (type: double), ((- cdouble) + 6981.0) (type: double), (cdouble * -5638.15) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -64,13 +64,13 @@ STAGE PLANS: native: true projectedOutputColumns: [6, 10, 5, 8, 12, 13, 14, 16, 15] selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 1)(children: col 1) -> 12:long, DoubleColSubtractDoubleScalar(col 5, val 9763215.5639) -> 13:double, DoubleColUnaryMinus(col 5) -> 14:double, DoubleColAddDoubleScalar(col 15, val 6981.0)(children: DoubleColUnaryMinus(col 5) -> 15:double) -> 16:double, DoubleColMultiplyDoubleScalar(col 5, val -5638.15) -> 15:double - Statistics: Num rows: 6144 Data size: 953272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6144 Data size: 953272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 182 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/vectorization_13.q.out b/ql/src/test/results/clientpositive/llap/vectorization_13.q.out index d3e43098c8..ebb83a6c88 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_13.q.out @@ -95,7 +95,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4, val 3569.0) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val 10.175, col 5) -> boolean, FilterLongColNotEqualLongScalar(col 10, val 1) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 12, val 11.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterDoubleColNotEqualDoubleScalar(col 12, val 12.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDecimalColLessDecimalScalar(col 13, val 9763215.5639)(children: CastLongToDecimal(col 0) -> 13:decimal(11,4)) -> boolean) -> boolean) -> boolean predicate: (((cfloat < 3569) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > 11.0) and (UDFToDouble(ctimestamp2) <> 12.0) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 @@ -103,7 +103,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 4, 6, 8, 10] - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) Group By Vectorization: @@ -118,7 +118,7 @@ STAGE PLANS: keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2730 Data size: 816734 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -129,7 +129,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [5, 6, 7, 8, 9, 10] - Statistics: Num rows: 2730 Data size: 816734 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -177,7 +177,7 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1365 Data size: 211860 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 @@ -186,7 +186,7 @@ STAGE PLANS: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 11, 5, 13, 6, 16, 15, 17, 7, 18, 8, 20, 22, 21, 9, 25, 10] selectExpressions: LongColUnaryMinus(col 1) -> 11:long, LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 13:long, DoubleColMultiplyDoubleColumn(col 6, col 15)(children: CastLongToDouble(col 14)(children: LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 14:long) -> 15:double) -> 16:double, DoubleColUnaryMinus(col 6) -> 15:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3) -> 17:double, DoubleColUnaryMinus(col 6) -> 18:double, DecimalColSubtractDecimalScalar(col 19, val 10.175)(children: CastLongToDecimal(col 14)(children: LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 14:long) -> 19:decimal(3,0)) -> 20:decimal(7,3), DoubleColUnaryMinus(col 21)(children: DoubleColUnaryMinus(col 6) -> 21:double) -> 22:double, DoubleScalarDivideDoubleColumn(val -26.28, col 23)(children: DoubleColUnaryMinus(col 21)(children: DoubleColUnaryMinus(col 6) -> 21:double) -> 23:double) -> 21:double, DoubleColDivideDoubleColumn(col 24, col 23)(children: DoubleColMultiplyDoubleColumn(col 6, col 23)(children: CastLongToDouble(col 14)(children: LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 14:long) -> 23:double) -> 24:double, CastLongToDouble(col 1) -> 23:double) -> 25:double - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 354 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) sort order: +++++++++++++++++++++ @@ -196,7 +196,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [] - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 354 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: vectorized, llap @@ -221,19 +221,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 10, 14, 15, 16, 17, 18, 19, 20] - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 354 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 354 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 354 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -450,7 +450,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4, val 3569.0) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val 10.175, col 5) -> boolean, FilterLongColNotEqualLongScalar(col 10, val 1) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 12, val -1.388)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterDoubleColNotEqualDoubleScalar(col 12, val -1.3359999999999999)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDecimalColLessDecimalScalar(col 13, val 9763215.5639)(children: CastLongToDecimal(col 0) -> 13:decimal(11,4)) -> boolean) -> boolean) -> boolean predicate: (((cfloat < 3569) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -1.388) and (UDFToDouble(ctimestamp2) <> -1.3359999999999999) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 @@ -458,7 +458,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 4, 6, 8, 10] - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) Group By Vectorization: @@ -473,7 +473,7 @@ STAGE PLANS: keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2730 Data size: 816734 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -482,7 +482,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2730 Data size: 816734 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -518,7 +518,7 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1365 Data size: 211860 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 @@ -527,7 +527,7 @@ STAGE PLANS: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 11, 5, 13, 6, 16, 15, 17, 7, 18, 8, 20, 22, 21, 9, 25, 10] selectExpressions: LongColUnaryMinus(col 1) -> 11:long, LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 13:long, DoubleColMultiplyDoubleColumn(col 6, col 15)(children: CastLongToDouble(col 14)(children: LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 14:long) -> 15:double) -> 16:double, DoubleColUnaryMinus(col 6) -> 15:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3) -> 17:double, DoubleColUnaryMinus(col 6) -> 18:double, DecimalColSubtractDecimalScalar(col 19, val 10.175)(children: CastLongToDecimal(col 14)(children: LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 14:long) -> 19:decimal(3,0)) -> 20:decimal(7,3), DoubleColUnaryMinus(col 21)(children: DoubleColUnaryMinus(col 6) -> 21:double) -> 22:double, DoubleScalarDivideDoubleColumn(val -26.28, col 23)(children: DoubleColUnaryMinus(col 21)(children: DoubleColUnaryMinus(col 6) -> 21:double) -> 23:double) -> 21:double, DoubleColDivideDoubleColumn(col 24, col 23)(children: DoubleColMultiplyDoubleColumn(col 6, col 23)(children: CastLongToDouble(col 14)(children: LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 14:long) -> 23:double) -> 24:double, CastLongToDouble(col 1) -> 23:double) -> 25:double - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 354 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) sort order: +++++++++++++++++++++ @@ -535,7 +535,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 354 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: vectorized, llap @@ -554,19 +554,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 10, 14, 15, 16, 17, 18, 19, 20] - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 354 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 354 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 354 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/vectorization_14.q.out b/ql/src/test/results/clientpositive/llap/vectorization_14.q.out index 418e4ea79f..637e6ab687 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_14.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_14.q.out @@ -95,7 +95,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0, col 3)(children: col 0) -> boolean, FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 2) -> 12:double) -> boolean, FilterTimestampColLessTimestampColumn(col 9, col 8) -> boolean) -> boolean, FilterDoubleColLessDoubleColumn(col 5, col 12)(children: CastLongToDouble(col 0) -> 12:double) -> boolean, FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3, val -257) -> boolean, FilterDoubleColLessDoubleColumn(col 4, col 12)(children: CastLongToFloatViaLongToDouble(col 2) -> 12:double) -> boolean) -> boolean) -> boolean predicate: ((UDFToLong(ctinyint) <= cbigint) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1)) and (cdouble < UDFToDouble(ctinyint)) and ((cbigint > -257) or (cfloat < UDFToFloat(cint)))) (type: boolean) - Statistics: Num rows: 606 Data size: 105558 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28 + cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 @@ -104,7 +104,7 @@ STAGE PLANS: native: true projectedOutputColumns: [8, 4, 6, 10, 5, 13] selectExpressions: DoubleColUnaryMinus(col 12)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5) -> 12:double) -> 13:double - Statistics: Num rows: 606 Data size: 105558 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: stddev_samp(_col5), max(_col1), stddev_pop(_col1), count(_col1), var_pop(_col1), var_samp(_col1) Group By Vectorization: @@ -119,7 +119,7 @@ STAGE PLANS: keys: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp), _col3 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 303 Data size: 137686 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 482 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ @@ -130,7 +130,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [5, 6, 7, 8, 9, 10] - Statistics: Num rows: 303 Data size: 137686 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 482 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: struct), _col6 (type: float), _col7 (type: struct), _col8 (type: bigint), _col9 (type: struct), _col10 (type: struct) Execution mode: vectorized, llap LLAP IO: all inputs @@ -178,7 +178,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 151 Data size: 25224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28 + _col2) (type: double), (- (-26.28 + _col2)) (type: double), _col5 (type: double), (_col1 * -26.28) (type: float), _col6 (type: float), (- _col1) (type: float), (- _col6) (type: float), ((- (-26.28 + _col2)) / 10.175) (type: double), _col7 (type: double), _col8 (type: bigint), (- ((- (-26.28 + _col2)) / 10.175)) (type: double), (-1.389 % _col5) (type: double), (UDFToDouble(_col1) - _col2) (type: double), _col9 (type: double), (_col9 % 10.175) (type: double), _col10 (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 @@ -187,7 +187,7 @@ STAGE PLANS: native: true projectedOutputColumns: [3, 1, 0, 4, 2, 11, 13, 5, 12, 6, 14, 15, 16, 7, 8, 18, 17, 19, 9, 20, 10, 22] selectExpressions: DoubleScalarAddDoubleColumn(val -26.28, col 2) -> 11:double, DoubleColUnaryMinus(col 12)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2) -> 12:double) -> 13:double, DoubleColMultiplyDoubleScalar(col 1, val -26.280000686645508) -> 12:double, DoubleColUnaryMinus(col 1) -> 14:double, DoubleColUnaryMinus(col 6) -> 15:double, DoubleColDivideDoubleScalar(col 17, val 10.175)(children: DoubleColUnaryMinus(col 16)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2) -> 16:double) -> 17:double) -> 16:double, DoubleColUnaryMinus(col 17)(children: DoubleColDivideDoubleScalar(col 18, val 10.175)(children: DoubleColUnaryMinus(col 17)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2) -> 17:double) -> 18:double) -> 17:double) -> 18:double, DoubleScalarModuloDoubleColumn(val -1.389, col 5) -> 17:double, DoubleColSubtractDoubleColumn(col 1, col 2)(children: col 1) -> 19:double, DoubleColModuloDoubleScalar(col 9, val 10.175) -> 20:double, DoubleColUnaryMinus(col 21)(children: DoubleColSubtractDoubleColumn(col 1, col 2)(children: col 1) -> 21:double) -> 22:double - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 270 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp) sort order: ++++ @@ -197,7 +197,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [4, 11, 13, 5, 12, 6, 14, 15, 16, 7, 8, 18, 17, 19, 9, 20, 10, 22] - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 270 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) Reducer 3 Execution mode: vectorized, llap @@ -222,13 +222,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [3, 1, 0, 4, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 270 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 270 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/vectorization_15.q.out b/ql/src/test/results/clientpositive/llap/vectorization_15.q.out index 9cc350d659..4fee0636d0 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_15.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_15.q.out @@ -91,7 +91,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7, pattern %ss%) -> boolean, FilterStringColLikeStringScalar(col 6, pattern 10%) -> boolean, FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2, val -75) -> boolean, FilterLongColEqualLongColumn(col 0, col 1)(children: col 0) -> boolean, FilterDoubleColGreaterEqualDoubleScalar(col 5, val -3728.0) -> boolean) -> boolean) -> boolean predicate: ((cstring2 like '%ss%') or (cstring1 like '10%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 258 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) outputColumnNames: ctinyint, cint, cfloat, cdouble, cstring1, ctimestamp1, cboolean1 @@ -99,7 +99,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 2, 4, 5, 6, 8, 10] - Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 258 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: stddev_samp(cfloat), min(cdouble), stddev_samp(ctinyint), var_pop(ctinyint), var_samp(cint), stddev_pop(cint) Group By Vectorization: @@ -114,7 +114,7 @@ STAGE PLANS: keys: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 6144 Data size: 3293884 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 566 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) sort order: +++++++ @@ -125,7 +125,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [7, 8, 9, 10, 11, 12] - Statistics: Num rows: 6144 Data size: 3293884 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 566 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col7 (type: struct), _col8 (type: double), _col9 (type: struct), _col10 (type: struct), _col11 (type: struct), _col12 (type: struct) Execution mode: vectorized, llap LLAP IO: all inputs @@ -160,15 +160,15 @@ STAGE PLANS: keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 3072 Data size: 541028 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), _col7 (type: double), (-26.28 - CAST( _col5 AS decimal(10,0))) (type: decimal(13,2)), _col8 (type: double), (_col2 * 79.553) (type: double), (33.0 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - CAST( _col5 AS decimal(10,0)))) (type: decimal(13,2)), _col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 3072 Data size: 1327460 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 462 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) sort order: +++++++ - Statistics: Num rows: 3072 Data size: 1327460 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 462 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col7 (type: double), _col8 (type: decimal(13,2)), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: decimal(13,2)), _col20 (type: double) Reducer 3 Execution mode: llap @@ -180,10 +180,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: decimal(13,2)), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: decimal(13,2)), VALUE._col13 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 3072 Data size: 1327460 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 462 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3072 Data size: 1327460 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 462 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/vectorization_16.q.out b/ql/src/test/results/clientpositive/llap/vectorization_16.q.out index d961af2513..c0416578ed 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_16.q.out @@ -68,7 +68,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7, pattern %b%) -> boolean, FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5, val -1.389) -> boolean, FilterStringGroupColLessStringScalar(col 6, val a) -> boolean) -> boolean) -> boolean predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 238 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) outputColumnNames: cdouble, cstring1, ctimestamp1 @@ -76,7 +76,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [5, 6, 8] - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 238 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) Group By Vectorization: @@ -91,7 +91,7 @@ STAGE PLANS: keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2048 Data size: 434588 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 238 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ @@ -102,7 +102,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [3, 4, 5] - Statistics: Num rows: 2048 Data size: 434588 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 238 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs @@ -149,7 +149,7 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1024 Data size: 143566 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 166 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 @@ -158,13 +158,13 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 0, 2, 6, 8, 3, 4, 7, 10, 5, 9, 12, 4] selectExpressions: DoubleColSubtractDoubleScalar(col 0, val 9763215.5639) -> 6:double, DoubleColUnaryMinus(col 7)(children: DoubleColSubtractDoubleScalar(col 0, val 9763215.5639) -> 7:double) -> 8:double, DoubleColUnaryMinus(col 4) -> 7:double, DoubleColMultiplyDoubleColumn(col 4, col 9)(children: CastLongToDouble(col 3) -> 9:double) -> 10:double, DoubleScalarDivideDoubleColumn(val 9763215.5639, col 0) -> 9:double, DecimalColDivideDecimalScalar(col 11, val -1.389)(children: CastLongToDecimal(col 3) -> 11:decimal(19,0)) -> 12:decimal(28,6) - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 326 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/vectorization_17.q.out b/ql/src/test/results/clientpositive/llap/vectorization_17.q.out index 1c07962d83..ee3a39869b 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_17.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_17.q.out @@ -76,7 +76,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3, val -23) -> boolean, FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5, val 988888.0) -> boolean, FilterDecimalColGreaterDecimalScalar(col 12, val -863.257)(children: CastLongToDecimal(col 2) -> 12:decimal(13,3)) -> boolean) -> boolean, FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0, val 33) -> boolean, FilterLongColGreaterEqualLongColumn(col 1, col 3)(children: col 1) -> boolean, FilterDoubleColEqualDoubleColumn(col 4, col 5)(children: col 4) -> boolean) -> boolean) -> boolean predicate: ((cbigint > -23) and ((cdouble <> 988888.0) or (CAST( cint AS decimal(13,3)) > -863.257)) and ((ctinyint >= 33) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble))) (type: boolean) - Statistics: Num rows: 4778 Data size: 640688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 166 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58 + (- (- cdouble))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -85,7 +85,7 @@ STAGE PLANS: native: true projectedOutputColumns: [4, 6, 2, 8, 5, 3, 14, 15, 13, 16, 18, 19, 21, 17] selectExpressions: DoubleColDivideDoubleColumn(col 4, col 13)(children: col 4, CastLongToDouble(col 0) -> 13:double) -> 14:double, LongColModuloLongColumn(col 2, col 3)(children: col 2) -> 15:long, DoubleColUnaryMinus(col 5) -> 13:double, DoubleColAddDoubleColumn(col 5, col 17)(children: DoubleColDivideDoubleColumn(col 4, col 16)(children: col 4, CastLongToDouble(col 0) -> 16:double) -> 17:double) -> 16:double, DoubleColDivideDoubleColumn(col 5, col 17)(children: CastLongToDouble(col 2) -> 17:double) -> 18:double, DoubleColUnaryMinus(col 17)(children: DoubleColUnaryMinus(col 5) -> 17:double) -> 19:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 20)(children: CastLongToDecimal(col 3) -> 20:decimal(19,0)) -> 21:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 22)(children: DoubleColUnaryMinus(col 17)(children: DoubleColUnaryMinus(col 5) -> 17:double) -> 22:double) -> 17:double - Statistics: Num rows: 4778 Data size: 1414848 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: bigint), _col0 (type: float) sort order: ++ @@ -95,7 +95,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [6, 2, 8, 5, 14, 15, 13, 16, 18, 19, 21, 17] - Statistics: Num rows: 4778 Data size: 1414848 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs @@ -136,13 +136,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [1, 2, 3, 4, 5, 0, 6, 7, 8, 9, 10, 11, 12, 13] - Statistics: Num rows: 4778 Data size: 1414848 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4778 Data size: 1414848 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 326 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/vectorization_2.q.out b/ql/src/test/results/clientpositive/llap/vectorization_2.q.out index affd1b6d7b..6920b979cb 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_2.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_2.q.out @@ -74,7 +74,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterTimestampColLessTimestampColumn(col 8, col 9) -> boolean, FilterStringColLikeStringScalar(col 7, pattern b%) -> boolean, FilterDoubleColLessEqualDoubleScalar(col 4, val -5638.14990234375) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5, col 12)(children: CastLongToDouble(col 0) -> 12:double) -> boolean, FilterExprOrExpr(children: FilterDoubleScalarNotEqualDoubleColumn(val -10669.0, col 12)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterLongScalarGreaterLongColumn(val 359, col 2) -> boolean) -> boolean) -> boolean) -> boolean predicate: (((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15)) or ((cdouble < UDFToDouble(ctinyint)) and ((-10669.0 <> UDFToDouble(ctimestamp2)) or (359 > cint)))) (type: boolean) - Statistics: Num rows: 4096 Data size: 719232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cbigint (type: bigint), cfloat (type: float), cdouble (type: double) outputColumnNames: ctinyint, csmallint, cbigint, cfloat, cdouble @@ -82,7 +82,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 3, 4, 5] - Statistics: Num rows: 4096 Data size: 719232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: avg(csmallint), sum(cfloat), var_pop(cbigint), count(), min(ctinyint), avg(cdouble) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorization_3.q.out b/ql/src/test/results/clientpositive/llap/vectorization_3.q.out index 415474665b..af270fe4d6 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_3.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_3.q.out @@ -79,7 +79,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 12, col 4)(children: CastLongToFloatViaLongToDouble(col 2) -> 12:double) -> boolean, FilterDecimalScalarNotEqualDecimalColumn(val 79.553, col 13)(children: CastLongToDecimal(col 3) -> 13:decimal(22,3)) -> boolean, FilterDoubleColEqualDoubleScalar(col 12, val -29071.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 3) -> 12:double) -> boolean, FilterDecimalScalarLessEqualDecimalColumn(val 79.553, col 14)(children: CastLongToDecimal(col 1) -> 14:decimal(8,3)) -> boolean, FilterTimestampColGreaterTimestampColumn(col 8, col 9) -> boolean) -> boolean) -> boolean predicate: (((UDFToFloat(cint) <= cfloat) and (79.553 <> CAST( cbigint AS decimal(22,3))) and (UDFToDouble(ctimestamp2) = -29071.0)) or ((UDFToDouble(cbigint) > cdouble) and (79.553 <= CAST( csmallint AS decimal(8,3))) and (ctimestamp1 > ctimestamp2))) (type: boolean) - Statistics: Num rows: 2503 Data size: 260060 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cfloat (type: float) outputColumnNames: ctinyint, csmallint, cint, cfloat @@ -87,7 +87,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 4] - Statistics: Num rows: 2503 Data size: 260060 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: stddev_samp(csmallint), stddev_pop(ctinyint), stddev_samp(cfloat), sum(cfloat), avg(cint), stddev_pop(cint) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorization_4.q.out b/ql/src/test/results/clientpositive/llap/vectorization_4.q.out index 0b2adade2c..ed1ac3c946 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_4.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_4.q.out @@ -74,7 +74,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 1, col 2)(children: col 1) -> boolean, FilterExprAndExpr(children: FilterLongScalarGreaterEqualLongColumn(val -89010, col 0)(children: col 0) -> boolean, FilterDoubleColGreaterDoubleScalar(col 5, val 79.553) -> boolean) -> boolean, FilterExprAndExpr(children: FilterLongScalarNotEqualLongColumn(val -563, col 3) -> boolean, FilterExprOrExpr(children: FilterLongColNotEqualLongColumn(col 0, col 3)(children: col 0) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val -3728.0, col 5) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((UDFToInteger(csmallint) >= cint) or ((-89010 >= UDFToInteger(ctinyint)) and (cdouble > 79.553)) or ((-563 <> cbigint) and ((UDFToLong(ctinyint) <> cbigint) or (-3728.0 >= cdouble)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), cdouble (type: double) outputColumnNames: ctinyint, cint, cdouble @@ -82,7 +82,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 2, 5] - Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(cint), stddev_pop(cdouble), avg(cdouble), var_pop(cdouble), min(ctinyint) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorization_5.q.out b/ql/src/test/results/clientpositive/llap/vectorization_5.q.out index 230078058a..acca624d1e 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_5.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_5.q.out @@ -68,7 +68,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 11) -> boolean, FilterStringColLikeStringScalar(col 6, pattern %b%) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColEqualDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 0) -> 12:double) -> boolean, SelectColumnIsNotNull(col 9) -> boolean, FilterStringColLikeStringScalar(col 7, pattern a) -> boolean) -> boolean) -> boolean predicate: ((cboolean2 is not null and (cstring1 like '%b%')) or ((UDFToDouble(ctinyint) = cdouble) and ctimestamp2 is not null and (cstring2 like 'a'))) (type: boolean) - Statistics: Num rows: 7658 Data size: 1529972 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 508 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int) outputColumnNames: ctinyint, csmallint, cint @@ -76,7 +76,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2] - Statistics: Num rows: 7658 Data size: 1529972 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 508 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(csmallint), count(), min(csmallint), sum(cint), max(ctinyint) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorization_6.q.out b/ql/src/test/results/clientpositive/llap/vectorization_6.q.out index 33814f258d..9b2ed52c36 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_6.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_6.q.out @@ -67,7 +67,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0, val 0) -> boolean, FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 10, val 0) -> boolean, FilterLongColGreaterEqualLongColumn(col 11, col 10) -> boolean) -> boolean, FilterExprAndExpr(children: SelectColumnIsNotNull(col 3) -> boolean, FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7, pattern %a) -> boolean, FilterDoubleColLessEqualDoubleScalar(col 4, val -257.0) -> boolean) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((ctinyint <> 0) and (((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (cbigint is not null and ((cstring2 like '%a') or (cfloat <= -257))))) (type: boolean) - Statistics: Num rows: 5951 Data size: 1022000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cstring1 (type: string), (988888 * UDFToInteger(csmallint)) (type: int), (- csmallint) (type: smallint), (- cfloat) (type: float), (-26.28 / UDFToDouble(cfloat)) (type: double), (cfloat * 359.0) (type: float), (cint % UDFToInteger(ctinyint)) (type: int), (- cdouble) (type: double), (UDFToInteger(ctinyint) - -75) (type: int), (762 * (cint % UDFToInteger(ctinyint))) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 @@ -76,13 +76,13 @@ STAGE PLANS: native: true projectedOutputColumns: [10, 4, 6, 12, 13, 14, 15, 16, 17, 18, 19, 21] selectExpressions: LongScalarMultiplyLongColumn(val 988888, col 1)(children: col 1) -> 12:long, LongColUnaryMinus(col 1) -> 13:long, DoubleColUnaryMinus(col 4) -> 14:double, DoubleScalarDivideDoubleColumn(val -26.28, col 4)(children: col 4) -> 15:double, DoubleColMultiplyDoubleScalar(col 4, val 359.0) -> 16:double, LongColModuloLongColumn(col 2, col 0)(children: col 0) -> 17:long, DoubleColUnaryMinus(col 5) -> 18:double, LongColSubtractLongScalar(col 0, val -75)(children: col 0) -> 19:long, LongScalarMultiplyLongColumn(val 762, col 20)(children: LongColModuloLongColumn(col 2, col 0)(children: col 0) -> 20:long) -> 21:long - Statistics: Num rows: 5951 Data size: 715128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 292 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5951 Data size: 715128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 292 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/vectorization_7.q.out b/ql/src/test/results/clientpositive/llap/vectorization_7.q.out index 6c32ccf42d..aa0a9b07ac 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_7.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_7.q.out @@ -82,7 +82,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0, val 0) -> boolean, FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 12, val 0.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterLongColEqualLongColumn(col 0, col 2)(children: col 0) -> boolean, FilterStringColLikeStringScalar(col 7, pattern ss) -> boolean) -> boolean, FilterExprOrExpr(children: FilterDoubleScalarLessDoubleColumn(val 988888.0, col 5) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 12, val -15.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val 3569.0, col 5) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > -15.0) and (3569.0 >= cdouble)))) (type: boolean) - Statistics: Num rows: 7281 Data size: 1789382 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 302 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -91,7 +91,7 @@ STAGE PLANS: native: true projectedOutputColumns: [10, 3, 1, 0, 8, 6, 13, 14, 15, 16, 18, 19, 17, 20, 22] selectExpressions: LongColAddLongColumn(col 3, col 3) -> 13:long, LongColModuloLongScalar(col 1, val -257)(children: col 1) -> 14:long, LongColUnaryMinus(col 1) -> 15:long, LongColUnaryMinus(col 0) -> 16:long, LongColAddLongScalar(col 17, val 17)(children: col 17) -> 18:long, LongColMultiplyLongColumn(col 3, col 17)(children: col 17) -> 19:long, LongColModuloLongColumn(col 2, col 1)(children: col 1) -> 17:long, LongColUnaryMinus(col 0) -> 20:long, LongColModuloLongColumn(col 21, col 0)(children: LongColUnaryMinus(col 0) -> 21:long) -> 22:long - Statistics: Num rows: 7281 Data size: 1231410 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -101,7 +101,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [] - Statistics: Num rows: 7281 Data size: 1231410 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -142,19 +142,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 9, 14] - Statistics: Num rows: 7281 Data size: 1231410 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -331,7 +331,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0, val 0) -> boolean, FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 12, val 0.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterLongColEqualLongColumn(col 0, col 2)(children: col 0) -> boolean, FilterStringColLikeStringScalar(col 7, pattern ss) -> boolean) -> boolean, FilterExprOrExpr(children: FilterDoubleScalarLessDoubleColumn(val 988888.0, col 5) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 12, val 7.6850000000000005)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val 3569.0, col 5) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > 7.6850000000000005) and (3569.0 >= cdouble)))) (type: boolean) - Statistics: Num rows: 7281 Data size: 1789382 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 302 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -340,7 +340,7 @@ STAGE PLANS: native: true projectedOutputColumns: [10, 3, 1, 0, 8, 6, 13, 14, 15, 16, 18, 19, 17, 20, 22] selectExpressions: LongColAddLongColumn(col 3, col 3) -> 13:long, LongColModuloLongScalar(col 1, val -257)(children: col 1) -> 14:long, LongColUnaryMinus(col 1) -> 15:long, LongColUnaryMinus(col 0) -> 16:long, LongColAddLongScalar(col 17, val 17)(children: col 17) -> 18:long, LongColMultiplyLongColumn(col 3, col 17)(children: col 17) -> 19:long, LongColModuloLongColumn(col 2, col 1)(children: col 1) -> 17:long, LongColUnaryMinus(col 0) -> 20:long, LongColModuloLongColumn(col 21, col 0)(children: LongColUnaryMinus(col 0) -> 21:long) -> 22:long - Statistics: Num rows: 7281 Data size: 1231410 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -348,7 +348,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 7281 Data size: 1231410 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -377,19 +377,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 9, 14] - Statistics: Num rows: 7281 Data size: 1231410 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 198 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/vectorization_8.q.out b/ql/src/test/results/clientpositive/llap/vectorization_8.q.out index 334e2dbb93..a290932287 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_8.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_8.q.out @@ -78,7 +78,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 7) -> boolean, FilterDoubleColLessEqualDoubleScalar(col 12, val 10.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterDoubleColNotEqualDoubleScalar(col 12, val 16.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean) -> boolean, FilterDoubleColLessDoubleScalar(col 4, val -6432.0) -> boolean, FilterExprAndExpr(children: SelectColumnIsNotNull(col 10) -> boolean, FilterDoubleColEqualDoubleScalar(col 5, val 988888.0) -> boolean) -> boolean) -> boolean predicate: ((cstring2 is not null and (UDFToDouble(ctimestamp1) <= 10.0) and (UDFToDouble(ctimestamp2) <> 16.0)) or (cfloat < -6432) or (cboolean1 is not null and (cdouble = 988888.0))) (type: boolean) - Statistics: Num rows: 3059 Data size: 742850 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15 - cdouble) (type: double), (cdouble * -257.0) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15 - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -87,7 +87,7 @@ STAGE PLANS: native: true projectedOutputColumns: [8, 5, 10, 6, 4, 12, 13, 14, 16, 18, 15, 17, 19, 21] selectExpressions: DoubleColUnaryMinus(col 5) -> 12:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5) -> 13:double, DoubleColMultiplyDoubleScalar(col 5, val -257.0) -> 14:double, DoubleColAddDoubleColumn(col 15, col 4)(children: CastLongToFloatViaLongToDouble(col 2) -> 15:double) -> 16:double, DoubleColAddDoubleColumn(col 15, col 17)(children: DoubleColUnaryMinus(col 5) -> 15:double, CastLongToDouble(col 3) -> 17:double) -> 18:double, DoubleColUnaryMinus(col 5) -> 15:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4) -> 17:double, DoubleColUnaryMinus(col 4) -> 19:double, DoubleColAddDoubleColumn(col 20, col 22)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5) -> 20:double, col 22) -> 21:double - Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double) sort order: ++++++++++++++ @@ -97,7 +97,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [] - Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -138,19 +138,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 5, 11, 12, 13] - Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -314,7 +314,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 7) -> boolean, FilterDoubleColLessEqualDoubleScalar(col 12, val 12.503)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterDoubleColNotEqualDoubleScalar(col 12, val 11.998)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean) -> boolean, FilterDoubleColLessDoubleScalar(col 4, val -6432.0) -> boolean, FilterExprAndExpr(children: SelectColumnIsNotNull(col 10) -> boolean, FilterDoubleColEqualDoubleScalar(col 5, val 988888.0) -> boolean) -> boolean) -> boolean predicate: ((cstring2 is not null and (UDFToDouble(ctimestamp1) <= 12.503) and (UDFToDouble(ctimestamp2) <> 11.998)) or (cfloat < -6432) or (cboolean1 is not null and (cdouble = 988888.0))) (type: boolean) - Statistics: Num rows: 3059 Data size: 742850 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15 - cdouble) (type: double), (cdouble * -257.0) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15 - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -323,7 +323,7 @@ STAGE PLANS: native: true projectedOutputColumns: [8, 5, 10, 6, 4, 12, 13, 14, 16, 18, 15, 17, 19, 21] selectExpressions: DoubleColUnaryMinus(col 5) -> 12:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5) -> 13:double, DoubleColMultiplyDoubleScalar(col 5, val -257.0) -> 14:double, DoubleColAddDoubleColumn(col 15, col 4)(children: CastLongToFloatViaLongToDouble(col 2) -> 15:double) -> 16:double, DoubleColAddDoubleColumn(col 15, col 17)(children: DoubleColUnaryMinus(col 5) -> 15:double, CastLongToDouble(col 3) -> 17:double) -> 18:double, DoubleColUnaryMinus(col 5) -> 15:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4) -> 17:double, DoubleColUnaryMinus(col 4) -> 19:double, DoubleColAddDoubleColumn(col 20, col 22)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5) -> 20:double, col 22) -> 21:double - Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double) sort order: ++++++++++++++ @@ -331,7 +331,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -360,19 +360,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 5, 11, 12, 13] - Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 420 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/vectorization_9.q.out b/ql/src/test/results/clientpositive/llap/vectorization_9.q.out index d961af2513..c0416578ed 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_9.q.out @@ -68,7 +68,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7, pattern %b%) -> boolean, FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5, val -1.389) -> boolean, FilterStringGroupColLessStringScalar(col 6, val a) -> boolean) -> boolean) -> boolean predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 238 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) outputColumnNames: cdouble, cstring1, ctimestamp1 @@ -76,7 +76,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [5, 6, 8] - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 238 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) Group By Vectorization: @@ -91,7 +91,7 @@ STAGE PLANS: keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2048 Data size: 434588 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 238 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ @@ -102,7 +102,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [3, 4, 5] - Statistics: Num rows: 2048 Data size: 434588 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 238 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs @@ -149,7 +149,7 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1024 Data size: 143566 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 166 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 @@ -158,13 +158,13 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 0, 2, 6, 8, 3, 4, 7, 10, 5, 9, 12, 4] selectExpressions: DoubleColSubtractDoubleScalar(col 0, val 9763215.5639) -> 6:double, DoubleColUnaryMinus(col 7)(children: DoubleColSubtractDoubleScalar(col 0, val 9763215.5639) -> 7:double) -> 8:double, DoubleColUnaryMinus(col 4) -> 7:double, DoubleColMultiplyDoubleColumn(col 4, col 9)(children: CastLongToDouble(col 3) -> 9:double) -> 10:double, DoubleScalarDivideDoubleColumn(val 9763215.5639, col 0) -> 9:double, DecimalColDivideDecimalScalar(col 11, val -1.389)(children: CastLongToDecimal(col 3) -> 11:decimal(19,0)) -> 12:decimal(28,6) - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 326 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/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out index 66764cf42b..e3f75ad409 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out @@ -102,7 +102,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongScalarEqualLongColumn(val 762, col 3) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 12, col 4)(children: CastLongToFloatViaLongToDouble(col 1) -> 12:double) -> boolean, FilterDoubleColGreaterDoubleScalar(col 12, val -5.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDoubleColNotEqualDoubleColumn(col 5, col 12)(children: CastLongToDouble(col 2) -> 12:double) -> boolean) -> boolean, FilterStringGroupColEqualStringScalar(col 6, val a) -> boolean, FilterExprAndExpr(children: FilterDecimalColLessEqualDecimalScalar(col 13, val -1.389)(children: CastLongToDecimal(col 3) -> 13:decimal(22,3)) -> boolean, FilterStringGroupColNotEqualStringScalar(col 7, val a) -> boolean, FilterDecimalScalarNotEqualDecimalColumn(val 79.553, col 14)(children: CastLongToDecimal(col 2) -> 14:decimal(13,3)) -> boolean, FilterLongColNotEqualLongColumn(col 11, col 10) -> boolean) -> boolean) -> boolean predicate: ((762 = cbigint) or ((UDFToFloat(csmallint) < cfloat) and (UDFToDouble(ctimestamp2) > -5.0) and (cdouble <> UDFToDouble(cint))) or (cstring1 = 'a') or ((CAST( cbigint AS decimal(22,3)) <= -1.389) and (cstring2 <> 'a') and (79.553 <> CAST( cint AS decimal(13,3))) and (cboolean2 <> cboolean1))) (type: boolean) - Statistics: Num rows: 5465 Data size: 1157230 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cfloat (type: float), cdouble (type: double) outputColumnNames: ctinyint, csmallint, cint, cfloat, cdouble @@ -110,7 +110,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 4, 5] - Statistics: Num rows: 5465 Data size: 1157230 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: avg(cint), sum(cdouble), stddev_pop(cint), stddev_samp(csmallint), var_samp(cint), avg(cfloat), stddev_samp(cint), min(ctinyint), count(csmallint) Group By Vectorization: @@ -366,7 +366,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 3, val 197) -> boolean, FilterLongColLessLongColumn(col 2, col 3)(children: col 2) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5, val -26.28) -> boolean, FilterDoubleColGreaterDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 1) -> 12:double) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 12, col 4)(children: CastLongToFloatViaLongToDouble(col 0) -> 12:double) -> boolean, FilterStringColRegExpStringScalar(col 6, pattern .*ss.*) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 4, val 79.5530014038086) -> boolean, FilterStringColLikeStringScalar(col 7, pattern 10%) -> boolean) -> boolean) -> boolean predicate: (((cbigint <= 197) and (UDFToLong(cint) < cbigint)) or ((cdouble >= -26.28) and (UDFToDouble(csmallint) > cdouble)) or ((UDFToFloat(ctinyint) > cfloat) and cstring1 regexp '.*ss.*') or ((cfloat > 79.553) and (cstring2 like '10%'))) (type: boolean) - Statistics: Num rows: 6826 Data size: 1131534 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cdouble (type: double) outputColumnNames: ctinyint, csmallint, cint, cbigint, cdouble @@ -374,7 +374,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 5] - Statistics: Num rows: 6826 Data size: 1131534 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(cint), var_pop(cbigint), stddev_pop(csmallint), max(cdouble), avg(ctinyint), min(cint), min(cdouble), stddev_samp(csmallint), var_samp(cint) Group By Vectorization: @@ -622,7 +622,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterTimestampColEqualTimestampColumn(col 8, col 9) -> boolean, FilterDoubleScalarEqualDoubleColumn(val 762.0, col 4) -> boolean, FilterStringGroupColEqualStringScalar(col 6, val ss) -> boolean, FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 1, col 3)(children: col 1) -> boolean, FilterLongScalarEqualLongColumn(val 1, col 11) -> boolean) -> boolean, FilterExprAndExpr(children: SelectColumnIsNotNull(col 10) -> boolean, SelectColumnIsNotNull(col 9) -> boolean, FilterStringGroupColGreaterStringScalar(col 7, val a) -> boolean) -> boolean) -> boolean predicate: ((ctimestamp1 = ctimestamp2) or (762 = cfloat) or (cstring1 = 'ss') or ((UDFToLong(csmallint) <= cbigint) and (1 = cboolean2)) or (cboolean1 is not null and ctimestamp2 is not null and (cstring2 > 'a'))) (type: boolean) - Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cdouble (type: double) outputColumnNames: ctinyint, csmallint, cint, cbigint, cdouble @@ -630,7 +630,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 5] - Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: var_pop(cbigint), count(), max(ctinyint), stddev_pop(csmallint), max(cint), stddev_samp(cdouble), count(ctinyint), avg(ctinyint) Group By Vectorization: @@ -857,7 +857,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterTimestampColLessEqualTimestampColumn(col 9, col 8) -> boolean, FilterDoubleColNotEqualDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 3) -> 12:double) -> boolean, FilterStringScalarLessEqualStringGroupColumn(val ss, col 6) -> boolean) -> boolean, FilterExprAndExpr(children: FilterLongColLessLongColumn(col 1, col 0)(children: col 0) -> boolean, FilterDoubleColGreaterEqualDoubleScalar(col 12, val 0.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean) -> boolean, FilterDoubleColEqualDoubleScalar(col 4, val 17.0) -> boolean) -> boolean predicate: (((ctimestamp2 <= ctimestamp1) and (UDFToDouble(cbigint) <> cdouble) and ('ss' <= cstring1)) or ((csmallint < UDFToShort(ctinyint)) and (UDFToDouble(ctimestamp1) >= 0.0)) or (cfloat = 17)) (type: boolean) - Statistics: Num rows: 2824 Data size: 491654 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 412 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), cbigint (type: bigint), cfloat (type: float) outputColumnNames: ctinyint, cint, cbigint, cfloat @@ -865,7 +865,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 2, 3, 4] - Statistics: Num rows: 2824 Data size: 491654 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 412 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: avg(ctinyint), max(cbigint), stddev_samp(cint), var_pop(cint), var_pop(cbigint), max(cfloat) Group By Vectorization: @@ -1100,7 +1100,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterStringColRegExpStringScalar(col 6, pattern a.*) -> boolean, FilterStringColLikeStringScalar(col 7, pattern %ss%) -> boolean) -> boolean, FilterExprAndExpr(children: FilterLongScalarNotEqualLongColumn(val 1, col 11) -> boolean, FilterDecimalColLessDecimalScalar(col 12, val 79.553)(children: CastLongToDecimal(col 1) -> 12:decimal(8,3)) -> boolean, FilterLongScalarNotEqualLongColumn(val -257, col 0)(children: col 0) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 5, col 13)(children: CastLongToDouble(col 0) -> 13:double) -> boolean, FilterDoubleColGreaterEqualDoubleColumn(col 4, col 13)(children: CastLongToFloatViaLongToDouble(col 2) -> 13:double) -> boolean) -> boolean, FilterExprAndExpr(children: FilterLongColLessLongColumn(col 2, col 3)(children: col 2) -> boolean, FilterLongColGreaterLongColumn(col 0, col 3)(children: col 0) -> boolean) -> boolean) -> boolean predicate: ((cstring1 regexp 'a.*' and (cstring2 like '%ss%')) or ((1 <> cboolean2) and (CAST( csmallint AS decimal(8,3)) < 79.553) and (-257 <> UDFToInteger(ctinyint))) or ((cdouble > UDFToDouble(ctinyint)) and (cfloat >= UDFToFloat(cint))) or ((UDFToLong(cint) < cbigint) and (UDFToLong(ctinyint) > cbigint))) (type: boolean) - Statistics: Num rows: 9898 Data size: 2462086 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 612 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cdouble (type: double), ctimestamp2 (type: timestamp), cstring1 (type: string), cboolean2 (type: boolean), ctinyint (type: tinyint), cfloat (type: float), ctimestamp1 (type: timestamp), csmallint (type: smallint), cbigint (type: bigint), (-3728 * cbigint) (type: bigint), (- cint) (type: int), (-863.257 - CAST( cint AS decimal(10,0))) (type: decimal(14,3)), (- csmallint) (type: smallint), (csmallint - (- csmallint)) (type: smallint), ((csmallint - (- csmallint)) + (- csmallint)) (type: smallint), (UDFToDouble(cint) / UDFToDouble(cint)) (type: double), ((-863.257 - CAST( cint AS decimal(10,0))) - -26.28) (type: decimal(15,3)), (- cfloat) (type: float), (cdouble * -89010.0) (type: double), (UDFToDouble(ctinyint) / 988888.0) (type: double), (- ctinyint) (type: tinyint), (79.553 / CAST( ctinyint AS decimal(3,0))) (type: decimal(9,7)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22 @@ -1109,7 +1109,7 @@ STAGE PLANS: native: true projectedOutputColumns: [2, 5, 9, 6, 11, 0, 4, 8, 1, 3, 14, 15, 17, 18, 20, 22, 24, 26, 13, 23, 28, 19, 30] selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 3) -> 14:long, LongColUnaryMinus(col 2) -> 15:long, DecimalScalarSubtractDecimalColumn(val -863.257, col 16)(children: CastLongToDecimal(col 2) -> 16:decimal(10,0)) -> 17:decimal(14,3), LongColUnaryMinus(col 1) -> 18:long, LongColSubtractLongColumn(col 1, col 19)(children: LongColUnaryMinus(col 1) -> 19:long) -> 20:long, LongColAddLongColumn(col 21, col 19)(children: LongColSubtractLongColumn(col 1, col 19)(children: LongColUnaryMinus(col 1) -> 19:long) -> 21:long, LongColUnaryMinus(col 1) -> 19:long) -> 22:long, DoubleColDivideDoubleColumn(col 13, col 23)(children: CastLongToDouble(col 2) -> 13:double, CastLongToDouble(col 2) -> 23:double) -> 24:double, DecimalColSubtractDecimalScalar(col 25, val -26.28)(children: DecimalScalarSubtractDecimalColumn(val -863.257, col 16)(children: CastLongToDecimal(col 2) -> 16:decimal(10,0)) -> 25:decimal(14,3)) -> 26:decimal(15,3), DoubleColUnaryMinus(col 4) -> 13:double, DoubleColMultiplyDoubleScalar(col 5, val -89010.0) -> 23:double, DoubleColDivideDoubleScalar(col 27, val 988888.0)(children: CastLongToDouble(col 0) -> 27:double) -> 28:double, LongColUnaryMinus(col 0) -> 19:long, DecimalScalarDivideDecimalColumn(val 79.553, col 29)(children: CastLongToDecimal(col 0) -> 29:decimal(3,0)) -> 30:decimal(9,7) - Statistics: Num rows: 9898 Data size: 5632662 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1204 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: timestamp), _col3 (type: string), _col4 (type: boolean), _col5 (type: tinyint), _col6 (type: float), _col7 (type: timestamp), _col8 (type: smallint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: int), _col12 (type: decimal(14,3)), _col13 (type: smallint), _col14 (type: smallint), _col15 (type: smallint), _col16 (type: double), _col17 (type: decimal(15,3)), _col18 (type: float), _col19 (type: double), _col20 (type: double), _col21 (type: tinyint), _col22 (type: decimal(9,7)) sort order: +++++++++++++++++++++++ @@ -1117,7 +1117,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 9898 Data size: 5632662 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1204 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -1146,19 +1146,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22] - Statistics: Num rows: 9898 Data size: 5632662 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1204 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 50 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 50 Data size: 28540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1204 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 50 Data size: 28540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1204 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1398,7 +1398,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongScalarGreaterLongColumn(val 197, col 0)(children: col 0) -> boolean, FilterLongColEqualLongColumn(col 2, col 3)(children: col 2) -> boolean) -> boolean, FilterLongColEqualLongScalar(col 3, val 359) -> boolean, FilterLongColLessLongScalar(col 10, val 0) -> boolean, FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 6, pattern %ss) -> boolean, FilterDoubleColLessEqualDoubleColumn(col 4, col 12)(children: CastLongToFloatViaLongToDouble(col 0) -> 12:double) -> boolean) -> boolean) -> boolean predicate: (((197 > UDFToInteger(ctinyint)) and (UDFToLong(cint) = cbigint)) or (cbigint = 359) or (cboolean1 < 0) or ((cstring1 like '%ss') and (cfloat <= UDFToFloat(ctinyint)))) (type: boolean) - Statistics: Num rows: 8194 Data size: 1734900 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cbigint (type: bigint), cstring1 (type: string), cboolean1 (type: boolean), cfloat (type: float), cdouble (type: double), ctimestamp2 (type: timestamp), csmallint (type: smallint), cstring2 (type: string), cboolean2 (type: boolean), (UDFToDouble(cint) / UDFToDouble(cbigint)) (type: double), (CAST( cbigint AS decimal(19,0)) % 79.553) (type: decimal(5,3)), (- (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (10.175 % cfloat) (type: float), (- cfloat) (type: float), (cfloat - (- cfloat)) (type: float), ((cfloat - (- cfloat)) % -6432.0) (type: float), (cdouble * UDFToDouble(csmallint)) (type: double), (- cdouble) (type: double), (- cbigint) (type: bigint), (UDFToDouble(cfloat) - (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (- csmallint) (type: smallint), (3569 % cbigint) (type: bigint), (359.0 - cdouble) (type: double), (- csmallint) (type: smallint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 @@ -1407,7 +1407,7 @@ STAGE PLANS: native: true projectedOutputColumns: [2, 3, 6, 10, 4, 5, 9, 1, 7, 11, 14, 16, 12, 13, 17, 19, 18, 21, 20, 22, 23, 26, 27, 24, 28] selectExpressions: DoubleColDivideDoubleColumn(col 12, col 13)(children: CastLongToDouble(col 2) -> 12:double, CastLongToDouble(col 3) -> 13:double) -> 14:double, DecimalColModuloDecimalScalar(col 15, val 79.553)(children: CastLongToDecimal(col 3) -> 15:decimal(19,0)) -> 16:decimal(5,3), DoubleColUnaryMinus(col 17)(children: DoubleColDivideDoubleColumn(col 12, col 13)(children: CastLongToDouble(col 2) -> 12:double, CastLongToDouble(col 3) -> 13:double) -> 17:double) -> 12:double, DoubleScalarModuloDoubleColumn(val 10.175000190734863, col 4) -> 13:double, DoubleColUnaryMinus(col 4) -> 17:double, DoubleColSubtractDoubleColumn(col 4, col 18)(children: DoubleColUnaryMinus(col 4) -> 18:double) -> 19:double, DoubleColModuloDoubleScalar(col 20, val -6432.0)(children: DoubleColSubtractDoubleColumn(col 4, col 18)(children: DoubleColUnaryMinus(col 4) -> 18:double) -> 20:double) -> 18:double, DoubleColMultiplyDoubleColumn(col 5, col 20)(children: CastLongToDouble(col 1) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 5) -> 20:double, LongColUnaryMinus(col 3) -> 22:long, DoubleColSubtractDoubleColumn(col 4, col 25)(children: col 4, DoubleColDivideDoubleColumn(col 23, col 24)(children: CastLongToDouble(col 2) -> 23:double, CastLongToDouble(col 3) -> 24:double) -> 25:double) -> 23:double, LongColUnaryMinus(col 1) -> 26:long, LongScalarModuloLongColumn(val 3569, col 3) -> 27:long, DoubleScalarSubtractDoubleColumn(val 359.0, col 5) -> 24:double, LongColUnaryMinus(col 1) -> 28:long - Statistics: Num rows: 8194 Data size: 3349228 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 932 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean), _col4 (type: float), _col5 (type: double), _col6 (type: timestamp), _col7 (type: smallint), _col8 (type: string), _col9 (type: boolean), _col10 (type: double), _col11 (type: decimal(5,3)), _col12 (type: double), _col13 (type: float), _col14 (type: float), _col15 (type: float), _col16 (type: float), _col17 (type: double), _col18 (type: double), _col19 (type: bigint), _col20 (type: double), _col21 (type: smallint), _col22 (type: bigint), _col23 (type: double), _col24 (type: smallint) sort order: +++++++++++++++++++++++++ @@ -1415,7 +1415,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 8194 Data size: 3349228 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 932 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -1444,19 +1444,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 21] - Statistics: Num rows: 8194 Data size: 3349228 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 932 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 10520 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 932 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 10520 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 932 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1645,7 +1645,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDecimalColGreaterDecimalScalar(col 12, val -26.28)(children: CastLongToDecimal(col 1) -> 12:decimal(7,2)) -> boolean, FilterStringColLikeStringScalar(col 7, pattern ss) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 5, col 13)(children: CastLongToDouble(col 3) -> 13:double) -> boolean, FilterStringGroupColGreaterEqualStringScalar(col 6, val ss) -> boolean, FilterDoubleColNotEqualDoubleColumn(col 13, col 5)(children: CastLongToDouble(col 2) -> 13:double) -> boolean) -> boolean, FilterLongColEqualLongScalar(col 0, val -89010)(children: col 0) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13, col 4)(children: CastLongToFloatViaLongToDouble(col 3) -> 13:double) -> boolean, FilterDecimalScalarLessEqualDecimalColumn(val -26.28, col 12)(children: CastLongToDecimal(col 1) -> 12:decimal(7,2)) -> boolean) -> boolean) -> boolean predicate: (((CAST( csmallint AS decimal(7,2)) > -26.28) and (cstring2 like 'ss')) or ((cdouble <= UDFToDouble(cbigint)) and (cstring1 >= 'ss') and (UDFToDouble(cint) <> cdouble)) or (UDFToInteger(ctinyint) = -89010) or ((UDFToFloat(cbigint) <= cfloat) and (-26.28 <= CAST( csmallint AS decimal(7,2))))) (type: boolean) - Statistics: Num rows: 10922 Data size: 2312410 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 810 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cstring1 (type: string), cboolean2 (type: boolean), ctimestamp2 (type: timestamp), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), cboolean1 (type: boolean), (cint + UDFToInteger(csmallint)) (type: int), (cbigint - UDFToLong(ctinyint)) (type: bigint), (- cbigint) (type: bigint), (- cfloat) (type: float), ((cbigint - UDFToLong(ctinyint)) + cbigint) (type: bigint), (cdouble / cdouble) (type: double), (- cdouble) (type: double), (UDFToLong((cint + UDFToInteger(csmallint))) * (- cbigint)) (type: bigint), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (-1.389 / CAST( ctinyint AS decimal(3,0))) (type: decimal(8,7)), (UDFToDouble(cbigint) % cdouble) (type: double), (- csmallint) (type: smallint), (UDFToInteger(csmallint) + (cint + UDFToInteger(csmallint))) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 @@ -1654,7 +1654,7 @@ STAGE PLANS: native: true projectedOutputColumns: [2, 6, 11, 9, 5, 4, 3, 1, 10, 14, 15, 16, 13, 18, 19, 20, 22, 25, 27, 24, 17, 28] selectExpressions: LongColAddLongColumn(col 2, col 1)(children: col 1) -> 14:long, LongColSubtractLongColumn(col 3, col 0)(children: col 0) -> 15:long, LongColUnaryMinus(col 3) -> 16:long, DoubleColUnaryMinus(col 4) -> 13:double, LongColAddLongColumn(col 17, col 3)(children: LongColSubtractLongColumn(col 3, col 0)(children: col 0) -> 17:long) -> 18:long, DoubleColDivideDoubleColumn(col 5, col 5) -> 19:double, DoubleColUnaryMinus(col 5) -> 20:double, LongColMultiplyLongColumn(col 17, col 21)(children: col 17, LongColUnaryMinus(col 3) -> 21:long) -> 22:long, DoubleColAddDoubleColumn(col 23, col 24)(children: DoubleColUnaryMinus(col 5) -> 23:double, CastLongToDouble(col 3) -> 24:double) -> 25:double, DecimalScalarDivideDecimalColumn(val -1.389, col 26)(children: CastLongToDecimal(col 0) -> 26:decimal(3,0)) -> 27:decimal(8,7), DoubleColModuloDoubleColumn(col 23, col 5)(children: CastLongToDouble(col 3) -> 23:double) -> 24:double, LongColUnaryMinus(col 1) -> 17:long, LongColAddLongColumn(col 1, col 21)(children: col 1, LongColAddLongColumn(col 2, col 1)(children: col 1) -> 21:long) -> 28:long - Statistics: Num rows: 10922 Data size: 3594034 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col8 (type: boolean), _col1 (type: string), _col3 (type: timestamp), _col5 (type: float), _col6 (type: bigint), _col1 (type: string), _col4 (type: double), _col0 (type: int), _col7 (type: smallint), _col4 (type: double), _col9 (type: int), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: float), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint), _col17 (type: double), _col18 (type: decimal(8,7)), _col19 (type: double), _col20 (type: smallint), _col21 (type: int) sort order: +++++++++++++++++++++++ @@ -1662,7 +1662,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 10922 Data size: 3594034 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: boolean) Execution mode: vectorized, llap @@ -1692,19 +1692,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [7, 1, 23, 2, 6, 3, 4, 8, 0, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22] - Statistics: Num rows: 10922 Data size: 3594034 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 75 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 75 Data size: 24810 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 75 Data size: 24810 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1950,7 +1950,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDecimalScalarGreaterEqualDecimalColumn(val -1.389, col 12)(children: CastLongToDecimal(col 2) -> 12:decimal(13,3)) -> boolean, FilterLongColLessLongColumn(col 1, col 0)(children: col 0) -> boolean, FilterLongScalarGreaterLongColumn(val -6432, col 1)(children: col 1) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleColumn(col 5, col 4)(children: col 4) -> boolean, FilterStringGroupColLessEqualStringScalar(col 7, val a) -> boolean) -> boolean, FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 6, pattern ss%) -> boolean, FilterDecimalScalarGreaterDecimalColumn(val 10.175, col 13)(children: CastLongToDecimal(col 3) -> 13:decimal(22,3)) -> boolean) -> boolean) -> boolean predicate: (((-1.389 >= CAST( cint AS decimal(13,3))) and (csmallint < UDFToShort(ctinyint)) and (-6432 > UDFToInteger(csmallint))) or ((cdouble >= UDFToDouble(cfloat)) and (cstring2 <= 'a')) or ((cstring1 like 'ss%') and (10.175 > CAST( cbigint AS decimal(22,3))))) (type: boolean) - Statistics: Num rows: 3868 Data size: 795962 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 524 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cstring2 (type: string), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), (UDFToDouble(cbigint) / 3569.0) (type: double), (-257 - UDFToInteger(csmallint)) (type: int), (-6432.0 * cfloat) (type: float), (- cdouble) (type: double), (cdouble * 10.175) (type: double), (UDFToDouble((-6432.0 * cfloat)) / UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), (cint % UDFToInteger(csmallint)) (type: int), (- cdouble) (type: double), (cdouble * (- cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 @@ -1959,7 +1959,7 @@ STAGE PLANS: native: true projectedOutputColumns: [8, 7, 5, 4, 3, 1, 15, 16, 14, 17, 18, 20, 19, 21, 22, 24] selectExpressions: DoubleColDivideDoubleScalar(col 14, val 3569.0)(children: CastLongToDouble(col 3) -> 14:double) -> 15:double, LongScalarSubtractLongColumn(val -257, col 1)(children: col 1) -> 16:long, DoubleScalarMultiplyDoubleColumn(val -6432.0, col 4) -> 14:double, DoubleColUnaryMinus(col 5) -> 17:double, DoubleColMultiplyDoubleScalar(col 5, val 10.175) -> 18:double, DoubleColDivideDoubleColumn(col 19, col 4)(children: col 19, col 4) -> 20:double, DoubleColUnaryMinus(col 4) -> 19:double, LongColModuloLongColumn(col 2, col 1)(children: col 1) -> 21:long, DoubleColUnaryMinus(col 5) -> 22:double, DoubleColMultiplyDoubleColumn(col 5, col 23)(children: DoubleColUnaryMinus(col 5) -> 23:double) -> 24:double - Statistics: Num rows: 3868 Data size: 748844 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: smallint), _col1 (type: string), _col2 (type: double), _col3 (type: float), _col4 (type: bigint), _col6 (type: double), _col7 (type: int), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: float), _col13 (type: int), _col14 (type: double), _col15 (type: double) sort order: +++++++++++++++ @@ -1967,7 +1967,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3868 Data size: 748844 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: timestamp) Execution mode: vectorized, llap @@ -1997,19 +1997,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [15, 1, 2, 3, 4, 0, 5, 6, 7, 8, 9, 10, 11, 12, 8, 14] - Statistics: Num rows: 3868 Data size: 748844 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 45 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 45 Data size: 8880 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 45 Data size: 8880 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2197,7 +2197,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 1, val -257)(children: col 1) -> boolean, FilterExprOrExpr(children: FilterLongScalarEqualLongColumn(val -6432, col 1)(children: col 1) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 2) -> 12:double) -> boolean, FilterLongColLessEqualLongColumn(col 0, col 2)(children: col 0) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((UDFToInteger(csmallint) >= -257) and ((-6432 = UDFToInteger(csmallint)) or ((UDFToDouble(cint) >= cdouble) and (UDFToInteger(ctinyint) <= cint)))) (type: boolean) - Statistics: Num rows: 2503 Data size: 52344 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cbigint (type: bigint) outputColumnNames: ctinyint, csmallint, cbigint @@ -2205,7 +2205,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 3] - Statistics: Num rows: 2503 Data size: 52344 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: stddev_samp(csmallint), sum(cbigint), var_pop(ctinyint), count() Group By Vectorization: @@ -2220,7 +2220,7 @@ STAGE PLANS: keys: csmallint (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1141 Data size: 204228 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + @@ -2229,7 +2229,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1141 Data size: 204228 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: bigint), _col3 (type: struct), _col4 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2265,7 +2265,7 @@ STAGE PLANS: keys: KEY._col0 (type: smallint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1141 Data size: 39924 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: smallint), (UDFToInteger(_col0) % -75) (type: int), _col1 (type: double), (-1.389 / CAST( _col0 AS decimal(5,0))) (type: decimal(10,9)), _col2 (type: bigint), (UDFToDouble((UDFToInteger(_col0) % -75)) / UDFToDouble(_col2)) (type: double), (- (UDFToInteger(_col0) % -75)) (type: int), _col3 (type: double), (- (- (UDFToInteger(_col0) % -75))) (type: int), _col4 (type: bigint), (_col4 - -89010) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 @@ -2274,7 +2274,7 @@ STAGE PLANS: native: true projectedOutputColumns: [0, 5, 1, 7, 2, 11, 12, 3, 8, 4, 13] selectExpressions: LongColModuloLongScalar(col 0, val -75)(children: col 0) -> 5:long, DecimalScalarDivideDecimalColumn(val -1.389, col 6)(children: CastLongToDecimal(col 0) -> 6:decimal(5,0)) -> 7:decimal(10,9), DoubleColDivideDoubleColumn(col 9, col 10)(children: CastLongToDouble(col 8)(children: LongColModuloLongScalar(col 0, val -75)(children: col 0) -> 8:long) -> 9:double, CastLongToDouble(col 2) -> 10:double) -> 11:double, LongColUnaryMinus(col 8)(children: LongColModuloLongScalar(col 0, val -75)(children: col 0) -> 8:long) -> 12:long, LongColUnaryMinus(col 13)(children: LongColUnaryMinus(col 8)(children: LongColModuloLongScalar(col 0, val -75)(children: col 0) -> 8:long) -> 13:long) -> 8:long, LongColSubtractLongScalar(col 4, val -89010) -> 13:long - Statistics: Num rows: 1141 Data size: 199664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: double), _col3 (type: decimal(10,9)), _col4 (type: bigint), _col5 (type: double), _col6 (type: int), _col7 (type: double), _col8 (type: int), _col9 (type: bigint), _col10 (type: bigint) sort order: +++++++++++ @@ -2282,7 +2282,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1141 Data size: 199664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: vectorized, llap @@ -2301,19 +2301,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10] - Statistics: Num rows: 1141 Data size: 199664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 20 Data size: 3504 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 20 Data size: 3504 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2477,7 +2477,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5, val 2563.58) -> boolean, FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 3, col 2)(children: col 2) -> boolean, FilterLongColLessLongColumn(col 1, col 2)(children: col 1) -> boolean, FilterDoubleColLessDoubleScalar(col 4, val -5638.14990234375) -> boolean) -> boolean, FilterDecimalScalarEqualDecimalColumn(val 2563.58, col 12)(children: CastLongToDecimal(col 0) -> 12:decimal(6,2)) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 5, col 13)(children: CastLongToDouble(col 3) -> 13:double) -> boolean, FilterDecimalScalarGreaterDecimalColumn(val -5638.15, col 14)(children: CastLongToDecimal(col 3) -> 14:decimal(21,2)) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and (UDFToInteger(csmallint) < cint) and (cfloat < -5638.15)) or (2563.58 = CAST( ctinyint AS decimal(6,2))) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > CAST( cbigint AS decimal(21,2)))))) (type: boolean) - Statistics: Num rows: 2503 Data size: 59820 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cfloat (type: float), cdouble (type: double) outputColumnNames: cfloat, cdouble @@ -2485,7 +2485,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [4, 5] - Statistics: Num rows: 2503 Data size: 59820 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: var_samp(cdouble), count(cfloat), sum(cfloat), var_pop(cdouble), stddev_pop(cdouble), sum(cdouble) Group By Vectorization: @@ -2500,7 +2500,7 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1136 Data size: 306696 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -2509,7 +2509,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1136 Data size: 306696 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: bigint), _col3 (type: double), _col4 (type: struct), _col5 (type: struct), _col6 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2545,7 +2545,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1136 Data size: 61320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double), _col1 (type: double), (2563.58 * _col1) (type: double), (- _col1) (type: double), _col2 (type: bigint), ((2563.58 * _col1) + -5638.15) (type: double), ((- _col1) * ((2563.58 * _col1) + -5638.15)) (type: double), _col3 (type: double), _col4 (type: double), (_col0 - (- _col1)) (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762.0) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762.0)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -2554,7 +2554,7 @@ STAGE PLANS: native: true projectedOutputColumns: [0, 1, 7, 8, 2, 10, 11, 3, 4, 12, 5, 9, 13, 6, 15] selectExpressions: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 1) -> 7:double, DoubleColUnaryMinus(col 1) -> 8:double, DoubleColAddDoubleScalar(col 9, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 1) -> 9:double) -> 10:double, DoubleColMultiplyDoubleColumn(col 9, col 12)(children: DoubleColUnaryMinus(col 1) -> 9:double, DoubleColAddDoubleScalar(col 11, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 1) -> 11:double) -> 12:double) -> 11:double, DoubleColSubtractDoubleColumn(col 0, col 9)(children: DoubleColUnaryMinus(col 1) -> 9:double) -> 12:double, DoubleColAddDoubleColumn(col 0, col 1) -> 9:double, DoubleColMultiplyDoubleScalar(col 0, val 762.0) -> 13:double, DoubleScalarModuloDoubleColumn(val -863.257, col 14)(children: DoubleColMultiplyDoubleScalar(col 0, val 762.0) -> 14:double) -> 15:double - Statistics: Num rows: 1136 Data size: 143112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -2562,7 +2562,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1136 Data size: 143112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double) Reducer 3 Execution mode: vectorized, llap @@ -2581,13 +2581,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 13] - Statistics: Num rows: 1136 Data size: 143112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1136 Data size: 143112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2801,7 +2801,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDoubleColNotEqualDoubleScalar(col 12, val 0.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongScalarNotEqualLongColumn(val -257, col 0)(children: col 0) -> boolean, SelectColumnIsNotNull(col 11) -> boolean, FilterStringColRegExpStringScalar(col 6, pattern .*ss) -> boolean, FilterDoubleScalarLessDoubleColumn(val -3.0, col 12)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean) -> boolean, FilterDoubleColEqualDoubleScalar(col 12, val -5.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 12, val 0.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterStringColLikeStringScalar(col 7, pattern %b%) -> boolean) -> boolean, FilterDoubleColEqualDoubleColumn(col 5, col 12)(children: CastLongToDouble(col 2) -> 12:double) -> boolean, FilterExprAndExpr(children: SelectColumnIsNull(col 10) -> boolean, FilterDoubleColLessDoubleColumn(col 4, col 12)(children: CastLongToFloatViaLongToDouble(col 2) -> 12:double) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((UDFToDouble(ctimestamp1) <> 0.0) and (((-257 <> UDFToInteger(ctinyint)) and cboolean2 is not null and cstring1 regexp '.*ss' and (-3.0 < UDFToDouble(ctimestamp1))) or (UDFToDouble(ctimestamp2) = -5.0) or ((UDFToDouble(ctimestamp1) < 0.0) and (cstring2 like '%b%')) or (cdouble = UDFToDouble(cint)) or (cboolean1 is null and (cfloat < UDFToFloat(cint))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 3019778 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1041 Data size: 255996 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) outputColumnNames: ctinyint, csmallint, cint, cfloat, cdouble, cstring1, ctimestamp1 @@ -2809,7 +2809,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 4, 5, 6, 8] - Statistics: Num rows: 12288 Data size: 3019778 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1041 Data size: 255996 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: stddev_pop(cint), avg(csmallint), count(), min(ctinyint), var_samp(csmallint), var_pop(cfloat), avg(cint), var_samp(cfloat), avg(cfloat), min(cdouble), var_pop(csmallint), stddev_pop(ctinyint), sum(cint) Group By Vectorization: @@ -2824,7 +2824,7 @@ STAGE PLANS: keys: ctimestamp1 (type: timestamp), cstring1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 6144 Data size: 5199016 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 520 Data size: 440086 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: string) sort order: ++ @@ -2833,7 +2833,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 6144 Data size: 5199016 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 520 Data size: 440086 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: bigint), _col5 (type: tinyint), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct), _col11 (type: double), _col12 (type: struct), _col13 (type: struct), _col14 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2869,7 +2869,7 @@ STAGE PLANS: keys: KEY._col0 (type: timestamp), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 3072 Data size: 645716 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 260 Data size: 54730 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / CAST( (- _col5) AS decimal(3,0))) (type: decimal(8,6)), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38 @@ -2878,7 +2878,7 @@ STAGE PLANS: native: true projectedOutputColumns: [0, 1, 2, 15, 16, 3, 17, 18, 4, 19, 22, 5, 21, 23, 6, 20, 26, 27, 7, 25, 8, 9, 29, 28, 10, 30, 32, 24, 11, 12, 31, 34, 37, 13, 14, 38, 40, 4, 39] selectExpressions: DoubleColMultiplyDoubleScalar(col 2, val 10.175) -> 15:double, DoubleColUnaryMinus(col 2) -> 16:double, DoubleColUnaryMinus(col 2) -> 17:double, DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 18:double, LongColUnaryMinus(col 4) -> 19:long, DoubleColMultiplyDoubleColumn(col 20, col 21)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 20:double, DoubleColUnaryMinus(col 2) -> 21:double) -> 22:double, DoubleColMultiplyDoubleColumn(col 23, col 20)(children: DoubleColMultiplyDoubleColumn(col 20, col 21)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 20:double, DoubleColUnaryMinus(col 2) -> 21:double) -> 23:double, CastLongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 20)(children: DoubleColMultiplyDoubleScalar(col 2, val 10.175) -> 20:double) -> 23:double, DoubleColAddDoubleColumn(col 6, col 25)(children: DoubleColMultiplyDoubleColumn(col 26, col 20)(children: DoubleColMultiplyDoubleColumn(col 20, col 25)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 20:double, DoubleColUnaryMinus(col 2) -> 25:double) -> 26:double, CastLongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 20:double) -> 25:double) -> 20:double, DoubleColUnaryMinus(col 25)(children: DoubleColUnaryMinus(col 2) -> 25:double) -> 26:double, DoubleColDivideDoubleColumn(col 25, col 2)(children: CastLongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 25:double) -> 27:double, DoubleScalarDivideDoubleColumn(val 10.175, col 3) -> 25:double, DoubleColSubtractDoubleColumn(col 28, col 30)(children: DoubleColAddDoubleColumn(col 6, col 29)(children: DoubleColMultiplyDoubleColumn(col 30, col 28)(children: DoubleColMultiplyDoubleColumn(col 28, col 29)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 28:double, DoubleColUnaryMinus(col 2) -> 29:double) -> 30:double, CastLongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 28:double) -> 29:double) -> 28:double, DoubleColMultiplyDoubleColumn(col 31, col 29)(children: DoubleColMultiplyDoubleColumn(col 29, col 30)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 29:double, DoubleColUnaryMinus(col 2) -> 30:double) -> 31:double, CastLongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 29:double) -> 30:double) -> 29:double, DoubleColUnaryMinus(col 30)(children: DoubleColUnaryMinus(col 28)(children: DoubleColMultiplyDoubleScalar(col 2, val 10.175) -> 28:double) -> 30:double) -> 28:double, DoubleColMultiplyDoubleScalar(col 31, val 10.175)(children: DoubleColSubtractDoubleColumn(col 30, col 32)(children: DoubleColAddDoubleColumn(col 6, col 31)(children: DoubleColMultiplyDoubleColumn(col 32, col 30)(children: DoubleColMultiplyDoubleColumn(col 30, col 31)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 30:double, DoubleColUnaryMinus(col 2) -> 31:double) -> 32:double, CastLongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 30:double) -> 31:double) -> 30:double, DoubleColMultiplyDoubleColumn(col 33, col 31)(children: DoubleColMultiplyDoubleColumn(col 31, col 32)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 31:double, DoubleColUnaryMinus(col 2) -> 32:double) -> 33:double, CastLongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 31:double) -> 32:double) -> 31:double) -> 30:double, DoubleScalarModuloDoubleColumn(val 10.175, col 31)(children: DoubleScalarDivideDoubleColumn(val 10.175, col 3) -> 31:double) -> 32:double, LongColUnaryMinus(col 5) -> 24:long, DoubleColUnaryMinus(col 34)(children: DoubleColMultiplyDoubleColumn(col 31, col 33)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 31:double, DoubleColUnaryMinus(col 2) -> 33:double) -> 34:double) -> 31:double, DoubleColModuloDoubleColumn(col 33, col 10)(children: DoubleColUnaryMinus(col 2) -> 33:double) -> 34:double, DecimalScalarDivideDecimalColumn(val -26.28, col 36)(children: CastLongToDecimal(col 35)(children: LongColUnaryMinus(col 5) -> 35:long) -> 36:decimal(3,0)) -> 37:decimal(8,6), DoubleColDivideDoubleColumn(col 33, col 7)(children: DoubleColAddDoubleColumn(col 6, col 38)(children: DoubleColMultiplyDoubleColumn(col 39, col 33)(children: DoubleColMultiplyDoubleColumn(col 33, col 38)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 33:double, DoubleColUnaryMinus(col 2) -> 38:double) -> 39:double, CastLongToDouble(col 35)(children: LongColUnaryMinus(col 4) -> 35:long) -> 33:double) -> 38:double) -> 33:double) -> 38:double, LongColUnaryMinus(col 35)(children: LongColUnaryMinus(col 4) -> 35:long) -> 40:long, DoubleColModuloDoubleScalar(col 33, val -26.28)(children: DoubleColAddDoubleColumn(col 6, col 39)(children: DoubleColMultiplyDoubleColumn(col 41, col 33)(children: DoubleColMultiplyDoubleColumn(col 33, col 39)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 33:double, DoubleColUnaryMinus(col 2) -> 39:double) -> 41:double, CastLongToDouble(col 35)(children: LongColUnaryMinus(col 4) -> 35:long) -> 33:double) -> 39:double) -> 33:double) -> 39:double - Statistics: Num rows: 3072 Data size: 1542740 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 260 Data size: 130650 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double), _col11 (type: tinyint), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double), _col22 (type: double), _col23 (type: double), _col24 (type: double), _col25 (type: double), _col26 (type: double), _col27 (type: tinyint), _col28 (type: double), _col29 (type: double), _col30 (type: double), _col31 (type: double), _col32 (type: decimal(8,6)), _col33 (type: double), _col34 (type: bigint), _col35 (type: double), _col36 (type: bigint), _col37 (type: bigint), _col38 (type: double) sort order: +++++++++++++++++++++++++++++++++++++++ @@ -2886,7 +2886,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3072 Data size: 1542740 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 260 Data size: 130650 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: vectorized, llap @@ -2905,7 +2905,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 4, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 8, 38] - Statistics: Num rows: 3072 Data size: 1542740 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 260 Data size: 130650 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 50 Limit Vectorization: @@ -3206,7 +3206,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5, col 12)(children: CastLongToDouble(col 1) -> 12:double) -> boolean, FilterLongColEqualLongColumn(col 11, col 10) -> boolean, FilterDecimalColLessEqualDecimalScalar(col 13, val -863.257)(children: CastLongToDecimal(col 3) -> 13:decimal(22,3)) -> boolean) -> boolean, FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2, val -257) -> boolean, SelectColumnIsNotNull(col 6) -> boolean, FilterLongColGreaterEqualLongScalar(col 10, val 1) -> boolean) -> boolean, FilterStringColRegExpStringScalar(col 7, pattern b) -> boolean, FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 1, col 0)(children: col 0) -> boolean, SelectColumnIsNull(col 9) -> boolean) -> boolean) -> boolean, SelectColumnIsNotNull(col 10) -> boolean) -> boolean predicate: ((((cdouble < UDFToDouble(csmallint)) and (cboolean2 = cboolean1) and (CAST( cbigint AS decimal(22,3)) <= -863.257)) or ((cint >= -257) and cstring1 is not null and (cboolean1 >= 1)) or cstring2 regexp 'b' or ((csmallint >= UDFToShort(ctinyint)) and ctimestamp2 is null)) and cboolean1 is not null) (type: boolean) - Statistics: Num rows: 7845 Data size: 1661020 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 810 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cboolean1 (type: boolean) outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cboolean1 @@ -3214,7 +3214,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 10] - Statistics: Num rows: 7845 Data size: 1661020 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 810 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(cfloat), sum(cbigint), var_samp(cint), avg(cdouble), min(cbigint), var_pop(cbigint), sum(cint), stddev_samp(ctinyint), stddev_pop(csmallint), avg(cint) Group By Vectorization: @@ -3229,7 +3229,7 @@ STAGE PLANS: keys: cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 3 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 508 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + @@ -3238,7 +3238,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 508 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: float), _col2 (type: bigint), _col3 (type: struct), _col4 (type: struct), _col5 (type: bigint), _col6 (type: struct), _col7 (type: bigint), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct) Execution mode: vectorized, llap LLAP IO: all inputs @@ -3274,7 +3274,7 @@ STAGE PLANS: keys: KEY._col0 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 3 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: float), (- _col1) (type: float), (-26.28 / UDFToDouble(_col1)) (type: double), _col2 (type: bigint), (CAST( _col2 AS decimal(19,0)) - 10.175) (type: decimal(23,3)), _col3 (type: double), (_col3 % UDFToDouble(_col1)) (type: double), (10.175 + (- _col1)) (type: float), _col4 (type: double), (UDFToDouble((CAST( _col2 AS decimal(19,0)) - 10.175)) + _col3) (type: double), _col5 (type: bigint), _col6 (type: double), (- (10.175 + (- _col1))) (type: float), (79.553 / _col6) (type: double), (_col3 % (79.553 / _col6)) (type: double), _col7 (type: bigint), _col8 (type: double), (-1.389 * CAST( _col5 AS decimal(19,0))) (type: decimal(24,3)), (CAST( _col7 AS decimal(19,0)) - (-1.389 * CAST( _col5 AS decimal(19,0)))) (type: decimal(25,3)), _col9 (type: double), (- (CAST( _col7 AS decimal(19,0)) - (-1.389 * CAST( _col5 AS decimal(19,0))))) (type: decimal(25,3)), _col10 (type: double), (- _col10) (type: double), (_col10 * UDFToDouble(_col7)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25 @@ -3283,7 +3283,7 @@ STAGE PLANS: native: true projectedOutputColumns: [0, 1, 11, 12, 2, 14, 3, 15, 17, 4, 19, 5, 6, 16, 20, 22, 7, 8, 23, 26, 9, 28, 10, 21, 30] selectExpressions: DoubleColUnaryMinus(col 1) -> 11:double, DoubleScalarDivideDoubleColumn(val -26.28, col 1)(children: col 1) -> 12:double, DecimalColSubtractDecimalScalar(col 13, val 10.175)(children: CastLongToDecimal(col 2) -> 13:decimal(19,0)) -> 14:decimal(23,3), DoubleColModuloDoubleColumn(col 3, col 1)(children: col 1) -> 15:double, DoubleScalarAddDoubleColumn(val 10.175000190734863, col 16)(children: DoubleColUnaryMinus(col 1) -> 16:double) -> 17:double, DoubleColAddDoubleColumn(col 16, col 3)(children: CastDecimalToDouble(col 18)(children: DecimalColSubtractDecimalScalar(col 13, val 10.175)(children: CastLongToDecimal(col 2) -> 13:decimal(19,0)) -> 18:decimal(23,3)) -> 16:double) -> 19:double, DoubleColUnaryMinus(col 20)(children: DoubleScalarAddDoubleColumn(val 10.175000190734863, col 16)(children: DoubleColUnaryMinus(col 1) -> 16:double) -> 20:double) -> 16:double, DoubleScalarDivideDoubleColumn(val 79.553, col 6) -> 20:double, DoubleColModuloDoubleColumn(col 3, col 21)(children: DoubleScalarDivideDoubleColumn(val 79.553, col 6) -> 21:double) -> 22:double, DecimalScalarMultiplyDecimalColumn(val -1.389, col 13)(children: CastLongToDecimal(col 5) -> 13:decimal(19,0)) -> 23:decimal(24,3), DecimalColSubtractDecimalColumn(col 13, col 25)(children: CastLongToDecimal(col 7) -> 13:decimal(19,0), DecimalScalarMultiplyDecimalColumn(val -1.389, col 24)(children: CastLongToDecimal(col 5) -> 24:decimal(19,0)) -> 25:decimal(24,3)) -> 26:decimal(25,3), FuncNegateDecimalToDecimal(col 27)(children: DecimalColSubtractDecimalColumn(col 13, col 25)(children: CastLongToDecimal(col 7) -> 13:decimal(19,0), DecimalScalarMultiplyDecimalColumn(val -1.389, col 24)(children: CastLongToDecimal(col 5) -> 24:decimal(19,0)) -> 25:decimal(24,3)) -> 27:decimal(25,3)) -> 28:decimal(25,3), DoubleColUnaryMinus(col 10) -> 21:double, DoubleColMultiplyDoubleColumn(col 10, col 29)(children: CastLongToDouble(col 7) -> 29:double) -> 30:double - Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + @@ -3291,7 +3291,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: float), _col2 (type: float), _col3 (type: double), _col4 (type: bigint), _col5 (type: decimal(23,3)), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint), _col12 (type: double), _col13 (type: float), _col14 (type: double), _col15 (type: double), _col17 (type: bigint), _col18 (type: double), _col19 (type: decimal(24,3)), _col20 (type: decimal(25,3)), _col21 (type: double), _col22 (type: decimal(25,3)), _col23 (type: double), _col24 (type: double), _col25 (type: double) Reducer 3 Execution mode: vectorized, llap @@ -3310,13 +3310,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 13, 16, 17, 18, 19, 20, 21, 22, 23, 24] - Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 600 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_case.q.out b/ql/src/test/results/clientpositive/llap/vectorized_case.q.out index 80add939e7..ba074dfe5e 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_case.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_case.q.out @@ -61,7 +61,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1, val 418) -> boolean, FilterLongColEqualLongScalar(col 1, val 12205) -> boolean, FilterLongColEqualLongScalar(col 1, val 10583) -> boolean) -> boolean predicate: ((csmallint = 418) or (csmallint = 12205) or (csmallint = 10583)) (type: boolean) - Statistics: Num rows: 6 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 @@ -70,13 +70,13 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 15, 16] selectExpressions: IfExprStringScalarStringGroupColumn(col 12, val a, col 14)(children: LongColEqualLongScalar(col 1, val 418) -> 12:long, IfExprStringScalarStringScalar(col 13, val b, val c)(children: LongColEqualLongScalar(col 1, val 12205) -> 13:long) -> 14:String) -> 15:String, IfExprStringScalarStringGroupColumn(col 12, val a, col 14)(children: LongColEqualLongScalar(col 1, val 418) -> 12:long, IfExprStringScalarStringScalar(col 13, val b, val c)(children: LongColEqualLongScalar(col 1, val 12205) -> 13:long) -> 14:String) -> 16:String - Statistics: Num rows: 6 Data size: 2228 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 2228 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -203,7 +203,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1, val 418) -> boolean, FilterLongColEqualLongScalar(col 1, val 12205) -> boolean, FilterLongColEqualLongScalar(col 1, val 10583) -> boolean) -> boolean predicate: ((csmallint = 418) or (csmallint = 12205) or (csmallint = 10583)) (type: boolean) - Statistics: Num rows: 6 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE (null) END (type: string), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN (null) ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 @@ -212,13 +212,13 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 16, 19] selectExpressions: IfExprStringScalarStringGroupColumn(col 12, val a, col 15)(children: LongColEqualLongScalar(col 1, val 418) -> 12:long, IfExprColumnNull(col 13, col 14, null)(children: LongColEqualLongScalar(col 1, val 12205) -> 13:long, ConstantVectorExpression(val b) -> 14:string) -> 15:string) -> 16:String, IfExprStringScalarStringGroupColumn(col 12, val a, col 18)(children: LongColEqualLongScalar(col 1, val 418) -> 12:long, IfExprNullColumn(col 17, null, col 15)(children: LongColEqualLongScalar(col 1, val 12205) -> 17:long, ConstantVectorExpression(val c) -> 15:string) -> 18:string) -> 19:String - Statistics: Num rows: 6 Data size: 2228 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 2228 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 372 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_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out index d4b9a1cafd..225435e27b 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out @@ -2589,9 +2589,9 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col4 residual filter predicates: {((_col0 = _col2) or (_col1 = _col4))} - Statistics: Num rows: 4000 Data size: 4420000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1105 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 4000 Data size: 4420000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1105 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -6755,45 +6755,45 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 2944 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), UDFToDouble(_col2) (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: string), UDFToDouble(_col2) (type: double) - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart_orc Partition key expr: ds - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Target Vertex: Map 1 Select Operator expressions: UDFToDouble(_col2) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Dynamic Partitioning Event Operator Target column: hr (int) Target Input: srcpart_orc Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Target Vertex: Map 1 Execution mode: llap LLAP IO: all inputs diff --git a/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out index 2a95065203..eb6eabea40 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out @@ -40,11 +40,11 @@ STAGE PLANS: outputColumnNames: _col2, _col3 input vertices: 1 Map 3 - Statistics: Num rows: 661228 Data size: 7913928 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 585044 Data size: 7002120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: smallint), _col3 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 661228 Data size: 7913928 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 585044 Data size: 7002120 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -54,7 +54,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 1452263 Data size: 11604232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1284939 Data size: 10267240 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) mode: hash @@ -81,16 +81,16 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 146796 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ctinyint is not null and csmallint is not null) (type: boolean) - Statistics: Num rows: 6848 Data size: 81820 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6059 Data size: 72396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cdouble (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6848 Data size: 81820 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6059 Data size: 72396 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 6848 Data size: 81820 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6059 Data size: 72396 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: smallint), _col2 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs diff --git a/ql/src/test/results/clientpositive/mapjoin47.q.out b/ql/src/test/results/clientpositive/mapjoin47.q.out index 2904b68813..89047295ed 100644 --- a/ql/src/test/results/clientpositive/mapjoin47.q.out +++ b/ql/src/test/results/clientpositive/mapjoin47.q.out @@ -378,13 +378,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((_col0 = _col2) or UDFToDouble(_col1) BETWEEN 100.0 AND 102.0 or UDFToDouble(_col3) BETWEEN 100.0 AND 102.0)} - Statistics: Num rows: 9026 Data size: 173876 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -488,13 +488,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0)} {((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0)} - Statistics: Num rows: 1388 Data size: 26738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -592,13 +592,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {(((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0) or ((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0))} - Statistics: Num rows: 8332 Data size: 160507 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -698,13 +698,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {(struct(_col0,_col2)) IN (const struct(100,100), const struct(101,101), const struct(102,102))} - Statistics: Num rows: 3125 Data size: 60200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -817,17 +817,17 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) >= 100.0)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -952,13 +952,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1064,7 +1064,7 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((UDFToDouble(_col2) + UDFToDouble(_col0)) >= 100.0)} - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1108,13 +1108,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4582 Data size: 88278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1130,7 +1130,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b @@ -1153,13 +1153,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4582 Data size: 88278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1282,13 +1282,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1393,12 +1393,12 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((UDFToDouble(_col2) + UDFToDouble(_col0)) >= 100.0)} - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Local Work: Map Reduce Local Work @@ -1410,13 +1410,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4582 Data size: 88278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1556,13 +1556,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1731,17 +1731,17 @@ STAGE PLANS: 3 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 residual filter predicates: {((_col6 = _col24) or ((_col28 = _col16) and (_col8 = 42)))} {((_col12 = _col24) or ((_col27 = _col15) and (_col13 = _col25)))} {((_col0 = _col24) or ((_col1 = _col25) and (_col26 = _col20)))} - Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: string), _col19 (type: string), _col20 (type: int), _col21 (type: float), _col22 (type: boolean), _col23 (type: string), _col24 (type: string), _col25 (type: string), _col26 (type: int), _col27 (type: float), _col28 (type: boolean), _col29 (type: string), _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: float), _col16 (type: boolean), _col17 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: float), _col10 (type: boolean), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE 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/multi_insert_move_tasks_share_dependencies.q.out b/ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out index af0ef54a74..041165aada 100644 --- a/ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out @@ -769,26 +769,26 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -796,15 +796,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -923,26 +923,26 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -950,15 +950,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1145,26 +1145,26 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1172,15 +1172,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1299,26 +1299,26 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1326,15 +1326,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2831,38 +2831,38 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2887,16 +2887,16 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2944,38 +2944,38 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -3000,16 +3000,16 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3057,38 +3057,38 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -3113,16 +3113,16 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3170,38 +3170,38 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -3226,16 +3226,16 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3321,38 +3321,38 @@ STAGE PLANS: name: default.src_multi2 Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -3403,16 +3403,16 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3545,38 +3545,38 @@ STAGE PLANS: name: default.src_multi2 Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -3627,16 +3627,16 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3779,38 +3779,38 @@ STAGE PLANS: name: default.src_multi2 Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -3939,16 +3939,16 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -4091,38 +4091,38 @@ STAGE PLANS: name: default.src_multi2 Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -4251,16 +4251,16 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/pcr.q.out b/ql/src/test/results/clientpositive/pcr.q.out index 5d0d170245..20a3359772 100644 --- a/ql/src/test/results/clientpositive/pcr.q.out +++ b/ql/src/test/results/clientpositive/pcr.q.out @@ -256,16 +256,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((ds <= '2000-04-09') or (key < 5)) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -422,13 +422,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -721,16 +721,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds < '2000-04-09') and (key < 5)) or ((ds > '2000-04-09') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -839,13 +839,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -914,16 +914,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds < '2000-04-10') and (key < 5)) or ((ds > '2000-04-08') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -1080,13 +1080,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1165,16 +1165,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds < '2000-04-10') or (key < 5)) and ((ds > '2000-04-08') or (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -1331,13 +1331,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2100,16 +2100,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds = '2000-04-08') and (key = 1)) or ((ds = '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false Path -> Alias: @@ -2217,13 +2217,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2865,16 +2865,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds > '2000-04-08') and (ds < '2000-04-11')) or (key = 2)) (type: boolean) - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false Path -> Alias: @@ -3078,13 +3078,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -3185,16 +3185,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((ds > '2000-04-08') or ((ds <= '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false Path -> Alias: @@ -3350,13 +3350,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/pcs.q.out b/ql/src/test/results/clientpositive/pcs.q.out index af5d11ad44..518d6115d5 100644 --- a/ql/src/test/results/clientpositive/pcs.q.out +++ b/ql/src/test/results/clientpositive/pcs.q.out @@ -1658,17 +1658,17 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((key = 3) or ((struct(((ds = '2000-04-08') or (key = 2)),key)) IN (const struct(true,2), const struct(false,3)) and ((key + 5) > 0))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/perf/query10.q.out b/ql/src/test/results/clientpositive/perf/query10.q.out index e300561101..2756c520ad 100644 --- a/ql/src/test/results/clientpositive/perf/query10.q.out +++ b/ql/src/test/results/clientpositive/perf/query10.q.out @@ -136,24 +136,24 @@ Stage-0 Stage-1 Reducer 7 File Output Operator [FS_74] - Limit [LIM_73] (rows=100 width=88) + Limit [LIM_73] (rows=1 width=88) Number of rows:100 - Select Operator [SEL_72] (rows=383325119 width=88) + Select Operator [SEL_72] (rows=1 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_71] - Select Operator [SEL_70] (rows=383325119 width=88) + Select Operator [SEL_70] (rows=1 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col8","_col10","_col12"] - Group By Operator [GBY_69] (rows=383325119 width=88) + Group By Operator [GBY_69] (rows=1 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_68] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Group By Operator [GBY_67] (rows=766650239 width=88) + Group By Operator [GBY_67] (rows=1 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["count()"],keys:_col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Select Operator [SEL_66] (rows=766650239 width=88) + Select Operator [SEL_66] (rows=1 width=88) Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - Filter Operator [FIL_65] (rows=766650239 width=88) + Filter Operator [FIL_65] (rows=1 width=88) predicate:(_col16 is not null or _col18 is not null) Merge Join Operator [MERGEJOIN_112] (rows=766650239 width=88) Conds:RS_62._col0=RS_63._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col16","_col18"] diff --git a/ql/src/test/results/clientpositive/perf/query13.q.out b/ql/src/test/results/clientpositive/perf/query13.q.out index ac9d3cbe9c..941b0e47de 100644 --- a/ql/src/test/results/clientpositive/perf/query13.q.out +++ b/ql/src/test/results/clientpositive/perf/query13.q.out @@ -120,27 +120,27 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_37] Group By Operator [GBY_36] (rows=1 width=764) Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(_col6)","avg(_col8)","avg(_col9)","sum(_col9)"] - Select Operator [SEL_35] (rows=715776 width=88) + Select Operator [SEL_35] (rows=2 width=1116) Output:["_col6","_col8","_col9"] - Filter Operator [FIL_34] (rows=715776 width=88) + Filter Operator [FIL_34] (rows=2 width=1116) predicate:(((_col19 = 'M') and (_col20 = '4 yr Degree') and _col7 BETWEEN 100 AND 150 and (_col14 = 3)) or ((_col19 = 'D') and (_col20 = 'Primary') and _col7 BETWEEN 50 AND 100 and (_col14 = 1)) or ((_col19 = 'U') and (_col20 = 'Advanced Degree') and _col7 BETWEEN 150 AND 200 and (_col14 = 1))) - Merge Join Operator [MERGEJOIN_71] (rows=17178642 width=88) + Merge Join Operator [MERGEJOIN_71] (rows=3 width=1116) Conds:RS_31._col2=RS_32._col0(Inner),Output:["_col6","_col7","_col8","_col9","_col14","_col19","_col20"] <-Map 12 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col0 - Select Operator [SEL_17] (rows=1861800 width=385) + Select Operator [SEL_17] (rows=1 width=385) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_66] (rows=1861800 width=385) + Filter Operator [FIL_66] (rows=1 width=385) predicate:(((cd_marital_status = 'M') or (cd_marital_status = 'D') or (cd_marital_status = 'U')) and ((cd_education_status = '4 yr Degree') or (cd_education_status = 'Primary') or (cd_education_status = 'Advanced Degree')) and cd_demo_sk is not null) TableScan [TS_15] (rows=1861800 width=385) default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col2 - Filter Operator [FIL_30] (rows=15616947 width=88) + Filter Operator [FIL_30] (rows=3 width=1014) predicate:(((_col16) IN ('KY', 'GA', 'NM') and _col10 BETWEEN 100 AND 200) or ((_col16) IN ('MT', 'OR', 'IN') and _col10 BETWEEN 150 AND 300) or ((_col16) IN ('WI', 'MO', 'WV') and _col10 BETWEEN 50 AND 250)) - Merge Join Operator [MERGEJOIN_70] (rows=93701693 width=88) + Merge Join Operator [MERGEJOIN_70] (rows=11000000 width=1014) Conds:RS_27._col4=RS_28._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10","_col14","_col16"] <-Map 11 [SIMPLE_EDGE] SHUFFLE [RS_28] @@ -154,21 +154,21 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_69] (rows=85183356 width=88) + Merge Join Operator [MERGEJOIN_69] (rows=44193 width=1119) Conds:RS_24._col3=RS_25._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8","_col9","_col10","_col14"] <-Map 10 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col0 - Select Operator [SEL_11] (rows=7200 width=107) + Select Operator [SEL_11] (rows=1 width=107) Output:["_col0","_col1"] - Filter Operator [FIL_64] (rows=7200 width=107) + Filter Operator [FIL_64] (rows=1 width=107) predicate:(((hd_dep_count = 3) or (hd_dep_count = 1)) and hd_demo_sk is not null) TableScan [TS_9] (rows=7200 width=107) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_68] (rows=77439413 width=88) + Merge Join Operator [MERGEJOIN_68] (rows=40176 width=1119) Conds:RS_21._col1=RS_22._col0(Inner),Output:["_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10"] <-Map 9 [SIMPLE_EDGE] SHUFFLE [RS_22] @@ -182,7 +182,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_67] (rows=70399465 width=88) + Merge Join Operator [MERGEJOIN_67] (rows=1874 width=1911) Conds:RS_18._col0=RS_19._col4(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_18] @@ -196,9 +196,9 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] SHUFFLE [RS_19] PartitionCols:_col4 - Select Operator [SEL_5] (rows=63999513 width=88) + Select Operator [SEL_5] (rows=1 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Filter Operator [FIL_62] (rows=63999513 width=88) + Filter Operator [FIL_62] (rows=1 width=88) predicate:((ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_net_profit BETWEEN 100 AND 200 or ss_net_profit BETWEEN 150 AND 300 or ss_net_profit BETWEEN 50 AND 250) and ss_store_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_addr_sk is not null and ss_sold_date_sk is not null) TableScan [TS_3] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_ext_sales_price","ss_ext_wholesale_cost","ss_net_profit"] diff --git a/ql/src/test/results/clientpositive/perf/query14.q.out b/ql/src/test/results/clientpositive/perf/query14.q.out index 2d3bf35e2b..bebe0571a7 100644 --- a/ql/src/test/results/clientpositive/perf/query14.q.out +++ b/ql/src/test/results/clientpositive/perf/query14.q.out @@ -1,6 +1,6 @@ -Warning: Shuffle Join MERGEJOIN[891][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 12' is a cross product Warning: Shuffle Join MERGEJOIN[890][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 5' is a cross product Warning: Shuffle Join MERGEJOIN[892][tables = [$hdt$_2, $hdt$_3, $hdt$_1]] in Stage 'Reducer 16' is a cross product +Warning: Shuffle Join MERGEJOIN[891][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 12' is a cross product PREHOOK: query: explain with cross_items as (select i_item_sk ss_item_sk diff --git a/ql/src/test/results/clientpositive/perf/query15.q.out b/ql/src/test/results/clientpositive/perf/query15.q.out index a2d95f65a9..6c53f443cc 100644 --- a/ql/src/test/results/clientpositive/perf/query15.q.out +++ b/ql/src/test/results/clientpositive/perf/query15.q.out @@ -51,22 +51,22 @@ Stage-0 Stage-1 Reducer 5 File Output Operator [FS_31] - Limit [LIM_30] (rows=100 width=135) + Limit [LIM_30] (rows=1 width=135) Number of rows:100 - Select Operator [SEL_29] (rows=174233858 width=135) + Select Operator [SEL_29] (rows=1 width=135) Output:["_col0","_col1"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_28] - Group By Operator [GBY_26] (rows=174233858 width=135) + Group By Operator [GBY_26] (rows=1 width=135) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col0 - Group By Operator [GBY_24] (rows=348467716 width=135) + Group By Operator [GBY_24] (rows=2 width=135) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col4 - Select Operator [SEL_23] (rows=348467716 width=135) + Select Operator [SEL_23] (rows=2 width=135) Output:["_col4","_col7"] - Filter Operator [FIL_22] (rows=348467716 width=135) + Filter Operator [FIL_22] (rows=2 width=135) predicate:((substr(_col4, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') or (_col3) IN ('CA', 'WA', 'GA') or (_col7 > 500)) Merge Join Operator [MERGEJOIN_46] (rows=348467716 width=135) Conds:RS_19._col0=RS_20._col1(Inner),Output:["_col3","_col4","_col7"] diff --git a/ql/src/test/results/clientpositive/perf/query23.q.out b/ql/src/test/results/clientpositive/perf/query23.q.out index dde707d0ea..5925869cbf 100644 --- a/ql/src/test/results/clientpositive/perf/query23.q.out +++ b/ql/src/test/results/clientpositive/perf/query23.q.out @@ -1,5 +1,5 @@ -Warning: Shuffle Join MERGEJOIN[367][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 25' is a cross product Warning: Shuffle Join MERGEJOIN[369][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product +Warning: Shuffle Join MERGEJOIN[367][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 25' is a cross product PREHOOK: query: explain with frequent_ss_items as (select substr(i_item_desc,1,30) itemdesc,i_item_sk item_sk,d_date solddate,count(*) cnt diff --git a/ql/src/test/results/clientpositive/perf/query26.q.out b/ql/src/test/results/clientpositive/perf/query26.q.out index 125dc77d74..140864c074 100644 --- a/ql/src/test/results/clientpositive/perf/query26.q.out +++ b/ql/src/test/results/clientpositive/perf/query26.q.out @@ -86,9 +86,9 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col0 - Select Operator [SEL_11] (rows=2300 width=1179) + Select Operator [SEL_11] (rows=1 width=1179) Output:["_col0"] - Filter Operator [FIL_53] (rows=2300 width=1179) + Filter Operator [FIL_53] (rows=1 width=1179) predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) TableScan [TS_9] (rows=2300 width=1179) default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_email","p_channel_event"] diff --git a/ql/src/test/results/clientpositive/perf/query28.q.out b/ql/src/test/results/clientpositive/perf/query28.q.out index 48e3dc5310..73fe9c0bf4 100644 --- a/ql/src/test/results/clientpositive/perf/query28.q.out +++ b/ql/src/test/results/clientpositive/perf/query28.q.out @@ -140,16 +140,16 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_80] Group By Operator [GBY_79] (rows=1 width=584) Output:["_col0","_col1","_col2"],aggregations:["avg(_col1)","count(_col2)","count(_col0)"] - Group By Operator [GBY_78] (rows=21333171 width=88) + Group By Operator [GBY_78] (rows=2 width=88) Output:["_col0","_col1","_col2"],aggregations:["avg(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_77] PartitionCols:_col0 - Group By Operator [GBY_76] (rows=21333171 width=88) + Group By Operator [GBY_76] (rows=2 width=88) Output:["_col0","_col1","_col2"],aggregations:["avg(ss_list_price)","count(ss_list_price)"],keys:ss_list_price - Select Operator [SEL_23] (rows=21333171 width=88) + Select Operator [SEL_23] (rows=2 width=88) Output:["ss_list_price"] - Filter Operator [FIL_55] (rows=21333171 width=88) + Filter Operator [FIL_55] (rows=2 width=88) predicate:(ss_quantity BETWEEN 16 AND 20 and (ss_list_price BETWEEN 142 AND 152 or ss_coupon_amt BETWEEN 3054 AND 4054 or ss_wholesale_cost BETWEEN 80 AND 100)) TableScan [TS_0] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] @@ -161,16 +161,16 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_86] Group By Operator [GBY_85] (rows=1 width=584) Output:["_col0","_col1","_col2"],aggregations:["avg(_col1)","count(_col2)","count(_col0)"] - Group By Operator [GBY_84] (rows=21333171 width=88) + Group By Operator [GBY_84] (rows=2 width=88) Output:["_col0","_col1","_col2"],aggregations:["avg(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_83] PartitionCols:_col0 - Group By Operator [GBY_82] (rows=21333171 width=88) + Group By Operator [GBY_82] (rows=2 width=88) Output:["_col0","_col1","_col2"],aggregations:["avg(ss_list_price)","count(ss_list_price)"],keys:ss_list_price - Select Operator [SEL_30] (rows=21333171 width=88) + Select Operator [SEL_30] (rows=2 width=88) Output:["ss_list_price"] - Filter Operator [FIL_56] (rows=21333171 width=88) + Filter Operator [FIL_56] (rows=2 width=88) predicate:(ss_quantity BETWEEN 11 AND 15 and (ss_list_price BETWEEN 66 AND 76 or ss_coupon_amt BETWEEN 920 AND 1920 or ss_wholesale_cost BETWEEN 4 AND 24)) Please refer to the previous TableScan [TS_0] <-Reducer 14 [CUSTOM_SIMPLE_EDGE] @@ -181,16 +181,16 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_92] Group By Operator [GBY_91] (rows=1 width=584) Output:["_col0","_col1","_col2"],aggregations:["avg(_col1)","count(_col2)","count(_col0)"] - Group By Operator [GBY_90] (rows=21333171 width=88) + Group By Operator [GBY_90] (rows=2 width=88) Output:["_col0","_col1","_col2"],aggregations:["avg(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_89] PartitionCols:_col0 - Group By Operator [GBY_88] (rows=21333171 width=88) + Group By Operator [GBY_88] (rows=2 width=88) Output:["_col0","_col1","_col2"],aggregations:["avg(ss_list_price)","count(ss_list_price)"],keys:ss_list_price - Select Operator [SEL_37] (rows=21333171 width=88) + Select Operator [SEL_37] (rows=2 width=88) Output:["ss_list_price"] - Filter Operator [FIL_57] (rows=21333171 width=88) + Filter Operator [FIL_57] (rows=2 width=88) predicate:(ss_quantity BETWEEN 6 AND 10 and (ss_list_price BETWEEN 91 AND 101 or ss_coupon_amt BETWEEN 1430 AND 2430 or ss_wholesale_cost BETWEEN 32 AND 52)) Please refer to the previous TableScan [TS_0] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] @@ -201,16 +201,16 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_62] Group By Operator [GBY_61] (rows=1 width=584) Output:["_col0","_col1","_col2"],aggregations:["avg(_col1)","count(_col2)","count(_col0)"] - Group By Operator [GBY_60] (rows=21333171 width=88) + Group By Operator [GBY_60] (rows=2 width=88) Output:["_col0","_col1","_col2"],aggregations:["avg(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_59] PartitionCols:_col0 - Group By Operator [GBY_58] (rows=21333171 width=88) + Group By Operator [GBY_58] (rows=2 width=88) Output:["_col0","_col1","_col2"],aggregations:["avg(ss_list_price)","count(ss_list_price)"],keys:ss_list_price - Select Operator [SEL_2] (rows=21333171 width=88) + Select Operator [SEL_2] (rows=2 width=88) Output:["ss_list_price"] - Filter Operator [FIL_52] (rows=21333171 width=88) + Filter Operator [FIL_52] (rows=2 width=88) predicate:(ss_quantity BETWEEN 0 AND 5 and (ss_list_price BETWEEN 11 AND 21 or ss_coupon_amt BETWEEN 460 AND 1460 or ss_wholesale_cost BETWEEN 14 AND 34)) Please refer to the previous TableScan [TS_0] <-Reducer 6 [CUSTOM_SIMPLE_EDGE] @@ -221,16 +221,16 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_68] Group By Operator [GBY_67] (rows=1 width=584) Output:["_col0","_col1","_col2"],aggregations:["avg(_col1)","count(_col2)","count(_col0)"] - Group By Operator [GBY_66] (rows=21333171 width=88) + Group By Operator [GBY_66] (rows=2 width=88) Output:["_col0","_col1","_col2"],aggregations:["avg(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_65] PartitionCols:_col0 - Group By Operator [GBY_64] (rows=21333171 width=88) + Group By Operator [GBY_64] (rows=2 width=88) Output:["_col0","_col1","_col2"],aggregations:["avg(ss_list_price)","count(ss_list_price)"],keys:ss_list_price - Select Operator [SEL_9] (rows=21333171 width=88) + Select Operator [SEL_9] (rows=2 width=88) Output:["ss_list_price"] - Filter Operator [FIL_53] (rows=21333171 width=88) + Filter Operator [FIL_53] (rows=2 width=88) predicate:(ss_quantity BETWEEN 26 AND 30 and (ss_list_price BETWEEN 28 AND 38 or ss_coupon_amt BETWEEN 2513 AND 3513 or ss_wholesale_cost BETWEEN 42 AND 62)) Please refer to the previous TableScan [TS_0] <-Reducer 8 [CUSTOM_SIMPLE_EDGE] @@ -241,16 +241,16 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_74] Group By Operator [GBY_73] (rows=1 width=584) Output:["_col0","_col1","_col2"],aggregations:["avg(_col1)","count(_col2)","count(_col0)"] - Group By Operator [GBY_72] (rows=21333171 width=88) + Group By Operator [GBY_72] (rows=2 width=88) Output:["_col0","_col1","_col2"],aggregations:["avg(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_71] PartitionCols:_col0 - Group By Operator [GBY_70] (rows=21333171 width=88) + Group By Operator [GBY_70] (rows=2 width=88) Output:["_col0","_col1","_col2"],aggregations:["avg(ss_list_price)","count(ss_list_price)"],keys:ss_list_price - Select Operator [SEL_16] (rows=21333171 width=88) + Select Operator [SEL_16] (rows=2 width=88) Output:["ss_list_price"] - Filter Operator [FIL_54] (rows=21333171 width=88) + Filter Operator [FIL_54] (rows=2 width=88) predicate:(ss_quantity BETWEEN 21 AND 25 and (ss_list_price BETWEEN 135 AND 145 or ss_coupon_amt BETWEEN 14180 AND 15180 or ss_wholesale_cost BETWEEN 38 AND 58)) Please refer to the previous TableScan [TS_0] diff --git a/ql/src/test/results/clientpositive/perf/query34.q.out b/ql/src/test/results/clientpositive/perf/query34.q.out index a535ce5cd9..7ce1169eca 100644 --- a/ql/src/test/results/clientpositive/perf/query34.q.out +++ b/ql/src/test/results/clientpositive/perf/query34.q.out @@ -124,9 +124,9 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] SHUFFLE [RS_19] PartitionCols:_col0 - Select Operator [SEL_11] (rows=1200 width=107) + Select Operator [SEL_11] (rows=1 width=107) Output:["_col0"] - Filter Operator [FIL_55] (rows=1200 width=107) + Filter Operator [FIL_55] (rows=1 width=107) predicate:(((hd_buy_potential = '>10000') or (hd_buy_potential = 'unknown')) and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.2)) ELSE (null) END and hd_demo_sk is not null) TableScan [TS_9] (rows=7200 width=107) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"] @@ -147,9 +147,9 @@ Stage-0 <-Map 9 [SIMPLE_EDGE] SHUFFLE [RS_16] PartitionCols:_col0 - Select Operator [SEL_8] (rows=8116 width=1119) + Select Operator [SEL_8] (rows=2 width=1119) Output:["_col0"] - Filter Operator [FIL_54] (rows=8116 width=1119) + Filter Operator [FIL_54] (rows=2 width=1119) predicate:((d_year) IN (2000, 2001, 2002) and (d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_dom"] diff --git a/ql/src/test/results/clientpositive/perf/query35.q.out b/ql/src/test/results/clientpositive/perf/query35.q.out index 5d45b17fe3..f423e41902 100644 --- a/ql/src/test/results/clientpositive/perf/query35.q.out +++ b/ql/src/test/results/clientpositive/perf/query35.q.out @@ -132,24 +132,24 @@ Stage-0 Stage-1 Reducer 7 File Output Operator [FS_75] - Limit [LIM_73] (rows=100 width=88) + Limit [LIM_73] (rows=1 width=88) Number of rows:100 - Select Operator [SEL_72] (rows=383325119 width=88) + Select Operator [SEL_72] (rows=1 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_71] - Select Operator [SEL_70] (rows=383325119 width=88) + Select Operator [SEL_70] (rows=1 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17"] - Group By Operator [GBY_69] (rows=383325119 width=88) + Group By Operator [GBY_69] (rows=1 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count(VALUE._col0)","avg(VALUE._col1)","max(VALUE._col2)","sum(VALUE._col3)","avg(VALUE._col4)","max(VALUE._col5)","sum(VALUE._col6)","avg(VALUE._col7)","max(VALUE._col8)","sum(VALUE._col9)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_68] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_67] (rows=766650239 width=88) + Group By Operator [GBY_67] (rows=1 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count()","avg(_col8)","max(_col8)","sum(_col8)","avg(_col9)","max(_col9)","sum(_col9)","avg(_col10)","max(_col10)","sum(_col10)"],keys:_col4, _col6, _col7, _col8, _col9, _col10 - Select Operator [SEL_66] (rows=766650239 width=88) + Select Operator [SEL_66] (rows=1 width=88) Output:["_col4","_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_65] (rows=766650239 width=88) + Filter Operator [FIL_65] (rows=1 width=88) predicate:(_col13 is not null or _col15 is not null) Merge Join Operator [MERGEJOIN_113] (rows=766650239 width=88) Conds:RS_62._col0=RS_63._col0(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col13","_col15"] diff --git a/ql/src/test/results/clientpositive/perf/query45.q.out b/ql/src/test/results/clientpositive/perf/query45.q.out index 112b47bb04..7c607cea42 100644 --- a/ql/src/test/results/clientpositive/perf/query45.q.out +++ b/ql/src/test/results/clientpositive/perf/query45.q.out @@ -57,22 +57,22 @@ Stage-0 Stage-1 Reducer 6 File Output Operator [FS_59] - Limit [LIM_58] (rows=100 width=152) + Limit [LIM_58] (rows=1 width=152) Number of rows:100 - Select Operator [SEL_57] (rows=95833781 width=152) + Select Operator [SEL_57] (rows=1 width=152) Output:["_col0","_col1","_col2"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_56] - Group By Operator [GBY_54] (rows=95833781 width=152) + Group By Operator [GBY_54] (rows=1 width=152) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_53] PartitionCols:_col0, _col1 - Group By Operator [GBY_52] (rows=191667562 width=152) + Group By Operator [GBY_52] (rows=1 width=152) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col8, _col7 - Select Operator [SEL_51] (rows=191667562 width=152) + Select Operator [SEL_51] (rows=1 width=152) Output:["_col3","_col7","_col8"] - Filter Operator [FIL_50] (rows=191667562 width=152) + Filter Operator [FIL_50] (rows=1 width=152) predicate:((substr(_col8, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') or CASE WHEN ((_col14 = 0)) THEN (false) WHEN (_col17 is not null) THEN (true) WHEN (_col13 is null) THEN (null) WHEN ((_col15 < _col14)) THEN (null) ELSE (false) END) Select Operator [SEL_49] (rows=191667562 width=152) Output:["_col3","_col7","_col8","_col13","_col14","_col15","_col17"] diff --git a/ql/src/test/results/clientpositive/perf/query46.q.out b/ql/src/test/results/clientpositive/perf/query46.q.out index 380944a05f..8eb19e8705 100644 --- a/ql/src/test/results/clientpositive/perf/query46.q.out +++ b/ql/src/test/results/clientpositive/perf/query46.q.out @@ -145,9 +145,9 @@ Stage-0 <-Map 14 [SIMPLE_EDGE] SHUFFLE [RS_28] PartitionCols:_col0 - Select Operator [SEL_17] (rows=7200 width=107) + Select Operator [SEL_17] (rows=1 width=107) Output:["_col0"] - Filter Operator [FIL_79] (rows=7200 width=107) + Filter Operator [FIL_79] (rows=1 width=107) predicate:(((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_sk is not null) TableScan [TS_15] (rows=7200 width=107) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] diff --git a/ql/src/test/results/clientpositive/perf/query47.q.out b/ql/src/test/results/clientpositive/perf/query47.q.out index 1d4f36be1d..19c93fae19 100644 --- a/ql/src/test/results/clientpositive/perf/query47.q.out +++ b/ql/src/test/results/clientpositive/perf/query47.q.out @@ -201,9 +201,9 @@ Stage-0 <-Map 20 [SIMPLE_EDGE] SHUFFLE [RS_13] PartitionCols:_col0 - Select Operator [SEL_75] (rows=73048 width=1119) + Select Operator [SEL_75] (rows=2 width=1119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_177] (rows=73048 width=1119) + Filter Operator [FIL_177] (rows=2 width=1119) predicate:(((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) TableScan [TS_73] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] diff --git a/ql/src/test/results/clientpositive/perf/query48.q.out b/ql/src/test/results/clientpositive/perf/query48.q.out index ffe80b4a95..26c30234fd 100644 --- a/ql/src/test/results/clientpositive/perf/query48.q.out +++ b/ql/src/test/results/clientpositive/perf/query48.q.out @@ -149,11 +149,11 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_30] Group By Operator [GBY_29] (rows=1 width=8) Output:["_col0"],aggregations:["sum(_col5)"] - Select Operator [SEL_28] (rows=15616947 width=88) + Select Operator [SEL_28] (rows=3 width=1014) Output:["_col5"] - Filter Operator [FIL_27] (rows=15616947 width=88) + Filter Operator [FIL_27] (rows=3 width=1014) predicate:(((_col14) IN ('KY', 'GA', 'NM') and _col7 BETWEEN 0 AND 2000) or ((_col14) IN ('MT', 'OR', 'IN') and _col7 BETWEEN 150 AND 3000) or ((_col14) IN ('WI', 'MO', 'WV') and _col7 BETWEEN 50 AND 25000)) - Merge Join Operator [MERGEJOIN_56] (rows=93701693 width=88) + Merge Join Operator [MERGEJOIN_56] (rows=11000000 width=1014) Conds:RS_24._col3=RS_25._col0(Inner),Output:["_col5","_col7","_col14"] <-Map 10 [SIMPLE_EDGE] SHUFFLE [RS_25] @@ -167,7 +167,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_55] (rows=85183356 width=88) + Merge Join Operator [MERGEJOIN_55] (rows=511995 width=385) Conds:RS_21._col2=RS_22._col0(Inner),Output:["_col3","_col5","_col7"] <-Map 9 [SIMPLE_EDGE] SHUFFLE [RS_22] @@ -181,7 +181,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_54] (rows=77439413 width=88) + Merge Join Operator [MERGEJOIN_54] (rows=40176 width=1119) Conds:RS_18._col1=RS_19._col0(Inner),Output:["_col2","_col3","_col5","_col7"] <-Map 8 [SIMPLE_EDGE] SHUFFLE [RS_19] @@ -195,7 +195,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_53] (rows=70399465 width=88) + Merge Join Operator [MERGEJOIN_53] (rows=1874 width=1911) Conds:RS_15._col0=RS_16._col3(Inner),Output:["_col1","_col2","_col3","_col5","_col7"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_15] @@ -209,9 +209,9 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] SHUFFLE [RS_16] PartitionCols:_col3 - Select Operator [SEL_5] (rows=63999513 width=88) + Select Operator [SEL_5] (rows=1 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col6"] - Filter Operator [FIL_49] (rows=63999513 width=88) + Filter Operator [FIL_49] (rows=1 width=88) predicate:((ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_net_profit BETWEEN 0 AND 2000 or ss_net_profit BETWEEN 150 AND 3000 or ss_net_profit BETWEEN 50 AND 25000) and ss_store_sk is not null and ss_cdemo_sk is not null and ss_addr_sk is not null and ss_sold_date_sk is not null) TableScan [TS_3] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_net_profit"] diff --git a/ql/src/test/results/clientpositive/perf/query49.q.out b/ql/src/test/results/clientpositive/perf/query49.q.out index c62549adf6..4ff0e5c2dd 100644 --- a/ql/src/test/results/clientpositive/perf/query49.q.out +++ b/ql/src/test/results/clientpositive/perf/query49.q.out @@ -278,25 +278,25 @@ Stage-0 Stage-1 Reducer 11 File Output Operator [FS_113] - Limit [LIM_112] (rows=100 width=101) + Limit [LIM_112] (rows=1 width=111) Number of rows:100 - Select Operator [SEL_111] (rows=5915494 width=101) + Select Operator [SEL_111] (rows=1 width=111) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_110] - Select Operator [SEL_109] (rows=5915494 width=101) + Select Operator [SEL_109] (rows=1 width=111) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_108] (rows=5915494 width=101) + Group By Operator [GBY_108] (rows=1 width=111) Output:["_col0","_col1","_col2","_col3","_col4"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Union 9 [SIMPLE_EDGE] <-Reducer 22 [CONTAINS] Reduce Output Operator [RS_107] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_106] (rows=11830988 width=101) + Group By Operator [GBY_106] (rows=2 width=111) Output:["_col0","_col1","_col2","_col3","_col4"],keys:_col0, _col3, _col4, _col1, _col2 - Select Operator [SEL_99] (rows=8604378 width=88) + Select Operator [SEL_99] (rows=1 width=88) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_137] (rows=8604378 width=88) + Filter Operator [FIL_137] (rows=1 width=88) predicate:((_col0 <= 10) or (rank_window_1 <= 10)) PTF Operator [PTF_98] (rows=12906568 width=88) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col4 AS decimal(15,4)) / CAST( _col5 AS decimal(15,4))) ASC NULLS FIRST","partition by:":"0"}] @@ -360,21 +360,21 @@ Stage-0 <-Reducer 8 [CONTAINS] Reduce Output Operator [RS_107] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_106] (rows=11830988 width=101) + Group By Operator [GBY_106] (rows=2 width=111) Output:["_col0","_col1","_col2","_col3","_col4"],keys:_col0, _col3, _col4, _col1, _col2 - Select Operator [SEL_70] (rows=3226610 width=135) + Select Operator [SEL_70] (rows=1 width=135) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_69] (rows=3226610 width=135) + Group By Operator [GBY_69] (rows=1 width=135) Output:["_col0","_col1","_col2","_col3","_col4"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Union 7 [SIMPLE_EDGE] <-Reducer 17 [CONTAINS] Reduce Output Operator [RS_68] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_67] (rows=6453220 width=135) + Group By Operator [GBY_67] (rows=2 width=135) Output:["_col0","_col1","_col2","_col3","_col4"],keys:_col0, _col3, _col4, _col1, _col2 - Select Operator [SEL_60] (rows=4302070 width=135) + Select Operator [SEL_60] (rows=1 width=135) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_133] (rows=4302070 width=135) + Filter Operator [FIL_133] (rows=1 width=135) predicate:((_col0 <= 10) or (rank_window_1 <= 10)) PTF Operator [PTF_59] (rows=6453105 width=135) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col4 AS decimal(15,4)) / CAST( _col5 AS decimal(15,4))) ASC NULLS FIRST","partition by:":"0"}] @@ -433,11 +433,11 @@ Stage-0 <-Reducer 6 [CONTAINS] Reduce Output Operator [RS_68] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_67] (rows=6453220 width=135) + Group By Operator [GBY_67] (rows=2 width=135) Output:["_col0","_col1","_col2","_col3","_col4"],keys:_col0, _col3, _col4, _col1, _col2 - Select Operator [SEL_28] (rows=2151150 width=135) + Select Operator [SEL_28] (rows=1 width=135) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_129] (rows=2151150 width=135) + Filter Operator [FIL_129] (rows=1 width=135) predicate:((_col0 <= 10) or (rank_window_1 <= 10)) PTF Operator [PTF_27] (rows=3226726 width=135) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col4 AS decimal(15,4)) / CAST( _col5 AS decimal(15,4))) ASC NULLS FIRST","partition by:":"0"}] diff --git a/ql/src/test/results/clientpositive/perf/query53.q.out b/ql/src/test/results/clientpositive/perf/query53.q.out index bc9e6c48a3..256cc7cf7d 100644 --- a/ql/src/test/results/clientpositive/perf/query53.q.out +++ b/ql/src/test/results/clientpositive/perf/query53.q.out @@ -132,9 +132,9 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] SHUFFLE [RS_13] PartitionCols:_col0 - Select Operator [SEL_5] (rows=115500 width=1436) + Select Operator [SEL_5] (rows=2 width=1436) Output:["_col0","_col4"] - Filter Operator [FIL_48] (rows=115500 width=1436) + Filter Operator [FIL_48] (rows=2 width=1436) predicate:(((i_class) IN ('personal', 'portable', 'reference', 'self-help') or (i_class) IN ('accessories', 'classical', 'fragrances', 'pants')) and ((i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9') or (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1')) and ((i_category) IN ('Books', 'Children', 'Electronics') or (i_category) IN ('Women', 'Music', 'Men')) and (((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'reference', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null) TableScan [TS_3] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category","i_manufact_id"] diff --git a/ql/src/test/results/clientpositive/perf/query57.q.out b/ql/src/test/results/clientpositive/perf/query57.q.out index e9630de9ac..eb449fa243 100644 --- a/ql/src/test/results/clientpositive/perf/query57.q.out +++ b/ql/src/test/results/clientpositive/perf/query57.q.out @@ -195,9 +195,9 @@ Stage-0 <-Map 20 [SIMPLE_EDGE] SHUFFLE [RS_13] PartitionCols:_col0 - Select Operator [SEL_75] (rows=73048 width=1119) + Select Operator [SEL_75] (rows=2 width=1119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_177] (rows=73048 width=1119) + Filter Operator [FIL_177] (rows=2 width=1119) predicate:(((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) TableScan [TS_73] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] diff --git a/ql/src/test/results/clientpositive/perf/query61.q.out b/ql/src/test/results/clientpositive/perf/query61.q.out index 93d4d427d0..e109e3ff6d 100644 --- a/ql/src/test/results/clientpositive/perf/query61.q.out +++ b/ql/src/test/results/clientpositive/perf/query61.q.out @@ -138,9 +138,9 @@ Stage-0 <-Map 22 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col0 - Select Operator [SEL_20] (rows=2300 width=1179) + Select Operator [SEL_20] (rows=1 width=1179) Output:["_col0"] - Filter Operator [FIL_138] (rows=2300 width=1179) + Filter Operator [FIL_138] (rows=1 width=1179) predicate:(((p_channel_dmail = 'Y') or (p_channel_email = 'Y') or (p_channel_tv = 'Y')) and p_promo_sk is not null) TableScan [TS_18] (rows=2300 width=1179) default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_dmail","p_channel_email","p_channel_tv"] diff --git a/ql/src/test/results/clientpositive/perf/query63.q.out b/ql/src/test/results/clientpositive/perf/query63.q.out index 1f0f184e93..d81364938d 100644 --- a/ql/src/test/results/clientpositive/perf/query63.q.out +++ b/ql/src/test/results/clientpositive/perf/query63.q.out @@ -134,9 +134,9 @@ Stage-0 <-Map 7 [SIMPLE_EDGE] SHUFFLE [RS_13] PartitionCols:_col0 - Select Operator [SEL_5] (rows=115500 width=1436) + Select Operator [SEL_5] (rows=2 width=1436) Output:["_col0","_col4"] - Filter Operator [FIL_48] (rows=115500 width=1436) + Filter Operator [FIL_48] (rows=2 width=1436) predicate:(((i_class) IN ('personal', 'portable', 'refernece', 'self-help') or (i_class) IN ('accessories', 'classical', 'fragrances', 'pants')) and ((i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9') or (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1')) and ((i_category) IN ('Books', 'Children', 'Electronics') or (i_category) IN ('Women', 'Music', 'Men')) and (((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'refernece', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null) TableScan [TS_3] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category","i_manager_id"] diff --git a/ql/src/test/results/clientpositive/perf/query68.q.out b/ql/src/test/results/clientpositive/perf/query68.q.out index 5f763d50c0..d1b11bbe3a 100644 --- a/ql/src/test/results/clientpositive/perf/query68.q.out +++ b/ql/src/test/results/clientpositive/perf/query68.q.out @@ -159,9 +159,9 @@ Stage-0 <-Map 14 [SIMPLE_EDGE] SHUFFLE [RS_28] PartitionCols:_col0 - Select Operator [SEL_17] (rows=7200 width=107) + Select Operator [SEL_17] (rows=1 width=107) Output:["_col0"] - Filter Operator [FIL_79] (rows=7200 width=107) + Filter Operator [FIL_79] (rows=1 width=107) predicate:(((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_sk is not null) TableScan [TS_15] (rows=7200 width=107) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] diff --git a/ql/src/test/results/clientpositive/perf/query7.q.out b/ql/src/test/results/clientpositive/perf/query7.q.out index d3045d126e..d1ebb39017 100644 --- a/ql/src/test/results/clientpositive/perf/query7.q.out +++ b/ql/src/test/results/clientpositive/perf/query7.q.out @@ -86,9 +86,9 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col0 - Select Operator [SEL_11] (rows=2300 width=1179) + Select Operator [SEL_11] (rows=1 width=1179) Output:["_col0"] - Filter Operator [FIL_53] (rows=2300 width=1179) + Filter Operator [FIL_53] (rows=1 width=1179) predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) TableScan [TS_9] (rows=2300 width=1179) default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_email","p_channel_event"] diff --git a/ql/src/test/results/clientpositive/perf/query71.q.out b/ql/src/test/results/clientpositive/perf/query71.q.out index 1dc8ba56d8..8a760e38c2 100644 --- a/ql/src/test/results/clientpositive/perf/query71.q.out +++ b/ql/src/test/results/clientpositive/perf/query71.q.out @@ -109,9 +109,9 @@ Stage-0 <-Map 16 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0 - Select Operator [SEL_37] (rows=86400 width=471) + Select Operator [SEL_37] (rows=1 width=471) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_81] (rows=86400 width=471) + Filter Operator [FIL_81] (rows=1 width=471) predicate:(((t_meal_time = 'breakfast') or (t_meal_time = 'dinner')) and t_time_sk is not null) TableScan [TS_35] (rows=86400 width=471) default@time_dim,time_dim,Tbl:COMPLETE,Col:NONE,Output:["t_time_sk","t_hour","t_minute","t_meal_time"] diff --git a/ql/src/test/results/clientpositive/perf/query73.q.out b/ql/src/test/results/clientpositive/perf/query73.q.out index db8dfc04a6..8f76822d5a 100644 --- a/ql/src/test/results/clientpositive/perf/query73.q.out +++ b/ql/src/test/results/clientpositive/perf/query73.q.out @@ -118,9 +118,9 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] SHUFFLE [RS_19] PartitionCols:_col0 - Select Operator [SEL_11] (rows=1200 width=107) + Select Operator [SEL_11] (rows=1 width=107) Output:["_col0"] - Filter Operator [FIL_55] (rows=1200 width=107) + Filter Operator [FIL_55] (rows=1 width=107) predicate:(((hd_buy_potential = '>10000') or (hd_buy_potential = 'unknown')) and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.0)) ELSE (null) END and hd_demo_sk is not null) TableScan [TS_9] (rows=7200 width=107) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"] diff --git a/ql/src/test/results/clientpositive/perf/query79.q.out b/ql/src/test/results/clientpositive/perf/query79.q.out index 18b32e0f8c..5b10e380f2 100644 --- a/ql/src/test/results/clientpositive/perf/query79.q.out +++ b/ql/src/test/results/clientpositive/perf/query79.q.out @@ -94,9 +94,9 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col0 - Select Operator [SEL_14] (rows=6000 width=107) + Select Operator [SEL_14] (rows=1 width=107) Output:["_col0"] - Filter Operator [FIL_57] (rows=6000 width=107) + Filter Operator [FIL_57] (rows=1 width=107) predicate:(((hd_dep_count = 8) or (hd_vehicle_count > 0)) and hd_demo_sk is not null) TableScan [TS_12] (rows=7200 width=107) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] diff --git a/ql/src/test/results/clientpositive/perf/query85.q.out b/ql/src/test/results/clientpositive/perf/query85.q.out index 8df7be673a..6a31126a27 100644 --- a/ql/src/test/results/clientpositive/perf/query85.q.out +++ b/ql/src/test/results/clientpositive/perf/query85.q.out @@ -183,38 +183,38 @@ Stage-0 Stage-1 Reducer 10 File Output Operator [FS_56] - Limit [LIM_54] (rows=100 width=385) + Limit [LIM_54] (rows=1 width=1230) Number of rows:100 - Select Operator [SEL_53] (rows=1023990 width=385) + Select Operator [SEL_53] (rows=1 width=1230) Output:["_col0","_col1","_col2","_col3"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_52] - Select Operator [SEL_51] (rows=1023990 width=385) + Select Operator [SEL_51] (rows=1 width=1230) Output:["_col5","_col6","_col7","_col8"] - Group By Operator [GBY_50] (rows=1023990 width=385) + Group By Operator [GBY_50] (rows=1 width=1230) Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(VALUE._col0)","avg(VALUE._col1)","avg(VALUE._col2)"],keys:KEY._col0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0 - Group By Operator [GBY_48] (rows=2047980 width=385) + Group By Operator [GBY_48] (rows=3 width=1230) Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(_col12)","avg(_col7)","avg(_col6)"],keys:_col22 - Merge Join Operator [MERGEJOIN_106] (rows=2047980 width=385) + Merge Join Operator [MERGEJOIN_106] (rows=3 width=1230) Conds:RS_44._col3, _col24, _col25=RS_45._col0, _col1, _col2(Inner),Output:["_col6","_col7","_col12","_col22"] <-Map 16 [SIMPLE_EDGE] SHUFFLE [RS_45] PartitionCols:_col0, _col1, _col2 - Select Operator [SEL_23] (rows=1861800 width=385) + Select Operator [SEL_23] (rows=1 width=385) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_99] (rows=1861800 width=385) + Filter Operator [FIL_99] (rows=1 width=385) predicate:(((cd_education_status = '4 yr Degree') or (cd_education_status = 'Primary') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'D') or (cd_marital_status = 'U')) and cd_demo_sk is not null and cd_marital_status is not null and cd_education_status is not null) TableScan [TS_21] (rows=1861800 width=385) default@customer_demographics,cd2,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col3, _col24, _col25 - Filter Operator [FIL_43] (rows=393687 width=135) + Filter Operator [FIL_43] (rows=3 width=1119) predicate:(((_col24 = 'M') and (_col25 = '4 yr Degree') and _col13 BETWEEN 100 AND 150) or ((_col24 = 'D') and (_col25 = 'Primary') and _col13 BETWEEN 50 AND 100) or ((_col24 = 'U') and (_col25 = 'Advanced Degree') and _col13 BETWEEN 150 AND 200)) - Merge Join Operator [MERGEJOIN_105] (rows=4724246 width=135) + Merge Join Operator [MERGEJOIN_105] (rows=48612 width=1119) Conds:RS_40._col1=RS_41._col0(Inner),Output:["_col3","_col6","_col7","_col12","_col13","_col22","_col24","_col25"] <-Map 16 [SIMPLE_EDGE] SHUFFLE [RS_41] @@ -223,7 +223,7 @@ Stage-0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_40] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_104] (rows=4294769 width=135) + Merge Join Operator [MERGEJOIN_104] (rows=44193 width=1119) Conds:RS_37._col4=RS_38._col0(Inner),Output:["_col1","_col3","_col6","_col7","_col12","_col13","_col22"] <-Map 15 [SIMPLE_EDGE] SHUFFLE [RS_38] @@ -237,7 +237,7 @@ Stage-0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_103] (rows=3904336 width=135) + Merge Join Operator [MERGEJOIN_103] (rows=40176 width=1119) Conds:RS_34._col8=RS_35._col0(Inner),Output:["_col1","_col3","_col4","_col6","_col7","_col12","_col13"] <-Map 14 [SIMPLE_EDGE] SHUFFLE [RS_35] @@ -251,7 +251,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col8 - Merge Join Operator [MERGEJOIN_102] (rows=3549397 width=135) + Merge Join Operator [MERGEJOIN_102] (rows=5062 width=585) Conds:RS_31._col10=RS_32._col0(Inner),Output:["_col1","_col3","_col4","_col6","_col7","_col8","_col12","_col13"] <-Map 13 [SIMPLE_EDGE] SHUFFLE [RS_32] @@ -265,9 +265,9 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col10 - Filter Operator [FIL_30] (rows=3226725 width=135) + Filter Operator [FIL_30] (rows=3 width=92) predicate:(((_col16) IN ('KY', 'GA', 'NM') and _col14 BETWEEN 100 AND 200) or ((_col16) IN ('MT', 'OR', 'IN') and _col14 BETWEEN 150 AND 300) or ((_col16) IN ('WI', 'MO', 'WV') and _col14 BETWEEN 50 AND 250)) - Merge Join Operator [MERGEJOIN_101] (rows=19360357 width=135) + Merge Join Operator [MERGEJOIN_101] (rows=17422145 width=92) Conds:RS_27._col2=RS_28._col0(Inner),Output:["_col1","_col3","_col4","_col6","_col7","_col8","_col10","_col12","_col13","_col14","_col16"] <-Map 12 [SIMPLE_EDGE] SHUFFLE [RS_28] @@ -281,7 +281,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_100] (rows=17600325 width=135) + Merge Join Operator [MERGEJOIN_100] (rows=15838314 width=92) Conds:RS_24._col0, _col5=RS_25._col1, _col3(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col10","_col12","_col13","_col14"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_24] @@ -295,9 +295,9 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col1, _col3 - Select Operator [SEL_5] (rows=16000296 width=135) + Select Operator [SEL_5] (rows=1 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_93] (rows=16000296 width=135) + Filter Operator [FIL_93] (rows=1 width=135) predicate:((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and (ws_net_profit BETWEEN 100 AND 200 or ws_net_profit BETWEEN 150 AND 300 or ws_net_profit BETWEEN 50 AND 250) and ws_item_sk is not null and ws_order_number is not null and ws_web_page_sk is not null and ws_sold_date_sk is not null) TableScan [TS_3] (rows=144002668 width=135) default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_page_sk","ws_order_number","ws_quantity","ws_sales_price","ws_net_profit"] diff --git a/ql/src/test/results/clientpositive/perf/query88.q.out b/ql/src/test/results/clientpositive/perf/query88.q.out index 6bad30cb53..59bc1670ca 100644 --- a/ql/src/test/results/clientpositive/perf/query88.q.out +++ b/ql/src/test/results/clientpositive/perf/query88.q.out @@ -257,9 +257,9 @@ Stage-0 <-Map 36 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0 - Select Operator [SEL_8] (rows=3600 width=107) + Select Operator [SEL_8] (rows=2 width=107) Output:["_col0"] - Filter Operator [FIL_293] (rows=3600 width=107) + Filter Operator [FIL_293] (rows=2 width=107) predicate:((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) TableScan [TS_6] (rows=7200 width=107) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] diff --git a/ql/src/test/results/clientpositive/perf/query89.q.out b/ql/src/test/results/clientpositive/perf/query89.q.out index 1f13f9ea60..7636e33ba1 100644 --- a/ql/src/test/results/clientpositive/perf/query89.q.out +++ b/ql/src/test/results/clientpositive/perf/query89.q.out @@ -138,9 +138,9 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] SHUFFLE [RS_13] PartitionCols:_col0 - Select Operator [SEL_5] (rows=231000 width=1436) + Select Operator [SEL_5] (rows=2 width=1436) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_49] (rows=231000 width=1436) + Filter Operator [FIL_49] (rows=2 width=1436) predicate:(((i_class) IN ('wallpaper', 'parenting', 'musical') or (i_class) IN ('womens', 'birdal', 'pants')) and ((i_category) IN ('Home', 'Books', 'Electronics') or (i_category) IN ('Shoes', 'Jewelry', 'Men')) and (((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and i_item_sk is not null) TableScan [TS_3] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category"] diff --git a/ql/src/test/results/clientpositive/perf/query91.q.out b/ql/src/test/results/clientpositive/perf/query91.q.out index ef04f4aa78..633dd7bb0f 100644 --- a/ql/src/test/results/clientpositive/perf/query91.q.out +++ b/ql/src/test/results/clientpositive/perf/query91.q.out @@ -129,9 +129,9 @@ Stage-0 <-Map 13 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col0 - Select Operator [SEL_14] (rows=930900 width=385) + Select Operator [SEL_14] (rows=1 width=385) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_74] (rows=930900 width=385) + Filter Operator [FIL_74] (rows=1 width=385) predicate:(((cd_education_status = 'Unknown') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'W')) and (((cd_marital_status = 'M') and (cd_education_status = 'Unknown')) or ((cd_marital_status = 'W') and (cd_education_status = 'Advanced Degree'))) and cd_demo_sk is not null) TableScan [TS_12] (rows=1861800 width=385) default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] diff --git a/ql/src/test/results/clientpositive/ppd2.q.out b/ql/src/test/results/clientpositive/ppd2.q.out index 43119be016..f113c4d853 100644 --- a/ql/src/test/results/clientpositive/ppd2.q.out +++ b/ql/src/test/results/clientpositive/ppd2.q.out @@ -282,14 +282,14 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((value like 'aaa%') or (value like 'vvv%')) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_gby_join.q.out b/ql/src/test/results/clientpositive/ppd_gby_join.q.out index 85191742fb..1093079117 100644 --- a/ql/src/test/results/clientpositive/ppd_gby_join.q.out +++ b/ql/src/test/results/clientpositive/ppd_gby_join.q.out @@ -32,16 +32,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < '400') and (key > '20') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -68,17 +68,17 @@ STAGE PLANS: Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -94,7 +94,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -102,10 +102,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -302,16 +302,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < '400') and (key > '20') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -338,17 +338,17 @@ STAGE PLANS: Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -364,7 +364,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -372,10 +372,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join.q.out b/ql/src/test/results/clientpositive/ppd_join.q.out index 0d0963383b..db0eb21093 100644 --- a/ql/src/test/results/clientpositive/ppd_join.q.out +++ b/ql/src/test/results/clientpositive/ppd_join.q.out @@ -29,16 +29,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < '400') and (key > '20') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -66,14 +66,14 @@ STAGE PLANS: Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -554,16 +554,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < '400') and (key > '20') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -591,14 +591,14 @@ STAGE PLANS: Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join2.q.out b/ql/src/test/results/clientpositive/ppd_join2.q.out index 279435a37c..55532f2455 100644 --- a/ql/src/test/results/clientpositive/ppd_join2.q.out +++ b/ql/src/test/results/clientpositive/ppd_join2.q.out @@ -52,16 +52,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <> '302') and (key < '400') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -74,7 +74,7 @@ STAGE PLANS: Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -90,7 +90,7 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: src @@ -1732,16 +1732,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <> '302') and (key < '400') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1754,7 +1754,7 @@ STAGE PLANS: Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1770,7 +1770,7 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: src diff --git a/ql/src/test/results/clientpositive/ppd_join3.q.out b/ql/src/test/results/clientpositive/ppd_join3.q.out index cdf887e64a..d1d77d51f8 100644 --- a/ql/src/test/results/clientpositive/ppd_join3.q.out +++ b/ql/src/test/results/clientpositive/ppd_join3.q.out @@ -50,16 +50,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <> '11') and (key < '400') and (key <> '12') and (key <> '13') and (key > '0') and ((value <> 'val_500') or (key > '1')) and (key <> '4') and (key <> '1')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -89,14 +89,14 @@ STAGE PLANS: Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col2 > '10') or (_col1 <> '10')) (type: boolean) - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1761,16 +1761,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <> '11') and (key < '400') and (key <> '12') and (key <> '13') and (key > '0') and ((value <> 'val_500') or (key > '1')) and (key <> '4') and (key <> '1')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1800,14 +1800,14 @@ STAGE PLANS: Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col2 > '10') or (_col1 <> '10')) (type: boolean) - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_transform.q.out b/ql/src/test/results/clientpositive/ppd_transform.q.out index b38088f16a..3d3a91bdaa 100644 --- a/ql/src/test/results/clientpositive/ppd_transform.q.out +++ b/ql/src/test/results/clientpositive/ppd_transform.q.out @@ -383,20 +383,20 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col0 = 'a') or (_col0 = 'b')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((_col0 = 'c') or (_col0 = 'd')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out b/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out index 3d9d5728eb..10c0b4b2d7 100644 --- a/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out +++ b/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out @@ -31,17 +31,17 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((value like 'aaa%') or (value like 'vvv%')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -224,17 +224,17 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((ds = '2008-04-08') and ((value like 'aaa%') or (value like 'vvv%'))) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/push_or.q.out b/ql/src/test/results/clientpositive/push_or.q.out index dacdc40192..f8a5860f24 100644 --- a/ql/src/test/results/clientpositive/push_or.q.out +++ b/ql/src/test/results/clientpositive/push_or.q.out @@ -49,16 +49,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((ds = '2000-04-09') or (key = 5)) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -167,13 +167,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out index de65931c2a..d468730895 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out @@ -94,11 +94,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -109,11 +109,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -127,11 +127,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -139,7 +139,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -154,11 +154,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -166,7 +166,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -231,11 +231,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -246,11 +246,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -264,11 +264,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -276,7 +276,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -291,11 +291,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -303,7 +303,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -370,11 +370,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -385,11 +385,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -403,18 +403,18 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -431,18 +431,18 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -515,11 +515,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -530,11 +530,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -548,18 +548,18 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -576,18 +576,18 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out index 074600ef02..55c14a7c44 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out @@ -397,13 +397,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 16 Data size: 317 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -507,13 +507,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col0 + _col3) >= 100)} {((_col0 + _col3) <= 102)} - Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -605,13 +605,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(((_col0 + _col3) >= 100) or ((_col0 + _col3) <= 102))} - Statistics: Num rows: 16 Data size: 317 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -711,13 +711,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(struct(_col0,_col3)) IN (const struct(100,100), const struct(101,101), const struct(102,102))} - Statistics: Num rows: 6 Data size: 119 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 6 Data size: 119 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 119 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1012,7 +1012,7 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col3 + _col0) >= 100)} - Statistics: Num rows: 8 Data size: 158 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1056,13 +1056,13 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1078,7 +1078,7 @@ STAGE PLANS: key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 8 Data size: 158 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) TableScan alias: b @@ -1101,13 +1101,13 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1314,12 +1314,12 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col3 + _col0) >= 100)} - Statistics: Num rows: 8 Data size: 158 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 8 Data size: 158 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) Local Work: Map Reduce Local Work @@ -1331,13 +1331,13 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1477,13 +1477,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 residual filter predicates: {((_col6 + _col0) <= 102)} - Statistics: Num rows: 12 Data size: 246 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE 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/bucketsortoptimize_insert_7.q.out b/ql/src/test/results/clientpositive/spark/bucketsortoptimize_insert_7.q.out index 7c23da7cc2..9a7b53dab7 100644 --- a/ql/src/test/results/clientpositive/spark/bucketsortoptimize_insert_7.q.out +++ b/ql/src/test/results/clientpositive/spark/bucketsortoptimize_insert_7.q.out @@ -84,11 +84,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -109,11 +109,11 @@ STAGE PLANS: Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -123,16 +123,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col4 input vertices: 0 Map 1 - Statistics: Num rows: 92 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), concat(_col1, _col4) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 92 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 92 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Local Work: Map Reduce Local Work @@ -141,10 +141,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 92 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 92 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -264,11 +264,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -289,11 +289,11 @@ STAGE PLANS: Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -303,16 +303,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 92 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), concat(_col1, _col3) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 92 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 92 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Local Work: Map Reduce Local Work @@ -321,10 +321,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 92 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 92 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -450,11 +450,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < 8) and ((key = 0) or (key = 5))) (type: boolean) - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -475,11 +475,11 @@ STAGE PLANS: Statistics: Num rows: 84 Data size: 736 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < 8) and ((key = 0) or (key = 5))) (type: boolean) - Statistics: Num rows: 28 Data size: 245 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 245 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -489,16 +489,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 30 Data size: 269 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), concat(_col1, _col3) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 30 Data size: 269 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 30 Data size: 269 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Local Work: Map Reduce Local Work @@ -507,10 +507,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 30 Data size: 269 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 269 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/groupby_multi_single_reducer3.q.out b/ql/src/test/results/clientpositive/spark/groupby_multi_single_reducer3.q.out index b6127475ea..f9130342e2 100644 --- a/ql/src/test/results/clientpositive/spark/groupby_multi_single_reducer3.q.out +++ b/ql/src/test/results/clientpositive/spark/groupby_multi_single_reducer3.q.out @@ -57,33 +57,33 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((value) IN ('val_400', 'val_500') and (key) IN (400, 450)) or ((value) IN ('val_100', 'val_200', 'val_300') and (key) IN (100, 150, 200))) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE value expressions: value (type: string) Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((VALUE._col0) IN ('val_100', 'val_200', 'val_300') and (KEY._col0) IN (100, 150, 200)) (type: boolean) - Statistics: Num rows: 63 Data size: 669 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -91,20 +91,20 @@ STAGE PLANS: name: default.e1 Filter Operator predicate: ((VALUE._col0) IN ('val_400', 'val_500') and (KEY._col0) IN (400, 450)) (type: boolean) - Statistics: Num rows: 63 Data size: 669 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -229,33 +229,33 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key + key) = 400) or (((key - 100) = 500) and value is not null)) or (((key + key) = 200) or ((key - 100) = 100) or ((key = 300) and value is not null))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: value (type: string) sort order: + Map-reduce partition columns: value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string) Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((VALUE._col0 + VALUE._col0) = 200) or ((VALUE._col0 - 100) = 100) or ((VALUE._col0 = 300) and KEY._col0 is not null)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -263,20 +263,20 @@ STAGE PLANS: name: default.e1 Filter Operator predicate: (((VALUE._col0 + VALUE._col0) = 400) or (((VALUE._col0 - 100) = 500) and KEY._col0 is not null)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -401,33 +401,33 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((value) IN ('val_400', 'val_500') and (key) IN (400, 450)) or ((value) IN ('val_100', 'val_200', 'val_300') and (key) IN (100, 150, 200))) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE value expressions: value (type: string) Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((VALUE._col0) IN ('val_100', 'val_200', 'val_300') and (KEY._col0) IN (100, 150, 200)) (type: boolean) - Statistics: Num rows: 63 Data size: 669 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -435,20 +435,20 @@ STAGE PLANS: name: default.e1 Filter Operator predicate: ((VALUE._col0) IN ('val_400', 'val_500') and (KEY._col0) IN (400, 450)) (type: boolean) - Statistics: Num rows: 63 Data size: 669 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -573,33 +573,33 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key + key) = 400) or (((key - 100) = 500) and value is not null)) or (((key + key) = 200) or ((key - 100) = 100) or ((key = 300) and value is not null))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: value (type: string) sort order: + Map-reduce partition columns: value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string) Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((VALUE._col0 + VALUE._col0) = 200) or ((VALUE._col0 - 100) = 100) or ((VALUE._col0 = 300) and KEY._col0 is not null)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -607,20 +607,20 @@ STAGE PLANS: name: default.e1 Filter Operator predicate: (((VALUE._col0 + VALUE._col0) = 400) or (((VALUE._col0 - 100) = 500) and KEY._col0 is not null)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/join34.q.out b/ql/src/test/results/clientpositive/spark/join34.q.out index 503235f607..52684bb42d 100644 --- a/ql/src/test/results/clientpositive/spark/join34.q.out +++ b/ql/src/test/results/clientpositive/spark/join34.q.out @@ -195,17 +195,17 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: string) auto parallelism: false diff --git a/ql/src/test/results/clientpositive/spark/join35.q.out b/ql/src/test/results/clientpositive/spark/join35.q.out index 54f68af58a..2922be009f 100644 --- a/ql/src/test/results/clientpositive/spark/join35.q.out +++ b/ql/src/test/results/clientpositive/spark/join35.q.out @@ -201,17 +201,17 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: string) auto parallelism: false diff --git a/ql/src/test/results/clientpositive/spark/multi_insert.q.out b/ql/src/test/results/clientpositive/spark/multi_insert.q.out index 33af962c97..b6324c623e 100644 --- a/ql/src/test/results/clientpositive/spark/multi_insert.q.out +++ b/ql/src/test/results/clientpositive/spark/multi_insert.q.out @@ -593,27 +593,27 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -621,15 +621,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -739,27 +739,27 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -767,15 +767,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -885,27 +885,27 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -913,15 +913,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1031,27 +1031,27 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1059,15 +1059,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/multi_insert_move_tasks_share_dependencies.q.out b/ql/src/test/results/clientpositive/spark/multi_insert_move_tasks_share_dependencies.q.out index 7f1d67b566..7c8c163003 100644 --- a/ql/src/test/results/clientpositive/spark/multi_insert_move_tasks_share_dependencies.q.out +++ b/ql/src/test/results/clientpositive/spark/multi_insert_move_tasks_share_dependencies.q.out @@ -610,27 +610,27 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -638,15 +638,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -760,27 +760,27 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -788,15 +788,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -910,27 +910,27 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -938,15 +938,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1060,27 +1060,27 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1088,15 +1088,15 @@ STAGE PLANS: name: default.src_multi1 Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2360,54 +2360,54 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2469,54 +2469,54 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2578,54 +2578,54 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2687,54 +2687,54 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2834,54 +2834,54 @@ STAGE PLANS: name: default.src_multi2 Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3054,54 +3054,54 @@ STAGE PLANS: name: default.src_multi2 Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3274,54 +3274,54 @@ STAGE PLANS: name: default.src_multi2 Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3494,54 +3494,54 @@ STAGE PLANS: name: default.src_multi2 Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/pcr.q.out b/ql/src/test/results/clientpositive/spark/pcr.q.out index 3ed71afc4d..3b3606ffd7 100644 --- a/ql/src/test/results/clientpositive/spark/pcr.q.out +++ b/ql/src/test/results/clientpositive/spark/pcr.q.out @@ -267,16 +267,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((ds <= '2000-04-09') or (key < 5)) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -434,13 +434,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -744,16 +744,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds < '2000-04-09') and (key < 5)) or ((ds > '2000-04-09') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -863,13 +863,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -943,16 +943,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds < '2000-04-10') and (key < 5)) or ((ds > '2000-04-08') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -1110,13 +1110,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1200,16 +1200,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds < '2000-04-10') or (key < 5)) and ((ds > '2000-04-08') or (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -1367,13 +1367,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2159,16 +2159,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds = '2000-04-08') and (key = 1)) or ((ds = '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false Path -> Alias: @@ -2277,13 +2277,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2902,16 +2902,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds > '2000-04-08') and (ds < '2000-04-11')) or (key = 2)) (type: boolean) - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false Path -> Alias: @@ -3116,13 +3116,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -3228,16 +3228,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((ds > '2000-04-08') or ((ds <= '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false Path -> Alias: @@ -3394,13 +3394,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out b/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out index 27c0873716..0f72d8dcb7 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out @@ -37,16 +37,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < '400') and (key > '20') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan @@ -76,22 +76,22 @@ STAGE PLANS: Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 3 Reduce Operator Tree: @@ -100,10 +100,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -305,16 +305,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < '400') and (key > '20') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan @@ -344,22 +344,22 @@ STAGE PLANS: Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 3 Reduce Operator Tree: @@ -368,10 +368,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE 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/ppd_join.q.out b/ql/src/test/results/clientpositive/spark/ppd_join.q.out index 1b2487e483..a695100681 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_join.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_join.q.out @@ -34,16 +34,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < '400') and (key > '20') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Map 3 Map Operator Tree: TableScan @@ -74,14 +74,14 @@ STAGE PLANS: Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -567,16 +567,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < '400') and (key > '20') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Map 3 Map Operator Tree: TableScan @@ -607,14 +607,14 @@ STAGE PLANS: Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE 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/ppd_join2.q.out b/ql/src/test/results/clientpositive/spark/ppd_join2.q.out index 024e9622c2..57c74f591b 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_join2.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_join2.q.out @@ -59,16 +59,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <> '302') and (key < '400') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 5 Map Operator Tree: @@ -99,12 +99,12 @@ STAGE PLANS: Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) Reducer 3 Reduce Operator Tree: @@ -1739,16 +1739,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <> '302') and (key < '400') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 5 Map Operator Tree: @@ -1779,12 +1779,12 @@ STAGE PLANS: Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) Reducer 3 Reduce Operator Tree: diff --git a/ql/src/test/results/clientpositive/spark/ppd_join3.q.out b/ql/src/test/results/clientpositive/spark/ppd_join3.q.out index 6706153fb4..f6db6baaad 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_join3.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_join3.q.out @@ -57,16 +57,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <> '11') and (key < '400') and (key <> '12') and (key <> '13') and (key > '0') and ((value <> 'val_500') or (key > '1')) and (key <> '4') and (key <> '1')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan @@ -99,14 +99,14 @@ STAGE PLANS: Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col2 > '10') or (_col1 <> '10')) (type: boolean) - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1778,16 +1778,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <> '11') and (key < '400') and (key <> '12') and (key <> '13') and (key > '0') and ((value <> 'val_500') or (key > '1')) and (key <> '4') and (key <> '1')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan @@ -1820,14 +1820,14 @@ STAGE PLANS: Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col2 > '10') or (_col1 <> '10')) (type: boolean) - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE 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/ppd_transform.q.out b/ql/src/test/results/clientpositive/spark/ppd_transform.q.out index b0753b6734..8d386ec758 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_transform.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_transform.q.out @@ -398,20 +398,20 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col0 = 'a') or (_col0 = 'b')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((_col0 = 'c') or (_col0 = 'd')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out b/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out index 21e7be2db3..217d94923f 100644 --- a/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out +++ b/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out @@ -91,16 +91,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 3 Map Operator Tree: @@ -109,16 +109,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 4 Map Operator Tree: @@ -127,16 +127,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key <> 2) and (key <> 3))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 6 Map Operator Tree: @@ -145,16 +145,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key <> 2) and (key <> 3))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: @@ -162,7 +162,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -176,7 +176,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -234,16 +234,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 3 Map Operator Tree: @@ -252,16 +252,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 4 Map Operator Tree: @@ -270,16 +270,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <> 2) and (key <> 3)) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 6 Map Operator Tree: @@ -288,16 +288,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <> 2) and (key <> 3)) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: @@ -305,7 +305,7 @@ STAGE PLANS: condition map: Right Outer Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -319,7 +319,7 @@ STAGE PLANS: condition map: Right Outer Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -380,16 +380,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan @@ -397,16 +397,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Map 5 Map Operator Tree: TableScan @@ -414,16 +414,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key <> 2) and (key <> 3))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Map 7 Map Operator Tree: TableScan @@ -431,22 +431,22 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and ((key <> 2) and (key <> 3))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -475,7 +475,7 @@ STAGE PLANS: Join Operator condition map: Inner Join 0 to 1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -529,16 +529,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan @@ -546,16 +546,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Map 5 Map Operator Tree: TableScan @@ -563,16 +563,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <> 2) and (key <> 3)) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Map 7 Map Operator Tree: TableScan @@ -580,22 +580,22 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <> 2) and (key <> 3)) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator condition map: Right Outer Join 0 to 1 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -624,7 +624,7 @@ STAGE PLANS: Join Operator condition map: Right Outer Join 0 to 1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out index 503efa2900..c73bdc3d22 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out @@ -1591,7 +1591,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7, pattern %b%) -> boolean, FilterDecimalScalarNotEqualDecimalColumn(val 79.553, col 12)(children: CastLongToDecimal(col 2) -> 12:decimal(13,3)) -> boolean, FilterDoubleColLessDoubleColumn(col 13, col 5)(children: CastLongToDouble(col 3) -> 13:double) -> boolean, FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 0, col 1)(children: col 0) -> boolean, FilterLongColEqualLongScalar(col 11, val 1) -> boolean, FilterLongScalarEqualLongColumn(val 3569, col 0)(children: col 0) -> boolean) -> boolean) -> boolean predicate: ((cstring2 like '%b%') or (79.553 <> CAST( cint AS decimal(13,3))) or (UDFToDouble(cbigint) < cdouble) or ((UDFToShort(ctinyint) >= csmallint) and (cboolean2 = 1) and (3569 = UDFToInteger(ctinyint)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cbigint (type: bigint), cfloat (type: float) outputColumnNames: ctinyint, cbigint, cfloat @@ -1599,7 +1599,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 3, 4] - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(cbigint), stddev_pop(cbigint), var_samp(cbigint), count(), sum(cfloat), min(ctinyint) Group By Vectorization: @@ -1781,9 +1781,9 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((cstring1 like 'a%') or (cstring1 like 'b%') or (cstring1 like 'c%') or ((length(cstring1) < 50) and (cstring1 like '%n') and (length(cstring1) > 0))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -30589,17 +30589,17 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean) - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -30816,17 +30816,17 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((cint = 49) or (cfloat = 3.5)) and ((cint = 47) or (cfloat = 2.09)) and ((cint = 45) or (cfloat = 3.02))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/spark/vectorization_10.q.out b/ql/src/test/results/clientpositive/spark/vectorization_10.q.out index 1f953575e3..b5ca7b62e9 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_10.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_10.q.out @@ -73,7 +73,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7, val 10) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 0) -> 12:double) -> boolean, FilterDecimalScalarGreaterEqualDecimalColumn(val -5638.15, col 13)(children: CastLongToDecimal(col 0) -> 13:decimal(6,2)) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5, val 6981.0) -> boolean, FilterExprOrExpr(children: FilterDecimalColEqualDecimalScalar(col 14, val 9763215.5639)(children: CastLongToDecimal(col 1) -> 14:decimal(11,4)) -> boolean, FilterStringColLikeStringScalar(col 6, pattern %a) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (-5638.15 >= CAST( ctinyint AS decimal(6,2)))) or ((cdouble > 6981.0) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a')))) (type: boolean) - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639 - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -82,13 +82,13 @@ STAGE PLANS: native: true projectedOutputColumns: [5, 8, 0, 10, 6, 12, 16, 15, 17, 19, 20, 18, 22, 23, 25] selectExpressions: DoubleColUnaryMinus(col 5) -> 12:double, DoubleColAddDoubleColumn(col 5, col 15)(children: CastLongToDouble(col 1) -> 15:double) -> 16:double, DoubleColModuloDoubleScalar(col 17, val 33.0)(children: DoubleColAddDoubleColumn(col 5, col 15)(children: CastLongToDouble(col 1) -> 15:double) -> 17:double) -> 15:double, DoubleColUnaryMinus(col 5) -> 17:double, DoubleColModuloDoubleColumn(col 18, col 5)(children: CastLongToDouble(col 0) -> 18:double) -> 19:double, LongColModuloLongColumn(col 0, col 1)(children: col 0) -> 20:long, DoubleColUnaryMinus(col 5) -> 18:double, LongColMultiplyLongColumn(col 3, col 21)(children: col 21) -> 22:long, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 24)(children: DoubleColAddDoubleColumn(col 5, col 23)(children: CastLongToDouble(col 1) -> 23:double) -> 24:double) -> 23:double, DoubleColUnaryMinus(col 24)(children: DoubleColUnaryMinus(col 5) -> 24:double) -> 25:double - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE 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/vectorization_11.q.out b/ql/src/test/results/clientpositive/spark/vectorization_11.q.out index 50307e964c..f9b9cd791e 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_11.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_11.q.out @@ -55,7 +55,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringGroupColumn(col 7, col 6) -> boolean, FilterExprAndExpr(children: SelectColumnIsNull(col 8) -> boolean, FilterStringColLikeStringScalar(col 6, pattern %a) -> boolean) -> boolean) -> boolean predicate: ((cstring2 = cstring1) or (ctimestamp1 is null and (cstring1 like '%a'))) (type: boolean) - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), ctimestamp1 (type: timestamp), (-3728 * UDFToInteger(csmallint)) (type: int), (cdouble - 9763215.5639) (type: double), (- cdouble) (type: double), ((- cdouble) + 6981.0) (type: double), (cdouble * -5638.15) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -64,13 +64,13 @@ STAGE PLANS: native: true projectedOutputColumns: [6, 10, 5, 8, 12, 13, 14, 16, 15] selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 1)(children: col 1) -> 12:long, DoubleColSubtractDoubleScalar(col 5, val 9763215.5639) -> 13:double, DoubleColUnaryMinus(col 5) -> 14:double, DoubleColAddDoubleScalar(col 15, val 6981.0)(children: DoubleColUnaryMinus(col 5) -> 15:double) -> 16:double, DoubleColMultiplyDoubleScalar(col 5, val -5638.15) -> 15:double - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_12.q.out b/ql/src/test/results/clientpositive/spark/vectorization_12.q.out index 4e26314499..07780de830 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_12.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_12.q.out @@ -92,7 +92,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNull(col 8) -> boolean, FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 10, col 11) -> boolean, FilterLongColNotEqualLongColumn(col 0, col 1)(children: col 0) -> boolean) -> boolean, FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6, pattern %a) -> boolean, FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 11, val 1) -> boolean, FilterLongColGreaterEqualLongColumn(col 3, col 1)(children: col 1) -> boolean) -> boolean) -> boolean) -> boolean predicate: (ctimestamp1 is null and ((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint))))) (type: boolean) - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cdouble (type: double), cstring1 (type: string), cboolean1 (type: boolean) outputColumnNames: cbigint, cdouble, cstring1, cboolean1 @@ -100,7 +100,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [3, 5, 6, 10] - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(cbigint), stddev_samp(cbigint), avg(cdouble), sum(cbigint), stddev_pop(cdouble) Group By Vectorization: @@ -115,7 +115,7 @@ STAGE PLANS: keys: cdouble (type: double), cbigint (type: bigint), cstring1 (type: string), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean) sort order: ++++ @@ -126,7 +126,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [4, 5, 6, 7, 8] - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col4 (type: bigint), _col5 (type: struct), _col6 (type: struct), _col7 (type: bigint), _col8 (type: struct) Execution mode: vectorized Map Vectorization: @@ -172,7 +172,7 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: bigint), KEY._col2 (type: string), KEY._col3 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col3 (type: boolean), _col2 (type: string), _col0 (type: double), (-6432.0 * _col0) (type: double), (- _col1) (type: bigint), _col4 (type: bigint), (_col1 * _col4) (type: bigint), _col5 (type: double), ((-6432.0 * _col0) / -6432.0) (type: double), (- ((-6432.0 * _col0) / -6432.0)) (type: double), _col6 (type: double), (- (-6432.0 * _col0)) (type: double), (-5638.15 + CAST( _col1 AS decimal(19,0))) (type: decimal(22,2)), _col7 (type: bigint), (_col6 / (-6432.0 * _col0)) (type: double), (- (- ((-6432.0 * _col0) / -6432.0))) (type: double), (((-6432.0 * _col0) / -6432.0) + (- (-6432.0 * _col0))) (type: double), _col8 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19 @@ -181,7 +181,7 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 3, 2, 0, 9, 10, 4, 11, 5, 13, 12, 6, 15, 17, 7, 18, 19, 14, 8] selectExpressions: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 9:double, LongColUnaryMinus(col 1) -> 10:long, LongColMultiplyLongColumn(col 1, col 4) -> 11:long, DoubleColDivideDoubleScalar(col 12, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 12:double) -> 13:double, DoubleColUnaryMinus(col 14)(children: DoubleColDivideDoubleScalar(col 12, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 12:double) -> 14:double) -> 12:double, DoubleColUnaryMinus(col 14)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 14:double) -> 15:double, DecimalScalarAddDecimalColumn(val -5638.15, col 16)(children: CastLongToDecimal(col 1) -> 16:decimal(19,0)) -> 17:decimal(22,2), DoubleColDivideDoubleColumn(col 6, col 14)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 14:double) -> 18:double, DoubleColUnaryMinus(col 14)(children: DoubleColUnaryMinus(col 19)(children: DoubleColDivideDoubleScalar(col 14, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 14:double) -> 19:double) -> 14:double) -> 19:double, DoubleColAddDoubleColumn(col 20, col 21)(children: DoubleColDivideDoubleScalar(col 14, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 14:double) -> 20:double, DoubleColUnaryMinus(col 14)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0) -> 14:double) -> 21:double) -> 14:double - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col3 (type: double), _col0 (type: bigint), _col2 (type: string) sort order: +++ @@ -191,7 +191,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [3, 9, 10, 4, 11, 5, 13, 12, 6, 15, 17, 7, 18, 19, 14, 8] - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: boolean), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(22,2)), _col14 (type: bigint), _col15 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double) Reducer 3 Execution mode: vectorized @@ -218,13 +218,13 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 3, 2, 19, 0, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 11, 16, 17, 18] selectExpressions: ConstantVectorExpression(val null) -> 19:timestamp - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_13.q.out b/ql/src/test/results/clientpositive/spark/vectorization_13.q.out index ce160a6971..ad821c0ca7 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_13.q.out @@ -94,7 +94,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4, val 3569.0) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val 10.175, col 5) -> boolean, FilterLongColNotEqualLongScalar(col 10, val 1) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 12, val 11.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterDoubleColNotEqualDoubleScalar(col 12, val 12.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDecimalColLessDecimalScalar(col 13, val 9763215.5639)(children: CastLongToDecimal(col 0) -> 13:decimal(11,4)) -> boolean) -> boolean) -> boolean predicate: (((cfloat < 3569) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > 11.0) and (UDFToDouble(ctimestamp2) <> 12.0) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 @@ -102,7 +102,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 4, 6, 8, 10] - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) Group By Vectorization: @@ -117,7 +117,7 @@ STAGE PLANS: keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -128,7 +128,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [5, 6, 7, 8, 9, 10] - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -175,7 +175,7 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 @@ -184,7 +184,7 @@ STAGE PLANS: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 11, 5, 13, 6, 16, 15, 17, 7, 18, 8, 20, 22, 21, 9, 25, 10] selectExpressions: LongColUnaryMinus(col 1) -> 11:long, LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 13:long, DoubleColMultiplyDoubleColumn(col 6, col 15)(children: CastLongToDouble(col 14)(children: LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 14:long) -> 15:double) -> 16:double, DoubleColUnaryMinus(col 6) -> 15:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3) -> 17:double, DoubleColUnaryMinus(col 6) -> 18:double, DecimalColSubtractDecimalScalar(col 19, val 10.175)(children: CastLongToDecimal(col 14)(children: LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 14:long) -> 19:decimal(3,0)) -> 20:decimal(7,3), DoubleColUnaryMinus(col 21)(children: DoubleColUnaryMinus(col 6) -> 21:double) -> 22:double, DoubleScalarDivideDoubleColumn(val -26.28, col 23)(children: DoubleColUnaryMinus(col 21)(children: DoubleColUnaryMinus(col 6) -> 21:double) -> 23:double) -> 21:double, DoubleColDivideDoubleColumn(col 24, col 23)(children: DoubleColMultiplyDoubleColumn(col 6, col 23)(children: CastLongToDouble(col 14)(children: LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 14:long) -> 23:double) -> 24:double, CastLongToDouble(col 1) -> 23:double) -> 25:double - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) sort order: +++++++++++++++++++++ @@ -194,7 +194,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [] - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: vectorized @@ -219,19 +219,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 10, 14, 15, 16, 17, 18, 19, 20] - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -447,7 +447,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4, val 3569.0) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val 10.175, col 5) -> boolean, FilterLongColNotEqualLongScalar(col 10, val 1) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 12, val -1.388)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterDoubleColNotEqualDoubleScalar(col 12, val -1.3359999999999999)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDecimalColLessDecimalScalar(col 13, val 9763215.5639)(children: CastLongToDecimal(col 0) -> 13:decimal(11,4)) -> boolean) -> boolean) -> boolean predicate: (((cfloat < 3569) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -1.388) and (UDFToDouble(ctimestamp2) <> -1.3359999999999999) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 @@ -455,7 +455,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 4, 6, 8, 10] - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) Group By Vectorization: @@ -470,7 +470,7 @@ STAGE PLANS: keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -479,7 +479,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -514,7 +514,7 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 @@ -523,7 +523,7 @@ STAGE PLANS: native: true projectedOutputColumns: [0, 1, 2, 3, 4, 11, 5, 13, 6, 16, 15, 17, 7, 18, 8, 20, 22, 21, 9, 25, 10] selectExpressions: LongColUnaryMinus(col 1) -> 11:long, LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 13:long, DoubleColMultiplyDoubleColumn(col 6, col 15)(children: CastLongToDouble(col 14)(children: LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 14:long) -> 15:double) -> 16:double, DoubleColUnaryMinus(col 6) -> 15:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3) -> 17:double, DoubleColUnaryMinus(col 6) -> 18:double, DecimalColSubtractDecimalScalar(col 19, val 10.175)(children: CastLongToDecimal(col 14)(children: LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 14:long) -> 19:decimal(3,0)) -> 20:decimal(7,3), DoubleColUnaryMinus(col 21)(children: DoubleColUnaryMinus(col 6) -> 21:double) -> 22:double, DoubleScalarDivideDoubleColumn(val -26.28, col 23)(children: DoubleColUnaryMinus(col 21)(children: DoubleColUnaryMinus(col 6) -> 21:double) -> 23:double) -> 21:double, DoubleColDivideDoubleColumn(col 24, col 23)(children: DoubleColMultiplyDoubleColumn(col 6, col 23)(children: CastLongToDouble(col 14)(children: LongColAddLongColumn(col 12, col 5)(children: LongColUnaryMinus(col 1) -> 12:long) -> 14:long) -> 23:double) -> 24:double, CastLongToDouble(col 1) -> 23:double) -> 25:double - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) sort order: +++++++++++++++++++++ @@ -531,7 +531,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: vectorized @@ -550,19 +550,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 10, 14, 15, 16, 17, 18, 19, 20] - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_14.q.out b/ql/src/test/results/clientpositive/spark/vectorization_14.q.out index 0d443913a9..3c7fb95da9 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_14.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_14.q.out @@ -94,7 +94,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0, col 3)(children: col 0) -> boolean, FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 2) -> 12:double) -> boolean, FilterTimestampColLessTimestampColumn(col 9, col 8) -> boolean) -> boolean, FilterDoubleColLessDoubleColumn(col 5, col 12)(children: CastLongToDouble(col 0) -> 12:double) -> boolean, FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3, val -257) -> boolean, FilterDoubleColLessDoubleColumn(col 4, col 12)(children: CastLongToFloatViaLongToDouble(col 2) -> 12:double) -> boolean) -> boolean) -> boolean predicate: ((UDFToLong(ctinyint) <= cbigint) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1)) and (cdouble < UDFToDouble(ctinyint)) and ((cbigint > -257) or (cfloat < UDFToFloat(cint)))) (type: boolean) - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28 + cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 @@ -103,7 +103,7 @@ STAGE PLANS: native: true projectedOutputColumns: [8, 4, 6, 10, 5, 13] selectExpressions: DoubleColUnaryMinus(col 12)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5) -> 12:double) -> 13:double - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(_col5), max(_col1), stddev_pop(_col1), count(_col1), var_pop(_col1), var_samp(_col1) Group By Vectorization: @@ -118,7 +118,7 @@ STAGE PLANS: keys: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp), _col3 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ @@ -129,7 +129,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [5, 6, 7, 8, 9, 10] - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: struct), _col6 (type: float), _col7 (type: struct), _col8 (type: bigint), _col9 (type: struct), _col10 (type: struct) Execution mode: vectorized Map Vectorization: @@ -176,7 +176,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28 + _col2) (type: double), (- (-26.28 + _col2)) (type: double), _col5 (type: double), (_col1 * -26.28) (type: float), _col6 (type: float), (- _col1) (type: float), (- _col6) (type: float), ((- (-26.28 + _col2)) / 10.175) (type: double), _col7 (type: double), _col8 (type: bigint), (- ((- (-26.28 + _col2)) / 10.175)) (type: double), (-1.389 % _col5) (type: double), (UDFToDouble(_col1) - _col2) (type: double), _col9 (type: double), (_col9 % 10.175) (type: double), _col10 (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 @@ -185,7 +185,7 @@ STAGE PLANS: native: true projectedOutputColumns: [3, 1, 0, 4, 2, 11, 13, 5, 12, 6, 14, 15, 16, 7, 8, 18, 17, 19, 9, 20, 10, 22] selectExpressions: DoubleScalarAddDoubleColumn(val -26.28, col 2) -> 11:double, DoubleColUnaryMinus(col 12)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2) -> 12:double) -> 13:double, DoubleColMultiplyDoubleScalar(col 1, val -26.280000686645508) -> 12:double, DoubleColUnaryMinus(col 1) -> 14:double, DoubleColUnaryMinus(col 6) -> 15:double, DoubleColDivideDoubleScalar(col 17, val 10.175)(children: DoubleColUnaryMinus(col 16)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2) -> 16:double) -> 17:double) -> 16:double, DoubleColUnaryMinus(col 17)(children: DoubleColDivideDoubleScalar(col 18, val 10.175)(children: DoubleColUnaryMinus(col 17)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2) -> 17:double) -> 18:double) -> 17:double) -> 18:double, DoubleScalarModuloDoubleColumn(val -1.389, col 5) -> 17:double, DoubleColSubtractDoubleColumn(col 1, col 2)(children: col 1) -> 19:double, DoubleColModuloDoubleScalar(col 9, val 10.175) -> 20:double, DoubleColUnaryMinus(col 21)(children: DoubleColSubtractDoubleColumn(col 1, col 2)(children: col 1) -> 21:double) -> 22:double - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp) sort order: ++++ @@ -195,7 +195,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [4, 11, 13, 5, 12, 6, 14, 15, 16, 7, 8, 18, 17, 19, 9, 20, 10, 22] - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) Reducer 3 Execution mode: vectorized @@ -220,13 +220,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [3, 1, 0, 4, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_15.q.out b/ql/src/test/results/clientpositive/spark/vectorization_15.q.out index 1b589f776f..c41dffd6a2 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_15.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_15.q.out @@ -90,7 +90,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7, pattern %ss%) -> boolean, FilterStringColLikeStringScalar(col 6, pattern 10%) -> boolean, FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2, val -75) -> boolean, FilterLongColEqualLongColumn(col 0, col 1)(children: col 0) -> boolean, FilterDoubleColGreaterEqualDoubleScalar(col 5, val -3728.0) -> boolean) -> boolean) -> boolean predicate: ((cstring2 like '%ss%') or (cstring1 like '10%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) outputColumnNames: ctinyint, cint, cfloat, cdouble, cstring1, ctimestamp1, cboolean1 @@ -98,7 +98,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 2, 4, 5, 6, 8, 10] - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(cfloat), min(cdouble), stddev_samp(ctinyint), var_pop(ctinyint), var_samp(cint), stddev_pop(cint) Group By Vectorization: @@ -113,7 +113,7 @@ STAGE PLANS: keys: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) sort order: +++++++ @@ -124,7 +124,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [7, 8, 9, 10, 11, 12] - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: struct), _col8 (type: double), _col9 (type: struct), _col10 (type: struct), _col11 (type: struct), _col12 (type: struct) Execution mode: vectorized Map Vectorization: @@ -157,15 +157,15 @@ STAGE PLANS: keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), _col7 (type: double), (-26.28 - CAST( _col5 AS decimal(10,0))) (type: decimal(13,2)), _col8 (type: double), (_col2 * 79.553) (type: double), (33.0 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - CAST( _col5 AS decimal(10,0)))) (type: decimal(13,2)), _col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) sort order: +++++++ - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: double), _col8 (type: decimal(13,2)), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: decimal(13,2)), _col20 (type: double) Reducer 3 Reduce Vectorization: @@ -176,10 +176,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: decimal(13,2)), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: decimal(13,2)), VALUE._col13 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_16.q.out b/ql/src/test/results/clientpositive/spark/vectorization_16.q.out index 84fc4b03f6..0c4150c1f9 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_16.q.out @@ -67,7 +67,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7, pattern %b%) -> boolean, FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5, val -1.389) -> boolean, FilterStringGroupColLessStringScalar(col 6, val a) -> boolean) -> boolean) -> boolean predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) outputColumnNames: cdouble, cstring1, ctimestamp1 @@ -75,7 +75,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [5, 6, 8] - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) Group By Vectorization: @@ -90,7 +90,7 @@ STAGE PLANS: keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ @@ -101,7 +101,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [3, 4, 5] - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized Map Vectorization: @@ -147,7 +147,7 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 @@ -156,13 +156,13 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 0, 2, 6, 8, 3, 4, 7, 10, 5, 9, 12, 4] selectExpressions: DoubleColSubtractDoubleScalar(col 0, val 9763215.5639) -> 6:double, DoubleColUnaryMinus(col 7)(children: DoubleColSubtractDoubleScalar(col 0, val 9763215.5639) -> 7:double) -> 8:double, DoubleColUnaryMinus(col 4) -> 7:double, DoubleColMultiplyDoubleColumn(col 4, col 9)(children: CastLongToDouble(col 3) -> 9:double) -> 10:double, DoubleScalarDivideDoubleColumn(val 9763215.5639, col 0) -> 9:double, DecimalColDivideDecimalScalar(col 11, val -1.389)(children: CastLongToDecimal(col 3) -> 11:decimal(19,0)) -> 12:decimal(28,6) - Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_17.q.out b/ql/src/test/results/clientpositive/spark/vectorization_17.q.out index b43c506c6f..15e5485635 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_17.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_17.q.out @@ -75,7 +75,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3, val -23) -> boolean, FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5, val 988888.0) -> boolean, FilterDecimalColGreaterDecimalScalar(col 12, val -863.257)(children: CastLongToDecimal(col 2) -> 12:decimal(13,3)) -> boolean) -> boolean, FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0, val 33) -> boolean, FilterLongColGreaterEqualLongColumn(col 1, col 3)(children: col 1) -> boolean, FilterDoubleColEqualDoubleColumn(col 4, col 5)(children: col 4) -> boolean) -> boolean) -> boolean predicate: ((cbigint > -23) and ((cdouble <> 988888.0) or (CAST( cint AS decimal(13,3)) > -863.257)) and ((ctinyint >= 33) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble))) (type: boolean) - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58 + (- (- cdouble))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -84,7 +84,7 @@ STAGE PLANS: native: true projectedOutputColumns: [4, 6, 2, 8, 5, 3, 14, 15, 13, 16, 18, 19, 21, 17] selectExpressions: DoubleColDivideDoubleColumn(col 4, col 13)(children: col 4, CastLongToDouble(col 0) -> 13:double) -> 14:double, LongColModuloLongColumn(col 2, col 3)(children: col 2) -> 15:long, DoubleColUnaryMinus(col 5) -> 13:double, DoubleColAddDoubleColumn(col 5, col 17)(children: DoubleColDivideDoubleColumn(col 4, col 16)(children: col 4, CastLongToDouble(col 0) -> 16:double) -> 17:double) -> 16:double, DoubleColDivideDoubleColumn(col 5, col 17)(children: CastLongToDouble(col 2) -> 17:double) -> 18:double, DoubleColUnaryMinus(col 17)(children: DoubleColUnaryMinus(col 5) -> 17:double) -> 19:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 20)(children: CastLongToDecimal(col 3) -> 20:decimal(19,0)) -> 21:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 22)(children: DoubleColUnaryMinus(col 17)(children: DoubleColUnaryMinus(col 5) -> 17:double) -> 22:double) -> 17:double - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col5 (type: bigint), _col0 (type: float) sort order: ++ @@ -94,7 +94,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: [6, 2, 8, 5, 14, 15, 13, 16, 18, 19, 21, 17] - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double) Execution mode: vectorized Map Vectorization: @@ -134,13 +134,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [1, 2, 3, 4, 5, 0, 6, 7, 8, 9, 10, 11, 12, 13] - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_2.q.out b/ql/src/test/results/clientpositive/spark/vectorization_2.q.out index 65ea41e2ba..6718187aff 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_2.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_2.q.out @@ -73,7 +73,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterTimestampColLessTimestampColumn(col 8, col 9) -> boolean, FilterStringColLikeStringScalar(col 7, pattern b%) -> boolean, FilterDoubleColLessEqualDoubleScalar(col 4, val -5638.14990234375) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5, col 12)(children: CastLongToDouble(col 0) -> 12:double) -> boolean, FilterExprOrExpr(children: FilterDoubleScalarNotEqualDoubleColumn(val -10669.0, col 12)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterLongScalarGreaterLongColumn(val 359, col 2) -> boolean) -> boolean) -> boolean) -> boolean predicate: (((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15)) or ((cdouble < UDFToDouble(ctinyint)) and ((-10669.0 <> UDFToDouble(ctimestamp2)) or (359 > cint)))) (type: boolean) - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cbigint (type: bigint), cfloat (type: float), cdouble (type: double) outputColumnNames: ctinyint, csmallint, cbigint, cfloat, cdouble @@ -81,7 +81,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 3, 4, 5] - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(csmallint), sum(cfloat), var_pop(cbigint), count(), min(ctinyint), avg(cdouble) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/spark/vectorization_3.q.out b/ql/src/test/results/clientpositive/spark/vectorization_3.q.out index ccf302e18e..2a13e98797 100644 --- a/ql/src/test/results/clientpositive/spark/vectorization_3.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorization_3.q.out @@ -78,7 +78,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 12, col 4)(children: CastLongToFloatViaLongToDouble(col 2) -> 12:double) -> boolean, FilterDecimalScalarNotEqualDecimalColumn(val 79.553, col 13)(children: CastLongToDecimal(col 3) -> 13:decimal(22,3)) -> boolean, FilterDoubleColEqualDoubleScalar(col 12, val -29071.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 3) -> 12:double) -> boolean, FilterDecimalScalarLessEqualDecimalColumn(val 79.553, col 14)(children: CastLongToDecimal(col 1) -> 14:decimal(8,3)) -> boolean, FilterTimestampColGreaterTimestampColumn(col 8, col 9) -> boolean) -> boolean) -> boolean predicate: (((UDFToFloat(cint) <= cfloat) and (79.553 <> CAST( cbigint AS decimal(22,3))) and (UDFToDouble(ctimestamp2) = -29071.0)) or ((UDFToDouble(cbigint) > cdouble) and (79.553 <= CAST( csmallint AS decimal(8,3))) and (ctimestamp1 > ctimestamp2))) (type: boolean) - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cfloat (type: float) outputColumnNames: ctinyint, csmallint, cint, cfloat @@ -86,7 +86,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 4] - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(csmallint), stddev_pop(ctinyint), stddev_samp(cfloat), sum(cfloat), avg(cint), stddev_pop(cint) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/spark/vectorized_case.q.out b/ql/src/test/results/clientpositive/spark/vectorized_case.q.out index 2c99ff31bd..abb0a23280 100644 --- a/ql/src/test/results/clientpositive/spark/vectorized_case.q.out +++ b/ql/src/test/results/clientpositive/spark/vectorized_case.q.out @@ -61,7 +61,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1, val 418) -> boolean, FilterLongColEqualLongScalar(col 1, val 12205) -> boolean, FilterLongColEqualLongScalar(col 1, val 10583) -> boolean) -> boolean predicate: ((csmallint = 418) or (csmallint = 12205) or (csmallint = 10583)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 @@ -70,13 +70,13 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 15, 16] selectExpressions: IfExprStringScalarStringGroupColumn(col 12, val a, col 14)(children: LongColEqualLongScalar(col 1, val 418) -> 12:long, IfExprStringScalarStringScalar(col 13, val b, val c)(children: LongColEqualLongScalar(col 1, val 12205) -> 13:long) -> 14:String) -> 15:String, IfExprStringScalarStringGroupColumn(col 12, val a, col 14)(children: LongColEqualLongScalar(col 1, val 418) -> 12:long, IfExprStringScalarStringScalar(col 13, val b, val c)(children: LongColEqualLongScalar(col 1, val 12205) -> 13:long) -> 14:String) -> 16:String - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -202,7 +202,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1, val 418) -> boolean, FilterLongColEqualLongScalar(col 1, val 12205) -> boolean, FilterLongColEqualLongScalar(col 1, val 10583) -> boolean) -> boolean predicate: ((csmallint = 418) or (csmallint = 12205) or (csmallint = 10583)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE (null) END (type: string), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN (null) ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 @@ -211,13 +211,13 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 16, 19] selectExpressions: IfExprStringScalarStringGroupColumn(col 12, val a, col 15)(children: LongColEqualLongScalar(col 1, val 418) -> 12:long, IfExprColumnNull(col 13, col 14, null)(children: LongColEqualLongScalar(col 1, val 12205) -> 13:long, ConstantVectorExpression(val b) -> 14:string) -> 15:string) -> 16:String, IfExprStringScalarStringGroupColumn(col 12, val a, col 18)(children: LongColEqualLongScalar(col 1, val 418) -> 12:long, IfExprNullColumn(col 17, null, col 15)(children: LongColEqualLongScalar(col 1, val 12205) -> 17:long, ConstantVectorExpression(val c) -> 15:string) -> 18:string) -> 19:String - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/subquery_notin_having.q.out b/ql/src/test/results/clientpositive/subquery_notin_having.q.out index 433609d016..89ad0fe00b 100644 --- a/ql/src/test/results/clientpositive/subquery_notin_having.q.out +++ b/ql/src/test/results/clientpositive/subquery_notin_having.q.out @@ -119,14 +119,14 @@ STAGE PLANS: Statistics: Num rows: 275 Data size: 7596 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 182 Data size: 5027 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 5027 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 5027 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -624,14 +624,14 @@ STAGE PLANS: Statistics: Num rows: 14 Data size: 2087 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 9 Data size: 1341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 149 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 1341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 149 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 9 Data size: 1341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 149 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out index ce943160d7..e45723650d 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out @@ -296,14 +296,14 @@ Stage-3 Reducer 2 File Output Operator [FS_8] table:{"name:":"default.acid_uami"} - Select Operator [SEL_4] (rows=4/2 width=302) + Select Operator [SEL_4] (rows=1/2 width=302) Output:["_col0","_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_3] PartitionCols:UDFToInteger(_col0) - Select Operator [SEL_2] (rows=4/2 width=302) + Select Operator [SEL_2] (rows=1/2 width=302) Output:["_col0","_col1","_col3"] - Filter Operator [FIL_9] (rows=4/2 width=226) + Filter Operator [FIL_9] (rows=1/2 width=226) predicate:((de = 109.23) or (de = 119.23)) TableScan [TS_0] (rows=8/4 width=226) default@acid_uami,acid_uami, ACID table,Tbl:COMPLETE,Col:COMPLETE,Output:["i","de","vc"] diff --git a/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out b/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out index 17ebb087e6..fa145ec204 100644 --- a/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out @@ -205,7 +205,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 2, val 0) -> boolean, FilterExprAndExpr(children: SelectColumnIsNull(col 4) -> boolean, SelectColumnIsNotNull(col 0) -> boolean, FilterLongColGreaterEqualLongColumn(col 3, col 2) -> boolean) -> boolean) -> boolean predicate: ((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 @@ -213,7 +213,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1] - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: @@ -250,7 +250,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: vectorized Map Vectorization: @@ -269,10 +269,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -306,11 +306,11 @@ STAGE PLANS: Statistics: Num rows: 550 Data size: 15193 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/vector_windowing_multipartitioning.q.out b/ql/src/test/results/clientpositive/vector_windowing_multipartitioning.q.out index 40994617f8..5b87225334 100644 --- a/ql/src/test/results/clientpositive/vector_windowing_multipartitioning.q.out +++ b/ql/src/test/results/clientpositive/vector_windowing_multipartitioning.q.out @@ -10196,7 +10196,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringScalar(col 7, val tom allen) -> boolean, FilterStringGroupColEqualStringScalar(col 7, val bob steinbeck) -> boolean) -> boolean predicate: ((s = 'tom allen') or (s = 'bob steinbeck')) (type: boolean) - Statistics: Num rows: 3912 Data size: 1017283 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: s (type: string), dec (type: decimal(4,2)) sort order: +- @@ -10206,7 +10206,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3912 Data size: 1017283 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: NONE value expressions: b (type: bigint), ts (type: timestamp) Execution mode: vectorized Map Vectorization: @@ -10230,7 +10230,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col3 (type: bigint), KEY.reducesinkkey0 (type: string), VALUE._col7 (type: timestamp), KEY.reducesinkkey1 (type: decimal(4,2)) outputColumnNames: _col3, _col7, _col8, _col9 - Statistics: Num rows: 3912 Data size: 1017283 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -10251,11 +10251,11 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 3912 Data size: 1017283 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: rank_window_0 (type: int), _col3 (type: bigint), _col7 (type: string), _col8 (type: timestamp) outputColumnNames: rank_window_0, _col3, _col7, _col8 - Statistics: Num rows: 3912 Data size: 1017283 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -10279,7 +10279,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3912 Data size: 1017283 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: NONE value expressions: rank_window_0 (type: int), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -10303,7 +10303,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col4 (type: bigint), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: timestamp) outputColumnNames: _col0, _col4, _col8, _col9 - Statistics: Num rows: 3912 Data size: 1017283 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -10323,14 +10323,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumLong window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 3912 Data size: 1017283 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col8 (type: string), _col0 (type: int), sum_window_1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3912 Data size: 1017283 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3912 Data size: 1017283 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -10421,7 +10421,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringScalar(col 7, val tom allen) -> boolean, FilterStringGroupColEqualStringScalar(col 7, val bob steinbeck) -> boolean) -> boolean predicate: ((s = 'tom allen') or (s = 'bob steinbeck')) (type: boolean) - Statistics: Num rows: 9084 Data size: 1017431 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: s (type: string) sort order: + @@ -10431,7 +10431,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 9084 Data size: 1017431 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE value expressions: si (type: smallint), i (type: int), f (type: float) Execution mode: vectorized Map Vectorization: @@ -10455,7 +10455,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col1 (type: smallint), VALUE._col2 (type: int), VALUE._col4 (type: float), KEY.reducesinkkey0 (type: string) outputColumnNames: _col1, _col2, _col4, _col7 - Statistics: Num rows: 9084 Data size: 1017431 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -10475,11 +10475,11 @@ STAGE PLANS: name: sum window function: GenericUDAFSumLong window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 9084 Data size: 1017431 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: sum_window_0 (type: bigint), _col1 (type: smallint), _col4 (type: float), _col7 (type: string) outputColumnNames: sum_window_0, _col1, _col4, _col7 - Statistics: Num rows: 9084 Data size: 1017431 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -10503,7 +10503,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 9084 Data size: 1017431 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE value expressions: sum_window_0 (type: bigint), _col4 (type: float), _col7 (type: string) Execution mode: vectorized Map Vectorization: @@ -10527,7 +10527,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: smallint), VALUE._col4 (type: float), VALUE._col7 (type: string) outputColumnNames: _col0, _col2, _col5, _col8 - Statistics: Num rows: 9084 Data size: 1017431 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -10547,14 +10547,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 9084 Data size: 1017431 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col8 (type: string), _col0 (type: bigint), sum_window_1 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 9084 Data size: 1017431 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 9084 Data size: 1017431 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -10639,7 +10639,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringScalar(col 7, val tom allen) -> boolean, FilterStringGroupColEqualStringScalar(col 7, val bob steinbeck) -> boolean) -> boolean predicate: ((s = 'tom allen') or (s = 'bob steinbeck')) (type: boolean) - Statistics: Num rows: 4892 Data size: 1017544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: s (type: string), bo (type: boolean) sort order: ++ @@ -10649,7 +10649,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4892 Data size: 1017544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE value expressions: si (type: smallint), bin (type: binary) Execution mode: vectorized Map Vectorization: @@ -10673,7 +10673,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col1 (type: smallint), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey0 (type: string), VALUE._col8 (type: binary) outputColumnNames: _col1, _col6, _col7, _col10 - Statistics: Num rows: 4892 Data size: 1017544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -10694,11 +10694,11 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 4892 Data size: 1017544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: rank_window_0 (type: int), _col1 (type: smallint), _col7 (type: string), _col10 (type: binary) outputColumnNames: rank_window_0, _col1, _col7, _col10 - Statistics: Num rows: 4892 Data size: 1017544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -10722,7 +10722,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4892 Data size: 1017544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE value expressions: rank_window_0 (type: int), _col7 (type: string) Execution mode: vectorized Map Vectorization: @@ -10746,7 +10746,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey0 (type: smallint), VALUE._col7 (type: string), KEY.reducesinkkey1 (type: binary) outputColumnNames: _col0, _col2, _col8, _col11 - Statistics: Num rows: 4892 Data size: 1017544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -10767,14 +10767,14 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 4892 Data size: 1017544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col8 (type: string), _col0 (type: int), rank_window_1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4892 Data size: 1017544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4892 Data size: 1017544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -10859,7 +10859,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringScalar(col 7, val tom allen) -> boolean, FilterStringGroupColEqualStringScalar(col 7, val bob steinbeck) -> boolean) -> boolean predicate: ((s = 'tom allen') or (s = 'bob steinbeck')) (type: boolean) - Statistics: Num rows: 9420 Data size: 1017435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: i (type: int) sort order: + @@ -10869,7 +10869,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 9420 Data size: 1017435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE value expressions: f (type: float), s (type: string) Execution mode: vectorized Map Vectorization: @@ -10893,7 +10893,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col3 (type: float), VALUE._col6 (type: string) outputColumnNames: _col2, _col4, _col7 - Statistics: Num rows: 9420 Data size: 1017435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -10913,11 +10913,11 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 9420 Data size: 1017435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: sum_window_0 (type: double), _col4 (type: float), _col7 (type: string) outputColumnNames: sum_window_0, _col4, _col7 - Statistics: Num rows: 9420 Data size: 1017435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -10941,7 +10941,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 9420 Data size: 1017435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE value expressions: sum_window_0 (type: double), _col7 (type: string) Execution mode: vectorized Map Vectorization: @@ -10966,7 +10966,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: double), KEY.reducesinkkey1 (type: float), VALUE._col7 (type: string) outputColumnNames: _col0, _col5, _col8 - Statistics: Num rows: 9420 Data size: 1017435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -10986,14 +10986,14 @@ STAGE PLANS: window function: GenericUDAFRowNumberEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 9420 Data size: 1017435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col8 (type: string), _col0 (type: double), row_number_window_1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 9420 Data size: 1017435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 9420 Data size: 1017435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -11088,7 +11088,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringScalar(col 7, val tom allen) -> boolean, FilterStringGroupColEqualStringScalar(col 7, val bob steinbeck) -> boolean) -> boolean predicate: ((s = 'tom allen') or (s = 'bob steinbeck')) (type: boolean) - Statistics: Num rows: 4624 Data size: 1017323 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: s (type: string), dec (type: decimal(4,2)) sort order: ++ @@ -11098,7 +11098,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4624 Data size: 1017323 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE value expressions: si (type: smallint), f (type: float) Execution mode: vectorized Map Vectorization: @@ -11122,7 +11122,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col1 (type: smallint), VALUE._col4 (type: float), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: decimal(4,2)) outputColumnNames: _col1, _col4, _col7, _col9 - Statistics: Num rows: 4624 Data size: 1017323 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -11143,11 +11143,11 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 4624 Data size: 1017323 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: rank_window_0 (type: int), _col1 (type: smallint), _col4 (type: float), _col7 (type: string) outputColumnNames: rank_window_0, _col1, _col4, _col7 - Statistics: Num rows: 4624 Data size: 1017323 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -11171,7 +11171,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4624 Data size: 1017323 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE value expressions: rank_window_0 (type: int), _col7 (type: string) Execution mode: vectorized Map Vectorization: @@ -11195,7 +11195,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey1 (type: float), VALUE._col6 (type: string) outputColumnNames: _col0, _col2, _col5, _col8 - Statistics: Num rows: 4624 Data size: 1017323 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -11216,14 +11216,14 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 4624 Data size: 1017323 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col8 (type: string), _col0 (type: int), rank_window_1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4624 Data size: 1017323 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4624 Data size: 1017323 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE 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/vectorization_10.q.out b/ql/src/test/results/clientpositive/vectorization_10.q.out index d2d9bf644b..c8eeed9703 100644 --- a/ql/src/test/results/clientpositive/vectorization_10.q.out +++ b/ql/src/test/results/clientpositive/vectorization_10.q.out @@ -70,7 +70,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7, val 10) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 0) -> 12:double) -> boolean, FilterDecimalScalarGreaterEqualDecimalColumn(val -5638.15, col 13)(children: CastLongToDecimal(col 0) -> 13:decimal(6,2)) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5, val 6981.0) -> boolean, FilterExprOrExpr(children: FilterDecimalColEqualDecimalScalar(col 14, val 9763215.5639)(children: CastLongToDecimal(col 1) -> 14:decimal(11,4)) -> boolean, FilterStringColLikeStringScalar(col 6, pattern %a) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (-5638.15 >= CAST( ctinyint AS decimal(6,2)))) or ((cdouble > 6981.0) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a')))) (type: boolean) - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639 - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -79,13 +79,13 @@ STAGE PLANS: native: true projectedOutputColumns: [5, 8, 0, 10, 6, 12, 16, 15, 17, 19, 20, 18, 22, 23, 25] selectExpressions: DoubleColUnaryMinus(col 5) -> 12:double, DoubleColAddDoubleColumn(col 5, col 15)(children: CastLongToDouble(col 1) -> 15:double) -> 16:double, DoubleColModuloDoubleScalar(col 17, val 33.0)(children: DoubleColAddDoubleColumn(col 5, col 15)(children: CastLongToDouble(col 1) -> 15:double) -> 17:double) -> 15:double, DoubleColUnaryMinus(col 5) -> 17:double, DoubleColModuloDoubleColumn(col 18, col 5)(children: CastLongToDouble(col 0) -> 18:double) -> 19:double, LongColModuloLongColumn(col 0, col 1)(children: col 0) -> 20:long, DoubleColUnaryMinus(col 5) -> 18:double, LongColMultiplyLongColumn(col 3, col 21)(children: col 21) -> 22:long, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 24)(children: DoubleColAddDoubleColumn(col 5, col 23)(children: CastLongToDouble(col 1) -> 23:double) -> 24:double) -> 23:double, DoubleColUnaryMinus(col 24)(children: DoubleColUnaryMinus(col 5) -> 24:double) -> 25:double - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5461 Data size: 1174134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE 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/vectorization_11.q.out b/ql/src/test/results/clientpositive/vectorization_11.q.out index bc03170554..5c6c5893d8 100644 --- a/ql/src/test/results/clientpositive/vectorization_11.q.out +++ b/ql/src/test/results/clientpositive/vectorization_11.q.out @@ -52,7 +52,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringGroupColumn(col 7, col 6) -> boolean, FilterExprAndExpr(children: SelectColumnIsNull(col 8) -> boolean, FilterStringColLikeStringScalar(col 6, pattern %a) -> boolean) -> boolean) -> boolean predicate: ((cstring2 = cstring1) or (ctimestamp1 is null and (cstring1 like '%a'))) (type: boolean) - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), ctimestamp1 (type: timestamp), (-3728 * UDFToInteger(csmallint)) (type: int), (cdouble - 9763215.5639) (type: double), (- cdouble) (type: double), ((- cdouble) + 6981.0) (type: double), (cdouble * -5638.15) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -61,13 +61,13 @@ STAGE PLANS: native: true projectedOutputColumns: [6, 10, 5, 8, 12, 13, 14, 16, 15] selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 1)(children: col 1) -> 12:long, DoubleColSubtractDoubleScalar(col 5, val 9763215.5639) -> 13:double, DoubleColUnaryMinus(col 5) -> 14:double, DoubleColAddDoubleScalar(col 15, val 6981.0)(children: DoubleColUnaryMinus(col 5) -> 15:double) -> 16:double, DoubleColMultiplyDoubleScalar(col 5, val -5638.15) -> 15:double - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_12.q.out b/ql/src/test/results/clientpositive/vectorization_12.q.out index 63ea984a33..ac1e08aec8 100644 --- a/ql/src/test/results/clientpositive/vectorization_12.q.out +++ b/ql/src/test/results/clientpositive/vectorization_12.q.out @@ -87,7 +87,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNull(col 8) -> boolean, FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 10, col 11) -> boolean, FilterLongColNotEqualLongColumn(col 0, col 1)(children: col 0) -> boolean) -> boolean, FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6, pattern %a) -> boolean, FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 11, val 1) -> boolean, FilterLongColGreaterEqualLongColumn(col 3, col 1)(children: col 1) -> boolean) -> boolean) -> boolean) -> boolean predicate: (ctimestamp1 is null and ((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint))))) (type: boolean) - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cdouble (type: double), cstring1 (type: string), cboolean1 (type: boolean) outputColumnNames: cbigint, cdouble, cstring1, cboolean1 @@ -95,7 +95,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [3, 5, 6, 10] - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(cbigint), stddev_samp(cbigint), avg(cdouble), sum(cbigint), stddev_pop(cdouble) Group By Vectorization: @@ -110,7 +110,7 @@ STAGE PLANS: keys: cdouble (type: double), cbigint (type: bigint), cstring1 (type: string), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean) sort order: ++++ @@ -120,7 +120,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5006 Data size: 1076307 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col4 (type: bigint), _col5 (type: struct), _col6 (type: struct), _col7 (type: bigint), _col8 (type: struct) Execution mode: vectorized Map Vectorization: @@ -152,11 +152,11 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: bigint), KEY._col2 (type: string), KEY._col3 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col3 (type: boolean), _col2 (type: string), _col0 (type: double), (-6432.0 * _col0) (type: double), (- _col1) (type: bigint), _col4 (type: bigint), (_col1 * _col4) (type: bigint), _col5 (type: double), ((-6432.0 * _col0) / -6432.0) (type: double), (- ((-6432.0 * _col0) / -6432.0)) (type: double), _col6 (type: double), (- (-6432.0 * _col0)) (type: double), (-5638.15 + CAST( _col1 AS decimal(19,0))) (type: decimal(22,2)), _col7 (type: bigint), (_col6 / (-6432.0 * _col0)) (type: double), (- (- ((-6432.0 * _col0) / -6432.0))) (type: double), (((-6432.0 * _col0) / -6432.0) + (- (-6432.0 * _col0))) (type: double), _col8 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19 - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -179,7 +179,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: boolean), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(22,2)), _col14 (type: bigint), _col15 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double) Execution mode: vectorized Map Vectorization: @@ -203,10 +203,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: bigint), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: string), null (type: timestamp), KEY.reducesinkkey0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: bigint), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(22,2)), VALUE._col11 (type: bigint), VALUE._col12 (type: double), VALUE._col8 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_13.q.out b/ql/src/test/results/clientpositive/vectorization_13.q.out index 58529720dd..fc940f6f51 100644 --- a/ql/src/test/results/clientpositive/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/vectorization_13.q.out @@ -89,7 +89,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4, val 3569.0) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val 10.175, col 5) -> boolean, FilterLongColNotEqualLongScalar(col 10, val 1) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 12, val 11.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterDoubleColNotEqualDoubleScalar(col 12, val 12.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDecimalColLessDecimalScalar(col 13, val 9763215.5639)(children: CastLongToDecimal(col 0) -> 13:decimal(11,4)) -> boolean) -> boolean) -> boolean predicate: (((cfloat < 3569) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > 11.0) and (UDFToDouble(ctimestamp2) <> 12.0) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 @@ -97,7 +97,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 4, 6, 8, 10] - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) Group By Vectorization: @@ -112,7 +112,7 @@ STAGE PLANS: keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -122,7 +122,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -155,11 +155,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -182,7 +182,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -206,13 +206,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -423,7 +423,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4, val 3569.0) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val 10.175, col 5) -> boolean, FilterLongColNotEqualLongScalar(col 10, val 1) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 12, val -1.388)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterDoubleColNotEqualDoubleScalar(col 12, val -1.3359999999999999)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDecimalColLessDecimalScalar(col 13, val 9763215.5639)(children: CastLongToDecimal(col 0) -> 13:decimal(11,4)) -> boolean) -> boolean) -> boolean predicate: (((cfloat < 3569) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -1.388) and (UDFToDouble(ctimestamp2) <> -1.3359999999999999) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 @@ -431,7 +431,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 4, 6, 8, 10] - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) Group By Vectorization: @@ -446,7 +446,7 @@ STAGE PLANS: keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -456,7 +456,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -483,11 +483,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -510,7 +510,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -529,13 +529,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 8600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_14.q.out b/ql/src/test/results/clientpositive/vectorization_14.q.out index 536a2a1730..a73cb8dbd5 100644 --- a/ql/src/test/results/clientpositive/vectorization_14.q.out +++ b/ql/src/test/results/clientpositive/vectorization_14.q.out @@ -89,7 +89,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0, col 3)(children: col 0) -> boolean, FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 2) -> 12:double) -> boolean, FilterTimestampColLessTimestampColumn(col 9, col 8) -> boolean) -> boolean, FilterDoubleColLessDoubleColumn(col 5, col 12)(children: CastLongToDouble(col 0) -> 12:double) -> boolean, FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3, val -257) -> boolean, FilterDoubleColLessDoubleColumn(col 4, col 12)(children: CastLongToFloatViaLongToDouble(col 2) -> 12:double) -> boolean) -> boolean) -> boolean predicate: ((UDFToLong(ctinyint) <= cbigint) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1)) and (cdouble < UDFToDouble(ctinyint)) and ((cbigint > -257) or (cfloat < UDFToFloat(cint)))) (type: boolean) - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28 + cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 @@ -98,7 +98,7 @@ STAGE PLANS: native: true projectedOutputColumns: [8, 4, 6, 10, 5, 13] selectExpressions: DoubleColUnaryMinus(col 12)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5) -> 12:double) -> 13:double - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(_col5), max(_col1), stddev_pop(_col1), count(_col1), var_pop(_col1), var_samp(_col1) Group By Vectorization: @@ -113,7 +113,7 @@ STAGE PLANS: keys: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp), _col3 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ @@ -123,7 +123,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 606 Data size: 130292 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: struct), _col6 (type: float), _col7 (type: struct), _col8 (type: bigint), _col9 (type: struct), _col10 (type: struct) Execution mode: vectorized Map Vectorization: @@ -156,11 +156,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28 + _col2) (type: double), (- (-26.28 + _col2)) (type: double), _col5 (type: double), (_col1 * -26.28) (type: float), _col6 (type: float), (- _col1) (type: float), (- _col6) (type: float), ((- (-26.28 + _col2)) / 10.175) (type: double), _col7 (type: double), _col8 (type: bigint), (- ((- (-26.28 + _col2)) / 10.175)) (type: double), (-1.389 % _col5) (type: double), (UDFToDouble(_col1) - _col2) (type: double), _col9 (type: double), (_col9 % 10.175) (type: double), _col10 (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -183,7 +183,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) Execution mode: vectorized Map Vectorization: @@ -207,10 +207,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 303 Data size: 65146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_15.q.out b/ql/src/test/results/clientpositive/vectorization_15.q.out index 8eff856829..cd218e5e92 100644 --- a/ql/src/test/results/clientpositive/vectorization_15.q.out +++ b/ql/src/test/results/clientpositive/vectorization_15.q.out @@ -85,7 +85,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7, pattern %ss%) -> boolean, FilterStringColLikeStringScalar(col 6, pattern 10%) -> boolean, FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2, val -75) -> boolean, FilterLongColEqualLongColumn(col 0, col 1)(children: col 0) -> boolean, FilterDoubleColGreaterEqualDoubleScalar(col 5, val -3728.0) -> boolean) -> boolean) -> boolean predicate: ((cstring2 like '%ss%') or (cstring1 like '10%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) outputColumnNames: ctinyint, cint, cfloat, cdouble, cstring1, ctimestamp1, cboolean1 @@ -93,7 +93,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 2, 4, 5, 6, 8, 10] - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(cfloat), min(cdouble), stddev_samp(ctinyint), var_pop(ctinyint), var_samp(cint), stddev_pop(cint) Group By Vectorization: @@ -108,7 +108,7 @@ STAGE PLANS: keys: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) sort order: +++++++ @@ -118,7 +118,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: struct), _col8 (type: double), _col9 (type: struct), _col10 (type: struct), _col11 (type: struct), _col12 (type: struct) Execution mode: vectorized Map Vectorization: @@ -149,11 +149,11 @@ STAGE PLANS: keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), _col7 (type: double), (-26.28 - CAST( _col5 AS decimal(10,0))) (type: decimal(13,2)), _col8 (type: double), (_col2 * 79.553) (type: double), (33.0 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - CAST( _col5 AS decimal(10,0)))) (type: decimal(13,2)), _col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -176,7 +176,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: double), _col8 (type: decimal(13,2)), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: decimal(13,2)), _col20 (type: double) Execution mode: vectorized Map Vectorization: @@ -199,10 +199,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: decimal(13,2)), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: decimal(13,2)), VALUE._col13 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_16.q.out b/ql/src/test/results/clientpositive/vectorization_16.q.out index 7af0bbd40c..828df56857 100644 --- a/ql/src/test/results/clientpositive/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/vectorization_16.q.out @@ -62,7 +62,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7, pattern %b%) -> boolean, FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5, val -1.389) -> boolean, FilterStringGroupColLessStringScalar(col 6, val a) -> boolean) -> boolean) -> boolean predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) outputColumnNames: cdouble, cstring1, ctimestamp1 @@ -70,7 +70,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [5, 6, 8] - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) Group By Vectorization: @@ -85,7 +85,7 @@ STAGE PLANS: keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ @@ -95,7 +95,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized Map Vectorization: @@ -127,14 +127,14 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_17.q.out b/ql/src/test/results/clientpositive/vectorization_17.q.out index c0186082df..e3a1a16c11 100644 --- a/ql/src/test/results/clientpositive/vectorization_17.q.out +++ b/ql/src/test/results/clientpositive/vectorization_17.q.out @@ -70,7 +70,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3, val -23) -> boolean, FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5, val 988888.0) -> boolean, FilterDecimalColGreaterDecimalScalar(col 12, val -863.257)(children: CastLongToDecimal(col 2) -> 12:decimal(13,3)) -> boolean) -> boolean, FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0, val 33) -> boolean, FilterLongColGreaterEqualLongColumn(col 1, col 3)(children: col 1) -> boolean, FilterDoubleColEqualDoubleColumn(col 4, col 5)(children: col 4) -> boolean) -> boolean) -> boolean predicate: ((cbigint > -23) and ((cdouble <> 988888.0) or (CAST( cint AS decimal(13,3)) > -863.257)) and ((ctinyint >= 33) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble))) (type: boolean) - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58 + (- (- cdouble))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -79,7 +79,7 @@ STAGE PLANS: native: true projectedOutputColumns: [4, 6, 2, 8, 5, 3, 14, 15, 13, 16, 18, 19, 21, 17] selectExpressions: DoubleColDivideDoubleColumn(col 4, col 13)(children: col 4, CastLongToDouble(col 0) -> 13:double) -> 14:double, LongColModuloLongColumn(col 2, col 3)(children: col 2) -> 15:long, DoubleColUnaryMinus(col 5) -> 13:double, DoubleColAddDoubleColumn(col 5, col 17)(children: DoubleColDivideDoubleColumn(col 4, col 16)(children: col 4, CastLongToDouble(col 0) -> 16:double) -> 17:double) -> 16:double, DoubleColDivideDoubleColumn(col 5, col 17)(children: CastLongToDouble(col 2) -> 17:double) -> 18:double, DoubleColUnaryMinus(col 17)(children: DoubleColUnaryMinus(col 5) -> 17:double) -> 19:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 20)(children: CastLongToDecimal(col 3) -> 20:decimal(19,0)) -> 21:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 22)(children: DoubleColUnaryMinus(col 17)(children: DoubleColUnaryMinus(col 5) -> 17:double) -> 22:double) -> 17:double - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col5 (type: bigint), _col0 (type: float) sort order: ++ @@ -88,7 +88,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double) Execution mode: vectorized Map Vectorization: @@ -113,10 +113,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: float), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: timestamp), VALUE._col3 (type: double), KEY.reducesinkkey0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(11,4)), VALUE._col11 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_2.q.out b/ql/src/test/results/clientpositive/vectorization_2.q.out index 47ff8d48ba..16b6799952 100644 --- a/ql/src/test/results/clientpositive/vectorization_2.q.out +++ b/ql/src/test/results/clientpositive/vectorization_2.q.out @@ -68,7 +68,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterTimestampColLessTimestampColumn(col 8, col 9) -> boolean, FilterStringColLikeStringScalar(col 7, pattern b%) -> boolean, FilterDoubleColLessEqualDoubleScalar(col 4, val -5638.14990234375) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5, col 12)(children: CastLongToDouble(col 0) -> 12:double) -> boolean, FilterExprOrExpr(children: FilterDoubleScalarNotEqualDoubleColumn(val -10669.0, col 12)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterLongScalarGreaterLongColumn(val 359, col 2) -> boolean) -> boolean) -> boolean) -> boolean predicate: (((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15)) or ((cdouble < UDFToDouble(ctinyint)) and ((-10669.0 <> UDFToDouble(ctimestamp2)) or (359 > cint)))) (type: boolean) - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cbigint (type: bigint), cfloat (type: float), cdouble (type: double) outputColumnNames: ctinyint, csmallint, cbigint, cfloat, cdouble @@ -76,7 +76,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 3, 4, 5] - Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: avg(csmallint), sum(cfloat), var_pop(cbigint), count(), min(ctinyint), avg(cdouble) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/vectorization_3.q.out b/ql/src/test/results/clientpositive/vectorization_3.q.out index a730ca6f56..cb58940536 100644 --- a/ql/src/test/results/clientpositive/vectorization_3.q.out +++ b/ql/src/test/results/clientpositive/vectorization_3.q.out @@ -73,7 +73,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 12, col 4)(children: CastLongToFloatViaLongToDouble(col 2) -> 12:double) -> boolean, FilterDecimalScalarNotEqualDecimalColumn(val 79.553, col 13)(children: CastLongToDecimal(col 3) -> 13:decimal(22,3)) -> boolean, FilterDoubleColEqualDoubleScalar(col 12, val -29071.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 3) -> 12:double) -> boolean, FilterDecimalScalarLessEqualDecimalColumn(val 79.553, col 14)(children: CastLongToDecimal(col 1) -> 14:decimal(8,3)) -> boolean, FilterTimestampColGreaterTimestampColumn(col 8, col 9) -> boolean) -> boolean) -> boolean predicate: (((UDFToFloat(cint) <= cfloat) and (79.553 <> CAST( cbigint AS decimal(22,3))) and (UDFToDouble(ctimestamp2) = -29071.0)) or ((UDFToDouble(cbigint) > cdouble) and (79.553 <= CAST( csmallint AS decimal(8,3))) and (ctimestamp1 > ctimestamp2))) (type: boolean) - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cfloat (type: float) outputColumnNames: ctinyint, csmallint, cint, cfloat @@ -81,7 +81,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 4] - Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: stddev_samp(csmallint), stddev_pop(ctinyint), stddev_samp(cfloat), sum(cfloat), avg(cint), stddev_pop(cint) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/vectorization_4.q.out b/ql/src/test/results/clientpositive/vectorization_4.q.out index 0199d7db16..bbc026d28f 100644 --- a/ql/src/test/results/clientpositive/vectorization_4.q.out +++ b/ql/src/test/results/clientpositive/vectorization_4.q.out @@ -68,7 +68,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 1, col 2)(children: col 1) -> boolean, FilterExprAndExpr(children: FilterLongScalarGreaterEqualLongColumn(val -89010, col 0)(children: col 0) -> boolean, FilterDoubleColGreaterDoubleScalar(col 5, val 79.553) -> boolean) -> boolean, FilterExprAndExpr(children: FilterLongScalarNotEqualLongColumn(val -563, col 3) -> boolean, FilterExprOrExpr(children: FilterLongColNotEqualLongColumn(col 0, col 3)(children: col 0) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val -3728.0, col 5) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((UDFToInteger(csmallint) >= cint) or ((-89010 >= UDFToInteger(ctinyint)) and (cdouble > 79.553)) or ((-563 <> cbigint) and ((UDFToLong(ctinyint) <> cbigint) or (-3728.0 >= cdouble)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), cdouble (type: double) outputColumnNames: ctinyint, cint, cdouble @@ -76,7 +76,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 2, 5] - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(cint), stddev_pop(cdouble), avg(cdouble), var_pop(cdouble), min(ctinyint) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/vectorization_5.q.out b/ql/src/test/results/clientpositive/vectorization_5.q.out index 33707c7006..be30a30ab6 100644 --- a/ql/src/test/results/clientpositive/vectorization_5.q.out +++ b/ql/src/test/results/clientpositive/vectorization_5.q.out @@ -62,7 +62,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 11) -> boolean, FilterStringColLikeStringScalar(col 6, pattern %b%) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColEqualDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 0) -> 12:double) -> boolean, SelectColumnIsNotNull(col 9) -> boolean, FilterStringColLikeStringScalar(col 7, pattern a) -> boolean) -> boolean) -> boolean predicate: ((cboolean2 is not null and (cstring1 like '%b%')) or ((UDFToDouble(ctinyint) = cdouble) and ctimestamp2 is not null and (cstring2 like 'a'))) (type: boolean) - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int) outputColumnNames: ctinyint, csmallint, cint @@ -70,7 +70,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2] - Statistics: Num rows: 9216 Data size: 1981473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(csmallint), count(), min(csmallint), sum(cint), max(ctinyint) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/vectorization_6.q.out b/ql/src/test/results/clientpositive/vectorization_6.q.out index 9f3da46212..85d688a046 100644 --- a/ql/src/test/results/clientpositive/vectorization_6.q.out +++ b/ql/src/test/results/clientpositive/vectorization_6.q.out @@ -64,7 +64,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0, val 0) -> boolean, FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 10, val 0) -> boolean, FilterLongColGreaterEqualLongColumn(col 11, col 10) -> boolean) -> boolean, FilterExprAndExpr(children: SelectColumnIsNotNull(col 3) -> boolean, FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7, pattern %a) -> boolean, FilterDoubleColLessEqualDoubleScalar(col 4, val -257.0) -> boolean) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((ctinyint <> 0) and (((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (cbigint is not null and ((cstring2 like '%a') or (cfloat <= -257))))) (type: boolean) - Statistics: Num rows: 11605 Data size: 2495116 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cstring1 (type: string), (988888 * UDFToInteger(csmallint)) (type: int), (- csmallint) (type: smallint), (- cfloat) (type: float), (-26.28 / UDFToDouble(cfloat)) (type: double), (cfloat * 359.0) (type: float), (cint % UDFToInteger(ctinyint)) (type: int), (- cdouble) (type: double), (UDFToInteger(ctinyint) - -75) (type: int), (762 * (cint % UDFToInteger(ctinyint))) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 @@ -73,13 +73,13 @@ STAGE PLANS: native: true projectedOutputColumns: [10, 4, 6, 12, 13, 14, 15, 16, 17, 18, 19, 21] selectExpressions: LongScalarMultiplyLongColumn(val 988888, col 1)(children: col 1) -> 12:long, LongColUnaryMinus(col 1) -> 13:long, DoubleColUnaryMinus(col 4) -> 14:double, DoubleScalarDivideDoubleColumn(val -26.28, col 4)(children: col 4) -> 15:double, DoubleColMultiplyDoubleScalar(col 4, val 359.0) -> 16:double, LongColModuloLongColumn(col 2, col 0)(children: col 0) -> 17:long, DoubleColUnaryMinus(col 5) -> 18:double, LongColSubtractLongScalar(col 0, val -75)(children: col 0) -> 19:long, LongScalarMultiplyLongColumn(val 762, col 20)(children: LongColModuloLongColumn(col 2, col 0)(children: col 0) -> 20:long) -> 21:long - Statistics: Num rows: 11605 Data size: 2495116 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 11605 Data size: 2495116 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 430 Basic stats: COMPLETE Column stats: NONE 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/vectorization_7.q.out b/ql/src/test/results/clientpositive/vectorization_7.q.out index 218d307915..806ae2be95 100644 --- a/ql/src/test/results/clientpositive/vectorization_7.q.out +++ b/ql/src/test/results/clientpositive/vectorization_7.q.out @@ -76,7 +76,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0, val 0) -> boolean, FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 12, val 0.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterLongColEqualLongColumn(col 0, col 2)(children: col 0) -> boolean, FilterStringColLikeStringScalar(col 7, pattern ss) -> boolean) -> boolean, FilterExprOrExpr(children: FilterDoubleScalarLessDoubleColumn(val 988888.0, col 5) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 12, val -15.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val 3569.0, col 5) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > -15.0) and (3569.0 >= cdouble)))) (type: boolean) - Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -85,7 +85,7 @@ STAGE PLANS: native: true projectedOutputColumns: [10, 3, 1, 0, 8, 6, 13, 14, 15, 16, 18, 19, 17, 20, 22] selectExpressions: LongColAddLongColumn(col 3, col 3) -> 13:long, LongColModuloLongScalar(col 1, val -257)(children: col 1) -> 14:long, LongColUnaryMinus(col 1) -> 15:long, LongColUnaryMinus(col 0) -> 16:long, LongColAddLongScalar(col 17, val 17)(children: col 17) -> 18:long, LongColMultiplyLongColumn(col 3, col 17)(children: col 17) -> 19:long, LongColModuloLongColumn(col 2, col 1)(children: col 1) -> 17:long, LongColUnaryMinus(col 0) -> 20:long, LongColModuloLongColumn(col 21, col 0)(children: LongColUnaryMinus(col 0) -> 21:long) -> 22:long - Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -94,7 +94,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -119,13 +119,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -296,7 +296,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0, val 0) -> boolean, FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 12, val 0.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterLongColEqualLongColumn(col 0, col 2)(children: col 0) -> boolean, FilterStringColLikeStringScalar(col 7, pattern ss) -> boolean) -> boolean, FilterExprOrExpr(children: FilterDoubleScalarLessDoubleColumn(val 988888.0, col 5) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 12, val 7.6850000000000005)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDoubleScalarGreaterEqualDoubleColumn(val 3569.0, col 5) -> boolean) -> boolean) -> boolean) -> boolean predicate: ((ctinyint <> 0) and ((UDFToDouble(ctimestamp1) <= 0.0) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((988888.0 < cdouble) or ((UDFToDouble(ctimestamp2) > 7.6850000000000005) and (3569.0 >= cdouble)))) (type: boolean) - Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -305,7 +305,7 @@ STAGE PLANS: native: true projectedOutputColumns: [10, 3, 1, 0, 8, 6, 13, 14, 15, 16, 18, 19, 17, 20, 22] selectExpressions: LongColAddLongColumn(col 3, col 3) -> 13:long, LongColModuloLongScalar(col 1, val -257)(children: col 1) -> 14:long, LongColUnaryMinus(col 1) -> 15:long, LongColUnaryMinus(col 0) -> 16:long, LongColAddLongScalar(col 17, val 17)(children: col 17) -> 18:long, LongColMultiplyLongColumn(col 3, col 17)(children: col 17) -> 19:long, LongColModuloLongColumn(col 2, col 1)(children: col 1) -> 17:long, LongColUnaryMinus(col 0) -> 20:long, LongColModuloLongColumn(col 21, col 0)(children: LongColUnaryMinus(col 0) -> 21:long) -> 22:long - Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -314,7 +314,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -333,13 +333,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 7281 Data size: 1565441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorization_9.q.out b/ql/src/test/results/clientpositive/vectorization_9.q.out index 7af0bbd40c..828df56857 100644 --- a/ql/src/test/results/clientpositive/vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/vectorization_9.q.out @@ -62,7 +62,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7, pattern %b%) -> boolean, FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5, val -1.389) -> boolean, FilterStringGroupColLessStringScalar(col 6, val a) -> boolean) -> boolean) -> boolean predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) outputColumnNames: cdouble, cstring1, ctimestamp1 @@ -70,7 +70,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumns: [5, 6, 8] - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) Group By Vectorization: @@ -85,7 +85,7 @@ STAGE PLANS: keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ @@ -95,7 +95,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized Map Vectorization: @@ -127,14 +127,14 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE 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/vectorized_case.q.out b/ql/src/test/results/clientpositive/vectorized_case.q.out index 0a2e803670..ee430259af 100644 --- a/ql/src/test/results/clientpositive/vectorized_case.q.out +++ b/ql/src/test/results/clientpositive/vectorized_case.q.out @@ -58,7 +58,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1, val 418) -> boolean, FilterLongColEqualLongScalar(col 1, val 12205) -> boolean, FilterLongColEqualLongScalar(col 1, val 10583) -> boolean) -> boolean predicate: ((csmallint = 418) or (csmallint = 12205) or (csmallint = 10583)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 @@ -67,13 +67,13 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 15, 16] selectExpressions: IfExprStringScalarStringGroupColumn(col 12, val a, col 14)(children: LongColEqualLongScalar(col 1, val 418) -> 12:long, IfExprStringScalarStringScalar(col 13, val b, val c)(children: LongColEqualLongScalar(col 1, val 12205) -> 13:long) -> 14:String) -> 15:String, IfExprStringScalarStringGroupColumn(col 12, val a, col 14)(children: LongColEqualLongScalar(col 1, val 418) -> 12:long, IfExprStringScalarStringScalar(col 13, val b, val c)(children: LongColEqualLongScalar(col 1, val 12205) -> 13:long) -> 14:String) -> 16:String - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -196,7 +196,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 1, val 418) -> boolean, FilterLongColEqualLongScalar(col 1, val 12205) -> boolean, FilterLongColEqualLongScalar(col 1, val 10583) -> boolean) -> boolean predicate: ((csmallint = 418) or (csmallint = 12205) or (csmallint = 10583)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE (null) END (type: string), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN (null) ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 @@ -205,13 +205,13 @@ STAGE PLANS: native: true projectedOutputColumns: [1, 16, 19] selectExpressions: IfExprStringScalarStringGroupColumn(col 12, val a, col 15)(children: LongColEqualLongScalar(col 1, val 418) -> 12:long, IfExprColumnNull(col 13, col 14, null)(children: LongColEqualLongScalar(col 1, val 12205) -> 13:long, ConstantVectorExpression(val b) -> 14:string) -> 15:string) -> 16:String, IfExprStringScalarStringGroupColumn(col 12, val a, col 18)(children: LongColEqualLongScalar(col 1, val 418) -> 12:long, IfExprNullColumn(col 17, null, col 15)(children: LongColEqualLongScalar(col 1, val 12205) -> 17:long, ConstantVectorExpression(val c) -> 15:string) -> 18:string) -> 19:String - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 215 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat