diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HivePlannerContext.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HivePlannerContext.java index d0b1757a82..bdf995548f 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HivePlannerContext.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HivePlannerContext.java @@ -22,6 +22,7 @@ import org.apache.calcite.rel.RelNode; import org.apache.hadoop.hive.ql.optimizer.calcite.cost.HiveAlgorithmsConf; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveRulesRegistry; + import java.util.Set; @@ -29,17 +30,18 @@ private HiveAlgorithmsConf algoConfig; private HiveRulesRegistry registry; private CalciteConnectionConfig calciteConfig; - private Set corrScalarRexSQWithAgg; + private SubqueryConf subqueryConfig; public HivePlannerContext(HiveAlgorithmsConf algoConfig, HiveRulesRegistry registry, - CalciteConnectionConfig calciteConfig, Set corrScalarRexSQWithAgg) { + CalciteConnectionConfig calciteConfig, Set corrScalarRexSQWithAgg, + Set scalarAggNoGbyWindowing) { this.algoConfig = algoConfig; this.registry = registry; this.calciteConfig = calciteConfig; // this is to keep track if a subquery is correlated and contains aggregate // this is computed in CalcitePlanner while planning and is later required by subuery remove rule // hence this is passed using HivePlannerContext - this.corrScalarRexSQWithAgg = corrScalarRexSQWithAgg; + this.subqueryConfig = new SubqueryConf(corrScalarRexSQWithAgg, scalarAggNoGbyWindowing); } public T unwrap(Class clazz) { @@ -52,8 +54,8 @@ public HivePlannerContext(HiveAlgorithmsConf algoConfig, HiveRulesRegistry regis if (clazz.isInstance(calciteConfig)) { return clazz.cast(calciteConfig); } - if(clazz.isInstance(corrScalarRexSQWithAgg)) { - return clazz.cast(corrScalarRexSQWithAgg); + if(clazz.isInstance(subqueryConfig)) { + return clazz.cast(subqueryConfig); } return null; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/SubqueryConf.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/SubqueryConf.java new file mode 100644 index 0000000000..ce608b0063 --- /dev/null +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/SubqueryConf.java @@ -0,0 +1,42 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.hadoop.hive.ql.optimizer.calcite; + +import org.apache.calcite.rel.RelNode; + +import java.util.Set; + +public class SubqueryConf{ + + private Set corrScalarRexSQWithAgg; + private Set scalarAggWithoutGbyWindowing; + + + public SubqueryConf(Set corrScalarRexSQWithAgg, + Set scalarAggWithoutGbyWindowing) { + this.corrScalarRexSQWithAgg = corrScalarRexSQWithAgg; + this.scalarAggWithoutGbyWindowing = scalarAggWithoutGbyWindowing; + } + + public Set getCorrScalarRexSQWithAgg() { + return corrScalarRexSQWithAgg; + } + public Set getScalarAggWithoutGbyWindowing() { + return scalarAggWithoutGbyWindowing; + } +} diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSubQueryRemoveRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSubQueryRemoveRule.java index c692cc0d4c..83d3f7436d 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSubQueryRemoveRule.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSubQueryRemoveRule.java @@ -56,6 +56,7 @@ import org.apache.hadoop.hive.ql.optimizer.calcite.HiveRelFactories; import org.apache.hadoop.hive.ql.optimizer.calcite.HiveSubQRemoveRelBuilder; +import org.apache.hadoop.hive.ql.optimizer.calcite.SubqueryConf; import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveFilter; /** @@ -99,11 +100,12 @@ public void onMatch(RelOptRuleCall call) { final int fieldCount = builder.peek().getRowType().getFieldCount(); assert(filter instanceof HiveFilter); - Set corrScalarQueries = filter.getCluster().getPlanner().getContext().unwrap(Set.class); - boolean isCorrScalarQuery = corrScalarQueries.contains(e.rel); + SubqueryConf subqueryConfig = filter.getCluster().getPlanner().getContext().unwrap(SubqueryConf.class); + boolean isCorrScalarQuery = subqueryConfig.getCorrScalarRexSQWithAgg().contains(e.rel); + boolean hasNoWindowingAndNoGby = subqueryConfig.getScalarAggWithoutGbyWindowing().contains(e.rel); final RexNode target = apply(e, HiveFilter.getVariablesSet(e), logic, - builder, 1, fieldCount, isCorrScalarQuery); + builder, 1, fieldCount, isCorrScalarQuery, hasNoWindowingAndNoGby); final RexShuttle shuttle = new ReplaceSubQueryShuttle(e, target); builder.filter(shuttle.apply(filter.getCondition())); builder.project(fields(builder, filter.getRowType().getFieldCount())); @@ -122,11 +124,12 @@ else if(relNode instanceof Project) { builder.push(project.getInput()); final int fieldCount = builder.peek().getRowType().getFieldCount(); - Set corrScalarQueries = project.getCluster().getPlanner().getContext().unwrap(Set.class); - boolean isCorrScalarQuery = corrScalarQueries.contains(e.rel); + SubqueryConf subqueryConfig = project.getCluster().getPlanner().getContext().unwrap(SubqueryConf.class); + boolean isCorrScalarQuery = subqueryConfig.getCorrScalarRexSQWithAgg().contains(e.rel); + boolean hasNoWindowingAndNoGby = subqueryConfig.getScalarAggWithoutGbyWindowing().contains(e.rel); final RexNode target = apply(e, HiveFilter.getVariablesSet(e), - logic, builder, 1, fieldCount, isCorrScalarQuery); + logic, builder, 1, fieldCount, isCorrScalarQuery, hasNoWindowingAndNoGby); final RexShuttle shuttle = new ReplaceSubQueryShuttle(e, target); builder.project(shuttle.apply(project.getProjects()), project.getRowType().getFieldNames()); @@ -165,28 +168,32 @@ private SqlTypeName getAggTypeForScalarSub(RexSubQuery e) { protected RexNode apply(RexSubQuery e, Set variablesSet, RelOptUtil.Logic logic, HiveSubQRemoveRelBuilder builder, int inputCount, int offset, - boolean isCorrScalarAgg) { + boolean isCorrScalarAgg, + boolean hasNoWindowingAndNoGby ) { switch (e.getKind()) { case SCALAR_QUERY: - builder.push(e.rel); - // returns single row/column - builder.aggregate(builder.groupKey(), - builder.count(false, "cnt")); - - SqlFunction countCheck = new SqlFunction("sq_count_check", SqlKind.OTHER_FUNCTION, ReturnTypes.BIGINT, - InferTypes.RETURN_TYPE, OperandTypes.NUMERIC, SqlFunctionCategory.USER_DEFINED_FUNCTION); - - // we create FILTER (sq_count_check(count()) <= 1) instead of PROJECT because RelFieldTrimmer - // ends up getting rid of Project since it is not used further up the tree - builder.filter(builder.call(SqlStdOperatorTable.LESS_THAN_OR_EQUAL, - builder.call(countCheck, builder.field("cnt")), - builder.literal(1))); - if( !variablesSet.isEmpty()) - { - builder.join(JoinRelType.LEFT, builder.literal(true), variablesSet); + // if scalar query has aggregate and no windowing and no gby avoid adding sq_count_check + // since it is guaranteed to produce at most one row + if(!hasNoWindowingAndNoGby) { + builder.push(e.rel); + // returns single row/column + builder.aggregate(builder.groupKey(), builder.count(false, "cnt")); + + SqlFunction countCheck = + new SqlFunction("sq_count_check", SqlKind.OTHER_FUNCTION, ReturnTypes.BIGINT, + InferTypes.RETURN_TYPE, OperandTypes.NUMERIC, SqlFunctionCategory.USER_DEFINED_FUNCTION); + + // we create FILTER (sq_count_check(count()) <= 1) instead of PROJECT because RelFieldTrimmer + // ends up getting rid of Project since it is not used further up the tree + builder.filter(builder.call(SqlStdOperatorTable.LESS_THAN_OR_EQUAL, + builder.call(countCheck, builder.field("cnt")), builder.literal(1))); + if (!variablesSet.isEmpty()) { + builder.join(JoinRelType.LEFT, builder.literal(true), variablesSet); + } else + builder.join(JoinRelType.INNER, builder.literal(true), variablesSet); + + offset++; } - else - builder.join(JoinRelType.INNER, builder.literal(true), variablesSet); if(isCorrScalarAgg) { // Transformation : // Outer Query Left Join (inner query) on correlated predicate and preserve rows only from left side. @@ -218,10 +225,8 @@ protected RexNode apply(RexSubQuery e, Set variablesSet, //Transformation is to left join for correlated predicates and inner join otherwise, // but do a count on inner side before that to make sure it generates atmost 1 row. - builder.push(e.rel); builder.join(JoinRelType.LEFT, builder.literal(true), variablesSet); - offset++; return field(builder, inputCount, offset); case IN: diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java index 5d640be914..fa96e94f64 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java @@ -1299,6 +1299,7 @@ private RowResolver genRowResolver(Operator op, QB qb) { // this is to keep track if a subquery is correlated and contains aggregate // since this is special cased when it is rewritten in SubqueryRemoveRule Set corrScalarRexSQWithAgg = new HashSet(); + Set scalarAggNoGbyNoWin = new HashSet(); // TODO: Do we need to keep track of RR, ColNameToPosMap for every op or // just last one. @@ -1332,7 +1333,7 @@ public RelNode apply(RelOptCluster cluster, RelOptSchema relOptSchema, SchemaPlu Boolean.FALSE.toString()); CalciteConnectionConfig calciteConfig = new CalciteConnectionConfigImpl(calciteConfigProperties); HivePlannerContext confContext = new HivePlannerContext(algorithmsConf, registry, calciteConfig, - corrScalarRexSQWithAgg); + corrScalarRexSQWithAgg, scalarAggNoGbyNoWin); RelOptPlanner planner = HiveVolcanoPlanner.createPlanner(confContext); final RexBuilder rexBuilder = cluster.getRexBuilder(); final RelOptCluster optCluster = RelOptCluster.create(planner, rexBuilder); @@ -2425,8 +2426,8 @@ private RelNode genFilterRelNode(ASTNode filterExpr, RelNode srcRel, } private void subqueryRestrictionCheck(QB qb, ASTNode searchCond, RelNode srcRel, - boolean forHavingClause, - Set corrScalarQueries) throws SemanticException { + boolean forHavingClause, Set corrScalarQueries, + Set scalarQueriesWithAggNoWinNoGby) throws SemanticException { List subQueriesInOriginalTree = SubQueryUtils.findSubQueries(searchCond); ASTNode clonedSearchCond = (ASTNode) SubQueryUtils.adaptor.dupTree(searchCond); @@ -2461,18 +2462,25 @@ private void subqueryRestrictionCheck(QB qb, ASTNode searchCond, RelNode srcRel, String havingInputAlias = null; - boolean isCorrScalarWithAgg = subQuery.subqueryRestrictionsCheck(inputRR, forHavingClause, havingInputAlias); - if(isCorrScalarWithAgg) { + boolean [] subqueryConfig = {false, false}; + subQuery.subqueryRestrictionsCheck(inputRR, forHavingClause, + havingInputAlias, subqueryConfig); + if(subqueryConfig[0]) { corrScalarQueries.add(originalSubQueryAST); } + if(subqueryConfig[1]) { + scalarQueriesWithAggNoWinNoGby.add(originalSubQueryAST); + } } } private boolean genSubQueryRelNode(QB qb, ASTNode node, RelNode srcRel, boolean forHavingClause, Map subQueryToRelNode) throws SemanticException { Set corrScalarQueriesWithAgg = new HashSet(); + Set scalarQueriesWithAggNoWinNoGby= new HashSet(); //disallow subqueries which HIVE doesn't currently support - subqueryRestrictionCheck(qb, node, srcRel, forHavingClause, corrScalarQueriesWithAgg); + subqueryRestrictionCheck(qb, node, srcRel, forHavingClause, corrScalarQueriesWithAgg, + scalarQueriesWithAggNoWinNoGby); Deque stack = new ArrayDeque(); stack.push(node); @@ -2502,9 +2510,14 @@ private boolean genSubQueryRelNode(QB qb, ASTNode node, RelNode srcRel, boolean subQueryToRelNode.put(next, subQueryRelNode); //keep track of subqueries which are scalar, correlated and contains aggregate // subquery expression. This will later be special cased in Subquery remove rule + // for correlated scalar queries with aggregate we have take care of the case where + // inner aggregate happens on empty result if(corrScalarQueriesWithAgg.contains(next)) { corrScalarRexSQWithAgg.add(subQueryRelNode); } + if(scalarQueriesWithAggNoWinNoGby.contains(next)) { + scalarAggNoGbyNoWin.add(subQueryRelNode); + } isSubQuery = true; break; default: diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/QBSubQuery.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/QBSubQuery.java index ec527410e6..0097a04ccd 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/QBSubQuery.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/QBSubQuery.java @@ -526,9 +526,9 @@ public ASTNode getOriginalSubQueryASTForRewrite() { * @return true if it is correlated scalar subquery with an aggregate * @throws SemanticException */ - boolean subqueryRestrictionsCheck(RowResolver parentQueryRR, + void subqueryRestrictionsCheck(RowResolver parentQueryRR, boolean forHavingClause, - String outerQueryAlias) + String outerQueryAlias, boolean [] subqueryConfig) throws SemanticException { ASTNode insertClause = getChildFromSubqueryAST("Insert", HiveParser.TOK_INSERT); @@ -568,37 +568,35 @@ boolean subqueryRestrictionsCheck(RowResolver parentQueryRR, hasCount = hasCount | ( r == 2 ); } - - - ASTNode whereClause = SubQueryUtils.subQueryWhere(insertClause); - - if ( whereClause == null ) { - return false; - } - ASTNode searchCond = (ASTNode) whereClause.getChild(0); - List conjuncts = new ArrayList(); - SubQueryUtils.extractConjuncts(searchCond, conjuncts); - - ConjunctAnalyzer conjunctAnalyzer = new ConjunctAnalyzer(parentQueryRR, - forHavingClause, outerQueryAlias); - + // figure out correlation and presence of non-equi join predicate boolean hasCorrelation = false; boolean hasNonEquiJoinPred = false; - for(ASTNode conjunctAST : conjuncts) { - Conjunct conjunct = conjunctAnalyzer.analyzeConjunct(conjunctAST); - if(conjunct.isCorrelated()){ - hasCorrelation = true; - } - if ( conjunct.eitherSideRefersBoth() && conjunctAST.getType() != HiveParser.EQUAL) { - hasNonEquiJoinPred = true; + + ASTNode whereClause = SubQueryUtils.subQueryWhere(insertClause); + if ( whereClause != null ) { + ASTNode searchCond = (ASTNode) whereClause.getChild(0); + List conjuncts = new ArrayList(); + SubQueryUtils.extractConjuncts(searchCond, conjuncts); + + ConjunctAnalyzer conjunctAnalyzer = + new ConjunctAnalyzer(parentQueryRR, forHavingClause, outerQueryAlias); + + for (ASTNode conjunctAST : conjuncts) { + Conjunct conjunct = conjunctAnalyzer.analyzeConjunct(conjunctAST); + if (conjunct.isCorrelated()) { + hasCorrelation = true; + } + if (conjunct.eitherSideRefersBoth() && conjunctAST.getType() != HiveParser.EQUAL) { + hasNonEquiJoinPred = true; + } } } + + // figure out if there is group by boolean noImplicityGby = true; - if ( insertClause.getChild(1).getChildCount() > 3 && - insertClause.getChild(1).getChild(3).getType() == HiveParser.TOK_GROUPBY ) { - if((ASTNode) insertClause.getChild(1).getChild(3) != null){ + if ( insertClause.getChildCount() > 3 && + insertClause.getChild(3).getType() == HiveParser.TOK_GROUPBY ) { noImplicityGby = false; - } } /* @@ -643,22 +641,24 @@ else if(operator.getType() == SubQueryType.SCALAR) { subQueryAST, "Scalar subqueries with aggregate cannot have non-equi join predicate")); } + if(!hasWindowing) { + subqueryConfig[1] = true; + } if(hasCorrelation) { - return true; + subqueryConfig[0] = true; } } else if(operator.getType() == SubQueryType.IN) { if(hasCount && hasCorrelation) { - return true; + subqueryConfig[0] = true; } } else if (operator.getType() == SubQueryType.NOT_IN) { if(hasCorrelation) { - return true; + subqueryConfig[0] = true; } } } - return false; } void validateAndRewriteAST(RowResolver outerQueryRR, diff --git a/ql/src/test/org/apache/hadoop/hive/ql/optimizer/calcite/TestCBORuleFiredOnlyOnce.java b/ql/src/test/org/apache/hadoop/hive/ql/optimizer/calcite/TestCBORuleFiredOnlyOnce.java index 4823950e9f..884e034731 100644 --- a/ql/src/test/org/apache/hadoop/hive/ql/optimizer/calcite/TestCBORuleFiredOnlyOnce.java +++ b/ql/src/test/org/apache/hadoop/hive/ql/optimizer/calcite/TestCBORuleFiredOnlyOnce.java @@ -61,7 +61,8 @@ public void testRuleFiredOnlyOnce() { // Create rules registry to not trigger a rule more than once HiveRulesRegistry registry = new HiveRulesRegistry(); - HivePlannerContext context = new HivePlannerContext(null, registry, null, null); + HivePlannerContext context = new HivePlannerContext(null, registry, null, + null, null); HepPlanner planner = new HepPlanner(programBuilder.build(), context); // Cluster diff --git a/ql/src/test/queries/clientnegative/subquery_scalar_corr_multi_rows.q b/ql/src/test/queries/clientnegative/subquery_scalar_corr_multi_rows.q index e9ea703466..e71a60d662 100644 --- a/ql/src/test/queries/clientnegative/subquery_scalar_corr_multi_rows.q +++ b/ql/src/test/queries/clientnegative/subquery_scalar_corr_multi_rows.q @@ -1,2 +1,3 @@ -- inner query produces more than one row -select * from part where p_size > (select count(*) from part p where p.p_mfgr = part.p_mfgr group by p_type); \ No newline at end of file +select * from part where p_size > + (select count(*) from part p where p.p_mfgr = part.p_mfgr group by p_type); \ No newline at end of file diff --git a/ql/src/test/results/clientnegative/subquery_scalar_corr_multi_rows.q.out b/ql/src/test/results/clientnegative/subquery_scalar_corr_multi_rows.q.out index 3235048f74..8377085e27 100644 --- a/ql/src/test/results/clientnegative/subquery_scalar_corr_multi_rows.q.out +++ b/ql/src/test/results/clientnegative/subquery_scalar_corr_multi_rows.q.out @@ -1,4 +1,5 @@ -PREHOOK: query: select * from part where p_size > (select count(*) from part p where p.p_mfgr = part.p_mfgr group by p_type) +PREHOOK: query: select * from part where p_size > + (select count(*) from part p where p.p_mfgr = part.p_mfgr group by p_type) PREHOOK: type: QUERY PREHOOK: Input: default@part #### A masked pattern was here #### 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 b2b5458c00..c8524df614 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out @@ -75,7 +75,7 @@ POSTHOOK: Lineage: part_null.p_partkey EXPRESSION [(values__tmp__table__2)values POSTHOOK: Lineage: part_null.p_retailprice EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col8, type:string, comment:), ] POSTHOOK: Lineage: part_null.p_size EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col6, type:string, comment:), ] POSTHOOK: Lineage: part_null.p_type SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col5, type:string, comment:), ] -Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select * from part where p_size > (select avg(p_size) from part_null) PREHOOK: type: QUERY POSTHOOK: query: explain select * from part where p_size > (select avg(p_size) from part_null) @@ -89,9 +89,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -115,26 +114,6 @@ STAGE PLANS: alias: part_null Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: part_null - Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Select Operator expressions: p_size (type: int) outputColumnNames: p_size Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE @@ -155,23 +134,21 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 1 - 2 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 - Statistics: Num rows: 26 Data size: 18304 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 26 Data size: 18096 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(_col5) > _col10) (type: boolean) - Statistics: Num rows: 8 Data size: 5632 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(_col5) > _col9) (type: boolean) + Statistics: Num rows: 8 Data size: 5568 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: 5632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 5568 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 5632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 5568 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -180,29 +157,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: avg(VALUE._col0) mode: mergepartial outputColumnNames: _col0 @@ -218,7 +172,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select * from part where p_size > (select avg(p_size) from part_null) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -698,7 +652,7 @@ POSTHOOK: Input: default@tnull 85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull 86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully 90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl -Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select * from part where (select max(p_name) from part_null) is not null PREHOOK: type: QUERY POSTHOOK: query: explain select * from part where (select max(p_name) from part_null) is not null @@ -712,9 +666,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -736,26 +689,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_null - Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: part_null Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_name (type: string) @@ -778,16 +711,14 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 1 - 2 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 21112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 20904 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 21112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 20904 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -796,29 +727,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 @@ -838,7 +746,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select * from part where (select max(p_name) from part_null) is not null PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -875,10 +783,8 @@ POSTHOOK: Input: default@part_null 85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull 86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully 90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl -Warning: Shuffle Join MERGEJOIN[57][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[58][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[59][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product -Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[24][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain select * from part where p_size between (select min(p_size) from part) and (select avg(p_size) from part) PREHOOK: type: QUERY POSTHOOK: query: explain select * from part where p_size between (select min(p_size) from part) and (select avg(p_size) from part) @@ -892,14 +798,10 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) - Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE) - Reducer 4 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE) Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) - Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -917,27 +819,27 @@ STAGE PLANS: 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) Execution mode: llap LLAP IO: no inputs - Map 10 + Map 4 Map Operator Tree: TableScan alias: part Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey + expressions: p_size (type: int) + outputColumnNames: p_size Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(p_partkey) + aggregations: min(p_size) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 12 + Map 6 Map Operator Tree: TableScan alias: part @@ -957,127 +859,22 @@ STAGE PLANS: value expressions: _col0 (type: struct) Execution mode: llap LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 8 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_size (type: int) - outputColumnNames: p_size - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: min(p_size) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: llap - LLAP IO: no inputs - Reducer 11 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 13 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: avg(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double) Reducer 2 Execution mode: llap Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE - 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 - Reduce Operator Tree: - Merge Join Operator - condition map: Left Outer Join0 to 1 keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 - Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE - 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), _col10 (type: int) - Reducer 4 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE - 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), _col10 (type: int) - Reducer 5 + 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), _col9 (type: int) + Reducer 3 Execution mode: llap Reduce Operator Tree: Merge Join Operator @@ -1086,10 +883,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col12 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 26 Data size: 16406 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: UDFToDouble(_col5) BETWEEN UDFToDouble(_col10) AND _col12 (type: boolean) + predicate: UDFToDouble(_col5) BETWEEN UDFToDouble(_col9) AND _col10 (type: boolean) Statistics: Num rows: 2 Data size: 1262 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) @@ -1102,41 +899,30 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 7 + Reducer 5 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) + aggregations: min(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 9 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Reducer 7 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0) + aggregations: avg(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double) Stage: Stage-0 Fetch Operator @@ -1144,10 +930,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[57][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[58][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[59][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product -Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[24][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product PREHOOK: query: select * from part where p_size between (select min(p_size) from part) and (select avg(p_size) from part) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -1426,7 +1210,7 @@ Manufacturer#5 almond antique medium spring khaki 6 Manufacturer#5 almond antique sky peru orange 2 Manufacturer#5 almond aquamarine dodger light gainsboro 46 Manufacturer#5 almond azure blanched chiffon midnight 23 -Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select * from part where (p_partkey*p_size) <> (select min(p_partkey) from part) PREHOOK: type: QUERY POSTHOOK: query: explain select * from part where (p_partkey*p_size) <> (select min(p_partkey) from part) @@ -1440,9 +1224,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1470,26 +1253,6 @@ STAGE PLANS: outputColumnNames: p_partkey Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator aggregations: min(p_partkey) mode: hash outputColumnNames: _col0 @@ -1506,15 +1269,13 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 1 - 2 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((_col0 * _col5) <> _col10) (type: boolean) + predicate: ((_col0 * _col5) <> _col9) (type: boolean) Statistics: Num rows: 26 Data size: 16198 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) @@ -1531,29 +1292,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: min(VALUE._col0) mode: mergepartial outputColumnNames: _col0 @@ -1569,7 +1307,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select * from part where (p_partkey*p_size) <> (select min(p_partkey) from part) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -1617,10 +1355,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Reducer 5 <- Map 4 (SIMPLE_EDGE) - Reducer 7 <- Map 6 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1644,26 +1381,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part - Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: p_name (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: part Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) @@ -1688,18 +1405,16 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col1, _col4, _col5 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + 1 _col2 (type: string) + outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((_col1 + 100) < CASE WHEN (_col5 is null) THEN (null) ELSE (_col4) END) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((_col1 + 100) < CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END) (type: boolean) + Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1728,32 +1443,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1677 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 4 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 516 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: 4 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 7 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: max(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -1798,9 +1487,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1824,26 +1512,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part_null - Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_type is not null (type: boolean) - Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: p_type (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 32 Data size: 3256 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: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: part_null Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_type is not null (type: boolean) @@ -1868,23 +1536,21 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col4 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12 - Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE + 1 _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(_col5) > CASE WHEN (_col12 is null) THEN (null) ELSE (_col11) END) (type: boolean) - Statistics: Num rows: 19 Data size: 11802 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(_col5) > CASE WHEN (_col10 is null) THEN (null) ELSE (_col9) END) (type: boolean) + Statistics: Num rows: 9 Data size: 5690 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: 19 Data size: 11802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 19 Data size: 11802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1893,32 +1559,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 203 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: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: avg(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -1952,8 +1592,7 @@ POSTHOOK: Input: default@part POSTHOOK: Input: default@part_null #### A masked pattern was here #### 192697 almond antique blue firebrick mint Manufacturer#5 Brand#52 MEDIUM BURNISHED TIN 31 LG DRUM 1789.69 ickly ir -Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[61][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[27][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain select * from part where p_size BETWEEN (select min(p_size) from part_null where part_null.p_type = part.p_type) AND (select max(p_size) from part_null) PREHOOK: type: QUERY POSTHOOK: query: explain select * from part where p_size BETWEEN (select min(p_size) from part_null where part_null.p_type = part.p_type) AND (select max(p_size) from part_null) @@ -1967,13 +1606,10 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) - Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) - Reducer 3 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) - Reducer 4 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) - Reducer 8 <- Map 7 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Map 4 (SIMPLE_EDGE) + Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1993,47 +1629,7 @@ STAGE PLANS: value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Execution mode: llap LLAP IO: no inputs - Map 11 - Map Operator Tree: - TableScan - alias: part_null - Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_size (type: int) - outputColumnNames: p_size - Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(p_size) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: part_null - Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_type is not null (type: boolean) - Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: p_type (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 32 Data size: 3256 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: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Execution mode: llap - LLAP IO: no inputs - Map 7 + Map 4 Map Operator Tree: TableScan alias: part_null @@ -2055,145 +1651,67 @@ STAGE PLANS: value expressions: _col1 (type: int) Execution mode: llap LLAP IO: no inputs - Map 9 + Map 6 Map Operator Tree: TableScan alias: part_null Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey + expressions: p_size (type: int) + outputColumnNames: p_size Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(p_partkey) + aggregations: max(p_size) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Reducer 10 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reducer 12 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) Reducer 2 Execution mode: llap Reduce Operator Tree: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col4 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12 - Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE + 1 _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 57 Data size: 35406 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), _col11 (type: int), _col12 (type: boolean) + Statistics: Num rows: 28 Data size: 17703 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), _col9 (type: int), _col10 (type: boolean) Reducer 3 Execution mode: llap Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12 - Statistics: Num rows: 57 Data size: 35919 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 57 Data size: 35919 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), _col11 (type: int), _col12 (type: boolean) - Reducer 4 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: Left Outer Join0 to 1 keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12, _col15 - Statistics: Num rows: 57 Data size: 36204 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 + Statistics: Num rows: 28 Data size: 17843 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: _col5 BETWEEN CASE WHEN (_col12 is null) THEN (null) ELSE (_col11) END AND _col15 (type: boolean) - Statistics: Num rows: 6 Data size: 3810 Basic stats: COMPLETE Column stats: NONE + predicate: _col5 BETWEEN CASE WHEN (_col10 is null) THEN (null) ELSE (_col9) END AND _col12 (type: boolean) + Statistics: Num rows: 3 Data size: 1911 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: 6 Data size: 3810 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1911 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 3810 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1911 Basic stats: COMPLETE Column stats: NONE 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 - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 203 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: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE - Reducer 8 + Reducer 5 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -2212,6 +1730,18 @@ STAGE PLANS: Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: boolean) + Reducer 7 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Stage: Stage-0 Fetch Operator @@ -2219,8 +1749,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[61][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[27][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product PREHOOK: query: select * from part where p_size BETWEEN (select min(p_size) from part_null where part_null.p_type = part.p_type) AND (select max(p_size) from part_null) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -2257,7 +1786,7 @@ POSTHOOK: Input: default@part_null 85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull 86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully 90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl -Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain select * from part where p_size >= (select min(p_size) from part_null where part_null.p_type = part.p_type) AND p_retailprice <= (select max(p_retailprice) from part_null) PREHOOK: type: QUERY POSTHOOK: query: explain select * from part where p_size >= (select min(p_size) from part_null where part_null.p_type = part.p_type) AND p_retailprice <= (select max(p_retailprice) from part_null) @@ -2271,12 +1800,10 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) - Reducer 3 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) Reducer 5 <- Map 4 (SIMPLE_EDGE) - Reducer 7 <- Map 6 (SIMPLE_EDGE) - Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) + Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -2296,50 +1823,10 @@ STAGE PLANS: value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Execution mode: llap LLAP IO: no inputs - Map 10 - Map Operator Tree: - TableScan - alias: part_null - Statistics: Num rows: 407 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_retailprice (type: double) - outputColumnNames: p_retailprice - Statistics: Num rows: 407 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(p_retailprice) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: double) - Execution mode: llap - LLAP IO: no inputs Map 4 Map Operator Tree: TableScan alias: part_null - Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_type is not null (type: boolean) - Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: p_type (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 32 Data size: 3256 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: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Execution mode: llap - LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: part_null Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_type is not null (type: boolean) @@ -2358,61 +1845,47 @@ STAGE PLANS: value expressions: _col1 (type: int) Execution mode: llap LLAP IO: no inputs - Map 8 + Map 6 Map Operator Tree: TableScan alias: part_null - Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 407 Data size: 3256 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE + expressions: p_retailprice (type: double) + outputColumnNames: p_retailprice + Statistics: Num rows: 407 Data size: 3256 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(p_partkey) + aggregations: max(p_retailprice) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: double) Execution mode: llap LLAP IO: no inputs - Reducer 11 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: double) Reducer 2 Execution mode: llap Reduce Operator Tree: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col4 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12 - Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE + 1 _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col5 >= CASE WHEN (_col12 is null) THEN (null) ELSE (_col11) END) (type: boolean) - Statistics: Num rows: 19 Data size: 11802 Basic stats: COMPLETE Column stats: NONE + predicate: (_col5 >= CASE WHEN (_col10 is null) THEN (null) ELSE (_col9) END) (type: boolean) + Statistics: Num rows: 9 Data size: 5690 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: 19 Data size: 11802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 19 Data size: 11802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 5690 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 @@ -2420,23 +1893,21 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 1 - 2 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col15 - Statistics: Num rows: 19 Data size: 12125 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12 + Statistics: Num rows: 9 Data size: 5771 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col7 <= _col15) (type: boolean) - Statistics: Num rows: 6 Data size: 3828 Basic stats: COMPLETE Column stats: NONE + predicate: (_col7 <= _col12) (type: boolean) + Statistics: Num rows: 3 Data size: 1923 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: 6 Data size: 3828 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1923 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 3828 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1923 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2445,32 +1916,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 203 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: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE - Reducer 7 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -2486,29 +1931,18 @@ STAGE PLANS: Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: boolean) - Reducer 9 + Reducer 7 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) + aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: double) Stage: Stage-0 Fetch Operator @@ -2516,7 +1950,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: select * from part where p_size >= (select min(p_size) from part_null where part_null.p_type = part.p_type) AND p_retailprice <= (select max(p_retailprice) from part_null) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -2553,7 +1987,7 @@ POSTHOOK: Input: default@part_null 85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull 86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully 90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl -Warning: Shuffle Join MERGEJOIN[46][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select * from part where p_brand <> (select min(p_brand) from part ) AND p_size IN (select (p_size) from part p where p.p_type = part.p_type ) AND p_size <> 340 PREHOOK: type: QUERY POSTHOOK: query: explain select * from part where p_brand <> (select min(p_brand) from part ) AND p_size IN (select (p_size) from part p where p.p_type = part.p_type ) AND p_size <> 340 @@ -2567,11 +2001,10 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE) - Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) - Reducer 9 <- Map 8 (SIMPLE_EDGE) + Reducer 7 <- Map 6 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -2596,26 +2029,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: part Statistics: Num rows: 26 Data size: 2392 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_brand (type: string) @@ -2632,7 +2045,7 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs - Map 8 + Map 6 Map Operator Tree: TableScan alias: p @@ -2658,15 +2071,13 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 1 - 2 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 26 Data size: 20878 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (_col3 <> _col10) (type: boolean) + predicate: (_col3 <> _col9) (type: boolean) Statistics: Num rows: 26 Data size: 20878 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: string), _col5 (type: int) @@ -2696,29 +2107,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 7 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: min(VALUE._col0) mode: mergepartial outputColumnNames: _col0 @@ -2727,7 +2115,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) - Reducer 9 + Reducer 7 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -2751,7 +2139,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[46][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select * from part where p_brand <> (select min(p_brand) from part ) AND p_size IN (select (p_size) from part p where p.p_type = part.p_type ) AND p_size <> 340 PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -2796,9 +2184,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -2822,26 +2209,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: p - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((p_size = p_size) and (p_partkey = p_partkey)) (type: boolean) - Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: p_partkey (type: int), p_size (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: p Statistics: Num rows: 26 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((p_size = p_size) and (p_partkey = p_partkey)) (type: boolean) @@ -2866,54 +2233,26 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col0 (type: int), _col5 (type: int) - 1 _col0 (type: int), _col1 (type: int) - 2 _col2 (type: int), _col3 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12, _col13 - Statistics: Num rows: 1 Data size: 631 Basic stats: COMPLETE Column stats: COMPLETE + 1 _col2 (type: int), _col3 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 26 Data size: 16406 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (UDFToLong(_col5) <> CASE WHEN (_col13 is null) THEN (0) ELSE (_col12) END) (type: boolean) - Statistics: Num rows: 1 Data size: 631 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (UDFToLong(_col5) <> CASE WHEN (_col10 is null) THEN (0) ELSE (_col9) END) (type: boolean) + Statistics: Num rows: 26 Data size: 16406 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: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - 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 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 4 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: int), _col1 (type: int) - mode: complete - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col2) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col1 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 6 + 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 + File Output Operator + compressed: false + Statistics: Num rows: 26 Data size: 16094 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 + Reducer 4 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -2970,8 +2309,8 @@ POSTHOOK: Input: default@part 85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull 86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully 90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl -Warning: Shuffle Join MERGEJOIN[64][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[65][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[49][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[50][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product PREHOOK: query: explain select key, count(*) from src where value <> (select max(value) from src) group by key having count(*) > (select count(*) from src s1 where s1.key = '90' group by s1.key ) PREHOOK: type: QUERY POSTHOOK: query: explain select key, count(*) from src where value <> (select max(value) from src) group by key having count(*) > (select count(*) from src s1 where s1.key = '90' group by s1.key ) @@ -2985,14 +2324,13 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 10 <- Map 9 (SIMPLE_EDGE) - Reducer 11 <- Reducer 10 (CUSTOM_SIMPLE_EDGE) - Reducer 13 <- Map 12 (SIMPLE_EDGE) - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE) + Reducer 11 <- Map 10 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) - Reducer 4 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE) Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE) - Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) + Reducer 8 <- Map 7 (SIMPLE_EDGE) + Reducer 9 <- Reducer 8 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -3010,7 +2348,7 @@ STAGE PLANS: value expressions: _col0 (type: string), _col1 (type: string) Execution mode: llap LLAP IO: no inputs - Map 12 + Map 10 Map Operator Tree: TableScan alias: s1 @@ -3038,26 +2376,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(key) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 7 - Map Operator Tree: - TableScan - alias: src Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) @@ -3074,7 +2392,7 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs - Map 9 + Map 7 Map Operator Tree: TableScan alias: s1 @@ -3096,46 +2414,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Reducer 10 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) Reducer 11 Execution mode: llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 13 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 @@ -3154,15 +2437,13 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 1 - 2 - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (_col1 <> _col3) (type: boolean) + predicate: (_col1 <> _col2) (type: boolean) Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) @@ -3224,37 +2505,49 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) + aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 8 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - mode: complete + mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 8 + value expressions: _col0 (type: bigint) + Reducer 9 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: max(VALUE._col0) + aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (sq_count_check(_col0) <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator @@ -3262,8 +2555,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[64][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[65][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[49][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[50][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product PREHOOK: query: select key, count(*) from src where value <> (select max(value) from src) group by key having count(*) > (select count(*) from src s1 where s1.key = '90' group by s1.key ) PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -3282,7 +2575,7 @@ POSTHOOK: Input: default@src 468 4 469 5 489 4 -Warning: Shuffle Join MERGEJOIN[33][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[18][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain select sum(p_retailprice) from part group by p_type having sum(p_retailprice) > (select max(pp.p_retailprice) from part pp) PREHOOK: type: QUERY POSTHOOK: query: explain select sum(p_retailprice) from part group by p_type having sum(p_retailprice) > (select max(pp.p_retailprice) from part pp) @@ -3297,9 +2590,8 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE) - Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -3329,26 +2621,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: pp - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: pp Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_retailprice (type: double) @@ -3388,15 +2660,13 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 1 - 2 - outputColumnNames: _col1, _col3 + outputColumnNames: _col1, _col2 Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (_col1 > _col3) (type: boolean) + predicate: (_col1 > _col2) (type: boolean) Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: double) @@ -3413,29 +2683,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 7 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 @@ -3451,7 +2698,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[33][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[18][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: select sum(p_retailprice) from part group by p_type having sum(p_retailprice) > (select max(pp.p_retailprice) from part pp) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -3881,11 +3128,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) - Reducer 8 <- Map 10 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) - Reducer 9 <- Reducer 8 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -3905,43 +3150,24 @@ STAGE PLANS: value expressions: _col0 (type: int), _col1 (type: string) Execution mode: llap LLAP IO: no inputs - Map 10 - Map Operator Tree: - TableScan - alias: pp - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (p_size is not null and p_type is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_type (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: int) - Execution mode: llap - LLAP IO: no inputs Map 3 Map Operator Tree: TableScan alias: p - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_type is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: p_type (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE + expressions: p_name (type: string), p_type (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs Map 6 @@ -3964,101 +3190,32 @@ STAGE PLANS: value expressions: _col1 (type: int) Execution mode: llap LLAP IO: no inputs - Map 7 - Map Operator Tree: - TableScan - alias: p - Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_type is not null (type: boolean) - Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_name (type: string), p_type (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Execution mode: llap - LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col2 (type: int) - 1 _col0 (type: int) - 2 _col2 (type: int) - outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 4 Data size: 1252 Basic stats: COMPLETE Column stats: COMPLETE + 1 _col2 (type: int) + outputColumnNames: _col0, _col1, _col3, _col4 + Statistics: Num rows: 26 Data size: 8138 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (_col1 like CASE WHEN (_col6 is null) THEN (null) ELSE (_col5) END) (type: boolean) - Statistics: Num rows: 2 Data size: 626 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (_col1 like CASE WHEN (_col4 is null) THEN (null) ELSE (_col3) END) (type: boolean) + Statistics: Num rows: 13 Data size: 4069 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 4 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col3 - Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col3 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 48 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: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 5 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 48 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: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 8 + Statistics: Num rows: 13 Data size: 52 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 + Reducer 4 Execution mode: llap Reduce Operator Tree: Merge Join Operator @@ -4081,7 +3238,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 12 Data size: 2256 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) - Reducer 9 + Reducer 5 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -4135,9 +3292,8 @@ POSTHOOK: Input: default@part 85768 86428 90681 -Warning: Shuffle Join MERGEJOIN[53][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[54][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[55][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[37][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain select * from part_null where p_name NOT LIKE (select min(p_name) from part_null) AND p_brand NOT IN (select p_name from part) PREHOOK: type: QUERY POSTHOOK: query: explain select * from part_null where p_name NOT LIKE (select min(p_name) from part_null) AND p_brand NOT IN (select p_name from part) @@ -4151,14 +3307,12 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) - Reducer 13 <- Map 12 (SIMPLE_EDGE) - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE) - Reducer 4 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Reducer 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) - Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) - Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) + Reducer 10 <- Map 9 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE) + Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -4176,7 +3330,27 @@ STAGE PLANS: 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) Execution mode: llap LLAP IO: no inputs - Map 10 + Map 5 + Map Operator Tree: + TableScan + alias: part_null + Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_name (type: string) + outputColumnNames: p_name + Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: min(p_name) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 7 Map Operator Tree: TableScan alias: part @@ -4196,7 +3370,7 @@ STAGE PLANS: value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs - Map 12 + Map 9 Map Operator Tree: TableScan alias: part @@ -4213,59 +3387,7 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: part_null - Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 8 - Map Operator Tree: - TableScan - alias: part_null - Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string) - outputColumnNames: p_name - Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(p_name) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: llap - LLAP IO: no inputs - Reducer 11 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Reducer 13 + Reducer 10 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -4288,39 +3410,24 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 5 Data size: 3301 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 5 Data size: 3301 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 - Reduce Operator Tree: - Merge Join Operator - condition map: Left Outer Join0 to 1 keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 - Statistics: Num rows: 5 Data size: 4226 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 5 Data size: 4181 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (not (_col1 like _col10)) (type: boolean) - Statistics: Num rows: 3 Data size: 2535 Basic stats: COMPLETE Column stats: NONE + predicate: (not (_col1 like _col9)) (type: boolean) + Statistics: Num rows: 3 Data size: 2508 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: 2535 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 2508 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 3 Data size: 2535 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 2508 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 4 + Reducer 3 Execution mode: llap Reduce Operator Tree: Merge Join Operator @@ -4329,15 +3436,15 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12 - Statistics: Num rows: 3 Data size: 2586 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11 + Statistics: Num rows: 3 Data size: 2559 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: 3 Data size: 2586 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), _col11 (type: bigint), _col12 (type: bigint) - Reducer 5 + Statistics: Num rows: 3 Data size: 2559 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), _col10 (type: bigint), _col11 (type: bigint) + Reducer 4 Execution mode: llap Reduce Operator Tree: Merge Join Operator @@ -4346,10 +3453,10 @@ STAGE PLANS: keys: 0 _col3 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12, _col14 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col13 Statistics: Num rows: 14 Data size: 1787 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col11 = 0) or (_col14 is null and _col3 is not null and (_col12 >= _col11))) (type: boolean) + 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 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) @@ -4362,30 +3469,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 7 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reducer 9 + Reducer 6 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -4397,6 +3481,18 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) + Reducer 8 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Stage: Stage-0 Fetch Operator @@ -4404,9 +3500,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[53][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[54][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[55][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[37][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: select * from part_null where p_name NOT LIKE (select min(p_name) from part_null) AND p_brand NOT IN (select p_name from part) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -4442,7 +3537,7 @@ POSTHOOK: Input: default@part_null 85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull 86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully 90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl -Warning: Shuffle Join MERGEJOIN[55][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[39][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select * from part_null where p_brand NOT IN (select p_name from part) AND p_name NOT LIKE (select min(p_name) from part_null pp where part_null.p_type = pp.p_type) PREHOOK: type: QUERY POSTHOOK: query: explain select * from part_null where p_brand NOT IN (select p_name from part) AND p_name NOT LIKE (select min(p_name) from part_null pp where part_null.p_type = pp.p_type) @@ -4457,10 +3552,9 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 10 <- Map 9 (SIMPLE_EDGE) - Reducer 12 <- Map 11 (SIMPLE_EDGE) Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) - Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) + Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE) Reducer 8 <- Map 7 (SIMPLE_EDGE) #### A masked pattern was here #### @@ -4480,28 +3574,6 @@ STAGE PLANS: 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) Execution mode: llap LLAP IO: no inputs - Map 11 - Map Operator Tree: - TableScan - alias: pp - Statistics: Num rows: 16 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_type is not null (type: boolean) - Statistics: Num rows: 16 Data size: 3256 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(p_name) - keys: p_type (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 3256 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: 3256 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: llap - LLAP IO: no inputs Map 5 Map Operator Tree: TableScan @@ -4543,52 +3615,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: pp - Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 3256 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p_type is not null (type: boolean) - Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 3256 Basic stats: COMPLETE Column stats: NONE Group By Operator + aggregations: min(p_name) keys: p_type (type: string) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 16 Data size: 3256 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: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 3256 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs Reducer 10 Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 203 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: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE - Reducer 12 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -4651,23 +3699,21 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col4 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col15, _col16 - Statistics: Num rows: 17 Data size: 3581 Basic stats: COMPLETE Column stats: NONE + 1 _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col13, _col14 + Statistics: Num rows: 8 Data size: 1790 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (not (_col1 like CASE WHEN (_col16 is null) THEN (null) ELSE (_col15) END)) (type: boolean) - Statistics: Num rows: 9 Data size: 1895 Basic stats: COMPLETE Column stats: NONE + predicate: (not (_col1 like CASE WHEN (_col14 is null) THEN (null) ELSE (_col13) END)) (type: boolean) + Statistics: Num rows: 4 Data size: 895 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: 1895 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 895 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 9 Data size: 1895 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 895 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4709,7 +3755,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[55][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[39][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select * from part_null where p_brand NOT IN (select p_name from part) AND p_name NOT LIKE (select min(p_name) from part_null pp where part_null.p_type = pp.p_type) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -4742,9 +3788,8 @@ STAGE PLANS: Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) - Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 7 <- Map 6 (SIMPLE_EDGE) - Reducer 9 <- Map 8 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -4791,30 +3836,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: lineitem - Statistics: Num rows: 100 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((l_shipmode = 'AIR') and (l_linenumber = l_linenumber)) (type: boolean) - Statistics: Num rows: 7 Data size: 644 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: l_linenumber (type: int) - outputColumnNames: l_linenumber - Statistics: Num rows: 7 Data size: 644 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: l_linenumber (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 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: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 8 - Map Operator Tree: - TableScan - alias: lineitem Statistics: Num rows: 100 Data size: 9600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((l_shipmode = 'AIR') and (l_linenumber = l_linenumber)) (type: boolean) @@ -4873,15 +3894,13 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col4 (type: int) - 1 _col0 (type: int) - 2 _col2 (type: int) - outputColumnNames: _col0, _col1, _col3, _col7, _col8 + 1 _col2 (type: int) + outputColumnNames: _col0, _col1, _col3, _col5, _col6 Statistics: Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (_col1 <> CASE WHEN (_col8 is null) THEN (null) ELSE (_col7) END) (type: boolean) + predicate: (_col1 <> CASE WHEN (_col6 is null) THEN (null) ELSE (_col5) END) (type: boolean) Statistics: Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col3 (type: int) @@ -4898,32 +3917,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 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: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 9 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: min(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial @@ -5006,9 +3999,8 @@ STAGE PLANS: Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) - Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 7 <- Map 6 (SIMPLE_EDGE) - Reducer 9 <- Map 8 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -5037,45 +4029,21 @@ STAGE PLANS: alias: li Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((l_linenumber = 1) and l_partkey is not null) (type: boolean) - Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 17 Data size: 272 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: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int) - Execution mode: llap - LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: lineitem - Statistics: Num rows: 100 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((l_shipmode = 'AIR') and (l_linenumber = l_linenumber)) (type: boolean) - Statistics: Num rows: 7 Data size: 644 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: l_linenumber (type: int) - outputColumnNames: l_linenumber - Statistics: Num rows: 7 Data size: 644 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: l_linenumber (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 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: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + predicate: ((l_linenumber = 1) and l_partkey is not null) (type: boolean) + Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 17 Data size: 272 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: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int) Execution mode: llap LLAP IO: no inputs - Map 8 + Map 6 Map Operator Tree: TableScan alias: lineitem @@ -5137,15 +4105,13 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col4 (type: int) - 1 _col0 (type: int) - 2 _col2 (type: int) - outputColumnNames: _col0, _col1, _col3, _col7, _col8 + 1 _col2 (type: int) + outputColumnNames: _col0, _col1, _col3, _col5, _col6 Statistics: Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (_col1 <> CASE WHEN (_col8 is null) THEN (null) ELSE (_col7) END) (type: boolean) + predicate: (_col1 <> CASE WHEN (_col6 is null) THEN (null) ELSE (_col5) END) (type: boolean) Statistics: Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col3 (type: int) @@ -5162,32 +4128,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 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: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 9 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: min(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial @@ -5262,10 +4202,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Reducer 6 <- Map 5 (SIMPLE_EDGE) - Reducer 8 <- Map 7 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -5311,26 +4250,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: lineitem - Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: l_partkey is not null (type: boolean) - Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: l_partkey (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 50 Data size: 200 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: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 7 - Map Operator Tree: - TableScan - alias: lineitem Statistics: Num rows: 100 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: l_partkey is not null (type: boolean) @@ -5355,29 +4274,29 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 - Left Outer Join1 to 2 - Inner Join 1 to 3 + Inner Join 1 to 2 keys: 0 _col0 (type: int) 1 _col0 (type: int) - 2 _col0 (type: int) - 3 _col1 (type: int) - outputColumnNames: _col1, _col2, _col6 - residual filter predicates: {(_col1 > _col6)} - Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col2 (type: double) - outputColumnNames: _col2 + 2 _col1 (type: int) + outputColumnNames: _col1, _col2, _col4 + Statistics: Num rows: 6 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col1 > _col4) (type: boolean) Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col2) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: + Select Operator + expressions: _col2 (type: double) + outputColumnNames: _col2 + Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -5397,32 +4316,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 16 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 16 Data size: 192 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: 16 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 8 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: avg(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial @@ -5470,9 +4363,8 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) - Reducer 4 <- Map 3 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) + Reducer 4 <- Map 3 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 6 <- Map 5 (SIMPLE_EDGE) - Reducer 8 <- Map 7 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -5516,26 +4408,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: pp - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_type is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: p_type (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1352 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: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 7 - Map Operator Tree: - TableScan - alias: pp Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_type is not null (type: boolean) @@ -5564,10 +4436,10 @@ STAGE PLANS: 0 _col1 (type: string), _col4 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 5 Data size: 3581 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1485 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 3581 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1485 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5578,60 +4450,32 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col2 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col5, _col6 - Statistics: Num rows: 1 Data size: 505 Basic stats: COMPLETE Column stats: COMPLETE + 1 _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 26 Data size: 13130 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (not (_col1 like CASE WHEN (_col6 is null) THEN (null) ELSE (_col5) END)) (type: boolean) - Statistics: Num rows: 1 Data size: 505 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (not (_col1 like CASE WHEN (_col4 is null) THEN (null) ELSE (_col3) END)) (type: boolean) + Statistics: Num rows: 13 Data size: 6565 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 225 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 225 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 1350 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 225 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 1350 Basic stats: COMPLETE Column stats: COMPLETE Reducer 6 Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 448 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: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 8 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: min(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -5822,9 +4666,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -5853,26 +4696,6 @@ STAGE PLANS: predicate: name is not null (type: boolean) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: name (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 31 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: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: depts - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: name is not null (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Group By Operator aggregations: count(deptno) keys: name (type: string) mode: hash @@ -5892,23 +4715,21 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col1 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col12, _col13 - Statistics: Num rows: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + 1 _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToLong(_col2) <> CASE WHEN (_col13 is null) THEN (0) ELSE (_col12) END) (type: boolean) - Statistics: Num rows: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToLong(_col2) <> CASE WHEN (_col11 is null) THEN (0) ELSE (_col10) END) (type: boolean) + Statistics: Num rows: 5 Data size: 261 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: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5917,32 +4738,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -5993,9 +4788,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -6024,26 +4818,6 @@ STAGE PLANS: predicate: deptno is not null (type: boolean) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: deptno (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 31 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: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: depts - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: deptno is not null (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Group By Operator aggregations: min(name) keys: deptno (type: int) mode: hash @@ -6063,23 +4837,21 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col2 (type: int) - 1 _col0 (type: int) - 2 _col2 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col12, _col13 - Statistics: Num rows: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + 1 _col2 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 > CASE WHEN (_col13 is null) THEN (null) ELSE (_col12) END) (type: boolean) - Statistics: Num rows: 3 Data size: 142 Basic stats: COMPLETE Column stats: NONE + predicate: (_col1 > CASE WHEN (_col11 is null) THEN (null) ELSE (_col10) END) (type: boolean) + Statistics: Num rows: 1 Data size: 52 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: 3 Data size: 142 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 142 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -6088,32 +4860,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 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: 10 Basic stats: COMPLETE Column stats: NONE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: min(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial @@ -6160,12 +4906,10 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 11 <- Map 10 (SIMPLE_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) - Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 5 <- Map 4 (SIMPLE_EDGE) Reducer 7 <- Map 6 (SIMPLE_EDGE) - Reducer 9 <- Map 8 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -6185,28 +4929,6 @@ STAGE PLANS: value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) Execution mode: llap LLAP IO: no inputs - Map 10 - Map Operator Tree: - TableScan - alias: depts - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: deptno is not null (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(name) - keys: deptno (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 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: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Execution mode: llap - LLAP IO: no inputs Map 4 Map Operator Tree: TableScan @@ -6216,26 +4938,6 @@ STAGE PLANS: predicate: name is not null (type: boolean) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: name (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 31 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: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Execution mode: llap - LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: depts - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: name is not null (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Group By Operator aggregations: count(deptno) keys: name (type: string) mode: hash @@ -6249,7 +4951,7 @@ STAGE PLANS: value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs - Map 8 + Map 6 Map Operator Tree: TableScan alias: depts @@ -6258,61 +4960,42 @@ STAGE PLANS: predicate: deptno is not null (type: boolean) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Group By Operator + aggregations: count(name) keys: deptno (type: int) mode: hash - outputColumnNames: _col0 + outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 31 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: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs - Reducer 11 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: boolean) Reducer 2 Execution mode: llap Reduce Operator Tree: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col1 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col12, _col13 - Statistics: Num rows: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + 1 _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToLong(_col2) <> CASE WHEN (_col13 is null) THEN (0) ELSE (_col12) END) (type: boolean) - Statistics: Num rows: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToLong(_col2) <> CASE WHEN (_col11 is null) THEN (0) ELSE (_col10) END) (type: boolean) + Statistics: Num rows: 5 Data size: 261 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: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _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 @@ -6320,23 +5003,21 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col2 (type: int) - 1 _col0 (type: int) - 2 _col2 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col17, _col18 - Statistics: Num rows: 24 Data size: 1150 Basic stats: COMPLETE Column stats: NONE + 1 _col2 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col13, _col14 + Statistics: Num rows: 5 Data size: 287 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToLong(_col0) > CASE WHEN (_col18 is null) THEN (0) ELSE (_col17) END) (type: boolean) - Statistics: Num rows: 8 Data size: 383 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToLong(_col0) > CASE WHEN (_col14 is null) THEN (0) ELSE (_col13) END) (type: boolean) + Statistics: Num rows: 1 Data size: 57 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: 8 Data size: 383 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 57 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 383 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 57 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -6345,32 +5026,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reducer 7 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -6386,32 +5041,25 @@ STAGE PLANS: Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: boolean) - Reducer 9 + Reducer 7 Execution mode: llap Reduce Operator Tree: Group By Operator + aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0 + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: complete - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 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: 10 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: boolean) Stage: Stage-0 Fetch Operator @@ -6434,7 +5082,7 @@ POSTHOOK: Input: default@emps 110 John 40 M Vancouver 2 NULL false true 2002-05-03 120 Wilma 20 F NULL 1 5 NULL true 2005-09-07 130 Alice 40 F Vancouver 2 NULL false true 2007-01-01 -Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain select * from emps where deptno <> (select sum(deptno) from depts where depts.name = emps.name) and empno > (select count(name) from depts) PREHOOK: type: QUERY POSTHOOK: query: explain select * from emps where deptno <> (select sum(deptno) from depts where depts.name = emps.name) and empno > (select count(name) from depts) @@ -6448,12 +5096,10 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) - Reducer 3 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) Reducer 5 <- Map 4 (SIMPLE_EDGE) - Reducer 7 <- Map 6 (SIMPLE_EDGE) - Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) + Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -6473,26 +5119,6 @@ STAGE PLANS: value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) Execution mode: llap LLAP IO: no inputs - Map 10 - Map Operator Tree: - TableScan - alias: depts - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: name (type: string) - outputColumnNames: name - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(name) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs Map 4 Map Operator Tree: TableScan @@ -6502,26 +5128,6 @@ STAGE PLANS: predicate: name is not null (type: boolean) Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: name (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 31 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: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Execution mode: llap - LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: depts - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: name is not null (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE - Group By Operator aggregations: sum(deptno) keys: name (type: string) mode: hash @@ -6535,17 +5141,17 @@ STAGE PLANS: value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs - Map 8 + Map 6 Map Operator Tree: TableScan alias: depts Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: deptno (type: int) - outputColumnNames: deptno + expressions: name (type: string) + outputColumnNames: name Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(deptno) + aggregations: count(name) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -6555,41 +5161,27 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs - Reducer 11 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) Reducer 2 Execution mode: llap Reduce Operator Tree: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col1 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col12, _col13 - Statistics: Num rows: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + 1 _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToLong(_col2) <> CASE WHEN (_col13 is null) THEN (null) ELSE (_col12) END) (type: boolean) - Statistics: Num rows: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToLong(_col2) <> CASE WHEN (_col11 is null) THEN (null) ELSE (_col10) END) (type: boolean) + Statistics: Num rows: 5 Data size: 261 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: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 11 Data size: 523 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 261 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 @@ -6597,23 +5189,21 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 1 - 2 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col16 - Statistics: Num rows: 11 Data size: 710 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col13 + Statistics: Num rows: 5 Data size: 306 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToLong(_col0) > _col16) (type: boolean) - Statistics: Num rows: 3 Data size: 193 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToLong(_col0) > _col13) (type: boolean) + Statistics: Num rows: 1 Data size: 61 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: 3 Data size: 193 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 61 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 193 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 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 @@ -6622,32 +5212,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - Reducer 7 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -6663,7 +5227,7 @@ STAGE PLANS: Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: boolean) - Reducer 9 + Reducer 7 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -6671,21 +5235,10 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Stage: Stage-0 Fetch Operator @@ -6693,7 +5246,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: select * from emps where deptno <> (select count(deptno) from depts where depts.name = emps.name) and empno > (select count(name) from depts) PREHOOK: type: QUERY PREHOOK: Input: default@depts @@ -6725,7 +5278,7 @@ POSTHOOK: query: drop table EMPS POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@emps POSTHOOK: Output: default@emps -Warning: Shuffle Join MERGEJOIN[37][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain select key, count(*) from src @@ -6748,9 +5301,8 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE) - Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -6784,25 +5336,6 @@ STAGE PLANS: Filter Operator predicate: (key > '9') (type: boolean) Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(key) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: s1 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '9') (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator @@ -6835,15 +5368,13 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 1 - 2 - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 205 Data size: 21115 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (_col1 > _col3) (type: boolean) + predicate: (_col1 > _col2) (type: boolean) Statistics: Num rows: 68 Data size: 7004 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) @@ -6864,29 +5395,6 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 7 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -6898,7 +5406,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[37][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: select key, count(*) from src group by key @@ -6923,7 +5431,7 @@ POSTHOOK: Input: default@src 468 4 469 5 489 4 -Warning: Shuffle Join MERGEJOIN[54][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[37][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 4' is a cross product PREHOOK: query: explain select key, value, count(*) from src b @@ -6947,10 +5455,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) - Reducer 4 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE) Reducer 6 <- Map 5 (SIMPLE_EDGE) Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### @@ -7003,25 +5510,6 @@ STAGE PLANS: Filter Operator predicate: (key > '9') (type: boolean) Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(key) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 9 - Map Operator Tree: - TableScan - alias: s1 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '9') (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator @@ -7035,18 +5523,6 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs - Reducer 10 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -7089,15 +5565,13 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 1 - 2 - outputColumnNames: _col0, _col1, _col2, _col4 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 83 Data size: 16102 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (_col2 > _col4) (type: boolean) + predicate: (_col2 > _col3) (type: boolean) Statistics: Num rows: 27 Data size: 5238 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) @@ -7131,21 +5605,10 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Stage: Stage-0 Fetch Operator @@ -7153,7 +5616,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[54][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[37][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 4' is a cross product PREHOOK: query: select key, value, count(*) from src b where b.key in (select key from src where src.key > '8') diff --git a/ql/src/test/results/clientpositive/llap/subquery_select.q.out b/ql/src/test/results/clientpositive/llap/subquery_select.q.out index 8eaec9e567..e96067f9a0 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_select.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_select.q.out @@ -1447,9 +1447,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1473,26 +1472,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: p - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_type is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: p_type (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1352 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: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: p Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_type is not null (type: boolean) @@ -1517,20 +1496,18 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col1, _col4, _col5 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + 1 _col2 (type: string) + outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int), CASE WHEN (_col5 is null) THEN (0) ELSE (_col4) END (type: bigint) + expressions: _col1 (type: int), CASE WHEN (_col3 is null) THEN (0) ELSE (_col2) END (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1539,32 +1516,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 448 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: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -1634,9 +1585,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1660,26 +1610,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: p - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_type is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: p_type (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1352 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: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: p Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_type is not null (type: boolean) @@ -1704,20 +1634,18 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col1, _col4, _col5 - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE + 1 _col2 (type: string) + outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 26 Data size: 4992 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int), CASE WHEN (_col5 is null) THEN (null) ELSE (_col4) END (type: string) + expressions: _col1 (type: int), CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 4888 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 4888 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1726,32 +1654,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 448 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: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: max(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -1808,8 +1710,7 @@ POSTHOOK: Input: default@part 7 NULL 12 NULL 23 NULL -Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain SELECT p_size, (SELECT max(p_size) FROM part) FROM part PREHOOK: type: QUERY @@ -1825,10 +1726,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE) - Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1846,27 +1745,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 6 + Map 3 Map Operator Tree: TableScan alias: part @@ -1891,62 +1770,20 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: Left Outer Join0 to 1 keys: 0 1 - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 26 Data size: 208 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 - Reducer 5 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 7 + 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 + Reducer 4 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -1965,8 +1802,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: SELECT p_size, (SELECT max(p_size) FROM part) FROM part PREHOOK: type: QUERY @@ -2003,8 +1839,7 @@ POSTHOOK: Input: default@part 2 46 46 46 23 46 -Warning: Shuffle Join MERGEJOIN[48][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product -Warning: Shuffle Join MERGEJOIN[49][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product PREHOOK: query: explain select * from src b @@ -2032,12 +1867,10 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) - Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Reducer 5 (SIMPLE_EDGE) - Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) + Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (SIMPLE_EDGE) + Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -2074,27 +1907,7 @@ STAGE PLANS: value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs - Map 7 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(key) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 9 + Map 6 Map Operator Tree: TableScan alias: src @@ -2114,18 +1927,6 @@ STAGE PLANS: value expressions: _col0 (type: string) Execution mode: llap LLAP IO: no inputs - Reducer 10 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -2149,29 +1950,14 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col1 - Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reducer 5 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: Left Outer Join0 to 1 keys: 0 1 - outputColumnNames: _col1, _col3 + outputColumnNames: _col1, _col2 Statistics: Num rows: 83 Data size: 22825 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - keys: _col3 (type: string), _col1 (type: string) + keys: _col2 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 36 Data size: 9900 Basic stats: COMPLETE Column stats: COMPLETE @@ -2180,7 +1966,7 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 36 Data size: 9900 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 6 + Reducer 5 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -2193,29 +1979,18 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 36 Data size: 9900 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 8 + Reducer 7 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) + aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) Stage: Stage-0 Fetch Operator @@ -2223,8 +1998,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[48][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product -Warning: Shuffle Join MERGEJOIN[49][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product PREHOOK: query: select * from src b where b.key in @@ -2275,9 +2049,8 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) - Reducer 4 <- Map 3 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) + Reducer 4 <- Map 3 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 6 <- Map 5 (SIMPLE_EDGE) - Reducer 8 <- Map 7 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -2319,36 +2092,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: sc - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator + aggregations: max(key) keys: value (type: string) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 214 Data size: 19474 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: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 7 - Map Operator Tree: - TableScan - alias: sc - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: max(key) - keys: value (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 214 Data size: 58850 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 214 Data size: 58850 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -2381,15 +2134,13 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col1 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col1, _col4, _col5 + 1 _col2 (type: string) + outputColumnNames: _col1, _col2, _col3 Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: CASE WHEN (_col5 is null) THEN (null) ELSE (_col4) END (type: string), _col1 (type: string) + expressions: CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 22825 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator @@ -2406,32 +2157,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 214 Data size: 21186 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 71 Data size: 7029 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 71 Data size: 7029 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: 71 Data size: 7029 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 8 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: max(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -2691,8 +2416,7 @@ POSTHOOK: query: CREATE TABLE tempty(i int) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@tempty -Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select p_size, (select count(*) from tempty) from part PREHOOK: type: QUERY POSTHOOK: query: explain select p_size, (select count(*) from tempty) from part @@ -2706,10 +2430,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE) - Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -2727,27 +2449,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: tempty - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: i (type: int) - outputColumnNames: i - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: count(i) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 6 + Map 3 Map Operator Tree: TableScan alias: tempty @@ -2770,62 +2472,20 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 338 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 338 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: Left Outer Join0 to 1 keys: 0 1 - outputColumnNames: _col0, _col2 - Statistics: Num rows: 26 Data size: 572 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col2 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 572 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 26 Data size: 572 Basic stats: COMPLETE Column stats: NONE - 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 - Reducer 5 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reducer 7 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 26 Data size: 312 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 + Reducer 4 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -2844,8 +2504,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select p_size, (select count(*) from tempty) from part PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -2882,8 +2541,7 @@ POSTHOOK: Input: default@tempty 2 0 46 0 23 0 -Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select p_size, (select max(i) from tempty) from part PREHOOK: type: QUERY POSTHOOK: query: explain select p_size, (select max(i) from tempty) from part @@ -2897,10 +2555,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE) - Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -2918,27 +2574,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: tempty - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: i (type: int) - outputColumnNames: i - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: count(i) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 6 + Map 3 Map Operator Tree: TableScan alias: tempty @@ -2963,62 +2599,20 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 338 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 338 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: Left Outer Join0 to 1 keys: 0 1 - outputColumnNames: _col0, _col2 - Statistics: Num rows: 26 Data size: 468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 468 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 26 Data size: 468 Basic stats: COMPLETE Column stats: NONE - 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 - Reducer 5 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reducer 7 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 26 Data size: 234 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 26 Data size: 234 Basic stats: COMPLETE Column stats: NONE + 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 + Reducer 4 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -3037,8 +2631,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select p_size, (select max(i) from tempty) from part PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -3106,9 +2699,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -3132,26 +2724,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: p - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_type is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: p_type (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1352 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: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: p Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_type is not null (type: boolean) @@ -3176,20 +2748,18 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col1, _col4, _col5 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + 1 _col2 (type: string) + outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int), (1 + CASE WHEN (_col5 is null) THEN (null) ELSE (_col4) END) (type: int) + expressions: _col1 (type: int), (1 + CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3198,32 +2768,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 448 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: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: max(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -3297,9 +2841,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -3323,26 +2866,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: p - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_type is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: p_type (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1352 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: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: p Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_type is not null (type: boolean) @@ -3367,20 +2890,18 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col1, _col4, _col5 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + 1 _col2 (type: string) + outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int), CASE WHEN (_col5 is null) THEN (false) ELSE (_col4 is null) END (type: boolean) + expressions: _col1 (type: int), CASE WHEN (_col3 is null) THEN (false) ELSE (_col2 is null) END (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3389,32 +2910,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 448 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: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial @@ -4139,11 +3634,9 @@ POSTHOOK: Input: default@part 6 false 18 false 45 false -Warning: Shuffle Join MERGEJOIN[85][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product -Warning: Shuffle Join MERGEJOIN[86][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 6' is a cross product -Warning: Shuffle Join MERGEJOIN[87][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[88][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 14' is a cross product -Warning: Shuffle Join MERGEJOIN[89][tables = [$hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 15' is a cross product +Warning: Shuffle Join MERGEJOIN[50][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[51][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[52][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 11' is a cross product PREHOOK: query: explain select p_size, (p_size IN (select (select max(p_size) from part) as sb from part order by sb limit 1)) = true from part @@ -4161,19 +3654,15 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) - Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) - Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE), Reducer 18 (CUSTOM_SIMPLE_EDGE) - Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE), Reducer 20 (CUSTOM_SIMPLE_EDGE) - Reducer 16 <- Reducer 15 (SIMPLE_EDGE) - Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE) - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE) - Reducer 20 <- Map 19 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) - Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE), Reducer 10 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) - Reducer 7 <- Reducer 6 (SIMPLE_EDGE) - Reducer 8 <- Reducer 7 (CUSTOM_SIMPLE_EDGE) + Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE), Reducer 14 (CUSTOM_SIMPLE_EDGE) + Reducer 12 <- Reducer 11 (SIMPLE_EDGE) + Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE) + Reducer 6 <- Reducer 5 (SIMPLE_EDGE) + Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) + Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -4191,27 +3680,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 11 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_size (type: int) - outputColumnNames: p_size - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: max(p_size) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: llap - LLAP IO: no inputs - Map 13 + Map 10 Map Operator Tree: TableScan alias: part @@ -4223,27 +3692,7 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 17 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 19 + Map 13 Map Operator Tree: TableScan alias: part @@ -4275,75 +3724,27 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 9 + Map 8 Map Operator Tree: TableScan alias: part Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey + expressions: p_size (type: int) + outputColumnNames: p_size Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(p_partkey) + aggregations: max(p_size) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Reducer 10 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 12 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Reducer 14 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 15 + Reducer 11 Execution mode: llap Reduce Operator Tree: Merge Join Operator @@ -4352,10 +3753,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col2 + outputColumnNames: _col1 Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col2 (type: int) + expressions: _col1 (type: int) outputColumnNames: _col0 Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator @@ -4363,7 +3764,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 16 + Reducer 12 Execution mode: llap Reduce Operator Tree: Select Operator @@ -4383,29 +3784,18 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) - Reducer 18 + Reducer 14 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) + aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -4423,18 +3813,6 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 26 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) - Reducer 20 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -4462,34 +3840,21 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: Left Outer Join0 to 1 keys: 0 1 - outputColumnNames: _col2 + outputColumnNames: _col1 Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col2 (type: int) + expressions: _col1 (type: int) outputColumnNames: _col0 Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 7 + Reducer 6 Execution mode: llap Reduce Operator Tree: Select Operator @@ -4508,7 +3873,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) - Reducer 8 + Reducer 7 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -4520,6 +3885,18 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) + Reducer 9 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Stage: Stage-0 Fetch Operator @@ -4527,11 +3904,9 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[85][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product -Warning: Shuffle Join MERGEJOIN[86][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 6' is a cross product -Warning: Shuffle Join MERGEJOIN[87][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[88][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 14' is a cross product -Warning: Shuffle Join MERGEJOIN[89][tables = [$hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 15' is a cross product +Warning: Shuffle Join MERGEJOIN[50][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[51][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[52][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 11' is a cross product PREHOOK: query: select p_size, (p_size IN (select (select max(p_size) from part) as sb from part order by sb limit 1)) = true from part @@ -4570,12 +3945,9 @@ POSTHOOK: Input: default@part 42 false 45 false 46 true -Warning: Shuffle Join MERGEJOIN[94][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[95][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[96][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product -Warning: Shuffle Join MERGEJOIN[97][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product -Warning: Shuffle Join MERGEJOIN[98][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5]] in Stage 'Reducer 6' is a cross product -Warning: Shuffle Join MERGEJOIN[99][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6]] in Stage 'Reducer 7' is a cross product +Warning: Shuffle Join MERGEJOIN[37][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[38][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product PREHOOK: query: explain select case when (select count(*) from part where p_size between 1 and 20) > 409437 @@ -4607,18 +3979,12 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) - Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) - Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) - Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) - Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) - Reducer 4 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Reducer 17 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) - Reducer 7 <- Reducer 19 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) - Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) + Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) + Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE) + Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -4633,7 +3999,7 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 10 + Map 5 Map Operator Tree: TableScan alias: part @@ -4654,26 +4020,7 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs - Map 12 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_partkey BETWEEN 1 AND 20 (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 14 + Map 7 Map Operator Tree: TableScan alias: part @@ -4692,26 +4039,7 @@ STAGE PLANS: value expressions: _col0 (type: struct) Execution mode: llap LLAP IO: no inputs - Map 16 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_partkey BETWEEN 10000 AND 20000 (type: boolean) - Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 18 + Map 9 Map Operator Tree: TableScan alias: part @@ -4734,100 +4062,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 8 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_size BETWEEN 1 AND 20 (type: boolean) - Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Reducer 11 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reducer 13 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 15 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: avg(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double) - Reducer 17 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 19 + Reducer 10 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -4844,45 +4079,17 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: Left Outer Join0 to 1 keys: 0 1 - outputColumnNames: _col2 - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: bigint) - Reducer 4 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col2 + outputColumnNames: _col1 Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: bigint) - Reducer 5 + value expressions: _col1 (type: bigint) + Reducer 3 Execution mode: llap Reduce Operator Tree: Merge Join Operator @@ -4891,28 +4098,13 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col2, _col4 - Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: bigint), _col4 (type: double) - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col2, _col4 + outputColumnNames: _col1, _col2 Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: bigint), _col4 (type: double) - Reducer 7 + value expressions: _col1 (type: bigint), _col2 (type: double) + Reducer 4 Execution mode: llap Reduce Operator Tree: Merge Join Operator @@ -4921,10 +4113,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col2, _col4, _col6 + outputColumnNames: _col1, _col2, _col3 Statistics: Num rows: 26 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: CASE WHEN ((_col2 > 409437)) THEN (_col4) ELSE (_col6) END (type: double) + expressions: CASE WHEN ((_col1 > 409437)) THEN (_col2) ELSE (_col3) END (type: double) outputColumnNames: _col0 Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -4934,7 +4126,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 9 + Reducer 6 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -4942,21 +4134,22 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reducer 8 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: avg(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double) Stage: Stage-0 Fetch Operator @@ -4964,12 +4157,9 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[94][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[95][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[96][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product -Warning: Shuffle Join MERGEJOIN[97][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product -Warning: Shuffle Join MERGEJOIN[98][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5]] in Stage 'Reducer 6' is a cross product -Warning: Shuffle Join MERGEJOIN[99][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6]] in Stage 'Reducer 7' is a cross product +Warning: Shuffle Join MERGEJOIN[37][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[38][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product PREHOOK: query: select case when (select count(*) from part where p_size between 1 and 20) > 409437 @@ -5022,8 +4212,7 @@ POSTHOOK: Input: default@part 46.0 46.0 46.0 -Warning: Shuffle Join MERGEJOIN[34][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[35][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain select max(p_size) > ( select count(*)-1 from part) from part PREHOOK: type: QUERY POSTHOOK: query: explain select max(p_size) > ( select count(*)-1 from part) from part @@ -5038,10 +4227,8 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) - Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE) - Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -5064,27 +4251,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 7 + Map 4 Map Operator Tree: TableScan alias: part @@ -5119,29 +4286,14 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Reducer 4 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: Left Outer Join0 to 1 keys: 0 1 - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: (UDFToLong(_col0) > _col2) (type: boolean) + expressions: (UDFToLong(_col0) > _col1) (type: boolean) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -5151,30 +4303,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 8 + Reducer 5 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -5197,8 +4326,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[34][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[35][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: select max(p_size) > ( select count(*)-1 from part) from part PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -5208,7 +4336,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### true -Warning: Shuffle Join MERGEJOIN[75][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[38][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product PREHOOK: query: explain select o.p_size, (select count(distinct p_type) from part p where p.p_partkey = o.p_partkey) tmp FROM part o right join (select * from part where p_size > (select avg(p_size) from part)) t on t.p_partkey = o.p_partkey PREHOOK: type: QUERY @@ -5224,12 +4352,10 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 10 <- Map 9 (SIMPLE_EDGE) - Reducer 12 <- Map 11 (SIMPLE_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) - Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) + Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE) - Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) + Reducer 8 <- Map 7 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -5249,26 +4375,6 @@ STAGE PLANS: value expressions: _col1 (type: int) Execution mode: llap LLAP IO: no inputs - Map 11 - Map Operator Tree: - TableScan - alias: p - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: p_partkey (type: int), p_type (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs Map 3 Map Operator Tree: TableScan @@ -5290,26 +4396,6 @@ STAGE PLANS: alias: part Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 7 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator expressions: p_size (type: int) outputColumnNames: p_size Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE @@ -5324,7 +4410,7 @@ STAGE PLANS: value expressions: _col0 (type: struct) Execution mode: llap LLAP IO: no inputs - Map 9 + Map 7 Map Operator Tree: TableScan alias: p @@ -5344,87 +4430,26 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Reducer 10 + Reducer 2 Execution mode: llap Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator + condition map: + Right Outer Join0 to 1 + Left Outer Join0 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col2 (type: int) + outputColumnNames: _col1, _col3, _col4 + Statistics: Num rows: 5 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: int) - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 48 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: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 12 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: int) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: boolean) - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Right Outer Join0 to 1 - Left Outer Join0 to 2 - Left Outer Join0 to 3 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - 3 _col2 (type: int) - outputColumnNames: _col1, _col5, _col6 - Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: int), CASE WHEN (_col6 is null) THEN (0) ELSE (_col5) END (type: bigint) + expressions: _col1 (type: int), CASE WHEN (_col4 is null) THEN (0) ELSE (_col3) END (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5435,15 +4460,13 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 - Inner Join 0 to 2 keys: 0 1 - 2 - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (UDFToDouble(_col1) > _col3) (type: boolean) + predicate: (UDFToDouble(_col1) > _col2) (type: boolean) Statistics: Num rows: 8 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) @@ -5458,37 +4481,38 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) + aggregations: avg(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double) Reducer 8 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: avg(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: int) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: boolean) Stage: Stage-0 Fetch Operator @@ -5496,7 +4520,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[75][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[38][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product PREHOOK: query: select o.p_size, (select count(distinct p_type) from part p where p.p_partkey = o.p_partkey) tmp FROM part o right join (select * from part where p_size > (select avg(p_size) from part)) t on t.p_partkey = o.p_partkey PREHOOK: type: QUERY @@ -5518,14 +4542,10 @@ POSTHOOK: Input: default@part 45 1 40 1 31 1 -Warning: Shuffle Join MERGEJOIN[108][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[109][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[110][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product -Warning: Shuffle Join MERGEJOIN[111][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product -Warning: Shuffle Join MERGEJOIN[112][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5]] in Stage 'Reducer 6' is a cross product -Warning: Shuffle Join MERGEJOIN[113][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6]] in Stage 'Reducer 7' is a cross product -Warning: Shuffle Join MERGEJOIN[114][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7]] in Stage 'Reducer 8' is a cross product -Warning: Shuffle Join MERGEJOIN[115][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8]] in Stage 'Reducer 9' is a cross product +Warning: Shuffle Join MERGEJOIN[40][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[41][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[42][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[43][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product PREHOOK: query: explain select (select max(p_size) from part), (select min(p_size) from part), (select avg(p_size) from part), (select sum(p_size) from part) from part @@ -5545,20 +4565,12 @@ STAGE PLANS: Edges: Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) - Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) - Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) - Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 11 (CUSTOM_SIMPLE_EDGE) - Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) - Reducer 23 <- Map 22 (CUSTOM_SIMPLE_EDGE) - Reducer 25 <- Map 24 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) - Reducer 4 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Reducer 17 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Reducer 19 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) - Reducer 7 <- Reducer 21 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) - Reducer 8 <- Reducer 23 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) - Reducer 9 <- Reducer 25 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) + Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) + Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -5579,18 +4591,18 @@ STAGE PLANS: alias: part Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey + expressions: p_size (type: int) + outputColumnNames: p_size Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(p_partkey) + aggregations: avg(p_size) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct) Execution mode: llap LLAP IO: no inputs Map 12 @@ -5603,27 +4615,7 @@ STAGE PLANS: outputColumnNames: p_size Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: max(p_size) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: llap - LLAP IO: no inputs - Map 14 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) + aggregations: sum(p_size) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -5633,7 +4625,7 @@ STAGE PLANS: value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: no inputs - Map 16 + Map 6 Map Operator Tree: TableScan alias: part @@ -5643,7 +4635,7 @@ STAGE PLANS: outputColumnNames: p_size Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: min(p_size) + aggregations: max(p_size) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE @@ -5653,67 +4645,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 18 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 20 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_size (type: int) - outputColumnNames: p_size - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: avg(p_size) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct) - Execution mode: llap - LLAP IO: no inputs - Map 22 - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int) - outputColumnNames: p_partkey - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(p_partkey) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 24 + Map 8 Map Operator Tree: TableScan alias: part @@ -5723,230 +4655,71 @@ STAGE PLANS: outputColumnNames: p_size Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(p_size) + aggregations: min(p_size) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs Reducer 11 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) + aggregations: avg(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double) Reducer 13 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: max(VALUE._col0) + aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Reducer 15 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 17 + value expressions: _col0 (type: bigint) + Reducer 2 Execution mode: llap Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 + 1 + outputColumnNames: _col1 + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Reducer 19 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 2 + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int) + Reducer 3 Execution mode: llap Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join0 to 1 keys: 0 1 + outputColumnNames: _col1, _col2 Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 21 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: avg(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double) - Reducer 23 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 25 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 - 1 - outputColumnNames: _col2 - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int) - Reducer 4 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col2 - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int) - Reducer 5 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 - 1 - outputColumnNames: _col2, _col4 - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int), _col4 (type: int) - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col2, _col4 - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int), _col4 (type: int) - Reducer 7 + value expressions: _col1 (type: int), _col2 (type: int) + Reducer 4 Execution mode: llap Reduce Operator Tree: Merge Join Operator @@ -5955,28 +4728,13 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col2, _col4, _col6 - Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int), _col4 (type: int), _col6 (type: double) - Reducer 8 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col2, _col4, _col6 + outputColumnNames: _col1, _col2, _col3 Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int), _col4 (type: int), _col6 (type: double) - Reducer 9 + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: double) + Reducer 5 Execution mode: llap Reduce Operator Tree: Merge Join Operator @@ -5985,10 +4743,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col2, _col4, _col6, _col8 + outputColumnNames: _col1, _col2, _col3, _col4 Statistics: Num rows: 26 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col2 (type: int), _col4 (type: int), _col6 (type: double), _col8 (type: bigint) + expressions: _col1 (type: int), _col2 (type: int), _col3 (type: double), _col4 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 26 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -5998,6 +4756,30 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 7 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Reducer 9 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Stage: Stage-0 Fetch Operator @@ -6005,14 +4787,10 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[108][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[109][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[110][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product -Warning: Shuffle Join MERGEJOIN[111][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product -Warning: Shuffle Join MERGEJOIN[112][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5]] in Stage 'Reducer 6' is a cross product -Warning: Shuffle Join MERGEJOIN[113][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6]] in Stage 'Reducer 7' is a cross product -Warning: Shuffle Join MERGEJOIN[114][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7]] in Stage 'Reducer 8' is a cross product -Warning: Shuffle Join MERGEJOIN[115][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8]] in Stage 'Reducer 9' is a cross product +Warning: Shuffle Join MERGEJOIN[40][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[41][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[42][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[43][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product PREHOOK: query: select (select max(p_size) from part), (select min(p_size) from part), (select avg(p_size) from part), (select sum(p_size) from part) from part @@ -6051,8 +4829,7 @@ POSTHOOK: Input: default@part 46 1 19.692307692307693 512 46 1 19.692307692307693 512 46 1 19.692307692307693 512 -Warning: Shuffle Join MERGEJOIN[55][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[57][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[26][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select t1.p_size, (select count(*) from part p, part pp where p.p_size = pp.p_size and p.p_type = pp.p_type) from part t1 @@ -6070,12 +4847,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 10 <- Reducer 9 (CUSTOM_SIMPLE_EDGE) - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) - Reducer 3 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) - Reducer 6 <- Reducer 5 (CUSTOM_SIMPLE_EDGE) - Reducer 9 <- Map 11 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 3 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -6093,26 +4867,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 11 - Map Operator Tree: - TableScan - alias: pp - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (p_type is not null and p_size is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_type (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 4 + Map 3 Map Operator Tree: TableScan alias: p @@ -6131,7 +4886,7 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 7 + Map 6 Map Operator Tree: TableScan alias: pp @@ -6150,75 +4905,25 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 8 - Map Operator Tree: - TableScan - alias: p - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (p_type is not null and p_size is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_type (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Reducer 10 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) Reducer 2 Execution mode: llap Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: Left Outer Join0 to 1 keys: 0 1 - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col2 (type: bigint) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 26 Data size: 312 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 - Reducer 5 + 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 + Reducer 4 Execution mode: llap Reduce Operator Tree: Merge Join Operator @@ -6227,10 +4932,9 @@ STAGE PLANS: keys: 0 _col0 (type: string), _col1 (type: int) 1 _col0 (type: string), _col1 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(_col0) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -6238,7 +4942,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Reducer 6 + Reducer 5 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -6246,40 +4950,10 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 9 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: int) - 1 _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Stage: Stage-0 Fetch Operator @@ -6287,8 +4961,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[55][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[57][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[26][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select t1.p_size, (select count(*) from part p, part pp where p.p_size = pp.p_size and p.p_type = pp.p_type) from part t1 @@ -6327,8 +5000,7 @@ POSTHOOK: Input: default@part 2 28 46 28 23 28 -Warning: Shuffle Join MERGEJOIN[116][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[119][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select t1.p_size, (select count(*) from part p, part pp where p.p_size = pp.p_size and p.p_type = pp.p_type and (select sum(p_size) from part a1 where a1.p_partkey = p.p_partkey @@ -6350,18 +5022,12 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 10 <- Map 9 (SIMPLE_EDGE) - Reducer 12 <- Map 11 (SIMPLE_EDGE) - Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) - Reducer 15 <- Reducer 14 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) - Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) - Reducer 19 <- Map 18 (SIMPLE_EDGE) - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) - Reducer 21 <- Map 20 (SIMPLE_EDGE) - Reducer 3 <- Reducer 16 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) - Reducer 6 <- Reducer 10 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) - Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) + Reducer 11 <- Map 10 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 3 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) + Reducer 5 <- Reducer 11 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) + Reducer 6 <- Reducer 5 (CUSTOM_SIMPLE_EDGE) + Reducer 9 <- Map 8 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -6379,7 +5045,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 11 + Map 10 Map Operator Tree: TableScan alias: a1 @@ -6401,7 +5067,7 @@ STAGE PLANS: value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs - Map 13 + Map 3 Map Operator Tree: TableScan alias: p @@ -6421,7 +5087,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: llap LLAP IO: no inputs - Map 17 + Map 7 Map Operator Tree: TableScan alias: pp @@ -6440,90 +5106,9 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 18 - Map Operator Tree: - TableScan - alias: a1 - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: p_partkey (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 52 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: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 20 - Map Operator Tree: - TableScan - alias: a1 - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(p_size) - keys: p_partkey (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 156 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: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: p - Statistics: Num rows: 26 Data size: 2912 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (p_type is not null and p_size is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 2912 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int), p_type (type: string), p_size (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 2912 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col2 (type: int) - Statistics: Num rows: 26 Data size: 2912 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: llap - LLAP IO: no inputs Map 8 Map Operator Tree: TableScan - alias: pp - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (p_type is not null and p_size is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_type (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 9 - Map Operator Tree: - TableScan alias: a1 Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator @@ -6541,52 +5126,50 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Reducer 10 + Reducer 11 Execution mode: llap Reduce Operator Tree: Group By Operator + aggregations: sum(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (_col2 > 0) (type: boolean) + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int) + expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 12 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 2 Execution mode: llap Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial + Merge Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 + 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: boolean) - Reducer 14 + Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 26 Data size: 312 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 + Reducer 4 Execution mode: llap Reduce Operator Tree: Merge Join Operator @@ -6602,34 +5185,28 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 15 + Reducer 5 Execution mode: llap Reduce Operator Tree: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 + Inner Join 0 to 2 keys: 0 _col0 (type: int) 1 _col0 (type: int) - 2 _col2 (type: int) - outputColumnNames: _col7, _col8 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (CASE WHEN (_col8 is null) THEN (null) ELSE (_col7) END > 0) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reducer 16 + 2 _col0 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reducer 6 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -6641,7 +5218,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Reducer 19 + Reducer 9 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -6667,130 +5244,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Reducer 21 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: boolean) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col2 - Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col2 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 26 Data size: 312 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 - Reducer 5 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string), _col2 (type: int) - 1 _col0 (type: string), _col1 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 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: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join0 to 1 - Left Outer Join0 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col2 (type: int) - outputColumnNames: _col0, _col7, _col8 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (CASE WHEN (_col8 is null) THEN (null) ELSE (_col7) END > 0) (type: boolean) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col0) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reducer 7 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator @@ -6798,8 +5251,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[116][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[119][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select t1.p_size, (select count(*) from part p, part pp where p.p_size = pp.p_size and p.p_type = pp.p_type and (select sum(p_size) from part a1 where a1.p_partkey = p.p_partkey @@ -6842,8 +5294,7 @@ POSTHOOK: Input: default@part 2 28 46 28 23 28 -Warning: Shuffle Join MERGEJOIN[147][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[149][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[90][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain select t1.p_size, (select count(*) from part t2 where t2.p_partkey = t1.p_partkey group by t2.p_partkey), (select count(*) from part p, part pp where p.p_size = pp.p_size and p.p_type = pp.p_type @@ -6867,21 +5318,15 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 10 <- Map 13 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) - Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE) - Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE) - Reducer 15 <- Map 14 (SIMPLE_EDGE) - Reducer 17 <- Map 16 (SIMPLE_EDGE) - Reducer 19 <- Map 18 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) - Reducer 20 <- Reducer 19 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE) - Reducer 21 <- Reducer 20 (CUSTOM_SIMPLE_EDGE) - Reducer 24 <- Map 23 (SIMPLE_EDGE) - Reducer 26 <- Map 25 (SIMPLE_EDGE) - Reducer 3 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) - Reducer 4 <- Reducer 21 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) - Reducer 8 <- Map 7 (SIMPLE_EDGE) + Reducer 10 <- Reducer 14 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) + Reducer 11 <- Reducer 10 (CUSTOM_SIMPLE_EDGE) + Reducer 14 <- Map 13 (SIMPLE_EDGE) + Reducer 16 <- Map 15 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) + Reducer 3 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Map 4 (SIMPLE_EDGE) + Reducer 7 <- Map 6 (SIMPLE_EDGE) + Reducer 9 <- Map 12 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -6901,88 +5346,7 @@ STAGE PLANS: value expressions: _col1 (type: int) Execution mode: llap LLAP IO: no inputs - Map 13 - Map Operator Tree: - TableScan - alias: pp - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (p_type is not null and p_size is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_type (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 14 - Map Operator Tree: - TableScan - alias: a1 - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: p_partkey (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 52 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: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 16 - Map Operator Tree: - TableScan - alias: a1 - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(p_size) - keys: p_partkey (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 156 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: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: llap - LLAP IO: no inputs - Map 18 - Map Operator Tree: - TableScan - alias: p - Statistics: Num rows: 26 Data size: 2912 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (p_type is not null and p_size is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 2912 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_partkey (type: int), p_type (type: string), p_size (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 2912 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col2 (type: int) - Statistics: Num rows: 26 Data size: 2912 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: llap - LLAP IO: no inputs - Map 22 + Map 12 Map Operator Tree: TableScan alias: pp @@ -7001,7 +5365,7 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 23 + Map 13 Map Operator Tree: TableScan alias: a1 @@ -7021,7 +5385,7 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 25 + Map 15 Map Operator Tree: TableScan alias: a1 @@ -7043,7 +5407,7 @@ STAGE PLANS: value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs - Map 5 + Map 4 Map Operator Tree: TableScan alias: t2 @@ -7063,7 +5427,7 @@ STAGE PLANS: Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs - Map 7 + Map 6 Map Operator Tree: TableScan alias: t2 @@ -7085,7 +5449,7 @@ STAGE PLANS: value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs - Map 9 + Map 8 Map Operator Tree: TableScan alias: p @@ -7110,175 +5474,23 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string), _col2 (type: int) - 1 _col0 (type: string), _col1 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 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: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 11 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 + Inner Join 0 to 2 keys: 0 _col0 (type: int) 1 _col0 (type: int) - 2 _col2 (type: int) - outputColumnNames: _col0, _col7, _col8 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (CASE WHEN (_col8 is null) THEN (null) ELSE (_col7) END > 0) (type: boolean) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col0) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reducer 12 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 + 2 _col0 (type: int) Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 15 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - keys: _col0 (type: int) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 48 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: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 17 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: boolean) - Reducer 19 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string), _col2 (type: int) - 1 _col0 (type: string), _col1 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 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: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join0 to 1 - Left Outer Join0 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col2 (type: int) - outputColumnNames: _col1, _col4, _col5 - Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: int), _col4 (type: bigint), _col5 (type: boolean) - Reducer 20 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join0 to 1 - Left Outer Join0 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col2 (type: int) - outputColumnNames: _col7, _col8 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (CASE WHEN (_col8 is null) THEN (null) ELSE (_col7) END > 0) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reducer 21 + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reducer 11 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -7290,7 +5502,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Reducer 24 + Reducer 14 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -7316,7 +5528,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 26 + Reducer 16 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -7326,31 +5538,39 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: _col0 (type: int), _col1 (type: bigint) + outputColumnNames: _col1, _col2 Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: boolean) - Reducer 3 + Filter Operator + predicate: (_col2 > 0) (type: boolean) + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 2 Execution mode: llap Reduce Operator Tree: Merge Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join0 to 1 + Left Outer Join0 to 2 keys: - 0 - 1 - outputColumnNames: _col1, _col4, _col5 - Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col1 (type: int) + outputColumnNames: _col1, _col4 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: int), _col4 (type: bigint), _col5 (type: boolean) - Reducer 4 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col4 (type: bigint) + Reducer 3 Execution mode: llap Reduce Operator Tree: Merge Join Operator @@ -7359,10 +5579,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col1, _col4, _col5, _col8 - Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col1, _col4, _col6 + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int), CASE WHEN (_col5 is null) THEN (0) ELSE (_col4) END (type: bigint), _col8 (type: bigint) + expressions: _col1 (type: int), _col4 (type: bigint), _col6 (type: bigint) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -7372,7 +5592,7 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 6 + Reducer 5 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -7398,7 +5618,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 8 + Reducer 7 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -7408,15 +5628,31 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE + expressions: _col1 (type: bigint), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col2 (type: int) + key expressions: _col1 (type: int) sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: boolean) + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reducer 9 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string), _col2 (type: int) + 1 _col0 (type: string), _col1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 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: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator @@ -7424,8 +5660,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[147][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[149][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[90][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 3' is a cross product PREHOOK: query: select t1.p_size, (select count(*) from part t2 where t2.p_partkey = t1.p_partkey group by t2.p_partkey), (select count(*) from part p, part pp where p.p_size = pp.p_size and p.p_type = pp.p_type @@ -7483,9 +5718,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -7509,26 +5743,6 @@ STAGE PLANS: Map Operator Tree: TableScan alias: p - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_type is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: p_type (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1352 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: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: p Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_type is not null (type: boolean) @@ -7553,20 +5767,18 @@ STAGE PLANS: Merge Join Operator condition map: Left Outer Join0 to 1 - Left Outer Join0 to 2 keys: 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col2 (type: string) - outputColumnNames: _col1, _col4, _col5 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + 1 _col2 (type: string) + outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int), exp(CASE WHEN (_col5 is null) THEN (null) ELSE (_col4) END) (type: double) + expressions: _col1 (type: int), exp(CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -7575,32 +5787,6 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (sq_count_check(_col1) <= 1) (type: boolean) - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 448 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: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Group By Operator aggregations: max(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial diff --git a/ql/src/test/results/clientpositive/perf/query1.q.out b/ql/src/test/results/clientpositive/perf/query1.q.out index 07828dac16..d84c76d166 100644 --- a/ql/src/test/results/clientpositive/perf/query1.q.out +++ b/ql/src/test/results/clientpositive/perf/query1.q.out @@ -47,175 +47,127 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 13 <- Map 12 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) -Reducer 14 <- Reducer 13 (SIMPLE_EDGE) -Reducer 17 <- Map 16 (SIMPLE_EDGE), Map 19 (SIMPLE_EDGE) -Reducer 18 <- Reducer 17 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) +Reducer 13 <- Reducer 12 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 11 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 14 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Reducer 18 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 7 (SIMPLE_EDGE) +Reducer 4 <- Map 9 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 10 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 13 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 8 - File Output Operator [FS_82] - Limit [LIM_81] (rows=100 width=860) + Reducer 7 + File Output Operator [FS_54] + Limit [LIM_53] (rows=100 width=860) Number of rows:100 - Select Operator [SEL_80] (rows=35493335 width=860) + Select Operator [SEL_52] (rows=32266667 width=860) Output:["_col0"] - <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_79] - Select Operator [SEL_78] (rows=35493335 width=860) + <-Reducer 6 [SIMPLE_EDGE] + SHUFFLE [RS_51] + Select Operator [SEL_50] (rows=32266667 width=860) Output:["_col0"] - Filter Operator [FIL_77] (rows=35493335 width=860) - predicate:(_col2 > CASE WHEN (_col10 is null) THEN (null) ELSE (_col9) END) - Merge Join Operator [MERGEJOIN_114] (rows=106480005 width=860) - Conds:RS_74._col1=RS_75._col2(Left Outer),Output:["_col2","_col6","_col9","_col10"] - <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_75] + Filter Operator [FIL_49] (rows=32266667 width=860) + predicate:(_col2 > CASE WHEN (_col8 is null) THEN (null) ELSE (_col7) END) + Merge Join Operator [MERGEJOIN_78] (rows=96800003 width=860) + Conds:RS_45._col1=RS_46._col2(Left Outer),Output:["_col2","_col6","_col7","_col8"] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_46] PartitionCols:_col2 - Select Operator [SEL_73] (rows=15837566 width=77) + Select Operator [SEL_38] (rows=15837566 width=77) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_72] (rows=15837566 width=77) + Group By Operator [GBY_37] (rows=15837566 width=77) Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col1 - Select Operator [SEL_68] (rows=31675133 width=77) + Select Operator [SEL_33] (rows=31675133 width=77) Output:["_col1","_col2"] - Group By Operator [GBY_67] (rows=31675133 width=77) + Group By Operator [GBY_32] (rows=31675133 width=77) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_66] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_31] PartitionCols:_col0 - Group By Operator [GBY_65] (rows=63350266 width=77) + Group By Operator [GBY_30] (rows=63350266 width=77) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1 - Merge Join Operator [MERGEJOIN_112] (rows=63350266 width=77) - Conds:RS_61._col0=RS_62._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 16 [SIMPLE_EDGE] - SHUFFLE [RS_61] + Merge Join Operator [MERGEJOIN_77] (rows=63350266 width=77) + Conds:RS_26._col0=RS_27._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 11 [SIMPLE_EDGE] + SHUFFLE [RS_26] PartitionCols:_col0 - Select Operator [SEL_57] (rows=57591150 width=77) + Select Operator [SEL_22] (rows=57591150 width=77) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_106] (rows=57591150 width=77) + Filter Operator [FIL_72] (rows=57591150 width=77) predicate:(sr_returned_date_sk is not null and sr_store_sk is not null) - TableScan [TS_55] (rows=57591150 width=77) + TableScan [TS_20] (rows=57591150 width=77) default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_customer_sk","sr_store_sk","sr_fee"] - <-Map 19 [SIMPLE_EDGE] - SHUFFLE [RS_62] + <-Map 14 [SIMPLE_EDGE] + SHUFFLE [RS_27] PartitionCols:_col0 - Select Operator [SEL_60] (rows=36524 width=1119) + Select Operator [SEL_25] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_107] (rows=36524 width=1119) + Filter Operator [FIL_73] (rows=36524 width=1119) predicate:((d_year = 2000) and d_date_sk is not null) - TableScan [TS_58] (rows=73049 width=1119) + TableScan [TS_23] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_74] + <-Reducer 5 [SIMPLE_EDGE] + SHUFFLE [RS_45] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_113] (rows=96800003 width=860) - Conds:RS_51._col1=RS_52._col0(Left Outer),Output:["_col1","_col2","_col6"] - <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_52] + Merge Join Operator [MERGEJOIN_76] (rows=88000001 width=860) + Conds:RS_42._col0=RS_43._col0(Inner),Output:["_col1","_col2","_col6"] + <-Map 10 [SIMPLE_EDGE] + SHUFFLE [RS_43] PartitionCols:_col0 - Select Operator [SEL_44] (rows=2639594 width=77) - Output:["_col0"] - Filter Operator [FIL_43] (rows=2639594 width=77) - predicate:(sq_count_check(_col1) <= 1) - Group By Operator [GBY_42] (rows=7918783 width=77) - Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Group By Operator [GBY_37] (rows=15837566 width=77) - Output:["_col0"],keys:_col1 - Select Operator [SEL_33] (rows=31675133 width=77) - Output:["_col1"] - Group By Operator [GBY_32] (rows=31675133 width=77) - Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_31] - PartitionCols:_col0 - Group By Operator [GBY_30] (rows=63350266 width=77) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1 - Merge Join Operator [MERGEJOIN_111] (rows=63350266 width=77) - Conds:RS_26._col0=RS_27._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 12 [SIMPLE_EDGE] - SHUFFLE [RS_26] - PartitionCols:_col0 - Select Operator [SEL_22] (rows=57591150 width=77) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_104] (rows=57591150 width=77) - predicate:(sr_returned_date_sk is not null and sr_store_sk is not null) - TableScan [TS_20] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_customer_sk","sr_store_sk","sr_fee"] - <-Map 15 [SIMPLE_EDGE] - SHUFFLE [RS_27] - PartitionCols:_col0 - Select Operator [SEL_25] (rows=36524 width=1119) - Output:["_col0"] - Filter Operator [FIL_105] (rows=36524 width=1119) - predicate:((d_year = 2000) and d_date_sk is not null) - TableScan [TS_23] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Reducer 5 [SIMPLE_EDGE] - SHUFFLE [RS_51] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_110] (rows=88000001 width=860) - Conds:RS_48._col0=RS_49._col0(Inner),Output:["_col1","_col2","_col6"] - <-Map 11 [SIMPLE_EDGE] - SHUFFLE [RS_49] - PartitionCols:_col0 - Select Operator [SEL_19] (rows=80000000 width=860) - Output:["_col0","_col1"] - Filter Operator [FIL_103] (rows=80000000 width=860) - predicate:c_customer_sk is not null - TableScan [TS_17] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_48] + Select Operator [SEL_19] (rows=80000000 width=860) + Output:["_col0","_col1"] + Filter Operator [FIL_71] (rows=80000000 width=860) + predicate:c_customer_sk is not null + TableScan [TS_17] (rows=80000000 width=860) + default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_42] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_75] (rows=34842647 width=77) + Conds:RS_39._col1=RS_40._col0(Inner),Output:["_col0","_col1","_col2"] + <-Map 9 [SIMPLE_EDGE] + SHUFFLE [RS_40] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_109] (rows=34842647 width=77) - Conds:RS_45._col1=RS_46._col0(Inner),Output:["_col0","_col1","_col2"] - <-Map 10 [SIMPLE_EDGE] - SHUFFLE [RS_46] - PartitionCols:_col0 - Select Operator [SEL_16] (rows=852 width=1910) - Output:["_col0"] - Filter Operator [FIL_102] (rows=852 width=1910) - predicate:((s_state = 'NM') and s_store_sk is not null) - TableScan [TS_14] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_state"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_45] - PartitionCols:_col1 - Select Operator [SEL_13] (rows=31675133 width=77) - Output:["_col0","_col1","_col2"] - Group By Operator [GBY_12] (rows=31675133 width=77) - Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_11] - PartitionCols:_col0, _col1 - Group By Operator [GBY_10] (rows=63350266 width=77) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1 - Merge Join Operator [MERGEJOIN_108] (rows=63350266 width=77) - Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_6] - PartitionCols:_col0 - Select Operator [SEL_2] (rows=57591150 width=77) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_100] (rows=57591150 width=77) - predicate:(sr_returned_date_sk is not null and sr_store_sk is not null and sr_customer_sk is not null) - TableScan [TS_0] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_customer_sk","sr_store_sk","sr_fee"] - <-Map 9 [SIMPLE_EDGE] - SHUFFLE [RS_7] - PartitionCols:_col0 - Select Operator [SEL_5] (rows=36524 width=1119) - Output:["_col0"] - Filter Operator [FIL_101] (rows=36524 width=1119) - predicate:((d_year = 2000) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + Select Operator [SEL_16] (rows=852 width=1910) + Output:["_col0"] + Filter Operator [FIL_70] (rows=852 width=1910) + predicate:((s_state = 'NM') and s_store_sk is not null) + TableScan [TS_14] (rows=1704 width=1910) + default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_state"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_39] + PartitionCols:_col1 + Select Operator [SEL_13] (rows=31675133 width=77) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_12] (rows=31675133 width=77) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_11] + PartitionCols:_col0, _col1 + Group By Operator [GBY_10] (rows=63350266 width=77) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1 + Merge Join Operator [MERGEJOIN_74] (rows=63350266 width=77) + Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_6] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=57591150 width=77) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_68] (rows=57591150 width=77) + predicate:(sr_returned_date_sk is not null and sr_store_sk is not null and sr_customer_sk is not null) + TableScan [TS_0] (rows=57591150 width=77) + default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_customer_sk","sr_store_sk","sr_fee"] + <-Map 8 [SIMPLE_EDGE] + SHUFFLE [RS_7] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_69] (rows=36524 width=1119) + predicate:((d_year = 2000) and d_date_sk is not null) + TableScan [TS_3] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] diff --git a/ql/src/test/results/clientpositive/perf/query30.q.out b/ql/src/test/results/clientpositive/perf/query30.q.out index 72871f4f24..4b7d949248 100644 --- a/ql/src/test/results/clientpositive/perf/query30.q.out +++ b/ql/src/test/results/clientpositive/perf/query30.q.out @@ -59,222 +59,159 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE) -Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 18 (SIMPLE_EDGE) -Reducer 16 <- Map 19 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 17 <- Reducer 16 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) -Reducer 21 <- Map 20 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE) -Reducer 22 <- Map 25 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) -Reducer 23 <- Reducer 22 (SIMPLE_EDGE) -Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 23 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 4 (SIMPLE_EDGE) -Reducer 8 <- Map 12 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 9 <- Map 13 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 10 <- Reducer 16 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) +Reducer 15 <- Map 18 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) +Reducer 16 <- Reducer 15 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 7 <- Map 11 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 8 <- Map 12 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 5 - File Output Operator [FS_101] - Limit [LIM_100] (rows=100 width=860) + Reducer 4 + File Output Operator [FS_67] + Limit [LIM_66] (rows=100 width=860) Number of rows:100 - Select Operator [SEL_99] (rows=35493335 width=860) + Select Operator [SEL_65] (rows=32266667 width=860) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_98] - Select Operator [SEL_97] (rows=35493335 width=860) + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_64] + Select Operator [SEL_63] (rows=32266667 width=860) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - Filter Operator [FIL_96] (rows=35493335 width=860) - predicate:(_col2 > CASE WHEN (_col22 is null) THEN (null) ELSE (_col21) END) - Merge Join Operator [MERGEJOIN_153] (rows=106480005 width=860) - Conds:RS_93._col1=RS_94._col2(Left Outer),Output:["_col2","_col6","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col21","_col22"] - <-Reducer 23 [SIMPLE_EDGE] - SHUFFLE [RS_94] - PartitionCols:_col2 - Select Operator [SEL_92] (rows=11000000 width=1014) - Output:["_col0","_col1","_col2"] - Group By Operator [GBY_91] (rows=11000000 width=1014) - Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col0 - Select Operator [SEL_87] (rows=22000000 width=1014) - Output:["_col0","_col2"] - Group By Operator [GBY_86] (rows=22000000 width=1014) - Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 22 [SIMPLE_EDGE] - SHUFFLE [RS_85] - PartitionCols:_col0 - Group By Operator [GBY_84] (rows=44000000 width=1014) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 - Merge Join Operator [MERGEJOIN_150] (rows=44000000 width=1014) - Conds:RS_80._col2=RS_81._col0(Inner),Output:["_col1","_col3","_col7"] - <-Map 25 [SIMPLE_EDGE] - SHUFFLE [RS_81] - PartitionCols:_col0 - Select Operator [SEL_76] (rows=40000000 width=1014) - Output:["_col0","_col1"] - Filter Operator [FIL_143] (rows=40000000 width=1014) - predicate:(ca_address_sk is not null and ca_state is not null) - TableScan [TS_74] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] - <-Reducer 21 [SIMPLE_EDGE] - SHUFFLE [RS_80] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_149] (rows=15838314 width=92) - Conds:RS_77._col0=RS_78._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 20 [SIMPLE_EDGE] - SHUFFLE [RS_77] - PartitionCols:_col0 - Select Operator [SEL_70] (rows=14398467 width=92) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_141] (rows=14398467 width=92) - predicate:(wr_returned_date_sk is not null and wr_returning_addr_sk is not null) - TableScan [TS_68] (rows=14398467 width=92) - default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_returning_customer_sk","wr_returning_addr_sk","wr_return_amt"] - <-Map 24 [SIMPLE_EDGE] - SHUFFLE [RS_78] - PartitionCols:_col0 - Select Operator [SEL_73] (rows=36524 width=1119) - Output:["_col0"] - Filter Operator [FIL_142] (rows=36524 width=1119) - predicate:((d_year = 2002) and d_date_sk is not null) - TableScan [TS_71] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_93] - PartitionCols:_col1 - Select Operator [SEL_67] (rows=96800003 width=860) - Output:["_col1","_col2","_col6","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"] - Merge Join Operator [MERGEJOIN_152] (rows=96800003 width=860) - Conds:RS_64._col0=RS_65._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col17","_col18"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_65] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_151] (rows=24200000 width=1014) - Conds:RS_57._col1=RS_58._col0(Left Outer),Output:["_col0","_col1","_col2"] - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_57] - PartitionCols:_col1 - Select Operator [SEL_25] (rows=22000000 width=1014) - Output:["_col0","_col1","_col2"] - Group By Operator [GBY_24] (rows=22000000 width=1014) + Filter Operator [FIL_62] (rows=32266667 width=860) + predicate:(_col2 > CASE WHEN (_col20 is null) THEN (null) ELSE (_col19) END) + Select Operator [SEL_61] (rows=96800003 width=860) + Output:["_col2","_col6","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20"] + Merge Join Operator [MERGEJOIN_105] (rows=96800003 width=860) + Conds:RS_58._col0=RS_59._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col18","_col19","_col20"] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_59] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_104] (rows=24200000 width=1014) + Conds:RS_51._col1=RS_52._col2(Left Outer),Output:["_col0","_col2","_col3","_col4"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_52] + PartitionCols:_col2 + Select Operator [SEL_50] (rows=11000000 width=1014) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_49] (rows=11000000 width=1014) + Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col0 + Select Operator [SEL_45] (rows=22000000 width=1014) + Output:["_col0","_col2"] + Group By Operator [GBY_44] (rows=22000000 width=1014) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_23] - PartitionCols:_col0, _col1 - Group By Operator [GBY_22] (rows=44000000 width=1014) + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_43] + PartitionCols:_col0 + Group By Operator [GBY_42] (rows=44000000 width=1014) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 - Merge Join Operator [MERGEJOIN_146] (rows=44000000 width=1014) - Conds:RS_18._col2=RS_19._col0(Inner),Output:["_col1","_col3","_col7"] - <-Map 13 [SIMPLE_EDGE] - SHUFFLE [RS_19] + Merge Join Operator [MERGEJOIN_103] (rows=44000000 width=1014) + Conds:RS_38._col2=RS_39._col0(Inner),Output:["_col1","_col3","_col7"] + <-Map 18 [SIMPLE_EDGE] + SHUFFLE [RS_39] PartitionCols:_col0 - Select Operator [SEL_14] (rows=40000000 width=1014) + Select Operator [SEL_34] (rows=40000000 width=1014) Output:["_col0","_col1"] - Filter Operator [FIL_137] (rows=40000000 width=1014) - predicate:ca_address_sk is not null - TableScan [TS_12] (rows=40000000 width=1014) + Filter Operator [FIL_98] (rows=40000000 width=1014) + predicate:(ca_address_sk is not null and ca_state is not null) + TableScan [TS_32] (rows=40000000 width=1014) default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] - <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_18] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_38] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_145] (rows=15838314 width=92) - Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 12 [SIMPLE_EDGE] - SHUFFLE [RS_16] + Merge Join Operator [MERGEJOIN_102] (rows=15838314 width=92) + Conds:RS_35._col0=RS_36._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 13 [SIMPLE_EDGE] + SHUFFLE [RS_35] + PartitionCols:_col0 + Select Operator [SEL_28] (rows=14398467 width=92) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_96] (rows=14398467 width=92) + predicate:(wr_returned_date_sk is not null and wr_returning_addr_sk is not null) + TableScan [TS_26] (rows=14398467 width=92) + default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_returning_customer_sk","wr_returning_addr_sk","wr_return_amt"] + <-Map 17 [SIMPLE_EDGE] + SHUFFLE [RS_36] PartitionCols:_col0 - Select Operator [SEL_11] (rows=36524 width=1119) + Select Operator [SEL_31] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_136] (rows=36524 width=1119) + Filter Operator [FIL_97] (rows=36524 width=1119) predicate:((d_year = 2002) and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=1119) + TableScan [TS_29] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Map 7 [SIMPLE_EDGE] - SHUFFLE [RS_15] - PartitionCols:_col0 - Select Operator [SEL_8] (rows=14398467 width=92) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_135] (rows=14398467 width=92) - predicate:(wr_returned_date_sk is not null and wr_returning_addr_sk is not null and wr_returning_customer_sk is not null) - TableScan [TS_6] (rows=14398467 width=92) - default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_returning_customer_sk","wr_returning_addr_sk","wr_return_amt"] - <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_58] - PartitionCols:_col0 - Select Operator [SEL_56] (rows=1833333 width=1014) - Output:["_col0"] - Filter Operator [FIL_55] (rows=1833333 width=1014) - predicate:(sq_count_check(_col1) <= 1) - Group By Operator [GBY_54] (rows=5500000 width=1014) - Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Group By Operator [GBY_49] (rows=11000000 width=1014) - Output:["_col0"],keys:_col0 - Select Operator [SEL_45] (rows=22000000 width=1014) - Output:["_col0"] - Group By Operator [GBY_44] (rows=22000000 width=1014) - Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_43] - PartitionCols:_col0 - Group By Operator [GBY_42] (rows=44000000 width=1014) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 - Merge Join Operator [MERGEJOIN_148] (rows=44000000 width=1014) - Conds:RS_38._col2=RS_39._col0(Inner),Output:["_col1","_col3","_col7"] - <-Map 19 [SIMPLE_EDGE] - SHUFFLE [RS_39] - PartitionCols:_col0 - Select Operator [SEL_34] (rows=40000000 width=1014) - Output:["_col0","_col1"] - Filter Operator [FIL_140] (rows=40000000 width=1014) - predicate:(ca_address_sk is not null and ca_state is not null) - TableScan [TS_32] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] - <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_38] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_147] (rows=15838314 width=92) - Conds:RS_35._col0=RS_36._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 14 [SIMPLE_EDGE] - SHUFFLE [RS_35] - PartitionCols:_col0 - Select Operator [SEL_28] (rows=14398467 width=92) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_138] (rows=14398467 width=92) - predicate:(wr_returned_date_sk is not null and wr_returning_addr_sk is not null) - TableScan [TS_26] (rows=14398467 width=92) - default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_returning_customer_sk","wr_returning_addr_sk","wr_return_amt"] - <-Map 18 [SIMPLE_EDGE] - SHUFFLE [RS_36] - PartitionCols:_col0 - Select Operator [SEL_31] (rows=36524 width=1119) - Output:["_col0"] - Filter Operator [FIL_139] (rows=36524 width=1119) - predicate:((d_year = 2002) and d_date_sk is not null) - TableScan [TS_29] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_64] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_51] + PartitionCols:_col1 + Select Operator [SEL_25] (rows=22000000 width=1014) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_24] (rows=22000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_23] + PartitionCols:_col0, _col1 + Group By Operator [GBY_22] (rows=44000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 + Merge Join Operator [MERGEJOIN_101] (rows=44000000 width=1014) + Conds:RS_18._col2=RS_19._col0(Inner),Output:["_col1","_col3","_col7"] + <-Map 12 [SIMPLE_EDGE] + SHUFFLE [RS_19] + PartitionCols:_col0 + Select Operator [SEL_14] (rows=40000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_95] (rows=40000000 width=1014) + predicate:ca_address_sk is not null + TableScan [TS_12] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] + <-Reducer 7 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_100] (rows=15838314 width=92) + Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 11 [SIMPLE_EDGE] + SHUFFLE [RS_16] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_94] (rows=36524 width=1119) + predicate:((d_year = 2002) and d_date_sk is not null) + TableScan [TS_9] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Map 6 [SIMPLE_EDGE] + SHUFFLE [RS_15] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=14398467 width=92) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_93] (rows=14398467 width=92) + predicate:(wr_returned_date_sk is not null and wr_returning_addr_sk is not null and wr_returning_customer_sk is not null) + TableScan [TS_6] (rows=14398467 width=92) + default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_returning_customer_sk","wr_returning_addr_sk","wr_return_amt"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_58] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_99] (rows=88000001 width=860) + Conds:RS_55._col2=RS_56._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_55] + PartitionCols:_col2 + Select Operator [SEL_2] (rows=80000000 width=860) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + Filter Operator [FIL_91] (rows=80000000 width=860) + predicate:(c_customer_sk is not null and c_current_addr_sk is not null) + TableScan [TS_0] (rows=80000000 width=860) + default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_current_addr_sk","c_salutation","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_day","c_birth_month","c_birth_year","c_birth_country","c_login","c_email_address","c_last_review_date"] + <-Map 5 [SIMPLE_EDGE] + SHUFFLE [RS_56] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_144] (rows=88000001 width=860) - Conds:RS_61._col2=RS_62._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_61] - PartitionCols:_col2 - Select Operator [SEL_2] (rows=80000000 width=860) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - Filter Operator [FIL_133] (rows=80000000 width=860) - predicate:(c_customer_sk is not null and c_current_addr_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_current_addr_sk","c_salutation","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_day","c_birth_month","c_birth_year","c_birth_country","c_login","c_email_address","c_last_review_date"] - <-Map 6 [SIMPLE_EDGE] - SHUFFLE [RS_62] - PartitionCols:_col0 - Select Operator [SEL_5] (rows=20000000 width=1014) - Output:["_col0"] - Filter Operator [FIL_134] (rows=20000000 width=1014) - predicate:((ca_state = 'IL') and ca_address_sk is not null) - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] + Select Operator [SEL_5] (rows=20000000 width=1014) + Output:["_col0"] + Filter Operator [FIL_92] (rows=20000000 width=1014) + predicate:((ca_state = 'IL') and ca_address_sk is not null) + TableScan [TS_3] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] diff --git a/ql/src/test/results/clientpositive/perf/query6.q.out b/ql/src/test/results/clientpositive/perf/query6.q.out index aede0d7068..183c2ec306 100644 --- a/ql/src/test/results/clientpositive/perf/query6.q.out +++ b/ql/src/test/results/clientpositive/perf/query6.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[129][tables = [$hdt$_5, $hdt$_6]] in Stage 'Reducer 17' is a cross product +Warning: Shuffle Join MERGEJOIN[111][tables = [$hdt$_5, $hdt$_6]] in Stage 'Reducer 16' is a cross product PREHOOK: query: explain select a.ca_state state, count(*) cnt from customer_address a ,customer c @@ -50,207 +50,180 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Map 9 (SIMPLE_EDGE) -Reducer 13 <- Map 12 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) -Reducer 16 <- Map 15 (SIMPLE_EDGE) -Reducer 17 <- Reducer 16 (CUSTOM_SIMPLE_EDGE), Reducer 21 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 22 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) -Reducer 20 <- Map 19 (SIMPLE_EDGE) -Reducer 21 <- Reducer 20 (CUSTOM_SIMPLE_EDGE) -Reducer 24 <- Map 23 (SIMPLE_EDGE) -Reducer 3 <- Map 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 18 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 24 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) +Reducer 15 <- Map 14 (SIMPLE_EDGE) +Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 20 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 21 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) +Reducer 19 <- Map 18 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 20 <- Reducer 19 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 17 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Map 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 8 - File Output Operator [FS_93] - Limit [LIM_92] (rows=100 width=88) + Reducer 7 + File Output Operator [FS_77] + Limit [LIM_76] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_91] (rows=46850848 width=88) + Select Operator [SEL_75] (rows=42591679 width=88) Output:["_col0","_col1"] - <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_90] - Filter Operator [FIL_88] (rows=46850848 width=88) + <-Reducer 6 [SIMPLE_EDGE] + SHUFFLE [RS_74] + Filter Operator [FIL_72] (rows=42591679 width=88) predicate:(_col1 >= 10) - Group By Operator [GBY_87] (rows=140552546 width=88) + Group By Operator [GBY_71] (rows=127775039 width=88) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 - <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_86] + <-Reducer 5 [SIMPLE_EDGE] + SHUFFLE [RS_70] PartitionCols:_col0 - Group By Operator [GBY_85] (rows=281105093 width=88) + Group By Operator [GBY_69] (rows=255550079 width=88) Output:["_col0","_col1"],aggregations:["count()"],keys:_col1 - Select Operator [SEL_84] (rows=281105093 width=88) + Select Operator [SEL_68] (rows=255550079 width=88) Output:["_col1"] - Filter Operator [FIL_83] (rows=281105093 width=88) - predicate:(_col10 > (1.2 * CASE WHEN (_col17 is null) THEN (null) ELSE (_col16) END)) - Merge Join Operator [MERGEJOIN_133] (rows=843315281 width=88) - Conds:RS_80._col11=RS_81._col2(Left Outer),Output:["_col1","_col10","_col16","_col17"] - <-Reducer 24 [SIMPLE_EDGE] - SHUFFLE [RS_81] - PartitionCols:_col2 - Select Operator [SEL_79] (rows=231000 width=1436) - Output:["_col0","_col1","_col2"] - Group By Operator [GBY_78] (rows=231000 width=1436) - Output:["_col0","_col1"],aggregations:["avg(VALUE._col0)"],keys:KEY._col0 - <-Map 23 [SIMPLE_EDGE] - SHUFFLE [RS_77] - PartitionCols:_col0 - Group By Operator [GBY_76] (rows=462000 width=1436) - Output:["_col0","_col1"],aggregations:["avg(i_current_price)"],keys:i_category - Filter Operator [FIL_125] (rows=462000 width=1436) - predicate:i_category is not null - TableScan [TS_73] (rows=462000 width=1436) - default@item,j,Tbl:COMPLETE,Col:NONE,Output:["i_current_price","i_category"] - <-Reducer 5 [SIMPLE_EDGE] - SHUFFLE [RS_80] - PartitionCols:_col11 - Select Operator [SEL_72] (rows=766650239 width=88) - Output:["_col1","_col10","_col11"] - Merge Join Operator [MERGEJOIN_132] (rows=766650239 width=88) - Conds:RS_69._col5=RS_70._col0(Inner),Output:["_col1","_col2","_col11"] - <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_70] + Filter Operator [FIL_67] (rows=255550079 width=88) + predicate:(_col10 > (1.2 * CASE WHEN (_col15 is null) THEN (null) ELSE (_col14) END)) + Select Operator [SEL_66] (rows=766650239 width=88) + Output:["_col1","_col10","_col14","_col15"] + Merge Join Operator [MERGEJOIN_114] (rows=766650239 width=88) + Conds:RS_63._col6=RS_64._col0(Inner),Output:["_col1","_col3","_col4","_col12"] + <-Reducer 17 [SIMPLE_EDGE] + SHUFFLE [RS_64] + PartitionCols:_col0 + Select Operator [SEL_53] (rows=80353 width=1119) + Output:["_col0"] + Merge Join Operator [MERGEJOIN_112] (rows=80353 width=1119) + Conds:RS_50._col0=RS_51._col1(Inner),Output:["_col2"] + <-Map 21 [SIMPLE_EDGE] + SHUFFLE [RS_51] + PartitionCols:_col1 + Select Operator [SEL_46] (rows=73049 width=1119) + Output:["_col0","_col1"] + Filter Operator [FIL_107] (rows=73049 width=1119) + predicate:(d_date_sk is not null and d_month_seq is not null) + TableScan [TS_44] (rows=73049 width=1119) + default@date_dim,d,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_50] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_111] (rows=9131 width=1128) + Conds:(Inner),Output:["_col0"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_47] + Group By Operator [GBY_28] (rows=9131 width=1119) + Output:["_col0"],keys:KEY._col0 + <-Map 14 [SIMPLE_EDGE] + SHUFFLE [RS_27] + PartitionCols:_col0 + Group By Operator [GBY_26] (rows=18262 width=1119) + Output:["_col0"],keys:d_month_seq + Select Operator [SEL_25] (rows=18262 width=1119) + Output:["d_month_seq"] + Filter Operator [FIL_105] (rows=18262 width=1119) + predicate:((d_year = 2000) and (d_moy = 2) and d_month_seq is not null) + TableScan [TS_23] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_month_seq","d_year","d_moy"] + <-Reducer 20 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_48] + Select Operator [SEL_43] (rows=1 width=8) + Filter Operator [FIL_42] (rows=1 width=8) + predicate:(sq_count_check(_col0) <= 1) + Group By Operator [GBY_40] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Reducer 19 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_39] + Group By Operator [GBY_38] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_36] (rows=9131 width=1119) + Group By Operator [GBY_35] (rows=9131 width=1119) + Output:["_col0"],keys:KEY._col0 + <-Map 18 [SIMPLE_EDGE] + SHUFFLE [RS_34] + PartitionCols:_col0 + Group By Operator [GBY_33] (rows=18262 width=1119) + Output:["_col0"],keys:d_month_seq + Select Operator [SEL_32] (rows=18262 width=1119) + Output:["d_month_seq"] + Filter Operator [FIL_106] (rows=18262 width=1119) + predicate:((d_year = 2000) and (d_moy = 2)) + TableScan [TS_30] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_month_seq","d_year","d_moy"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_63] + PartitionCols:_col6 + Merge Join Operator [MERGEJOIN_113] (rows=696954748 width=88) + Conds:RS_60._col8=RS_61._col0(Inner),Output:["_col1","_col3","_col4","_col6","_col12"] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_61] PartitionCols:_col0 - Select Operator [SEL_59] (rows=80353 width=1119) - Output:["_col0"] - Merge Join Operator [MERGEJOIN_130] (rows=80353 width=1119) - Conds:RS_56._col0=RS_57._col1(Inner),Output:["_col2"] - <-Map 22 [SIMPLE_EDGE] - SHUFFLE [RS_57] - PartitionCols:_col1 - Select Operator [SEL_52] (rows=73049 width=1119) - Output:["_col0","_col1"] - Filter Operator [FIL_124] (rows=73049 width=1119) - predicate:(d_date_sk is not null and d_month_seq is not null) - TableScan [TS_50] (rows=73049 width=1119) - default@date_dim,d,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] - <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_56] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_129] (rows=9131 width=1128) - Conds:(Inner),Output:["_col0"] - <-Reducer 16 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_53] - Group By Operator [GBY_34] (rows=9131 width=1119) - Output:["_col0"],keys:KEY._col0 - <-Map 15 [SIMPLE_EDGE] - SHUFFLE [RS_33] - PartitionCols:_col0 - Group By Operator [GBY_32] (rows=18262 width=1119) - Output:["_col0"],keys:d_month_seq - Select Operator [SEL_31] (rows=18262 width=1119) - Output:["d_month_seq"] - Filter Operator [FIL_122] (rows=18262 width=1119) - predicate:((d_year = 2000) and (d_moy = 2) and d_month_seq is not null) - TableScan [TS_29] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_month_seq","d_year","d_moy"] - <-Reducer 21 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_54] - Select Operator [SEL_49] (rows=1 width=8) - Filter Operator [FIL_48] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_46] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 20 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_45] - Group By Operator [GBY_44] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_42] (rows=9131 width=1119) - Group By Operator [GBY_41] (rows=9131 width=1119) - Output:["_col0"],keys:KEY._col0 - <-Map 19 [SIMPLE_EDGE] - SHUFFLE [RS_40] - PartitionCols:_col0 - Group By Operator [GBY_39] (rows=18262 width=1119) - Output:["_col0"],keys:d_month_seq - Select Operator [SEL_38] (rows=18262 width=1119) - Output:["d_month_seq"] - Filter Operator [FIL_123] (rows=18262 width=1119) - predicate:((d_year = 2000) and (d_moy = 2)) - TableScan [TS_36] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_month_seq","d_year","d_moy"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_69] - PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_131] (rows=696954748 width=88) - Conds:RS_66._col7=RS_67._col0(Inner),Output:["_col1","_col2","_col5","_col11"] - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_67] + Merge Join Operator [MERGEJOIN_110] (rows=88000001 width=860) + Conds:RS_19._col1=RS_20._col0(Inner),Output:["_col0","_col3"] + <-Map 11 [SIMPLE_EDGE] + SHUFFLE [RS_19] + PartitionCols:_col1 + Select Operator [SEL_15] (rows=80000000 width=860) + Output:["_col0","_col1"] + Filter Operator [FIL_103] (rows=80000000 width=860) + predicate:(c_current_addr_sk is not null and c_customer_sk is not null) + TableScan [TS_13] (rows=80000000 width=860) + default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] + <-Map 13 [SIMPLE_EDGE] + SHUFFLE [RS_20] + PartitionCols:_col0 + Select Operator [SEL_18] (rows=40000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_104] (rows=40000000 width=1014) + predicate:ca_address_sk is not null + TableScan [TS_16] (rows=40000000 width=1014) + default@customer_address,a,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_60] + PartitionCols:_col8 + Merge Join Operator [MERGEJOIN_109] (rows=633595212 width=88) + Conds:RS_57._col0=RS_58._col1(Inner),Output:["_col1","_col3","_col4","_col6","_col8"] + <-Map 10 [SIMPLE_EDGE] + SHUFFLE [RS_58] + PartitionCols:_col1 + Select Operator [SEL_12] (rows=575995635 width=88) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_102] (rows=575995635 width=88) + predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null and ss_item_sk is not null) + TableScan [TS_10] (rows=575995635 width=88) + default@store_sales,s,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_57] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_128] (rows=88000001 width=860) - Conds:RS_25._col1=RS_26._col0(Inner),Output:["_col0","_col3"] - <-Map 12 [SIMPLE_EDGE] - SHUFFLE [RS_25] - PartitionCols:_col1 - Select Operator [SEL_21] (rows=80000000 width=860) - Output:["_col0","_col1"] - Filter Operator [FIL_120] (rows=80000000 width=860) - predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_19] (rows=80000000 width=860) - default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] - <-Map 14 [SIMPLE_EDGE] - SHUFFLE [RS_26] - PartitionCols:_col0 - Select Operator [SEL_24] (rows=40000000 width=1014) - Output:["_col0","_col1"] - Filter Operator [FIL_121] (rows=40000000 width=1014) - predicate:ca_address_sk is not null - TableScan [TS_22] (rows=40000000 width=1014) - default@customer_address,a,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_66] - PartitionCols:_col7 - Merge Join Operator [MERGEJOIN_127] (rows=633595212 width=88) - Conds:RS_63._col0=RS_64._col1(Inner),Output:["_col1","_col2","_col5","_col7"] - <-Map 11 [SIMPLE_EDGE] - SHUFFLE [RS_64] - PartitionCols:_col1 - Select Operator [SEL_18] (rows=575995635 width=88) + Merge Join Operator [MERGEJOIN_108] (rows=508200 width=1436) + Conds:RS_54._col2=RS_55._col2(Left Outer),Output:["_col0","_col1","_col3","_col4"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_54] + PartitionCols:_col2 + Select Operator [SEL_2] (rows=462000 width=1436) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_119] (rows=575995635 width=88) - predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null and ss_item_sk is not null) - TableScan [TS_16] (rows=575995635 width=88) - default@store_sales,s,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_63] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_126] (rows=508200 width=1436) - Conds:RS_60._col2=RS_61._col0(Left Outer),Output:["_col0","_col1","_col2"] - <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_60] - PartitionCols:_col2 - Select Operator [SEL_2] (rows=462000 width=1436) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_117] (rows=462000 width=1436) - predicate:i_item_sk is not null - TableScan [TS_0] (rows=462000 width=1436) - default@item,i,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_category"] - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_61] - PartitionCols:_col0 - Select Operator [SEL_15] (rows=38500 width=1436) - Output:["_col0"] - Filter Operator [FIL_14] (rows=38500 width=1436) - predicate:(sq_count_check(_col1) <= 1) - Group By Operator [GBY_13] (rows=115500 width=1436) - Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Group By Operator [GBY_8] (rows=231000 width=1436) - Output:["_col0"],keys:KEY._col0 - <-Map 9 [SIMPLE_EDGE] - SHUFFLE [RS_7] - PartitionCols:_col0 - Group By Operator [GBY_6] (rows=462000 width=1436) - Output:["_col0"],keys:i_category - Filter Operator [FIL_118] (rows=462000 width=1436) - predicate:i_category is not null - TableScan [TS_3] (rows=462000 width=1436) - default@item,j,Tbl:COMPLETE,Col:NONE,Output:["i_category"] + Filter Operator [FIL_100] (rows=462000 width=1436) + predicate:i_item_sk is not null + TableScan [TS_0] (rows=462000 width=1436) + default@item,i,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_category"] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_55] + PartitionCols:_col2 + Select Operator [SEL_9] (rows=231000 width=1436) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_8] (rows=231000 width=1436) + Output:["_col0","_col1"],aggregations:["avg(VALUE._col0)"],keys:KEY._col0 + <-Map 8 [SIMPLE_EDGE] + SHUFFLE [RS_7] + PartitionCols:_col0 + Group By Operator [GBY_6] (rows=462000 width=1436) + Output:["_col0","_col1"],aggregations:["avg(i_current_price)"],keys:i_category + Filter Operator [FIL_101] (rows=462000 width=1436) + predicate:i_category is not null + TableScan [TS_3] (rows=462000 width=1436) + default@item,j,Tbl:COMPLETE,Col:NONE,Output:["i_current_price","i_category"] diff --git a/ql/src/test/results/clientpositive/perf/query81.q.out b/ql/src/test/results/clientpositive/perf/query81.q.out index a09d5c99b5..769a3d1a20 100644 --- a/ql/src/test/results/clientpositive/perf/query81.q.out +++ b/ql/src/test/results/clientpositive/perf/query81.q.out @@ -59,222 +59,159 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE) -Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 18 (SIMPLE_EDGE) -Reducer 16 <- Map 19 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 17 <- Reducer 16 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) -Reducer 21 <- Map 20 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE) -Reducer 22 <- Map 25 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) -Reducer 23 <- Reducer 22 (SIMPLE_EDGE) -Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 23 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 4 (SIMPLE_EDGE) -Reducer 8 <- Map 12 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 9 <- Map 13 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 10 <- Reducer 16 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) +Reducer 15 <- Map 18 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) +Reducer 16 <- Reducer 15 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 7 <- Map 11 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 8 <- Map 12 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 5 - File Output Operator [FS_101] - Limit [LIM_100] (rows=100 width=860) + Reducer 4 + File Output Operator [FS_67] + Limit [LIM_66] (rows=100 width=860) Number of rows:100 - Select Operator [SEL_99] (rows=35493335 width=860) + Select Operator [SEL_65] (rows=32266667 width=860) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_98] - Select Operator [SEL_97] (rows=35493335 width=860) + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_64] + Select Operator [SEL_63] (rows=32266667 width=860) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col11","_col12","_col13","_col14","_col15"] - Filter Operator [FIL_96] (rows=35493335 width=860) - predicate:(_col2 > CASE WHEN (_col24 is null) THEN (null) ELSE (_col23) END) - Merge Join Operator [MERGEJOIN_153] (rows=106480005 width=860) - Conds:RS_93._col1=RS_94._col2(Left Outer),Output:["_col2","_col4","_col5","_col6","_col7","_col8","_col9","_col11","_col12","_col13","_col14","_col16","_col18","_col19","_col20","_col23","_col24"] - <-Reducer 23 [SIMPLE_EDGE] - SHUFFLE [RS_94] - PartitionCols:_col2 - Select Operator [SEL_92] (rows=11000000 width=1014) - Output:["_col0","_col1","_col2"] - Group By Operator [GBY_91] (rows=11000000 width=1014) - Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col0 - Select Operator [SEL_87] (rows=22000000 width=1014) - Output:["_col0","_col2"] - Group By Operator [GBY_86] (rows=22000000 width=1014) - Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 22 [SIMPLE_EDGE] - SHUFFLE [RS_85] - PartitionCols:_col0 - Group By Operator [GBY_84] (rows=44000000 width=1014) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 - Merge Join Operator [MERGEJOIN_150] (rows=44000000 width=1014) - Conds:RS_80._col2=RS_81._col0(Inner),Output:["_col1","_col3","_col7"] - <-Map 25 [SIMPLE_EDGE] - SHUFFLE [RS_81] - PartitionCols:_col0 - Select Operator [SEL_76] (rows=40000000 width=1014) - Output:["_col0","_col1"] - Filter Operator [FIL_143] (rows=40000000 width=1014) - predicate:(ca_address_sk is not null and ca_state is not null) - TableScan [TS_74] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] - <-Reducer 21 [SIMPLE_EDGE] - SHUFFLE [RS_80] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_149] (rows=31678769 width=106) - Conds:RS_77._col0=RS_78._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 20 [SIMPLE_EDGE] - SHUFFLE [RS_77] - PartitionCols:_col0 - Select Operator [SEL_70] (rows=28798881 width=106) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_141] (rows=28798881 width=106) - predicate:(cr_returned_date_sk is not null and cr_returning_addr_sk is not null) - TableScan [TS_68] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_returned_date_sk","cr_returning_customer_sk","cr_returning_addr_sk","cr_return_amt_inc_tax"] - <-Map 24 [SIMPLE_EDGE] - SHUFFLE [RS_78] - PartitionCols:_col0 - Select Operator [SEL_73] (rows=36524 width=1119) - Output:["_col0"] - Filter Operator [FIL_142] (rows=36524 width=1119) - predicate:((d_year = 1998) and d_date_sk is not null) - TableScan [TS_71] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_93] - PartitionCols:_col1 - Select Operator [SEL_67] (rows=96800003 width=860) - Output:["_col1","_col2","_col4","_col5","_col6","_col7","_col8","_col9","_col11","_col12","_col13","_col14","_col16","_col18","_col19","_col20"] - Merge Join Operator [MERGEJOIN_152] (rows=96800003 width=860) - Conds:RS_64._col0=RS_65._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17","_col19","_col20"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_65] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_151] (rows=24200000 width=1014) - Conds:RS_57._col1=RS_58._col0(Left Outer),Output:["_col0","_col1","_col2"] - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_57] - PartitionCols:_col1 - Select Operator [SEL_25] (rows=22000000 width=1014) - Output:["_col0","_col1","_col2"] - Group By Operator [GBY_24] (rows=22000000 width=1014) + Filter Operator [FIL_62] (rows=32266667 width=860) + predicate:(_col2 > CASE WHEN (_col22 is null) THEN (null) ELSE (_col21) END) + Select Operator [SEL_61] (rows=96800003 width=860) + Output:["_col2","_col4","_col5","_col6","_col7","_col8","_col9","_col11","_col12","_col13","_col14","_col16","_col18","_col19","_col20","_col21","_col22"] + Merge Join Operator [MERGEJOIN_105] (rows=96800003 width=860) + Conds:RS_58._col0=RS_59._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17","_col20","_col21","_col22"] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_59] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_104] (rows=24200000 width=1014) + Conds:RS_51._col1=RS_52._col2(Left Outer),Output:["_col0","_col2","_col3","_col4"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_52] + PartitionCols:_col2 + Select Operator [SEL_50] (rows=11000000 width=1014) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_49] (rows=11000000 width=1014) + Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col0 + Select Operator [SEL_45] (rows=22000000 width=1014) + Output:["_col0","_col2"] + Group By Operator [GBY_44] (rows=22000000 width=1014) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_23] - PartitionCols:_col0, _col1 - Group By Operator [GBY_22] (rows=44000000 width=1014) + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_43] + PartitionCols:_col0 + Group By Operator [GBY_42] (rows=44000000 width=1014) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 - Merge Join Operator [MERGEJOIN_146] (rows=44000000 width=1014) - Conds:RS_18._col2=RS_19._col0(Inner),Output:["_col1","_col3","_col7"] - <-Map 13 [SIMPLE_EDGE] - SHUFFLE [RS_19] + Merge Join Operator [MERGEJOIN_103] (rows=44000000 width=1014) + Conds:RS_38._col2=RS_39._col0(Inner),Output:["_col1","_col3","_col7"] + <-Map 18 [SIMPLE_EDGE] + SHUFFLE [RS_39] PartitionCols:_col0 - Select Operator [SEL_14] (rows=40000000 width=1014) + Select Operator [SEL_34] (rows=40000000 width=1014) Output:["_col0","_col1"] - Filter Operator [FIL_137] (rows=40000000 width=1014) - predicate:ca_address_sk is not null - TableScan [TS_12] (rows=40000000 width=1014) + Filter Operator [FIL_98] (rows=40000000 width=1014) + predicate:(ca_address_sk is not null and ca_state is not null) + TableScan [TS_32] (rows=40000000 width=1014) default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] - <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_18] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_38] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_145] (rows=31678769 width=106) - Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 12 [SIMPLE_EDGE] - SHUFFLE [RS_16] + Merge Join Operator [MERGEJOIN_102] (rows=31678769 width=106) + Conds:RS_35._col0=RS_36._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 13 [SIMPLE_EDGE] + SHUFFLE [RS_35] + PartitionCols:_col0 + Select Operator [SEL_28] (rows=28798881 width=106) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_96] (rows=28798881 width=106) + predicate:(cr_returned_date_sk is not null and cr_returning_addr_sk is not null) + TableScan [TS_26] (rows=28798881 width=106) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_returned_date_sk","cr_returning_customer_sk","cr_returning_addr_sk","cr_return_amt_inc_tax"] + <-Map 17 [SIMPLE_EDGE] + SHUFFLE [RS_36] PartitionCols:_col0 - Select Operator [SEL_11] (rows=36524 width=1119) + Select Operator [SEL_31] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_136] (rows=36524 width=1119) + Filter Operator [FIL_97] (rows=36524 width=1119) predicate:((d_year = 1998) and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=1119) + TableScan [TS_29] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Map 7 [SIMPLE_EDGE] - SHUFFLE [RS_15] - PartitionCols:_col0 - Select Operator [SEL_8] (rows=28798881 width=106) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_135] (rows=28798881 width=106) - predicate:(cr_returned_date_sk is not null and cr_returning_addr_sk is not null and cr_returning_customer_sk is not null) - TableScan [TS_6] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_returned_date_sk","cr_returning_customer_sk","cr_returning_addr_sk","cr_return_amt_inc_tax"] - <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_58] - PartitionCols:_col0 - Select Operator [SEL_56] (rows=1833333 width=1014) - Output:["_col0"] - Filter Operator [FIL_55] (rows=1833333 width=1014) - predicate:(sq_count_check(_col1) <= 1) - Group By Operator [GBY_54] (rows=5500000 width=1014) - Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Group By Operator [GBY_49] (rows=11000000 width=1014) - Output:["_col0"],keys:_col0 - Select Operator [SEL_45] (rows=22000000 width=1014) - Output:["_col0"] - Group By Operator [GBY_44] (rows=22000000 width=1014) - Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_43] - PartitionCols:_col0 - Group By Operator [GBY_42] (rows=44000000 width=1014) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 - Merge Join Operator [MERGEJOIN_148] (rows=44000000 width=1014) - Conds:RS_38._col2=RS_39._col0(Inner),Output:["_col1","_col3","_col7"] - <-Map 19 [SIMPLE_EDGE] - SHUFFLE [RS_39] - PartitionCols:_col0 - Select Operator [SEL_34] (rows=40000000 width=1014) - Output:["_col0","_col1"] - Filter Operator [FIL_140] (rows=40000000 width=1014) - predicate:(ca_address_sk is not null and ca_state is not null) - TableScan [TS_32] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] - <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_38] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_147] (rows=31678769 width=106) - Conds:RS_35._col0=RS_36._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 14 [SIMPLE_EDGE] - SHUFFLE [RS_35] - PartitionCols:_col0 - Select Operator [SEL_28] (rows=28798881 width=106) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_138] (rows=28798881 width=106) - predicate:(cr_returned_date_sk is not null and cr_returning_addr_sk is not null) - TableScan [TS_26] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_returned_date_sk","cr_returning_customer_sk","cr_returning_addr_sk","cr_return_amt_inc_tax"] - <-Map 18 [SIMPLE_EDGE] - SHUFFLE [RS_36] - PartitionCols:_col0 - Select Operator [SEL_31] (rows=36524 width=1119) - Output:["_col0"] - Filter Operator [FIL_139] (rows=36524 width=1119) - predicate:((d_year = 1998) and d_date_sk is not null) - TableScan [TS_29] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_64] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_51] + PartitionCols:_col1 + Select Operator [SEL_25] (rows=22000000 width=1014) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_24] (rows=22000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_23] + PartitionCols:_col0, _col1 + Group By Operator [GBY_22] (rows=44000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 + Merge Join Operator [MERGEJOIN_101] (rows=44000000 width=1014) + Conds:RS_18._col2=RS_19._col0(Inner),Output:["_col1","_col3","_col7"] + <-Map 12 [SIMPLE_EDGE] + SHUFFLE [RS_19] + PartitionCols:_col0 + Select Operator [SEL_14] (rows=40000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_95] (rows=40000000 width=1014) + predicate:ca_address_sk is not null + TableScan [TS_12] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] + <-Reducer 7 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_100] (rows=31678769 width=106) + Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 11 [SIMPLE_EDGE] + SHUFFLE [RS_16] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_94] (rows=36524 width=1119) + predicate:((d_year = 1998) and d_date_sk is not null) + TableScan [TS_9] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Map 6 [SIMPLE_EDGE] + SHUFFLE [RS_15] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=28798881 width=106) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_93] (rows=28798881 width=106) + predicate:(cr_returned_date_sk is not null and cr_returning_addr_sk is not null and cr_returning_customer_sk is not null) + TableScan [TS_6] (rows=28798881 width=106) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_returned_date_sk","cr_returning_customer_sk","cr_returning_addr_sk","cr_return_amt_inc_tax"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_58] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_99] (rows=88000001 width=860) + Conds:RS_55._col2=RS_56._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_55] + PartitionCols:_col2 + Select Operator [SEL_2] (rows=80000000 width=860) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_91] (rows=80000000 width=860) + predicate:(c_customer_sk is not null and c_current_addr_sk is not null) + TableScan [TS_0] (rows=80000000 width=860) + default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_current_addr_sk","c_salutation","c_first_name","c_last_name"] + <-Map 5 [SIMPLE_EDGE] + SHUFFLE [RS_56] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_144] (rows=88000001 width=860) - Conds:RS_61._col2=RS_62._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17"] - <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_61] - PartitionCols:_col2 - Select Operator [SEL_2] (rows=80000000 width=860) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_133] (rows=80000000 width=860) - predicate:(c_customer_sk is not null and c_current_addr_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_current_addr_sk","c_salutation","c_first_name","c_last_name"] - <-Map 6 [SIMPLE_EDGE] - SHUFFLE [RS_62] - PartitionCols:_col0 - Select Operator [SEL_5] (rows=20000000 width=1014) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col9","_col10","_col11"] - Filter Operator [FIL_134] (rows=20000000 width=1014) - predicate:((ca_state = 'IL') and ca_address_sk is not null) - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_street_type","ca_suite_number","ca_city","ca_county","ca_state","ca_zip","ca_country","ca_gmt_offset","ca_location_type"] + Select Operator [SEL_5] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col9","_col10","_col11"] + Filter Operator [FIL_92] (rows=20000000 width=1014) + predicate:((ca_state = 'IL') and ca_address_sk is not null) + TableScan [TS_3] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_street_type","ca_suite_number","ca_city","ca_county","ca_state","ca_zip","ca_country","ca_gmt_offset","ca_location_type"] diff --git a/ql/src/test/results/clientpositive/perf/query9.q.out b/ql/src/test/results/clientpositive/perf/query9.q.out index d714d411c4..3c913e1c51 100644 --- a/ql/src/test/results/clientpositive/perf/query9.q.out +++ b/ql/src/test/results/clientpositive/perf/query9.q.out @@ -1,33 +1,18 @@ -Warning: Shuffle Join MERGEJOIN[456][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[457][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product -Warning: Shuffle Join MERGEJOIN[458][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product -Warning: Shuffle Join MERGEJOIN[459][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product -Warning: Shuffle Join MERGEJOIN[460][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5]] in Stage 'Reducer 6' is a cross product -Warning: Shuffle Join MERGEJOIN[461][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6]] in Stage 'Reducer 7' is a cross product -Warning: Shuffle Join MERGEJOIN[462][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7]] in Stage 'Reducer 8' is a cross product -Warning: Shuffle Join MERGEJOIN[463][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8]] in Stage 'Reducer 9' is a cross product -Warning: Shuffle Join MERGEJOIN[464][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9]] in Stage 'Reducer 10' is a cross product -Warning: Shuffle Join MERGEJOIN[465][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10]] in Stage 'Reducer 11' is a cross product -Warning: Shuffle Join MERGEJOIN[466][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11]] in Stage 'Reducer 12' is a cross product -Warning: Shuffle Join MERGEJOIN[467][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12]] in Stage 'Reducer 13' is a cross product -Warning: Shuffle Join MERGEJOIN[468][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13]] in Stage 'Reducer 14' is a cross product -Warning: Shuffle Join MERGEJOIN[469][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14]] in Stage 'Reducer 15' is a cross product -Warning: Shuffle Join MERGEJOIN[470][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15]] in Stage 'Reducer 16' is a cross product -Warning: Shuffle Join MERGEJOIN[471][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16]] in Stage 'Reducer 17' is a cross product -Warning: Shuffle Join MERGEJOIN[472][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17]] in Stage 'Reducer 18' is a cross product -Warning: Shuffle Join MERGEJOIN[473][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18]] in Stage 'Reducer 19' is a cross product -Warning: Shuffle Join MERGEJOIN[474][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18, $hdt$_19]] in Stage 'Reducer 20' is a cross product -Warning: Shuffle Join MERGEJOIN[475][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18, $hdt$_19, $hdt$_20]] in Stage 'Reducer 21' is a cross product -Warning: Shuffle Join MERGEJOIN[476][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18, $hdt$_19, $hdt$_20, $hdt$_21]] in Stage 'Reducer 22' is a cross product -Warning: Shuffle Join MERGEJOIN[477][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18, $hdt$_19, $hdt$_20, $hdt$_21, $hdt$_22]] in Stage 'Reducer 23' is a cross product -Warning: Shuffle Join MERGEJOIN[478][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18, $hdt$_19, $hdt$_20, $hdt$_21, $hdt$_22, $hdt$_23]] in Stage 'Reducer 24' is a cross product -Warning: Shuffle Join MERGEJOIN[479][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18, $hdt$_19, $hdt$_20, $hdt$_21, $hdt$_22, $hdt$_23, $hdt$_24]] in Stage 'Reducer 25' is a cross product -Warning: Shuffle Join MERGEJOIN[480][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18, $hdt$_19, $hdt$_20, $hdt$_21, $hdt$_22, $hdt$_23, $hdt$_24, $hdt$_25]] in Stage 'Reducer 26' is a cross product -Warning: Shuffle Join MERGEJOIN[481][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18, $hdt$_19, $hdt$_20, $hdt$_21, $hdt$_22, $hdt$_23, $hdt$_24, $hdt$_25, $hdt$_26]] in Stage 'Reducer 27' is a cross product -Warning: Shuffle Join MERGEJOIN[482][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18, $hdt$_19, $hdt$_20, $hdt$_21, $hdt$_22, $hdt$_23, $hdt$_24, $hdt$_25, $hdt$_26, $hdt$_27]] in Stage 'Reducer 28' is a cross product -Warning: Shuffle Join MERGEJOIN[483][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18, $hdt$_19, $hdt$_20, $hdt$_21, $hdt$_22, $hdt$_23, $hdt$_24, $hdt$_25, $hdt$_26, $hdt$_27, $hdt$_28]] in Stage 'Reducer 29' is a cross product -Warning: Shuffle Join MERGEJOIN[484][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18, $hdt$_19, $hdt$_20, $hdt$_21, $hdt$_22, $hdt$_23, $hdt$_24, $hdt$_25, $hdt$_26, $hdt$_27, $hdt$_28, $hdt$_29]] in Stage 'Reducer 30' is a cross product -Warning: Shuffle Join MERGEJOIN[485][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15, $hdt$_16, $hdt$_17, $hdt$_18, $hdt$_19, $hdt$_20, $hdt$_21, $hdt$_22, $hdt$_23, $hdt$_24, $hdt$_25, $hdt$_26, $hdt$_27, $hdt$_28, $hdt$_29, $hdt$_30]] in Stage 'Reducer 31' is a cross product +Warning: Shuffle Join MERGEJOIN[171][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[172][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[173][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[174][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[175][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5]] in Stage 'Reducer 6' is a cross product +Warning: Shuffle Join MERGEJOIN[176][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6]] in Stage 'Reducer 7' is a cross product +Warning: Shuffle Join MERGEJOIN[177][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7]] in Stage 'Reducer 8' is a cross product +Warning: Shuffle Join MERGEJOIN[178][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8]] in Stage 'Reducer 9' is a cross product +Warning: Shuffle Join MERGEJOIN[179][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9]] in Stage 'Reducer 10' is a cross product +Warning: Shuffle Join MERGEJOIN[180][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10]] in Stage 'Reducer 11' is a cross product +Warning: Shuffle Join MERGEJOIN[181][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11]] in Stage 'Reducer 12' is a cross product +Warning: Shuffle Join MERGEJOIN[182][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12]] in Stage 'Reducer 13' is a cross product +Warning: Shuffle Join MERGEJOIN[183][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13]] in Stage 'Reducer 14' is a cross product +Warning: Shuffle Join MERGEJOIN[184][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14]] in Stage 'Reducer 15' is a cross product +Warning: Shuffle Join MERGEJOIN[185][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6, $hdt$_7, $hdt$_8, $hdt$_9, $hdt$_10, $hdt$_11, $hdt$_12, $hdt$_13, $hdt$_14, $hdt$_15]] in Stage 'Reducer 16' is a cross product PREHOOK: query: explain select case when (select count(*) from store_sales where ss_quantity between 1 and 20) > 409437 @@ -127,703 +112,313 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Reducer 49 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 51 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 53 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 55 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 57 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE), Reducer 59 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 61 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Reducer 16 (CUSTOM_SIMPLE_EDGE), Reducer 63 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Reducer 17 (CUSTOM_SIMPLE_EDGE), Reducer 65 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Reducer 18 (CUSTOM_SIMPLE_EDGE), Reducer 67 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 33 (CUSTOM_SIMPLE_EDGE) -Reducer 20 <- Reducer 19 (CUSTOM_SIMPLE_EDGE), Reducer 69 (CUSTOM_SIMPLE_EDGE) -Reducer 21 <- Reducer 20 (CUSTOM_SIMPLE_EDGE), Reducer 71 (CUSTOM_SIMPLE_EDGE) -Reducer 22 <- Reducer 21 (CUSTOM_SIMPLE_EDGE), Reducer 73 (CUSTOM_SIMPLE_EDGE) -Reducer 23 <- Reducer 22 (CUSTOM_SIMPLE_EDGE), Reducer 75 (CUSTOM_SIMPLE_EDGE) -Reducer 24 <- Reducer 23 (CUSTOM_SIMPLE_EDGE), Reducer 77 (CUSTOM_SIMPLE_EDGE) -Reducer 25 <- Reducer 24 (CUSTOM_SIMPLE_EDGE), Reducer 79 (CUSTOM_SIMPLE_EDGE) -Reducer 26 <- Reducer 25 (CUSTOM_SIMPLE_EDGE), Reducer 81 (CUSTOM_SIMPLE_EDGE) -Reducer 27 <- Reducer 26 (CUSTOM_SIMPLE_EDGE), Reducer 83 (CUSTOM_SIMPLE_EDGE) -Reducer 28 <- Reducer 27 (CUSTOM_SIMPLE_EDGE), Reducer 85 (CUSTOM_SIMPLE_EDGE) -Reducer 29 <- Reducer 28 (CUSTOM_SIMPLE_EDGE), Reducer 87 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 35 (CUSTOM_SIMPLE_EDGE) -Reducer 30 <- Reducer 29 (CUSTOM_SIMPLE_EDGE), Reducer 89 (CUSTOM_SIMPLE_EDGE) -Reducer 31 <- Reducer 30 (CUSTOM_SIMPLE_EDGE), Reducer 91 (CUSTOM_SIMPLE_EDGE) -Reducer 33 <- Map 32 (CUSTOM_SIMPLE_EDGE) -Reducer 35 <- Map 34 (CUSTOM_SIMPLE_EDGE) -Reducer 37 <- Map 36 (CUSTOM_SIMPLE_EDGE) -Reducer 39 <- Map 38 (CUSTOM_SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 37 (CUSTOM_SIMPLE_EDGE) -Reducer 41 <- Map 40 (CUSTOM_SIMPLE_EDGE) -Reducer 43 <- Map 42 (CUSTOM_SIMPLE_EDGE) -Reducer 45 <- Map 44 (CUSTOM_SIMPLE_EDGE) -Reducer 47 <- Map 46 (CUSTOM_SIMPLE_EDGE) -Reducer 49 <- Map 48 (CUSTOM_SIMPLE_EDGE) -Reducer 5 <- Reducer 39 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) -Reducer 51 <- Map 50 (CUSTOM_SIMPLE_EDGE) -Reducer 53 <- Map 52 (CUSTOM_SIMPLE_EDGE) -Reducer 55 <- Map 54 (CUSTOM_SIMPLE_EDGE) -Reducer 57 <- Map 56 (CUSTOM_SIMPLE_EDGE) -Reducer 59 <- Map 58 (CUSTOM_SIMPLE_EDGE) -Reducer 6 <- Reducer 41 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) -Reducer 61 <- Map 60 (CUSTOM_SIMPLE_EDGE) -Reducer 63 <- Map 62 (CUSTOM_SIMPLE_EDGE) -Reducer 65 <- Map 64 (CUSTOM_SIMPLE_EDGE) -Reducer 67 <- Map 66 (CUSTOM_SIMPLE_EDGE) -Reducer 69 <- Map 68 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Reducer 43 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) -Reducer 71 <- Map 70 (CUSTOM_SIMPLE_EDGE) -Reducer 73 <- Map 72 (CUSTOM_SIMPLE_EDGE) -Reducer 75 <- Map 74 (CUSTOM_SIMPLE_EDGE) -Reducer 77 <- Map 76 (CUSTOM_SIMPLE_EDGE) -Reducer 79 <- Map 78 (CUSTOM_SIMPLE_EDGE) -Reducer 8 <- Reducer 45 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) -Reducer 81 <- Map 80 (CUSTOM_SIMPLE_EDGE) -Reducer 83 <- Map 82 (CUSTOM_SIMPLE_EDGE) -Reducer 85 <- Map 84 (CUSTOM_SIMPLE_EDGE) -Reducer 87 <- Map 86 (CUSTOM_SIMPLE_EDGE) -Reducer 89 <- Map 88 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Reducer 47 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE) -Reducer 91 <- Map 90 (CUSTOM_SIMPLE_EDGE) +Reducer 10 <- Reducer 34 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 36 (CUSTOM_SIMPLE_EDGE) +Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 38 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 40 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 42 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE), Reducer 44 (CUSTOM_SIMPLE_EDGE) +Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 46 (CUSTOM_SIMPLE_EDGE) +Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 18 (CUSTOM_SIMPLE_EDGE) +Reducer 20 <- Map 19 (CUSTOM_SIMPLE_EDGE) +Reducer 22 <- Map 21 (CUSTOM_SIMPLE_EDGE) +Reducer 24 <- Map 23 (CUSTOM_SIMPLE_EDGE) +Reducer 26 <- Map 25 (CUSTOM_SIMPLE_EDGE) +Reducer 28 <- Map 27 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 20 (CUSTOM_SIMPLE_EDGE) +Reducer 30 <- Map 29 (CUSTOM_SIMPLE_EDGE) +Reducer 32 <- Map 31 (CUSTOM_SIMPLE_EDGE) +Reducer 34 <- Map 33 (CUSTOM_SIMPLE_EDGE) +Reducer 36 <- Map 35 (CUSTOM_SIMPLE_EDGE) +Reducer 38 <- Map 37 (CUSTOM_SIMPLE_EDGE) +Reducer 4 <- Reducer 22 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) +Reducer 40 <- Map 39 (CUSTOM_SIMPLE_EDGE) +Reducer 42 <- Map 41 (CUSTOM_SIMPLE_EDGE) +Reducer 44 <- Map 43 (CUSTOM_SIMPLE_EDGE) +Reducer 46 <- Map 45 (CUSTOM_SIMPLE_EDGE) +Reducer 5 <- Reducer 24 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Reducer 26 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Reducer 28 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Reducer 30 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Reducer 32 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 31 - File Output Operator [FS_424] - Select Operator [SEL_423] (rows=36 width=3270) + Reducer 16 + File Output Operator [FS_154] + Select Operator [SEL_153] (rows=36 width=3135) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_485] (rows=36 width=3270) - Conds:(Left Outer),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18","_col20","_col22","_col24","_col26","_col28","_col30"] - <-Reducer 30 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_420] - Merge Join Operator [MERGEJOIN_484] (rows=36 width=2981) - Conds:(Inner),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18","_col20","_col22","_col24","_col26","_col28"] - <-Reducer 29 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_417] - Merge Join Operator [MERGEJOIN_483] (rows=36 width=2972) - Conds:(Left Outer),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18","_col20","_col22","_col24","_col26","_col28"] - <-Reducer 28 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_414] - Merge Join Operator [MERGEJOIN_482] (rows=36 width=2683) - Conds:(Inner),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18","_col20","_col22","_col24","_col26"] - <-Reducer 27 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_411] - Merge Join Operator [MERGEJOIN_481] (rows=36 width=2674) - Conds:(Left Outer),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18","_col20","_col22","_col24","_col26"] - <-Reducer 26 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_408] - Merge Join Operator [MERGEJOIN_480] (rows=36 width=2665) - Conds:(Inner),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18","_col20","_col22","_col24"] - <-Reducer 25 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_405] - Merge Join Operator [MERGEJOIN_479] (rows=36 width=2656) - Conds:(Left Outer),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18","_col20","_col22","_col24"] - <-Reducer 24 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_402] - Merge Join Operator [MERGEJOIN_478] (rows=36 width=2367) - Conds:(Inner),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18","_col20","_col22"] - <-Reducer 23 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_399] - Merge Join Operator [MERGEJOIN_477] (rows=36 width=2358) - Conds:(Left Outer),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18","_col20","_col22"] - <-Reducer 22 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_396] - Merge Join Operator [MERGEJOIN_476] (rows=36 width=2069) - Conds:(Inner),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18","_col20"] - <-Reducer 21 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_393] - Merge Join Operator [MERGEJOIN_475] (rows=36 width=2060) - Conds:(Left Outer),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18","_col20"] - <-Reducer 20 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_390] - Merge Join Operator [MERGEJOIN_474] (rows=36 width=2051) - Conds:(Inner),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18"] - <-Reducer 19 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_387] - Merge Join Operator [MERGEJOIN_473] (rows=36 width=2042) - Conds:(Left Outer),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16","_col18"] - <-Reducer 18 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_384] - Merge Join Operator [MERGEJOIN_472] (rows=36 width=1753) - Conds:(Inner),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16"] - <-Reducer 17 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_381] - Merge Join Operator [MERGEJOIN_471] (rows=36 width=1744) - Conds:(Left Outer),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14","_col16"] - <-Reducer 16 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_378] - Merge Join Operator [MERGEJOIN_470] (rows=36 width=1455) - Conds:(Inner),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_375] - Merge Join Operator [MERGEJOIN_469] (rows=36 width=1446) - Conds:(Left Outer),Output:["_col2","_col4","_col6","_col8","_col10","_col12","_col14"] - <-Reducer 14 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_372] - Merge Join Operator [MERGEJOIN_468] (rows=36 width=1437) - Conds:(Inner),Output:["_col2","_col4","_col6","_col8","_col10","_col12"] - <-Reducer 13 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_369] - Merge Join Operator [MERGEJOIN_467] (rows=36 width=1428) - Conds:(Left Outer),Output:["_col2","_col4","_col6","_col8","_col10","_col12"] - <-Reducer 12 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_366] - Merge Join Operator [MERGEJOIN_466] (rows=36 width=1139) - Conds:(Inner),Output:["_col2","_col4","_col6","_col8","_col10"] - <-Reducer 11 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_363] - Merge Join Operator [MERGEJOIN_465] (rows=36 width=1130) - Conds:(Left Outer),Output:["_col2","_col4","_col6","_col8","_col10"] - <-Reducer 10 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_360] - Merge Join Operator [MERGEJOIN_464] (rows=36 width=841) - Conds:(Inner),Output:["_col2","_col4","_col6","_col8"] - <-Reducer 49 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_358] - Select Operator [SEL_105] (rows=1 width=8) - Filter Operator [FIL_104] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_102] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_97] (rows=1 width=8) - Group By Operator [GBY_96] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 48 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_95] - Group By Operator [GBY_94] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_93] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_434] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 21 AND 40 - TableScan [TS_91] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 9 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_357] - Merge Join Operator [MERGEJOIN_463] (rows=36 width=832) - Conds:(Left Outer),Output:["_col2","_col4","_col6","_col8"] - <-Reducer 47 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_355] - Group By Operator [GBY_89] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 46 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_88] - Group By Operator [GBY_87] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_86] (rows=63999515 width=88) - Filter Operator [FIL_433] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 21 AND 40 - TableScan [TS_84] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity"] - <-Reducer 8 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_354] - Merge Join Operator [MERGEJOIN_462] (rows=36 width=823) - Conds:(Inner),Output:["_col2","_col4","_col6"] - <-Reducer 45 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_352] - Select Operator [SEL_83] (rows=1 width=8) - Filter Operator [FIL_82] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_80] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_75] (rows=1 width=8) - Group By Operator [GBY_74] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 44 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_73] - Group By Operator [GBY_72] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_71] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_432] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 21 AND 40 - TableScan [TS_69] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 7 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_351] - Merge Join Operator [MERGEJOIN_461] (rows=36 width=814) - Conds:(Left Outer),Output:["_col2","_col4","_col6"] - <-Reducer 43 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_349] - Group By Operator [GBY_67] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(VALUE._col0)"] - <-Map 42 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_66] - Group By Operator [GBY_65] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(ss_net_paid_inc_tax)"] - Select Operator [SEL_64] (rows=63999515 width=88) - Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_431] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 1 AND 20 - TableScan [TS_62] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_net_paid_inc_tax"] - <-Reducer 6 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_348] - Merge Join Operator [MERGEJOIN_460] (rows=36 width=525) - Conds:(Inner),Output:["_col2","_col4"] - <-Reducer 41 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_346] - Select Operator [SEL_61] (rows=1 width=8) - Filter Operator [FIL_60] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_58] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_53] (rows=1 width=8) - Group By Operator [GBY_52] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 40 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_51] - Group By Operator [GBY_50] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_49] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_430] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 1 AND 20 - TableScan [TS_47] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 5 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_345] - Merge Join Operator [MERGEJOIN_459] (rows=36 width=516) - Conds:(Left Outer),Output:["_col2","_col4"] - <-Reducer 39 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_343] - Group By Operator [GBY_45] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(VALUE._col0)"] - <-Map 38 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_44] - Group By Operator [GBY_43] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(ss_ext_list_price)"] - Select Operator [SEL_42] (rows=63999515 width=88) - Output:["ss_ext_list_price"] - Filter Operator [FIL_429] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 1 AND 20 - TableScan [TS_40] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_ext_list_price"] - <-Reducer 4 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_342] - Merge Join Operator [MERGEJOIN_458] (rows=36 width=227) - Conds:(Inner),Output:["_col2"] - <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_339] - Merge Join Operator [MERGEJOIN_457] (rows=36 width=218) - Conds:(Left Outer),Output:["_col2"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_336] - Merge Join Operator [MERGEJOIN_456] (rows=36 width=209) - Conds:(Inner) - <-Map 1 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_333] - Select Operator [SEL_2] (rows=36 width=200) - Filter Operator [FIL_425] (rows=36 width=200) - predicate:(r_reason_sk = 1) - TableScan [TS_0] (rows=72 width=200) - default@reason,reason,Tbl:COMPLETE,Col:NONE,Output:["r_reason_sk"] - <-Reducer 33 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_334] - Select Operator [SEL_17] (rows=1 width=8) - Filter Operator [FIL_16] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_14] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_9] (rows=1 width=8) - Group By Operator [GBY_8] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 32 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_7] - Group By Operator [GBY_6] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_5] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_426] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 1 AND 20 - TableScan [TS_3] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 35 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_337] - Group By Operator [GBY_23] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 34 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_22] - Group By Operator [GBY_21] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_20] (rows=63999515 width=88) - Filter Operator [FIL_427] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 1 AND 20 - TableScan [TS_18] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity"] - <-Reducer 37 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_340] - Select Operator [SEL_39] (rows=1 width=8) - Filter Operator [FIL_38] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_36] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_31] (rows=1 width=8) - Group By Operator [GBY_30] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 36 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_29] - Group By Operator [GBY_28] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_27] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_428] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 1 AND 20 - TableScan [TS_25] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 51 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_361] - Group By Operator [GBY_111] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(VALUE._col0)"] - <-Map 50 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_110] - Group By Operator [GBY_109] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(ss_ext_list_price)"] - Select Operator [SEL_108] (rows=63999515 width=88) - Output:["ss_ext_list_price"] - Filter Operator [FIL_435] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 21 AND 40 - TableScan [TS_106] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_ext_list_price"] - <-Reducer 53 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_364] - Select Operator [SEL_127] (rows=1 width=8) - Filter Operator [FIL_126] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_124] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_119] (rows=1 width=8) - Group By Operator [GBY_118] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 52 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_117] - Group By Operator [GBY_116] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_115] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_436] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 21 AND 40 - TableScan [TS_113] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 55 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_367] - Group By Operator [GBY_133] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(VALUE._col0)"] - <-Map 54 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_132] - Group By Operator [GBY_131] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(ss_net_paid_inc_tax)"] - Select Operator [SEL_130] (rows=63999515 width=88) - Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_437] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 21 AND 40 - TableScan [TS_128] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_net_paid_inc_tax"] - <-Reducer 57 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_370] - Select Operator [SEL_149] (rows=1 width=8) - Filter Operator [FIL_148] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_146] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_141] (rows=1 width=8) - Group By Operator [GBY_140] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 56 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_139] - Group By Operator [GBY_138] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_137] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_438] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 41 AND 60 - TableScan [TS_135] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 59 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_373] - Group By Operator [GBY_155] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 58 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_154] - Group By Operator [GBY_153] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_152] (rows=63999515 width=88) - Filter Operator [FIL_439] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 41 AND 60 - TableScan [TS_150] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity"] - <-Reducer 61 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_376] - Select Operator [SEL_171] (rows=1 width=8) - Filter Operator [FIL_170] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_168] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_163] (rows=1 width=8) - Group By Operator [GBY_162] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 60 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_161] - Group By Operator [GBY_160] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_159] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_440] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 41 AND 60 - TableScan [TS_157] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 63 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_379] - Group By Operator [GBY_177] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(VALUE._col0)"] - <-Map 62 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_176] - Group By Operator [GBY_175] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(ss_ext_list_price)"] - Select Operator [SEL_174] (rows=63999515 width=88) - Output:["ss_ext_list_price"] - Filter Operator [FIL_441] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 41 AND 60 - TableScan [TS_172] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_ext_list_price"] - <-Reducer 65 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_382] - Select Operator [SEL_193] (rows=1 width=8) - Filter Operator [FIL_192] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_190] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_185] (rows=1 width=8) - Group By Operator [GBY_184] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 64 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_183] - Group By Operator [GBY_182] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_181] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_442] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 41 AND 60 - TableScan [TS_179] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 67 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_385] - Group By Operator [GBY_199] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(VALUE._col0)"] - <-Map 66 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_198] - Group By Operator [GBY_197] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(ss_net_paid_inc_tax)"] - Select Operator [SEL_196] (rows=63999515 width=88) - Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_443] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 41 AND 60 - TableScan [TS_194] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_net_paid_inc_tax"] - <-Reducer 69 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_388] - Select Operator [SEL_215] (rows=1 width=8) - Filter Operator [FIL_214] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_212] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_207] (rows=1 width=8) - Group By Operator [GBY_206] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 68 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_205] - Group By Operator [GBY_204] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_203] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_444] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 61 AND 80 - TableScan [TS_201] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 71 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_391] - Group By Operator [GBY_221] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 70 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_220] - Group By Operator [GBY_219] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_218] (rows=63999515 width=88) - Filter Operator [FIL_445] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 61 AND 80 - TableScan [TS_216] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity"] - <-Reducer 73 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_394] - Select Operator [SEL_237] (rows=1 width=8) - Filter Operator [FIL_236] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_234] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_229] (rows=1 width=8) - Group By Operator [GBY_228] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 72 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_227] - Group By Operator [GBY_226] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_225] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_446] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 61 AND 80 - TableScan [TS_223] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 75 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_397] - Group By Operator [GBY_243] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(VALUE._col0)"] - <-Map 74 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_242] - Group By Operator [GBY_241] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(ss_ext_list_price)"] - Select Operator [SEL_240] (rows=63999515 width=88) - Output:["ss_ext_list_price"] - Filter Operator [FIL_447] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 61 AND 80 - TableScan [TS_238] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_ext_list_price"] - <-Reducer 77 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_400] - Select Operator [SEL_259] (rows=1 width=8) - Filter Operator [FIL_258] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_256] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_251] (rows=1 width=8) - Group By Operator [GBY_250] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 76 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_249] - Group By Operator [GBY_248] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_247] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_448] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 61 AND 80 - TableScan [TS_245] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 79 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_403] - Group By Operator [GBY_265] (rows=1 width=288) + Merge Join Operator [MERGEJOIN_185] (rows=36 width=3135) + Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_150] + Merge Join Operator [MERGEJOIN_184] (rows=36 width=2846) + Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] + <-Reducer 14 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_147] + Merge Join Operator [MERGEJOIN_183] (rows=36 width=2557) + Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + <-Reducer 13 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_144] + Merge Join Operator [MERGEJOIN_182] (rows=36 width=2548) + Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] + <-Reducer 12 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_141] + Merge Join Operator [MERGEJOIN_181] (rows=36 width=2259) + Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Reducer 11 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_138] + Merge Join Operator [MERGEJOIN_180] (rows=36 width=1970) + Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] + <-Reducer 10 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_135] + Merge Join Operator [MERGEJOIN_179] (rows=36 width=1961) + Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] + <-Reducer 34 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_133] + Group By Operator [GBY_64] (rows=1 width=288) Output:["_col0"],aggregations:["avg(VALUE._col0)"] - <-Map 78 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_264] - Group By Operator [GBY_263] (rows=1 width=288) + <-Map 33 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_63] + Group By Operator [GBY_62] (rows=1 width=288) Output:["_col0"],aggregations:["avg(ss_net_paid_inc_tax)"] - Select Operator [SEL_262] (rows=63999515 width=88) + Select Operator [SEL_61] (rows=63999515 width=88) Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_449] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 61 AND 80 - TableScan [TS_260] (rows=575995635 width=88) + Filter Operator [FIL_164] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 41 AND 60 + TableScan [TS_59] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_net_paid_inc_tax"] - <-Reducer 81 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_406] - Select Operator [SEL_281] (rows=1 width=8) - Filter Operator [FIL_280] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_278] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_273] (rows=1 width=8) - Group By Operator [GBY_272] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 80 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_271] - Group By Operator [GBY_270] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_269] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_450] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 81 AND 100 - TableScan [TS_267] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 83 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_409] - Group By Operator [GBY_287] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 82 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_286] - Group By Operator [GBY_285] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_284] (rows=63999515 width=88) - Filter Operator [FIL_451] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 81 AND 100 - TableScan [TS_282] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity"] - <-Reducer 85 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_412] - Select Operator [SEL_303] (rows=1 width=8) - Filter Operator [FIL_302] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_300] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_295] (rows=1 width=8) - Group By Operator [GBY_294] (rows=1 width=8) + <-Reducer 9 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_132] + Merge Join Operator [MERGEJOIN_178] (rows=36 width=1672) + Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Reducer 32 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_130] + Group By Operator [GBY_57] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(VALUE._col0)"] + <-Map 31 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_56] + Group By Operator [GBY_55] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(ss_ext_list_price)"] + Select Operator [SEL_54] (rows=63999515 width=88) + Output:["ss_ext_list_price"] + Filter Operator [FIL_163] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 41 AND 60 + TableScan [TS_52] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_ext_list_price"] + <-Reducer 8 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_129] + Merge Join Operator [MERGEJOIN_177] (rows=36 width=1383) + Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Reducer 30 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_127] + Group By Operator [GBY_50] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Map 29 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_49] + Group By Operator [GBY_48] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_47] (rows=63999515 width=88) + Filter Operator [FIL_162] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 41 AND 60 + TableScan [TS_45] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity"] + <-Reducer 7 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_126] + Merge Join Operator [MERGEJOIN_176] (rows=36 width=1374) + Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] + <-Reducer 28 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_124] + Group By Operator [GBY_43] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(VALUE._col0)"] + <-Map 27 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_42] + Group By Operator [GBY_41] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(ss_net_paid_inc_tax)"] + Select Operator [SEL_40] (rows=63999515 width=88) + Output:["ss_net_paid_inc_tax"] + Filter Operator [FIL_161] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 21 AND 40 + TableScan [TS_38] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_net_paid_inc_tax"] + <-Reducer 6 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_123] + Merge Join Operator [MERGEJOIN_175] (rows=36 width=1085) + Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5"] + <-Reducer 26 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_121] + Group By Operator [GBY_36] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(VALUE._col0)"] + <-Map 25 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_35] + Group By Operator [GBY_34] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(ss_ext_list_price)"] + Select Operator [SEL_33] (rows=63999515 width=88) + Output:["ss_ext_list_price"] + Filter Operator [FIL_160] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 21 AND 40 + TableScan [TS_31] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_ext_list_price"] + <-Reducer 5 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_120] + Merge Join Operator [MERGEJOIN_174] (rows=36 width=796) + Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4"] + <-Reducer 24 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_118] + Group By Operator [GBY_29] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Map 23 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_28] + Group By Operator [GBY_27] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_26] (rows=63999515 width=88) + Filter Operator [FIL_159] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 21 AND 40 + TableScan [TS_24] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity"] + <-Reducer 4 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_117] + Merge Join Operator [MERGEJOIN_173] (rows=36 width=787) + Conds:(Left Outer),Output:["_col1","_col2","_col3"] + <-Reducer 22 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_115] + Group By Operator [GBY_22] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(VALUE._col0)"] + <-Map 21 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_21] + Group By Operator [GBY_20] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(ss_net_paid_inc_tax)"] + Select Operator [SEL_19] (rows=63999515 width=88) + Output:["ss_net_paid_inc_tax"] + Filter Operator [FIL_158] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 1 AND 20 + TableScan [TS_17] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_net_paid_inc_tax"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_114] + Merge Join Operator [MERGEJOIN_172] (rows=36 width=498) + Conds:(Left Outer),Output:["_col1","_col2"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_111] + Merge Join Operator [MERGEJOIN_171] (rows=36 width=209) + Conds:(Left Outer),Output:["_col1"] + <-Map 1 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_108] + Select Operator [SEL_2] (rows=36 width=200) + Filter Operator [FIL_155] (rows=36 width=200) + predicate:(r_reason_sk = 1) + TableScan [TS_0] (rows=72 width=200) + default@reason,reason,Tbl:COMPLETE,Col:NONE,Output:["r_reason_sk"] + <-Reducer 18 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_109] + Group By Operator [GBY_8] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Map 17 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_7] + Group By Operator [GBY_6] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_5] (rows=63999515 width=88) + Filter Operator [FIL_156] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 1 AND 20 + TableScan [TS_3] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity"] + <-Reducer 20 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_112] + Group By Operator [GBY_15] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(VALUE._col0)"] + <-Map 19 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_14] + Group By Operator [GBY_13] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(ss_ext_list_price)"] + Select Operator [SEL_12] (rows=63999515 width=88) + Output:["ss_ext_list_price"] + Filter Operator [FIL_157] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 1 AND 20 + TableScan [TS_10] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_ext_list_price"] + <-Reducer 36 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_136] + Group By Operator [GBY_71] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 84 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_293] - Group By Operator [GBY_292] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_291] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_452] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 81 AND 100 - TableScan [TS_289] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 87 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_415] - Group By Operator [GBY_309] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(VALUE._col0)"] - <-Map 86 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_308] - Group By Operator [GBY_307] (rows=1 width=288) - Output:["_col0"],aggregations:["avg(ss_ext_list_price)"] - Select Operator [SEL_306] (rows=63999515 width=88) - Output:["ss_ext_list_price"] - Filter Operator [FIL_453] (rows=63999515 width=88) + <-Map 35 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_70] + Group By Operator [GBY_69] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_68] (rows=63999515 width=88) + Filter Operator [FIL_165] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 61 AND 80 + TableScan [TS_66] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity"] + <-Reducer 38 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_139] + Group By Operator [GBY_78] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(VALUE._col0)"] + <-Map 37 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_77] + Group By Operator [GBY_76] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(ss_ext_list_price)"] + Select Operator [SEL_75] (rows=63999515 width=88) + Output:["ss_ext_list_price"] + Filter Operator [FIL_166] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 61 AND 80 + TableScan [TS_73] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_ext_list_price"] + <-Reducer 40 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_142] + Group By Operator [GBY_85] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(VALUE._col0)"] + <-Map 39 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_84] + Group By Operator [GBY_83] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(ss_net_paid_inc_tax)"] + Select Operator [SEL_82] (rows=63999515 width=88) + Output:["ss_net_paid_inc_tax"] + Filter Operator [FIL_167] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 61 AND 80 + TableScan [TS_80] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_net_paid_inc_tax"] + <-Reducer 42 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_145] + Group By Operator [GBY_92] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Map 41 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_91] + Group By Operator [GBY_90] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_89] (rows=63999515 width=88) + Filter Operator [FIL_168] (rows=63999515 width=88) predicate:ss_quantity BETWEEN 81 AND 100 - TableScan [TS_304] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_ext_list_price"] - <-Reducer 89 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_418] - Select Operator [SEL_325] (rows=1 width=8) - Filter Operator [FIL_324] (rows=1 width=8) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_322] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_317] (rows=1 width=8) - Group By Operator [GBY_316] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 88 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_315] - Group By Operator [GBY_314] (rows=1 width=8) - Output:["_col0"],aggregations:["count(ss_sold_date_sk)"] - Select Operator [SEL_313] (rows=63999515 width=88) - Output:["ss_sold_date_sk"] - Filter Operator [FIL_454] (rows=63999515 width=88) - predicate:ss_quantity BETWEEN 81 AND 100 - TableScan [TS_311] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 91 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_421] - Group By Operator [GBY_331] (rows=1 width=288) + TableScan [TS_87] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity"] + <-Reducer 44 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_148] + Group By Operator [GBY_99] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(VALUE._col0)"] + <-Map 43 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_98] + Group By Operator [GBY_97] (rows=1 width=288) + Output:["_col0"],aggregations:["avg(ss_ext_list_price)"] + Select Operator [SEL_96] (rows=63999515 width=88) + Output:["ss_ext_list_price"] + Filter Operator [FIL_169] (rows=63999515 width=88) + predicate:ss_quantity BETWEEN 81 AND 100 + TableScan [TS_94] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_ext_list_price"] + <-Reducer 46 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_151] + Group By Operator [GBY_106] (rows=1 width=288) Output:["_col0"],aggregations:["avg(VALUE._col0)"] - <-Map 90 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_330] - Group By Operator [GBY_329] (rows=1 width=288) + <-Map 45 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_105] + Group By Operator [GBY_104] (rows=1 width=288) Output:["_col0"],aggregations:["avg(ss_net_paid_inc_tax)"] - Select Operator [SEL_328] (rows=63999515 width=88) + Select Operator [SEL_103] (rows=63999515 width=88) Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_455] (rows=63999515 width=88) + Filter Operator [FIL_170] (rows=63999515 width=88) predicate:ss_quantity BETWEEN 81 AND 100 - TableScan [TS_326] (rows=575995635 width=88) + TableScan [TS_101] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_net_paid_inc_tax"]