diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveProjectSortTransposeRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveProjectSortTransposeRule.java index 1487ed4..3bd1d42 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveProjectSortTransposeRule.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveProjectSortTransposeRule.java @@ -17,23 +17,42 @@ */ package org.apache.hadoop.hive.ql.optimizer.calcite.rules; +<<<<<<< HEAD import org.apache.calcite.plan.RelOptCluster; +======= +import java.util.ArrayList; +import java.util.HashMap; +import java.util.HashSet; +import java.util.List; +import java.util.Map; +import java.util.Set; + +>>>>>>> clidriver golden file change import org.apache.calcite.plan.RelOptRule; import org.apache.calcite.plan.RelOptRuleCall; import org.apache.calcite.plan.RelOptRuleOperand; import org.apache.calcite.plan.RelOptUtil; +import org.apache.calcite.plan.RelTraitSet; import org.apache.calcite.rel.RelCollation; +import org.apache.calcite.rel.RelCollationImpl; import org.apache.calcite.rel.RelCollationTraitDef; import org.apache.calcite.rel.RelFieldCollation; import org.apache.calcite.rel.RelNode; +<<<<<<< HEAD import org.apache.calcite.rex.RexCall; import org.apache.calcite.rex.RexCallBinding; +======= +import org.apache.calcite.rex.RexInputRef; +>>>>>>> clidriver golden file change import org.apache.calcite.rex.RexNode; import org.apache.calcite.rex.RexUtil; import org.apache.calcite.sql.SqlKind; import org.apache.calcite.sql.validate.SqlMonotonicity; import org.apache.calcite.util.mapping.Mappings; +import org.apache.commons.collections.map.HashedMap; +import org.apache.hadoop.hive.ql.optimizer.calcite.HiveCalciteUtil; import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject; +import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveRelNode; import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveSortLimit; import com.google.common.collect.ImmutableList; @@ -67,15 +86,15 @@ public void onMatch(RelOptRuleCall call) { final HiveSortLimit sort = call.rel(1); final RelOptCluster cluster = project.getCluster(); - // Determine mapping between project input and output fields. If sort - // relies on non-trivial expressions, we can't push. + // Determine mapping between project input and output fields. + // In Hive, Sort is always based on RexInputRef + // We only need to check if project can contain all the positions that sort needs. final Mappings.TargetMapping map = RelOptUtil.permutationIgnoreCast( project.getProjects(), project.getInput().getRowType()).inverse(); + Set needed = new HashSet<>(); for (RelFieldCollation fc : sort.getCollation().getFieldCollations()) { - if (map.getTarget(fc.getFieldIndex()) < 0) { - return; - } + needed.add(fc.getFieldIndex()); final RexNode node = project.getProjects().get(map.getTarget(fc.getFieldIndex())); if (node.isA(SqlKind.CAST)) { // Check whether it is a monotonic preserving cast, otherwise we cannot push @@ -88,12 +107,35 @@ public void onMatch(RelOptRuleCall call) { } } } + Map m = new HashMap<>(); + for (int projPos = 0; projPos < project.getChildExps().size(); projPos++) { + RexNode expr = project.getChildExps().get(projPos); + if (expr instanceof RexInputRef) { + Set positions = HiveCalciteUtil.getInputRefs(expr); + if (positions.size() > 1) { + continue; + } else { + int parentPos = positions.iterator().next(); + if(needed.contains(parentPos)){ + m.put(parentPos, projPos); + needed.remove(parentPos); + } + } + } + } + if(!needed.isEmpty()){ + return; + } + + List fieldCollations = new ArrayList<>(); + for (RelFieldCollation fc : sort.getCollation().getFieldCollations()) { + fieldCollations.add(new RelFieldCollation(m.get(fc.getFieldIndex()), fc.direction, + fc.nullDirection)); + } - // Create new collation - final RelCollation newCollation = - RelCollationTraitDef.INSTANCE.canonize( - RexUtil.apply(map, sort.getCollation())); - + RelTraitSet traitSet = sort.getCluster().traitSetOf(HiveRelNode.CONVENTION); + RelCollation newCollation = traitSet.canonize(RelCollationImpl.of(fieldCollations)); + // New operators final RelNode newProject = project.copy(sort.getInput().getTraitSet(), ImmutableList.of(sort.getInput())); diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSortProjectRealignRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSortProjectRealignRule.java new file mode 100644 index 0000000..2f8a260 --- /dev/null +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSortProjectRealignRule.java @@ -0,0 +1,145 @@ +/* + * 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.rules; + +import java.util.ArrayList; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.Set; + +import org.apache.calcite.plan.RelOptRule; +import org.apache.calcite.plan.RelOptRuleCall; +import org.apache.calcite.plan.RelOptRuleOperand; +import org.apache.calcite.plan.RelOptUtil; +import org.apache.calcite.plan.RelTraitSet; +import org.apache.calcite.rel.RelCollation; +import org.apache.calcite.rel.RelCollationImpl; +import org.apache.calcite.rel.RelCollationTraitDef; +import org.apache.calcite.rel.RelFieldCollation; +import org.apache.calcite.rel.RelNode; +import org.apache.calcite.rex.RexInputRef; +import org.apache.calcite.rex.RexNode; +import org.apache.calcite.rex.RexOver; +import org.apache.calcite.rex.RexUtil; +import org.apache.calcite.util.mapping.Mappings; +import org.apache.hadoop.hive.ql.optimizer.calcite.HiveCalciteUtil; +import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject; +import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveRelNode; +import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveSortLimit; + +import sun.tools.tree.PostIncExpression; + +import com.google.common.collect.ImmutableList; + +public class HiveSortProjectRealignRule extends RelOptRule { + + public static final HiveSortProjectRealignRule INSTANCE = + new HiveSortProjectRealignRule(); + + //~ Constructors ----------------------------------------------------------- + + /** + * Creates a HiveProjectSortProjectMergeRule. + * This rule will try to do the + * following + * Sort($1) + * --Project($0,$0) will be realigned to + * Sort($0) + * --Project($0,$0) + * + * E.g. HiveProject(mykey=[$0]) + * HiveSortLimit(sort0=[$1], dir0=[ASC-nulls-first]) + * HiveProject(mykey=[$0], _o__col1=[$0]) + * HiveAggregate(group=[{0}]) + * HiveProject($f0=[$0]) + * HiveTableScan(table=[[default.test]], table:alias=[t1]) + */ + private HiveSortProjectRealignRule() { + super(operand(HiveSortLimit.class, operand(HiveProject.class, any()))); + } + + protected HiveSortProjectRealignRule(RelOptRuleOperand operand) { + super(operand); + } + + //~ Methods ---------------------------------------------------------------- + + // implement RelOptRule + public void onMatch(RelOptRuleCall call) { + final HiveSortLimit sort = call.rel(0); + final HiveProject project = call.rel(1); + + // first scan the project to get the smallest position of RexInputRef + Map parentToProjPosMap = new HashMap<>(); + Map projToProjPosMap = new HashMap<>(); + for (int projPos = 0; projPos < project.getChildExps().size(); projPos++) { + RexNode expr = project.getChildExps().get(projPos); + if (expr instanceof RexInputRef) { + Set positions = HiveCalciteUtil.getInputRefs(expr); + if (positions.size() > 1) { + continue; + } else { + int parentPos = positions.iterator().next(); + if (parentToProjPosMap.containsKey(parentPos)) { + projToProjPosMap.put(projPos, parentToProjPosMap.get(parentPos)); + } else { + parentToProjPosMap.put(parentPos, projPos); + } + } + } + } + + // there is nothing to realign + if (projToProjPosMap.isEmpty()) { + return; + } + + // then scan the sort to realign the position + boolean needChange = false; + List fieldCollations = new ArrayList<>(); + for (RelFieldCollation fc : sort.getCollation().getFieldCollations()) { + int fieldIndex = fc.getFieldIndex(); + if (projToProjPosMap.containsKey(fieldIndex)) { + RelFieldCollation rfc = new RelFieldCollation(projToProjPosMap.get(fieldIndex), + fc.direction, fc.nullDirection); + fieldCollations.add(rfc); + needChange = true; + } else { + fieldCollations.add(new RelFieldCollation(fc.getFieldIndex(), fc.direction, + fc.nullDirection)); + } + } + + if (!needChange) { + return; + } + + RelTraitSet traitSet = sort.getCluster().traitSetOf(HiveRelNode.CONVENTION); + RelCollation newCollation = traitSet.canonize(RelCollationImpl.of(fieldCollations)); + + // finally create new operators + final RelNode newProject = project.copy(project.getInput().getTraitSet(), + ImmutableList.of(project.getInput())); + final HiveSortLimit newSort = sort.copy(newProject.getTraitSet(), + newProject, newCollation, sort.offset, sort.fetch); + + call.transformTo(newSort); + } + +} 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 1b054a7..700b661 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 @@ -205,6 +205,7 @@ import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveSortJoinReduceRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveSortLimitPullUpConstantsRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveSortMergeRule; +import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveSortProjectRealignRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveSortProjectTransposeRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveSortRemoveRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveSortUnionReduceRule; @@ -1626,6 +1627,14 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER, "Calcite: HiveExceptRewrite rule"); + // SortProjectRealign rewrite + perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.OPTIMIZER); + basePlan = hepPlan(basePlan, true, mdProvider, null, HepMatchOrder.BOTTOM_UP, + HiveProjectMergeRule.INSTANCE, ProjectRemoveRule.INSTANCE, + HiveSortProjectRealignRule.INSTANCE); + perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER, + "Calcite: Merge Project-Project, HiveSortProjectRealignRule rules"); + //1. Distinct aggregate rewrite // Run this optimization early, since it is expanding the operator pipeline. if (!conf.getVar(HiveConf.ConfVars.HIVE_EXECUTION_ENGINE).equals("mr") && @@ -1736,9 +1745,9 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv // 8. Merge, remove and reduce Project if possible perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.OPTIMIZER); basePlan = hepPlan(basePlan, false, mdProvider, executorProvider, - HiveProjectMergeRule.INSTANCE, ProjectRemoveRule.INSTANCE); + HiveProjectMergeRule.INSTANCE, ProjectRemoveRule.INSTANCE, HiveSortMergeRule.INSTANCE); perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER, - "Calcite: Prejoin ordering transformation, Merge Project-Project"); + "Calcite: Prejoin ordering transformation, Merge Project-Project, Merge Sort-Sort"); // 9. Rerun PPD through Project as column pruning would have introduced // DT above scans; By pushing filter just above TS, Hive can push it into @@ -2867,7 +2876,7 @@ private RelNode genGBLogicalPlan(QB qb, RelNode srcRel) throws SemanticException && selExprList.getChildCount() == 1 && selExprList.getChild(0).getChildCount() == 1) { ASTNode node = (ASTNode) selExprList.getChild(0).getChild(0); if (node.getToken().getType() == HiveParser.TOK_ALLCOLREF) { - srcRel = genSelectLogicalPlan(qb, srcRel, srcRel, null,null); + srcRel = genSelectLogicalPlan(qb, srcRel, srcRel, null,null).getKey(); RowResolver rr = this.relToHiveRR.get(srcRel); qbp.setSelExprForClause(detsClauseName, SemanticAnalyzer.genSelectDIAST(rr)); } @@ -3033,9 +3042,13 @@ private RelNode genGBLogicalPlan(QB qb, RelNode srcRel) throws SemanticException * top constraining Select * @throws SemanticException */ - private Pair genOBLogicalPlan(QB qb, RelNode srcRel, boolean outermostOB) - throws SemanticException { + private Pair genOBLogicalPlan(QB qb, Pair selPair, + boolean outermostOB) throws SemanticException { + // selPair.getKey() is the operator right before OB + // selPair.getValue() is the original RR that should be OB's RR + RelNode srcRel = selPair.getKey(); RelNode sortRel = null; + RelNode returnRel = null; RelNode originalOBChild = null; QBParseInfo qbp = getQBParseInfo(qb); @@ -3043,13 +3056,16 @@ private RelNode genGBLogicalPlan(QB qb, RelNode srcRel) throws SemanticException ASTNode obAST = qbp.getOrderByForClause(dest); if (obAST != null) { - // 1. OB Expr sanity test - // in strict mode, in the presence of order by, limit must be specified - Integer limit = qb.getParseInfo().getDestLimit(dest); - if (limit == null) { - String error = StrictChecks.checkNoLimit(conf); - if (error != null) { - throw new SemanticException(SemanticAnalyzer.generateErrorMessage(obAST, error)); + if (selPair.getValue() == null) { + // 1. OB Expr sanity test + // in strict mode, in the presence of order by, limit must be + // specified + Integer limit = qb.getParseInfo().getDestLimit(dest); + if (limit == null) { + String error = StrictChecks.checkNoLimit(conf); + if (error != null) { + throw new SemanticException(SemanticAnalyzer.generateErrorMessage(obAST, error)); + } } } @@ -3106,8 +3122,8 @@ private RelNode genGBLogicalPlan(QB qb, RelNode srcRel) throws SemanticException } else if (nullObASTExpr.getType() == HiveParser.TOK_NULLS_LAST) { nullOrder = RelFieldCollation.NullDirection.LAST; } else { - throw new SemanticException( - "Unexpected null ordering option: " + nullObASTExpr.getType()); + throw new SemanticException("Unexpected null ordering option: " + + nullObASTExpr.getType()); } // 2.5 Add to field collations @@ -3179,9 +3195,25 @@ public RexNode apply(RelDataTypeField input) { outputRR, sortRel); relToHiveRR.put(sortRel, outputRR); relToHiveColNameCalcitePosMap.put(sortRel, hiveColNameCalcitePosMap); - } - return (new Pair(sortRel, originalOBChild)); + if (selPair.getValue() != null) { + List originalInputRefs = Lists.transform(srcRel.getRowType().getFieldList(), + new Function() { + @Override + public RexNode apply(RelDataTypeField input) { + return new RexInputRef(input.getIndex(), input.getType()); + } + }); + List selectedRefs = Lists.newArrayList(); + for (int index = 0; index < selPair.getValue().getColumnInfos().size(); index++) { + selectedRefs.add(originalInputRefs.get(index)); + } + returnRel = genSelectRelNode(selectedRefs, selPair.getValue(), sortRel); + } else { + returnRel = sortRel; + } + } + return (new Pair(returnRel, originalOBChild)); } private RelNode genLimitLogicalPlan(QB qb, RelNode srcRel) throws SemanticException { @@ -3512,7 +3544,7 @@ private void setQueryHints(QB qb) throws SemanticException { * * @throws SemanticException */ - private RelNode genSelectLogicalPlan(QB qb, RelNode srcRel, RelNode starSrcRel, + private Pair genSelectLogicalPlan(QB qb, RelNode srcRel, RelNode starSrcRel, ImmutableMap outerNameToPosMap, RowResolver outerRR) throws SemanticException { // 0. Generate a Select Node for Windowing @@ -3778,15 +3810,62 @@ private RelNode genSelectLogicalPlan(QB qb, RelNode srcRel, RelNode starSrcRel, // 8. Build Calcite Rel RelNode outputRel = null; if (genericUDTF != null) { - // The basic idea for CBO support of UDTF is to treat UDTF as a special project. - // In AST return path, as we just need to generate a SEL_EXPR, we just need to remember the expressions and the alias. - // In OP return path, we need to generate a SEL and then a UDTF following old semantic analyzer. - outputRel = genUDTFPlan(genericUDTF, genericUDTFName, udtfTableAlias, udtfColAliases, qb, calciteColLst, out_rwsch, srcRel); - } - else{ - outputRel = genSelectRelNode(calciteColLst, out_rwsch, srcRel); + // The basic idea for CBO support of UDTF is to treat UDTF as a special + // project. + // In AST return path, as we just need to generate a SEL_EXPR, we just + // need to remember the expressions and the alias. + // In OP return path, we need to generate a SEL and then a UDTF + // following old semantic analyzer. + outputRel = genUDTFPlan(genericUDTF, genericUDTFName, udtfTableAlias, udtfColAliases, qb, + calciteColLst, out_rwsch, srcRel); + } else { + String dest = qbp.getClauseNames().iterator().next(); + ASTNode obAST = qbp.getOrderByForClause(dest); + + RowResolver originalRR = null; + // We only support unselected column following by order by. + // TODO: support unselected columns in genericUDTF and windowing functions. + if (obAST != null && !(selForWindow != null && selExprList.getToken().getType() == HiveParser.TOK_SELECTDI)) { + // 1. OB Expr sanity test + // in strict mode, in the presence of order by, limit must be + // specified + Integer limit = qb.getParseInfo().getDestLimit(dest); + if (limit == null) { + String error = StrictChecks.checkNoLimit(conf); + if (error != null) { + throw new SemanticException(SemanticAnalyzer.generateErrorMessage(obAST, error)); + } + } + List originalInputRefs = Lists.transform(srcRel.getRowType().getFieldList(), + new Function() { + @Override + public RexNode apply(RelDataTypeField input) { + return new RexInputRef(input.getIndex(), input.getType()); + } + }); + originalRR = out_rwsch.duplicate(); + for (int i = 0; i < inputRR.getColumnInfos().size(); i++) { + ColumnInfo colInfo = new ColumnInfo(inputRR.getColumnInfos().get(i)); + String internalName = SemanticAnalyzer.getColumnInternalName(out_rwsch.getColumnInfos() + .size() + i); + colInfo.setInternalName(internalName); + if (!out_rwsch.putWithCheck(colInfo.getTabAlias(), colInfo.getAlias(), internalName, + colInfo)) { + LOG.info("There is confict when we add column to RR for order by: " + + colInfo.getTabAlias() + "." + colInfo.getAlias() + " => " + colInfo + + " due to duplication, see previous warnings"); + } else { + calciteColLst.add(originalInputRefs.get(i)); + } + } + outputRel = genSelectRelNode(calciteColLst, out_rwsch, srcRel); + // outputRel is the generated augmented select with extra unselected + // columns, and originalRR is the original generated select + return new Pair(outputRel, originalRR); + } else { + outputRel = genSelectRelNode(calciteColLst, out_rwsch, srcRel); + } } - // 9. Handle select distinct as GBY if there exist windowing functions if (selForWindow != null && selExprList.getToken().getType() == HiveParser.TOK_SELECTDI) { ImmutableBitSet groupSet = ImmutableBitSet.range(outputRel.getRowType().getFieldList().size()); @@ -3804,7 +3883,7 @@ private RelNode genSelectLogicalPlan(QB qb, RelNode srcRel, RelNode starSrcRel, this.relToHiveRR.put(outputRel, groupByOutputRowResolver); } - return outputRel; + return new Pair(outputRel, null); } private RelNode genUDTFPlan(GenericUDTF genericUDTF, String genericUDTFName, String outputTableAlias, @@ -4031,11 +4110,12 @@ private RelNode genLogicalPlan(QB qb, boolean outerMostQB, srcRel = (gbHavingRel == null) ? srcRel : gbHavingRel; // 5. Build Rel for Select Clause - selectRel = genSelectLogicalPlan(qb, srcRel, starSrcRel, outerNameToPosMap, outerRR); + Pair selPair = genSelectLogicalPlan(qb, srcRel, starSrcRel, outerNameToPosMap, outerRR); + selectRel = selPair.getKey(); srcRel = (selectRel == null) ? srcRel : selectRel; // 6. Build Rel for OB Clause - Pair obTopProjPair = genOBLogicalPlan(qb, srcRel, outerMostQB); + Pair obTopProjPair = genOBLogicalPlan(qb, selPair, outerMostQB); obRel = obTopProjPair.getKey(); RelNode topConstrainingProjArgsRel = obTopProjPair.getValue(); srcRel = (obRel == null) ? srcRel : obRel; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/RowResolver.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/RowResolver.java index 262dafb..0a3ac20 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/RowResolver.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/RowResolver.java @@ -180,23 +180,31 @@ public ColumnInfo get(String tab_alias, String col_alias) throws SemanticExcepti } ret = f_map.get(col_alias); } else { - boolean found = false; - String foundTbl = null; - for (Map.Entry> rslvEntry: rslvMap.entrySet()) { - String rslvKey = rslvEntry.getKey(); - LinkedHashMap cmap = rslvEntry.getValue(); - for (Map.Entry cmapEnt : cmap.entrySet()) { - if (col_alias.equalsIgnoreCase(cmapEnt.getKey())) { - /* - * We can have an unaliased and one aliased mapping to a Column. - */ - if (found && foundTbl != null && rslvKey != null) { - throw new SemanticException("Column " + col_alias - + " Found in more than One Tables/Subqueries"); + HashMap f_map = rslvMap.get(tab_alias); + // first try rslvMap directly + if (f_map != null) { + ret = f_map.get(col_alias); + } + // then try others + if (ret == null) { + boolean found = false; + String foundTbl = null; + for (Map.Entry> rslvEntry : rslvMap.entrySet()) { + String rslvKey = rslvEntry.getKey(); + LinkedHashMap cmap = rslvEntry.getValue(); + for (Map.Entry cmapEnt : cmap.entrySet()) { + if (col_alias.equalsIgnoreCase(cmapEnt.getKey())) { + /* + * We can have an unaliased and one aliased mapping to a Column. + */ + if (found && foundTbl != null && rslvKey != null) { + throw new SemanticException("Column " + col_alias + + " Found in more than One Tables/Subqueries"); + } + found = true; + foundTbl = rslvKey == null ? foundTbl : rslvKey; + ret = cmapEnt.getValue(); } - found = true; - foundTbl = rslvKey == null ? foundTbl : rslvKey; - ret = cmapEnt.getValue(); } } } @@ -460,7 +468,11 @@ public static RowResolver getCombinedRR(RowResolver leftRR, public RowResolver duplicate() { RowResolver resolver = new RowResolver(); resolver.rowSchema = new RowSchema(rowSchema); - resolver.rslvMap.putAll(rslvMap); + for (Map.Entry> entry : rslvMap.entrySet()) { + LinkedHashMap map = new LinkedHashMap<>(); + map.putAll(entry.getValue()); + resolver.rslvMap.put(entry.getKey(), map); + } resolver.invRslvMap.putAll(invRslvMap); resolver.altInvRslvMap.putAll(altInvRslvMap); resolver.expressionMap.putAll(expressionMap); diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java index d39b8bd..7f79bca 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java @@ -1612,6 +1612,8 @@ public boolean doPhase1(ASTNode ast, QB qb, Phase1Ctx ctx_1, PlannerContext plan throw new SemanticException(generateErrorMessage(ast, ErrorMsg.CLUSTERBY_ORDERBY_CONFLICT.getMsg())); } + qbp.addAggregationExprsForClause(ctx_1.dest, + doPhase1GetAggregationsFromSelect(ast, qb, ctx_1.dest)); break; case HiveParser.TOK_GROUPBY: diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/TypeCheckProcFactory.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/TypeCheckProcFactory.java index 8f8eab0..a8a3ef2 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/TypeCheckProcFactory.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/TypeCheckProcFactory.java @@ -163,7 +163,7 @@ public static ExprNodeDesc processGByExpr(Node nd, Object procCtx) if (colInfo != null) { desc = new ExprNodeColumnDesc(colInfo); ASTNode source = input.getExpressionSource(expr); - if (source != null) { + if (source != null && ctx.getUnparseTranslator() != null) { ctx.getUnparseTranslator().addCopyTranslation(expr, source); } return desc; diff --git a/ql/src/test/queries/clientpositive/order_by_expr_1.q b/ql/src/test/queries/clientpositive/order_by_expr_1.q new file mode 100644 index 0000000..1d99e6a --- /dev/null +++ b/ql/src/test/queries/clientpositive/order_by_expr_1.q @@ -0,0 +1,44 @@ +set hive.fetch.task.conversion=none; + +create table t(a int, b int); + +insert into t values (1,2),(1,2),(1,3),(2,4),(20,-100),(-1000,100),(4,5),(3,7),(8,9); + +select a, count(a) from t group by a order by count(a), a; + +explain +select + interval '2-2' year to month + interval '3-3' year to month, + interval '2-2' year to month - interval '3-3' year to month +from t +order by interval '2-2' year to month + interval '3-3' year to month +limit 2; + +select a,b, count(*) from t group by a, b order by a+b; +select a,b, count(*) from t group by a, b order by count(*), b desc; +select a,b,count(*),a+b from t group by a, b order by a+b; +select a,b from t order by a+b; +select a,b,a+b from t order by a+b; +select a,b,a+b from t order by a+b desc; +select cast(0.99999999999999999999 as decimal(20,19)) as c from t limit 1; +select cast(0.99999999999999999999 as decimal(20,19)) as c from t order by c limit 1; +select a from t order by b; +select a from t order by 0-b; +select b from t order by 0-b; +select b from t order by a, 0-b; +select b from t order by a+1, 0-b; +select b from t order by 0-b, a+1; +explain select b from t order by 0-b, a+1; +select a,b from t order by 0-b; +select a,b from t order by a, a+1, 0-b; +select a,b from t order by 0-b, a+1; +select a+1,b from t order by a, a+1, 0-b; +select a+1 as c, b from t order by a, a+1, 0-b; +select a, a+1 as c, b from t order by a, a+1, 0-b; +select a, a+1 as c, b, 2*b from t order by a, a+1, 0-b; +explain select a, a+1 as c, b, 2*b from t order by a, a+1, 0-b; +select a, a+1 as c, b, 2*b from t order by a+1, 0-b; +select a,b, count(*) as c from t group by a, b order by c, a+b desc; + +select a, max(b) from t group by a order by count(b), a desc; +select a, max(b) from t group by a order by count(b), a; diff --git a/ql/src/test/queries/clientpositive/order_by_expr_2.q b/ql/src/test/queries/clientpositive/order_by_expr_2.q new file mode 100644 index 0000000..043f8ed --- /dev/null +++ b/ql/src/test/queries/clientpositive/order_by_expr_2.q @@ -0,0 +1,11 @@ +set hive.fetch.task.conversion=none; + +create table t(a int, b int); + +insert into t values (1,2),(1,2),(1,3),(2,4),(20,-100),(-1000,100),(4,5),(3,7),(8,9); + +select a as b, b as a from t order by a; +select a as b, b as a from t order by t.a; +select a as b from t order by b; +select a as b from t order by 0-a; +select a,b,count(*),a+b from t group by a, b order by a+b; diff --git a/ql/src/test/results/clientpositive/auto_join8.q.out b/ql/src/test/results/clientpositive/auto_join8.q.out index ccbafba..cf57079 100644 --- a/ql/src/test/results/clientpositive/auto_join8.q.out +++ b/ql/src/test/results/clientpositive/auto_join8.q.out @@ -91,7 +91,7 @@ STAGE PLANS: predicate: _col2 is null (type: boolean) Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), null (type: int), _col3 (type: string) + expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -152,7 +152,7 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT sum(hash(dest1.c1,dest1.c2,dest1.c3,dest1.c4)) FROM dest1 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out b/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out index 17a912e..0b73bce 100644 --- a/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out +++ b/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out @@ -21,25 +21,21 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:b + b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:b + b TableScan alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + HashTable Sink Operator + keys: + 0 key (type: string) + 1 key (type: string) Stage: Stage-4 Map Reduce @@ -50,24 +46,20 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -99,25 +91,21 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:a + a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:a + a TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + HashTable Sink Operator + keys: + 0 key (type: string) + 1 key (type: string) Stage: Stage-5 Map Reduce @@ -128,24 +116,20 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -158,38 +142,30 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) TableScan alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 key (type: string) + 1 key (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/cp_sel.q.out b/ql/src/test/results/clientpositive/cp_sel.q.out index 1778ccd..af2efeb 100644 --- a/ql/src/test/results/clientpositive/cp_sel.q.out +++ b/ql/src/test/results/clientpositive/cp_sel.q.out @@ -27,23 +27,27 @@ STAGE PLANS: value expressions: _col1 (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), 'hello' (type: string), 'world' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'hello' (type: string), 'world' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator - limit: 1 + limit: -1 Processor Tree: ListSink diff --git a/ql/src/test/results/clientpositive/druid_basic2.q.out b/ql/src/test/results/clientpositive/druid_basic2.q.out index 6177d56..a6555f9 100644 --- a/ql/src/test/results/clientpositive/druid_basic2.q.out +++ b/ql/src/test/results/clientpositive/druid_basic2.q.out @@ -544,6 +544,7 @@ ORDER BY CAST(robot AS INTEGER) ASC, m DESC LIMIT 10 POSTHOOK: type: QUERY STAGE DEPENDENCIES: +<<<<<<< HEAD Stage-1 is a root stage Stage-0 depends on stages: Stage-1 @@ -926,6 +927,27 @@ STAGE PLANS: limit: 10 Processor Tree: ListSink +======= + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: druid_table_1 + properties: + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"DAY","dimensions":["robot","language"],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"robot","direction":"ascending"},{"dimension":"$f3","direction":"descending"}]},"aggregations":[{"type":"longMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]} + druid.query.type groupBy + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + GatherStats: false + Select Operator + expressions: robot (type: string), __time (type: timestamp), $f3 (type: bigint), $f4 (type: float) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + ListSink +>>>>>>> clidriver golden file change PREHOOK: query: EXPLAIN EXTENDED SELECT robot, floor_day(`__time`), max(added) as m, sum(delta) as s diff --git a/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out b/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out index 2abb819..e12c05a 100644 --- a/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out +++ b/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out @@ -1109,7 +1109,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: _col1 (type: int), _col2 (type: int), _col3 (type: double), _col4 (type: double), _col6 (type: int), _col7 (type: int), _col8 (type: double), _col9 (type: double) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col8, _col9 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: true @@ -1123,10 +1123,10 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col3 (type: double), _col4 (type: double), _col8 (type: double), _col9 (type: double) + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: double), _col3 (type: double), _col6 (type: double), _col7 (type: double) sort order: ++++++ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col5 (type: int), _col6 (type: int) + value expressions: _col4 (type: int), _col5 (type: int) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), 3 (type: int), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: double), VALUE._col0 (type: int), VALUE._col1 (type: int), 4 (type: int), KEY.reducesinkkey4 (type: double), KEY.reducesinkkey5 (type: double) diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets_grouping.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets_grouping.q.out index 473d17a..f6f7d16 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets_grouping.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets_grouping.q.out @@ -317,8 +317,13 @@ STAGE PLANS: predicate: ((grouping(_col2, 1) = 1) or (grouping(_col2, 0) = 1)) (type: boolean) Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE Select Operator +<<<<<<< HEAD expressions: _col0 (type: int), _col1 (type: int), (grouping(_col2, 1) + grouping(_col2, 0)) (type: int) outputColumnNames: _col0, _col1, _col2 +======= + expressions: _col0 (type: int), _col1 (type: int), (grouping(_col2, 1) + grouping(_col2, 0)) (type: tinyint), CASE WHEN (((grouping(_col2, 1) + grouping(_col2, 0)) = 1)) THEN (_col0) ELSE (null) END (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 +>>>>>>> clidriver golden file change Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -332,7 +337,11 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator +<<<<<<< HEAD key expressions: _col2 (type: int), CASE WHEN ((_col2 = 1)) THEN (_col0) ELSE (null) END (type: int) +======= + key expressions: _col2 (type: tinyint), _col3 (type: int) +>>>>>>> clidriver golden file change sort order: -+ Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) diff --git a/ql/src/test/results/clientpositive/join8.q.out b/ql/src/test/results/clientpositive/join8.q.out index c1035b4..a352d52 100644 --- a/ql/src/test/results/clientpositive/join8.q.out +++ b/ql/src/test/results/clientpositive/join8.q.out @@ -90,7 +90,7 @@ STAGE PLANS: predicate: _col2 is null (type: boolean) Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), null (type: int), _col3 (type: string) + expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -149,7 +149,7 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [] +POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out index 325d568..6cc1f57 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out @@ -526,32 +526,28 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 484 (type: int), _col1 (type: bigint) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types int:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1 + columns.types int:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/materialized_view_create_rewrite.q.out b/ql/src/test/results/clientpositive/materialized_view_create_rewrite.q.out index 041621f..62f7393 100644 --- a/ql/src/test/results/clientpositive/materialized_view_create_rewrite.q.out +++ b/ql/src/test/results/clientpositive/materialized_view_create_rewrite.q.out @@ -119,7 +119,7 @@ POSTHOOK: Input: default@cmv_mat_view2 #### A masked pattern was here #### 3 978.76 3 9.80 -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [default.cmv_mat_view2, $hdt$_0]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from ( (select a, c from cmv_basetable where a = 3) table1 @@ -143,30 +143,26 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: default.cmv_mat_view2 - Statistics: Num rows: 2 Data size: 322 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c (type: decimal(10,2)) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 322 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 2 Data size: 322 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(10,2)) - TableScan alias: cmv_basetable Statistics: Num rows: 5 Data size: 81 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((d = 3) and (3 = a)) (type: boolean) Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: c (type: decimal(10,2)) - outputColumnNames: _col0 + expressions: 3 (type: int), c (type: decimal(10,2)) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(10,2)) + value expressions: _col0 (type: int), _col1 (type: decimal(10,2)) + TableScan + alias: default.cmv_mat_view2 + Statistics: Num rows: 2 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 2 Data size: 322 Basic stats: COMPLETE Column stats: NONE + value expressions: a (type: int), c (type: decimal(10,2)) Reduce Operator Tree: Join Operator condition map: @@ -174,10 +170,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1 + outputColumnNames: _col0, _col1, _col5, _col6 Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 3 (type: int), _col0 (type: decimal(10,2)), 3 (type: int), _col1 (type: decimal(10,2)) + expressions: _col0 (type: int), _col1 (type: decimal(10,2)), _col5 (type: int), _col6 (type: decimal(10,2)) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -194,7 +190,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [default.cmv_mat_view2, $hdt$_0]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select * from ( (select a, c from cmv_basetable where a = 3) table1 join @@ -253,13 +249,13 @@ STAGE PLANS: predicate: (a = 3) (type: boolean) Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: c (type: decimal(10,2)) - outputColumnNames: _col0 + expressions: 3 (type: int), c (type: decimal(10,2)) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(10,2)) + value expressions: _col0 (type: int), _col1 (type: decimal(10,2)) TableScan alias: cmv_basetable Statistics: Num rows: 5 Data size: 81 Basic stats: COMPLETE Column stats: NONE @@ -267,13 +263,13 @@ STAGE PLANS: predicate: ((d = 3) and (3 = a)) (type: boolean) Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: c (type: decimal(10,2)) - outputColumnNames: _col0 + expressions: 3 (type: int), c (type: decimal(10,2)) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(10,2)) + value expressions: _col0 (type: int), _col1 (type: decimal(10,2)) Reduce Operator Tree: Join Operator condition map: @@ -281,19 +277,15 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 3 (type: int), _col0 (type: decimal(10,2)), 3 (type: int), _col1 (type: decimal(10,2)) - outputColumnNames: _col0, _col1, _col2, _col3 + File Output Operator + compressed: false Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 66 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 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/order3.q.out b/ql/src/test/results/clientpositive/order3.q.out index 898f7a8..d3db1b9 100644 --- a/ql/src/test/results/clientpositive/order3.q.out +++ b/ql/src/test/results/clientpositive/order3.q.out @@ -256,23 +256,27 @@ STAGE PLANS: value expressions: _col1 (type: bigint) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: bigint), 'AAA' (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: bigint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: int), _col1 (type: bigint), 'AAA' (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 30 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 + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 30 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 Stage: Stage-0 Fetch Operator - limit: 3 + limit: -1 Processor Tree: ListSink diff --git a/ql/src/test/results/clientpositive/order_by_expr_1.q.out b/ql/src/test/results/clientpositive/order_by_expr_1.q.out new file mode 100644 index 0000000..39babb7 --- /dev/null +++ b/ql/src/test/results/clientpositive/order_by_expr_1.q.out @@ -0,0 +1,566 @@ +PREHOOK: query: create table t(a int, b int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t +POSTHOOK: query: create table t(a int, b int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t +PREHOOK: query: insert into t values (1,2),(1,2),(1,3),(2,4),(20,-100),(-1000,100),(4,5),(3,7),(8,9) +PREHOOK: type: QUERY +PREHOOK: Output: default@t +POSTHOOK: query: insert into t values (1,2),(1,2),(1,3),(2,4),(20,-100),(-1000,100),(4,5),(3,7),(8,9) +POSTHOOK: type: QUERY +POSTHOOK: Output: default@t +POSTHOOK: Lineage: t.a EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: t.b EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] +PREHOOK: query: select a, count(a) from t group by a order by count(a), a +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a, count(a) from t group by a order by count(a), a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 1 +2 1 +3 1 +4 1 +8 1 +20 1 +1 3 +PREHOOK: query: explain +select + interval '2-2' year to month + interval '3-3' year to month, + interval '2-2' year to month - interval '3-3' year to month +from t +order by interval '2-2' year to month + interval '3-3' year to month +limit 2 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select + interval '2-2' year to month + interval '3-3' year to month, + interval '2-2' year to month - interval '3-3' year to month +from t +order by interval '2-2' year to month + interval '3-3' year to month +limit 2 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t + Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 5-5 (type: interval_year_month), -1-1 (type: interval_year_month) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 2 + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 2 + Processor Tree: + ListSink + +PREHOOK: query: select a,b, count(*) from t group by a, b order by a+b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a,b, count(*) from t group by a, b order by a+b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 100 1 +20 -100 1 +1 2 2 +1 3 1 +2 4 1 +4 5 1 +3 7 1 +8 9 1 +PREHOOK: query: select a,b, count(*) from t group by a, b order by count(*), b desc +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a,b, count(*) from t group by a, b order by count(*), b desc +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 100 1 +8 9 1 +3 7 1 +4 5 1 +2 4 1 +1 3 1 +20 -100 1 +1 2 2 +PREHOOK: query: select a,b,count(*),a+b from t group by a, b order by a+b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a,b,count(*),a+b from t group by a, b order by a+b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 100 1 -900 +20 -100 1 -80 +1 2 2 3 +1 3 1 4 +2 4 1 6 +4 5 1 9 +3 7 1 10 +8 9 1 17 +PREHOOK: query: select a,b from t order by a+b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a,b from t order by a+b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 100 +20 -100 +1 2 +1 2 +1 3 +2 4 +4 5 +3 7 +8 9 +PREHOOK: query: select a,b,a+b from t order by a+b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a,b,a+b from t order by a+b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 100 -900 +20 -100 -80 +1 2 3 +1 2 3 +1 3 4 +2 4 6 +4 5 9 +3 7 10 +8 9 17 +PREHOOK: query: select a,b,a+b from t order by a+b desc +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a,b,a+b from t order by a+b desc +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +8 9 17 +3 7 10 +4 5 9 +2 4 6 +1 3 4 +1 2 3 +1 2 3 +20 -100 -80 +-1000 100 -900 +PREHOOK: query: select cast(0.99999999999999999999 as decimal(20,19)) as c from t limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select cast(0.99999999999999999999 as decimal(20,19)) as c from t limit 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +1.0000000000000000000 +PREHOOK: query: select cast(0.99999999999999999999 as decimal(20,19)) as c from t order by c limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select cast(0.99999999999999999999 as decimal(20,19)) as c from t order by c limit 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +1.0000000000000000000 +PREHOOK: query: select a from t order by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a from t order by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +20 +1 +1 +1 +2 +4 +3 +8 +-1000 +PREHOOK: query: select a from t order by 0-b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a from t order by 0-b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 +8 +3 +4 +2 +1 +1 +1 +20 +PREHOOK: query: select b from t order by 0-b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select b from t order by 0-b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +100 +9 +7 +5 +4 +3 +2 +2 +-100 +PREHOOK: query: select b from t order by a, 0-b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select b from t order by a, 0-b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +100 +3 +2 +2 +4 +7 +5 +9 +-100 +PREHOOK: query: select b from t order by a+1, 0-b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select b from t order by a+1, 0-b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +100 +3 +2 +2 +4 +7 +5 +9 +-100 +PREHOOK: query: select b from t order by 0-b, a+1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select b from t order by 0-b, a+1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +100 +9 +7 +5 +4 +3 +2 +2 +-100 +PREHOOK: query: explain select b from t order by 0-b, a+1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select b from t order by 0-b, a+1 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t + Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: b (type: int), (0 - b) (type: int), (a + 1) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 37 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select a,b from t order by 0-b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a,b from t order by 0-b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 100 +8 9 +3 7 +4 5 +2 4 +1 3 +1 2 +1 2 +20 -100 +PREHOOK: query: select a,b from t order by a, a+1, 0-b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a,b from t order by a, a+1, 0-b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 100 +1 3 +1 2 +1 2 +2 4 +3 7 +4 5 +8 9 +20 -100 +PREHOOK: query: select a,b from t order by 0-b, a+1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a,b from t order by 0-b, a+1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 100 +8 9 +3 7 +4 5 +2 4 +1 3 +1 2 +1 2 +20 -100 +PREHOOK: query: select a+1,b from t order by a, a+1, 0-b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a+1,b from t order by a, a+1, 0-b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-999 100 +2 3 +2 2 +2 2 +3 4 +4 7 +5 5 +9 9 +21 -100 +PREHOOK: query: select a+1 as c, b from t order by a, a+1, 0-b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a+1 as c, b from t order by a, a+1, 0-b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-999 100 +2 3 +2 2 +2 2 +3 4 +4 7 +5 5 +9 9 +21 -100 +PREHOOK: query: select a, a+1 as c, b from t order by a, a+1, 0-b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a, a+1 as c, b from t order by a, a+1, 0-b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 -999 100 +1 2 3 +1 2 2 +1 2 2 +2 3 4 +3 4 7 +4 5 5 +8 9 9 +20 21 -100 +PREHOOK: query: select a, a+1 as c, b, 2*b from t order by a, a+1, 0-b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a, a+1 as c, b, 2*b from t order by a, a+1, 0-b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 -999 100 200 +1 2 3 6 +1 2 2 4 +1 2 2 4 +2 3 4 8 +3 4 7 14 +4 5 5 10 +8 9 9 18 +20 21 -100 -200 +PREHOOK: query: explain select a, a+1 as c, b, 2*b from t order by a, a+1, 0-b +PREHOOK: type: QUERY +POSTHOOK: query: explain select a, a+1 as c, b, 2*b from t order by a, a+1, 0-b +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t + Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: int), b (type: int), (2 * b) (type: int), (a + 1) (type: int), (0 - b) (type: int) + outputColumnNames: _col0, _col2, _col3, _col4, _col5 + Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col4 (type: int), _col5 (type: int) + sort order: +++ + Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int), _col3 (type: int) + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 37 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select a, a+1 as c, b, 2*b from t order by a+1, 0-b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a, a+1 as c, b, 2*b from t order by a+1, 0-b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 -999 100 200 +1 2 3 6 +1 2 2 4 +1 2 2 4 +2 3 4 8 +3 4 7 14 +4 5 5 10 +8 9 9 18 +20 21 -100 -200 +PREHOOK: query: select a,b, count(*) as c from t group by a, b order by c, a+b desc +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a,b, count(*) as c from t group by a, b order by c, a+b desc +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +8 9 1 +3 7 1 +4 5 1 +2 4 1 +1 3 1 +20 -100 1 +-1000 100 1 +1 2 2 +PREHOOK: query: select a, max(b) from t group by a order by count(b), a desc +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a, max(b) from t group by a order by count(b), a desc +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +20 -100 +8 9 +4 5 +3 7 +2 4 +-1000 100 +1 3 +PREHOOK: query: select a, max(b) from t group by a order by count(b), a +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a, max(b) from t group by a order by count(b), a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 100 +2 4 +3 7 +4 5 +8 9 +20 -100 +1 3 diff --git a/ql/src/test/results/clientpositive/order_by_expr_2.q.out b/ql/src/test/results/clientpositive/order_by_expr_2.q.out new file mode 100644 index 0000000..4b835b0 --- /dev/null +++ b/ql/src/test/results/clientpositive/order_by_expr_2.q.out @@ -0,0 +1,100 @@ +PREHOOK: query: create table t(a int, b int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t +POSTHOOK: query: create table t(a int, b int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t +PREHOOK: query: insert into t values (1,2),(1,2),(1,3),(2,4),(20,-100),(-1000,100),(4,5),(3,7),(8,9) +PREHOOK: type: QUERY +PREHOOK: Output: default@t +POSTHOOK: query: insert into t values (1,2),(1,2),(1,3),(2,4),(20,-100),(-1000,100),(4,5),(3,7),(8,9) +POSTHOOK: type: QUERY +POSTHOOK: Output: default@t +POSTHOOK: Lineage: t.a EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: t.b EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] +PREHOOK: query: select a as b, b as a from t order by a +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a as b, b as a from t order by a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +20 -100 +1 2 +1 2 +1 3 +2 4 +4 5 +3 7 +8 9 +-1000 100 +PREHOOK: query: select a as b, b as a from t order by t.a +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a as b, b as a from t order by t.a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 100 +1 3 +1 2 +1 2 +2 4 +3 7 +4 5 +8 9 +20 -100 +PREHOOK: query: select a as b from t order by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a as b from t order by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 +1 +1 +1 +2 +3 +4 +8 +20 +PREHOOK: query: select a as b from t order by 0-a +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a as b from t order by 0-a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +20 +8 +4 +3 +2 +1 +1 +1 +-1000 +PREHOOK: query: select a,b,count(*),a+b from t group by a, b order by a+b +PREHOOK: type: QUERY +PREHOOK: Input: default@t +#### A masked pattern was here #### +POSTHOOK: query: select a,b,count(*),a+b from t group by a, b order by a+b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +#### A masked pattern was here #### +-1000 100 1 -900 +20 -100 1 -80 +1 2 2 3 +1 3 1 4 +2 4 1 6 +4 5 1 9 +3 7 1 10 +8 9 1 17 diff --git a/ql/src/test/results/clientpositive/pcr.q.out b/ql/src/test/results/clientpositive/pcr.q.out index a1301fd..ffb1d91 100644 --- a/ql/src/test/results/clientpositive/pcr.q.out +++ b/ql/src/test/results/clientpositive/pcr.q.out @@ -1427,10 +1427,10 @@ STAGE PLANS: Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: string) null sort order: a sort order: + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE @@ -1534,8 +1534,8 @@ STAGE PLANS: name: default.pcr_t1 name: default.pcr_t1 Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] + /pcr_t1/ds=2000-04-08 [$hdt$_0:pcr_t1] + /pcr_t1/ds=2000-04-09 [$hdt$_0:pcr_t1] Needs Tagging: false Reduce Operator Tree: Select Operator @@ -2366,7 +2366,7 @@ STAGE PLANS: name: default.pcr_t1 name: default.pcr_t1 Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [$hdt$_0:t1, $hdt$_1:t2] + /pcr_t1/ds=2000-04-08 [$hdt$_0:$hdt$_0:t1, $hdt$_0:$hdt$_1:t2] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -2377,24 +2377,28 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col3,_col4 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -2407,7 +2411,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -2419,7 +2423,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col1,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2429,7 +2433,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col1,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2672,8 +2676,8 @@ STAGE PLANS: name: default.pcr_t1 name: default.pcr_t1 Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [$hdt$_0:t1] - /pcr_t1/ds=2000-04-09 [$hdt$_1:t2] + /pcr_t1/ds=2000-04-08 [$hdt$_0:$hdt$_0:t1] + /pcr_t1/ds=2000-04-09 [$hdt$_0:$hdt$_1:t2] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -2684,24 +2688,28 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col3,_col4 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -2714,7 +2722,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -2726,7 +2734,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col1,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2736,7 +2744,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col1,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -4846,10 +4854,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col3 (type: string) + key expressions: _col0 (type: string), _col2 (type: string) null sort order: aa sort order: ++ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -4956,8 +4964,8 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:srcpart] Needs Tagging: false Reduce Operator Tree: Select Operator @@ -5139,8 +5147,8 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-09/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart] + /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:srcpart] Needs Tagging: false Reduce Operator Tree: Select Operator diff --git a/ql/src/test/results/clientpositive/perf/query31.q.out b/ql/src/test/results/clientpositive/perf/query31.q.out index 3ed312d..95a8e9e 100644 --- a/ql/src/test/results/clientpositive/perf/query31.q.out +++ b/ql/src/test/results/clientpositive/perf/query31.q.out @@ -31,6 +31,7 @@ Stage-0 Fetch Operator limit:-1 Stage-1 +<<<<<<< HEAD Reducer 6 File Output Operator [FS_135] Select Operator [SEL_134] (rows=287493839 width=88) @@ -45,6 +46,22 @@ Stage-0 Conds:RS_125._col0=RS_126._col0(Inner),RS_125._col0=RS_127._col0(Inner),RS_125._col0=RS_128._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col7","_col9","_col11"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_126] +======= + Reducer 7 + File Output Operator [FS_141] + Select Operator [SEL_139] (rows=316243230 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + <-Reducer 6 [SIMPLE_EDGE] + SHUFFLE [RS_138] + Select Operator [SEL_137] (rows=316243230 width=88) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_136] (rows=316243230 width=88) + predicate:CASE WHEN ((_col3 > 0)) THEN (CASE WHEN ((_col9 > 0)) THEN (((_col11 / _col9) > (_col5 / _col3))) ELSE ((null > (_col5 / _col3))) END) ELSE (CASE WHEN ((_col9 > 0)) THEN (((_col11 / _col9) > null)) ELSE (null) END) END + Merge Join Operator [MERGEJOIN_273] (rows=632486460 width=88) + Conds:RS_132._col6=RS_133._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col7","_col9","_col11"] + <-Reducer 38 [SIMPLE_EDGE] + SHUFFLE [RS_133] +>>>>>>> clidriver golden file change PartitionCols:_col0 Group By Operator [GBY_38] (rows=348477374 width=88) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 @@ -53,6 +70,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_36] (rows=696954748 width=88) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 +<<<<<<< HEAD Merge Join Operator [MERGEJOIN_259] (rows=696954748 width=88) Conds:RS_32._col1=RS_33._col0(Inner),Output:["_col2","_col7"] <-Map 14 [SIMPLE_EDGE] @@ -312,4 +330,286 @@ Stage-0 predicate:((d_qoy = 2) and (d_year = 1998) 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","d_qoy"] +======= + Select Operator [SEL_127] (rows=174243235 width=135) + Output:["_col7","_col2"] + Merge Join Operator [MERGEJOIN_270] (rows=174243235 width=135) + Conds:RS_124._col1=RS_125._col0(Inner),Output:["_col2","_col7"] + <-Map 40 [SIMPLE_EDGE] + SHUFFLE [RS_125] + PartitionCols:_col0 + Select Operator [SEL_120] (rows=40000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_258] (rows=40000000 width=1014) + predicate:(ca_address_sk is not null and ca_county is not null) + TableScan [TS_118] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"] + <-Reducer 36 [SIMPLE_EDGE] + SHUFFLE [RS_124] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_269] (rows=158402938 width=135) + Conds:RS_121._col0=RS_122._col0(Inner),Output:["_col1","_col2"] + <-Map 35 [SIMPLE_EDGE] + SHUFFLE [RS_121] + PartitionCols:_col0 + Select Operator [SEL_114] (rows=144002668 width=135) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_256] (rows=144002668 width=135) + predicate:(ws_sold_date_sk is not null and ws_bill_addr_sk is not null) + TableScan [TS_112] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] + <-Map 39 [SIMPLE_EDGE] + SHUFFLE [RS_122] + PartitionCols:_col0 + Select Operator [SEL_117] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_257] (rows=18262 width=1119) + predicate:((d_qoy = 3) and (d_year = 1998) and d_date_sk is not null) + TableScan [TS_115] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] + <-Reducer 5 [SIMPLE_EDGE] + SHUFFLE [RS_132] + PartitionCols:_col6 + Filter Operator [FIL_110] (rows=574987679 width=88) + predicate:CASE WHEN ((_col1 > 0)) THEN (CASE WHEN ((_col7 > 0)) THEN (((_col9 / _col7) > (_col3 / _col1))) ELSE ((null > (_col3 / _col1))) END) ELSE (CASE WHEN ((_col7 > 0)) THEN (((_col9 / _col7) > null)) ELSE (null) END) END + Select Operator [SEL_109] (rows=1149975359 width=88) + Output:["_col0","_col1","_col3","_col5","_col6","_col7","_col9"] + Merge Join Operator [MERGEJOIN_272] (rows=1149975359 width=88) + Conds:RS_104._col0=RS_105._col0(Inner),RS_104._col0=RS_106._col0(Inner),RS_104._col0=RS_107._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col6","_col7","_col9"] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_105] + PartitionCols:_col0 + Group By Operator [GBY_38] (rows=348477374 width=88) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:_col0 + Group By Operator [GBY_36] (rows=696954748 width=88) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 + Select Operator [SEL_35] (rows=696954748 width=88) + Output:["_col7","_col2"] + Merge Join Operator [MERGEJOIN_262] (rows=696954748 width=88) + Conds:RS_32._col1=RS_33._col0(Inner),Output:["_col2","_col7"] + <-Map 15 [SIMPLE_EDGE] + SHUFFLE [RS_33] + PartitionCols:_col0 + Select Operator [SEL_28] (rows=40000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_246] (rows=40000000 width=1014) + predicate:(ca_address_sk is not null and ca_county is not null) + TableScan [TS_26] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"] + <-Reducer 11 [SIMPLE_EDGE] + SHUFFLE [RS_32] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_261] (rows=633595212 width=88) + Conds:RS_29._col0=RS_30._col0(Inner),Output:["_col1","_col2"] + <-Map 10 [SIMPLE_EDGE] + SHUFFLE [RS_29] + PartitionCols:_col0 + Select Operator [SEL_22] (rows=575995635 width=88) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_244] (rows=575995635 width=88) + predicate:(ss_sold_date_sk is not null and ss_addr_sk is not null) + TableScan [TS_20] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] + <-Map 14 [SIMPLE_EDGE] + SHUFFLE [RS_30] + PartitionCols:_col0 + Select Operator [SEL_25] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_245] (rows=18262 width=1119) + predicate:((d_qoy = 1) and (d_year = 1998) 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","d_qoy"] + <-Reducer 19 [SIMPLE_EDGE] + SHUFFLE [RS_106] + PartitionCols:_col0 + Group By Operator [GBY_58] (rows=348477374 width=88) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_57] + PartitionCols:_col0 + Group By Operator [GBY_56] (rows=696954748 width=88) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 + Select Operator [SEL_55] (rows=696954748 width=88) + Output:["_col7","_col2"] + Merge Join Operator [MERGEJOIN_264] (rows=696954748 width=88) + Conds:RS_52._col1=RS_53._col0(Inner),Output:["_col2","_col7"] + <-Map 21 [SIMPLE_EDGE] + SHUFFLE [RS_53] + PartitionCols:_col0 + Select Operator [SEL_48] (rows=40000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_249] (rows=40000000 width=1014) + predicate:(ca_address_sk is not null and ca_county is not null) + TableScan [TS_46] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"] + <-Reducer 17 [SIMPLE_EDGE] + SHUFFLE [RS_52] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_263] (rows=633595212 width=88) + Conds:RS_49._col0=RS_50._col0(Inner),Output:["_col1","_col2"] + <-Map 16 [SIMPLE_EDGE] + SHUFFLE [RS_49] + PartitionCols:_col0 + Select Operator [SEL_42] (rows=575995635 width=88) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_247] (rows=575995635 width=88) + predicate:(ss_sold_date_sk is not null and ss_addr_sk is not null) + TableScan [TS_40] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] + <-Map 20 [SIMPLE_EDGE] + SHUFFLE [RS_50] + PartitionCols:_col0 + Select Operator [SEL_45] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_248] (rows=18262 width=1119) + predicate:((d_qoy = 3) and (d_year = 1998) and d_date_sk is not null) + TableScan [TS_43] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] + <-Reducer 26 [SIMPLE_EDGE] + SHUFFLE [RS_107] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_271] (rows=95833780 width=135) + Conds:RS_100._col0=RS_101._col0(Inner),Output:["_col0","_col1","_col3"] + <-Reducer 25 [SIMPLE_EDGE] + SHUFFLE [RS_100] + PartitionCols:_col0 + Group By Operator [GBY_78] (rows=87121617 width=135) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 24 [SIMPLE_EDGE] + SHUFFLE [RS_77] + PartitionCols:_col0 + Group By Operator [GBY_76] (rows=174243235 width=135) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 + Select Operator [SEL_75] (rows=174243235 width=135) + Output:["_col7","_col2"] + Merge Join Operator [MERGEJOIN_266] (rows=174243235 width=135) + Conds:RS_72._col1=RS_73._col0(Inner),Output:["_col2","_col7"] + <-Map 28 [SIMPLE_EDGE] + SHUFFLE [RS_73] + PartitionCols:_col0 + Select Operator [SEL_68] (rows=40000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_252] (rows=40000000 width=1014) + predicate:(ca_address_sk is not null and ca_county is not null) + TableScan [TS_66] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"] + <-Reducer 23 [SIMPLE_EDGE] + SHUFFLE [RS_72] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_265] (rows=158402938 width=135) + Conds:RS_69._col0=RS_70._col0(Inner),Output:["_col1","_col2"] + <-Map 22 [SIMPLE_EDGE] + SHUFFLE [RS_69] + PartitionCols:_col0 + Select Operator [SEL_62] (rows=144002668 width=135) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_250] (rows=144002668 width=135) + predicate:(ws_sold_date_sk is not null and ws_bill_addr_sk is not null) + TableScan [TS_60] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] + <-Map 27 [SIMPLE_EDGE] + SHUFFLE [RS_70] + PartitionCols:_col0 + Select Operator [SEL_65] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_251] (rows=18262 width=1119) + predicate:((d_qoy = 1) and (d_year = 1998) and d_date_sk is not null) + TableScan [TS_63] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] + <-Reducer 32 [SIMPLE_EDGE] + SHUFFLE [RS_101] + PartitionCols:_col0 + Group By Operator [GBY_98] (rows=87121617 width=135) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 31 [SIMPLE_EDGE] + SHUFFLE [RS_97] + PartitionCols:_col0 + Group By Operator [GBY_96] (rows=174243235 width=135) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 + Select Operator [SEL_95] (rows=174243235 width=135) + Output:["_col7","_col2"] + Merge Join Operator [MERGEJOIN_268] (rows=174243235 width=135) + Conds:RS_92._col1=RS_93._col0(Inner),Output:["_col2","_col7"] + <-Map 34 [SIMPLE_EDGE] + SHUFFLE [RS_93] + PartitionCols:_col0 + Select Operator [SEL_88] (rows=40000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_255] (rows=40000000 width=1014) + predicate:(ca_address_sk is not null and ca_county is not null) + TableScan [TS_86] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"] + <-Reducer 30 [SIMPLE_EDGE] + SHUFFLE [RS_92] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_267] (rows=158402938 width=135) + Conds:RS_89._col0=RS_90._col0(Inner),Output:["_col1","_col2"] + <-Map 29 [SIMPLE_EDGE] + SHUFFLE [RS_89] + PartitionCols:_col0 + Select Operator [SEL_82] (rows=144002668 width=135) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_253] (rows=144002668 width=135) + predicate:(ws_sold_date_sk is not null and ws_bill_addr_sk is not null) + TableScan [TS_80] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] + <-Map 33 [SIMPLE_EDGE] + SHUFFLE [RS_90] + PartitionCols:_col0 + Select Operator [SEL_85] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_254] (rows=18262 width=1119) + predicate:((d_qoy = 2) and (d_year = 1998) and d_date_sk is not null) + TableScan [TS_83] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_104] + PartitionCols:_col0 + Group By Operator [GBY_18] (rows=348477374 width=88) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_17] + PartitionCols:_col0 + Group By Operator [GBY_16] (rows=696954748 width=88) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 + Select Operator [SEL_15] (rows=696954748 width=88) + Output:["_col7","_col2"] + Merge Join Operator [MERGEJOIN_260] (rows=696954748 width=88) + Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col2","_col7"] + <-Map 9 [SIMPLE_EDGE] + SHUFFLE [RS_13] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=40000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_243] (rows=40000000 width=1014) + predicate:(ca_address_sk is not null and ca_county is not null) + TableScan [TS_6] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_259] (rows=633595212 width=88) + Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_9] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=575995635 width=88) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_241] (rows=575995635 width=88) + predicate:(ss_sold_date_sk is not null and ss_addr_sk is not null) + TableScan [TS_0] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] + <-Map 8 [SIMPLE_EDGE] + SHUFFLE [RS_10] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_242] (rows=18262 width=1119) + predicate:((d_qoy = 2) and (d_year = 1998) 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","d_qoy"] +>>>>>>> clidriver golden file change diff --git a/ql/src/test/results/clientpositive/perf/query36.q.out b/ql/src/test/results/clientpositive/perf/query36.q.out index 57ab26a..b5110d9 100644 --- a/ql/src/test/results/clientpositive/perf/query36.q.out +++ b/ql/src/test/results/clientpositive/perf/query36.q.out @@ -68,10 +68,10 @@ Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Stage-0 Fetch Operator - limit:100 + limit:-1 Stage-1 Reducer 7 - File Output Operator [FS_35] + File Output Operator [FS_36] Limit [LIM_34] (rows=100 width=88) Number of rows:100 Select Operator [SEL_33] (rows=1149975358 width=88) @@ -79,7 +79,7 @@ Stage-0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_32] Select Operator [SEL_30] (rows=1149975358 width=88) - Output:["_col0","_col1","_col2","_col3","_col4"] + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] PTF Operator [PTF_29] (rows=1149975358 width=88) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(_col4 / _col5) ASC NULLS FIRST","partition by:":"(grouping(_col6, 1) + grouping(_col6, 0)), CASE WHEN ((grouping(_col6, 0) = 0)) THEN (_col0) ELSE (null) END"}] Select Operator [SEL_28] (rows=1149975358 width=88) @@ -98,42 +98,42 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col0, _col1, 0 Select Operator [SEL_21] (rows=766650239 width=88) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_51] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_52] (rows=766650239 width=88) Conds:RS_18._col1=RS_19._col0(Inner),Output:["_col3","_col4","_col10","_col11"] <-Map 10 [SIMPLE_EDGE] SHUFFLE [RS_19] PartitionCols:_col0 Select Operator [SEL_11] (rows=462000 width=1436) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_48] (rows=462000 width=1436) + Filter Operator [FIL_49] (rows=462000 width=1436) predicate:i_item_sk is not null TableScan [TS_9] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_class","i_category"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_50] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_51] (rows=696954748 width=88) Conds:RS_15._col2=RS_16._col0(Inner),Output:["_col1","_col3","_col4"] <-Map 9 [SIMPLE_EDGE] SHUFFLE [RS_16] PartitionCols:_col0 Select Operator [SEL_8] (rows=852 width=1910) Output:["_col0"] - Filter Operator [FIL_47] (rows=852 width=1910) + Filter Operator [FIL_48] (rows=852 width=1910) predicate:((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC', 'AL', 'GA') and s_store_sk is not null) TableScan [TS_6] (rows=1704 width=1910) default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_state"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_49] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_50] (rows=633595212 width=88) Conds:RS_12._col0=RS_13._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col0 Select Operator [SEL_2] (rows=575995635 width=88) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_45] (rows=575995635 width=88) + Filter Operator [FIL_46] (rows=575995635 width=88) predicate:(ss_sold_date_sk is not null and ss_item_sk is not null and ss_store_sk is not null) TableScan [TS_0] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_ext_sales_price","ss_net_profit"] @@ -142,7 +142,7 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_5] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_46] (rows=36524 width=1119) + Filter Operator [FIL_47] (rows=36524 width=1119) predicate:((d_year = 1999) and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=1119) default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] diff --git a/ql/src/test/results/clientpositive/perf/query39.q.out b/ql/src/test/results/clientpositive/perf/query39.q.out index 19472c4..c93fe14 100644 --- a/ql/src/test/results/clientpositive/perf/query39.q.out +++ b/ql/src/test/results/clientpositive/perf/query39.q.out @@ -21,14 +21,14 @@ Stage-0 limit:-1 Stage-1 Reducer 7 - File Output Operator [FS_62] + File Output Operator [FS_63] Select Operator [SEL_61] (rows=13756683 width=15) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_60] Select Operator [SEL_59] (rows=13756683 width=15) - Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col8","_col9"] - Merge Join Operator [MERGEJOIN_103] (rows=13756683 width=15) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_104] (rows=13756683 width=15) Conds:RS_56._col1, _col2=RS_57._col1, _col2(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col9"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_57] @@ -46,6 +46,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_50] (rows=50024305 width=15) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["stddev_samp(_col3)","avg(_col3)"],keys:_col8, _col7, _col9 +<<<<<<< HEAD Merge Join Operator [MERGEJOIN_102] (rows=50024305 width=15) Conds:RS_46._col2=RS_47._col0(Inner),Output:["_col3","_col7","_col8","_col9"] <-Map 18 [SIMPLE_EDGE] @@ -94,6 +95,58 @@ Stage-0 predicate:((d_year = 1999) and (d_moy = 4) and d_date_sk is not null) TableScan [TS_31] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] +======= + Select Operator [SEL_49] (rows=50024305 width=15) + Output:["_col8","_col7","_col9","_col3"] + Merge Join Operator [MERGEJOIN_103] (rows=50024305 width=15) + Conds:RS_46._col2=RS_47._col0(Inner),Output:["_col3","_col7","_col8","_col9"] + <-Map 18 [SIMPLE_EDGE] + SHUFFLE [RS_47] + PartitionCols:_col0 + Select Operator [SEL_39] (rows=27 width=1029) + Output:["_col0","_col1"] + Filter Operator [FIL_97] (rows=27 width=1029) + predicate:w_warehouse_sk is not null + TableScan [TS_37] (rows=27 width=1029) + default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_warehouse_name"] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_46] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_102] (rows=45476640 width=15) + Conds:RS_43._col1=RS_44._col0(Inner),Output:["_col2","_col3","_col7"] + <-Map 17 [SIMPLE_EDGE] + SHUFFLE [RS_44] + PartitionCols:_col0 + Select Operator [SEL_36] (rows=462000 width=1436) + Output:["_col0"] + Filter Operator [FIL_96] (rows=462000 width=1436) + predicate:i_item_sk is not null + TableScan [TS_34] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk"] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_43] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_101] (rows=41342400 width=15) + Conds:RS_40._col0=RS_41._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 11 [SIMPLE_EDGE] + SHUFFLE [RS_40] + PartitionCols:_col0 + Select Operator [SEL_30] (rows=37584000 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_94] (rows=37584000 width=15) + predicate:(inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) + TableScan [TS_28] (rows=37584000 width=15) + default@inventory,inventory,Tbl:COMPLETE,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"] + <-Map 16 [SIMPLE_EDGE] + SHUFFLE [RS_41] + PartitionCols:_col0 + Select Operator [SEL_33] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_95] (rows=18262 width=1119) + predicate:((d_year = 1999) and (d_moy = 4) and d_date_sk is not null) + TableScan [TS_31] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] +>>>>>>> clidriver golden file change <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col1, _col2 @@ -110,6 +163,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_22] (rows=50024305 width=15) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["stddev_samp(_col3)","avg(_col3)"],keys:_col8, _col7, _col9 +<<<<<<< HEAD Merge Join Operator [MERGEJOIN_99] (rows=50024305 width=15) Conds:RS_18._col2=RS_19._col0(Inner),Output:["_col3","_col7","_col8","_col9"] <-Map 10 [SIMPLE_EDGE] @@ -158,6 +212,58 @@ Stage-0 predicate:((d_year = 1999) and (d_moy = 3) 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","d_moy"] +======= + Select Operator [SEL_21] (rows=50024305 width=15) + Output:["_col8","_col7","_col9","_col3"] + Merge Join Operator [MERGEJOIN_100] (rows=50024305 width=15) + Conds:RS_18._col2=RS_19._col0(Inner),Output:["_col3","_col7","_col8","_col9"] + <-Map 10 [SIMPLE_EDGE] + SHUFFLE [RS_19] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=27 width=1029) + Output:["_col0","_col1"] + Filter Operator [FIL_93] (rows=27 width=1029) + predicate:w_warehouse_sk is not null + TableScan [TS_9] (rows=27 width=1029) + default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_warehouse_name"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_99] (rows=45476640 width=15) + Conds:RS_15._col1=RS_16._col0(Inner),Output:["_col2","_col3","_col7"] + <-Map 9 [SIMPLE_EDGE] + SHUFFLE [RS_16] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=462000 width=1436) + Output:["_col0"] + Filter Operator [FIL_92] (rows=462000 width=1436) + predicate:i_item_sk is not null + TableScan [TS_6] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_15] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_98] (rows=41342400 width=15) + Conds:RS_12._col0=RS_13._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=37584000 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_90] (rows=37584000 width=15) + predicate:(inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) + TableScan [TS_0] (rows=37584000 width=15) + default@inventory,inventory,Tbl:COMPLETE,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"] + <-Map 8 [SIMPLE_EDGE] + SHUFFLE [RS_13] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_91] (rows=18262 width=1119) + predicate:((d_year = 1999) and (d_moy = 3) 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","d_moy"] +>>>>>>> clidriver golden file change PREHOOK: query: with inv as (select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy ,stdev,mean, case mean when 0 then null else stdev/mean end cov from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean from inventory ,item ,warehouse ,date_dim where inv_item_sk = i_item_sk and inv_warehouse_sk = w_warehouse_sk and inv_date_sk = d_date_sk and d_year =1999 group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo where case mean when 0 then 0 else stdev/mean end > 1) select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov from inv inv1,inv inv2 where inv1.i_item_sk = inv2.i_item_sk and inv1.w_warehouse_sk = inv2.w_warehouse_sk and inv1.d_moy=3 and inv2.d_moy=3+1 and inv1.cov > 1.5 order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov ,inv2.d_moy,inv2.mean, inv2.cov PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/perf/query42.q.out b/ql/src/test/results/clientpositive/perf/query42.q.out index 3bebac3..b7392d1 100644 --- a/ql/src/test/results/clientpositive/perf/query42.q.out +++ b/ql/src/test/results/clientpositive/perf/query42.q.out @@ -12,18 +12,18 @@ Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Stage-0 Fetch Operator - limit:100 + limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_23] - Limit [LIM_22] (rows=100 width=88) - Number of rows:100 - Select Operator [SEL_21] (rows=348477374 width=88) - Output:["_col0","_col1","_col2","_col3"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_20] - Select Operator [SEL_19] (rows=348477374 width=88) - Output:["_col1","_col2","_col3"] + File Output Operator [FS_24] + Select Operator [SEL_23] (rows=100 width=88) + Output:["_col0","_col1","_col2","_col3"] + Limit [LIM_22] (rows=100 width=88) + Number of rows:100 + Select Operator [SEL_21] (rows=348477374 width=88) + Output:["_col0","_col1","_col2"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_20] Group By Operator [GBY_18] (rows=348477374 width=88) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 3 [SIMPLE_EDGE] @@ -31,6 +31,7 @@ Stage-0 PartitionCols:_col0, _col1 Group By Operator [GBY_16] (rows=696954748 width=88) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col7, _col8 +<<<<<<< HEAD Merge Join Operator [MERGEJOIN_33] (rows=696954748 width=88) Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col2","_col7","_col8"] <-Map 7 [SIMPLE_EDGE] @@ -65,4 +66,42 @@ Stage-0 predicate:((d_moy = 12) and (d_year = 1998) and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=1119) default@date_dim,dt,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] +======= + Select Operator [SEL_15] (rows=696954748 width=88) + Output:["_col7","_col8","_col2"] + Merge Join Operator [MERGEJOIN_34] (rows=696954748 width=88) + Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col2","_col7","_col8"] + <-Map 7 [SIMPLE_EDGE] + SHUFFLE [RS_13] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=231000 width=1436) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_32] (rows=231000 width=1436) + predicate:((i_manager_id = 1) and i_item_sk is not null) + TableScan [TS_6] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_category_id","i_category","i_manager_id"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_33] (rows=633595212 width=88) + Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_9] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=575995635 width=88) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_30] (rows=575995635 width=88) + predicate:(ss_sold_date_sk is not null and ss_item_sk is not null) + TableScan [TS_0] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] + <-Map 6 [SIMPLE_EDGE] + SHUFFLE [RS_10] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_31] (rows=18262 width=1119) + predicate:((d_moy = 12) and (d_year = 1998) and d_date_sk is not null) + TableScan [TS_3] (rows=73049 width=1119) + default@date_dim,dt,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] +>>>>>>> clidriver golden file change diff --git a/ql/src/test/results/clientpositive/perf/query52.q.out b/ql/src/test/results/clientpositive/perf/query52.q.out index 74ecaf2..5fad58c 100644 --- a/ql/src/test/results/clientpositive/perf/query52.q.out +++ b/ql/src/test/results/clientpositive/perf/query52.q.out @@ -12,18 +12,18 @@ Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Stage-0 Fetch Operator - limit:100 + limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_24] - Limit [LIM_23] (rows=100 width=88) - Number of rows:100 - Select Operator [SEL_22] (rows=348477374 width=88) - Output:["_col0","_col1","_col2","_col3"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_21] - Select Operator [SEL_19] (rows=348477374 width=88) - Output:["_col1","_col2","_col3"] + File Output Operator [FS_25] + Select Operator [SEL_24] (rows=100 width=88) + Output:["_col0","_col1","_col2","_col3"] + Limit [LIM_23] (rows=100 width=88) + Number of rows:100 + Select Operator [SEL_22] (rows=348477374 width=88) + Output:["_col0","_col1","_col2"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_21] Group By Operator [GBY_18] (rows=348477374 width=88) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 3 [SIMPLE_EDGE] @@ -31,6 +31,7 @@ Stage-0 PartitionCols:_col0, _col1 Group By Operator [GBY_16] (rows=696954748 width=88) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col7, _col8 +<<<<<<< HEAD Merge Join Operator [MERGEJOIN_34] (rows=696954748 width=88) Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col2","_col7","_col8"] <-Map 7 [SIMPLE_EDGE] @@ -65,4 +66,42 @@ Stage-0 predicate:((d_moy = 12) and (d_year = 1998) and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=1119) default@date_dim,dt,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] +======= + Select Operator [SEL_15] (rows=696954748 width=88) + Output:["_col7","_col8","_col2"] + Merge Join Operator [MERGEJOIN_35] (rows=696954748 width=88) + Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col2","_col7","_col8"] + <-Map 7 [SIMPLE_EDGE] + SHUFFLE [RS_13] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=231000 width=1436) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_33] (rows=231000 width=1436) + predicate:((i_manager_id = 1) and i_item_sk is not null) + TableScan [TS_6] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_brand","i_manager_id"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_34] (rows=633595212 width=88) + Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_9] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=575995635 width=88) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_31] (rows=575995635 width=88) + predicate:(ss_sold_date_sk is not null and ss_item_sk is not null) + TableScan [TS_0] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] + <-Map 6 [SIMPLE_EDGE] + SHUFFLE [RS_10] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_32] (rows=18262 width=1119) + predicate:((d_moy = 12) and (d_year = 1998) and d_date_sk is not null) + TableScan [TS_3] (rows=73049 width=1119) + default@date_dim,dt,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] +>>>>>>> clidriver golden file change diff --git a/ql/src/test/results/clientpositive/perf/query58.q.out b/ql/src/test/results/clientpositive/perf/query58.q.out index d03a736..f4b2e19 100644 --- a/ql/src/test/results/clientpositive/perf/query58.q.out +++ b/ql/src/test/results/clientpositive/perf/query58.q.out @@ -92,9 +92,10 @@ ON ss_items.item_id=ws_items.item_id order by item_id ,ss_item_rev limit 100 POSTHOOK: type: QUERY -Plan optimized by CBO. +Plan not optimized by CBO. Vertex dependency in root stage +<<<<<<< HEAD Reducer 14 <- Map 13 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) Reducer 15 <- Map 21 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) Reducer 16 <- Map 22 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) @@ -112,11 +113,31 @@ Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 17 (SIMPLE_EDGE), Reducer 27 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 9 <- Map 10 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +======= +Reducer 10 <- Map 12 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) +Reducer 15 <- Reducer 14 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) +Reducer 16 <- Reducer 15 (SIMPLE_EDGE) +Reducer 19 <- Map 18 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 20 <- Map 22 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) +Reducer 24 <- Map 23 (SIMPLE_EDGE), Map 27 (SIMPLE_EDGE) +Reducer 25 <- Reducer 24 (SIMPLE_EDGE), Reducer 30 (SIMPLE_EDGE) +Reducer 26 <- Reducer 25 (SIMPLE_EDGE) +Reducer 29 <- Map 28 (SIMPLE_EDGE), Map 31 (SIMPLE_EDGE) +Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 30 <- Map 32 (SIMPLE_EDGE), Reducer 29 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 16 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 9 <- Map 11 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +>>>>>>> clidriver golden file change Stage-0 Fetch Operator limit:100 Stage-1 +<<<<<<< HEAD Reducer 7 File Output Operator [FS_113] Limit [LIM_112] (rows=100 width=88) @@ -347,4 +368,218 @@ Stage-0 predicate:(d_week_seq is not null and d_date is not null) TableScan [TS_3] (rows=73049 width=1119) default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"] +======= + Reducer 6 + File Output Operator [FS_108] + Limit [LIM_107] (rows=100 width=88) + Number of rows:100 + Select Operator [SEL_106] (rows=1586 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Reducer 5 [SIMPLE_EDGE] + SHUFFLE [RS_105] + Select Operator [SEL_104] (rows=1586 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_175] (rows=1586 width=88) + predicate:(_col3 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col3 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col1 BETWEEN (0.9 * _col3) AND (1.1 * _col3) and _col1 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col5 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col5 BETWEEN (0.9 * _col3) AND (1.1 * _col3)) + Merge Join Operator [MERGEJOIN_203] (rows=843315280 width=88) + Conds:RS_97._col0=RS_99._col0(Inner),RS_97._col0=RS_101._col0(Inner),Output:["_col0","_col1","_col3","_col5"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_99] + PartitionCols:_col0 + Group By Operator [GBY_62] (rows=191657247 width=135) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_61] + PartitionCols:_col0 + Group By Operator [GBY_60] (rows=383314495 width=135) + Output:["_col0","_col1"],aggregations:["sum(_col23)"],keys:_col38 + Select Operator [SEL_59] (rows=383314495 width=135) + Output:["_col38","_col23"] + Merge Join Operator [MERGEJOIN_201] (rows=383314495 width=135) + Conds:RS_55._col64=RS_57._col0(Inner),Output:["_col23","_col38"] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_57] + PartitionCols:_col0 + Select Operator [SEL_40] (rows=80353 width=1119) + Output:["_col0"] + Merge Join Operator [MERGEJOIN_194] (rows=80353 width=1119) + Conds:RS_35.d_week_seq=RS_37.d_week_seq(Inner),Output:["_col2"] + <-Map 13 [SIMPLE_EDGE] + SHUFFLE [RS_35] + PartitionCols:d_week_seq + Filter Operator [FIL_181] (rows=73049 width=1119) + predicate:(d_week_seq is not null and d_date is not null) + TableScan [TS_32] (rows=73049 width=1119) + default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"] + <-Map 17 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:d_week_seq + Filter Operator [FIL_182] (rows=36524 width=1119) + predicate:(d_week_seq is not null and (d_date = '1998-08-04')) + TableScan [TS_33] (rows=73049 width=1119) + default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_55] + PartitionCols:_col64 + Merge Join Operator [MERGEJOIN_196] (rows=348467716 width=135) + Conds:RS_50._col0=RS_52.d_date_sk(Inner),Output:["_col23","_col38","_col64"] + <-Map 22 [SIMPLE_EDGE] + SHUFFLE [RS_52] + PartitionCols:d_date_sk + Filter Operator [FIL_185] (rows=73049 width=1119) + predicate:(d_date_sk is not null and d_date is not null) + TableScan [TS_43] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + <-Reducer 19 [SIMPLE_EDGE] + SHUFFLE [RS_50] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_195] (rows=316788826 width=135) + Conds:RS_45.cs_item_sk=RS_47.i_item_sk(Inner),Output:["_col0","_col23","_col38"] + <-Map 18 [SIMPLE_EDGE] + SHUFFLE [RS_45] + PartitionCols:cs_item_sk + Filter Operator [FIL_183] (rows=287989836 width=135) + predicate:(cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_41] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_sales_price"] + <-Map 21 [SIMPLE_EDGE] + SHUFFLE [RS_47] + PartitionCols:i_item_sk + Filter Operator [FIL_184] (rows=462000 width=1436) + predicate:(i_item_sk is not null and i_item_id is not null) + TableScan [TS_42] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] + <-Reducer 26 [SIMPLE_EDGE] + SHUFFLE [RS_101] + PartitionCols:_col0 + Group By Operator [GBY_94] (rows=95833781 width=135) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 25 [SIMPLE_EDGE] + SHUFFLE [RS_93] + PartitionCols:_col0 + Group By Operator [GBY_92] (rows=191667562 width=135) + Output:["_col0","_col1"],aggregations:["sum(_col23)"],keys:_col38 + Select Operator [SEL_91] (rows=191667562 width=135) + Output:["_col38","_col23"] + Merge Join Operator [MERGEJOIN_202] (rows=191667562 width=135) + Conds:RS_87._col64=RS_89._col0(Inner),Output:["_col23","_col38"] + <-Reducer 24 [SIMPLE_EDGE] + SHUFFLE [RS_89] + PartitionCols:_col0 + Select Operator [SEL_72] (rows=80353 width=1119) + Output:["_col0"] + Merge Join Operator [MERGEJOIN_197] (rows=80353 width=1119) + Conds:RS_67.d_week_seq=RS_69.d_week_seq(Inner),Output:["_col2"] + <-Map 23 [SIMPLE_EDGE] + SHUFFLE [RS_67] + PartitionCols:d_week_seq + Filter Operator [FIL_186] (rows=73049 width=1119) + predicate:(d_week_seq is not null and d_date is not null) + TableScan [TS_64] (rows=73049 width=1119) + default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"] + <-Map 27 [SIMPLE_EDGE] + SHUFFLE [RS_69] + PartitionCols:d_week_seq + Filter Operator [FIL_187] (rows=36524 width=1119) + predicate:(d_week_seq is not null and (d_date = '1998-08-04')) + TableScan [TS_65] (rows=73049 width=1119) + default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"] + <-Reducer 30 [SIMPLE_EDGE] + SHUFFLE [RS_87] + PartitionCols:_col64 + Merge Join Operator [MERGEJOIN_199] (rows=174243235 width=135) + Conds:RS_82._col0=RS_84.d_date_sk(Inner),Output:["_col23","_col38","_col64"] + <-Map 32 [SIMPLE_EDGE] + SHUFFLE [RS_84] + PartitionCols:d_date_sk + Filter Operator [FIL_190] (rows=73049 width=1119) + predicate:(d_date_sk is not null and d_date is not null) + TableScan [TS_75] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + <-Reducer 29 [SIMPLE_EDGE] + SHUFFLE [RS_82] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_198] (rows=158402938 width=135) + Conds:RS_77.ws_item_sk=RS_79.i_item_sk(Inner),Output:["_col0","_col23","_col38"] + <-Map 28 [SIMPLE_EDGE] + SHUFFLE [RS_77] + PartitionCols:ws_item_sk + Filter Operator [FIL_188] (rows=144002668 width=135) + predicate:(ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_73] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_sales_price"] + <-Map 31 [SIMPLE_EDGE] + SHUFFLE [RS_79] + PartitionCols:i_item_sk + Filter Operator [FIL_189] (rows=462000 width=1436) + predicate:(i_item_sk is not null and i_item_id is not null) + TableScan [TS_74] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_97] + PartitionCols:_col0 + Group By Operator [GBY_30] (rows=383325119 width=88) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_29] + PartitionCols:_col0 + Group By Operator [GBY_28] (rows=766650239 width=88) + Output:["_col0","_col1"],aggregations:["sum(_col15)"],keys:_col27 + Select Operator [SEL_27] (rows=766650239 width=88) + Output:["_col27","_col15"] + Merge Join Operator [MERGEJOIN_200] (rows=766650239 width=88) + Conds:RS_23._col53=RS_25._col0(Inner),Output:["_col15","_col27"] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_23] + PartitionCols:_col53 + Merge Join Operator [MERGEJOIN_193] (rows=696954748 width=88) + Conds:RS_18._col0=RS_20.d_date_sk(Inner),Output:["_col15","_col27","_col53"] + <-Map 12 [SIMPLE_EDGE] + SHUFFLE [RS_20] + PartitionCols:d_date_sk + Filter Operator [FIL_180] (rows=73049 width=1119) + predicate:(d_date_sk is not null and d_date is not null) + TableScan [TS_11] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_192] (rows=633595212 width=88) + Conds:RS_13.ss_item_sk=RS_15.i_item_sk(Inner),Output:["_col0","_col15","_col27"] + <-Map 11 [SIMPLE_EDGE] + SHUFFLE [RS_15] + PartitionCols:i_item_sk + Filter Operator [FIL_179] (rows=462000 width=1436) + predicate:(i_item_sk is not null and i_item_id is not null) + TableScan [TS_10] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] + <-Map 8 [SIMPLE_EDGE] + SHUFFLE [RS_13] + PartitionCols:ss_item_sk + Filter Operator [FIL_178] (rows=575995635 width=88) + predicate:(ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_9] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_25] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=80353 width=1119) + Output:["_col0"] + Merge Join Operator [MERGEJOIN_191] (rows=80353 width=1119) + Conds:RS_3.d_week_seq=RS_5.d_week_seq(Inner),Output:["_col2"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_3] + PartitionCols:d_week_seq + Filter Operator [FIL_176] (rows=73049 width=1119) + predicate:(d_week_seq is not null and d_date is not null) + TableScan [TS_0] (rows=73049 width=1119) + default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"] + <-Map 7 [SIMPLE_EDGE] + SHUFFLE [RS_5] + PartitionCols:d_week_seq + Filter Operator [FIL_177] (rows=36524 width=1119) + predicate:(d_week_seq is not null and (d_date = '1998-08-04')) + TableScan [TS_1] (rows=73049 width=1119) + default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"] +>>>>>>> clidriver golden file change diff --git a/ql/src/test/results/clientpositive/perf/query64.q.out b/ql/src/test/results/clientpositive/perf/query64.q.out index 6b42393..6c43b84 100644 --- a/ql/src/test/results/clientpositive/perf/query64.q.out +++ b/ql/src/test/results/clientpositive/perf/query64.q.out @@ -52,6 +52,7 @@ Stage-0 Fetch Operator limit:-1 Stage-1 +<<<<<<< HEAD Reducer 11 File Output Operator [FS_263] Select Operator [SEL_262] (rows=273897192 width=88) @@ -66,6 +67,22 @@ Stage-0 Conds:RS_256._col2, _col1, _col3=RS_257._col2, _col1, _col3(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col13","_col14","_col15","_col16","_col30","_col31","_col32","_col33"] <-Reducer 50 [SIMPLE_EDGE] SHUFFLE [RS_257] +======= + Reducer 6 + File Output Operator [FS_268] + Select Operator [SEL_266] (rows=331415616 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20"] + <-Reducer 5 [SIMPLE_EDGE] + SHUFFLE [RS_265] + Select Operator [SEL_264] (rows=331415616 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"] + Filter Operator [FIL_263] (rows=331415616 width=88) + predicate:(_col30 <= _col13) + Merge Join Operator [MERGEJOIN_659] (rows=994246850 width=88) + Conds:RS_260._col2, _col1, _col3=RS_261._col2, _col1, _col3(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col13","_col14","_col15","_col16","_col30","_col31","_col32","_col33"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_260] +>>>>>>> clidriver golden file change PartitionCols:_col2, _col1, _col3 Select Operator [SEL_254] (rows=746992327 width=88) Output:["_col1","_col2","_col3","_col13","_col14","_col15","_col16"] @@ -74,6 +91,7 @@ Stage-0 <-Reducer 49 [SIMPLE_EDGE] SHUFFLE [RS_252] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 +<<<<<<< HEAD Group By Operator [GBY_251] (rows=1493984654 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col45)","sum(_col46)","sum(_col47)"],keys:_col26, _col48, _col27, _col7, _col9, _col14, _col15, _col16, _col17, _col21, _col22, _col23, _col24, _col51 Select Operator [SEL_250] (rows=1493984654 width=88) @@ -173,16 +191,244 @@ Stage-0 Conds:RS_143._col1=RS_144._col0(Inner),Output:["_col0"] <-Map 53 [SIMPLE_EDGE] SHUFFLE [RS_143] +======= + Group By Operator [GBY_125] (rows=1807721509 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col26)","sum(_col27)","sum(_col28)"],keys:_col44, _col50, _col45, _col4, _col5, _col6, _col7, _col9, _col10, _col11, _col12, _col40, _col42, _col53 + Select Operator [SEL_124] (rows=1807721509 width=88) + Output:["_col44","_col50","_col45","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col40","_col42","_col53","_col26","_col27","_col28"] + Merge Join Operator [MERGEJOIN_657] (rows=1807721509 width=88) + Conds:RS_121._col0=RS_122._col18(Inner),Output:["_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col26","_col27","_col28","_col40","_col42","_col44","_col45","_col50","_col53"] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_122] + PartitionCols:_col18 + Select Operator [SEL_117] (rows=1643383155 width=88) + Output:["_col1","_col18","_col2","_col23","_col24","_col25","_col3","_col37","_col39","_col4","_col41","_col42","_col47","_col50","_col6","_col7","_col8","_col9"] + Merge Join Operator [MERGEJOIN_639] (rows=1643383155 width=88) + Conds:RS_114._col21=RS_115._col0(Inner),Output:["_col8","_col13","_col14","_col15","_col27","_col29","_col31","_col32","_col37","_col40","_col45","_col46","_col47","_col48","_col50","_col51","_col52","_col53"] + <-Map 41 [SIMPLE_EDGE] + SHUFFLE [RS_115] + PartitionCols:_col0 + Select Operator [SEL_101] (rows=40000000 width=1014) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_603] (rows=40000000 width=1014) + predicate:ca_address_sk is not null + TableScan [TS_99] (rows=40000000 width=1014) + default@customer_address,ad2,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_city","ca_zip"] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_114] + PartitionCols:_col21 + Merge Join Operator [MERGEJOIN_638] (rows=1493984654 width=88) + Conds:RS_111._col9=RS_112._col0(Inner),Output:["_col8","_col13","_col14","_col15","_col21","_col27","_col29","_col31","_col32","_col37","_col40","_col45","_col46","_col47","_col48"] + <-Map 40 [SIMPLE_EDGE] + SHUFFLE [RS_112] + PartitionCols:_col0 + Select Operator [SEL_98] (rows=40000000 width=1014) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_602] (rows=40000000 width=1014) + predicate:ca_address_sk is not null + TableScan [TS_96] (rows=40000000 width=1014) + default@customer_address,ad1,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_city","ca_zip"] + <-Reducer 11 [SIMPLE_EDGE] + SHUFFLE [RS_111] + PartitionCols:_col9 + Merge Join Operator [MERGEJOIN_637] (rows=1358167838 width=88) + Conds:RS_108._col5=RS_109._col0(Inner),Output:["_col8","_col9","_col13","_col14","_col15","_col21","_col27","_col29","_col31","_col32","_col37","_col40"] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_108] + PartitionCols:_col5 + Merge Join Operator [MERGEJOIN_636] (rows=1234698008 width=88) + Conds:RS_105._col0=RS_106._col17(Inner),Output:["_col5","_col8","_col9","_col13","_col14","_col15","_col21","_col27","_col29","_col31","_col32","_col37","_col40"] + <-Reducer 21 [SIMPLE_EDGE] + SHUFFLE [RS_106] + PartitionCols:_col17 + Select Operator [SEL_79] (rows=1122452711 width=88) + Output:["_col10","_col11","_col12","_col17","_col18","_col2","_col24","_col26","_col28","_col29","_col34","_col37","_col5","_col6"] + Merge Join Operator [MERGEJOIN_634] (rows=1122452711 width=88) + Conds:RS_76._col7=RS_77._col0(Inner),Output:["_col1","_col4","_col5","_col9","_col10","_col11","_col16","_col17","_col23","_col25","_col27","_col28","_col33","_col36"] + <-Map 35 [SIMPLE_EDGE] + SHUFFLE [RS_77] + PartitionCols:_col0 + Select Operator [SEL_72] (rows=2300 width=1179) + Output:["_col0"] + Filter Operator [FIL_599] (rows=2300 width=1179) + predicate:p_promo_sk is not null + TableScan [TS_70] (rows=2300 width=1179) + default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk"] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_76] + PartitionCols:_col7 + Merge Join Operator [MERGEJOIN_633] (rows=1020411534 width=88) + Conds:RS_73._col1=RS_74._col0(Inner),Output:["_col1","_col4","_col5","_col7","_col9","_col10","_col11","_col16","_col17","_col23","_col25","_col27","_col28","_col33","_col36"] + <-Map 34 [SIMPLE_EDGE] + SHUFFLE [RS_74] + PartitionCols:_col0 + Select Operator [SEL_69] (rows=2851 width=1436) + Output:["_col0","_col3"] + Filter Operator [FIL_598] (rows=2851 width=1436) + predicate:((i_color) IN ('maroon', 'burnished', 'dim', 'steel', 'navajo', 'chocolate') and i_current_price BETWEEN 35 AND 45 and i_current_price BETWEEN 36 AND 50 and i_item_sk is not null) + TableScan [TS_67] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_color","i_product_name"] + <-Reducer 19 [SIMPLE_EDGE] + SHUFFLE [RS_73] + PartitionCols:_col1 + Select Operator [SEL_66] (rows=927646829 width=88) + Output:["_col1","_col10","_col11","_col16","_col17","_col23","_col25","_col27","_col28","_col4","_col5","_col7","_col9"] + Filter Operator [FIL_65] (rows=927646829 width=88) + predicate:(_col30 <> _col32) + Select Operator [SEL_64] (rows=927646829 width=88) + Output:["_col1","_col4","_col5","_col7","_col9","_col10","_col11","_col16","_col17","_col23","_col25","_col27","_col28","_col30","_col32"] + Merge Join Operator [MERGEJOIN_632] (rows=927646829 width=88) + Conds:RS_61._col0=RS_62._col4(Inner),Output:["_col2","_col3","_col7","_col9","_col11","_col13","_col15","_col18","_col19","_col21","_col23","_col24","_col25","_col31","_col32"] + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_61] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_627] (rows=106480005 width=860) + Conds:RS_58._col1=RS_59._col0(Inner),Output:["_col0","_col2","_col3","_col7","_col9","_col11"] + <-Map 24 [SIMPLE_EDGE] + SHUFFLE [RS_59] + PartitionCols:_col0 + Select Operator [SEL_23] (rows=1861800 width=385) + Output:["_col0","_col1"] + Filter Operator [FIL_592] (rows=1861800 width=385) + predicate:cd_demo_sk is not null + TableScan [TS_21] (rows=1861800 width=385) + default@customer_demographics,cd2,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"] + <-Reducer 17 [SIMPLE_EDGE] + SHUFFLE [RS_58] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_626] (rows=96800003 width=860) + Conds:RS_55._col4=RS_56._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col7","_col9"] + <-Map 23 [SIMPLE_EDGE] + SHUFFLE [RS_56] + PartitionCols:_col0 + Select Operator [SEL_20] (rows=73049 width=1119) + Output:["_col0","_col1"] + Filter Operator [FIL_591] (rows=73049 width=1119) + predicate:d_date_sk is not null + TableScan [TS_18] (rows=73049 width=1119) + default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_55] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_625] (rows=88000001 width=860) + Conds:RS_52._col5=RS_53._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col7"] + <-Map 15 [SIMPLE_EDGE] + SHUFFLE [RS_52] + PartitionCols:_col5 + Select Operator [SEL_14] (rows=80000000 width=860) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_589] (rows=80000000 width=860) + predicate:(c_customer_sk is not null and c_first_sales_date_sk is not null and c_first_shipto_date_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null and c_current_addr_sk is not null) + TableScan [TS_12] (rows=80000000 width=860) + default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk","c_first_shipto_date_sk","c_first_sales_date_sk"] + <-Map 22 [SIMPLE_EDGE] + SHUFFLE [RS_53] + PartitionCols:_col0 + Select Operator [SEL_17] (rows=73049 width=1119) + Output:["_col0","_col1"] + Filter Operator [FIL_590] (rows=73049 width=1119) + predicate:d_date_sk is not null + TableScan [TS_15] (rows=73049 width=1119) + default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Reducer 29 [SIMPLE_EDGE] + SHUFFLE [RS_62] + PartitionCols:_col4 + Select Operator [SEL_51] (rows=843315281 width=88) + Output:["_col1","_col11","_col12","_col13","_col19","_col20","_col3","_col4","_col6","_col7","_col9"] + Merge Join Operator [MERGEJOIN_631] (rows=843315281 width=88) + Conds:RS_48._col3=RS_49._col0(Inner),Output:["_col1","_col2","_col4","_col5","_col7","_col9","_col10","_col11","_col17","_col18","_col20"] + <-Map 33 [SIMPLE_EDGE] + SHUFFLE [RS_49] + PartitionCols:_col0 + Select Operator [SEL_38] (rows=1861800 width=385) + Output:["_col0","_col1"] + Filter Operator [FIL_597] (rows=1861800 width=385) + predicate:cd_demo_sk is not null + TableScan [TS_36] (rows=1861800 width=385) + default@customer_demographics,cd1,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"] + <-Reducer 28 [SIMPLE_EDGE] + SHUFFLE [RS_48] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_630] (rows=766650239 width=88) + Conds:RS_45._col6=RS_46._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col7","_col9","_col10","_col11","_col17","_col18"] + <-Map 32 [SIMPLE_EDGE] + SHUFFLE [RS_46] + PartitionCols:_col0 + Select Operator [SEL_35] (rows=1704 width=1910) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_596] (rows=1704 width=1910) + predicate:(s_store_sk is not null and s_store_name is not null and s_zip is not null) + TableScan [TS_33] (rows=1704 width=1910) + default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_zip"] + <-Reducer 27 [SIMPLE_EDGE] + SHUFFLE [RS_45] + PartitionCols:_col6 + Merge Join Operator [MERGEJOIN_629] (rows=696954748 width=88) + Conds:RS_42._col0=RS_43._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11"] + <-Map 31 [SIMPLE_EDGE] + SHUFFLE [RS_43] + PartitionCols:_col0 + Select Operator [SEL_32] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_595] (rows=36524 width=1119) + predicate:((d_year = 2000) and d_date_sk is not null) + TableScan [TS_30] (rows=73049 width=1119) + default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Reducer 26 [SIMPLE_EDGE] + SHUFFLE [RS_42] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_628] (rows=633595212 width=88) + Conds:RS_39._col1, _col8=RS_40._col0, _col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11"] + <-Map 25 [SIMPLE_EDGE] + SHUFFLE [RS_39] + PartitionCols:_col1, _col8 + Select Operator [SEL_26] (rows=575995635 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + Filter Operator [FIL_593] (rows=575995635 width=88) + predicate:(ss_item_sk is not null and ss_ticket_number is not null and ss_customer_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_cdemo_sk is not null and ss_promo_sk is not null and ss_hdemo_sk is not null and ss_addr_sk is not null) + TableScan [TS_24] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_promo_sk","ss_ticket_number","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] + <-Map 30 [SIMPLE_EDGE] + SHUFFLE [RS_40] + PartitionCols:_col0, _col1 + Select Operator [SEL_29] (rows=57591150 width=77) + Output:["_col0","_col1"] + Filter Operator [FIL_594] (rows=57591150 width=77) + predicate:(sr_item_sk is not null and sr_ticket_number is not null) + TableScan [TS_27] (rows=57591150 width=77) + default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number"] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_105] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_624] (rows=7920 width=107) + Conds:RS_102._col1=RS_103._col0(Inner),Output:["_col0"] + <-Map 14 [SIMPLE_EDGE] + SHUFFLE [RS_103] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=20 width=12) + Output:["_col0"] + Filter Operator [FIL_588] (rows=20 width=12) + predicate:ib_income_band_sk is not null + TableScan [TS_9] (rows=20 width=12) + default@income_band,ib2,Tbl:COMPLETE,Col:NONE,Output:["ib_income_band_sk"] + <-Map 8 [SIMPLE_EDGE] + SHUFFLE [RS_102] +>>>>>>> clidriver golden file change PartitionCols:_col1 Select Operator [SEL_139] (rows=7200 width=107) Output:["_col0","_col1"] +<<<<<<< HEAD Filter Operator [FIL_558] (rows=7200 width=107) +======= + Filter Operator [FIL_587] (rows=7200 width=107) +>>>>>>> clidriver golden file change predicate:(hd_demo_sk is not null and hd_income_band_sk is not null) TableScan [TS_137] (rows=7200 width=107) default@household_demographics,hd2,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_income_band_sk"] <-Map 55 [SIMPLE_EDGE] SHUFFLE [RS_144] PartitionCols:_col0 +<<<<<<< HEAD Select Operator [SEL_142] (rows=20 width=12) Output:["_col0"] Filter Operator [FIL_559] (rows=20 width=12) @@ -357,6 +603,57 @@ Stage-0 default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_refunded_cash","cr_reversed_charge","cr_store_credit"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_256] +======= + Group By Operator [GBY_91] (rows=316788826 width=135) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","sum(_col2)"],keys:_col0 + Select Operator [SEL_89] (rows=316788826 width=135) + Output:["_col0","_col1","_col2"] + Merge Join Operator [MERGEJOIN_635] (rows=316788826 width=135) + Conds:RS_86._col0, _col1=RS_87._col0, _col1(Inner),Output:["_col0","_col2","_col5","_col6","_col7"] + <-Map 36 [SIMPLE_EDGE] + SHUFFLE [RS_86] + PartitionCols:_col0, _col1 + Select Operator [SEL_82] (rows=287989836 width=135) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_600] (rows=287989836 width=135) + predicate:(cs_order_number is not null and cs_item_sk is not null) + TableScan [TS_80] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_item_sk","cs_order_number","cs_ext_list_price"] + <-Map 39 [SIMPLE_EDGE] + SHUFFLE [RS_87] + PartitionCols:_col0, _col1 + Select Operator [SEL_85] (rows=28798881 width=106) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_601] (rows=28798881 width=106) + predicate:(cr_order_number is not null and cr_item_sk is not null) + TableScan [TS_83] (rows=28798881 width=106) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_refunded_cash","cr_reversed_charge","cr_store_credit"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_121] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_623] (rows=7920 width=107) + Conds:RS_118._col1=RS_119._col0(Inner),Output:["_col0"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_118] + PartitionCols:_col1 + Select Operator [SEL_2] (rows=7200 width=107) + Output:["_col0","_col1"] + Filter Operator [FIL_585] (rows=7200 width=107) + predicate:(hd_demo_sk is not null and hd_income_band_sk is not null) + TableScan [TS_0] (rows=7200 width=107) + default@household_demographics,hd1,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_income_band_sk"] + <-Map 7 [SIMPLE_EDGE] + SHUFFLE [RS_119] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=20 width=12) + Output:["_col0"] + Filter Operator [FIL_586] (rows=20 width=12) + predicate:ib_income_band_sk is not null + TableScan [TS_3] (rows=20 width=12) + default@income_band,ib1,Tbl:COMPLETE,Col:NONE,Output:["ib_income_band_sk"] + <-Reducer 45 [SIMPLE_EDGE] + SHUFFLE [RS_261] +>>>>>>> clidriver golden file change PartitionCols:_col2, _col1, _col3 Select Operator [SEL_126] (rows=746992327 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col13","_col14","_col15","_col16"] @@ -365,6 +662,7 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_124] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 +<<<<<<< HEAD Group By Operator [GBY_123] (rows=1493984654 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col45)","sum(_col46)","sum(_col47)"],keys:_col26, _col48, _col27, _col7, _col9, _col14, _col15, _col16, _col17, _col21, _col22, _col23, _col24, _col51 Select Operator [SEL_122] (rows=1493984654 width=88) @@ -593,10 +891,92 @@ Stage-0 Conds:RS_15._col1=RS_16._col0(Inner),Output:["_col0"] <-Map 14 [SIMPLE_EDGE] SHUFFLE [RS_15] +======= + Group By Operator [GBY_255] (rows=1807721509 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col26)","sum(_col27)","sum(_col28)"],keys:_col44, _col50, _col45, _col4, _col5, _col6, _col7, _col9, _col10, _col11, _col12, _col40, _col42, _col53 + Select Operator [SEL_254] (rows=1807721509 width=88) + Output:["_col44","_col50","_col45","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col40","_col42","_col53","_col26","_col27","_col28"] + Merge Join Operator [MERGEJOIN_658] (rows=1807721509 width=88) + Conds:RS_251._col0=RS_252._col18(Inner),Output:["_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col26","_col27","_col28","_col40","_col42","_col44","_col45","_col50","_col53"] + <-Reducer 43 [SIMPLE_EDGE] + SHUFFLE [RS_251] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_640] (rows=7920 width=107) + Conds:RS_248._col1=RS_249._col0(Inner),Output:["_col0"] + <-Map 42 [SIMPLE_EDGE] + SHUFFLE [RS_248] + PartitionCols:_col1 + Select Operator [SEL_132] (rows=7200 width=107) + Output:["_col0","_col1"] + Filter Operator [FIL_604] (rows=7200 width=107) + predicate:(hd_demo_sk is not null and hd_income_band_sk is not null) + TableScan [TS_130] (rows=7200 width=107) + default@household_demographics,hd1,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_income_band_sk"] + <-Map 46 [SIMPLE_EDGE] + SHUFFLE [RS_249] + PartitionCols:_col0 + Select Operator [SEL_135] (rows=20 width=12) + Output:["_col0"] + Filter Operator [FIL_605] (rows=20 width=12) + predicate:ib_income_band_sk is not null + TableScan [TS_133] (rows=20 width=12) + default@income_band,ib1,Tbl:COMPLETE,Col:NONE,Output:["ib_income_band_sk"] + <-Reducer 52 [SIMPLE_EDGE] + SHUFFLE [RS_252] + PartitionCols:_col18 + Select Operator [SEL_247] (rows=1643383155 width=88) + Output:["_col1","_col18","_col2","_col23","_col24","_col25","_col3","_col37","_col39","_col4","_col41","_col42","_col47","_col50","_col6","_col7","_col8","_col9"] + Merge Join Operator [MERGEJOIN_656] (rows=1643383155 width=88) + Conds:RS_244._col21=RS_245._col0(Inner),Output:["_col8","_col13","_col14","_col15","_col27","_col29","_col31","_col32","_col37","_col40","_col45","_col46","_col47","_col48","_col50","_col51","_col52","_col53"] + <-Map 80 [SIMPLE_EDGE] + SHUFFLE [RS_245] + PartitionCols:_col0 + Select Operator [SEL_231] (rows=40000000 width=1014) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_622] (rows=40000000 width=1014) + predicate:ca_address_sk is not null + TableScan [TS_229] (rows=40000000 width=1014) + default@customer_address,ad2,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_city","ca_zip"] + <-Reducer 51 [SIMPLE_EDGE] + SHUFFLE [RS_244] + PartitionCols:_col21 + Merge Join Operator [MERGEJOIN_655] (rows=1493984654 width=88) + Conds:RS_241._col9=RS_242._col0(Inner),Output:["_col8","_col13","_col14","_col15","_col21","_col27","_col29","_col31","_col32","_col37","_col40","_col45","_col46","_col47","_col48"] + <-Map 79 [SIMPLE_EDGE] + SHUFFLE [RS_242] + PartitionCols:_col0 + Select Operator [SEL_228] (rows=40000000 width=1014) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_621] (rows=40000000 width=1014) + predicate:ca_address_sk is not null + TableScan [TS_226] (rows=40000000 width=1014) + default@customer_address,ad1,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_city","ca_zip"] + <-Reducer 50 [SIMPLE_EDGE] + SHUFFLE [RS_241] + PartitionCols:_col9 + Merge Join Operator [MERGEJOIN_654] (rows=1358167838 width=88) + Conds:RS_238._col5=RS_239._col0(Inner),Output:["_col8","_col9","_col13","_col14","_col15","_col21","_col27","_col29","_col31","_col32","_col37","_col40"] + <-Reducer 49 [SIMPLE_EDGE] + SHUFFLE [RS_238] + PartitionCols:_col5 + Merge Join Operator [MERGEJOIN_653] (rows=1234698008 width=88) + Conds:RS_235._col0=RS_236._col17(Inner),Output:["_col5","_col8","_col9","_col13","_col14","_col15","_col21","_col27","_col29","_col31","_col32","_col37","_col40"] + <-Reducer 48 [SIMPLE_EDGE] + SHUFFLE [RS_235] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_641] (rows=7920 width=107) + Conds:RS_232._col1=RS_233._col0(Inner),Output:["_col0"] + <-Map 47 [SIMPLE_EDGE] + SHUFFLE [RS_232] +>>>>>>> clidriver golden file change PartitionCols:_col1 Select Operator [SEL_11] (rows=7200 width=107) Output:["_col0","_col1"] +<<<<<<< HEAD Filter Operator [FIL_539] (rows=7200 width=107) +======= + Filter Operator [FIL_606] (rows=7200 width=107) +>>>>>>> clidriver golden file change predicate:(hd_demo_sk is not null and hd_income_band_sk is not null) TableScan [TS_9] (rows=7200 width=107) default@household_demographics,hd2,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_income_band_sk"] @@ -605,10 +985,15 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_14] (rows=20 width=12) Output:["_col0"] +<<<<<<< HEAD Filter Operator [FIL_540] (rows=20 width=12) +======= + Filter Operator [FIL_607] (rows=20 width=12) +>>>>>>> clidriver golden file change predicate:ib_income_band_sk is not null TableScan [TS_12] (rows=20 width=12) default@income_band,ib2,Tbl:COMPLETE,Col:NONE,Output:["ib_income_band_sk"] +<<<<<<< HEAD <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_106] PartitionCols:_col2 @@ -646,4 +1031,201 @@ Stage-0 predicate:d_date_sk is not null TableScan [TS_3] (rows=73049 width=1119) default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] +======= + <-Reducer 60 [SIMPLE_EDGE] + SHUFFLE [RS_236] + PartitionCols:_col17 + Select Operator [SEL_209] (rows=1122452711 width=88) + Output:["_col10","_col11","_col12","_col17","_col18","_col2","_col24","_col26","_col28","_col29","_col34","_col37","_col5","_col6"] + Merge Join Operator [MERGEJOIN_651] (rows=1122452711 width=88) + Conds:RS_206._col7=RS_207._col0(Inner),Output:["_col1","_col4","_col5","_col9","_col10","_col11","_col16","_col17","_col23","_col25","_col27","_col28","_col33","_col36"] + <-Map 74 [SIMPLE_EDGE] + SHUFFLE [RS_207] + PartitionCols:_col0 + Select Operator [SEL_202] (rows=2300 width=1179) + Output:["_col0"] + Filter Operator [FIL_618] (rows=2300 width=1179) + predicate:p_promo_sk is not null + TableScan [TS_200] (rows=2300 width=1179) + default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk"] + <-Reducer 59 [SIMPLE_EDGE] + SHUFFLE [RS_206] + PartitionCols:_col7 + Merge Join Operator [MERGEJOIN_650] (rows=1020411534 width=88) + Conds:RS_203._col1=RS_204._col0(Inner),Output:["_col1","_col4","_col5","_col7","_col9","_col10","_col11","_col16","_col17","_col23","_col25","_col27","_col28","_col33","_col36"] + <-Map 73 [SIMPLE_EDGE] + SHUFFLE [RS_204] + PartitionCols:_col0 + Select Operator [SEL_199] (rows=2851 width=1436) + Output:["_col0","_col3"] + Filter Operator [FIL_617] (rows=2851 width=1436) + predicate:((i_color) IN ('maroon', 'burnished', 'dim', 'steel', 'navajo', 'chocolate') and i_current_price BETWEEN 35 AND 45 and i_current_price BETWEEN 36 AND 50 and i_item_sk is not null) + TableScan [TS_197] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_color","i_product_name"] + <-Reducer 58 [SIMPLE_EDGE] + SHUFFLE [RS_203] + PartitionCols:_col1 + Select Operator [SEL_196] (rows=927646829 width=88) + Output:["_col1","_col10","_col11","_col16","_col17","_col23","_col25","_col27","_col28","_col4","_col5","_col7","_col9"] + Filter Operator [FIL_195] (rows=927646829 width=88) + predicate:(_col30 <> _col32) + Select Operator [SEL_194] (rows=927646829 width=88) + Output:["_col1","_col4","_col5","_col7","_col9","_col10","_col11","_col16","_col17","_col23","_col25","_col27","_col28","_col30","_col32"] + Merge Join Operator [MERGEJOIN_649] (rows=927646829 width=88) + Conds:RS_191._col0=RS_192._col4(Inner),Output:["_col2","_col3","_col7","_col9","_col11","_col13","_col15","_col18","_col19","_col21","_col23","_col24","_col25","_col31","_col32"] + <-Reducer 57 [SIMPLE_EDGE] + SHUFFLE [RS_191] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_644] (rows=106480005 width=860) + Conds:RS_188._col1=RS_189._col0(Inner),Output:["_col0","_col2","_col3","_col7","_col9","_col11"] + <-Map 63 [SIMPLE_EDGE] + SHUFFLE [RS_189] + PartitionCols:_col0 + Select Operator [SEL_153] (rows=1861800 width=385) + Output:["_col0","_col1"] + Filter Operator [FIL_611] (rows=1861800 width=385) + predicate:cd_demo_sk is not null + TableScan [TS_151] (rows=1861800 width=385) + default@customer_demographics,cd2,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"] + <-Reducer 56 [SIMPLE_EDGE] + SHUFFLE [RS_188] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_643] (rows=96800003 width=860) + Conds:RS_185._col4=RS_186._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col7","_col9"] + <-Map 62 [SIMPLE_EDGE] + SHUFFLE [RS_186] + PartitionCols:_col0 + Select Operator [SEL_150] (rows=73049 width=1119) + Output:["_col0","_col1"] + Filter Operator [FIL_610] (rows=73049 width=1119) + predicate:d_date_sk is not null + TableScan [TS_148] (rows=73049 width=1119) + default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Reducer 55 [SIMPLE_EDGE] + SHUFFLE [RS_185] + PartitionCols:_col4 + Merge Join Operator [MERGEJOIN_642] (rows=88000001 width=860) + Conds:RS_182._col5=RS_183._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col7"] + <-Map 54 [SIMPLE_EDGE] + SHUFFLE [RS_182] + PartitionCols:_col5 + Select Operator [SEL_144] (rows=80000000 width=860) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_608] (rows=80000000 width=860) + predicate:(c_customer_sk is not null and c_first_sales_date_sk is not null and c_first_shipto_date_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null and c_current_addr_sk is not null) + TableScan [TS_142] (rows=80000000 width=860) + default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk","c_first_shipto_date_sk","c_first_sales_date_sk"] + <-Map 61 [SIMPLE_EDGE] + SHUFFLE [RS_183] + PartitionCols:_col0 + Select Operator [SEL_147] (rows=73049 width=1119) + Output:["_col0","_col1"] + Filter Operator [FIL_609] (rows=73049 width=1119) + predicate:d_date_sk is not null + TableScan [TS_145] (rows=73049 width=1119) + default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Reducer 68 [SIMPLE_EDGE] + SHUFFLE [RS_192] + PartitionCols:_col4 + Select Operator [SEL_181] (rows=843315281 width=88) + Output:["_col1","_col11","_col12","_col13","_col19","_col20","_col3","_col4","_col6","_col7","_col9"] + Merge Join Operator [MERGEJOIN_648] (rows=843315281 width=88) + Conds:RS_178._col3=RS_179._col0(Inner),Output:["_col1","_col2","_col4","_col5","_col7","_col9","_col10","_col11","_col17","_col18","_col20"] + <-Map 72 [SIMPLE_EDGE] + SHUFFLE [RS_179] + PartitionCols:_col0 + Select Operator [SEL_168] (rows=1861800 width=385) + Output:["_col0","_col1"] + Filter Operator [FIL_616] (rows=1861800 width=385) + predicate:cd_demo_sk is not null + TableScan [TS_166] (rows=1861800 width=385) + default@customer_demographics,cd1,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"] + <-Reducer 67 [SIMPLE_EDGE] + SHUFFLE [RS_178] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_647] (rows=766650239 width=88) + Conds:RS_175._col6=RS_176._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col7","_col9","_col10","_col11","_col17","_col18"] + <-Map 71 [SIMPLE_EDGE] + SHUFFLE [RS_176] + PartitionCols:_col0 + Select Operator [SEL_165] (rows=1704 width=1910) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_615] (rows=1704 width=1910) + predicate:(s_store_sk is not null and s_store_name is not null and s_zip is not null) + TableScan [TS_163] (rows=1704 width=1910) + default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_zip"] + <-Reducer 66 [SIMPLE_EDGE] + SHUFFLE [RS_175] + PartitionCols:_col6 + Merge Join Operator [MERGEJOIN_646] (rows=696954748 width=88) + Conds:RS_172._col0=RS_173._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11"] + <-Map 70 [SIMPLE_EDGE] + SHUFFLE [RS_173] + PartitionCols:_col0 + Select Operator [SEL_162] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_614] (rows=36524 width=1119) + predicate:((d_year = 2001) and d_date_sk is not null) + TableScan [TS_160] (rows=73049 width=1119) + default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Reducer 65 [SIMPLE_EDGE] + SHUFFLE [RS_172] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_645] (rows=633595212 width=88) + Conds:RS_169._col1, _col8=RS_170._col0, _col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11"] + <-Map 64 [SIMPLE_EDGE] + SHUFFLE [RS_169] + PartitionCols:_col1, _col8 + Select Operator [SEL_156] (rows=575995635 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] + Filter Operator [FIL_612] (rows=575995635 width=88) + predicate:(ss_item_sk is not null and ss_ticket_number is not null and ss_customer_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_cdemo_sk is not null and ss_promo_sk is not null and ss_hdemo_sk is not null and ss_addr_sk is not null) + TableScan [TS_154] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_promo_sk","ss_ticket_number","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] + <-Map 69 [SIMPLE_EDGE] + SHUFFLE [RS_170] + PartitionCols:_col0, _col1 + Select Operator [SEL_159] (rows=57591150 width=77) + Output:["_col0","_col1"] + Filter Operator [FIL_613] (rows=57591150 width=77) + predicate:(sr_item_sk is not null and sr_ticket_number is not null) + TableScan [TS_157] (rows=57591150 width=77) + default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number"] + <-Reducer 77 [SIMPLE_EDGE] + SHUFFLE [RS_239] + PartitionCols:_col0 + Select Operator [SEL_225] (rows=52798137 width=135) + Output:["_col0"] + Filter Operator [FIL_224] (rows=52798137 width=135) + predicate:(_col1 > (2 * _col2)) + Group By Operator [GBY_223] (rows=158394413 width=135) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 + <-Reducer 76 [SIMPLE_EDGE] + SHUFFLE [RS_222] + PartitionCols:_col0 + Group By Operator [GBY_221] (rows=316788826 width=135) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","sum(_col2)"],keys:_col0 + Select Operator [SEL_219] (rows=316788826 width=135) + Output:["_col0","_col1","_col2"] + Merge Join Operator [MERGEJOIN_652] (rows=316788826 width=135) + Conds:RS_216._col0, _col1=RS_217._col0, _col1(Inner),Output:["_col0","_col2","_col5","_col6","_col7"] + <-Map 75 [SIMPLE_EDGE] + SHUFFLE [RS_216] + PartitionCols:_col0, _col1 + Select Operator [SEL_212] (rows=287989836 width=135) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_619] (rows=287989836 width=135) + predicate:(cs_order_number is not null and cs_item_sk is not null) + TableScan [TS_210] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_item_sk","cs_order_number","cs_ext_list_price"] + <-Map 78 [SIMPLE_EDGE] + SHUFFLE [RS_217] + PartitionCols:_col0, _col1 + Select Operator [SEL_215] (rows=28798881 width=106) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_620] (rows=28798881 width=106) + predicate:(cr_order_number is not null and cr_item_sk is not null) + TableScan [TS_213] (rows=28798881 width=106) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_refunded_cash","cr_reversed_charge","cr_store_credit"] +>>>>>>> clidriver golden file change diff --git a/ql/src/test/results/clientpositive/perf/query70.q.out b/ql/src/test/results/clientpositive/perf/query70.q.out index 8e42fac..e22b624 100644 --- a/ql/src/test/results/clientpositive/perf/query70.q.out +++ b/ql/src/test/results/clientpositive/perf/query70.q.out @@ -88,21 +88,35 @@ Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Stage-0 Fetch Operator - limit:100 + limit:-1 Stage-1 Reducer 7 +<<<<<<< HEAD File Output Operator [FS_60] Limit [LIM_59] (rows=100 width=88) +======= + File Output Operator [FS_63] + Limit [LIM_61] (rows=100 width=88) +>>>>>>> clidriver golden file change Number of rows:100 Select Operator [SEL_58] (rows=1149975358 width=88) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 6 [SIMPLE_EDGE] +<<<<<<< HEAD SHUFFLE [RS_57] Select Operator [SEL_55] (rows=1149975358 width=88) Output:["_col0","_col1","_col2","_col3","_col4"] PTF Operator [PTF_54] (rows=1149975358 width=88) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col4 DESC NULLS LAST","partition by:":"(grouping(_col5, 1) + grouping(_col5, 0)), CASE WHEN ((grouping(_col5, 0) = 0)) THEN (_col0) ELSE (null) END"}] Select Operator [SEL_53] (rows=1149975358 width=88) +======= + SHUFFLE [RS_59] + Select Operator [SEL_57] (rows=1149975358 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + PTF Operator [PTF_56] (rows=1149975358 width=88) + Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col4 DESC NULLS LAST","partition by:":"(grouping(_col5, 1) + grouping(_col5, 0)), CASE WHEN ((UDFToInteger(grouping(_col5, 0)) = 0)) THEN (_col0) ELSE (null) END"}] + Select Operator [SEL_55] (rows=1149975358 width=88) +>>>>>>> clidriver golden file change Output:["_col0","_col1","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_52] @@ -118,11 +132,17 @@ Stage-0 Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)"],keys:_col0, _col1, 0 Select Operator [SEL_46] (rows=766650239 width=88) Output:["_col0","_col1","_col2"] +<<<<<<< HEAD Merge Join Operator [MERGEJOIN_88] (rows=766650239 width=88) Conds:RS_43._col7=RS_44._col0(Inner),Output:["_col2","_col6","_col7"] +======= + Merge Join Operator [MERGEJOIN_91] (rows=766650239 width=88) + Conds:RS_45._col7=RS_46._col0(Left Semi),Output:["_col2","_col6","_col7"] +>>>>>>> clidriver golden file change <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col0 +<<<<<<< HEAD Select Operator [SEL_32] (rows=116159124 width=88) Output:["_col0"] Filter Operator [FIL_80] (rows=116159124 width=88) @@ -175,31 +195,105 @@ Stage-0 predicate:(d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) TableScan [TS_12] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] +======= + Group By Operator [GBY_44] (rows=116159124 width=88) + Output:["_col0"],keys:_col0 + Select Operator [SEL_32] (rows=116159124 width=88) + Output:["_col0"] + Filter Operator [FIL_83] (rows=116159124 width=88) + predicate:(rank_window_0 <= 5) + PTF Operator [PTF_31] (rows=348477374 width=88) + Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 DESC NULLS LAST","partition by:":"_col0"}] + Select Operator [SEL_30] (rows=348477374 width=88) + Output:["_col0","_col1"] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_29] + PartitionCols:_col0 + Group By Operator [GBY_27] (rows=348477374 width=88) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_26] + PartitionCols:_col0 + Group By Operator [GBY_25] (rows=696954748 width=88) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col6 + Select Operator [SEL_24] (rows=696954748 width=88) + Output:["_col6","_col2"] + Merge Join Operator [MERGEJOIN_90] (rows=696954748 width=88) + Conds:RS_21._col1=RS_22._col0(Inner),Output:["_col2","_col6"] + <-Map 16 [SIMPLE_EDGE] + SHUFFLE [RS_22] + PartitionCols:_col0 + Select Operator [SEL_17] (rows=1704 width=1910) + Output:["_col0","_col1"] + Filter Operator [FIL_86] (rows=1704 width=1910) + predicate:(s_store_sk is not null and s_state is not null) + TableScan [TS_15] (rows=1704 width=1910) + default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_state"] + <-Reducer 11 [SIMPLE_EDGE] + SHUFFLE [RS_21] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_89] (rows=633595212 width=88) + Conds:RS_18._col0=RS_19._col0(Inner),Output:["_col1","_col2"] + <-Map 10 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=575995635 width=88) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_84] (rows=575995635 width=88) + predicate:(ss_store_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_9] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_net_profit"] + <-Map 15 [SIMPLE_EDGE] + SHUFFLE [RS_19] + PartitionCols:_col0 + Select Operator [SEL_14] (rows=8116 width=1119) + Output:["_col0"] + Filter Operator [FIL_85] (rows=8116 width=1119) + predicate:(d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) + TableScan [TS_12] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] +>>>>>>> clidriver golden file change <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:_col7 +<<<<<<< HEAD Merge Join Operator [MERGEJOIN_85] (rows=696954748 width=88) +======= + Merge Join Operator [MERGEJOIN_88] (rows=696954748 width=88) +>>>>>>> clidriver golden file change Conds:RS_40._col1=RS_41._col0(Inner),Output:["_col2","_col6","_col7"] <-Map 9 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col0 Select Operator [SEL_8] (rows=1704 width=1910) Output:["_col0","_col1","_col2"] +<<<<<<< HEAD Filter Operator [FIL_79] (rows=1704 width=1910) +======= + Filter Operator [FIL_82] (rows=1704 width=1910) +>>>>>>> clidriver golden file change predicate:(s_state is not null and s_store_sk is not null) TableScan [TS_6] (rows=1704 width=1910) default@store,s,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_county","s_state"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_40] PartitionCols:_col1 +<<<<<<< HEAD Merge Join Operator [MERGEJOIN_84] (rows=633595212 width=88) +======= + Merge Join Operator [MERGEJOIN_87] (rows=633595212 width=88) +>>>>>>> clidriver golden file change Conds:RS_37._col0=RS_38._col0(Inner),Output:["_col1","_col2"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col0 Select Operator [SEL_2] (rows=575995635 width=88) Output:["_col0","_col1","_col2"] +<<<<<<< HEAD Filter Operator [FIL_77] (rows=575995635 width=88) +======= + Filter Operator [FIL_80] (rows=575995635 width=88) +>>>>>>> clidriver golden file change predicate:(ss_sold_date_sk is not null and ss_store_sk is not null) TableScan [TS_0] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_net_profit"] @@ -208,7 +302,11 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_5] (rows=8116 width=1119) Output:["_col0"] +<<<<<<< HEAD Filter Operator [FIL_78] (rows=8116 width=1119) +======= + Filter Operator [FIL_81] (rows=8116 width=1119) +>>>>>>> clidriver golden file change predicate:(d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=1119) default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] diff --git a/ql/src/test/results/clientpositive/perf/query75.q.out b/ql/src/test/results/clientpositive/perf/query75.q.out index b1e236d..83c0f90 100644 --- a/ql/src/test/results/clientpositive/perf/query75.q.out +++ b/ql/src/test/results/clientpositive/perf/query75.q.out @@ -30,9 +30,10 @@ Reducer 8 <- Reducer 7 (SIMPLE_EDGE) Stage-0 Fetch Operator - limit:100 + limit:-1 Stage-1 Reducer 8 +<<<<<<< HEAD File Output Operator [FS_156] Limit [LIM_155] (rows=100 width=108) Number of rows:100 @@ -388,4 +389,363 @@ Stage-0 predicate:((d_year = 2001) 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"] +======= + File Output Operator [FS_157] + Select Operator [SEL_156] (rows=100 width=108) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] + Limit [LIM_155] (rows=100 width=108) + Number of rows:100 + Select Operator [SEL_154] (rows=245965926 width=108) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Reducer 7 [SIMPLE_EDGE] + SHUFFLE [RS_153] + Select Operator [SEL_152] (rows=245965926 width=108) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_151] (rows=245965926 width=108) + predicate:((CAST( _col4 AS decimal(17,2)) / CAST( _col10 AS decimal(17,2))) < 0.9) + Merge Join Operator [MERGEJOIN_260] (rows=737897778 width=108) + Conds:RS_148._col0, _col1, _col2, _col3=RS_149._col0, _col1, _col2, _col3(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col10","_col11"] + <-Reducer 31 [SIMPLE_EDGE] + SHUFFLE [RS_149] + PartitionCols:_col0, _col1, _col2, _col3 + Group By Operator [GBY_146] (rows=670816148 width=108) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 + <-Union 30 [SIMPLE_EDGE] + <-Reducer 29 [CONTAINS] + Reduce Output Operator [RS_145] + PartitionCols:_col0, _col1, _col2, _col3 + Group By Operator [GBY_144] (rows=1341632296 width=108) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 + Select Operator [SEL_95] (rows=383314495 width=135) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_253] (rows=383314495 width=135) + Conds:RS_92._col1, _col2=RS_93._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] + <-Map 34 [SIMPLE_EDGE] + SHUFFLE [RS_93] + PartitionCols:_col0, _col1 + Select Operator [SEL_85] (rows=28798881 width=106) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_233] (rows=28798881 width=106) + predicate:cr_item_sk is not null + TableScan [TS_83] (rows=28798881 width=106) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_return_quantity","cr_return_amount"] + <-Reducer 28 [SIMPLE_EDGE] + SHUFFLE [RS_92] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_252] (rows=348467716 width=135) + Conds:RS_89._col1=RS_90._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] + <-Map 33 [SIMPLE_EDGE] + SHUFFLE [RS_90] + PartitionCols:_col0 + Select Operator [SEL_82] (rows=231000 width=1436) + Output:["_col0","_col1","_col2","_col3","_col5"] + Filter Operator [FIL_232] (rows=231000 width=1436) + predicate:((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) + TableScan [TS_80] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id","i_category","i_manufact_id"] + <-Reducer 27 [SIMPLE_EDGE] + SHUFFLE [RS_89] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_251] (rows=316788826 width=135) + Conds:RS_86._col0=RS_87._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 26 [SIMPLE_EDGE] + SHUFFLE [RS_86] + PartitionCols:_col0 + Select Operator [SEL_76] (rows=287989836 width=135) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_230] (rows=287989836 width=135) + predicate:(cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_74] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_order_number","cs_quantity","cs_ext_sales_price"] + <-Map 32 [SIMPLE_EDGE] + SHUFFLE [RS_87] + PartitionCols:_col0 + Select Operator [SEL_79] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_231] (rows=36524 width=1119) + predicate:((d_year = 2001) and d_date_sk is not null) + TableScan [TS_77] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Reducer 38 [CONTAINS] + Reduce Output Operator [RS_145] + PartitionCols:_col0, _col1, _col2, _col3 + Group By Operator [GBY_144] (rows=1341632296 width=108) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 + Select Operator [SEL_117] (rows=766650239 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_256] (rows=766650239 width=88) + Conds:RS_114._col1, _col2=RS_115._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] + <-Map 41 [SIMPLE_EDGE] + SHUFFLE [RS_115] + PartitionCols:_col0, _col1 + Select Operator [SEL_107] (rows=57591150 width=77) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_237] (rows=57591150 width=77) + predicate:sr_item_sk is not null + TableScan [TS_105] (rows=57591150 width=77) + default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number","sr_return_quantity","sr_return_amt"] + <-Reducer 37 [SIMPLE_EDGE] + SHUFFLE [RS_114] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_255] (rows=696954748 width=88) + Conds:RS_111._col1=RS_112._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] + <-Map 40 [SIMPLE_EDGE] + SHUFFLE [RS_112] + PartitionCols:_col0 + Select Operator [SEL_104] (rows=231000 width=1436) + Output:["_col0","_col1","_col2","_col3","_col5"] + Filter Operator [FIL_236] (rows=231000 width=1436) + predicate:((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) + TableScan [TS_102] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id","i_category","i_manufact_id"] + <-Reducer 36 [SIMPLE_EDGE] + SHUFFLE [RS_111] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_254] (rows=633595212 width=88) + Conds:RS_108._col0=RS_109._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 35 [SIMPLE_EDGE] + SHUFFLE [RS_108] + PartitionCols:_col0 + Select Operator [SEL_98] (rows=575995635 width=88) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_234] (rows=575995635 width=88) + predicate:(ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_96] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ticket_number","ss_quantity","ss_ext_sales_price"] + <-Map 39 [SIMPLE_EDGE] + SHUFFLE [RS_109] + PartitionCols:_col0 + Select Operator [SEL_101] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_235] (rows=36524 width=1119) + predicate:((d_year = 2001) and d_date_sk is not null) + TableScan [TS_99] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Reducer 45 [CONTAINS] + Reduce Output Operator [RS_145] + PartitionCols:_col0, _col1, _col2, _col3 + Group By Operator [GBY_144] (rows=1341632296 width=108) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 + Select Operator [SEL_141] (rows=191667562 width=135) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_259] (rows=191667562 width=135) + Conds:RS_138._col1, _col2=RS_139._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] + <-Map 48 [SIMPLE_EDGE] + SHUFFLE [RS_139] + PartitionCols:_col0, _col1 + Select Operator [SEL_131] (rows=14398467 width=92) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_241] (rows=14398467 width=92) + predicate:wr_item_sk is not null + TableScan [TS_129] (rows=14398467 width=92) + default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_item_sk","wr_order_number","wr_return_quantity","wr_return_amt"] + <-Reducer 44 [SIMPLE_EDGE] + SHUFFLE [RS_138] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_258] (rows=174243235 width=135) + Conds:RS_135._col1=RS_136._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] + <-Map 47 [SIMPLE_EDGE] + SHUFFLE [RS_136] + PartitionCols:_col0 + Select Operator [SEL_128] (rows=231000 width=1436) + Output:["_col0","_col1","_col2","_col3","_col5"] + Filter Operator [FIL_240] (rows=231000 width=1436) + predicate:((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) + TableScan [TS_126] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id","i_category","i_manufact_id"] + <-Reducer 43 [SIMPLE_EDGE] + SHUFFLE [RS_135] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_257] (rows=158402938 width=135) + Conds:RS_132._col0=RS_133._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 42 [SIMPLE_EDGE] + SHUFFLE [RS_132] + PartitionCols:_col0 + Select Operator [SEL_122] (rows=144002668 width=135) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_238] (rows=144002668 width=135) + predicate:(ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_120] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_order_number","ws_quantity","ws_ext_sales_price"] + <-Map 46 [SIMPLE_EDGE] + SHUFFLE [RS_133] + PartitionCols:_col0 + Select Operator [SEL_125] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_239] (rows=36524 width=1119) + predicate:((d_year = 2001) and d_date_sk is not null) + TableScan [TS_123] (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_148] + PartitionCols:_col0, _col1, _col2, _col3 + Group By Operator [GBY_72] (rows=670816148 width=108) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 + <-Union 5 [SIMPLE_EDGE] + <-Reducer 15 [CONTAINS] + Reduce Output Operator [RS_71] + PartitionCols:_col0, _col1, _col2, _col3 + Group By Operator [GBY_70] (rows=1341632296 width=108) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 + Select Operator [SEL_43] (rows=766650239 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_247] (rows=766650239 width=88) + Conds:RS_40._col1, _col2=RS_41._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] + <-Map 18 [SIMPLE_EDGE] + SHUFFLE [RS_41] + PartitionCols:_col0, _col1 + Select Operator [SEL_33] (rows=57591150 width=77) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_225] (rows=57591150 width=77) + predicate:sr_item_sk is not null + TableScan [TS_31] (rows=57591150 width=77) + default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number","sr_return_quantity","sr_return_amt"] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_40] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_246] (rows=696954748 width=88) + Conds:RS_37._col1=RS_38._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] + <-Map 17 [SIMPLE_EDGE] + SHUFFLE [RS_38] + PartitionCols:_col0 + Select Operator [SEL_30] (rows=231000 width=1436) + Output:["_col0","_col1","_col2","_col3","_col5"] + Filter Operator [FIL_224] (rows=231000 width=1436) + predicate:((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) + TableScan [TS_28] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id","i_category","i_manufact_id"] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_245] (rows=633595212 width=88) + Conds:RS_34._col0=RS_35._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 12 [SIMPLE_EDGE] + SHUFFLE [RS_34] + PartitionCols:_col0 + Select Operator [SEL_24] (rows=575995635 width=88) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_222] (rows=575995635 width=88) + predicate:(ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_22] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ticket_number","ss_quantity","ss_ext_sales_price"] + <-Map 16 [SIMPLE_EDGE] + SHUFFLE [RS_35] + PartitionCols:_col0 + Select Operator [SEL_27] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_223] (rows=36524 width=1119) + predicate:((d_year = 2002) and d_date_sk is not null) + TableScan [TS_25] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Reducer 22 [CONTAINS] + Reduce Output Operator [RS_71] + PartitionCols:_col0, _col1, _col2, _col3 + Group By Operator [GBY_70] (rows=1341632296 width=108) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 + Select Operator [SEL_67] (rows=191667562 width=135) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_250] (rows=191667562 width=135) + Conds:RS_64._col1, _col2=RS_65._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] + <-Map 25 [SIMPLE_EDGE] + SHUFFLE [RS_65] + PartitionCols:_col0, _col1 + Select Operator [SEL_57] (rows=14398467 width=92) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_229] (rows=14398467 width=92) + predicate:wr_item_sk is not null + TableScan [TS_55] (rows=14398467 width=92) + default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_item_sk","wr_order_number","wr_return_quantity","wr_return_amt"] + <-Reducer 21 [SIMPLE_EDGE] + SHUFFLE [RS_64] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_249] (rows=174243235 width=135) + Conds:RS_61._col1=RS_62._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] + <-Map 24 [SIMPLE_EDGE] + SHUFFLE [RS_62] + PartitionCols:_col0 + Select Operator [SEL_54] (rows=231000 width=1436) + Output:["_col0","_col1","_col2","_col3","_col5"] + Filter Operator [FIL_228] (rows=231000 width=1436) + predicate:((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) + TableScan [TS_52] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id","i_category","i_manufact_id"] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_61] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_248] (rows=158402938 width=135) + Conds:RS_58._col0=RS_59._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 19 [SIMPLE_EDGE] + SHUFFLE [RS_58] + PartitionCols:_col0 + Select Operator [SEL_48] (rows=144002668 width=135) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_226] (rows=144002668 width=135) + predicate:(ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_46] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_order_number","ws_quantity","ws_ext_sales_price"] + <-Map 23 [SIMPLE_EDGE] + SHUFFLE [RS_59] + PartitionCols:_col0 + Select Operator [SEL_51] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_227] (rows=36524 width=1119) + predicate:((d_year = 2002) and d_date_sk is not null) + TableScan [TS_49] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Reducer 4 [CONTAINS] + Reduce Output Operator [RS_71] + PartitionCols:_col0, _col1, _col2, _col3 + Group By Operator [GBY_70] (rows=1341632296 width=108) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 + Select Operator [SEL_21] (rows=383314495 width=135) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_244] (rows=383314495 width=135) + Conds:RS_18._col1, _col2=RS_19._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] + <-Map 11 [SIMPLE_EDGE] + SHUFFLE [RS_19] + PartitionCols:_col0, _col1 + Select Operator [SEL_11] (rows=28798881 width=106) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_221] (rows=28798881 width=106) + predicate:cr_item_sk is not null + TableScan [TS_9] (rows=28798881 width=106) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_return_quantity","cr_return_amount"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_243] (rows=348467716 width=135) + Conds:RS_15._col1=RS_16._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] + <-Map 10 [SIMPLE_EDGE] + SHUFFLE [RS_16] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=231000 width=1436) + Output:["_col0","_col1","_col2","_col3","_col5"] + Filter Operator [FIL_220] (rows=231000 width=1436) + predicate:((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) + TableScan [TS_6] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id","i_category","i_manufact_id"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_15] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_242] (rows=316788826 width=135) + Conds:RS_12._col0=RS_13._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=287989836 width=135) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_218] (rows=287989836 width=135) + predicate:(cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_0] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_order_number","cs_quantity","cs_ext_sales_price"] + <-Map 9 [SIMPLE_EDGE] + SHUFFLE [RS_13] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_219] (rows=36524 width=1119) + predicate:((d_year = 2002) 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"] +>>>>>>> clidriver golden file change diff --git a/ql/src/test/results/clientpositive/perf/query81.q.out b/ql/src/test/results/clientpositive/perf/query81.q.out index a09d5c9..227bddf 100644 --- a/ql/src/test/results/clientpositive/perf/query81.q.out +++ b/ql/src/test/results/clientpositive/perf/query81.q.out @@ -76,8 +76,9 @@ Reducer 9 <- Map 13 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator - limit:100 + limit:-1 Stage-1 +<<<<<<< HEAD Reducer 5 File Output Operator [FS_101] Limit [LIM_100] (rows=100 width=860) @@ -169,10 +170,105 @@ Stage-0 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] +======= + Reducer 4 + File Output Operator [FS_68] + Select Operator [SEL_67] (rows=100 width=860) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + Limit [LIM_66] (rows=100 width=860) + Number of rows:100 + Select Operator [SEL_65] (rows=32266667 width=860) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] + <-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","_col13","_col14"] + 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_106] (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_105] (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=8711661 width=106) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_49] (rows=8711661 width=106) + Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col0 + Select Operator [SEL_45] (rows=17423323 width=106) + Output:["_col0","_col2"] + Group By Operator [GBY_44] (rows=17423323 width=106) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_43] + PartitionCols:_col0 + Group By Operator [GBY_42] (rows=34846646 width=106) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 + Select Operator [SEL_41] (rows=34846646 width=106) + Output:["_col7","_col1","_col3"] + Merge Join Operator [MERGEJOIN_104] (rows=34846646 width=106) + Conds:RS_38._col2=RS_39._col0(Inner),Output:["_col1","_col3","_col7"] + <-Map 18 [SIMPLE_EDGE] + SHUFFLE [RS_39] + PartitionCols:_col0 + Select Operator [SEL_34] (rows=20000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_99] (rows=20000000 width=1014) + predicate:((ca_state = ca_state) and ca_address_sk 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 14 [SIMPLE_EDGE] + SHUFFLE [RS_38] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_103] (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_97] (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_31] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_98] (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 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 + Select Operator [SEL_21] (rows=44000000 width=1014) + Output:["_col7","_col1","_col3"] + Merge Join Operator [MERGEJOIN_102] (rows=44000000 width=1014) + Conds:RS_18._col2=RS_19._col0(Inner),Output:["_col1","_col3","_col7"] + <-Map 12 [SIMPLE_EDGE] +>>>>>>> clidriver golden file change SHUFFLE [RS_19] PartitionCols:_col0 Select Operator [SEL_14] (rows=40000000 width=1014) Output:["_col0","_col1"] +<<<<<<< HEAD Filter Operator [FIL_137] (rows=40000000 width=1014) predicate:ca_address_sk is not null TableScan [TS_12] (rows=40000000 width=1014) @@ -183,19 +279,40 @@ Stage-0 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] +======= + Filter Operator [FIL_96] (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_101] (rows=31678769 width=106) + Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 11 [SIMPLE_EDGE] +>>>>>>> clidriver golden file change SHUFFLE [RS_16] PartitionCols:_col0 Select Operator [SEL_11] (rows=36524 width=1119) Output:["_col0"] +<<<<<<< HEAD Filter Operator [FIL_136] (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 7 [SIMPLE_EDGE] +======= + Filter Operator [FIL_95] (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] +>>>>>>> clidriver golden file change SHUFFLE [RS_15] PartitionCols:_col0 Select Operator [SEL_8] (rows=28798881 width=106) Output:["_col0","_col1","_col2","_col3"] +<<<<<<< HEAD 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) @@ -277,4 +394,33 @@ Stage-0 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"] +======= + Filter Operator [FIL_94] (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_100] (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_92] (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 + Select Operator [SEL_5] (rows=20000000 width=1014) + Output:["_col0","_col1","_col10","_col11","_col2","_col3","_col4","_col5","_col6","_col8","_col9"] + Filter Operator [FIL_93] (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"] +>>>>>>> clidriver golden file change diff --git a/ql/src/test/results/clientpositive/perf/query85.q.out b/ql/src/test/results/clientpositive/perf/query85.q.out index 168bcd2..290c955 100644 --- a/ql/src/test/results/clientpositive/perf/query85.q.out +++ b/ql/src/test/results/clientpositive/perf/query85.q.out @@ -17,11 +17,17 @@ Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator - limit:100 + limit:-1 Stage-1 +<<<<<<< HEAD Reducer 10 File Output Operator [FS_55] Limit [LIM_54] (rows=100 width=385) +======= + Reducer 5 + File Output Operator [FS_60] + Limit [LIM_58] (rows=100 width=1014) +>>>>>>> clidriver golden file change Number of rows:100 Select Operator [SEL_53] (rows=1023990 width=385) Output:["_col0","_col1","_col2","_col3"] @@ -34,6 +40,7 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0 +<<<<<<< HEAD Group By Operator [GBY_48] (rows=2047980 width=385) Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(_col5)","avg(_col17)","avg(_col16)"],keys:_col19 Merge Join Operator [MERGEJOIN_105] (rows=2047980 width=385) @@ -144,4 +151,126 @@ Stage-0 predicate:((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and (ws_net_profit BETWEEN 100 AND 200 or ws_net_profit BETWEEN 150 AND 300 or ws_net_profit BETWEEN 50 AND 250) and ws_order_number is not null and ws_item_sk is not null and ws_web_page_sk is not null and ws_sold_date_sk is not null) TableScan [TS_3] (rows=144002668 width=135) default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_page_sk","ws_order_number","ws_quantity","ws_sales_price","ws_net_profit"] +======= + Group By Operator [GBY_52] (rows=2440165 width=1014) + Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(_col6)","avg(_col16)","avg(_col15)"],keys:_col28 + Select Operator [SEL_51] (rows=2440165 width=1014) + Output:["_col28","_col6","_col16","_col15"] + Merge Join Operator [MERGEJOIN_110] (rows=2440165 width=1014) + Conds:RS_48._col13=RS_49._col0(Inner),Output:["_col6","_col15","_col16","_col28"] + <-Map 17 [SIMPLE_EDGE] + SHUFFLE [RS_49] + PartitionCols:_col0 + Select Operator [SEL_44] (rows=72 width=200) + Output:["_col0","_col1"] + Filter Operator [FIL_103] (rows=72 width=200) + predicate:r_reason_sk is not null + TableScan [TS_42] (rows=72 width=200) + default@reason,reason,Tbl:COMPLETE,Col:NONE,Output:["r_reason_sk","r_reason_desc"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_48] + PartitionCols:_col13 + Merge Join Operator [MERGEJOIN_109] (rows=2218332 width=1014) + Conds:RS_45._col0=RS_46._col0(Inner),Output:["_col6","_col13","_col15","_col16"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_45] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=36524 width=1119) + Output:["_col0"] + Filter Operator [FIL_96] (rows=36524 width=1119) + predicate:((d_year = 1998) and d_date_sk is not null) + TableScan [TS_0] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_46] + PartitionCols:_col0 + Select Operator [SEL_41] (rows=2016666 width=1014) + Output:["_col0","_col11","_col13","_col14","_col4"] + Filter Operator [FIL_40] (rows=2016666 width=1014) + predicate:(((_col23) IN ('KY', 'GA', 'NM') and _col6 BETWEEN 100 AND 200) or ((_col23) IN ('MT', 'OR', 'IN') and _col6 BETWEEN 150 AND 300) or ((_col23) IN ('WI', 'MO', 'WV') and _col6 BETWEEN 50 AND 250)) + Select Operator [SEL_39] (rows=12100000 width=1014) + Output:["_col0","_col4","_col6","_col11","_col13","_col14","_col23"] + Merge Join Operator [MERGEJOIN_108] (rows=12100000 width=1014) + Conds:RS_36._col13, _col20, _col21=RS_37._col0, _col1, _col2(Inner),Output:["_col1","_col3","_col7","_col9","_col14","_col16","_col17"] + <-Map 16 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:_col0, _col1, _col2 + Select Operator [SEL_32] (rows=1861800 width=385) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_102] (rows=1861800 width=385) + predicate:(((cd_education_status = '4 yr Degree') or (cd_education_status = 'Primary') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'D') or (cd_marital_status = 'U')) and cd_demo_sk is not null and cd_marital_status is not null and cd_education_status is not null) + TableScan [TS_30] (rows=1861800 width=385) + default@customer_demographics,cd2,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + <-Reducer 7 [SIMPLE_EDGE] + SHUFFLE [RS_36] + PartitionCols:_col13, _col20, _col21 + Merge Join Operator [MERGEJOIN_107] (rows=11000000 width=1014) + Conds:RS_33._col0=RS_34._col9(Inner),Output:["_col1","_col3","_col7","_col9","_col13","_col14","_col16","_col17","_col20","_col21"] + <-Map 6 [SIMPLE_EDGE] + SHUFFLE [RS_33] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=10000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_97] (rows=10000000 width=1014) + predicate:((ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and (ca_country = 'United States') 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","ca_country"] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_34] + PartitionCols:_col9 + Select Operator [SEL_29] (rows=1774698 width=135) + Output:["_col0","_col10","_col11","_col13","_col14","_col17","_col18","_col4","_col6","_col9"] + Filter Operator [FIL_28] (rows=1774698 width=135) + predicate:(((_col17 = 'M') and (_col18 = '4 yr Degree') and _col5 BETWEEN 100 AND 150) or ((_col17 = 'D') and (_col18 = 'Primary') and _col5 BETWEEN 50 AND 100) or ((_col17 = 'U') and (_col18 = 'Advanced Degree') and _col5 BETWEEN 150 AND 200)) + Select Operator [SEL_27] (rows=21296393 width=135) + Output:["_col0","_col4","_col5","_col6","_col9","_col10","_col11","_col13","_col14","_col17","_col18"] + Merge Join Operator [MERGEJOIN_106] (rows=21296393 width=135) + Conds:RS_24._col9=RS_25._col0(Inner),Output:["_col1","_col5","_col6","_col7","_col10","_col11","_col12","_col14","_col15","_col17","_col18"] + <-Map 15 [SIMPLE_EDGE] + SHUFFLE [RS_25] + PartitionCols:_col0 + Select Operator [SEL_17] (rows=1861800 width=385) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_101] (rows=1861800 width=385) + predicate:(((cd_education_status = '4 yr Degree') or (cd_education_status = 'Primary') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'D') or (cd_marital_status = 'U')) and cd_demo_sk is not null and cd_marital_status is not null and cd_education_status is not null) + TableScan [TS_15] (rows=1861800 width=385) + default@customer_demographics,cd1,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + <-Reducer 11 [SIMPLE_EDGE] + SHUFFLE [RS_24] + PartitionCols:_col9 + Merge Join Operator [MERGEJOIN_105] (rows=19360357 width=135) + Conds:RS_21._col2, _col4=RS_22._col0, _col5(Inner),Output:["_col1","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col14","_col15"] + <-Map 14 [SIMPLE_EDGE] + SHUFFLE [RS_22] + PartitionCols:_col0, _col5 + Select Operator [SEL_14] (rows=14398467 width=92) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_100] (rows=14398467 width=92) + predicate:(wr_item_sk is not null and wr_order_number is not null and wr_refunded_cdemo_sk is not null and wr_returning_cdemo_sk is not null and wr_refunded_addr_sk is not null and wr_reason_sk is not null) + TableScan [TS_12] (rows=14398467 width=92) + default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_item_sk","wr_refunded_cdemo_sk","wr_refunded_addr_sk","wr_returning_cdemo_sk","wr_reason_sk","wr_order_number","wr_fee","wr_refunded_cash"] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_21] + PartitionCols:_col2, _col4 + Merge Join Operator [MERGEJOIN_104] (rows=17600325 width=135) + Conds:RS_18._col0=RS_19._col2(Inner),Output:["_col1","_col2","_col4","_col5","_col6","_col7"] + <-Map 13 [SIMPLE_EDGE] + SHUFFLE [RS_19] + PartitionCols:_col2 + Select Operator [SEL_11] (rows=16000296 width=135) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Filter Operator [FIL_99] (rows=16000296 width=135) + predicate:((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and (ws_net_profit BETWEEN 100 AND 200 or ws_net_profit BETWEEN 150 AND 300 or ws_net_profit BETWEEN 50 AND 250) and ws_order_number is not null and ws_item_sk is not null and ws_web_page_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_9] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_page_sk","ws_order_number","ws_quantity","ws_sales_price","ws_net_profit"] + <-Map 9 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=4602 width=585) + Output:["_col0"] + Filter Operator [FIL_98] (rows=4602 width=585) + predicate:wp_web_page_sk is not null + TableScan [TS_6] (rows=4602 width=585) + default@web_page,web_page,Tbl:COMPLETE,Col:NONE,Output:["wp_web_page_sk"] +>>>>>>> clidriver golden file change diff --git a/ql/src/test/results/clientpositive/perf/query86.q.out b/ql/src/test/results/clientpositive/perf/query86.q.out index 734e6a4..bc86291 100644 --- a/ql/src/test/results/clientpositive/perf/query86.q.out +++ b/ql/src/test/results/clientpositive/perf/query86.q.out @@ -59,10 +59,10 @@ Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Stage-0 Fetch Operator - limit:100 + limit:-1 Stage-1 Reducer 6 - File Output Operator [FS_29] + File Output Operator [FS_30] Limit [LIM_28] (rows=100 width=135) Number of rows:100 Select Operator [SEL_27] (rows=261364852 width=135) @@ -70,7 +70,7 @@ Stage-0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_26] Select Operator [SEL_24] (rows=261364852 width=135) - Output:["_col0","_col1","_col2","_col3","_col4"] + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] PTF Operator [PTF_23] (rows=261364852 width=135) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col4 DESC NULLS LAST","partition by:":"(grouping(_col5, 1) + grouping(_col5, 0)), CASE WHEN ((grouping(_col5, 0) = 0)) THEN (_col0) ELSE (null) END"}] Select Operator [SEL_22] (rows=261364852 width=135) @@ -89,28 +89,28 @@ Stage-0 Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)"],keys:_col0, _col1, 0 Select Operator [SEL_15] (rows=174243235 width=135) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_39] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_40] (rows=174243235 width=135) Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col2","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] SHUFFLE [RS_13] PartitionCols:_col0 Select Operator [SEL_8] (rows=462000 width=1436) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_37] (rows=462000 width=1436) + Filter Operator [FIL_38] (rows=462000 width=1436) predicate:i_item_sk is not null TableScan [TS_6] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_class","i_category"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_38] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_39] (rows=158402938 width=135) Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col1","_col2"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_9] PartitionCols:_col0 Select Operator [SEL_2] (rows=144002668 width=135) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_35] (rows=144002668 width=135) + Filter Operator [FIL_36] (rows=144002668 width=135) predicate:(ws_sold_date_sk is not null and ws_item_sk is not null) TableScan [TS_0] (rows=144002668 width=135) default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_net_paid"] @@ -119,7 +119,7 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_5] (rows=8116 width=1119) Output:["_col0"] - Filter Operator [FIL_36] (rows=8116 width=1119) + Filter Operator [FIL_37] (rows=8116 width=1119) predicate:(d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=1119) default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] diff --git a/ql/src/test/results/clientpositive/perf/query89.q.out b/ql/src/test/results/clientpositive/perf/query89.q.out index 66481f7..39ab2a2 100644 --- a/ql/src/test/results/clientpositive/perf/query89.q.out +++ b/ql/src/test/results/clientpositive/perf/query89.q.out @@ -64,10 +64,10 @@ Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Stage-0 Fetch Operator - limit:100 + limit:-1 Stage-1 Reducer 7 - File Output Operator [FS_36] + File Output Operator [FS_37] Limit [LIM_35] (rows=100 width=88) Number of rows:100 Select Operator [SEL_34] (rows=191662559 width=88) @@ -75,8 +75,8 @@ Stage-0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_33] Select Operator [SEL_30] (rows=191662559 width=88) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_46] (rows=191662559 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Filter Operator [FIL_47] (rows=191662559 width=88) predicate:CASE WHEN ((avg_window_0 <> 0)) THEN (((abs((_col6 - avg_window_0)) / avg_window_0) > 0.1)) ELSE (null) END Select Operator [SEL_29] (rows=383325119 width=88) Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] @@ -96,6 +96,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 Group By Operator [GBY_22] (rows=766650239 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)"],keys:_col5, _col6, _col7, _col10, _col12, _col13 +<<<<<<< HEAD Merge Join Operator [MERGEJOIN_53] (rows=766650239 width=88) Conds:RS_18._col2=RS_19._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col10","_col12","_col13"] <-Map 10 [SIMPLE_EDGE] @@ -144,4 +145,56 @@ Stage-0 predicate:(((i_class) IN ('wallpaper', 'parenting', 'musical') or (i_class) IN ('womens', 'birdal', 'pants')) and ((i_category) IN ('Home', 'Books', 'Electronics') or (i_category) IN ('Shoes', 'Jewelry', 'Men')) and (((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and i_item_sk is not null) TableScan [TS_3] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category"] +======= + Select Operator [SEL_21] (rows=766650239 width=88) + Output:["_col5","_col6","_col7","_col10","_col12","_col13","_col3"] + Merge Join Operator [MERGEJOIN_54] (rows=766650239 width=88) + Conds:RS_18._col2=RS_19._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col10","_col12","_col13"] + <-Map 10 [SIMPLE_EDGE] + SHUFFLE [RS_19] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=1704 width=1910) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_51] (rows=1704 width=1910) + predicate:s_store_sk is not null + TableScan [TS_9] (rows=1704 width=1910) + default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_company_name"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_53] (rows=696954748 width=88) + Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col7","_col10"] + <-Map 9 [SIMPLE_EDGE] + SHUFFLE [RS_16] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=36525 width=1119) + Output:["_col0","_col2"] + Filter Operator [FIL_50] (rows=36525 width=1119) + predicate:((d_year) IN (2000) and d_date_sk is not null) + TableScan [TS_6] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_15] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_52] (rows=633595212 width=88) + Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col0","_col2","_col3","_col5","_col6","_col7"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col1 + Select Operator [SEL_2] (rows=575995635 width=88) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_48] (rows=575995635 width=88) + predicate:(ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] + <-Map 8 [SIMPLE_EDGE] + SHUFFLE [RS_13] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=231000 width=1436) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_49] (rows=231000 width=1436) + predicate:(((i_class) IN ('wallpaper', 'parenting', 'musical') or (i_class) IN ('womens', 'birdal', 'pants')) and ((i_category) IN ('Home', 'Books', 'Electronics') or (i_category) IN ('Shoes', 'Jewelry', 'Men')) and (((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and i_item_sk is not null) + TableScan [TS_3] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category"] +>>>>>>> clidriver golden file change diff --git a/ql/src/test/results/clientpositive/perf/query91.q.out b/ql/src/test/results/clientpositive/perf/query91.q.out index e592bba..ea04616 100644 --- a/ql/src/test/results/clientpositive/perf/query91.q.out +++ b/ql/src/test/results/clientpositive/perf/query91.q.out @@ -19,7 +19,7 @@ Stage-0 limit:-1 Stage-1 Reducer 6 - File Output Operator [FS_47] + File Output Operator [FS_48] Select Operator [SEL_46] (rows=58564004 width=860) Output:["_col0","_col1","_col2","_col3"] <-Reducer 5 [SIMPLE_EDGE] @@ -33,6 +33,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2, _col3, _col4 Group By Operator [GBY_41] (rows=117128008 width=860) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col3)"],keys:_col8, _col9, _col10, _col18, _col19 +<<<<<<< HEAD Merge Join Operator [MERGEJOIN_81] (rows=117128008 width=860) Conds:RS_37._col1=RS_38._col2(Inner),Output:["_col3","_col8","_col9","_col10","_col18","_col19"] <-Reducer 12 [SIMPLE_EDGE] @@ -58,9 +59,99 @@ Stage-0 Conds:RS_24._col3=RS_25._col0(Inner),Output:["_col0","_col2","_col5","_col6"] <-Map 14 [SIMPLE_EDGE] SHUFFLE [RS_25] +======= + Select Operator [SEL_40] (rows=117128008 width=860) + Output:["_col8","_col9","_col10","_col18","_col19","_col3"] + Merge Join Operator [MERGEJOIN_82] (rows=117128008 width=860) + Conds:RS_37._col1=RS_38._col2(Inner),Output:["_col3","_col8","_col9","_col10","_col18","_col19"] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_38] + PartitionCols:_col2 + Select Operator [SEL_30] (rows=106480005 width=860) + Output:["_col2","_col7","_col8"] + Merge Join Operator [MERGEJOIN_81] (rows=106480005 width=860) + Conds:RS_27._col2=RS_28._col0(Inner),Output:["_col0","_col5","_col6"] + <-Map 15 [SIMPLE_EDGE] + SHUFFLE [RS_28] + PartitionCols:_col0 + Select Operator [SEL_20] (rows=3600 width=107) + Output:["_col0"] + Filter Operator [FIL_76] (rows=3600 width=107) + predicate:((hd_buy_potential like '0-500%') and hd_demo_sk is not null) + TableScan [TS_18] (rows=7200 width=107) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_buy_potential"] + <-Reducer 11 [SIMPLE_EDGE] + SHUFFLE [RS_27] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_80] (rows=96800003 width=860) + Conds:RS_24._col3=RS_25._col0(Inner),Output:["_col0","_col2","_col5","_col6"] + <-Map 14 [SIMPLE_EDGE] + SHUFFLE [RS_25] + PartitionCols:_col0 + Select Operator [SEL_17] (rows=20000000 width=1014) + Output:["_col0"] + Filter Operator [FIL_75] (rows=20000000 width=1014) + predicate:((ca_gmt_offset = -7) and ca_address_sk is not null) + TableScan [TS_15] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_gmt_offset"] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_24] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_79] (rows=88000001 width=860) + Conds:RS_21._col1=RS_22._col0(Inner),Output:["_col0","_col2","_col3","_col5","_col6"] + <-Map 13 [SIMPLE_EDGE] + SHUFFLE [RS_22] + PartitionCols:_col0 + Select Operator [SEL_14] (rows=930900 width=385) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_74] (rows=930900 width=385) + predicate:(((cd_education_status = 'Unknown') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'W')) and (((cd_marital_status = 'M') and (cd_education_status = 'Unknown')) or ((cd_marital_status = 'W') and (cd_education_status = 'Advanced Degree'))) and cd_demo_sk is not null) + TableScan [TS_12] (rows=1861800 width=385) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + <-Map 9 [SIMPLE_EDGE] + SHUFFLE [RS_21] + PartitionCols:_col1 + Select Operator [SEL_11] (rows=80000000 width=860) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_73] (rows=80000000 width=860) + predicate:(c_customer_sk is not null and c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null) + TableScan [TS_9] (rows=80000000 width=860) + default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_78] (rows=34846646 width=106) + Conds:RS_34._col2=RS_35._col0(Inner),Output:["_col1","_col3","_col8","_col9","_col10"] + <-Map 8 [SIMPLE_EDGE] + SHUFFLE [RS_35] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=60 width=2045) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_72] (rows=60 width=2045) + predicate:cc_call_center_sk is not null + TableScan [TS_6] (rows=60 width=2045) + default@call_center,call_center,Tbl:COMPLETE,Col:NONE,Output:["cc_call_center_sk","cc_call_center_id","cc_name","cc_manager"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_34] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_77] (rows=31678769 width=106) + Conds:RS_31._col0=RS_32._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_31] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=28798881 width=106) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_70] (rows=28798881 width=106) + predicate:(cr_call_center_sk is not null and cr_returned_date_sk is not null and cr_returning_customer_sk is not null) + TableScan [TS_0] (rows=28798881 width=106) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_returned_date_sk","cr_returning_customer_sk","cr_call_center_sk","cr_net_loss"] + <-Map 7 [SIMPLE_EDGE] + SHUFFLE [RS_32] +>>>>>>> clidriver golden file change PartitionCols:_col0 Select Operator [SEL_17] (rows=20000000 width=1014) Output:["_col0"] +<<<<<<< HEAD Filter Operator [FIL_74] (rows=20000000 width=1014) predicate:((ca_gmt_offset = -7) and ca_address_sk is not null) TableScan [TS_15] (rows=40000000 width=1014) @@ -125,4 +216,10 @@ Stage-0 predicate:((d_year = 1999) and (d_moy = 11) 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","d_moy"] +======= + Filter Operator [FIL_71] (rows=18262 width=1119) + predicate:((d_year = 1999) and (d_moy = 11) 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","d_moy"] +>>>>>>> clidriver golden file change diff --git a/ql/src/test/results/clientpositive/pointlookup2.q.out b/ql/src/test/results/clientpositive/pointlookup2.q.out index 3438c74..158e885 100644 --- a/ql/src/test/results/clientpositive/pointlookup2.q.out +++ b/ql/src/test/results/clientpositive/pointlookup2.q.out @@ -374,7 +374,7 @@ STAGE PLANS: name: default.pcr_t1 name: default.pcr_t1 Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [$hdt$_0:t1, $hdt$_1:t2] + /pcr_t1/ds=2000-04-08 [$hdt$_0:$hdt$_0:t1, $hdt$_0:$hdt$_1:t2] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -385,24 +385,28 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col3,_col4 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -415,7 +419,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -427,7 +431,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col1,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -437,7 +441,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col1,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -640,8 +644,8 @@ STAGE PLANS: name: default.pcr_t1 name: default.pcr_t1 Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [$hdt$_0:t1] - /pcr_t1/ds=2000-04-09 [$hdt$_1:t2] + /pcr_t1/ds=2000-04-08 [$hdt$_0:$hdt$_0:t1] + /pcr_t1/ds=2000-04-09 [$hdt$_0:$hdt$_1:t2] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -652,24 +656,28 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col3,_col4 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -682,7 +690,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -694,7 +702,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col1,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -704,7 +712,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col1,_col3,_col4 + columns _col0,_col1,_col2,_col3 columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe diff --git a/ql/src/test/results/clientpositive/pointlookup3.q.out b/ql/src/test/results/clientpositive/pointlookup3.q.out index 2c3e39f..eb61e17 100644 --- a/ql/src/test/results/clientpositive/pointlookup3.q.out +++ b/ql/src/test/results/clientpositive/pointlookup3.q.out @@ -307,7 +307,7 @@ STAGE PLANS: name: default.pcr_t1 name: default.pcr_t1 Truncated Path -> Alias: - /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1] + /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:pcr_t1] Needs Tagging: false Reduce Operator Tree: Select Operator @@ -458,7 +458,7 @@ STAGE PLANS: name: default.pcr_t1 name: default.pcr_t1 Truncated Path -> Alias: - /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:t1, $hdt$_1:t2] + /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:$hdt$_0:t1, $hdt$_0:$hdt$_1:t2] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -469,24 +469,28 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col3,_col4,_col5,_col6 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int,string,string,int,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -499,7 +503,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string) + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -511,7 +515,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col1,_col3,_col4,_col5,_col6 + columns _col0,_col1,_col2,_col3,_col4,_col5 columns.types int,string,string,int,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -521,7 +525,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col1,_col3,_col4,_col5,_col6 + columns _col0,_col1,_col2,_col3,_col4,_col5 columns.types int,string,string,int,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -726,8 +730,8 @@ STAGE PLANS: name: default.pcr_t1 name: default.pcr_t1 Truncated Path -> Alias: - /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:t1] - /pcr_t1/ds1=2000-04-09/ds2=2001-04-09 [$hdt$_1:t2] + /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:$hdt$_0:t1] + /pcr_t1/ds1=2000-04-09/ds2=2001-04-09 [$hdt$_0:$hdt$_1:t2] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -738,24 +742,28 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col7 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col3,_col4,_col5,_col7 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int,string,string,int,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -768,7 +776,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col7 (type: string) + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -780,7 +788,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col1,_col3,_col4,_col5,_col7 + columns _col0,_col1,_col2,_col3,_col4,_col5 columns.types int,string,string,int,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -790,7 +798,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: column.name.delimiter , - columns _col0,_col1,_col3,_col4,_col5,_col7 + columns _col0,_col1,_col2,_col3,_col4,_col5 columns.types int,string,string,int,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe diff --git a/ql/src/test/results/clientpositive/ppd_udf_case.q.out b/ql/src/test/results/clientpositive/ppd_udf_case.q.out index 7678d03..3cf8e81 100644 --- a/ql/src/test/results/clientpositive/ppd_udf_case.q.out +++ b/ql/src/test/results/clientpositive/ppd_udf_case.q.out @@ -71,19 +71,23 @@ STAGE PLANS: 1 outputColumnNames: _col1, _col3, _col5, _col7 Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col1 (type: string), _col3 (type: string), _col5 (type: string), _col7 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: string), _col3 (type: string), _col5 (type: string), _col7 (type: string) + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: @@ -215,19 +219,23 @@ STAGE PLANS: 1 outputColumnNames: _col1, _col3, _col5, _col7 Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col1 (type: string), _col3 (type: string), _col5 (type: string), _col7 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col1 (type: string), _col3 (type: string), _col5 (type: string), _col7 (type: string) + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: diff --git a/ql/src/test/results/clientpositive/ppd_vc.q.out b/ql/src/test/results/clientpositive/ppd_vc.q.out index 86ab427..e841cb6 100644 --- a/ql/src/test/results/clientpositive/ppd_vc.q.out +++ b/ql/src/test/results/clientpositive/ppd_vc.q.out @@ -325,26 +325,6 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: 0 - auto parallelism: false - TableScan alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE GatherStats: false @@ -365,6 +345,22 @@ STAGE PLANS: tag: 1 value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) auto parallelism: false + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + tag: 0 + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -607,23 +603,23 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:srcpart] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:srcpart] - /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:srcpart] - /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:srcpart] + /src [a] + /srcpart/ds=2008-04-08/hr=11 [b:srcpart] + /srcpart/ds=2008-04-08/hr=12 [b:srcpart] + /srcpart/ds=2008-04-09/hr=11 [b:srcpart] + /srcpart/ds=2008-04-09/hr=12 [b:srcpart] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 key (type: string) 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 + outputColumnNames: _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: bigint) + expressions: _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/ppd_windowing1.q.out b/ql/src/test/results/clientpositive/ppd_windowing1.q.out index ad57ba9..734032e 100644 --- a/ql/src/test/results/clientpositive/ppd_windowing1.q.out +++ b/ql/src/test/results/clientpositive/ppd_windowing1.q.out @@ -278,7 +278,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) + predicate: ((((UDFToInteger(key) + 2) + 2) + 1) > 2) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) @@ -608,7 +608,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) + predicate: ((((UDFToInteger(key) + 2) + 2) + 1) > 2) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) @@ -1014,7 +1014,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) + predicate: ((((UDFToInteger(key) + 2) + 2) + 1) > 2) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) @@ -1466,7 +1466,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) + predicate: ((((UDFToInteger(key) + 2) + 2) + 1) > 2) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), value (type: string) @@ -1989,23 +1989,19 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1, _col2 + expressions: (UDFToInteger(_col0) + UDFToInteger(_col1)) (type: int), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToInteger(_col0) + UDFToInteger(_col1)) > 2) (type: boolean) + predicate: (_col0 > 2) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (UDFToInteger(_col0) + UDFToInteger(_col1)) (type: int), _col2 (type: double) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 1763 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 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/regex_col.q.out b/ql/src/test/results/clientpositive/regex_col.q.out index 70ec363..16be747 100644 --- a/ql/src/test/results/clientpositive/regex_col.q.out +++ b/ql/src/test/results/clientpositive/regex_col.q.out @@ -165,43 +165,35 @@ STAGE PLANS: alias: a Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) = 103.0) (type: boolean) + predicate: (key = 103) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: key (type: string), hr (type: string), ds (type: string) + sort order: +++ + Map-reduce partition columns: key (type: string), hr (type: string), ds (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: string), _col0 (type: string) - sort order: +++ - Map-reduce partition columns: _col1 (type: string), _col2 (type: string), _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TableScan alias: b Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) = 103.0) (type: boolean) + predicate: (key = 103) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: key (type: string), hr (type: string), ds (type: string) + sort order: +++ + Map-reduce partition columns: key (type: string), hr (type: string), ds (type: string) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: string), _col0 (type: string) - sort order: +++ - Map-reduce partition columns: _col1 (type: string), _col2 (type: string), _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string), _col2 (type: string), _col0 (type: string) - 1 _col1 (type: string), _col2 (type: string), _col0 (type: string) - outputColumnNames: _col4, _col5 + 0 key (type: string), hr (type: string), ds (type: string) + 1 key (type: string), hr (type: string), ds (type: string) + outputColumnNames: _col9, _col10 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col4 (type: string), _col5 (type: string) + expressions: _col9 (type: string), _col10 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/semijoin4.q.out b/ql/src/test/results/clientpositive/semijoin4.q.out index d6117ed..0b9a6fd 100644 --- a/ql/src/test/results/clientpositive/semijoin4.q.out +++ b/ql/src/test/results/clientpositive/semijoin4.q.out @@ -90,14 +90,15 @@ STAGE PLANS: predicate: ((tinyint_col_21 = -92) and tinyint_col_18 is not null and decimal2709_col_9 is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: decimal2709_col_9 (type: decimal(27,9)), tinyint_col_18 (type: tinyint) - outputColumnNames: _col0, _col1 + expressions: decimal2709_col_9 (type: decimal(27,9)), tinyint_col_18 (type: tinyint), -92 (type: tinyint) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(27,9)), UDFToLong(_col1) (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: decimal(27,9)), UDFToLong(_col1) (type: bigint) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col2 (type: tinyint) Reduce Operator Tree: Join Operator condition map: @@ -105,7 +106,7 @@ STAGE PLANS: keys: 0 _col4 (type: decimal(27,9)), _col0 (type: bigint) 1 _col0 (type: decimal(27,9)), UDFToLong(_col1) (type: bigint) - outputColumnNames: _col1, _col3 + outputColumnNames: _col1, _col3, _col7 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false @@ -121,7 +122,7 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: smallint), _col3 (type: double) + value expressions: _col1 (type: smallint), _col3 (type: double), _col7 (type: tinyint) TableScan Reduce Output Operator sort order: @@ -133,7 +134,7 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col1, _col3 + outputColumnNames: _col1, _col3, _col7 Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -147,27 +148,27 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: (UDFToShort(UDFToByte(-92)) + _col1) (type: smallint), floor(_col3) (type: bigint) + key expressions: (UDFToShort(_col7) + _col1) (type: smallint), floor(_col3) (type: bigint) sort order: +- - Map-reduce partition columns: (UDFToShort(UDFToByte(-92)) + _col1) (type: smallint) + Map-reduce partition columns: (UDFToShort(_col7) + _col1) (type: smallint) Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: smallint), _col3 (type: double) + value expressions: _col1 (type: smallint), _col3 (type: double), _col7 (type: tinyint) Reduce Operator Tree: Select Operator - expressions: VALUE._col1 (type: smallint), VALUE._col3 (type: double) - outputColumnNames: _col1, _col3 + expressions: VALUE._col1 (type: smallint), VALUE._col3 (type: double), VALUE._col7 (type: tinyint) + outputColumnNames: _col1, _col3, _col7 Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col1: smallint, _col3: double + output shape: _col1: smallint, _col3: double, _col7: tinyint type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: (UDFToShort(UDFToByte(-92)) + _col1) ASC NULLS FIRST, floor(_col3) DESC NULLS LAST - partition by: (UDFToShort(UDFToByte(-92)) + _col1) + order by: (UDFToShort(_col7) + _col1) ASC NULLS FIRST, floor(_col3) DESC NULLS LAST + partition by: (UDFToShort(_col7) + _col1) raw input shape: window functions: window function definition diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out index f72c2a7..9a1e2e2 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out @@ -95,12 +95,16 @@ STAGE PLANS: 0 1 Statistics: Num rows: 650 Data size: 5850 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: 5 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 650 Data size: 5850 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -109,10 +113,12 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 650 Data size: 5850 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) TableScan Reduce Output Operator sort order: Statistics: Num rows: 675 Data size: 6075 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator condition map: @@ -120,18 +126,15 @@ STAGE PLANS: keys: 0 1 + outputColumnNames: _col0, _col1 Statistics: Num rows: 438750 Data size: 8336250 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 5 (type: int), 5 (type: int) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 438750 Data size: 8336250 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 438750 Data size: 8336250 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 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce @@ -166,12 +169,16 @@ STAGE PLANS: 0 1 Statistics: Num rows: 675 Data size: 6075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: 5 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 675 Data size: 6075 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -243,12 +250,16 @@ STAGE PLANS: 0 1 Statistics: Num rows: 650 Data size: 5850 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: 5 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 650 Data size: 5850 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -279,18 +290,15 @@ STAGE PLANS: keys: 0 1 + outputColumnNames: _col0, _col1 Statistics: Num rows: 438750 Data size: 8336250 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 5 (type: int), 5 (type: int) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 438750 Data size: 8336250 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 438750 Data size: 8336250 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 + 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 Local Work: Map Reduce Local Work @@ -318,18 +326,15 @@ STAGE PLANS: keys: 0 1 + outputColumnNames: _col0, _col1 Statistics: Num rows: 438750 Data size: 8336250 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 5 (type: int), 5 (type: int) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 438750 Data size: 8336250 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 438750 Data size: 8336250 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 + 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 Local Work: Map Reduce Local Work @@ -340,10 +345,12 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 650 Data size: 5850 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) TableScan Reduce Output Operator sort order: Statistics: Num rows: 675 Data size: 6075 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator condition map: @@ -351,18 +358,15 @@ STAGE PLANS: keys: 0 1 + outputColumnNames: _col0, _col1 Statistics: Num rows: 438750 Data size: 8336250 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 5 (type: int), 5 (type: int) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 438750 Data size: 8336250 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 438750 Data size: 8336250 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 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-14 Map Reduce Local Work @@ -403,12 +407,16 @@ STAGE PLANS: 0 1 Statistics: Num rows: 675 Data size: 6075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: 5 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 675 Data size: 6075 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out index 0a7a36f..a0db9d0 100644 --- a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out +++ b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out @@ -284,7 +284,7 @@ STAGE PLANS: alias: part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (p_mfgr = p_mfgr) (type: boolean) + predicate: (p_size = p_size) (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -323,12 +323,16 @@ STAGE PLANS: predicate: (rank_window_0 <= 2) (type: boolean) Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE Select Operator +<<<<<<< HEAD expressions: _col1 (type: string), _col2 (type: string) +======= + expressions: _col2 (type: string), _col1 (type: string) +>>>>>>> clidriver golden file change outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0) - keys: _col1 (type: string) + aggregations: count(), count(_col1) + keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE @@ -450,7 +454,7 @@ STAGE PLANS: alias: part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (p_mfgr = p_mfgr) (type: boolean) + predicate: (p_size = p_size) (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) @@ -490,10 +494,10 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col1, _col0 Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: _col1 (type: string), _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/timestamp.q.out b/ql/src/test/results/clientpositive/timestamp.q.out index 9d0ceef..89ac01c 100644 --- a/ql/src/test/results/clientpositive/timestamp.q.out +++ b/ql/src/test/results/clientpositive/timestamp.q.out @@ -14,62 +14,58 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 2011-01-01 01:01:01.0 (type: timestamp) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 20000 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 1000 Data size: 40000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1000 Data size: 40000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: 2011-01-01 01:01:01.0 (type: timestamp) - mode: hash - outputColumnNames: _col0 + Group By Operator + keys: _col0 (type: timestamp) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: timestamp) + sort order: + + Map-reduce partition columns: _col0 (type: timestamp) Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: timestamp) - sort order: + - Map-reduce partition columns: _col0 (type: timestamp) - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + TopN Hash Memory Usage: 0.1 TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 2011-01-01 01:01:01.0 (type: timestamp) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 20000 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 1000 Data size: 40000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1000 Data size: 40000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: 2011-01-01 01:01:01.0 (type: timestamp) - mode: hash - outputColumnNames: _col0 + Group By Operator + keys: _col0 (type: timestamp) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: timestamp) + sort order: + + Map-reduce partition columns: _col0 (type: timestamp) Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: timestamp) - sort order: + - Map-reduce partition columns: _col0 (type: timestamp) - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: timestamp) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 2011-01-01 01:01:01.0 (type: timestamp) - outputColumnNames: _col0 + Limit + Number of rows: 5 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 5 + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -102,62 +98,58 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 2011-01-01 01:01:01.123 (type: timestamp) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 20000 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 1000 Data size: 40000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1000 Data size: 40000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: 2011-01-01 01:01:01.123 (type: timestamp) - mode: hash - outputColumnNames: _col0 + Group By Operator + keys: _col0 (type: timestamp) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: timestamp) + sort order: + + Map-reduce partition columns: _col0 (type: timestamp) Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: timestamp) - sort order: + - Map-reduce partition columns: _col0 (type: timestamp) - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + TopN Hash Memory Usage: 0.1 TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator + expressions: 2011-01-01 01:01:01.123 (type: timestamp) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 20000 Basic stats: COMPLETE Column stats: COMPLETE Union Statistics: Num rows: 1000 Data size: 40000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1000 Data size: 40000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: 2011-01-01 01:01:01.123 (type: timestamp) - mode: hash - outputColumnNames: _col0 + Group By Operator + keys: _col0 (type: timestamp) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: timestamp) + sort order: + + Map-reduce partition columns: _col0 (type: timestamp) Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: timestamp) - sort order: + - Map-reduce partition columns: _col0 (type: timestamp) - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: timestamp) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 2011-01-01 01:01:01.123 (type: timestamp) - outputColumnNames: _col0 + Limit + Number of rows: 5 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 5 + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_coalesce.q.out b/ql/src/test/results/clientpositive/vector_coalesce.q.out index f158236..fb70564 100644 --- a/ql/src/test/results/clientpositive/vector_coalesce.q.out +++ b/ql/src/test/results/clientpositive/vector_coalesce.q.out @@ -202,12 +202,23 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true +<<<<<<< HEAD projectedOutputColumns: [] Reduce Sink Vectorization: className: VectorReduceSinkOperator native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, No TopN IS false +======= + projectedOutputColumns: [12, 13, 14] + selectExpressions: ConstantVectorExpression(val null) -> 12:float, ConstantVectorExpression(val null) -> 13:bigint, ConstantVectorExpression(val 0.0) -> 14:double + Limit Vectorization: + className: VectorLimitOperator + native: true + File Sink Vectorization: + className: VectorFileSinkOperator + native: false +>>>>>>> clidriver golden file change Execution mode: vectorized Map Vectorization: enabled: true @@ -217,11 +228,6 @@ STAGE PLANS: allNative: false usesVectorUDFAdaptor: false vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: Stage: Stage-0 Fetch Operator @@ -371,12 +377,23 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true +<<<<<<< HEAD projectedOutputColumns: [] Reduce Sink Vectorization: className: VectorReduceSinkOperator native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, No TopN IS false +======= + projectedOutputColumns: [12, 13, 14] + selectExpressions: ConstantVectorExpression(val null) -> 12:float, ConstantVectorExpression(val null) -> 13:bigint, ConstantVectorExpression(val null) -> 14:float + Limit Vectorization: + className: VectorLimitOperator + native: true + File Sink Vectorization: + className: VectorFileSinkOperator + native: false +>>>>>>> clidriver golden file change Execution mode: vectorized Map Vectorization: enabled: true @@ -386,11 +403,6 @@ STAGE PLANS: allNative: false usesVectorUDFAdaptor: false vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_date_1.q.out b/ql/src/test/results/clientpositive/vector_date_1.q.out index c2389e6..6762374 100644 --- a/ql/src/test/results/clientpositive/vector_date_1.q.out +++ b/ql/src/test/results/clientpositive/vector_date_1.q.out @@ -594,26 +594,17 @@ STAGE PLANS: predicate: ((dt1 = 2001-01-01) and (2001-01-01 = dt1) and (dt1 <> 1970-01-01) and (1970-01-01 <> dt1) and (dt1 > 1970-01-01) and (dt1 >= 1970-01-01) and (1970-01-01 < dt1) and (1970-01-01 <= dt1)) (type: boolean) Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: dt2 (type: date) - outputColumnNames: _col1 + expressions: 2001-01-01 (type: date), dt2 (type: date) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: date) + 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 Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: 2001-01-01 (type: date), VALUE._col0 (type: date) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 74 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 Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_decimal_round.q.out b/ql/src/test/results/clientpositive/vector_decimal_round.q.out index de49c17..04f6d79 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_round.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_round.q.out @@ -137,15 +137,20 @@ STAGE PLANS: native: true projectedOutputColumns: [0] Select Operator +<<<<<<< HEAD expressions: dec (type: decimal(10,0)) outputColumnNames: _col0 Select Vectorization: className: VectorSelectOperator native: true projectedOutputColumns: [0] +======= + expressions: dec (type: decimal(10,0)), round(dec, -1) (type: decimal(11,0)) + outputColumnNames: _col0, _col2 +>>>>>>> clidriver golden file change Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: round(_col0, -1) (type: decimal(11,0)) + key expressions: _col2 (type: decimal(11,0)) sort order: + Reduce Sink Vectorization: className: VectorReduceSinkOperator @@ -309,11 +314,11 @@ STAGE PLANS: alias: decimal_tbl_rc Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: dec (type: decimal(10,0)) - outputColumnNames: _col0 + expressions: dec (type: decimal(10,0)), round(dec, -1) (type: decimal(11,0)) + outputColumnNames: _col0, _col2 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: round(_col0, -1) (type: decimal(11,0)) + key expressions: _col2 (type: decimal(11,0)) sort order: + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: decimal(10,0)) @@ -488,15 +493,16 @@ STAGE PLANS: native: true projectedOutputColumns: [0] Select Operator - expressions: dec (type: decimal(10,0)) - outputColumnNames: _col0 + expressions: dec (type: decimal(10,0)), round(dec, -1) (type: decimal(11,0)) + outputColumnNames: _col0, _col2 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumns: [0] + projectedOutputColumns: [0, 1] + selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 0, decimalPlaces -1) -> 1:decimal(11,0) Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: round(_col0, -1) (type: decimal(11,0)) + key expressions: _col2 (type: decimal(11,0)) sort order: + Reduce Sink Vectorization: className: VectorReduceSinkOperator diff --git a/ql/src/test/results/clientpositive/vector_interval_1.q.out b/ql/src/test/results/clientpositive/vector_interval_1.q.out index f53a2c2..007753a 100644 --- a/ql/src/test/results/clientpositive/vector_interval_1.q.out +++ b/ql/src/test/results/clientpositive/vector_interval_1.q.out @@ -72,7 +72,7 @@ STAGE PLANS: projectedOutputColumns: [0, 1, 2, 3] Select Operator expressions: str1 (type: string), CAST( str1 AS INTERVAL YEAR TO MONTH) (type: interval_year_month), CAST( str2 AS INTERVAL DAY TO SECOND) (type: interval_day_time) - outputColumnNames: _col0, _col2, _col4 + outputColumnNames: _col0, _col1, _col2 Select Vectorization: className: VectorSelectOperator native: true @@ -88,7 +88,7 @@ STAGE PLANS: nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: interval_year_month), _col4 (type: interval_day_time) + value expressions: _col1 (type: interval_year_month), _col2 (type: interval_day_time) Execution mode: vectorized Map Vectorization: enabled: true @@ -181,7 +181,7 @@ STAGE PLANS: projectedOutputColumns: [0, 1, 2, 3] Select Operator expressions: dt (type: date), (CAST( str1 AS INTERVAL YEAR TO MONTH) + CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: interval_year_month), (1-2 + CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: interval_year_month), (CAST( str1 AS INTERVAL YEAR TO MONTH) - CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: interval_year_month), (1-2 - CAST( str1 AS INTERVAL YEAR TO MONTH)) (type: interval_year_month) - outputColumnNames: _col0, _col2, _col3, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Select Vectorization: className: VectorSelectOperator native: true @@ -197,7 +197,7 @@ STAGE PLANS: nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: interval_year_month), _col3 (type: interval_year_month), _col5 (type: interval_year_month), _col6 (type: interval_year_month) + value expressions: _col1 (type: interval_year_month), _col2 (type: interval_year_month), _col3 (type: interval_year_month), _col4 (type: interval_year_month) Execution mode: vectorized Map Vectorization: enabled: true @@ -298,7 +298,7 @@ STAGE PLANS: projectedOutputColumns: [0, 1, 2, 3] Select Operator expressions: dt (type: date), (CAST( str2 AS INTERVAL DAY TO SECOND) + CAST( str2 AS INTERVAL DAY TO SECOND)) (type: interval_day_time), (1 02:03:04.000000000 + CAST( str2 AS INTERVAL DAY TO SECOND)) (type: interval_day_time), (CAST( str2 AS INTERVAL DAY TO SECOND) - CAST( str2 AS INTERVAL DAY TO SECOND)) (type: interval_day_time), (1 02:03:04.000000000 - CAST( str2 AS INTERVAL DAY TO SECOND)) (type: interval_day_time) - outputColumnNames: _col0, _col2, _col3, _col5, _col6 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Select Vectorization: className: VectorSelectOperator native: true @@ -314,7 +314,7 @@ STAGE PLANS: nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false Statistics: Num rows: 2 Data size: 442 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: interval_day_time), _col3 (type: interval_day_time), _col5 (type: interval_day_time), _col6 (type: interval_day_time) + value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time), _col4 (type: interval_day_time) Execution mode: vectorized Map Vectorization: enabled: true diff --git a/ql/src/test/results/clientpositive/vector_interval_arithmetic.q.out b/ql/src/test/results/clientpositive/vector_interval_arithmetic.q.out index 75250e3..b0aaba3 100644 --- a/ql/src/test/results/clientpositive/vector_interval_arithmetic.q.out +++ b/ql/src/test/results/clientpositive/vector_interval_arithmetic.q.out @@ -572,11 +572,15 @@ STAGE PLANS: native: true projectedOutputColumns: [0, 1] Select Operator + expressions: 5-5 (type: interval_year_month), -1-1 (type: interval_year_month) + outputColumnNames: _col0, _col1 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumns: [] + projectedOutputColumns: [2, 3] + selectExpressions: ConstantVectorExpression(val 65) -> 2:long, ConstantVectorExpression(val -13) -> 3:long Statistics: Num rows: 50 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE +<<<<<<< HEAD Reduce Output Operator key expressions: CAST( 5-5 AS INTERVAL YEAR TO MONTH) (type: interval_year_month) sort order: + @@ -587,6 +591,24 @@ STAGE PLANS: nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, No TopN IS false Statistics: Num rows: 50 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 +======= + Limit + Number of rows: 2 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +>>>>>>> clidriver golden file change Execution mode: vectorized Map Vectorization: enabled: true @@ -596,25 +618,6 @@ STAGE PLANS: allNative: false usesVectorUDFAdaptor: false vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: 5-5 (type: interval_year_month), -1-1 (type: interval_year_month) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 50 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 2 - Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/vector_null_projection.q.out b/ql/src/test/results/clientpositive/vector_null_projection.q.out index 94aea2f..358496b 100644 --- a/ql/src/test/results/clientpositive/vector_null_projection.q.out +++ b/ql/src/test/results/clientpositive/vector_null_projection.q.out @@ -163,17 +163,13 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: null (type: void) - outputColumnNames: _col0 + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 4 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 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/view_alias.q.out b/ql/src/test/results/clientpositive/view_alias.q.out index 90bf28d..1582f06 100644 --- a/ql/src/test/results/clientpositive/view_alias.q.out +++ b/ql/src/test/results/clientpositive/view_alias.q.out @@ -56,11 +56,11 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@v #### A masked pattern was here #### -165 12 -27 12 -311 12 -97 12 238 12 +86 12 +311 12 +27 12 +165 12 PREHOOK: query: drop view v PREHOOK: type: DROPVIEW PREHOOK: Input: default@v @@ -123,11 +123,11 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@v #### A masked pattern was here #### -165 12 -27 12 -311 12 -97 12 238 12 +86 12 +311 12 +27 12 +165 12 PREHOOK: query: drop view v PREHOOK: type: DROPVIEW PREHOOK: Input: default@v @@ -192,11 +192,11 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@v #### A masked pattern was here #### -165 val_165 12 -27 val_27 12 -311 val_311 12 -97 val_97 12 238 val_238 12 +86 val_86 12 +311 val_311 12 +27 val_27 12 +165 val_165 12 PREHOOK: query: drop view v PREHOOK: type: DROPVIEW PREHOOK: Input: default@v @@ -261,11 +261,11 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@v #### A masked pattern was here #### -165 val_165 12 -27 val_27 12 -311 val_311 12 -97 val_97 12 238 val_238 12 +86 val_86 12 +311 val_311 12 +27 val_27 12 +165 val_165 12 PREHOOK: query: drop view v PREHOOK: type: DROPVIEW PREHOOK: Input: default@v @@ -445,8 +445,8 @@ POSTHOOK: Input: default@a POSTHOOK: Input: default@b POSTHOOK: Input: default@v #### A masked pattern was here #### -010 86 val_86 121 86 val_86 234 -010 311 val_311 121 311 val_311 234 -010 27 val_27 121 27 val_27 234 -010 238 val_238 121 238 val_238 234 010 165 val_165 121 165 val_165 234 +010 238 val_238 121 238 val_238 234 +010 27 val_27 121 27 val_27 234 +010 311 val_311 121 311 val_311 234 +010 86 val_86 121 86 val_86 234 diff --git a/ql/src/test/results/clientpositive/windowing_duplicate.q.out b/ql/src/test/results/clientpositive/windowing_duplicate.q.out index c7b6d4f..a0deae6 100644 --- a/ql/src/test/results/clientpositive/windowing_duplicate.q.out +++ b/ql/src/test/results/clientpositive/windowing_duplicate.q.out @@ -36,4 +36,4 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@mytable1 POSTHOOK: Output: database:default POSTHOOK: Output: default@t1 -POSTHOOK: Lineage: t1.bound1 SCRIPT [(mytable1)mytable1.FieldSchema(name:mytime, type:timestamp, comment:null), (mytable1)mytable1.FieldSchema(name:string1, type:string, comment:null), ] +POSTHOOK: Lineage: t1.bound1 SCRIPT [(mytable1)mytable1.FieldSchema(name:string1, type:string, comment:null), (mytable1)mytable1.FieldSchema(name:mytime, type:timestamp, comment:null), ]