diff --git a/druid-handler/pom.xml b/druid-handler/pom.xml
index 6afb5b8..3f8a74f 100644
--- a/druid-handler/pom.xml
+++ b/druid-handler/pom.xml
@@ -222,6 +222,17 @@
org.apache.calcite
calcite-druid
${calcite.version}
+
+
+ org.apache.calcite.avatica
+ avatica-core
+
+
+
+
+ org.apache.calcite.avatica
+ avatica
+ ${avatica.version}
diff --git a/druid-handler/src/java/org/apache/hadoop/hive/druid/io/DruidQueryBasedInputFormat.java b/druid-handler/src/java/org/apache/hadoop/hive/druid/io/DruidQueryBasedInputFormat.java
index 0b35428..fe6c901 100644
--- a/druid-handler/src/java/org/apache/hadoop/hive/druid/io/DruidQueryBasedInputFormat.java
+++ b/druid-handler/src/java/org/apache/hadoop/hive/druid/io/DruidQueryBasedInputFormat.java
@@ -170,7 +170,8 @@ private static String createSelectStarQuery(String dataSource) throws IOExceptio
// Create Select query
SelectQueryBuilder builder = new Druids.SelectQueryBuilder();
builder.dataSource(dataSource);
- builder.intervals(Arrays.asList(DruidTable.DEFAULT_INTERVAL));
+ final List intervals = Arrays.asList();
+ builder.intervals(intervals);
builder.pagingSpec(PagingSpec.newSpec(1));
Map context = new HashMap<>();
context.put(Constants.DRUID_QUERY_FETCH, false);
@@ -413,11 +414,15 @@ private static String createSelectStarQuery(String dataSource) throws IOExceptio
private static List> createSplitsIntervals(List intervals, int numSplits
) {
- final long totalTime = DruidDateTimeUtils.extractTotalTime(intervals);
+
long startTime = intervals.get(0).getStartMillis();
long endTime = startTime;
long currTime = 0;
List> newIntervals = new ArrayList<>();
+ long totalTime = 0;
+ for (Interval interval: intervals) {
+ totalTime += interval.getEndMillis() - interval.getStartMillis();
+ }
for (int i = 0, posIntervals = 0; i < numSplits; i++) {
final long rangeSize = Math.round((double) (totalTime * (i + 1)) / numSplits) -
Math.round((double) (totalTime * i) / numSplits);
diff --git a/pom.xml b/pom.xml
index 400716f..5ec6bef 100644
--- a/pom.xml
+++ b/pom.xml
@@ -115,10 +115,10 @@
3.5.2
1.5.6
0.1
- 1.8.0
+ 1.9.0
1.7.7
0.8.0.RELEASE
- 1.10.0
+ 1.12.0
4.2.4
4.1.17
4.1.19
diff --git a/ql/pom.xml b/ql/pom.xml
index df70a7a..e5d063f 100644
--- a/ql/pom.xml
+++ b/ql/pom.xml
@@ -379,12 +379,22 @@
com.fasterxml.jackson.core
jackson-core
+
+ org.apache.calcite.avatica
+ avatica-core
+
org.apache.calcite
calcite-druid
${calcite.version}
+
+
+ org.apache.calcite.avatica
+ avatica-core
+
+
org.apache.calcite.avatica
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/metadata/HiveMaterializedViewsRegistry.java b/ql/src/java/org/apache/hadoop/hive/ql/metadata/HiveMaterializedViewsRegistry.java
index 1d78b4c..b121eea 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/metadata/HiveMaterializedViewsRegistry.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/metadata/HiveMaterializedViewsRegistry.java
@@ -34,6 +34,7 @@
import org.apache.calcite.adapter.druid.DruidQuery;
import org.apache.calcite.adapter.druid.DruidSchema;
import org.apache.calcite.adapter.druid.DruidTable;
+import org.apache.calcite.adapter.druid.LocalInterval;
import org.apache.calcite.jdbc.JavaTypeFactoryImpl;
import org.apache.calcite.plan.RelOptCluster;
import org.apache.calcite.plan.RelOptMaterialization;
@@ -310,7 +311,7 @@ private static RelNode createTableScan(Table viewTable) {
}
metrics.add(field.getName());
}
- List intervals = Arrays.asList(DruidTable.DEFAULT_INTERVAL);
+ List intervals = Arrays.asList(DruidTable.DEFAULT_INTERVAL);
DruidTable druidTable = new DruidTable(new DruidSchema(address, address, false),
dataSource, RelDataTypeImpl.proto(rowType), metrics, DruidTable.DEFAULT_TIMESTAMP_COLUMN, intervals);
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/CalciteSemanticException.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/CalciteSemanticException.java
index 0c6996c..8c43774 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/CalciteSemanticException.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/CalciteSemanticException.java
@@ -34,7 +34,8 @@
Having_clause_without_any_groupby, Invalid_column_reference, Invalid_decimal,
Less_than_equal_greater_than, Others, Same_name_in_multiple_expressions,
Schema_less_table, Select_alias_in_having_clause, Select_transform, Subquery,
- Table_sample_clauses, UDTF, Union_type, Unique_join
+ Table_sample_clauses, UDTF, Union_type, Unique_join,
+ HighPrecissionTimestamp // CALCITE-1690
};
private UnsupportedFeature unsupportedFeature;
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveCalciteUtil.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveCalciteUtil.java
index 6ccd879..e339d0a 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveCalciteUtil.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveCalciteUtil.java
@@ -48,6 +48,7 @@
import org.apache.calcite.rex.RexLocalRef;
import org.apache.calcite.rex.RexNode;
import org.apache.calcite.rex.RexOver;
+import org.apache.calcite.rex.RexPatternFieldRef;
import org.apache.calcite.rex.RexRangeRef;
import org.apache.calcite.rex.RexSubQuery;
import org.apache.calcite.rex.RexUtil;
@@ -1074,6 +1075,11 @@ public Boolean visitSubQuery(RexSubQuery subQuery) {
// it seems that it is not used by anything.
return false;
}
+
+ @Override
+ public Boolean visitPatternFieldRef(RexPatternFieldRef fieldRef) {
+ return false;
+ }
}
public static Set getInputRefs(RexNode expr) {
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HivePlannerContext.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HivePlannerContext.java
index 9a65de3..d0b1757 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HivePlannerContext.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HivePlannerContext.java
@@ -17,6 +17,7 @@
*/
package org.apache.hadoop.hive.ql.optimizer.calcite;
+import org.apache.calcite.config.CalciteConnectionConfig;
import org.apache.calcite.plan.Context;
import org.apache.calcite.rel.RelNode;
import org.apache.hadoop.hive.ql.optimizer.calcite.cost.HiveAlgorithmsConf;
@@ -27,11 +28,14 @@
public class HivePlannerContext implements Context {
private HiveAlgorithmsConf algoConfig;
private HiveRulesRegistry registry;
+ private CalciteConnectionConfig calciteConfig;
private Set corrScalarRexSQWithAgg;
- public HivePlannerContext(HiveAlgorithmsConf algoConfig, HiveRulesRegistry registry, Set corrScalarRexSQWithAgg) {
+ public HivePlannerContext(HiveAlgorithmsConf algoConfig, HiveRulesRegistry registry,
+ CalciteConnectionConfig calciteConfig, Set corrScalarRexSQWithAgg) {
this.algoConfig = algoConfig;
this.registry = registry;
+ this.calciteConfig = calciteConfig;
// this is to keep track if a subquery is correlated and contains aggregate
// this is computed in CalcitePlanner while planning and is later required by subuery remove rule
// hence this is passed using HivePlannerContext
@@ -45,6 +49,9 @@ public HivePlannerContext(HiveAlgorithmsConf algoConfig, HiveRulesRegistry regis
if (clazz.isInstance(registry)) {
return clazz.cast(registry);
}
+ if (clazz.isInstance(calciteConfig)) {
+ return clazz.cast(calciteConfig);
+ }
if(clazz.isInstance(corrScalarRexSQWithAgg)) {
return clazz.cast(corrScalarRexSQWithAgg);
}
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRelShuttleImpl.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRelShuttleImpl.java
index 2aadf50..8e52d88 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRelShuttleImpl.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRelShuttleImpl.java
@@ -27,6 +27,7 @@
import org.apache.calcite.rel.logical.LogicalFilter;
import org.apache.calcite.rel.logical.LogicalIntersect;
import org.apache.calcite.rel.logical.LogicalJoin;
+import org.apache.calcite.rel.logical.LogicalMatch;
import org.apache.calcite.rel.logical.LogicalMinus;
import org.apache.calcite.rel.logical.LogicalProject;
import org.apache.calcite.rel.logical.LogicalSort;
@@ -140,6 +141,10 @@ public RelNode visit(LogicalExchange exchange) {
public RelNode visit(RelNode other) {
return visitChildren(other);
}
+
+ public RelNode visit(LogicalMatch match) {
+ return visitChildren(match);
+ }
}
// End RelShuttleImpl.java
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/reloperators/HiveExtractDate.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/reloperators/HiveExtractDate.java
index 4edc4df..0b94b8a 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/reloperators/HiveExtractDate.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/reloperators/HiveExtractDate.java
@@ -24,6 +24,7 @@
import org.apache.calcite.sql.SqlKind;
import org.apache.calcite.sql.type.OperandTypes;
import org.apache.calcite.sql.type.ReturnTypes;
+import org.apache.calcite.sql.type.SqlTypeTransforms;
import com.google.common.collect.Sets;
@@ -42,9 +43,10 @@
Sets.newHashSet(YEAR, QUARTER, MONTH, WEEK, DAY, HOUR, MINUTE, SECOND);
private HiveExtractDate(String name) {
- super(name, SqlKind.EXTRACT, ReturnTypes.INTEGER_NULLABLE, null,
- OperandTypes.INTERVALINTERVAL_INTERVALDATETIME,
- SqlFunctionCategory.SYSTEM);
+ super(name, SqlKind.EXTRACT,
+ ReturnTypes.cascade(ReturnTypes.INTEGER, SqlTypeTransforms.FORCE_NULLABLE), null,
+ OperandTypes.INTERVALINTERVAL_INTERVALDATETIME,
+ SqlFunctionCategory.SYSTEM);
}
}
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterJoinRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterJoinRule.java
index 4b8568e..a4da6db 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterJoinRule.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterJoinRule.java
@@ -106,57 +106,6 @@ public void onMatch(RelOptRuleCall call) {
}
}
- /*
- * Any predicates pushed down to joinFilters that aren't equality conditions:
- * put them back as aboveFilters because Hive doesn't support not equi join
- * conditions.
- */
- @Override
- protected void validateJoinFilters(List aboveFilters, List joinFilters,
- Join join, JoinRelType joinType) {
- if (joinType.equals(JoinRelType.INNER)) {
- ListIterator filterIter = joinFilters.listIterator();
- while (filterIter.hasNext()) {
- RexNode exp = filterIter.next();
-
- if (exp instanceof RexCall) {
- RexCall c = (RexCall) exp;
- boolean validHiveJoinFilter = false;
-
- if ((c.getOperator().getKind() == SqlKind.EQUALS)) {
- validHiveJoinFilter = true;
- for (RexNode rn : c.getOperands()) {
- // NOTE: Hive dis-allows projections from both left & right side
- // of join condition. Example: Hive disallows
- // (r1.x +r2.x)=(r1.y+r2.y) on join condition.
- if (filterRefersToBothSidesOfJoin(rn, join)) {
- validHiveJoinFilter = false;
- break;
- }
- }
- } else if ((c.getOperator().getKind() == SqlKind.LESS_THAN)
- || (c.getOperator().getKind() == SqlKind.GREATER_THAN)
- || (c.getOperator().getKind() == SqlKind.LESS_THAN_OR_EQUAL)
- || (c.getOperator().getKind() == SqlKind.GREATER_THAN_OR_EQUAL)) {
- validHiveJoinFilter = true;
- // NOTE: Hive dis-allows projections from both left & right side of
- // join in in equality condition. Example: Hive disallows (r1.x <
- // r2.x) on join condition.
- if (filterRefersToBothSidesOfJoin(c, join)) {
- validHiveJoinFilter = false;
- }
- }
-
- if (validHiveJoinFilter)
- continue;
- }
-
- aboveFilters.add(exp);
- filterIter.remove();
- }
- }
- }
-
private boolean filterRefersToBothSidesOfJoin(RexNode filter, Join j) {
boolean refersToBothSides = false;
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HivePointLookupOptimizerRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HivePointLookupOptimizerRule.java
index 4cfe782..f3d7293 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HivePointLookupOptimizerRule.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HivePointLookupOptimizerRule.java
@@ -55,36 +55,89 @@
import com.google.common.collect.Maps;
import com.google.common.collect.Multimap;
import com.google.common.collect.Sets;
+import org.apache.calcite.plan.RelOptRuleOperand;
+import org.apache.calcite.rel.AbstractRelNode;
+import org.apache.calcite.rel.core.Join;
+import org.apache.calcite.rel.core.JoinRelType;
+
+
+public abstract class HivePointLookupOptimizerRule extends RelOptRule {
/**
- * This optimization will take a Filter expression, and if its predicate contains
+ * This optimization will take a Filter or expression, and if its predicate contains
* an OR operator whose children are constant equality expressions, it will try
* to generate an IN clause (which is more efficient). If the OR operator contains
* AND operator children, the optimization might generate an IN clause that uses
* structs.
*/
-public class HivePointLookupOptimizerRule extends RelOptRule {
+ public static class FilterCondition extends HivePointLookupOptimizerRule {
+ public FilterCondition (int minNumORClauses) {
+ super(operand(Filter.class, any()), minNumORClauses);
+ }
- protected static final Log LOG = LogFactory.getLog(HivePointLookupOptimizerRule.class);
+ public void onMatch(RelOptRuleCall call) {
+ final Filter filter = call.rel(0);
+ final RexBuilder rexBuilder = filter.getCluster().getRexBuilder();
+ final RexNode condition = RexUtil.pullFactors(rexBuilder, filter.getCondition());
+ analyzeCondition(call , rexBuilder, filter, condition);
+ }
+ @Override protected RelNode copyNode(AbstractRelNode node, RexNode newCondition) {
+ final Filter filter = (Filter) node;
+ return filter.copy(filter.getTraitSet(), filter.getInput(), newCondition);
+ }
+ }
- // Minimum number of OR clauses needed to transform into IN clauses
- private final int minNumORClauses;
+/**
+ * This optimization will take a Join or expression, and if its join condition contains
+ * an OR operator whose children are constant equality expressions, it will try
+ * to generate an IN clause (which is more efficient). If the OR operator contains
+ * AND operator children, the optimization might generate an IN clause that uses
+ * structs.
+ */
+ public static class JoinCondition extends HivePointLookupOptimizerRule {
+ public JoinCondition (int minNumORClauses) {
+ super(operand(Join.class, any()), minNumORClauses);
+ }
+
+ public void onMatch(RelOptRuleCall call) {
+ final Join join = call.rel(0);
+ final RexBuilder rexBuilder = join.getCluster().getRexBuilder();
+ final RexNode condition = RexUtil.pullFactors(rexBuilder, join.getCondition());
+ analyzeCondition(call , rexBuilder, join, condition);
+ }
- public HivePointLookupOptimizerRule(int minNumORClauses) {
- super(operand(Filter.class, any()));
- this.minNumORClauses = minNumORClauses;
+ @Override protected RelNode copyNode(AbstractRelNode node, RexNode newCondition) {
+ final Join join = (Join) node;
+ return join.copy(join.getTraitSet(),
+ newCondition,
+ join.getLeft(),
+ join.getRight(),
+ join.getJoinType(),
+ join.isSemiJoinDone());
+ }
}
- public void onMatch(RelOptRuleCall call) {
- final Filter filter = call.rel(0);
+ protected static final Log LOG = LogFactory.getLog(HivePointLookupOptimizerRule.class);
- final RexBuilder rexBuilder = filter.getCluster().getRexBuilder();
+ // Minimum number of OR clauses needed to transform into IN clauses
+ protected final int minNumORClauses;
+
+ protected abstract RelNode copyNode(AbstractRelNode node, RexNode newCondition);
+
+ protected HivePointLookupOptimizerRule(
+ RelOptRuleOperand operand, int minNumORClauses) {
+ super(operand);
+ this.minNumORClauses = minNumORClauses;
+ }
- final RexNode condition = RexUtil.pullFactors(rexBuilder, filter.getCondition());
+ public void analyzeCondition(RelOptRuleCall call,
+ RexBuilder rexBuilder,
+ AbstractRelNode node,
+ RexNode condition) {
// 1. We try to transform possible candidates
- RexTransformIntoInClause transformIntoInClause = new RexTransformIntoInClause(rexBuilder, filter,
+ RexTransformIntoInClause transformIntoInClause = new RexTransformIntoInClause(rexBuilder, node,
minNumORClauses);
RexNode newCondition = transformIntoInClause.apply(condition);
@@ -97,10 +150,10 @@ public void onMatch(RelOptRuleCall call) {
return;
}
- // 4. We create the filter with the new condition
- RelNode newFilter = filter.copy(filter.getTraitSet(), filter.getInput(), newCondition);
+ // 4. We create the Filter/Join with the new condition
+ RelNode newNode = copyNode(node, newCondition);
- call.transformTo(newFilter);
+ call.transformTo(newNode);
}
@@ -109,11 +162,11 @@ public void onMatch(RelOptRuleCall call) {
*/
protected static class RexTransformIntoInClause extends RexShuttle {
private final RexBuilder rexBuilder;
- private final Filter filterOp;
+ private final AbstractRelNode nodeOp;
private final int minNumORClauses;
- RexTransformIntoInClause(RexBuilder rexBuilder, Filter filterOp, int minNumORClauses) {
- this.filterOp = filterOp;
+ RexTransformIntoInClause(RexBuilder rexBuilder, AbstractRelNode nodeOp, int minNumORClauses) {
+ this.nodeOp = nodeOp;
this.rexBuilder = rexBuilder;
this.minNumORClauses = minNumORClauses;
}
@@ -129,7 +182,7 @@ public void onMatch(RelOptRuleCall call) {
if (operand.getKind() == SqlKind.OR) {
try {
newOperand = transformIntoInClauseCondition(rexBuilder,
- filterOp.getRowType(), operand, minNumORClauses);
+ nodeOp.getRowType(), operand, minNumORClauses);
if (newOperand == null) {
newOperand = operand;
}
@@ -147,7 +200,7 @@ public void onMatch(RelOptRuleCall call) {
case OR:
try {
node = transformIntoInClauseCondition(rexBuilder,
- filterOp.getRowType(), call, minNumORClauses);
+ nodeOp.getRowType(), call, minNumORClauses);
if (node == null) {
return call;
}
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/views/HiveMaterializedViewFilterScanRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/views/HiveMaterializedViewFilterScanRule.java
index 38d7906..81de33f 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/views/HiveMaterializedViewFilterScanRule.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/views/HiveMaterializedViewFilterScanRule.java
@@ -21,6 +21,7 @@
import java.util.List;
import org.apache.calcite.plan.RelOptMaterialization;
+import org.apache.calcite.plan.RelOptMaterializations;
import org.apache.calcite.plan.RelOptPlanner;
import org.apache.calcite.plan.RelOptRule;
import org.apache.calcite.plan.RelOptRuleCall;
@@ -77,7 +78,7 @@ protected void apply(RelOptRuleCall call, Project project, Filter filter, TableS
// Costing is done in transformTo(), so we call it repeatedly with all applicable
// materialized views and cheapest one will be picked
List applicableMaterializations =
- VolcanoPlanner.getApplicableMaterializations(root, materializations);
+ RelOptMaterializations.getApplicableMaterializations(root, materializations);
for (RelOptMaterialization materialization : applicableMaterializations) {
List subs = new MaterializedViewSubstitutionVisitor(
materialization.queryRel, root, relBuilderFactory).go(materialization.tableRel);
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/stats/HiveRelMdPredicates.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/stats/HiveRelMdPredicates.java
index 69e157e..9bcdd0c 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/stats/HiveRelMdPredicates.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/stats/HiveRelMdPredicates.java
@@ -165,7 +165,7 @@ public RelOptPredicateList getPredicates(Project project, RelMetadataQuery mq) {
rexBuilder.makeInputRef(project, expr.i), expr.e));
}
}
- return RelOptPredicateList.of(projectPullUpPredicates);
+ return RelOptPredicateList.of(rexBuilder, projectPullUpPredicates);
}
/** Infers predicates for a {@link org.apache.calcite.rel.core.Join}. */
@@ -202,6 +202,7 @@ public RelOptPredicateList getPredicates(Aggregate agg, RelMetadataQuery mq) {
final RelNode input = agg.getInput();
final RelOptPredicateList inputInfo = mq.getPulledUpPredicates(input);
final List aggPullUpPredicates = new ArrayList<>();
+ final RexBuilder rexBuilder = agg.getCluster().getRexBuilder();
ImmutableBitSet groupKeys = agg.getGroupSet();
Mapping m = Mappings.create(MappingType.PARTIAL_FUNCTION,
@@ -219,7 +220,7 @@ public RelOptPredicateList getPredicates(Aggregate agg, RelMetadataQuery mq) {
aggPullUpPredicates.add(r);
}
}
- return RelOptPredicateList.of(aggPullUpPredicates);
+ return RelOptPredicateList.of(rexBuilder, aggPullUpPredicates);
}
/**
@@ -271,7 +272,7 @@ public RelOptPredicateList getPredicates(Union union, RelMetadataQuery mq) {
if (!disjPred.isAlwaysTrue()) {
preds.add(disjPred);
}
- return RelOptPredicateList.of(preds);
+ return RelOptPredicateList.of(rB, preds);
}
/**
@@ -411,6 +412,7 @@ public RelOptPredicateList inferPredicates(
final JoinRelType joinType = joinRel.getJoinType();
final List leftPreds = ImmutableList.copyOf(RelOptUtil.conjunctions(leftChildPredicates));
final List rightPreds = ImmutableList.copyOf(RelOptUtil.conjunctions(rightChildPredicates));
+ final RexBuilder rexBuilder = joinRel.getCluster().getRexBuilder();
switch (joinType) {
case INNER:
case LEFT:
@@ -476,13 +478,13 @@ public RelOptPredicateList inferPredicates(
pulledUpPredicates = Iterables.concat(leftPreds, rightPreds,
RelOptUtil.conjunctions(joinRel.getCondition()), inferredPredicates);
}
- return RelOptPredicateList.of(
+ return RelOptPredicateList.of(rexBuilder,
pulledUpPredicates, leftInferredPredicates, rightInferredPredicates);
case LEFT:
- return RelOptPredicateList.of(
+ return RelOptPredicateList.of(rexBuilder,
leftPreds, EMPTY_LIST, rightInferredPredicates);
case RIGHT:
- return RelOptPredicateList.of(
+ return RelOptPredicateList.of(rexBuilder,
rightPreds, leftInferredPredicates, EMPTY_LIST);
default:
assert inferredPredicates.size() == 0;
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ASTBuilder.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ASTBuilder.java
index 0dc0c24..a43d2be 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ASTBuilder.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ASTBuilder.java
@@ -37,6 +37,8 @@
import org.apache.hadoop.hive.ql.parse.HiveParser;
import org.apache.hadoop.hive.ql.parse.ParseDriver;
import org.apache.hadoop.hive.ql.parse.SemanticAnalyzer;
+import org.joda.time.DateTime;
+import org.joda.time.DateTimeZone;
public class ASTBuilder {
@@ -269,19 +271,23 @@ public static ASTNode literal(RexLiteral literal, boolean useTypeQualInLiteral)
type = ((Boolean) val).booleanValue() ? HiveParser.KW_TRUE : HiveParser.KW_FALSE;
break;
case DATE: {
- val = literal.getValue();
+ //Calcite Calendar is always GMT, Hive atm uses JVM local
+ final Calendar c = (Calendar) literal.getValue();
+ final DateTime dt = new DateTime(c.getTimeInMillis(), DateTimeZone.forTimeZone(c.getTimeZone()));
type = HiveParser.TOK_DATELITERAL;
DateFormat df = new SimpleDateFormat("yyyy-MM-dd");
- val = df.format(((Calendar) val).getTime());
+ val = df.format(dt.toDateTime(DateTimeZone.getDefault()).toDate());
val = "'" + val + "'";
}
break;
case TIME:
case TIMESTAMP: {
- val = literal.getValue();
+ //Calcite Calendar is always GMT, Hive atm uses JVM local
+ final Calendar c = (Calendar) literal.getValue();
+ final DateTime dt = new DateTime(c.getTimeInMillis(), DateTimeZone.forTimeZone(c.getTimeZone()));
type = HiveParser.TOK_TIMESTAMPLITERAL;
DateFormat df = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.SSS");
- val = df.format(((Calendar) val).getTime());
+ val = df.format(dt.toDateTime(DateTimeZone.getDefault()).toDate());
val = "'" + val + "'";
}
break;
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ASTConverter.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ASTConverter.java
index 27990a2..165f8c4 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ASTConverter.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ASTConverter.java
@@ -24,7 +24,6 @@
import java.util.Map;
import org.apache.calcite.adapter.druid.DruidQuery;
-import org.apache.calcite.avatica.util.TimeUnitRange;
import org.apache.calcite.rel.RelFieldCollation;
import org.apache.calcite.rel.RelNode;
import org.apache.calcite.rel.RelVisitor;
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ExprNodeConverter.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ExprNodeConverter.java
index e840938..b1efbbd 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ExprNodeConverter.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/ExprNodeConverter.java
@@ -18,7 +18,6 @@
package org.apache.hadoop.hive.ql.optimizer.calcite.translator;
import java.math.BigDecimal;
-import java.sql.Date;
import java.sql.Timestamp;
import java.util.ArrayList;
import java.util.Calendar;
@@ -75,6 +74,8 @@
import org.apache.hadoop.hive.serde2.typeinfo.StructTypeInfo;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoFactory;
+import org.joda.time.DateTime;
+import org.joda.time.DateTimeZone;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@@ -291,16 +292,17 @@ public ExprNodeDesc visitLiteral(RexLiteral literal) {
case DOUBLE:
return new ExprNodeConstantDesc(TypeInfoFactory.doubleTypeInfo,
Double.valueOf(((Number) literal.getValue3()).doubleValue()));
- case DATE:
+ case DATE: {
+ final Calendar c = (Calendar) literal.getValue();
return new ExprNodeConstantDesc(TypeInfoFactory.dateTypeInfo,
- new Date(((Calendar)literal.getValue()).getTimeInMillis()));
+ new java.sql.Date(c.getTimeInMillis()));
+ }
case TIME:
case TIMESTAMP: {
- Object value = literal.getValue3();
- if (value instanceof Long) {
- value = new Timestamp((Long)value);
- }
- return new ExprNodeConstantDesc(TypeInfoFactory.timestampTypeInfo, value);
+ final Calendar c = (Calendar) literal.getValue();
+ final DateTime dt = new DateTime(c.getTimeInMillis(), DateTimeZone.forTimeZone(c.getTimeZone()));
+ return new ExprNodeConstantDesc(TypeInfoFactory.timestampTypeInfo,
+ new Timestamp(dt.getMillis()));
}
case BINARY:
return new ExprNodeConstantDesc(TypeInfoFactory.binaryTypeInfo, literal.getValue3());
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/RexNodeConverter.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/RexNodeConverter.java
index a05b89c..52ca3b0 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/RexNodeConverter.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/RexNodeConverter.java
@@ -23,11 +23,12 @@
import java.util.ArrayList;
import java.util.Calendar;
import java.util.Date;
-import java.util.GregorianCalendar;
import java.util.LinkedHashMap;
import java.util.List;
+import java.util.Locale;
import java.util.Map;
+import org.apache.calcite.avatica.util.DateTimeUtils;
import org.apache.calcite.avatica.util.TimeUnit;
import org.apache.calcite.avatica.util.TimeUnitRange;
import org.apache.calcite.plan.RelOptCluster;
@@ -38,8 +39,8 @@
import org.apache.calcite.rex.RexBuilder;
import org.apache.calcite.rex.RexCall;
import org.apache.calcite.rex.RexNode;
-import org.apache.calcite.rex.RexUtil;
import org.apache.calcite.rex.RexSubQuery;
+import org.apache.calcite.rex.RexUtil;
import org.apache.calcite.sql.SqlCollation;
import org.apache.calcite.sql.SqlIntervalQualifier;
import org.apache.calcite.sql.SqlKind;
@@ -76,8 +77,10 @@
import org.apache.hadoop.hive.ql.udf.generic.GenericUDF;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDFBaseBinary;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDFBaseCompare;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDFBetween;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDFCase;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDFIn;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDFTimestamp;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDFToBinary;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDFToChar;
@@ -96,6 +99,8 @@
import org.apache.hadoop.hive.serde2.typeinfo.PrimitiveTypeInfo;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils;
+import org.joda.time.DateTime;
+import org.joda.time.DateTimeZone;
import com.google.common.collect.ImmutableList;
import com.google.common.collect.ImmutableList.Builder;
@@ -248,6 +253,8 @@ private RexNode convert(ExprNodeGenericFuncDesc func) throws SemanticException {
boolean isWhenCase = tgtUdf instanceof GenericUDFWhen || tgtUdf instanceof GenericUDFCase;
boolean isTransformableTimeStamp = func.getGenericUDF() instanceof GenericUDFUnixTimeStamp &&
func.getChildren().size() != 0;
+ boolean isBetween = !isNumeric && tgtUdf instanceof GenericUDFBetween;
+ boolean isIN = !isNumeric && tgtUdf instanceof GenericUDFIn;
if (isNumeric) {
tgtDT = func.getTypeInfo();
@@ -266,15 +273,33 @@ private RexNode convert(ExprNodeGenericFuncDesc func) throws SemanticException {
} else if (isTransformableTimeStamp) {
// unix_timestamp(args) -> to_unix_timestamp(args)
func = ExprNodeGenericFuncDesc.newInstance(new GenericUDFToUnixTimeStamp(), func.getChildren());
+ } else if (isBetween) {
+ assert func.getChildren().size() == 4;
+ // We skip first child as is not involved (is the revert boolean)
+ // The target type needs to account for all 3 operands
+ tgtDT = FunctionRegistry.getCommonClassForComparison(
+ func.getChildren().get(1).getTypeInfo(),
+ FunctionRegistry.getCommonClassForComparison(
+ func.getChildren().get(2).getTypeInfo(),
+ func.getChildren().get(3).getTypeInfo()));
+ } else if (isIN) {
+ // We're only considering the first element of the IN list for the type
+ assert func.getChildren().size() > 1;
+ tgtDT = FunctionRegistry.getCommonClassForComparison(func.getChildren().get(0)
+ .getTypeInfo(), func.getChildren().get(1).getTypeInfo());
}
- for (ExprNodeDesc childExpr : func.getChildren()) {
+ for (int i =0; i < func.getChildren().size(); ++i) {
+ ExprNodeDesc childExpr = func.getChildren().get(i);
tmpExprNode = childExpr;
if (tgtDT != null
&& TypeInfoUtils.isConversionRequiredForComparison(tgtDT, childExpr.getTypeInfo())) {
- if (isCompare) {
+ if (isCompare || isBetween || isIN) {
// For compare, we will convert requisite children
- tmpExprNode = ParseUtils.createConversionCast(childExpr, (PrimitiveTypeInfo) tgtDT);
+ // For BETWEEN skip the first child (the revert boolean)
+ if (!isBetween || i > 0) {
+ tmpExprNode = ParseUtils.createConversionCast(childExpr, (PrimitiveTypeInfo) tgtDT);
+ }
} else if (isNumeric) {
// For numeric, we'll do minimum necessary cast - if we cast to the type
// of expression, bad things will happen.
@@ -634,20 +659,40 @@ protected RexNode convert(ExprNodeConstantDesc literal) throws CalciteSemanticEx
calciteLiteral = rexBuilder.makeCharLiteral(asUnicodeString((String) value));
break;
case DATE:
- Calendar cal = new GregorianCalendar();
- cal.setTime((Date) value);
- calciteLiteral = rexBuilder.makeDateLiteral(cal);
- break;
- case TIMESTAMP:
- Calendar c = null;
- if (value instanceof Calendar) {
- c = (Calendar)value;
- } else {
- c = Calendar.getInstance();
- c.setTimeInMillis(((Timestamp)value).getTime());
- }
- calciteLiteral = rexBuilder.makeTimestampLiteral(c, RelDataType.PRECISION_NOT_SPECIFIED);
- break;
+ // The Calcite literal is in GMT, this will be converted back to JVM locale
+ // by ASTBuilder.literal during Calcite->Hive plan conversion
+ final Calendar cal = Calendar.getInstance(DateTimeUtils.GMT_ZONE, Locale.getDefault());
+ cal.setTime((Date) value);
+ calciteLiteral = rexBuilder.makeDateLiteral(cal);
+ break;
+ case TIMESTAMP:
+ // The Calcite literal is in GMT, this will be converted back to JVM locale
+ // by ASTBuilder.literal during Calcite->Hive plan conversion
+ final Calendar calt = Calendar.getInstance(DateTimeUtils.GMT_ZONE, Locale.getDefault());
+ if (value instanceof Calendar) {
+ final Calendar c = (Calendar) value;
+ long timeMs = c.getTimeInMillis();
+ calt.setTimeInMillis(timeMs);
+ } else {
+ final Timestamp ts = (Timestamp) value;
+ // CALCITE-1690
+ // Calcite cannot represent TIMESTAMP literals with precision higher than 3
+ if (ts.getNanos() % 1000000 != 0) {
+ throw new CalciteSemanticException(
+ "High Precision Timestamp: " + String.valueOf(ts),
+ UnsupportedFeature.HighPrecissionTimestamp);
+ }
+ calt.setTimeInMillis(ts.getTime());
+ }
+ // Must call makeLiteral, not makeTimestampLiteral
+ // to have the RexBuilder.roundTime logic kick in
+ calciteLiteral = rexBuilder.makeLiteral(
+ calt,
+ rexBuilder.getTypeFactory().createSqlType(
+ SqlTypeName.TIMESTAMP,
+ rexBuilder.getTypeFactory().getTypeSystem().getDefaultPrecision(SqlTypeName.TIMESTAMP)),
+ false);
+ break;
case INTERVAL_YEAR_MONTH:
// Calcite year-month literal value is months as BigDecimal
BigDecimal totalMonths = BigDecimal.valueOf(((HiveIntervalYearMonth) value).getTotalMonths());
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/ReduceSinkDeDuplication.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/ReduceSinkDeDuplication.java
index 2b075be..701bde4 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/ReduceSinkDeDuplication.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/ReduceSinkDeDuplication.java
@@ -194,7 +194,7 @@ protected boolean merge(ReduceSinkOperator cRS, JoinOperator pJoin, int minReduc
ReduceSinkDesc cRSc = cRS.getConf();
for (ReduceSinkOperator pRSNs : pRSs) {
ReduceSinkDesc pRSNc = pRSNs.getConf();
- if (cRSc.getKeyCols().size() < pRSNc.getKeyCols().size()) {
+ if (cRSc.getKeyCols().size() != pRSNc.getKeyCols().size()) {
return false;
}
if (cRSc.getPartitionCols().size() != pRSNc.getPartitionCols().size()) {
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 79662ec..67ea05d 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
@@ -38,6 +38,7 @@
import java.util.LinkedList;
import java.util.List;
import java.util.Map;
+import java.util.Properties;
import java.util.Set;
import java.util.concurrent.atomic.AtomicBoolean;
import java.util.concurrent.atomic.AtomicInteger;
@@ -50,10 +51,12 @@
import org.apache.calcite.adapter.druid.DruidRules;
import org.apache.calcite.adapter.druid.DruidSchema;
import org.apache.calcite.adapter.druid.DruidTable;
+import org.apache.calcite.adapter.druid.LocalInterval;
+import org.apache.calcite.config.CalciteConnectionConfigImpl;
+import org.apache.calcite.config.CalciteConnectionProperty;
import org.apache.calcite.plan.RelOptCluster;
import org.apache.calcite.plan.RelOptMaterialization;
import org.apache.calcite.plan.RelOptPlanner;
-import org.apache.calcite.plan.RelOptPlanner.Executor;
import org.apache.calcite.plan.RelOptRule;
import org.apache.calcite.plan.RelOptSchema;
import org.apache.calcite.plan.RelOptUtil;
@@ -93,6 +96,7 @@
import org.apache.calcite.rel.type.RelDataTypeField;
import org.apache.calcite.rel.type.RelDataTypeImpl;
import org.apache.calcite.rex.RexBuilder;
+import org.apache.calcite.rex.RexExecutor;
import org.apache.calcite.rex.RexFieldCollation;
import org.apache.calcite.rex.RexInputRef;
import org.apache.calcite.rex.RexNode;
@@ -245,7 +249,6 @@
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoFactory;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils;
-import org.joda.time.Interval;
import com.google.common.base.Function;
import com.google.common.collect.ArrayListMultimap;
@@ -254,6 +257,7 @@
import com.google.common.collect.ImmutableMap;
import com.google.common.collect.Lists;
import com.google.common.collect.Multimap;
+import org.apache.calcite.config.CalciteConnectionConfig;
public class CalcitePlanner extends SemanticAnalyzer {
@@ -1299,7 +1303,13 @@ public RelNode apply(RelOptCluster cluster, RelOptSchema relOptSchema, SchemaPlu
conf, HiveConf.ConfVars.HIVECONVERTJOINNOCONDITIONALTASKTHRESHOLD);
HiveAlgorithmsConf algorithmsConf = new HiveAlgorithmsConf(maxSplitSize, maxMemory);
HiveRulesRegistry registry = new HiveRulesRegistry();
- HivePlannerContext confContext = new HivePlannerContext(algorithmsConf, registry, corrScalarRexSQWithAgg);
+ Properties calciteConfigProperties = new Properties();
+ calciteConfigProperties.setProperty(
+ CalciteConnectionProperty.MATERIALIZATIONS_ENABLED.camelName(),
+ Boolean.FALSE.toString());
+ CalciteConnectionConfig calciteConfig = new CalciteConnectionConfigImpl(calciteConfigProperties);
+ HivePlannerContext confContext = new HivePlannerContext(algorithmsConf, registry, calciteConfig,
+ corrScalarRexSQWithAgg);
RelOptPlanner planner = HiveVolcanoPlanner.createPlanner(confContext);
final RexBuilder rexBuilder = cluster.getRexBuilder();
final RelOptCluster optCluster = RelOptCluster.create(planner, rexBuilder);
@@ -1324,10 +1334,15 @@ public RelNode apply(RelOptCluster cluster, RelOptSchema relOptSchema, SchemaPlu
}
perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER, "Calcite: Plan generation");
+ // Create executor
+ RexExecutor executorProvider = new HiveRexExecutorImpl(optCluster);
+ calciteGenPlan.getCluster().getPlanner().setExecutor(executorProvider);
+
// We need to get the ColumnAccessInfo and viewToTableSchema for views.
HiveRelFieldTrimmer fieldTrimmer = new HiveRelFieldTrimmer(null,
HiveRelFactories.HIVE_BUILDER.create(optCluster, null), this.columnAccessInfo,
this.viewProjectToTableSchema);
+
fieldTrimmer.trim(calciteGenPlan);
// Create and set MD provider
@@ -1335,9 +1350,6 @@ public RelNode apply(RelOptCluster cluster, RelOptSchema relOptSchema, SchemaPlu
RelMetadataQuery.THREAD_PROVIDERS.set(
JaninoRelMetadataProvider.of(mdProvider.getMetadataProvider()));
- // Create executor
- Executor executorProvider = new HiveRexExecutorImpl(optCluster);
-
//Remove subquery
LOG.debug("Plan before removing subquery:\n" + RelOptUtil.toString(calciteGenPlan));
calciteGenPlan = hepPlan(calciteGenPlan, false, mdProvider.getMetadataProvider(), null,
@@ -1503,9 +1515,9 @@ public RelOptMaterialization apply(RelOptMaterialization materialization) {
// 9. Apply Druid transformation rules
perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.OPTIMIZER);
calciteOptimizedPlan = hepPlan(calciteOptimizedPlan, false, mdProvider.getMetadataProvider(), null,
- HepMatchOrder.BOTTOM_UP, DruidRules.FILTER, DruidRules.PROJECT_AGGREGATE,
- DruidRules.PROJECT, DruidRules.AGGREGATE, DruidRules.PROJECT_SORT,
- DruidRules.SORT, DruidRules.SORT_PROJECT);
+ HepMatchOrder.BOTTOM_UP, DruidRules.FILTER, DruidRules.AGGREGATE_PROJECT,
+ DruidRules.PROJECT, DruidRules.AGGREGATE, DruidRules.SORT_PROJECT_TRANSPOSE,
+ DruidRules.SORT, DruidRules.PROJECT_SORT_TRANSPOSE);
perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER, "Calcite: Druid transformation rules");
// 10. Run rules to aid in translation from Calcite tree to Hive tree
@@ -1559,7 +1571,7 @@ public RelOptMaterialization apply(RelOptMaterialization materialization) {
* executor
* @return
*/
- private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProvider mdProvider, Executor executorProvider) {
+ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProvider mdProvider, RexExecutor executorProvider) {
// TODO: Decorelation of subquery should be done before attempting
// Partition Pruning; otherwise Expression evaluation may try to execute
// corelated sub query.
@@ -1577,13 +1589,13 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv
"Calcite: HiveProjectOverIntersectRemoveRule and HiveIntersectMerge rules");
perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.OPTIMIZER);
- basePlan = hepPlan(basePlan, false, mdProvider, null, HepMatchOrder.BOTTOM_UP,
+ basePlan = hepPlan(basePlan, false, mdProvider, executorProvider, HepMatchOrder.BOTTOM_UP,
HiveIntersectRewriteRule.INSTANCE);
perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER,
"Calcite: HiveIntersectRewrite rule");
perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.OPTIMIZER);
- basePlan = hepPlan(basePlan, false, mdProvider, null, HepMatchOrder.BOTTOM_UP,
+ basePlan = hepPlan(basePlan, false, mdProvider, executorProvider, HepMatchOrder.BOTTOM_UP,
HiveExceptRewriteRule.INSTANCE);
perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER,
"Calcite: HiveExceptRewrite rule");
@@ -1596,7 +1608,7 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv
// Its not clear, if this rewrite is always performant on MR, since extra map phase
// introduced for 2nd MR job may offset gains of this multi-stage aggregation.
// We need a cost model for MR to enable this on MR.
- basePlan = hepPlan(basePlan, true, mdProvider, null, HiveExpandDistinctAggregatesRule.INSTANCE);
+ basePlan = hepPlan(basePlan, true, mdProvider, executorProvider, HiveExpandDistinctAggregatesRule.INSTANCE);
perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER,
"Calcite: Prejoin ordering transformation, Distinct aggregate rewrite");
}
@@ -1607,7 +1619,7 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv
// Ex: select * from R1 join R2 where ((R1.x=R2.x) and R1.y<10) or
// ((R1.x=R2.x) and R1.z=10)) and rand(1) < 0.1
perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.OPTIMIZER);
- basePlan = hepPlan(basePlan, false, mdProvider, null, HepMatchOrder.ARBITRARY,
+ basePlan = hepPlan(basePlan, false, mdProvider, executorProvider, HepMatchOrder.ARBITRARY,
new HivePreFilteringRule(maxCNFNodeCount));
perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER,
"Calcite: Prejoin ordering transformation, factor out common filter elements and separating deterministic vs non-deterministic UDF");
@@ -1634,7 +1646,8 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv
rules.add(HiveReduceExpressionsRule.FILTER_INSTANCE);
rules.add(HiveReduceExpressionsRule.JOIN_INSTANCE);
if (conf.getBoolVar(HiveConf.ConfVars.HIVEPOINTLOOKUPOPTIMIZER)) {
- rules.add(new HivePointLookupOptimizerRule(minNumORClauses));
+ rules.add(new HivePointLookupOptimizerRule.FilterCondition(minNumORClauses));
+ rules.add(new HivePointLookupOptimizerRule.JoinCondition(minNumORClauses));
}
rules.add(HiveJoinAddNotNullRule.INSTANCE_JOIN);
rules.add(HiveJoinAddNotNullRule.INSTANCE_SEMIJOIN);
@@ -1662,10 +1675,10 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv
HiveConf.ConfVars.HIVE_OPTIMIZE_LIMIT_TRANSPOSE_REDUCTION_PERCENTAGE);
final long reductionTuples = HiveConf.getLongVar(conf,
HiveConf.ConfVars.HIVE_OPTIMIZE_LIMIT_TRANSPOSE_REDUCTION_TUPLES);
- basePlan = hepPlan(basePlan, true, mdProvider, null, HiveSortMergeRule.INSTANCE,
+ basePlan = hepPlan(basePlan, true, mdProvider, executorProvider, HiveSortMergeRule.INSTANCE,
HiveSortProjectTransposeRule.INSTANCE, HiveSortJoinReduceRule.INSTANCE,
HiveSortUnionReduceRule.INSTANCE);
- basePlan = hepPlan(basePlan, true, mdProvider, null, HepMatchOrder.BOTTOM_UP,
+ basePlan = hepPlan(basePlan, true, mdProvider, executorProvider, HepMatchOrder.BOTTOM_UP,
new HiveSortRemoveRule(reductionProportion, reductionTuples),
HiveProjectSortTransposeRule.INSTANCE);
perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER,
@@ -1674,14 +1687,14 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv
// 5. Push Down Semi Joins
perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.OPTIMIZER);
- basePlan = hepPlan(basePlan, true, mdProvider, null, SemiJoinJoinTransposeRule.INSTANCE,
+ basePlan = hepPlan(basePlan, true, mdProvider, executorProvider, SemiJoinJoinTransposeRule.INSTANCE,
SemiJoinFilterTransposeRule.INSTANCE, SemiJoinProjectTransposeRule.INSTANCE);
perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER,
"Calcite: Prejoin ordering transformation, Push Down Semi Joins");
// 6. Apply Partition Pruning
perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.OPTIMIZER);
- basePlan = hepPlan(basePlan, false, mdProvider, null, new HivePartitionPruneRule(conf));
+ basePlan = hepPlan(basePlan, false, mdProvider, executorProvider, new HivePartitionPruneRule(conf));
perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER,
"Calcite: Prejoin ordering transformation, Partition Pruning");
@@ -1696,7 +1709,7 @@ 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, null,
+ basePlan = hepPlan(basePlan, false, mdProvider, executorProvider,
HiveProjectMergeRule.INSTANCE, ProjectRemoveRule.INSTANCE);
perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER,
"Calcite: Prejoin ordering transformation, Merge Project-Project");
@@ -1706,7 +1719,7 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv
// storage (incase there are filters on non partition cols). This only
// matches FIL-PROJ-TS
perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.OPTIMIZER);
- basePlan = hepPlan(basePlan, true, mdProvider, null,
+ basePlan = hepPlan(basePlan, true, mdProvider, executorProvider,
HiveFilterProjectTSTransposeRule.INSTANCE, HiveFilterProjectTSTransposeRule.INSTANCE_DRUID,
HiveProjectFilterPullUpConstantsRule.INSTANCE);
perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER,
@@ -1726,7 +1739,7 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv
* @return optimized RelNode
*/
private RelNode hepPlan(RelNode basePlan, boolean followPlanChanges,
- RelMetadataProvider mdProvider, Executor executorProvider, RelOptRule... rules) {
+ RelMetadataProvider mdProvider, RexExecutor executorProvider, RelOptRule... rules) {
return hepPlan(basePlan, followPlanChanges, mdProvider, executorProvider,
HepMatchOrder.TOP_DOWN, rules);
}
@@ -1743,7 +1756,7 @@ private RelNode hepPlan(RelNode basePlan, boolean followPlanChanges,
* @return optimized RelNode
*/
private RelNode hepPlan(RelNode basePlan, boolean followPlanChanges,
- RelMetadataProvider mdProvider, Executor executorProvider, HepMatchOrder order,
+ RelMetadataProvider mdProvider, RexExecutor executorProvider, HepMatchOrder order,
RelOptRule... rules) {
RelNode optimizedRelNode = basePlan;
@@ -1769,7 +1782,10 @@ private RelNode hepPlan(RelNode basePlan, boolean followPlanChanges,
new CachingRelMetadataProvider(chainedProvider, planner));
if (executorProvider != null) {
+ // basePlan.getCluster.getPlanner is the VolcanoPlanner from apply()
+ // both planners need to use the correct executor
basePlan.getCluster().getPlanner().setExecutor(executorProvider);
+ planner.setExecutor(executorProvider);
}
planner.setRoot(basePlan);
@@ -2284,7 +2300,7 @@ private RelNode genTableLogicalPlan(String tableAlias, QB qb) throws SemanticExc
}
metrics.add(field.getName());
}
- List intervals = Arrays.asList(DruidTable.DEFAULT_INTERVAL);
+ List intervals = Arrays.asList(DruidTable.DEFAULT_INTERVAL);
DruidTable druidTable = new DruidTable(new DruidSchema(address, address, false),
dataSource, RelDataTypeImpl.proto(rowType), metrics, DruidTable.DEFAULT_TIMESTAMP_COLUMN, intervals);
@@ -4200,5 +4216,4 @@ private QBParseInfo getQBParseInfo(QB qb) throws CalciteSemanticException {
DRUID,
NATIVE
}
-
}
diff --git a/ql/src/test/org/apache/hadoop/hive/ql/optimizer/calcite/TestCBORuleFiredOnlyOnce.java b/ql/src/test/org/apache/hadoop/hive/ql/optimizer/calcite/TestCBORuleFiredOnlyOnce.java
index 7229cc7..4823950 100644
--- a/ql/src/test/org/apache/hadoop/hive/ql/optimizer/calcite/TestCBORuleFiredOnlyOnce.java
+++ b/ql/src/test/org/apache/hadoop/hive/ql/optimizer/calcite/TestCBORuleFiredOnlyOnce.java
@@ -61,7 +61,7 @@ public void testRuleFiredOnlyOnce() {
// Create rules registry to not trigger a rule more than once
HiveRulesRegistry registry = new HiveRulesRegistry();
- HivePlannerContext context = new HivePlannerContext(null, registry, null);
+ HivePlannerContext context = new HivePlannerContext(null, registry, null, null);
HepPlanner planner = new HepPlanner(programBuilder.build(), context);
// Cluster
diff --git a/ql/src/test/results/clientnegative/subquery_scalar_multi_rows.q.out b/ql/src/test/results/clientnegative/subquery_scalar_multi_rows.q.out
index 92f1365..0a780db 100644
--- a/ql/src/test/results/clientnegative/subquery_scalar_multi_rows.q.out
+++ b/ql/src/test/results/clientnegative/subquery_scalar_multi_rows.q.out
@@ -1,5 +1,4 @@
-Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product
-Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: select p_name from part where p_size > (select p_size from part)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
diff --git a/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out b/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out
index fe4bc4f..a2f5dbf 100644
--- a/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out
+++ b/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out
@@ -1023,7 +1023,7 @@ STAGE PLANS:
alias: subq1:a
Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: (key + 1) (type: int)
@@ -1126,7 +1126,7 @@ STAGE PLANS:
alias: subq2:a
Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: (key + 1) (type: int)
diff --git a/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out b/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out
index 0bb18cc..6d6a38a 100644
--- a/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out
@@ -28,36 +28,44 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: key, value
- 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
- value expressions: value (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: value (type: string)
+ auto parallelism: false
TableScan
alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: key, value, ds
- Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: value (type: string), ds (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 12 Data size: 127 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: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: value (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -203,153 +211,46 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart
name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
Truncated Path -> Alias:
/src [a]
/srcpart/ds=2008-04-08/hr=11 [b]
/srcpart/ds=2008-04-08/hr=12 [b]
- /srcpart/ds=2008-04-09/hr=11 [b]
- /srcpart/ds=2008-04-09/hr=12 [b]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
- Outer Join 0 to 1
- filter mappings:
- 1 [0, 1]
- filter predicates:
- 0
- 1 {(VALUE.ds = '2008-04-08')}
+ Inner Join 0 to 1
keys:
0 key (type: string)
1 key (type: string)
outputColumnNames: key, value, key0, value0
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string)
- outputColumnNames: key, value, key0, value0
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key0) > 15.0) and (UDFToDouble(key0) < 25.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 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 key,value,key0,value0
- columns.types string:string:string:string
- 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
+ outputColumnNames: key, value, key1, value1
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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 key,value,key1,value1
+ columns.types string:string:string:string
+ 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
@@ -369,8 +270,6 @@ PREHOOK: Input: default@src
PREHOOK: Input: default@srcpart
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
POSTHOOK: query: FROM
src a
@@ -384,8 +283,6 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
17 val_17 17 val_17
17 val_17 17 val_17
@@ -431,18 +328,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: value (type: string)
auto parallelism: false
@@ -452,18 +349,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: value (type: string)
auto parallelism: false
@@ -620,42 +517,38 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Right Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 key (type: string)
1 key (type: string)
outputColumnNames: key, value, key0, value0
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string)
- outputColumnNames: key, value, key0, value0
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 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 key,value,key0,value0
- columns.types string:string:string:string
- 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
+ outputColumnNames: key, value, key1, value1
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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 key,value,key1,value1
+ columns.types string:string:string:string
+ 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/constprog2.q.out b/ql/src/test/results/clientpositive/constprog2.q.out
index 7bfd0cf..cbc5fd2 100644
--- a/ql/src/test/results/clientpositive/constprog2.q.out
+++ b/ql/src/test/results/clientpositive/constprog2.q.out
@@ -67,6 +67,7 @@ STAGE PLANS:
Processor Tree:
ListSink
+Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: EXPLAIN
SELECT src1.key, src1.key + 1, src2.value
FROM srcbucket src1 join srcbucket src2 ON src1.key = src2.key AND cast(src1.key as double) = 86
@@ -90,28 +91,22 @@ STAGE PLANS:
predicate: (UDFToDouble(key) = 86.0) (type: boolean)
Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ sort order:
Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE
TableScan
alias: src2
Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (UDFToDouble(key) = 86.0) (type: boolean)
+ predicate: (86 = key) (type: boolean)
Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
+ expressions: value (type: string)
+ outputColumnNames: _col1
Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ sort order:
Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Reduce Operator Tree:
@@ -119,17 +114,17 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0, _col2
- Statistics: Num rows: 550 Data size: 5831 Basic stats: COMPLETE Column stats: NONE
+ 0
+ 1
+ outputColumnNames: _col2
+ Statistics: Num rows: 250000 Data size: 5551000 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col0 (type: int), (_col0 + 1) (type: int), _col2 (type: string)
+ expressions: 86 (type: int), 87 (type: int), _col2 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 550 Data size: 5831 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250000 Data size: 5551000 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 550 Data size: 5831 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250000 Data size: 5551000 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
diff --git a/ql/src/test/results/clientpositive/druid_basic2.q.out b/ql/src/test/results/clientpositive/druid_basic2.q.out
index 495ebbe..ebbaec1 100644
--- a/ql/src/test/results/clientpositive/druid_basic2.q.out
+++ b/ql/src/test/results/clientpositive/druid_basic2.q.out
@@ -77,7 +77,7 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
@@ -104,7 +104,7 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":[],"metrics":["delta"],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":[],"metrics":["delta"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
@@ -135,7 +135,7 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
@@ -166,7 +166,7 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":["robot"],"limitSpec":{"type":"default"},"filter":{"type":"selector","dimension":"language","value":"en"},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":["robot"],"limitSpec":{"type":"default"},"filter":{"type":"selector","dimension":"language","value":"en"},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]}
druid.query.type groupBy
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
@@ -212,7 +212,7 @@ STAGE PLANS:
alias: druid_table_1
filterExpr: language is not null (type: boolean)
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
@@ -237,7 +237,7 @@ STAGE PLANS:
alias: druid_table_1
filterExpr: language is not null (type: boolean)
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
@@ -274,7 +274,7 @@ STAGE PLANS:
columns.comments 'from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer'
columns.types timestamp:string:string:string:string:string:string:string:string:float:float:float:float:float
druid.datasource wikipedia
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
#### A masked pattern was here ####
name default.druid_table_1
@@ -300,7 +300,7 @@ STAGE PLANS:
columns.comments 'from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer'
columns.types timestamp:string:string:string:string:string:string:string:string:float:float:float:float:float
druid.datasource wikipedia
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
#### A masked pattern was here ####
name default.druid_table_1
@@ -399,7 +399,7 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
GatherStats: false
@@ -414,7 +414,7 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
@@ -442,7 +442,7 @@ STAGE PLANS:
columns.comments 'from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer'
columns.types timestamp:string:string:string:string:string:string:string:string:float:float:float:float:float
druid.datasource wikipedia
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
#### A masked pattern was here ####
name default.druid_table_1
@@ -468,7 +468,7 @@ STAGE PLANS:
columns.comments 'from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer'
columns.types timestamp:string:string:string:string:string:string:string:string:float:float:float:float:float
druid.datasource wikipedia
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
#### A masked pattern was here ####
name default.druid_table_1
@@ -545,8 +545,7 @@ LIMIT 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -554,27 +553,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: druid_table_1
+ properties:
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"day","dimensions":["robot","language"],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]}
+ druid.query.type groupBy
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
Select Operator
- expressions: __time (type: timestamp), robot (type: string), language (type: string), added (type: float), delta (type: float)
- outputColumnNames: __time, robot, language, added, delta
+ expressions: robot (type: string), __time (type: timestamp), $f3 (type: float), $f4 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Group By Operator
- aggregations: max(added), sum(delta)
- keys: robot (type: string), language (type: string), floor_day(__time) (type: timestamp)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Reduce Output Operator
+ key expressions: UDFToInteger(_col0) (type: int), _col2 (type: float)
+ null sort order: az
+ sort order: +-
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: timestamp)
- null sort order: aaa
- sort order: +++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: timestamp)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- tag: -1
- value expressions: _col3 (type: float), _col4 (type: double)
- auto parallelism: false
+ tag: -1
+ TopN: 10
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: string), _col1 (type: timestamp), _col3 (type: float)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -592,6 +589,8 @@ STAGE PLANS:
columns.comments 'from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer'
columns.types timestamp:string:string:string:string:string:string:string:string:float:float:float:float:float
druid.datasource wikipedia
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"day","dimensions":["robot","language"],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]}
+ druid.query.type groupBy
#### A masked pattern was here ####
name default.druid_table_1
numFiles 0
@@ -616,6 +615,8 @@ STAGE PLANS:
columns.comments 'from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer'
columns.types timestamp:string:string:string:string:string:string:string:string:float:float:float:float:float
druid.datasource wikipedia
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"day","dimensions":["robot","language"],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]}
+ druid.query.type groupBy
#### A masked pattern was here ####
name default.druid_table_1
numFiles 0
@@ -634,81 +635,8 @@ STAGE PLANS:
/druid_table_1 [druid_table_1]
Needs Tagging: false
Reduce Operator Tree:
- Group By Operator
- aggregations: max(VALUE._col0), sum(VALUE._col1)
- keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: timestamp)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col2 (type: timestamp), _col3 (type: float), _col4 (type: double)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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,_col2,_col3
- columns.types string,timestamp,float,double
- 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
- Map Operator Tree:
- TableScan
- GatherStats: false
- Reduce Output Operator
- key expressions: UDFToInteger(_col0) (type: int), _col2 (type: float)
- null sort order: az
- sort order: +-
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- tag: -1
- TopN: 10
- TopN Hash Memory Usage: 0.1
- value expressions: _col0 (type: string), _col1 (type: timestamp), _col3 (type: double)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: -mr-10004
- 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 string,timestamp,float,double
- escape.delim \
- serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- 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 string,timestamp,float,double
- escape.delim \
- serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Truncated Path -> Alias:
-#### A masked pattern was here ####
- Needs Tagging: false
- Reduce Operator Tree:
Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: timestamp), KEY.reducesinkkey1 (type: float), VALUE._col2 (type: double)
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: timestamp), KEY.reducesinkkey1 (type: float), VALUE._col2 (type: float)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Limit
@@ -726,7 +654,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
properties:
columns _col0,_col1,_col2,_col3
- columns.types string:timestamp:float:double
+ columns.types string:timestamp:float:float
escape.delim \
hive.serialization.extend.additional.nesting.levels true
serialization.escape.crlf true
diff --git a/ql/src/test/results/clientpositive/druid_intervals.q.out b/ql/src/test/results/clientpositive/druid_intervals.q.out
index ca3febf..dc520b7 100644
--- a/ql/src/test/results/clientpositive/druid_intervals.q.out
+++ b/ql/src/test/results/clientpositive/druid_intervals.q.out
@@ -79,7 +79,7 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
@@ -109,7 +109,7 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/2012-03-01T00:00:00.000Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/2012-03-01T08:00:00.000"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
@@ -139,7 +139,7 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T00:00:00.000Z/2012-03-01T00:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000/2012-03-01T08:00:00.001"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
@@ -171,7 +171,7 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T00:00:00.000Z/2011-01-01T00:00:00.000Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000/2011-01-01T08:00:00.000"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
@@ -191,24 +191,40 @@ FROM druid_table_1
WHERE `__time` BETWEEN '2010-01-01 00:00:00' AND '2011-01-01 00:00:00'
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ 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: druid_table_1
+ filterExpr: __time BETWEEN 2010-01-01 00:00:00.0 AND 2011-01-01 00:00:00.0 (type: boolean)
+ properties:
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
+ druid.query.type select
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: __time BETWEEN 2010-01-01 00:00:00.0 AND 2011-01-01 00:00:00.0 (type: boolean)
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: __time (type: timestamp)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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:
- TableScan
- alias: druid_table_1
- properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T00:00:00.000Z/2011-01-01T00:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
- druid.query.type select
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: __time (type: timestamp)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: EXPLAIN
SELECT `__time`
@@ -233,7 +249,7 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T00:00:00.000Z/2011-01-01T00:00:00.001Z","2012-01-01T00:00:00.000Z/2013-01-01T00:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":[],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
@@ -265,7 +281,7 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T00:00:00.000Z/2012-01-01T00:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":[],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
@@ -285,24 +301,40 @@ FROM druid_table_1
WHERE `__time` IN ('2010-01-01 00:00:00','2011-01-01 00:00:00')
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ 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: druid_table_1
+ filterExpr: (__time) IN (2010-01-01 00:00:00.0, 2011-01-01 00:00:00.0) (type: boolean)
+ properties:
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
+ druid.query.type select
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (__time) IN (2010-01-01 00:00:00.0, 2011-01-01 00:00:00.0) (type: boolean)
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: __time (type: timestamp)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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:
- TableScan
- alias: druid_table_1
- properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T00:00:00.000Z/2010-01-01T00:00:00.001Z","2011-01-01T00:00:00.000Z/2011-01-01T00:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
- druid.query.type select
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: __time (type: timestamp)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: EXPLAIN
SELECT `__time`, robot
@@ -315,24 +347,40 @@ FROM druid_table_1
WHERE robot = 'user1' AND `__time` IN ('2010-01-01 00:00:00','2011-01-01 00:00:00')
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ 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: druid_table_1
+ filterExpr: ((__time) IN (2010-01-01 00:00:00.0, 2011-01-01 00:00:00.0) and (robot = 'user1')) (type: boolean)
+ properties:
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
+ druid.query.type select
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: ((__time) IN (2010-01-01 00:00:00.0, 2011-01-01 00:00:00.0) and (robot = 'user1')) (type: boolean)
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: __time (type: timestamp), 'user1' (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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:
- TableScan
- alias: druid_table_1
- properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T00:00:00.000Z/2010-01-01T00:00:00.001Z","2011-01-01T00:00:00.000Z/2011-01-01T00:00:00.001Z"],"filter":{"type":"selector","dimension":"robot","value":"user1"},"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
- druid.query.type select
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: __time (type: timestamp), 'user1' (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: EXPLAIN
SELECT `__time`, robot
@@ -354,13 +402,13 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: druid_table_1
- filterExpr: ((__time) IN ('2010-01-01 00:00:00', '2011-01-01 00:00:00') or (robot = 'user1')) (type: boolean)
+ filterExpr: ((__time) IN (2010-01-01 00:00:00.0, 2011-01-01 00:00:00.0) or (robot = 'user1')) (type: boolean)
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: ((__time) IN ('2010-01-01 00:00:00', '2011-01-01 00:00:00') or (robot = 'user1')) (type: boolean)
+ predicate: ((__time) IN (2010-01-01 00:00:00.0, 2011-01-01 00:00:00.0) or (robot = 'user1')) (type: boolean)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: __time (type: timestamp), robot (type: string)
diff --git a/ql/src/test/results/clientpositive/druid_timeseries.q.out b/ql/src/test/results/clientpositive/druid_timeseries.q.out
index 6b2ffe9..4ecf67f 100644
--- a/ql/src/test/results/clientpositive/druid_timeseries.q.out
+++ b/ql/src/test/results/clientpositive/druid_timeseries.q.out
@@ -79,11 +79,11 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"all","aggregations":[{"type":"longMax","name":"$f0","fieldName":"added"},{"type":"doubleSum","name":"$f1","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"all","aggregations":[{"type":"doubleMax","name":"$f0","fieldName":"added"},{"type":"doubleSum","name":"$f1","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: $f0 (type: bigint), $f1 (type: float)
+ expressions: $f0 (type: float), $f1 (type: float)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
ListSink
@@ -109,11 +109,11 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"NONE","aggregations":[{"type":"longMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"none","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: __time (type: timestamp), $f1 (type: bigint), $f2 (type: float)
+ expressions: __time (type: timestamp), $f1 (type: float), $f2 (type: float)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
ListSink
@@ -139,11 +139,11 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"YEAR","aggregations":[{"type":"longMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"year","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: __time (type: timestamp), $f1 (type: bigint), $f2 (type: float)
+ expressions: __time (type: timestamp), $f1 (type: float), $f2 (type: float)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
ListSink
@@ -169,11 +169,11 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"QUARTER","aggregations":[{"type":"longMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"quarter","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: __time (type: timestamp), $f1 (type: bigint), $f2 (type: float)
+ expressions: __time (type: timestamp), $f1 (type: float), $f2 (type: float)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
ListSink
@@ -199,11 +199,11 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"MONTH","aggregations":[{"type":"longMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"month","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: __time (type: timestamp), $f1 (type: bigint), $f2 (type: float)
+ expressions: __time (type: timestamp), $f1 (type: float), $f2 (type: float)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
ListSink
@@ -229,11 +229,11 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"WEEK","aggregations":[{"type":"longMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"week","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: __time (type: timestamp), $f1 (type: bigint), $f2 (type: float)
+ expressions: __time (type: timestamp), $f1 (type: float), $f2 (type: float)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
ListSink
@@ -259,11 +259,11 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"DAY","aggregations":[{"type":"longMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"day","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: __time (type: timestamp), $f1 (type: bigint), $f2 (type: float)
+ expressions: __time (type: timestamp), $f1 (type: float), $f2 (type: float)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
ListSink
@@ -289,11 +289,11 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"HOUR","aggregations":[{"type":"longMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"hour","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: __time (type: timestamp), $f1 (type: bigint), $f2 (type: float)
+ expressions: __time (type: timestamp), $f1 (type: float), $f2 (type: float)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
ListSink
@@ -319,11 +319,11 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"MINUTE","aggregations":[{"type":"longMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"minute","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: __time (type: timestamp), $f1 (type: bigint), $f2 (type: float)
+ expressions: __time (type: timestamp), $f1 (type: float), $f2 (type: float)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
ListSink
@@ -349,11 +349,11 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"SECOND","aggregations":[{"type":"longMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"second","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: __time (type: timestamp), $f1 (type: bigint), $f2 (type: float)
+ expressions: __time (type: timestamp), $f1 (type: float), $f2 (type: float)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
ListSink
@@ -381,11 +381,11 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"HOUR","filter":{"type":"selector","dimension":"robot","value":"1"},"aggregations":[{"type":"longMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"hour","filter":{"type":"selector","dimension":"robot","value":"1"},"aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: __time (type: timestamp), $f1 (type: bigint), $f2 (type: float)
+ expressions: __time (type: timestamp), $f1 (type: float), $f2 (type: float)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
ListSink
@@ -418,7 +418,7 @@ STAGE PLANS:
alias: druid_table_1
filterExpr: floor_hour(__time) BETWEEN 2010-01-01 00:00:00.0 AND 2014-01-01 00:00:00.0 (type: boolean)
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Filter Operator
@@ -495,7 +495,7 @@ STAGE PLANS:
alias: druid_table_1
filterExpr: floor_hour(__time) BETWEEN 2010-01-01 00:00:00.0 AND 2014-01-01 00:00:00.0 (type: boolean)
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Filter Operator
diff --git a/ql/src/test/results/clientpositive/druid_topn.q.out b/ql/src/test/results/clientpositive/druid_topn.q.out
index 57d6586..387c4c3 100644
--- a/ql/src/test/results/clientpositive/druid_topn.q.out
+++ b/ql/src/test/results/clientpositive/druid_topn.q.out
@@ -85,11 +85,11 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"topN","dataSource":"wikipedia","granularity":"all","dimension":"robot","metric":"$f1","aggregations":[{"type":"longMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"threshold":100}
- druid.query.type topN
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":["robot"],"limitSpec":{"type":"default","limit":100,"columns":[{"dimension":"$f1","direction":"descending"}]},"aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]}
+ druid.query.type groupBy
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: robot (type: string), $f1 (type: bigint), $f2 (type: float)
+ expressions: robot (type: string), $f1 (type: float), $f2 (type: float)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
ListSink
@@ -109,24 +109,54 @@ ORDER BY s DESC
LIMIT 100
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: druid_table_1
+ properties:
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"none","dimensions":["robot"],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f2","fieldName":"added"},{"type":"doubleSum","name":"$f3","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]}
+ druid.query.type groupBy
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: __time (type: timestamp), robot (type: string), $f2 (type: float), $f3 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col3 (type: float)
+ sort order: -
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: float)
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: timestamp), VALUE._col1 (type: string), VALUE._col2 (type: float), KEY.reducesinkkey0 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col0 (type: timestamp), _col2 (type: float), _col3 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
- TableScan
- alias: druid_table_1
- properties:
- druid.query.json {"queryType":"topN","dataSource":"wikipedia","granularity":"NONE","dimension":"robot","metric":"$f3","aggregations":[{"type":"longMax","name":"$f2","fieldName":"added"},{"type":"doubleSum","name":"$f3","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"threshold":100}
- druid.query.type topN
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: robot (type: string), __time (type: timestamp), $f2 (type: bigint), $f3 (type: float)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: EXPLAIN
SELECT robot, floor_year(`__time`), max(added), sum(variation) as s
@@ -143,24 +173,50 @@ ORDER BY s DESC
LIMIT 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: druid_table_1
+ properties:
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"year","dimensions":["robot"],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f2","fieldName":"added"},{"type":"doubleSum","name":"$f3","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]}
+ druid.query.type groupBy
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: robot (type: string), __time (type: timestamp), $f2 (type: float), $f3 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col3 (type: float)
+ sort order: -
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: string), _col1 (type: timestamp), _col2 (type: float)
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: timestamp), VALUE._col2 (type: float), KEY.reducesinkkey0 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
Stage: Stage-0
Fetch Operator
- limit: -1
+ limit: 10
Processor Tree:
- TableScan
- alias: druid_table_1
- properties:
- druid.query.json {"queryType":"topN","dataSource":"wikipedia","granularity":"YEAR","dimension":"robot","metric":"$f3","aggregations":[{"type":"longMax","name":"$f2","fieldName":"added"},{"type":"doubleSum","name":"$f3","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"threshold":10}
- druid.query.type topN
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: robot (type: string), __time (type: timestamp), $f2 (type: bigint), $f3 (type: float)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: EXPLAIN
SELECT robot, floor_month(`__time`), max(added), sum(variation) as s
@@ -177,24 +233,50 @@ ORDER BY s
LIMIT 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: druid_table_1
+ properties:
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"month","dimensions":["robot"],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f2","fieldName":"added"},{"type":"doubleSum","name":"$f3","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]}
+ druid.query.type groupBy
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: robot (type: string), __time (type: timestamp), $f2 (type: float), $f3 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col3 (type: float)
+ sort order: +
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: string), _col1 (type: timestamp), _col2 (type: float)
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: timestamp), VALUE._col2 (type: float), KEY.reducesinkkey0 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
Stage: Stage-0
Fetch Operator
- limit: -1
+ limit: 10
Processor Tree:
- TableScan
- alias: druid_table_1
- properties:
- druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"MONTH","dimensions":["robot"],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f3","direction":"ascending"}]},"aggregations":[{"type":"longMax","name":"$f2","fieldName":"added"},{"type":"doubleSum","name":"$f3","fieldName":"variation"}],"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
- Select Operator
- expressions: robot (type: string), __time (type: timestamp), $f2 (type: bigint), $f3 (type: float)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: EXPLAIN
SELECT robot, floor_month(`__time`), max(added) as m, sum(variation) as s
@@ -211,24 +293,54 @@ ORDER BY s DESC, m DESC
LIMIT 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: druid_table_1
+ properties:
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"month","dimensions":["robot","namespace"],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]}
+ druid.query.type groupBy
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: robot (type: string), __time (type: timestamp), $f3 (type: float), $f4 (type: float)
+ outputColumnNames: _col0, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col4 (type: float), _col3 (type: float)
+ sort order: --
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: string), _col2 (type: timestamp)
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col2 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: float)
+ outputColumnNames: _col0, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col2 (type: timestamp), _col3 (type: float), _col4 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
- TableScan
- alias: druid_table_1
- properties:
- druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"MONTH","dimensions":["robot","namespace"],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f4","direction":"descending"},{"dimension":"$f3","direction":"descending"}]},"aggregations":[{"type":"longMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"variation"}],"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
- Select Operator
- expressions: robot (type: string), __time (type: timestamp), $f3 (type: bigint), $f4 (type: float)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: EXPLAIN
SELECT robot, floor_month(`__time`), max(added) as m, sum(variation) as s
@@ -245,24 +357,54 @@ ORDER BY robot ASC, m DESC
LIMIT 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: druid_table_1
+ properties:
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"month","dimensions":["robot","namespace"],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]}
+ druid.query.type groupBy
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: robot (type: string), __time (type: timestamp), $f3 (type: float), $f4 (type: float)
+ outputColumnNames: _col0, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col3 (type: float)
+ sort order: +-
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col2 (type: timestamp), _col4 (type: float)
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), VALUE._col1 (type: timestamp), KEY.reducesinkkey1 (type: float), VALUE._col2 (type: float)
+ outputColumnNames: _col0, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col2 (type: timestamp), _col3 (type: float), _col4 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
- TableScan
- alias: druid_table_1
- properties:
- druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"MONTH","dimensions":["robot","namespace"],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"robot","direction":"ascending"},{"dimension":"$f3","direction":"descending"}]},"aggregations":[{"type":"longMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"variation"}],"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
- Select Operator
- expressions: robot (type: string), __time (type: timestamp), $f3 (type: bigint), $f4 (type: float)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: EXPLAIN
SELECT robot, floor_year(`__time`), max(added), sum(variation) as s
@@ -281,24 +423,54 @@ ORDER BY s
LIMIT 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: druid_table_1
+ properties:
+ druid.query.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"year","filter":{"type":"selector","dimension":"robot","value":"1"},"aggregations":[{"type":"doubleMax","name":"$f1_0","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}}
+ druid.query.type timeseries
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: __time (type: timestamp), $f1_0 (type: float), $f2 (type: float)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: float)
+ sort order: +
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: timestamp), _col1 (type: float)
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: timestamp), VALUE._col1 (type: float), KEY.reducesinkkey0 (type: float)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: '1' (type: string), _col0 (type: timestamp), _col1 (type: float), _col2 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
- TableScan
- alias: druid_table_1
- properties:
- druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"YEAR","dimensions":[],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f2","direction":"ascending"}]},"filter":{"type":"selector","dimension":"robot","value":"1"},"aggregations":[{"type":"longMax","name":"$f1_0","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"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
- Select Operator
- expressions: '1' (type: string), __time (type: timestamp), $f1_0 (type: bigint), $f2 (type: float)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- ListSink
+ ListSink
PREHOOK: query: EXPLAIN
SELECT robot, floor_hour(`__time`), max(added) as m, sum(variation)
@@ -333,7 +505,7 @@ STAGE PLANS:
alias: druid_table_1
filterExpr: floor_hour(__time) BETWEEN 2010-01-01 00:00:00.0 AND 2014-01-01 00:00:00.0 (type: boolean)
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384},"context":{"druid.query.fetch":false}}
+ druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","namespace","anonymous","unpatrolled","page","language","newpage","user"],"metrics":["count","added","delta","variation","deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
druid.query.type select
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Filter Operator
diff --git a/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out b/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out
index 8c6f0f1..d986120 100644
--- a/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out
+++ b/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out
@@ -9,19 +9,19 @@ FROM src f JOIN src m JOIN src g ON(g.value = m.value AND m.value is not null AN
WHERE (f.key = m.key AND f.value='2008-04-08' AND m.value='2008-04-08') OR (f.key = m.key AND f.value='2008-04-09')
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
- Stage-0 depends on stages: Stage-1
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Map Reduce
Map Operator Tree:
TableScan
- alias: f
+ alias: m
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((value = '2008-04-08') or (value = '2008-04-09')) and key is not null) (type: boolean)
+ predicate: ((value <> '') and 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)
@@ -34,10 +34,10 @@ STAGE PLANS:
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
TableScan
- alias: m
+ alias: f
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((value <> '') and key is not null) (type: boolean)
+ predicate: (((value = '2008-04-08') or (value = '2008-04-09')) and key is not null) (type: boolean)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
@@ -56,26 +56,29 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3
+ outputColumnNames: _col1, _col2, _col3
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((_col1 = '2008-04-08') and (_col3 = '2008-04-08')) or (_col1 = '2008-04-09')) (type: boolean)
+ predicate: (((_col3 = '2008-04-08') and (_col1 = '2008-04-08')) or (_col3 = '2008-04-09')) (type: boolean)
Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col3
- Statistics: Num rows: 412 Data size: 4376 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
+ 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-1
+ Stage: Stage-2
Map Reduce
Map Operator Tree:
TableScan
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: string)
+ TableScan
alias: g
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -90,24 +93,17 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- TableScan
- Reduce Output Operator
- key expressions: _col3 (type: string)
- sort order: +
- Map-reduce partition columns: _col3 (type: string)
- Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col3 (type: string)
- outputColumnNames: _col0, _col1
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col2, _col4
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col1 (type: string), _col0 (type: string)
+ expressions: _col2 (type: string), _col4 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -135,19 +131,19 @@ FROM src f JOIN src m JOIN src g ON(g.value = m.value AND m.value is not null AN
WHERE (f.key = m.key AND f.value IN ('2008-04-08','2008-04-10') AND m.value='2008-04-08') OR (f.key = m.key AND f.value='2008-04-09')
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
- Stage-0 depends on stages: Stage-1
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Map Reduce
Map Operator Tree:
TableScan
- alias: f
+ alias: m
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((value) IN ('2008-04-08', '2008-04-10') or (value = '2008-04-09')) and key is not null) (type: boolean)
+ predicate: ((value <> '') and 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)
@@ -160,10 +156,10 @@ STAGE PLANS:
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
TableScan
- alias: m
+ alias: f
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((value <> '') and key is not null) (type: boolean)
+ predicate: (((value) IN ('2008-04-08', '2008-04-10') or (value = '2008-04-09')) and key is not null) (type: boolean)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
@@ -182,26 +178,29 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3
+ outputColumnNames: _col1, _col2, _col3
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((_col1) IN ('2008-04-08', '2008-04-10') and (_col3 = '2008-04-08')) or (_col1 = '2008-04-09')) (type: boolean)
+ predicate: (((_col3) IN ('2008-04-08', '2008-04-10') and (_col1 = '2008-04-08')) or (_col3 = '2008-04-09')) (type: boolean)
Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col3
- Statistics: Num rows: 412 Data size: 4376 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
+ 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-1
+ Stage: Stage-2
Map Reduce
Map Operator Tree:
TableScan
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: string)
+ TableScan
alias: g
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -216,24 +215,17 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- TableScan
- Reduce Output Operator
- key expressions: _col3 (type: string)
- sort order: +
- Map-reduce partition columns: _col3 (type: string)
- Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col3 (type: string)
- outputColumnNames: _col0, _col1
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col2, _col4
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col1 (type: string), _col0 (type: string)
+ expressions: _col2 (type: string), _col4 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -321,7 +313,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col4
Statistics: Num rows: 11 Data size: 144 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((_col2 + _col4) > 2.0) or ((_col1 + 1) > 2)) (type: boolean)
+ predicate: (((_col2 + _col4) > 2) or ((_col1 + 1) > 2)) (type: boolean)
Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
@@ -419,7 +411,7 @@ STAGE PLANS:
alias: m
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((value = '2008-04-10') or (value = '2008-04-08')) and (value <> '') and key is not null) (type: boolean)
+ predicate: ((value <> '') and ((value = '2008-04-10') or (value = '2008-04-08')) and key is not null) (type: boolean)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
diff --git a/ql/src/test/results/clientpositive/fouter_join_ppr.q.out b/ql/src/test/results/clientpositive/fouter_join_ppr.q.out
index 1897aa7..2dfcc18 100644
--- a/ql/src/test/results/clientpositive/fouter_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/fouter_join_ppr.q.out
@@ -28,36 +28,44 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- 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
- 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
- value expressions: _col1 (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
TableScan
alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string), _col2 (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 12 Data size: 127 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: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -203,149 +211,42 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart
name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
Truncated Path -> Alias:
/src [$hdt$_0:a]
/srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b]
/srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b]
- /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:b]
- /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:b]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
- Outer Join 0 to 1
- filter mappings:
- 1 [0, 1]
- filter predicates:
- 0
- 1 {(VALUE._col1 = '2008-04-08')}
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -365,8 +266,6 @@ PREHOOK: Input: default@src
PREHOOK: Input: default@srcpart
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
POSTHOOK: query: FROM
src a
@@ -380,8 +279,6 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
17 val_17 17 val_17
17 val_17 17 val_17
@@ -423,38 +320,46 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: _col1 (type: string), _col2 (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 12 Data size: 127 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: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
TableScan
alias: b
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- 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
- 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: 1
- value expressions: _col1 (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -600,153 +505,46 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart
name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
Truncated Path -> Alias:
/src [$hdt$_1:b]
/srcpart/ds=2008-04-08/hr=11 [$hdt$_0:a]
/srcpart/ds=2008-04-08/hr=12 [$hdt$_0:a]
- /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:a]
- /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:a]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
- Outer Join 0 to 1
- filter mappings:
- 0 [1, 1]
- filter predicates:
- 0 {(VALUE._col1 = '2008-04-08')}
- 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 25.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -766,8 +564,6 @@ PREHOOK: Input: default@src
PREHOOK: Input: default@srcpart
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
POSTHOOK: query: FROM
srcpart a
@@ -781,8 +577,6 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
17 val_17 17 val_17
17 val_17 17 val_17
@@ -828,18 +622,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -849,18 +643,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -1017,38 +811,34 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Right Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -1126,18 +916,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -1147,18 +937,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -1315,42 +1105,38 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 25.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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/index_auto_unused.q.out b/ql/src/test/results/clientpositive/index_auto_unused.q.out
index 8a270d6..cff5313 100644
--- a/ql/src/test/results/clientpositive/index_auto_unused.q.out
+++ b/ql/src/test/results/clientpositive/index_auto_unused.q.out
@@ -340,37 +340,25 @@ PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN SELECT * FROM srcpart WHERE ds='2008-04-09' AND hr=12 AND key < 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
+ Stage-0 is a root stage
STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- filterExpr: ((ds = '2008-04-09') and (12.0 = 12.0) and (UDFToDouble(key) < 10.0)) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (UDFToDouble(key) < 10.0) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string), '2008-04-09' (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- 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
-
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
- ListSink
+ TableScan
+ alias: srcpart
+ filterExpr: ((ds = '2008-04-09') and (12.0 = 12.0) and (UDFToDouble(key) < 10.0)) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (UDFToDouble(key) < 10.0) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string), '2008-04-09' (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ ListSink
PREHOOK: query: SELECT * FROM srcpart WHERE ds='2008-04-09' AND hr=12 AND key < 10
PREHOOK: type: QUERY
diff --git a/ql/src/test/results/clientpositive/join45.q.out b/ql/src/test/results/clientpositive/join45.q.out
index 249fe9c..66f8893 100644
--- a/ql/src/test/results/clientpositive/join45.q.out
+++ b/ql/src/test/results/clientpositive/join45.q.out
@@ -26,40 +26,34 @@ STAGE PLANS:
alias: src1
Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ predicate: (UDFToDouble(value) BETWEEN 100.0 AND 102.0 and key is not null) (type: boolean)
+ Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col1 BETWEEN 100 AND 102 (type: boolean)
+ Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ value expressions: _col1 (type: string)
TableScan
alias: src
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
+ predicate: (UDFToDouble(value) BETWEEN 100.0 AND 102.0 and key is not null) (type: boolean)
+ Statistics: Num rows: 55 Data size: 584 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
- Filter Operator
- predicate: _col1 BETWEEN 100 AND 102 (type: boolean)
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ value expressions: _col1 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
@@ -238,12 +232,12 @@ STAGE PLANS:
TableScan
alias: src1
Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col1 BETWEEN 100 AND 102 (type: boolean)
+ Filter Operator
+ predicate: UDFToDouble(value) BETWEEN 100.0 AND 102.0 (type: boolean)
+ Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
@@ -252,12 +246,12 @@ STAGE PLANS:
TableScan
alias: src
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
- Filter Operator
- predicate: _col1 BETWEEN 100 AND 102 (type: boolean)
+ Filter Operator
+ predicate: UDFToDouble(value) BETWEEN 100.0 AND 102.0 (type: boolean)
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
@@ -367,7 +361,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 12500 Data size: 240800 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 = _col2) or _col1 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102) (type: boolean)
+ predicate: ((_col0 = _col2) or UDFToDouble(_col1) BETWEEN 100.0 AND 102.0 or UDFToDouble(_col3) BETWEEN 100.0 AND 102.0) (type: boolean)
Statistics: Num rows: 9026 Data size: 173876 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
diff --git a/ql/src/test/results/clientpositive/join_alt_syntax.q.out b/ql/src/test/results/clientpositive/join_alt_syntax.q.out
index cef5272..1c08e6a 100644
--- a/ql/src/test/results/clientpositive/join_alt_syntax.q.out
+++ b/ql/src/test/results/clientpositive/join_alt_syntax.q.out
@@ -230,7 +230,7 @@ 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[13][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product
PREHOOK: query: explain select p1.p_name, p2.p_name, p3.p_name
from part p1 , part p2 , part p3
where p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name
@@ -249,17 +249,6 @@ STAGE PLANS:
Map Reduce
Map Operator Tree:
TableScan
- alias: p1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_partkey (type: int), p_name (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string)
- TableScan
alias: p2
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -270,42 +259,11 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- sort order:
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 676 Data size: 164320 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col2 + _col0) = _col0) (type: boolean)
- Statistics: Num rows: 338 Data size: 82160 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col1, _col3
- Statistics: Num rows: 338 Data size: 82160 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: _col3 (type: string)
- sort order: +
- Map-reduce partition columns: _col3 (type: string)
- Statistics: Num rows: 338 Data size: 82160 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ value expressions: _col0 (type: int)
TableScan
alias: p3
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
@@ -326,21 +284,59 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col3 (type: string)
+ 0 _col1 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col1, _col3, _col4
- Statistics: Num rows: 371 Data size: 90376 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 371 Data size: 90376 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 371 Data size: 90376 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
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 28 Data size: 3461 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
+ sort order:
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
+ TableScan
+ alias: p1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_partkey (type: int), p_name (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 + _col3) = _col3) (type: boolean)
+ Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col4 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 364 Data size: 89415 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/join_cond_pushdown_1.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out
index 9461a1b..831d84f 100644
--- a/ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out
+++ b/ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out
@@ -172,7 +172,7 @@ 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[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product
PREHOOK: query: explain select *
from part p1 join part p2 join part p3 on p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name
PREHOOK: type: QUERY
@@ -189,17 +189,6 @@ STAGE PLANS:
Map Reduce
Map Operator Tree:
TableScan
- alias: p1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- TableScan
alias: p2
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -210,38 +199,11 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- sort order:
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17
- Statistics: Num rows: 676 Data size: 164320 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col9 + _col0) = _col0) (type: boolean)
- Statistics: Num rows: 338 Data size: 82160 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: _col10 (type: string)
- sort order: +
- Map-reduce partition columns: _col10 (type: string)
- Statistics: Num rows: 338 Data size: 82160 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
TableScan
alias: p3
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
@@ -263,17 +225,59 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col10 (type: string)
+ 0 _col1 (type: string)
1 _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
- Statistics: Num rows: 371 Data size: 90376 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 371 Data size: 90376 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
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ TableScan
+ alias: p1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
+ Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 + _col18) = _col18) (type: boolean)
+ Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
+ Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 364 Data size: 89415 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/join_cond_pushdown_3.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out
index 2205c4e..560b8e0 100644
--- a/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out
+++ b/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out
@@ -176,7 +176,7 @@ 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[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product
PREHOOK: query: explain select *
from part p1 join part p2 join part p3
where p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name
@@ -195,17 +195,6 @@ STAGE PLANS:
Map Reduce
Map Operator Tree:
TableScan
- alias: p1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- TableScan
alias: p2
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -216,38 +205,11 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- sort order:
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17
- Statistics: Num rows: 676 Data size: 164320 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col9 + _col0) = _col0) (type: boolean)
- Statistics: Num rows: 338 Data size: 82160 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: _col10 (type: string)
- sort order: +
- Map-reduce partition columns: _col10 (type: string)
- Statistics: Num rows: 338 Data size: 82160 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
TableScan
alias: p3
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
@@ -269,17 +231,59 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col10 (type: string)
+ 0 _col1 (type: string)
1 _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
- Statistics: Num rows: 371 Data size: 90376 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 371 Data size: 90376 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
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ TableScan
+ alias: p1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
+ Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 + _col18) = _col18) (type: boolean)
+ Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
+ Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 364 Data size: 89415 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/join_cond_pushdown_unqual1.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out
index 966330d..f77c75c 100644
--- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out
+++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out
@@ -228,7 +228,7 @@ 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[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: explain select *
from part p1 join part2 p2 join part3 p3 on p2_partkey + p_partkey = p1.p_partkey and p3_name = p2_name
PREHOOK: type: QUERY
diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out
index 54a2d06..f15d536 100644
--- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out
+++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out
@@ -232,7 +232,7 @@ 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[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: explain select *
from part p1 join part2 p2 join part3 p3
where p2_partkey + p1.p_partkey = p1.p_partkey and p3_name = p2_name
diff --git a/ql/src/test/results/clientpositive/join_merging.q.out b/ql/src/test/results/clientpositive/join_merging.q.out
index 79a7023..7cc04f5 100644
--- a/ql/src/test/results/clientpositive/join_merging.q.out
+++ b/ql/src/test/results/clientpositive/join_merging.q.out
@@ -97,19 +97,18 @@ from part p1 left outer join part p2 on p1.p_partkey = p2.p_partkey
p1.p_size > 10 and p1.p_size > p2.p_size + 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Map Reduce
Map Operator Tree:
TableScan
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_size > 10) (type: boolean)
+ predicate: ((p_size > 10) and p_partkey is not null) (type: boolean)
Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_partkey (type: int), p_size (type: int)
@@ -124,38 +123,19 @@ STAGE PLANS:
TableScan
alias: p2
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_partkey (type: int), p_size (type: int)
- outputColumnNames: _col0, _col1
+ Filter Operator
+ predicate: p_partkey is not null (type: boolean)
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ Select Operator
+ expressions: p_partkey (type: int), p_size (type: int)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: int)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col1, _col2, _col3
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col1 > (_col3 + 10)) (type: boolean)
- Statistics: Num rows: 9 Data size: 1112 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-1
- Map Reduce
- Map Operator Tree:
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int)
TableScan
alias: p3
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
@@ -168,29 +148,25 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- TableScan
- Reduce Output Operator
- key expressions: _col2 (type: int)
- sort order: +
- Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: int), _col3 (type: int)
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
+ Right Outer Join1 to 2
keys:
0 _col0 (type: int)
- 1 _col2 (type: int)
- outputColumnNames: _col2, _col4
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ 1 _col0 (type: int)
+ 2 _col0 (type: int)
+ outputColumnNames: _col1, _col3
+ residual filter predicates: {(_col1 > (_col3 + 10))}
+ Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: int), _col4 (type: int)
+ expressions: _col1 (type: int), _col3 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
diff --git a/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out
index a867bd2..841ef14 100644
--- a/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out
+++ b/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out
@@ -1044,7 +1044,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
@@ -1063,7 +1063,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out
index c08a534..b69d0bd 100644
--- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out
+++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out
@@ -1261,7 +1261,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
@@ -1293,7 +1293,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
diff --git a/ql/src/test/results/clientpositive/llap/constprog_semijoin.q.out b/ql/src/test/results/clientpositive/llap/constprog_semijoin.q.out
index 98d2328..4bdb186 100644
--- a/ql/src/test/results/clientpositive/llap/constprog_semijoin.q.out
+++ b/ql/src/test/results/clientpositive/llap/constprog_semijoin.q.out
@@ -274,7 +274,7 @@ Stage-0
Select Operator [SEL_5] (rows=2 width=3)
Output:["_col0","_col1"]
Filter Operator [FIL_16] (rows=2 width=3)
- predicate:((id = 100) and (id = 100) is not null)
+ predicate:(id = 100)
TableScan [TS_3] (rows=5 width=3)
default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"]
@@ -311,7 +311,7 @@ Stage-0
Select Operator [SEL_2] (rows=5 width=20)
Output:["_col0","_col1","_col2"]
Filter Operator [FIL_15] (rows=5 width=20)
- predicate:((dimid = 100) and (dimid = 100) is not null)
+ predicate:(dimid = 100)
TableScan [TS_0] (rows=10 width=20)
default@table1,table1,Tbl:COMPLETE,Col:NONE,Output:["id","val","val1","dimid"]
<-Map 3 [SIMPLE_EDGE] llap
@@ -322,7 +322,7 @@ Stage-0
Select Operator [SEL_5] (rows=2 width=3)
Output:["_col0","_col1"]
Filter Operator [FIL_16] (rows=2 width=3)
- predicate:((id = 100) and (id = 100) is not null)
+ predicate:(id = 100)
TableScan [TS_3] (rows=5 width=3)
default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"]
@@ -372,7 +372,7 @@ Stage-0
Select Operator [SEL_5] (rows=2 width=3)
Output:["_col0","_col1"]
Filter Operator [FIL_16] (rows=2 width=3)
- predicate:((id = 100) and (id = 100) is not null)
+ predicate:(id = 100)
TableScan [TS_3] (rows=5 width=3)
default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"]
@@ -409,7 +409,7 @@ Stage-0
Select Operator [SEL_2] (rows=5 width=20)
Output:["_col0","_col1","_col2"]
Filter Operator [FIL_15] (rows=5 width=20)
- predicate:((dimid = 100) and (dimid = 100) is not null)
+ predicate:(dimid = 100)
TableScan [TS_0] (rows=10 width=20)
default@table1,table1,Tbl:COMPLETE,Col:NONE,Output:["id","val","val1","dimid"]
<-Map 3 [SIMPLE_EDGE] llap
@@ -420,7 +420,7 @@ Stage-0
Select Operator [SEL_5] (rows=2 width=3)
Output:["_col0","_col1"]
Filter Operator [FIL_16] (rows=2 width=3)
- predicate:((id = 100) and (id = 100) is not null)
+ predicate:(id = 100)
TableScan [TS_3] (rows=5 width=3)
default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"]
@@ -459,7 +459,7 @@ Stage-0
Select Operator [SEL_2] (rows=5 width=20)
Output:["_col0","_col1","_col2"]
Filter Operator [FIL_15] (rows=5 width=20)
- predicate:((dimid = 100) and (dimid = 100) is not null)
+ predicate:(dimid = 100)
TableScan [TS_0] (rows=10 width=20)
default@table1,table1,Tbl:COMPLETE,Col:NONE,Output:["id","val","val1","dimid"]
<-Map 3 [SIMPLE_EDGE] llap
@@ -470,7 +470,7 @@ Stage-0
Select Operator [SEL_5] (rows=2 width=3)
Output:["_col0","_col1"]
Filter Operator [FIL_16] (rows=2 width=3)
- predicate:((id = 100) and (id = 100) is not null)
+ predicate:(id = 100)
TableScan [TS_3] (rows=5 width=3)
default@table3,table3,Tbl:COMPLETE,Col:NONE,Output:["id"]
diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_2.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_2.q.out
index d291e7d..a5fdd90 100644
--- a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_2.q.out
@@ -105,10 +105,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: tt2
- filterExpr: ((timestamp_col_18 = timestamp_col_18) and decimal1911_col_16 is not null and (timestamp_col_18 BETWEEN DynamicValue(RS_23_t1_timestamp_col_18_min) AND DynamicValue(RS_23_t1_timestamp_col_18_max) and in_bloom_filter(timestamp_col_18, DynamicValue(RS_23_t1_timestamp_col_18_bloom_filter)))) (type: boolean)
+ filterExpr: (timestamp_col_18 is not null and decimal1911_col_16 is not null and (timestamp_col_18 BETWEEN DynamicValue(RS_23_t1_timestamp_col_18_min) AND DynamicValue(RS_23_t1_timestamp_col_18_max) and in_bloom_filter(timestamp_col_18, DynamicValue(RS_23_t1_timestamp_col_18_bloom_filter)))) (type: boolean)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: ((timestamp_col_18 = timestamp_col_18) and decimal1911_col_16 is not null and (timestamp_col_18 BETWEEN DynamicValue(RS_23_t1_timestamp_col_18_min) AND DynamicValue(RS_23_t1_timestamp_col_18_max) and in_bloom_filter(timestamp_col_18, DynamicValue(RS_23_t1_timestamp_col_18_bloom_filter)))) (type: boolean)
+ predicate: (timestamp_col_18 is not null and decimal1911_col_16 is not null and (timestamp_col_18 BETWEEN DynamicValue(RS_23_t1_timestamp_col_18_min) AND DynamicValue(RS_23_t1_timestamp_col_18_max) and in_bloom_filter(timestamp_col_18, DynamicValue(RS_23_t1_timestamp_col_18_bloom_filter)))) (type: boolean)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: decimal1911_col_16 (type: decimal(19,11)), timestamp_col_18 (type: timestamp)
diff --git a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out
index a69f2ad..584c3b5 100644
--- a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out
@@ -346,11 +346,10 @@ Plan optimized by CBO.
Vertex dependency in root stage
Reducer 10 <- Reducer 9 (SIMPLE_EDGE)
-Reducer 2 <- Map 1 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
-Reducer 5 <- Map 11 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
-Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
+Reducer 6 <- Map 5 (SIMPLE_EDGE)
Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
Reducer 9 <- Map 8 (SIMPLE_EDGE)
@@ -358,85 +357,76 @@ Stage-0
Fetch Operator
limit:-1
Stage-1
- Reducer 7 llap
- File Output Operator [FS_42]
- Select Operator [SEL_41] (rows=1 width=20)
+ Reducer 4 llap
+ File Output Operator [FS_38]
+ Select Operator [SEL_37] (rows=1 width=20)
Output:["_col0","_col1","_col2"]
- <-Reducer 6 [SIMPLE_EDGE] llap
- SHUFFLE [RS_40]
- Select Operator [SEL_38] (rows=1 width=20)
+ <-Reducer 3 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_36]
+ Select Operator [SEL_35] (rows=1 width=20)
Output:["_col0","_col1","_col2"]
- Group By Operator [GBY_37] (rows=1 width=20)
+ Group By Operator [GBY_34] (rows=1 width=20)
Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1
- <-Reducer 5 [SIMPLE_EDGE] llap
- SHUFFLE [RS_36]
+ <-Reducer 2 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_33]
PartitionCols:_col0, _col1
- Group By Operator [GBY_35] (rows=1 width=20)
- Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col2, _col6
- Select Operator [SEL_34] (rows=3 width=16)
- Output:["_col2","_col6"]
- Filter Operator [FIL_33] (rows=3 width=16)
- predicate:((_col1 > 0) or (_col6 >= 0))
- Merge Join Operator [MERGEJOIN_52] (rows=3 width=16)
- Conds:RS_30._col0=RS_31._col0(Inner),Output:["_col1","_col2","_col6"]
- <-Map 11 [SIMPLE_EDGE] llap
- SHUFFLE [RS_31]
+ Group By Operator [GBY_32] (rows=1 width=20)
+ Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col4, _col1
+ Select Operator [SEL_31] (rows=1 width=20)
+ Output:["_col1","_col4"]
+ Filter Operator [FIL_29] (rows=1 width=20)
+ predicate:(((_col3 + _col6) >= 0) and ((_col3 > 0) or (_col1 >= 0)))
+ Merge Join Operator [MERGEJOIN_48] (rows=3 width=20)
+ Conds:RS_25._col0=RS_26._col0(Inner),RS_26._col0=RS_27._col0(Inner),Output:["_col1","_col3","_col4","_col6"]
+ <-Map 1 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_25]
PartitionCols:_col0
- Select Operator [SEL_29] (rows=18 width=84)
+ Select Operator [SEL_2] (rows=18 width=84)
Output:["_col0","_col1"]
- Filter Operator [FIL_50] (rows=18 width=84)
+ Filter Operator [FIL_45] (rows=18 width=84)
predicate:key is not null
- TableScan [TS_27] (rows=20 width=84)
+ TableScan [TS_0] (rows=20 width=84)
default@cbo_t3,cbo_t3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int"]
- <-Reducer 4 [SIMPLE_EDGE] llap
- SHUFFLE [RS_30]
+ <-Reducer 10 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_27]
+ PartitionCols:_col0
+ Select Operator [SEL_23] (rows=1 width=89)
+ Output:["_col0","_col1"]
+ <-Reducer 9 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_22]
+ Select Operator [SEL_20] (rows=1 width=105)
+ Output:["_col0","_col1","_col2","_col3"]
+ Group By Operator [GBY_19] (rows=1 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
+ <-Map 8 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_18]
+ PartitionCols:_col0, _col1, _col2
+ Group By Operator [GBY_17] (rows=2 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
+ Filter Operator [FIL_47] (rows=5 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and key is not null)
+ TableScan [TS_14] (rows=20 width=88)
+ default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ <-Reducer 7 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_26]
PartitionCols:_col0
- Select Operator [SEL_26] (rows=1 width=101)
+ Select Operator [SEL_12] (rows=1 width=97)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_25] (rows=1 width=101)
- predicate:((_col1 + _col4) >= 0)
- Merge Join Operator [MERGEJOIN_51] (rows=1 width=101)
- Conds:RS_22._col0=RS_23._col0(Inner),Output:["_col0","_col1","_col2","_col4"]
- <-Reducer 10 [SIMPLE_EDGE] llap
- SHUFFLE [RS_23]
- PartitionCols:_col0
- Select Operator [SEL_20] (rows=1 width=89)
- Output:["_col0","_col1"]
- <-Reducer 9 [SIMPLE_EDGE] llap
- SHUFFLE [RS_19]
- Select Operator [SEL_17] (rows=1 width=105)
- Output:["_col0","_col1","_col2","_col3"]
- Group By Operator [GBY_16] (rows=1 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Map 8 [SIMPLE_EDGE] llap
- SHUFFLE [RS_15]
- PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_14] (rows=2 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
- Filter Operator [FIL_49] (rows=5 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and key is not null)
- TableScan [TS_11] (rows=20 width=88)
- default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
- <-Reducer 3 [SIMPLE_EDGE] llap
- SHUFFLE [RS_22]
- PartitionCols:_col0
- Select Operator [SEL_9] (rows=1 width=97)
- Output:["_col0","_col1","_col2"]
- <-Reducer 2 [SIMPLE_EDGE] llap
- SHUFFLE [RS_8]
- Select Operator [SEL_6] (rows=1 width=97)
- Output:["_col0","_col1","_col2"]
- Group By Operator [GBY_5] (rows=1 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Map 1 [SIMPLE_EDGE] llap
- SHUFFLE [RS_4]
- PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_3] (rows=2 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
- Filter Operator [FIL_48] (rows=5 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and key is not null)
- TableScan [TS_0] (rows=20 width=88)
- default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ <-Reducer 6 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_11]
+ Select Operator [SEL_9] (rows=1 width=97)
+ Output:["_col0","_col1","_col2"]
+ Group By Operator [GBY_8] (rows=1 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
+ <-Map 5 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_7]
+ PartitionCols:_col0, _col1, _col2
+ Group By Operator [GBY_6] (rows=2 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
+ Filter Operator [FIL_46] (rows=5 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and key is not null)
+ TableScan [TS_3] (rows=20 width=88)
+ default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b % c asc, b desc) cbo_t1 left outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int % c asc, cbo_t3.c_int desc
PREHOOK: type: QUERY
@@ -445,11 +435,10 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 2 <- Map 1 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
-Reducer 5 <- Map 10 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
-Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
+Reducer 6 <- Map 5 (SIMPLE_EDGE)
Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
Reducer 9 <- Map 8 (SIMPLE_EDGE)
@@ -457,79 +446,70 @@ Stage-0
Fetch Operator
limit:-1
Stage-1
- Reducer 7 llap
- File Output Operator [FS_39]
- Select Operator [SEL_38] (rows=1 width=20)
+ Reducer 4 llap
+ File Output Operator [FS_37]
+ Select Operator [SEL_36] (rows=1 width=20)
Output:["_col0","_col1","_col2"]
- <-Reducer 6 [SIMPLE_EDGE] llap
- SHUFFLE [RS_37]
- Group By Operator [GBY_34] (rows=1 width=20)
+ <-Reducer 3 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_35]
+ Group By Operator [GBY_33] (rows=1 width=20)
Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1
- <-Reducer 5 [SIMPLE_EDGE] llap
- SHUFFLE [RS_33]
+ <-Reducer 2 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_32]
PartitionCols:_col0, _col1
- Group By Operator [GBY_32] (rows=1 width=20)
- Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col6, _col2
- Select Operator [SEL_31] (rows=1 width=16)
- Output:["_col2","_col6"]
- Filter Operator [FIL_30] (rows=1 width=16)
- predicate:(((_col1 > 0) or (_col6 >= 0)) and ((_col6 >= 1) or (_col2 >= 1)) and ((UDFToLong(_col6) + _col2) >= 0))
- Merge Join Operator [MERGEJOIN_48] (rows=3 width=16)
- Conds:RS_27._col0=RS_28._col0(Inner),Output:["_col1","_col2","_col6"]
- <-Map 10 [SIMPLE_EDGE] llap
- SHUFFLE [RS_28]
+ Group By Operator [GBY_31] (rows=1 width=20)
+ Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4
+ Select Operator [SEL_30] (rows=1 width=20)
+ Output:["_col1","_col4"]
+ Filter Operator [FIL_26] (rows=1 width=20)
+ predicate:(((_col3 + _col6) >= 0) and ((UDFToLong(_col1) + _col4) >= 0) and ((_col1 >= 1) or (_col4 >= 1)) and ((_col3 > 0) or (_col1 >= 0)))
+ Merge Join Operator [MERGEJOIN_47] (rows=3 width=20)
+ Conds:RS_22._col0=RS_23._col0(Inner),RS_23._col0=RS_24._col0(Inner),Output:["_col1","_col3","_col4","_col6"]
+ <-Map 1 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_22]
PartitionCols:_col0
- Select Operator [SEL_26] (rows=18 width=84)
+ Select Operator [SEL_2] (rows=18 width=84)
Output:["_col0","_col1"]
- Filter Operator [FIL_46] (rows=18 width=84)
+ Filter Operator [FIL_44] (rows=18 width=84)
predicate:((c_int > 0) and key is not null)
- TableScan [TS_24] (rows=20 width=84)
+ TableScan [TS_0] (rows=20 width=84)
default@cbo_t3,cbo_t3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int"]
- <-Reducer 4 [SIMPLE_EDGE] llap
- SHUFFLE [RS_27]
+ <-Reducer 7 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_23]
PartitionCols:_col0
- Select Operator [SEL_23] (rows=1 width=101)
+ Select Operator [SEL_12] (rows=1 width=97)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_22] (rows=1 width=101)
- predicate:((_col1 + _col4) >= 0)
- Merge Join Operator [MERGEJOIN_47] (rows=1 width=101)
- Conds:RS_19._col0=RS_20._col0(Left Outer),Output:["_col0","_col1","_col2","_col4"]
- <-Reducer 3 [SIMPLE_EDGE] llap
- SHUFFLE [RS_19]
- PartitionCols:_col0
- Select Operator [SEL_9] (rows=1 width=97)
- Output:["_col0","_col1","_col2"]
- <-Reducer 2 [SIMPLE_EDGE] llap
- SHUFFLE [RS_8]
- Select Operator [SEL_6] (rows=1 width=105)
- Output:["_col0","_col1","_col2","_col3"]
- Group By Operator [GBY_5] (rows=1 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Map 1 [SIMPLE_EDGE] llap
- SHUFFLE [RS_4]
- PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_3] (rows=1 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
- Filter Operator [FIL_44] (rows=2 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0.0) and key is not null)
- TableScan [TS_0] (rows=20 width=88)
- default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
- <-Reducer 9 [SIMPLE_EDGE] llap
- SHUFFLE [RS_20]
- PartitionCols:_col0
- Select Operator [SEL_17] (rows=1 width=89)
- Output:["_col0","_col1"]
- Group By Operator [GBY_16] (rows=1 width=93)
- Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Map 8 [SIMPLE_EDGE] llap
- SHUFFLE [RS_15]
- PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_14] (rows=1 width=93)
- Output:["_col0","_col1","_col2"],keys:key, c_int, c_float
- Filter Operator [FIL_45] (rows=2 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0.0) and key is not null)
- TableScan [TS_11] (rows=20 width=88)
- default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ <-Reducer 6 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_11]
+ Select Operator [SEL_9] (rows=1 width=105)
+ Output:["_col0","_col1","_col2","_col3"]
+ Group By Operator [GBY_8] (rows=1 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
+ <-Map 5 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_7]
+ PartitionCols:_col0, _col1, _col2
+ Group By Operator [GBY_6] (rows=1 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
+ Filter Operator [FIL_45] (rows=2 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null)
+ TableScan [TS_3] (rows=20 width=88)
+ default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ <-Reducer 9 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_24]
+ PartitionCols:_col0
+ Select Operator [SEL_20] (rows=1 width=89)
+ Output:["_col0","_col1"]
+ Group By Operator [GBY_19] (rows=1 width=93)
+ Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2
+ <-Map 8 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_18]
+ PartitionCols:_col0, _col1, _col2
+ Group By Operator [GBY_17] (rows=1 width=93)
+ Output:["_col0","_col1","_col2"],keys:key, c_int, c_float
+ Filter Operator [FIL_46] (rows=2 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null)
+ TableScan [TS_14] (rows=20 width=88)
+ default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b+c, a desc) cbo_t1 right outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 2) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c
PREHOOK: type: QUERY
@@ -538,76 +518,76 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 2 <- Map 1 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-Reducer 4 <- Map 8 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
-Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
-Reducer 7 <- Map 6 (SIMPLE_EDGE)
+Reducer 5 <- Map 4 (SIMPLE_EDGE)
+Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
+Reducer 8 <- Map 7 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
- Reducer 5 llap
- File Output Operator [FS_31]
- Select Operator [SEL_30] (rows=1 width=20)
- Output:["_col0","_col1","_col2"]
- Group By Operator [GBY_29] (rows=1 width=20)
- Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1
- <-Reducer 4 [SIMPLE_EDGE] llap
- SHUFFLE [RS_28]
- PartitionCols:_col0, _col1
- Group By Operator [GBY_27] (rows=1 width=20)
- Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col2, _col6
- Select Operator [SEL_26] (rows=1 width=20)
- Output:["_col2","_col6"]
- Filter Operator [FIL_25] (rows=1 width=20)
- predicate:(((_col1 + _col4) >= 2) and ((_col1 > 0) or (_col6 >= 0)))
- Merge Join Operator [MERGEJOIN_36] (rows=4 width=20)
- Conds:RS_21._col0=RS_22._col0(Right Outer),RS_21._col0=RS_23._col0(Right Outer),Output:["_col1","_col2","_col4","_col6"]
- <-Map 8 [SIMPLE_EDGE] llap
- SHUFFLE [RS_23]
- PartitionCols:_col0
- Select Operator [SEL_20] (rows=20 width=84)
- Output:["_col0","_col1"]
- TableScan [TS_19] (rows=20 width=84)
+ Reducer 3 llap
+ File Output Operator [FS_33]
+ Group By Operator [GBY_31] (rows=1 width=20)
+ Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1
+ <-Reducer 2 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_30]
+ PartitionCols:_col0, _col1
+ Group By Operator [GBY_29] (rows=1 width=20)
+ Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4
+ Select Operator [SEL_28] (rows=1 width=20)
+ Output:["_col1","_col4"]
+ Filter Operator [FIL_26] (rows=1 width=20)
+ predicate:(((_col3 + _col6) >= 2) and ((_col3 > 0) or (_col1 >= 0)))
+ Merge Join Operator [MERGEJOIN_43] (rows=3 width=20)
+ Conds:RS_22._col0=RS_23._col0(Inner),RS_23._col0=RS_24._col0(Inner),Output:["_col1","_col3","_col4","_col6"]
+ <-Map 1 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_22]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=18 width=84)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_40] (rows=18 width=84)
+ predicate:key is not null
+ TableScan [TS_0] (rows=20 width=84)
default@cbo_t3,cbo_t3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int"]
- <-Reducer 3 [SIMPLE_EDGE] llap
- SHUFFLE [RS_21]
- PartitionCols:_col0
- Select Operator [SEL_9] (rows=1 width=97)
- Output:["_col0","_col1","_col2"]
- <-Reducer 2 [SIMPLE_EDGE] llap
- SHUFFLE [RS_8]
- Select Operator [SEL_6] (rows=1 width=105)
- Output:["_col0","_col1","_col2","_col3"]
- Group By Operator [GBY_5] (rows=1 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Map 1 [SIMPLE_EDGE] llap
- SHUFFLE [RS_4]
- PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_3] (rows=1 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
- Filter Operator [FIL_34] (rows=2 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0.0))
- TableScan [TS_0] (rows=20 width=88)
- default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
- <-Reducer 7 [SIMPLE_EDGE] llap
- SHUFFLE [RS_22]
- PartitionCols:_col0
- Select Operator [SEL_17] (rows=1 width=89)
- Output:["_col0","_col1"]
- Group By Operator [GBY_16] (rows=1 width=93)
- Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Map 6 [SIMPLE_EDGE] llap
- SHUFFLE [RS_15]
- PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_14] (rows=1 width=93)
- Output:["_col0","_col1","_col2"],keys:key, c_int, c_float
- Filter Operator [FIL_35] (rows=2 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0.0))
- TableScan [TS_11] (rows=20 width=88)
- default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ <-Reducer 6 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_23]
+ PartitionCols:_col0
+ Select Operator [SEL_12] (rows=1 width=97)
+ Output:["_col0","_col1","_col2"]
+ <-Reducer 5 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_11]
+ Select Operator [SEL_9] (rows=1 width=105)
+ Output:["_col0","_col1","_col2","_col3"]
+ Group By Operator [GBY_8] (rows=1 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
+ <-Map 4 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_7]
+ PartitionCols:_col0, _col1, _col2
+ Group By Operator [GBY_6] (rows=1 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
+ Filter Operator [FIL_41] (rows=2 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null)
+ TableScan [TS_3] (rows=20 width=88)
+ default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ <-Reducer 8 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_24]
+ PartitionCols:_col0
+ Select Operator [SEL_20] (rows=1 width=89)
+ Output:["_col0","_col1"]
+ Group By Operator [GBY_19] (rows=1 width=93)
+ Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2
+ <-Map 7 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_18]
+ PartitionCols:_col0, _col1, _col2
+ Group By Operator [GBY_17] (rows=1 width=93)
+ Output:["_col0","_col1","_col2"],keys:key, c_int, c_float
+ Filter Operator [FIL_42] (rows=2 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null)
+ TableScan [TS_14] (rows=20 width=88)
+ default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by c+a desc) cbo_t1 full outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by p+q desc, r asc) cbo_t2 on cbo_t1.a=p full outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int
PREHOOK: type: QUERY
@@ -616,86 +596,86 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 2 <- Map 1 (SIMPLE_EDGE)
+Reducer 10 <- Reducer 9 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
-Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
-Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
-Reducer 8 <- Map 7 (SIMPLE_EDGE)
-Reducer 9 <- Reducer 8 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
+Reducer 6 <- Map 5 (SIMPLE_EDGE)
+Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
+Reducer 9 <- Map 8 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
- Reducer 6 llap
- File Output Operator [FS_37]
- Select Operator [SEL_36] (rows=1 width=20)
+ Reducer 4 llap
+ File Output Operator [FS_40]
+ Select Operator [SEL_39] (rows=1 width=20)
Output:["_col0","_col1","_col2"]
- <-Reducer 5 [SIMPLE_EDGE] llap
- SHUFFLE [RS_35]
- Group By Operator [GBY_33] (rows=1 width=20)
+ <-Reducer 3 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_38]
+ Group By Operator [GBY_36] (rows=1 width=20)
Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1
- <-Reducer 4 [SIMPLE_EDGE] llap
- SHUFFLE [RS_32]
+ <-Reducer 2 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_35]
PartitionCols:_col0, _col1
- Group By Operator [GBY_31] (rows=1 width=20)
- Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col6, _col2
- Select Operator [SEL_30] (rows=1 width=20)
- Output:["_col2","_col6"]
+ Group By Operator [GBY_34] (rows=1 width=20)
+ Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4
+ Select Operator [SEL_33] (rows=1 width=20)
+ Output:["_col1","_col4"]
Filter Operator [FIL_29] (rows=1 width=20)
- predicate:(((_col1 + _col4) >= 0) and ((_col1 > 0) or (_col6 >= 0)) and ((_col6 >= 1) or (_col2 >= 1)) and ((UDFToLong(_col6) + _col2) >= 0))
- Merge Join Operator [MERGEJOIN_42] (rows=4 width=20)
- Conds:RS_25._col0=RS_26._col0(Outer),RS_25._col0=RS_27._col0(Right Outer),Output:["_col1","_col2","_col4","_col6"]
- <-Map 10 [SIMPLE_EDGE] llap
- SHUFFLE [RS_27]
+ predicate:(((_col3 + _col6) >= 0) and ((UDFToLong(_col1) + _col4) >= 0) and ((_col1 >= 1) or (_col4 >= 1)) and ((_col3 > 0) or (_col1 >= 0)))
+ Merge Join Operator [MERGEJOIN_50] (rows=3 width=20)
+ Conds:RS_25._col0=RS_26._col0(Inner),RS_26._col0=RS_27._col0(Inner),Output:["_col1","_col3","_col4","_col6"]
+ <-Map 1 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_25]
PartitionCols:_col0
- Select Operator [SEL_24] (rows=20 width=84)
+ Select Operator [SEL_2] (rows=18 width=84)
Output:["_col0","_col1"]
- Filter Operator [FIL_41] (rows=20 width=84)
- predicate:(c_int > 0)
- TableScan [TS_22] (rows=20 width=84)
+ Filter Operator [FIL_47] (rows=18 width=84)
+ predicate:((c_int > 0) and key is not null)
+ TableScan [TS_0] (rows=20 width=84)
default@cbo_t3,cbo_t3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int"]
- <-Reducer 3 [SIMPLE_EDGE] llap
- SHUFFLE [RS_25]
+ <-Reducer 10 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_27]
PartitionCols:_col0
- Select Operator [SEL_9] (rows=1 width=97)
- Output:["_col0","_col1","_col2"]
- <-Reducer 2 [SIMPLE_EDGE] llap
- SHUFFLE [RS_8]
- Select Operator [SEL_6] (rows=1 width=105)
+ Select Operator [SEL_23] (rows=1 width=89)
+ Output:["_col0","_col1"]
+ <-Reducer 9 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_22]
+ Select Operator [SEL_20] (rows=1 width=105)
Output:["_col0","_col1","_col2","_col3"]
- Group By Operator [GBY_5] (rows=1 width=101)
+ Group By Operator [GBY_19] (rows=1 width=101)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Map 1 [SIMPLE_EDGE] llap
- SHUFFLE [RS_4]
+ <-Map 8 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_18]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_3] (rows=1 width=101)
+ Group By Operator [GBY_17] (rows=1 width=101)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
- Filter Operator [FIL_39] (rows=2 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0.0))
- TableScan [TS_0] (rows=20 width=88)
- default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
- <-Reducer 9 [SIMPLE_EDGE] llap
+ Filter Operator [FIL_49] (rows=2 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null)
+ TableScan [TS_14] (rows=20 width=88)
+ default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ <-Reducer 7 [SIMPLE_EDGE] llap
SHUFFLE [RS_26]
PartitionCols:_col0
- Select Operator [SEL_20] (rows=1 width=89)
- Output:["_col0","_col1"]
- <-Reducer 8 [SIMPLE_EDGE] llap
- SHUFFLE [RS_19]
- Select Operator [SEL_17] (rows=1 width=105)
+ Select Operator [SEL_12] (rows=1 width=97)
+ Output:["_col0","_col1","_col2"]
+ <-Reducer 6 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_11]
+ Select Operator [SEL_9] (rows=1 width=105)
Output:["_col0","_col1","_col2","_col3"]
- Group By Operator [GBY_16] (rows=1 width=101)
+ Group By Operator [GBY_8] (rows=1 width=101)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Map 7 [SIMPLE_EDGE] llap
- SHUFFLE [RS_15]
+ <-Map 5 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_7]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_14] (rows=1 width=101)
+ Group By Operator [GBY_6] (rows=1 width=101)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
- Filter Operator [FIL_40] (rows=2 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0.0))
- TableScan [TS_11] (rows=20 width=88)
- default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ Filter Operator [FIL_48] (rows=2 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null)
+ TableScan [TS_3] (rows=20 width=88)
+ default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c
PREHOOK: type: QUERY
@@ -704,83 +684,71 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 2 <- Map 1 (SIMPLE_EDGE)
-Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
-Reducer 4 <- Map 8 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
-Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
+Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+Reducer 5 <- Map 4 (SIMPLE_EDGE)
Reducer 7 <- Map 6 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
- Reducer 5 llap
- File Output Operator [FS_33]
- Select Operator [SEL_32] (rows=1 width=20)
- Output:["_col0","_col1","_col2"]
- Group By Operator [GBY_31] (rows=1 width=20)
- Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1
- <-Reducer 4 [SIMPLE_EDGE] llap
- SHUFFLE [RS_30]
- PartitionCols:_col0, _col1
- Group By Operator [GBY_29] (rows=1 width=20)
- Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col2, _col6
- Select Operator [SEL_28] (rows=3 width=16)
- Output:["_col2","_col6"]
- Filter Operator [FIL_27] (rows=3 width=16)
- predicate:((_col1 > 0) or (_col6 >= 0))
- Merge Join Operator [MERGEJOIN_43] (rows=3 width=16)
- Conds:RS_24._col0=RS_25._col0(Inner),Output:["_col1","_col2","_col6"]
- <-Map 8 [SIMPLE_EDGE] llap
- SHUFFLE [RS_25]
- PartitionCols:_col0
- Select Operator [SEL_23] (rows=18 width=84)
- Output:["_col0","_col1"]
- Filter Operator [FIL_41] (rows=18 width=84)
- predicate:key is not null
- TableScan [TS_21] (rows=20 width=84)
- default@cbo_t3,cbo_t3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int"]
- <-Reducer 3 [SIMPLE_EDGE] llap
- SHUFFLE [RS_24]
- PartitionCols:_col0
- Select Operator [SEL_20] (rows=1 width=101)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_19] (rows=1 width=101)
- predicate:((_col1 + _col4) >= 0)
- Merge Join Operator [MERGEJOIN_42] (rows=1 width=101)
- Conds:RS_16._col0=RS_17._col0(Inner),Output:["_col0","_col1","_col2","_col4"]
- <-Reducer 2 [SIMPLE_EDGE] llap
- SHUFFLE [RS_16]
- PartitionCols:_col0
- Select Operator [SEL_6] (rows=1 width=97)
- Output:["_col0","_col1","_col2"]
- Group By Operator [GBY_5] (rows=1 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Map 1 [SIMPLE_EDGE] llap
- SHUFFLE [RS_4]
- PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_3] (rows=1 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
- Filter Operator [FIL_39] (rows=2 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0.0) and key is not null)
- TableScan [TS_0] (rows=20 width=88)
- default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
- <-Reducer 7 [SIMPLE_EDGE] llap
- SHUFFLE [RS_17]
- PartitionCols:_col0
- Select Operator [SEL_14] (rows=1 width=89)
- Output:["_col0","_col1"]
- Group By Operator [GBY_13] (rows=1 width=93)
- Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Map 6 [SIMPLE_EDGE] llap
- SHUFFLE [RS_12]
- PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_11] (rows=1 width=93)
- Output:["_col0","_col1","_col2"],keys:key, c_int, c_float
- Filter Operator [FIL_40] (rows=2 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0.0) and key is not null)
- TableScan [TS_8] (rows=20 width=88)
- default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ Reducer 3 llap
+ File Output Operator [FS_30]
+ Group By Operator [GBY_28] (rows=1 width=20)
+ Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1
+ <-Reducer 2 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_27]
+ PartitionCols:_col0, _col1
+ Group By Operator [GBY_26] (rows=1 width=20)
+ Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4
+ Select Operator [SEL_25] (rows=1 width=20)
+ Output:["_col1","_col4"]
+ Filter Operator [FIL_23] (rows=1 width=20)
+ predicate:(((_col3 + _col6) >= 0) and ((_col3 > 0) or (_col1 >= 0)))
+ Merge Join Operator [MERGEJOIN_40] (rows=3 width=20)
+ Conds:RS_19._col0=RS_20._col0(Inner),RS_20._col0=RS_21._col0(Inner),Output:["_col1","_col3","_col4","_col6"]
+ <-Map 1 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_19]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=18 width=84)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_37] (rows=18 width=84)
+ predicate:key is not null
+ TableScan [TS_0] (rows=20 width=84)
+ default@cbo_t3,cbo_t3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int"]
+ <-Reducer 5 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_20]
+ PartitionCols:_col0
+ Select Operator [SEL_9] (rows=1 width=97)
+ Output:["_col0","_col1","_col2"]
+ Group By Operator [GBY_8] (rows=1 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
+ <-Map 4 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_7]
+ PartitionCols:_col0, _col1, _col2
+ Group By Operator [GBY_6] (rows=1 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
+ Filter Operator [FIL_38] (rows=2 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null)
+ TableScan [TS_3] (rows=20 width=88)
+ default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ <-Reducer 7 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_21]
+ PartitionCols:_col0
+ Select Operator [SEL_17] (rows=1 width=89)
+ Output:["_col0","_col1"]
+ Group By Operator [GBY_16] (rows=1 width=93)
+ Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2
+ <-Map 6 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_15]
+ PartitionCols:_col0, _col1, _col2
+ Group By Operator [GBY_14] (rows=1 width=93)
+ Output:["_col0","_col1","_col2"],keys:key, c_int, c_float
+ Filter Operator [FIL_39] (rows=2 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and key is not null)
+ TableScan [TS_11] (rows=20 width=88)
+ default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
PREHOOK: query: explain select unionsrc.key FROM (select 'tst1' as key, count(1) as value from src) unionsrc
PREHOOK: type: QUERY
@@ -1155,55 +1123,47 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
-Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
- Reducer 3 llap
- File Output Operator [FS_19]
- Select Operator [SEL_18] (rows=36 width=101)
+ Reducer 2 llap
+ File Output Operator [FS_16]
+ Select Operator [SEL_15] (rows=72 width=101)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_17] (rows=36 width=101)
- predicate:((_col1 > 0) or (_col6 >= 0))
- Merge Join Operator [MERGEJOIN_28] (rows=36 width=101)
- Conds:RS_14._col0=RS_15._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6"]
- <-Map 5 [SIMPLE_EDGE] llap
- SHUFFLE [RS_15]
+ Filter Operator [FIL_13] (rows=72 width=101)
+ predicate:(((_col1 > 0) or (_col6 >= 0)) and ((_col1 + _col4) = 2))
+ Merge Join Operator [MERGEJOIN_26] (rows=145 width=101)
+ Conds:RS_9._col0=RS_10._col0(Inner),RS_9._col0=RS_11._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6"]
+ <-Map 1 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_9]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=9 width=93)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_23] (rows=9 width=93)
+ predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null)
+ TableScan [TS_0] (rows=20 width=88)
+ default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ <-Map 3 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_10]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=9 width=89)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_24] (rows=9 width=93)
+ predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null)
+ TableScan [TS_3] (rows=20 width=88)
+ default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ <-Map 4 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_11]
PartitionCols:_col0
- Select Operator [SEL_13] (rows=18 width=84)
+ Select Operator [SEL_8] (rows=18 width=84)
Output:["_col0","_col1"]
- Filter Operator [FIL_26] (rows=18 width=84)
+ Filter Operator [FIL_25] (rows=18 width=84)
predicate:key is not null
- TableScan [TS_11] (rows=20 width=84)
+ TableScan [TS_6] (rows=20 width=84)
default@cbo_t3,cbo_t3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int"]
- <-Reducer 2 [SIMPLE_EDGE] llap
- SHUFFLE [RS_14]
- PartitionCols:_col0
- Filter Operator [FIL_9] (rows=10 width=182)
- predicate:(((_col1 + _col4) = 2) and ((_col4 + 1) = 2))
- Merge Join Operator [MERGEJOIN_27] (rows=40 width=182)
- Conds:RS_6._col0=RS_7._col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4"]
- <-Map 1 [SIMPLE_EDGE] llap
- SHUFFLE [RS_6]
- PartitionCols:_col0
- Select Operator [SEL_2] (rows=9 width=93)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_24] (rows=9 width=93)
- predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null)
- TableScan [TS_0] (rows=20 width=88)
- default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
- <-Map 4 [SIMPLE_EDGE] llap
- SHUFFLE [RS_7]
- PartitionCols:_col0
- Select Operator [SEL_5] (rows=9 width=89)
- Output:["_col0","_col1"]
- Filter Operator [FIL_25] (rows=9 width=93)
- predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null)
- TableScan [TS_3] (rows=20 width=88)
- default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
PREHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 right outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0)
PREHOOK: type: QUERY
@@ -1219,38 +1179,40 @@ Stage-0
limit:-1
Stage-1
Reducer 2 llap
- File Output Operator [FS_14]
- Select Operator [SEL_13] (rows=50 width=101)
+ File Output Operator [FS_16]
+ Select Operator [SEL_15] (rows=72 width=101)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_12] (rows=50 width=101)
- predicate:(((_col1 + _col4) = 2) and ((_col1 > 0) or (_col6 >= 0)) and ((_col4 + 1) = 2))
- Merge Join Operator [MERGEJOIN_19] (rows=200 width=101)
- Conds:RS_8._col0=RS_9._col0(Right Outer),RS_8._col0=RS_10._col0(Right Outer),Output:["_col1","_col2","_col3","_col4","_col6"]
+ Filter Operator [FIL_13] (rows=72 width=101)
+ predicate:(((_col1 > 0) or (_col6 >= 0)) and ((_col1 + _col4) = 2))
+ Merge Join Operator [MERGEJOIN_26] (rows=145 width=101)
+ Conds:RS_9._col0=RS_10._col0(Inner),RS_9._col0=RS_11._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6"]
<-Map 1 [SIMPLE_EDGE] llap
- SHUFFLE [RS_8]
+ SHUFFLE [RS_9]
PartitionCols:_col0
- Select Operator [SEL_2] (rows=10 width=93)
+ Select Operator [SEL_2] (rows=9 width=93)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_17] (rows=10 width=93)
- predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)))
+ Filter Operator [FIL_23] (rows=9 width=93)
+ predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null)
TableScan [TS_0] (rows=20 width=88)
default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
<-Map 3 [SIMPLE_EDGE] llap
- SHUFFLE [RS_9]
+ SHUFFLE [RS_10]
PartitionCols:_col0
- Select Operator [SEL_5] (rows=10 width=89)
+ Select Operator [SEL_5] (rows=9 width=89)
Output:["_col0","_col1"]
- Filter Operator [FIL_18] (rows=10 width=93)
- predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)))
+ Filter Operator [FIL_24] (rows=9 width=93)
+ predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0)) and key is not null)
TableScan [TS_3] (rows=20 width=88)
default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
<-Map 4 [SIMPLE_EDGE] llap
- SHUFFLE [RS_10]
+ SHUFFLE [RS_11]
PartitionCols:_col0
- Select Operator [SEL_7] (rows=20 width=84)
+ Select Operator [SEL_8] (rows=18 width=84)
Output:["_col0","_col1"]
- TableScan [TS_6] (rows=20 width=84)
- default@cbo_t3,cbo_t3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int"]
+ Filter Operator [FIL_25] (rows=18 width=84)
+ predicate:key is not null
+ TableScan [TS_6] (rows=20 width=84)
+ default@cbo_t3,cbo_t3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int"]
PREHOOK: query: explain select key, (c_int+1)+2 as x, sum(c_int) from cbo_t1 group by c_float, cbo_t1.c_int, key order by x limit 1
PREHOOK: type: QUERY
@@ -1418,108 +1380,98 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 10 <- Reducer 9 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
-Reducer 5 <- Map 11 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
+Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
-Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
-Reducer 9 <- Map 8 (SIMPLE_EDGE)
+Reducer 8 <- Map 7 (SIMPLE_EDGE)
+Reducer 9 <- Reducer 8 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:5
Stage-1
- Reducer 7 llap
- File Output Operator [FS_49]
- Limit [LIM_48] (rows=1 width=20)
+ Reducer 6 llap
+ File Output Operator [FS_45]
+ Limit [LIM_44] (rows=1 width=20)
Number of rows:5
- Select Operator [SEL_47] (rows=1 width=20)
+ Select Operator [SEL_43] (rows=1 width=20)
Output:["_col0","_col1","_col2"]
- <-Reducer 6 [SIMPLE_EDGE] llap
- SHUFFLE [RS_46]
- Select Operator [SEL_44] (rows=1 width=20)
+ <-Reducer 5 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_42]
+ Select Operator [SEL_41] (rows=1 width=20)
Output:["_col0","_col1","_col2"]
- Group By Operator [GBY_43] (rows=1 width=20)
+ Group By Operator [GBY_40] (rows=1 width=20)
Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1
- <-Reducer 5 [SIMPLE_EDGE] llap
- SHUFFLE [RS_42]
+ <-Reducer 4 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_39]
PartitionCols:_col0, _col1
- Group By Operator [GBY_41] (rows=1 width=20)
- Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col2, _col6
- Select Operator [SEL_40] (rows=3 width=16)
- Output:["_col2","_col6"]
- Filter Operator [FIL_39] (rows=3 width=16)
- predicate:((_col1 > 0) or (_col6 >= 0))
- Merge Join Operator [MERGEJOIN_61] (rows=3 width=16)
- Conds:RS_36._col0=RS_37._col0(Inner),Output:["_col1","_col2","_col6"]
- <-Map 11 [SIMPLE_EDGE] llap
- SHUFFLE [RS_37]
+ Group By Operator [GBY_38] (rows=1 width=20)
+ Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col4, _col6
+ Select Operator [SEL_37] (rows=3 width=20)
+ Output:["_col4","_col6"]
+ Filter Operator [FIL_35] (rows=3 width=20)
+ predicate:(((_col3 > 0) or (_col6 >= 0)) and ((_col3 + _col1) >= 0))
+ Merge Join Operator [MERGEJOIN_57] (rows=7 width=20)
+ Conds:RS_31._col0=RS_32._col0(Inner),RS_32._col0=RS_33._col0(Inner),Output:["_col1","_col3","_col4","_col6"]
+ <-Map 10 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_33]
PartitionCols:_col0
- Select Operator [SEL_35] (rows=18 width=84)
+ Select Operator [SEL_30] (rows=18 width=84)
Output:["_col0","_col1"]
- Filter Operator [FIL_59] (rows=18 width=84)
+ Filter Operator [FIL_56] (rows=18 width=84)
predicate:key is not null
- TableScan [TS_33] (rows=20 width=84)
+ TableScan [TS_28] (rows=20 width=84)
default@cbo_t3,cbo_t3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int"]
- <-Reducer 4 [SIMPLE_EDGE] llap
- SHUFFLE [RS_36]
+ <-Reducer 3 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_31]
PartitionCols:_col0
- Select Operator [SEL_32] (rows=1 width=101)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_31] (rows=1 width=101)
- predicate:((_col1 + _col4) >= 0)
- Merge Join Operator [MERGEJOIN_60] (rows=2 width=101)
- Conds:RS_28._col0=RS_29._col0(Inner),Output:["_col0","_col1","_col2","_col4"]
- <-Reducer 10 [SIMPLE_EDGE] llap
- SHUFFLE [RS_29]
- PartitionCols:_col0
- Filter Operator [FIL_26] (rows=2 width=105)
- predicate:_col0 is not null
- Limit [LIM_24] (rows=3 width=105)
- Number of rows:5
- Select Operator [SEL_23] (rows=3 width=105)
- Output:["_col0","_col1"]
- <-Reducer 9 [SIMPLE_EDGE] llap
- SHUFFLE [RS_22]
- Select Operator [SEL_20] (rows=3 width=105)
- Output:["_col0","_col1","_col2","_col3"]
- Group By Operator [GBY_19] (rows=3 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Map 8 [SIMPLE_EDGE] llap
- SHUFFLE [RS_18]
- PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_17] (rows=3 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
- Filter Operator [FIL_58] (rows=6 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)))
- TableScan [TS_14] (rows=20 width=88)
- default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
- <-Reducer 3 [SIMPLE_EDGE] llap
- SHUFFLE [RS_28]
- PartitionCols:_col0
- Filter Operator [FIL_12] (rows=2 width=97)
- predicate:_col0 is not null
- Limit [LIM_10] (rows=3 width=97)
- Number of rows:5
- Select Operator [SEL_9] (rows=3 width=97)
- Output:["_col0","_col1","_col2"]
- <-Reducer 2 [SIMPLE_EDGE] llap
- SHUFFLE [RS_8]
- Select Operator [SEL_6] (rows=3 width=97)
- Output:["_col0","_col1","_col2"]
- Group By Operator [GBY_5] (rows=3 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Map 1 [SIMPLE_EDGE] llap
- SHUFFLE [RS_4]
- PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_3] (rows=3 width=101)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
- Filter Operator [FIL_56] (rows=6 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)))
- TableScan [TS_0] (rows=20 width=88)
- default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ Filter Operator [FIL_12] (rows=2 width=105)
+ predicate:_col0 is not null
+ Limit [LIM_10] (rows=3 width=105)
+ Number of rows:5
+ Select Operator [SEL_9] (rows=3 width=105)
+ Output:["_col0","_col1"]
+ <-Reducer 2 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_8]
+ Select Operator [SEL_6] (rows=3 width=105)
+ Output:["_col0","_col1","_col2","_col3"]
+ Group By Operator [GBY_5] (rows=3 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
+ <-Map 1 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_4]
+ PartitionCols:_col0, _col1, _col2
+ Group By Operator [GBY_3] (rows=3 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
+ Filter Operator [FIL_53] (rows=6 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)))
+ TableScan [TS_0] (rows=20 width=88)
+ default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ <-Reducer 9 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_32]
+ PartitionCols:_col0
+ Filter Operator [FIL_26] (rows=2 width=97)
+ predicate:_col0 is not null
+ Limit [LIM_24] (rows=3 width=97)
+ Number of rows:5
+ Select Operator [SEL_23] (rows=3 width=97)
+ Output:["_col0","_col1","_col2"]
+ <-Reducer 8 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_22]
+ Select Operator [SEL_20] (rows=3 width=97)
+ Output:["_col0","_col1","_col2"]
+ Group By Operator [GBY_19] (rows=3 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
+ <-Map 7 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_18]
+ PartitionCols:_col0, _col1, _col2
+ Group By Operator [GBY_17] (rows=3 width=101)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
+ Filter Operator [FIL_55] (rows=6 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)))
+ TableScan [TS_14] (rows=20 width=88)
+ default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
PREHOOK: query: explain select cbo_t1.c_int from cbo_t1 left semi join cbo_t2 on cbo_t1.key=cbo_t2.key where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)
PREHOOK: type: QUERY
@@ -1680,7 +1632,7 @@ Stage-0
Group By Operator [GBY_3] (rows=1 width=101)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
Filter Operator [FIL_48] (rows=1 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0.0) and (((c_int + 1) + 1) >= 0) and (((c_int + 1) > 0) or (UDFToDouble(key) >= 0.0)) and (UDFToDouble(key) > 0.0))
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and (((c_int + 1) + 1) >= 0) and (((c_int + 1) > 0) or (UDFToDouble(key) >= 0.0)) and (UDFToDouble(key) > 0.0))
TableScan [TS_0] (rows=20 width=88)
default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
<-Reducer 9 [SIMPLE_EDGE] llap
@@ -1702,7 +1654,7 @@ Stage-0
Group By Operator [GBY_15] (rows=1 width=101)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
Filter Operator [FIL_49] (rows=1 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0.0) and (UDFToDouble(key) > 0.0))
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and (c_float > 0) and ((c_int >= 1) or (c_float >= 1)) and ((UDFToFloat(c_int) + c_float) >= 0) and (UDFToDouble(key) > 0.0))
TableScan [TS_12] (rows=20 width=88)
default@cbo_t2,cbo_t2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
@@ -2430,10 +2382,10 @@ Stage-0
<-Reducer 7 [SIMPLE_EDGE] llap
SHUFFLE [RS_22]
PartitionCols:_col0, _col1
- Select Operator [SEL_17] (rows=1 width=223)
+ Select Operator [SEL_17] (rows=2 width=223)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_16] (rows=1 width=219)
- predicate:(_col0 = _col0)
+ Filter Operator [FIL_16] (rows=2 width=219)
+ predicate:_col0 is not null
Group By Operator [GBY_14] (rows=2 width=219)
Output:["_col0","_col1"],keys:KEY._col0, KEY._col1
<-Map 6 [SIMPLE_EDGE] llap
@@ -2468,41 +2420,40 @@ Plan optimized by CBO.
Vertex dependency in root stage
Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE)
-Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
+Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE)
Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE)
-Reducer 9 <- Reducer 8 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
Reducer 4 llap
- File Output Operator [FS_36]
- Select Operator [SEL_35] (rows=26 width=125)
+ File Output Operator [FS_31]
+ Select Operator [SEL_30] (rows=26 width=125)
Output:["_col0","_col1"]
<-Reducer 3 [SIMPLE_EDGE] llap
- SHUFFLE [RS_34]
- Select Operator [SEL_33] (rows=26 width=125)
+ SHUFFLE [RS_29]
+ Select Operator [SEL_28] (rows=26 width=125)
Output:["_col0","_col1"]
- Filter Operator [FIL_32] (rows=26 width=145)
+ Filter Operator [FIL_27] (rows=26 width=145)
predicate:((_col2 = 0) or (_col5 is null and _col1 is not null and (_col3 >= _col2)))
- Merge Join Operator [MERGEJOIN_42] (rows=26 width=145)
- Conds:RS_29.UDFToDouble(_col1)=RS_30._col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5"]
+ Merge Join Operator [MERGEJOIN_37] (rows=26 width=145)
+ Conds:RS_24.UDFToDouble(_col1)=RS_25._col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5"]
<-Reducer 2 [SIMPLE_EDGE] llap
- SHUFFLE [RS_29]
+ SHUFFLE [RS_24]
PartitionCols:UDFToDouble(_col1)
- Merge Join Operator [MERGEJOIN_41] (rows=26 width=141)
+ Merge Join Operator [MERGEJOIN_36] (rows=26 width=141)
Conds:(Inner),Output:["_col0","_col1","_col2","_col3"]
<-Map 1 [CUSTOM_SIMPLE_EDGE] llap
- PARTITION_ONLY_SHUFFLE [RS_26]
+ PARTITION_ONLY_SHUFFLE [RS_21]
Select Operator [SEL_1] (rows=26 width=125)
Output:["_col0","_col1"]
TableScan [TS_0] (rows=26 width=125)
default@part,part,Tbl:COMPLETE,Col:COMPLETE,Output:["p_name","p_size"]
<-Reducer 6 [CUSTOM_SIMPLE_EDGE] llap
- PARTITION_ONLY_SHUFFLE [RS_27]
+ PARTITION_ONLY_SHUFFLE [RS_22]
Group By Operator [GBY_12] (rows=1 width=16)
Output:["_col0","_col1"],aggregations:["count()","count(_col0)"]
Group By Operator [GBY_7] (rows=1 width=8)
@@ -2511,32 +2462,25 @@ Stage-0
PARTITION_ONLY_SHUFFLE [RS_6]
Group By Operator [GBY_5] (rows=1 width=76)
Output:["_col0"],aggregations:["avg(p_size)"]
- Filter Operator [FIL_38] (rows=8 width=4)
+ Filter Operator [FIL_33] (rows=8 width=4)
predicate:(p_size < 10)
TableScan [TS_2] (rows=26 width=4)
default@part,part,Tbl:COMPLETE,Col:COMPLETE,Output:["p_size"]
- <-Reducer 9 [SIMPLE_EDGE] llap
- SHUFFLE [RS_30]
+ <-Reducer 8 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_25]
PartitionCols:_col0
- Select Operator [SEL_25] (rows=1 width=12)
+ Select Operator [SEL_20] (rows=1 width=12)
Output:["_col0","_col1"]
- Group By Operator [GBY_24] (rows=1 width=8)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 8 [SIMPLE_EDGE] llap
- SHUFFLE [RS_23]
- PartitionCols:_col0
- Group By Operator [GBY_22] (rows=1 width=8)
- Output:["_col0"],keys:_col0
- Group By Operator [GBY_19] (rows=1 width=8)
- Output:["_col0"],aggregations:["avg(VALUE._col0)"]
- <-Map 7 [CUSTOM_SIMPLE_EDGE] llap
- PARTITION_ONLY_SHUFFLE [RS_18]
- Group By Operator [GBY_17] (rows=1 width=76)
- Output:["_col0"],aggregations:["avg(p_size)"]
- Filter Operator [FIL_40] (rows=8 width=4)
- predicate:(p_size < 10)
- TableScan [TS_14] (rows=26 width=4)
- default@part,part,Tbl:COMPLETE,Col:COMPLETE,Output:["p_size"]
+ Group By Operator [GBY_19] (rows=1 width=8)
+ Output:["_col0"],aggregations:["avg(VALUE._col0)"]
+ <-Map 7 [CUSTOM_SIMPLE_EDGE] llap
+ PARTITION_ONLY_SHUFFLE [RS_18]
+ Group By Operator [GBY_17] (rows=1 width=76)
+ Output:["_col0"],aggregations:["avg(p_size)"]
+ Filter Operator [FIL_35] (rows=8 width=4)
+ predicate:(p_size < 10)
+ TableScan [TS_14] (rows=26 width=4)
+ default@part,part,Tbl:COMPLETE,Col:COMPLETE,Output:["p_size"]
PREHOOK: query: explain select b.p_mfgr, min(p_retailprice)
from part b
@@ -2562,10 +2506,9 @@ Plan optimized by CBO.
Vertex dependency in root stage
Reducer 10 <- Map 9 (SIMPLE_EDGE)
-Reducer 11 <- Reducer 10 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
-Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
Reducer 7 <- Map 6 (SIMPLE_EDGE)
Reducer 8 <- Reducer 7 (SIMPLE_EDGE)
@@ -2575,51 +2518,44 @@ Stage-0
limit:-1
Stage-1
Reducer 5 llap
- File Output Operator [FS_42]
- Select Operator [SEL_41] (rows=3 width=106)
+ File Output Operator [FS_37]
+ Select Operator [SEL_36] (rows=3 width=106)
Output:["_col0","_col1"]
<-Reducer 4 [SIMPLE_EDGE] llap
- SHUFFLE [RS_40]
- Select Operator [SEL_39] (rows=3 width=106)
+ SHUFFLE [RS_35]
+ Select Operator [SEL_34] (rows=3 width=106)
Output:["_col0","_col1"]
- Filter Operator [FIL_38] (rows=3 width=126)
+ Filter Operator [FIL_33] (rows=3 width=126)
predicate:(not CASE WHEN ((_col3 = 0)) THEN (false) WHEN (_col3 is null) THEN (false) WHEN (_col7 is not null) THEN (true) WHEN (_col0 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (true) ELSE (false) END)
- Merge Join Operator [MERGEJOIN_49] (rows=5 width=126)
- Conds:RS_35._col0, _col1=RS_36._col0, _col1(Left Outer),Output:["_col0","_col1","_col3","_col4","_col7"]
- <-Reducer 11 [SIMPLE_EDGE] llap
- SHUFFLE [RS_36]
+ Merge Join Operator [MERGEJOIN_44] (rows=5 width=126)
+ Conds:RS_30._col0, _col1=RS_31._col0, _col1(Left Outer),Output:["_col0","_col1","_col3","_col4","_col7"]
+ <-Reducer 10 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_31]
PartitionCols:_col0, _col1
- Select Operator [SEL_31] (rows=1 width=110)
+ Select Operator [SEL_26] (rows=1 width=110)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_30] (rows=1 width=106)
- predicate:(_col0 = _col0)
- Group By Operator [GBY_28] (rows=1 width=106)
- Output:["_col0","_col1"],keys:KEY._col0, KEY._col1
- <-Reducer 10 [SIMPLE_EDGE] llap
- SHUFFLE [RS_27]
- PartitionCols:_col0, _col1
- Group By Operator [GBY_26] (rows=1 width=106)
- Output:["_col0","_col1"],keys:_col0, _col1
- Select Operator [SEL_24] (rows=1 width=114)
- Output:["_col0","_col1"]
- Filter Operator [FIL_46] (rows=1 width=114)
- predicate:((_col1 = _col1) and ((_col2 - _col1) > 600.0))
- Group By Operator [GBY_22] (rows=5 width=114)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)"],keys:KEY._col0
- <-Map 9 [SIMPLE_EDGE] llap
- SHUFFLE [RS_21]
- PartitionCols:_col0
- Group By Operator [GBY_20] (rows=5 width=114)
- Output:["_col0","_col1","_col2"],aggregations:["min(p_retailprice)","max(p_retailprice)"],keys:p_mfgr
- TableScan [TS_18] (rows=26 width=106)
- default@part,part,Tbl:COMPLETE,Col:COMPLETE,Output:["p_mfgr","p_retailprice"]
+ Filter Operator [FIL_25] (rows=1 width=110)
+ predicate:_col0 is not null
+ Select Operator [SEL_24] (rows=1 width=110)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_41] (rows=1 width=114)
+ predicate:((_col1 = _col1) and ((_col2 - _col1) > 600.0))
+ Group By Operator [GBY_22] (rows=5 width=114)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)"],keys:KEY._col0
+ <-Map 9 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_21]
+ PartitionCols:_col0
+ Group By Operator [GBY_20] (rows=5 width=114)
+ Output:["_col0","_col1","_col2"],aggregations:["min(p_retailprice)","max(p_retailprice)"],keys:p_mfgr
+ TableScan [TS_18] (rows=26 width=106)
+ default@part,part,Tbl:COMPLETE,Col:COMPLETE,Output:["p_mfgr","p_retailprice"]
<-Reducer 3 [SIMPLE_EDGE] llap
- SHUFFLE [RS_35]
+ SHUFFLE [RS_30]
PartitionCols:_col0, _col1
- Merge Join Operator [MERGEJOIN_48] (rows=5 width=122)
- Conds:RS_32._col1=RS_33._col0(Left Outer),Output:["_col0","_col1","_col3","_col4"]
+ Merge Join Operator [MERGEJOIN_43] (rows=5 width=122)
+ Conds:RS_27._col1=RS_28._col0(Left Outer),Output:["_col0","_col1","_col3","_col4"]
<-Reducer 2 [SIMPLE_EDGE] llap
- SHUFFLE [RS_32]
+ SHUFFLE [RS_27]
PartitionCols:_col1
Group By Operator [GBY_4] (rows=5 width=106)
Output:["_col0","_col1"],aggregations:["min(VALUE._col0)"],keys:KEY._col0
@@ -2633,7 +2569,7 @@ Stage-0
TableScan [TS_0] (rows=26 width=106)
default@part,b,Tbl:COMPLETE,Col:COMPLETE,Output:["p_mfgr","p_retailprice"]
<-Reducer 8 [SIMPLE_EDGE] llap
- SHUFFLE [RS_33]
+ SHUFFLE [RS_28]
PartitionCols:_col0
Group By Operator [GBY_16] (rows=1 width=24)
Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0
@@ -2644,7 +2580,7 @@ Stage-0
Output:["_col0","_col1","_col2"],aggregations:["count()","count(_col0)"],keys:_col1
Select Operator [SEL_12] (rows=1 width=114)
Output:["_col0","_col1"]
- Filter Operator [FIL_45] (rows=1 width=114)
+ Filter Operator [FIL_40] (rows=1 width=114)
predicate:((_col1 = _col1) and ((_col2 - _col1) > 600.0))
Group By Operator [GBY_10] (rows=5 width=114)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)"],keys:KEY._col0
diff --git a/ql/src/test/results/clientpositive/llap/explainuser_4.q.out b/ql/src/test/results/clientpositive/llap/explainuser_4.q.out
index 9804569..023627e 100644
--- a/ql/src/test/results/clientpositive/llap/explainuser_4.q.out
+++ b/ql/src/test/results/clientpositive/llap/explainuser_4.q.out
@@ -499,7 +499,7 @@ Stage-0
Reducer 2 llap
File Output Operator [FS_8]
Merge Join Operator [MERGEJOIN_9] (rows=150994944 width=431)
- Conds:(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"],residual filter predicates:{((_col2 = _col14) or _col1 BETWEEN 1 AND 10)}
+ Conds:(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"],residual filter predicates:{((_col2 = _col14) or UDFToInteger(_col1) BETWEEN 1 AND 10)}
<-Map 1 [CUSTOM_SIMPLE_EDGE] llap
PARTITION_ONLY_SHUFFLE [RS_4]
Select Operator [SEL_1] (rows=12288 width=215)
diff --git a/ql/src/test/results/clientpositive/llap/lineage3.q.out b/ql/src/test/results/clientpositive/llap/lineage3.q.out
index 2f53e60..25f0439 100644
--- a/ql/src/test/results/clientpositive/llap/lineage3.q.out
+++ b/ql/src/test/results/clientpositive/llap/lineage3.q.out
@@ -166,7 +166,7 @@ where key in (select key+18 from src1) order by key
PREHOOK: type: QUERY
PREHOOK: Input: default@src1
#### A masked pattern was here ####
-{"version":"1.0","engine":"tez","database":"default","hash":"8b9d63653e36ecf4dd425d3cc3de9199","queryText":"select key, value from src1\nwhere key in (select key+18 from src1) order by key","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"src1.key is not null","edgeType":"PREDICATE"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(src1.key) = (UDFToDouble(src1.key) + 18.0))","edgeType":"PREDICATE"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(src1.key) + 18.0) is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"key"},{"id":1,"vertexType":"COLUMN","vertexId":"value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]}
+{"version":"1.0","engine":"tez","database":"default","hash":"8b9d63653e36ecf4dd425d3cc3de9199","queryText":"select key, value from src1\nwhere key in (select key+18 from src1) order by key","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"src1.key is not null","edgeType":"PREDICATE"},{"sources":[2],"targets":[0,1],"expression":"(UDFToDouble(src1.key) = (UDFToDouble(src1.key) + 18.0))","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"key"},{"id":1,"vertexType":"COLUMN","vertexId":"value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]}
146 val_146
273 val_273
PREHOOK: query: select * from src1 a
@@ -297,7 +297,7 @@ PREHOOK: type: CREATEVIEW
PREHOOK: Input: default@alltypesorc
PREHOOK: Output: database:default
PREHOOK: Output: default@dest_v3
-{"version":"1.0","engine":"tez","database":"default","hash":"a0c2481ce1c24895a43a950f93a10da7","queryText":"create view dest_v3 (a1, a2, a3, a4, a5, a6, a7) as\n select x.csmallint, x.cbigint bint1, x.ctinyint, c.cbigint bint2, x.cint, x.cfloat, c.cstring1\n from alltypesorc c\n join (\n select a.csmallint csmallint, a.ctinyint ctinyint, a.cstring2 cstring2,\n a.cint cint, a.cstring1 ctring1, b.cfloat cfloat, b.cbigint cbigint\n from ( select * from alltypesorc a where cboolean1=true ) a\n join alltypesorc b on (a.csmallint = b.cint)\n ) x on (x.ctinyint = c.cbigint)\n where x.csmallint=11\n and x.cint > 899\n and x.cfloat > 4.5\n and c.cstring1 < '7'\n and x.cint + x.cfloat + length(c.cstring1) < 1000","edges":[{"sources":[],"targets":[0],"expression":"11","edgeType":"PROJECTION"},{"sources":[7],"targets":[1,2],"edgeType":"PROJECTION"},{"sources":[8],"targets":[3],"edgeType":"PROJECTION"},{"sources":[9],"targets":[4],"edgeType":"PROJECTION"},{"sources":[10],"targets":[5],"edgeType":"PROJECTION"},{"sources":[11],"targets":[6],"edgeType":"PROJECTION"},{"sources":[11,7],"targets":[0,1,3,2,4,5,6],"expression":"((c.cstring1 < '7') and c.cbigint is not null)","edgeType":"PREDICATE"},{"sources":[7,8],"targets":[0,1,3,2,4,5,6],"expression":"(c.cbigint = UDFToLong(a.ctinyint))","edgeType":"PREDICATE"},{"sources":[10,9],"targets":[0,1,3,2,4,5,6],"expression":"((b.cfloat > 4.5) and (11 = b.cint))","edgeType":"PREDICATE"},{"sources":[12,13,9,8],"targets":[0,1,3,2,4,5,6],"expression":"(a.cboolean1 and (a.csmallint = 11) and (a.cint > 899) and a.ctinyint is not null)","edgeType":"PREDICATE"},{"sources":[9,10,11],"targets":[0,1,3,2,4,5,6],"expression":"(((UDFToFloat(a.cint) + b.cfloat) + UDFToFloat(length(c.cstring1))) < 1000.0)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest_v3.csmallint"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest_v3.bint1"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest_v3.bint2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest_v3.ctinyint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.dest_v3.cint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.dest_v3.cfloat"},{"id":6,"vertexType":"COLUMN","vertexId":"default.dest_v3.cstring1"},{"id":7,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"},{"id":8,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":9,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":10,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cfloat"},{"id":11,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring1"},{"id":12,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean1"},{"id":13,"vertexType":"COLUMN","vertexId":"default.alltypesorc.csmallint"}]}
+{"version":"1.0","engine":"tez","database":"default","hash":"a0c2481ce1c24895a43a950f93a10da7","queryText":"create view dest_v3 (a1, a2, a3, a4, a5, a6, a7) as\n select x.csmallint, x.cbigint bint1, x.ctinyint, c.cbigint bint2, x.cint, x.cfloat, c.cstring1\n from alltypesorc c\n join (\n select a.csmallint csmallint, a.ctinyint ctinyint, a.cstring2 cstring2,\n a.cint cint, a.cstring1 ctring1, b.cfloat cfloat, b.cbigint cbigint\n from ( select * from alltypesorc a where cboolean1=true ) a\n join alltypesorc b on (a.csmallint = b.cint)\n ) x on (x.ctinyint = c.cbigint)\n where x.csmallint=11\n and x.cint > 899\n and x.cfloat > 4.5\n and c.cstring1 < '7'\n and x.cint + x.cfloat + length(c.cstring1) < 1000","edges":[{"sources":[],"targets":[0],"expression":"11","edgeType":"PROJECTION"},{"sources":[7],"targets":[1,2],"edgeType":"PROJECTION"},{"sources":[8],"targets":[3],"edgeType":"PROJECTION"},{"sources":[9],"targets":[4],"edgeType":"PROJECTION"},{"sources":[10],"targets":[5],"edgeType":"PROJECTION"},{"sources":[11],"targets":[6],"edgeType":"PROJECTION"},{"sources":[11,7],"targets":[0,1,3,2,4,5,6],"expression":"((c.cstring1 < '7') and c.cbigint is not null)","edgeType":"PREDICATE"},{"sources":[7,8],"targets":[0,1,3,2,4,5,6],"expression":"(c.cbigint = UDFToLong(a.ctinyint))","edgeType":"PREDICATE"},{"sources":[10,9],"targets":[0,1,3,2,4,5,6],"expression":"((b.cfloat > 4.5) and (11 = b.cint))","edgeType":"PREDICATE"},{"sources":[12,13,9,8],"targets":[0,1,3,2,4,5,6],"expression":"(a.cboolean1 and (a.csmallint = 11) and (a.cint > 899) and a.ctinyint is not null)","edgeType":"PREDICATE"},{"sources":[9,10,11],"targets":[0,1,3,2,4,5,6],"expression":"(((UDFToFloat(a.cint) + b.cfloat) + UDFToFloat(length(c.cstring1))) < 1000)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest_v3.csmallint"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest_v3.bint1"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest_v3.bint2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest_v3.ctinyint"},{"id":4,"vertexType":"COLUMN","vertexId":"default.dest_v3.cint"},{"id":5,"vertexType":"COLUMN","vertexId":"default.dest_v3.cfloat"},{"id":6,"vertexType":"COLUMN","vertexId":"default.dest_v3.cstring1"},{"id":7,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cbigint"},{"id":8,"vertexType":"COLUMN","vertexId":"default.alltypesorc.ctinyint"},{"id":9,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cint"},{"id":10,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cfloat"},{"id":11,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cstring1"},{"id":12,"vertexType":"COLUMN","vertexId":"default.alltypesorc.cboolean1"},{"id":13,"vertexType":"COLUMN","vertexId":"default.alltypesorc.csmallint"}]}
PREHOOK: query: alter view dest_v3 as
select * from (
select sum(a.ctinyint) over (partition by a.csmallint order by a.csmallint) a,
diff --git a/ql/src/test/results/clientpositive/llap/mergejoin.q.out b/ql/src/test/results/clientpositive/llap/mergejoin.q.out
index 64929cc..45e58e0 100644
--- a/ql/src/test/results/clientpositive/llap/mergejoin.q.out
+++ b/ql/src/test/results/clientpositive/llap/mergejoin.q.out
@@ -2806,16 +2806,14 @@ POSTHOOK: Input: default@tab_part@ds=2008-04-08
#### A masked pattern was here ####
NULL NULL NULL 98 val_98 2008-04-08
NULL NULL NULL 98 val_98 2008-04-08
-Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[18][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select * from
(select * from tab where tab.key = 0)a
full outer join
(select * from tab_part where tab_part.key = 98)b join tab_part c on a.key = b.key and b.key = c.key
PREHOOK: type: QUERY
PREHOOK: Input: default@tab
-PREHOOK: Input: default@tab@ds=2008-04-08
PREHOOK: Input: default@tab_part
-PREHOOK: Input: default@tab_part@ds=2008-04-08
#### A masked pattern was here ####
POSTHOOK: query: select * from
(select * from tab where tab.key = 0)a
@@ -2823,9 +2821,7 @@ full outer join
(select * from tab_part where tab_part.key = 98)b join tab_part c on a.key = b.key and b.key = c.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab
-POSTHOOK: Input: default@tab@ds=2008-04-08
POSTHOOK: Input: default@tab_part
-POSTHOOK: Input: default@tab_part@ds=2008-04-08
#### A masked pattern was here ####
Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
@@ -3379,15 +3375,14 @@ NULL NULL NULL NULL NULL NULL 97 val_97 2008-04-08
NULL NULL NULL NULL NULL NULL 97 val_97 2008-04-08
NULL NULL NULL NULL NULL NULL 98 val_98 2008-04-08
NULL NULL NULL NULL NULL NULL 98 val_98 2008-04-08
-Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[18][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: select * from
(select * from tab where tab.key = 0)a
join
(select * from tab_part where tab_part.key = 98)b on a.key = b.key full outer join tab_part c on b.key = c.key
PREHOOK: type: QUERY
PREHOOK: Input: default@tab
-PREHOOK: Input: default@tab@ds=2008-04-08
PREHOOK: Input: default@tab_part
PREHOOK: Input: default@tab_part@ds=2008-04-08
#### A masked pattern was here ####
@@ -3397,7 +3392,6 @@ join
(select * from tab_part where tab_part.key = 98)b on a.key = b.key full outer join tab_part c on b.key = c.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab
-POSTHOOK: Input: default@tab@ds=2008-04-08
POSTHOOK: Input: default@tab_part
POSTHOOK: Input: default@tab_part@ds=2008-04-08
#### A masked pattern was here ####
diff --git a/ql/src/test/results/clientpositive/llap/orc_ppd_decimal.q.out b/ql/src/test/results/clientpositive/llap/orc_ppd_decimal.q.out
index b5e8658..e3e822a 100644
--- a/ql/src/test/results/clientpositive/llap/orc_ppd_decimal.q.out
+++ b/ql/src/test/results/clientpositive/llap/orc_ppd_decimal.q.out
@@ -386,7 +386,7 @@ POSTHOOK: query: select sum(hash(*)) from newtypesorc where d in ('0.9', 0.22, c
POSTHOOK: type: QUERY
POSTHOOK: Input: default@newtypesorc
#### A masked pattern was here ####
-81475875500
+-252951929000
PREHOOK: query: select sum(hash(*)) from newtypesorc where d in ('0.9', 0.22, cast('11.22' as float))
PREHOOK: type: QUERY
PREHOOK: Input: default@newtypesorc
@@ -395,7 +395,7 @@ POSTHOOK: query: select sum(hash(*)) from newtypesorc where d in ('0.9', 0.22, c
POSTHOOK: type: QUERY
POSTHOOK: Input: default@newtypesorc
#### A masked pattern was here ####
-81475875500
+-252951929000
PREHOOK: query: select sum(hash(*)) from newtypesorc where d between 0 and 1
PREHOOK: type: QUERY
PREHOOK: Input: default@newtypesorc
diff --git a/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out b/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out
index 07ef62f..8c6f97e 100644
--- a/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out
+++ b/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out
@@ -788,7 +788,7 @@ STAGE PLANS:
alias: orc_pred
Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and si BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean)
+ predicate: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and UDFToInteger(si) BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean)
Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string)
@@ -864,10 +864,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orc_pred
- filterExpr: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and si BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean)
+ filterExpr: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and UDFToInteger(si) BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean)
Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and si BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean)
+ predicate: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and UDFToInteger(si) BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean)
Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string)
diff --git a/ql/src/test/results/clientpositive/llap/parquet_predicate_pushdown.q.out b/ql/src/test/results/clientpositive/llap/parquet_predicate_pushdown.q.out
index 6fa478c..aecbcfd 100644
--- a/ql/src/test/results/clientpositive/llap/parquet_predicate_pushdown.q.out
+++ b/ql/src/test/results/clientpositive/llap/parquet_predicate_pushdown.q.out
@@ -726,7 +726,7 @@ STAGE PLANS:
alias: tbl_pred
Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and si BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean)
+ predicate: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and UDFToInteger(si) BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean)
Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string)
@@ -802,10 +802,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: tbl_pred
- filterExpr: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and si BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean)
+ filterExpr: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and UDFToInteger(si) BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean)
Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and si BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean)
+ predicate: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and UDFToInteger(si) BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean)
Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string)
diff --git a/ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended.q.out b/ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended.q.out
index 08a9bd1..834a251 100644
--- a/ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended.q.out
+++ b/ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended.q.out
@@ -559,23 +559,18 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
+ aggregations: count(_col1)
+ keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count(_col1)
- keys: _col0 (type: string)
- mode: complete
- outputColumnNames: _col0, _col1
+ Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 205 Data size: 19475 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
@@ -3094,23 +3089,18 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
+ aggregations: count(_col1)
+ keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count(_col1)
- keys: _col0 (type: string)
- mode: complete
- outputColumnNames: _col0, _col1
+ Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 205 Data size: 19475 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/llap/smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out
index ddb7624..df32ad4 100644
--- a/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out
+++ b/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out
@@ -1065,7 +1065,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
@@ -1084,7 +1084,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
diff --git a/ql/src/test/results/clientpositive/llap/subquery_exists.q.out b/ql/src/test/results/clientpositive/llap/subquery_exists.q.out
index 9e0a1d7..3004e36 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_exists.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_exists.q.out
@@ -255,22 +255,22 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (value = value) (type: boolean)
- Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: value (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 107 Data size: 9737 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 107 Data size: 9737 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -283,10 +283,10 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -948,7 +948,7 @@ POSTHOOK: query: insert into t values(0)
POSTHOOK: type: QUERY
POSTHOOK: Output: default@t
POSTHOOK: Lineage: t.i EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
-Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain select * from t where exists (select count(*) from src where 1=2)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from t where exists (select count(*) from src where 1=2)
@@ -963,7 +963,7 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
- Reducer 4 <- Map 3 (SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -997,9 +997,7 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: true (type: boolean)
- sort order: +
- Map-reduce partition columns: true (type: boolean)
+ sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: llap
@@ -1014,10 +1012,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1032,16 +1030,9 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: true (type: boolean)
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -1049,7 +1040,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select * from t where exists (select count(*) from src where 1=2)
PREHOOK: type: QUERY
PREHOOK: Input: default@src
diff --git a/ql/src/test/results/clientpositive/llap/subquery_in.q.out b/ql/src/test/results/clientpositive/llap/subquery_in.q.out
index bdf34a9..58e78c4 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_in.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_in.q.out
@@ -308,7 +308,7 @@ STAGE PLANS:
Reduce Operator Tree:
Merge Join Operator
condition map:
- Left Semi Join 0 to 1
+ Inner Join 0 to 1
keys:
0 UDFToDouble(_col1) (type: double)
1 _col0 (type: double)
@@ -376,16 +376,11 @@ STAGE PLANS:
Filter Operator
predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: double)
- mode: hash
- outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions: _col0 (type: double)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: double)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- sort order: +
- Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -440,10 +435,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
Reducer 4 <- Map 3 (SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
- Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -557,24 +551,6 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 6
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), _col0 (type: string)
outputColumnNames: _col0, _col1
@@ -642,8 +618,7 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
- Reducer 4 <- Map 3 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -670,16 +645,20 @@ STAGE PLANS:
Filter Operator
predicate: ((value = value) and (key > '9')) (type: boolean)
Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: key (type: string), value (type: string)
- mode: hash
+ Select Operator
+ expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 41 Data size: 7298 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 41 Data size: 7298 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 41 Data size: 7298 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -700,24 +679,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 4
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 41 Data size: 7298 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -979,10 +940,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
Reducer 7 <- Map 6 (SIMPLE_EDGE)
- Reducer 8 <- Reducer 7 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1030,19 +990,19 @@ STAGE PLANS:
alias: lineitem
Statistics: Num rows: 100 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (l_partkey = l_partkey) (type: boolean)
- Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: l_partkey is not null (type: boolean)
+ Statistics: Num rows: 100 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: avg(l_quantity)
keys: l_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 25 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: struct)
Execution mode: llap
LLAP IO: no inputs
@@ -1106,30 +1066,16 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col1 (type: double), _col0 (type: int)
- mode: hash
+ Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: double), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: double), _col1 (type: int)
- Statistics: Num rows: 12 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 8
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: double), KEY._col1 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: double), _col1 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: double), _col1 (type: int)
- Statistics: Num rows: 12 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -1191,18 +1137,18 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string), p_size (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1230,21 +1176,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: int)
- mode: complete
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: int), _col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col1 (type: string), _col0 (type: int)
- sort order: ++
- Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: string), _col0 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -1601,18 +1542,18 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_name = p_name) (type: boolean)
- Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_name is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_name (type: string), p_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1656,16 +1597,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: int)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -2156,18 +2097,18 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_brand = p_brand) (type: boolean)
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_brand is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string), p_brand (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -2195,12 +2136,12 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -2686,18 +2627,18 @@ STAGE PLANS:
alias: sc
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (key = key) (type: boolean)
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: key (type: string), value (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 7
@@ -2734,7 +2675,7 @@ STAGE PLANS:
0 _col0 (type: string), _col1 (type: string)
1 _col1 (type: string), _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
@@ -2790,16 +2731,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 8
Execution mode: llap
Reduce Operator Tree:
@@ -3488,17 +3429,17 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((p_size = p_size) and p_type is not null) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (p_size is not null and p_type is not null) (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_type (type: string), p_size (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -3530,21 +3471,21 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col3
- Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 24 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col3 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 24 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -3628,17 +3569,17 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 5954 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((p_size = p_size) and p_type is not null) (type: boolean)
- Statistics: Num rows: 13 Data size: 2977 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (p_size is not null and p_type is not null) (type: boolean)
+ Statistics: Num rows: 26 Data size: 5954 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_name (type: string), p_type (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 2977 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 5954 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 13 Data size: 2977 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 5954 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -3648,17 +3589,17 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((p_size = p_size) and p_type is not null) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (p_size is not null and p_type is not null) (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_type (type: string), p_size (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -3690,21 +3631,21 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col4
- Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 24 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col4 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 24 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -3790,17 +3731,17 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_name (type: string), p_type (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -3810,17 +3751,17 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((p_size = p_size) and p_type is not null) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (p_size is not null and p_type is not null) (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_type (type: string), p_size (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -3852,21 +3793,21 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 12 Data size: 2748 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 24 Data size: 5496 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 2748 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 24 Data size: 5496 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: string), _col2 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 1374 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 2748 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
- Statistics: Num rows: 6 Data size: 1374 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 2748 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -3936,17 +3877,17 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((p_size = p_size) and p_type is not null) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (p_size is not null and p_type is not null) (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_type (type: string), p_size (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -3978,21 +3919,21 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col3
- Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 24 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col3 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 24 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -4050,10 +3991,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (SIMPLE_EDGE)
Reducer 7 <- Map 6 (SIMPLE_EDGE)
- Reducer 8 <- Reducer 7 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -4079,18 +4019,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 6
@@ -4099,19 +4039,19 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -4164,18 +4104,18 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 7
Execution mode: llap
@@ -4185,34 +4125,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: bigint)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 8
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: bigint), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: bigint)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: bigint)
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -4244,9 +4166,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
Reducer 4 <- Map 3 (SIMPLE_EDGE)
- Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -4272,19 +4193,19 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: avg(p_size)
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 480 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 480 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: struct)
Execution mode: llap
LLAP IO: no inputs
@@ -4314,34 +4235,16 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: int), _col1 (type: double)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: double)
- sort order: ++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: double)
- Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 5
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: int), KEY._col1 (type: double)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: double), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int), _col0 (type: double)
sort order: ++
Map-reduce partition columns: _col1 (type: int), _col0 (type: double)
- Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -4383,7 +4286,7 @@ POSTHOOK: Input: default@part
85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull
86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully
90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl
-Warning: Shuffle Join MERGEJOIN[35][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
PREHOOK: query: explain select * from part where p_size in (select min(pp.p_size) from part pp where pp.p_partkey > part.p_partkey)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where p_size in (select min(pp.p_size) from part pp where pp.p_partkey > part.p_partkey)
@@ -4397,11 +4300,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
- Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
- Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
- Reducer 8 <- Map 7 (SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -4436,7 +4338,7 @@ STAGE PLANS:
value expressions: _col0 (type: int), _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 7
+ Map 6
Map Operator Tree:
TableScan
alias: part
@@ -4510,34 +4412,16 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: int), _col1 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 6
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: int), KEY._col1 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int), _col0 (type: int)
sort order: ++
Map-reduce partition columns: _col1 (type: int), _col0 (type: int)
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 8
+ Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 7
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -4556,7 +4440,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[35][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
PREHOOK: query: select * from part where p_size in (select min(pp.p_size) from part pp where pp.p_partkey > part.p_partkey)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -4582,10 +4466,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 10 <- Map 9 (SIMPLE_EDGE)
- Reducer 11 <- Reducer 10 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
- Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 6 <- Map 5 (SIMPLE_EDGE)
Reducer 8 <- Map 7 (SIMPLE_EDGE)
#### A masked pattern was here ####
@@ -4613,18 +4496,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 7
@@ -4633,19 +4516,19 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -4655,19 +4538,19 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -4679,41 +4562,23 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: bigint)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 11
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: bigint), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: bigint), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: bigint)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: bigint)
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Reducer 2
Execution mode: llap
@@ -4788,18 +4653,18 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 8
Execution mode: llap
@@ -4809,18 +4674,18 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(_col1)
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Stage: Stage-0
@@ -4874,10 +4739,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 10 <- Map 9 (SIMPLE_EDGE)
- Reducer 11 <- Reducer 10 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
- Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 6 <- Map 5 (SIMPLE_EDGE)
Reducer 8 <- Map 7 (SIMPLE_EDGE)
#### A masked pattern was here ####
@@ -4905,18 +4769,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 7
@@ -4925,19 +4789,19 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: avg(p_size)
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 480 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 480 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: struct)
Execution mode: llap
LLAP IO: no inputs
@@ -4947,19 +4811,19 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: avg(p_size)
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 480 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 480 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: struct)
Execution mode: llap
LLAP IO: no inputs
@@ -4971,41 +4835,23 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: int), _col1 (type: double)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: double)
- sort order: ++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: double)
- Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 11
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: int), KEY._col1 (type: double)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: double), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double), _col1 (type: int), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int), _col0 (type: double)
sort order: ++
Map-reduce partition columns: _col1 (type: int), _col0 (type: double)
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Reducer 2
Execution mode: llap
@@ -5080,18 +4926,18 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 8
Execution mode: llap
@@ -5101,18 +4947,18 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(_col1)
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Stage: Stage-0
@@ -5219,7 +5065,7 @@ STAGE PLANS:
Reduce Operator Tree:
Merge Join Operator
condition map:
- Left Semi Join 0 to 1
+ Inner Join 0 to 1
keys:
0 UDFToLong(_col0) (type: bigint)
1 _col0 (type: bigint)
@@ -5243,16 +5089,11 @@ STAGE PLANS:
Filter Operator
predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: bigint)
- mode: hash
- outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: bigint)
- sort order: +
- Map-reduce partition columns: _col0 (type: bigint)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -5385,9 +5226,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
Reducer 4 <- Map 3 (SIMPLE_EDGE)
- Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -5413,7 +5253,7 @@ STAGE PLANS:
alias: tt
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (j = j) (type: boolean)
+ predicate: j is not null (type: boolean)
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(i)
@@ -5456,9 +5296,8 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col1 (type: bigint), _col0 (type: int)
- mode: hash
+ Select Operator
+ expressions: _col1 (type: bigint), _col0 (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
@@ -5466,19 +5305,6 @@ STAGE PLANS:
sort order: ++
Map-reduce partition columns: _col0 (type: bigint), _col1 (type: int)
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
- Reducer 5
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: bigint), KEY._col1 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: bigint), _col1 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: bigint), _col1 (type: int)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
diff --git a/ql/src/test/results/clientpositive/llap/subquery_multi.q.out b/ql/src/test/results/clientpositive/llap/subquery_multi.q.out
index ca99b87..b6fb37a 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_multi.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_multi.q.out
@@ -1733,18 +1733,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string), p_brand (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 12
@@ -1753,17 +1753,17 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_brand (type: string), p_type (type: string), p_container (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -1773,18 +1773,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string), p_brand (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
@@ -1793,18 +1793,18 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string), p_name (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1350 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 1350 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 7
@@ -1813,17 +1813,17 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_brand (type: string), p_type (type: string), p_container (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -1834,16 +1834,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 13
Execution mode: llap
Reduce Operator Tree:
@@ -1874,7 +1874,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), true (type: boolean)
@@ -1893,16 +1893,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -1913,12 +1913,12 @@ STAGE PLANS:
0 _col4 (type: string), _col1 (type: string)
1 _col1 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 6 Data size: 1485 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 3217 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col4 (type: string)
sort order: +
Map-reduce partition columns: _col4 (type: string)
- Statistics: Num rows: 6 Data size: 1485 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 3217 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
Reducer 3
Execution mode: llap
@@ -1930,12 +1930,12 @@ STAGE PLANS:
0 _col4 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12, _col13
- Statistics: Num rows: 6 Data size: 1633 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 3538 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col3 (type: string), _col4 (type: string)
sort order: ++
Map-reduce partition columns: _col3 (type: string), _col4 (type: string)
- Statistics: Num rows: 6 Data size: 1633 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 3538 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col12 (type: bigint), _col13 (type: bigint)
Reducer 4
Execution mode: llap
@@ -1947,17 +1947,17 @@ STAGE PLANS:
0 _col3 (type: string), _col4 (type: string)
1 _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12, _col13, _col16
- Statistics: Num rows: 6 Data size: 1796 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 3891 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (not CASE WHEN ((_col12 = 0)) THEN (false) WHEN (_col12 is null) THEN (false) WHEN (_col16 is not null) THEN (true) WHEN (_col3 is null) THEN (null) WHEN ((_col13 < _col12)) THEN (true) ELSE (false) END) (type: boolean)
- Statistics: Num rows: 3 Data size: 898 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 1945 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 3 Data size: 898 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 1945 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 898 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 1945 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1969,16 +1969,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1350 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1350 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 6 Data size: 1350 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 8
Execution mode: llap
Reduce Operator Tree:
@@ -2128,22 +2128,22 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_brand (type: string), p_type (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -2285,18 +2285,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string), p_brand (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 12
@@ -2305,17 +2305,17 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_brand (type: string), p_type (type: string), p_container (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -2325,18 +2325,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string), p_brand (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
@@ -2365,17 +2365,17 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_brand (type: string), p_type (type: string), p_container (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 7488 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -2386,16 +2386,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 13
Execution mode: llap
Reduce Operator Tree:
@@ -2430,7 +2430,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), true (type: boolean)
@@ -2449,16 +2449,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -2660,18 +2660,18 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_name (type: string), p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1350 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 1350 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 7
@@ -2680,19 +2680,19 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_size = p_size) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_size is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(p_type)
keys: p_size (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -2702,18 +2702,18 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_size = p_size) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_size is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string), p_size (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 10
@@ -2723,19 +2723,19 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: int), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Reducer 2
Execution mode: llap
@@ -2747,12 +2747,12 @@ STAGE PLANS:
0 _col1 (type: string), _col4 (type: string)
1 _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 6 Data size: 1485 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 3217 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col5 (type: int)
sort order: +
Map-reduce partition columns: _col5 (type: int)
- Statistics: Num rows: 6 Data size: 1485 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 3217 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col6 (type: string), _col7 (type: double), _col8 (type: string)
Reducer 3
Execution mode: llap
@@ -2764,12 +2764,12 @@ STAGE PLANS:
0 _col5 (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12, _col13
- Statistics: Num rows: 6 Data size: 1633 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 3538 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col3 (type: string), _col5 (type: int)
sort order: ++
Map-reduce partition columns: _col3 (type: string), _col5 (type: int)
- Statistics: Num rows: 6 Data size: 1633 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 3538 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col12 (type: bigint), _col13 (type: bigint)
Reducer 4
Execution mode: llap
@@ -2781,17 +2781,17 @@ STAGE PLANS:
0 _col3 (type: string), _col5 (type: int)
1 _col0 (type: string), _col1 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12, _col13, _col16
- Statistics: Num rows: 6 Data size: 1796 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 3891 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (not CASE WHEN ((_col12 = 0)) THEN (false) WHEN (_col12 is null) THEN (false) WHEN (_col16 is not null) THEN (true) WHEN (_col3 is null) THEN (null) WHEN ((_col13 < _col12)) THEN (true) ELSE (false) END) (type: boolean)
- Statistics: Num rows: 3 Data size: 898 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 1945 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 3 Data size: 898 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 1945 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 898 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 1945 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2803,12 +2803,12 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1350 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 1350 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 8
Execution mode: llap
Reduce Operator Tree:
@@ -2817,12 +2817,12 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Stage: Stage-0
@@ -2908,17 +2908,17 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 8242 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 4121 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 8242 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_name (type: string), p_brand (type: string), p_type (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 4121 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 8242 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col2 (type: string), _col1 (type: string)
- Statistics: Num rows: 13 Data size: 4121 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 8242 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -2928,18 +2928,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string), p_brand (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -2992,16 +2992,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -3045,7 +3045,7 @@ POSTHOOK: Input: default@part_null
17927 almond aquamarine yellow dodger mint Manufacturer#4 Brand#41 ECONOMY BRUSHED COPPER 7 SM PKG 1844.92 ites. eve
33357 almond azure aquamarine papaya violet Manufacturer#4 Brand#41 STANDARD ANODIZED TIN 12 WRAP CASE 1290.35 reful
78486 almond azure blanched chiffon midnight Manufacturer#5 Brand#52 LARGE BRUSHED BRASS 23 MED BAG 1464.48 hely blith
-Warning: Shuffle Join MERGEJOIN[66][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 7' is a cross product
+Warning: Shuffle Join MERGEJOIN[61][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 7' is a cross product
PREHOOK: query: explain select p.p_partkey, li.l_suppkey
from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey
where li.l_linenumber = 1 and
@@ -3067,12 +3067,11 @@ STAGE PLANS:
Edges:
Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE)
Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE)
- Reducer 13 <- Reducer 12 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE), Reducer 10 (CUSTOM_SIMPLE_EDGE)
- Reducer 8 <- Reducer 13 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
+ Reducer 8 <- Reducer 12 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -3198,24 +3197,6 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: double)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- sort order: +
- Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 13
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: double)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double), true (type: boolean)
outputColumnNames: _col0, _col1
@@ -3330,7 +3311,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[66][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 7' is a cross product
+Warning: Shuffle Join MERGEJOIN[61][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 7' is a cross product
PREHOOK: query: select p.p_partkey, li.l_suppkey
from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey
where li.l_linenumber = 1 and
@@ -3401,18 +3382,18 @@ STAGE PLANS:
alias: s2
Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (value = value) (type: boolean)
- Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: value (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 107 Data size: 9737 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 107 Data size: 9737 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
@@ -3421,18 +3402,18 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (value = value) (type: boolean)
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: key (type: string), value (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 7
@@ -3462,12 +3443,12 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 107 Data size: 9737 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 107 Data size: 9737 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -3478,7 +3459,7 @@ STAGE PLANS:
0 _col0 (type: string), _col1 (type: string)
1 _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string), _col1 (type: string)
@@ -3534,12 +3515,12 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 8
Execution mode: llap
Reduce Operator Tree:
diff --git a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out
index 2c004fb..f28fcab 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out
@@ -541,17 +541,17 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 2 Data size: 438 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 219 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 2 Data size: 438 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 446 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 446 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Stage: Stage-0
@@ -598,7 +598,7 @@ Manufacturer#4 almond azure aquamarine papaya violet 12
Manufacturer#5 almond antique blue firebrick mint 31
Manufacturer#5 almond aquamarine dodger light gainsboro 46
Manufacturer#5 almond azure blanched chiffon midnight 23
-Warning: Shuffle Join MERGEJOIN[49][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[44][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain
select p_name, p_size
from
@@ -626,9 +626,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 10 <- Reducer 9 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE)
- Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (SIMPLE_EDGE)
Reducer 6 <- Reducer 5 (CUSTOM_SIMPLE_EDGE)
Reducer 8 <- Map 7 (SIMPLE_EDGE)
@@ -676,24 +675,6 @@ STAGE PLANS:
TopN Hash Memory Usage: 0.1
Execution mode: llap
LLAP IO: no inputs
- Reducer 10
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: double)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: double), true (type: boolean)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- sort order: +
- Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: boolean)
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -849,16 +830,16 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: double)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: double), true (type: boolean)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: boolean)
Stage: Stage-0
Fetch Operator
@@ -866,7 +847,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[51][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[46][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select p_name, p_size
from
part where part.p_size not in
@@ -941,10 +922,9 @@ STAGE PLANS:
Reducer 10 <- Reducer 9 (SIMPLE_EDGE)
Reducer 12 <- Map 11 (SIMPLE_EDGE)
Reducer 13 <- Reducer 12 (SIMPLE_EDGE)
- Reducer 14 <- Reducer 13 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
- Reducer 4 <- Reducer 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 6 <- Map 5 (SIMPLE_EDGE)
Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
Reducer 9 <- Map 8 (SIMPLE_EDGE)
@@ -1092,31 +1072,13 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 14
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
@@ -1779,23 +1741,23 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_type (type: string), (p_size * p_size) (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(_col1)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -1805,22 +1767,22 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: (p_size * p_size) (type: int), p_type (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col1 (type: string), _col0 (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1873,12 +1835,12 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Reducer 7
Execution mode: llap
@@ -1887,23 +1849,23 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: int)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Stage: Stage-0
@@ -2055,7 +2017,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12
Statistics: Num rows: 26 Data size: 16614 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((_col9 = 0) or (_col12 is null and (_col5 - 1) is not null and (_col10 >= _col9))) (type: boolean)
+ predicate: ((_col9 = 0) or (_col12 is null and _col5 is not null and (_col10 >= _col9))) (type: boolean)
Statistics: Num rows: 26 Data size: 16614 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
@@ -2287,7 +2249,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12
Statistics: Num rows: 26 Data size: 16614 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((_col9 = 0) or (_col12 is null and (_col0 * _col5) is not null and (_col10 >= _col9))) (type: boolean)
+ predicate: ((_col9 = 0) or (_col12 is null and _col0 is not null and _col5 is not null and (_col10 >= _col9))) (type: boolean)
Statistics: Num rows: 26 Data size: 16614 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
@@ -2478,19 +2440,19 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_name = p_name) (type: boolean)
- Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_name is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(p_partkey)
keys: p_name (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 822 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1781 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 822 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1781 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -2500,18 +2462,18 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_name = p_name) (type: boolean)
- Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_name is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_partkey (type: int), p_name (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 11
@@ -2593,12 +2555,12 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 822 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1781 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 822 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1781 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Reducer 8
Execution mode: llap
@@ -2607,16 +2569,16 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 774 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1677 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 774 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1677 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: boolean)
Reducer 9
Execution mode: llap
@@ -2628,12 +2590,12 @@ STAGE PLANS:
0 _col0 (type: int)
1 (_col0 + 100) (type: int)
outputColumnNames: _col1, _col2, _col3
- Statistics: Num rows: 6 Data size: 774 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 7 Data size: 903 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col3 (type: int)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col3 (type: int)
- Statistics: Num rows: 6 Data size: 774 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 7 Data size: 903 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Stage: Stage-0
@@ -3006,7 +2968,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: int), true (type: boolean)
@@ -3311,17 +3273,17 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 3 Data size: 387 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 129 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 387 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), true (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 133 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 399 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int), _col0 (type: string), _col2 (type: int)
sort order: +++
Map-reduce partition columns: _col1 (type: int), _col0 (type: string), _col2 (type: int)
- Statistics: Num rows: 1 Data size: 133 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 399 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: boolean)
Stage: Stage-0
@@ -3380,23 +3342,23 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_brand = p_brand) (type: boolean)
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_brand is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_brand (type: string), (UDFToDouble(p_type) + 2.0) (type: double)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(_col1)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -3406,22 +3368,22 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_brand = p_brand) (type: boolean)
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_brand is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: (UDFToDouble(p_type) + 2.0) (type: double), p_brand (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1300 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2600 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: double), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1300 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: double), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1300 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -3474,12 +3436,12 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Reducer 7
Execution mode: llap
@@ -3488,19 +3450,19 @@ STAGE PLANS:
keys: KEY._col0 (type: double), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1300 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1300 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: double), _col1 (type: string)
- Statistics: Num rows: 3 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Stage: Stage-0
@@ -3663,17 +3625,17 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 9 Data size: 972 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 4 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 9 Data size: 972 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: int), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 9 Data size: 1008 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 9 Data size: 1008 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Reducer 13
Execution mode: llap
@@ -4180,23 +4142,23 @@ STAGE PLANS:
alias: sc
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (key = key) (type: boolean)
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), concat('v', value) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(_col1)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 103 Data size: 10609 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 205 Data size: 21115 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 103 Data size: 10609 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 205 Data size: 21115 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -4206,22 +4168,22 @@ STAGE PLANS:
alias: sc
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (key = key) (type: boolean)
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: concat('v', value) (type: string), key (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 500 Data size: 135500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col1 (type: string), _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 33875 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 125 Data size: 33875 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 11
@@ -4294,12 +4256,12 @@ STAGE PLANS:
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 2470 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 26 Data size: 2470 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 4
Execution mode: llap
@@ -4309,15 +4271,15 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 2470 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: _col1 is not null (type: boolean)
- Statistics: Num rows: 26 Data size: 2470 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: bigint)
sort order: +
Map-reduce partition columns: _col1 (type: bigint)
- Statistics: Num rows: 26 Data size: 2470 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Reducer 5
Execution mode: llap
@@ -4345,12 +4307,12 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 103 Data size: 10609 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 205 Data size: 21115 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 103 Data size: 10609 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 205 Data size: 21115 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Reducer 9
Execution mode: llap
@@ -4359,23 +4321,23 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 33875 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 34375 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 62 Data size: 17050 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 62 Data size: 17050 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 62 Data size: 17050 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Stage: Stage-0
@@ -4554,7 +4516,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12
Statistics: Num rows: 26 Data size: 16614 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((_col9 = 0) or (_col12 is null and (_col5 - 1) is not null and (_col10 >= _col9))) (type: boolean)
+ predicate: ((_col9 = 0) or (_col12 is null and _col5 is not null and (_col10 >= _col9))) (type: boolean)
Statistics: Num rows: 26 Data size: 16614 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
@@ -4799,7 +4761,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12
Statistics: Num rows: 26 Data size: 16614 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((_col9 = 0) or (_col12 is null and (_col5 - 1) is not null and (_col10 >= _col9))) (type: boolean)
+ predicate: ((_col9 = 0) or (_col12 is null and _col5 is not null and (_col10 >= _col9))) (type: boolean)
Statistics: Num rows: 26 Data size: 16614 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
@@ -5682,19 +5644,19 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_brand = p_brand) (type: boolean)
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_brand is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(p_type)
keys: p_brand (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -5704,18 +5666,18 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_brand = p_brand) (type: boolean)
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_brand is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_brand (type: string), p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 11
@@ -5797,12 +5759,12 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Reducer 8
Execution mode: llap
@@ -5811,16 +5773,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2600 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: UDFToDouble(_col0) (type: double)
sort order: +
Map-reduce partition columns: UDFToDouble(_col0) (type: double)
- Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2600 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: boolean)
Reducer 9
Execution mode: llap
@@ -5832,12 +5794,12 @@ STAGE PLANS:
0 UDFToDouble(_col0) (type: double)
1 UDFToDouble((_col0 + 100)) (type: double)
outputColumnNames: _col1, _col2, _col3
- Statistics: Num rows: 5 Data size: 500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col3 (type: int)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col3 (type: int)
- Statistics: Num rows: 5 Data size: 500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Stage: Stage-0
@@ -6186,7 +6148,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: char(100)), true (type: boolean)
@@ -6415,19 +6377,19 @@ STAGE PLANS:
alias: t2
Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (b = b) (type: boolean)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ predicate: b is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(), count(a)
keys: b (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -6437,18 +6399,18 @@ STAGE PLANS:
alias: t2
Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (b = b) (type: boolean)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ predicate: b is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: b (type: int), a (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -6521,7 +6483,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), true (type: boolean)
@@ -6641,19 +6603,19 @@ STAGE PLANS:
alias: t7
Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (j = j) (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ predicate: j is not null (type: boolean)
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(), count(i)
keys: j (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -6663,18 +6625,18 @@ STAGE PLANS:
alias: t7
Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (j = j) (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ predicate: j is not null (type: boolean)
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: i (type: int), j (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Map 8
@@ -6877,19 +6839,19 @@ STAGE PLANS:
alias: t1
Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (j = j) (type: boolean)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ predicate: j is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(), count(i)
keys: j (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -6899,18 +6861,18 @@ STAGE PLANS:
alias: t1
Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (j = j) (type: boolean)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ predicate: j is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: i (type: int), j (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Map 8
@@ -7080,19 +7042,19 @@ STAGE PLANS:
alias: t1
Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (j = j) (type: boolean)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ predicate: j is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(), count(i)
keys: j (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -7102,18 +7064,18 @@ STAGE PLANS:
alias: t1
Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (j = j) (type: boolean)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ predicate: j is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: i (type: int), j (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -7182,7 +7144,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), true (type: boolean)
@@ -7697,17 +7659,17 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 1656 Data size: 294768 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 828 Data size: 147384 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 1656 Data size: 294768 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 828 Data size: 150696 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1656 Data size: 301392 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 828 Data size: 150696 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1656 Data size: 301392 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Reducer 13
Execution mode: llap
diff --git a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
index 4cecdd6..250c93d 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
@@ -75,8 +75,7 @@ POSTHOOK: Lineage: part_null.p_partkey EXPRESSION [(values__tmp__table__2)values
POSTHOOK: Lineage: part_null.p_retailprice EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col8, type:string, comment:), ]
POSTHOOK: Lineage: part_null.p_size EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col6, type:string, comment:), ]
POSTHOOK: Lineage: part_null.p_type SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col5, type:string, comment:), ]
-Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[32][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain select * from part where p_size > (select avg(p_size) from part_null)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where p_size > (select avg(p_size) from part_null)
@@ -90,10 +89,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
- Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
- Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -111,7 +109,7 @@ STAGE PLANS:
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 4
+ Map 3
Map Operator Tree:
TableScan
alias: part_null
@@ -131,7 +129,7 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Map 6
+ Map 5
Map Operator Tree:
TableScan
alias: part_null
@@ -157,41 +155,28 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 26 Data size: 16328 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 16328 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- Reducer 3
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0
- 1
+ 2
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10
- Statistics: Num rows: 26 Data size: 18330 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 18304 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (UDFToDouble(_col5) > _col10) (type: boolean)
- Statistics: Num rows: 8 Data size: 5640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 5632 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 8 Data size: 5640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 5632 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 8 Data size: 5640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 5632 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 5
+ Reducer 4
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -214,7 +199,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reducer 7
+ Reducer 6
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -233,8 +218,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[32][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select * from part where p_size > (select avg(p_size) from part_null)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -256,8 +240,7 @@ POSTHOOK: Input: default@part_null
192697 almond antique blue firebrick mint Manufacturer#5 Brand#52 MEDIUM BURNISHED TIN 31 LG DRUM 1789.69 ickly ir
15103 almond aquamarine dodger light gainsboro Manufacturer#5 Brand#53 ECONOMY BURNISHED STEEL 46 LG PACK 1018.1 packages hinder carefu
78486 almond azure blanched chiffon midnight Manufacturer#5 Brand#52 LARGE BRUSHED BRASS 23 MED BAG 1464.48 hely blith
-Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[22][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select * from part where p_size > (select * from tempty)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -268,8 +251,7 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
POSTHOOK: Input: default@tempty
#### A masked pattern was here ####
-Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[22][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain select * from part where p_size > (select * from tempty)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where p_size > (select * from tempty)
@@ -283,9 +265,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
- Reducer 3 <- Map 6 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE)
- Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 5 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -303,7 +284,7 @@ STAGE PLANS:
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 4
+ Map 3
Map Operator Tree:
TableScan
alias: tempty
@@ -321,7 +302,7 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Map 6
+ Map 5
Map Operator Tree:
TableScan
alias: tempty
@@ -342,41 +323,28 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- Reducer 3
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0
- 1
+ 2
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10
- Statistics: Num rows: 26 Data size: 16120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 16328 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (UDFToDouble(_col5) > UDFToDouble(_col10)) (type: boolean)
- Statistics: Num rows: 8 Data size: 4960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 5024 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 8 Data size: 4960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 5024 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 8 Data size: 4960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 5024 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 5
+ Reducer 4
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -1121,7 +1089,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col12
Statistics: Num rows: 26 Data size: 16406 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: _col5 BETWEEN _col10 AND _col12 (type: boolean)
+ predicate: UDFToDouble(_col5) BETWEEN UDFToDouble(_col10) AND _col12 (type: boolean)
Statistics: Num rows: 2 Data size: 1262 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
@@ -1203,8 +1171,7 @@ POSTHOOK: Input: default@part
33357 almond azure aquamarine papaya violet Manufacturer#4 Brand#41 STANDARD ANODIZED TIN 12 WRAP CASE 1290.35 reful
42669 almond antique medium spring khaki Manufacturer#5 Brand#51 STANDARD BURNISHED TIN 6 MED CAN 1611.66 sits haggl
155733 almond antique sky peru orange Manufacturer#5 Brand#53 SMALL PLATED BRASS 2 WRAP DRUM 1788.73 furiously. bra
-Warning: Shuffle Join MERGEJOIN[38][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[36][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain select p_mfgr, p_name, p_size from part
where part.p_size >
(select first_value(p_size) over(partition by p_mfgr order by p_size) as fv from part order by fv limit 1)
@@ -1222,13 +1189,12 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 10 <- Reducer 9 (SIMPLE_EDGE)
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
- Reducer 3 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE)
- Reducer 5 <- Map 4 (SIMPLE_EDGE)
- Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
- Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE)
- Reducer 9 <- Map 8 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (SIMPLE_EDGE)
+ Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
+ Reducer 6 <- Reducer 5 (CUSTOM_SIMPLE_EDGE)
+ Reducer 8 <- Map 7 (SIMPLE_EDGE)
+ Reducer 9 <- Reducer 8 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1246,7 +1212,7 @@ STAGE PLANS:
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 4
+ Map 3
Map Operator Tree:
TableScan
alias: part
@@ -1258,7 +1224,7 @@ STAGE PLANS:
Statistics: Num rows: 26 Data size: 2652 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 8
+ Map 7
Map Operator Tree:
TableScan
alias: part
@@ -1270,44 +1236,17 @@ STAGE PLANS:
Statistics: Num rows: 26 Data size: 2652 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Reducer 10
- Execution mode: llap
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 1
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int)
Reducer 2
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
- Reducer 3
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0
- 1
+ 2
outputColumnNames: _col0, _col1, _col2, _col4
Statistics: Num rows: 26 Data size: 5902 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
@@ -1324,7 +1263,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 5
+ Reducer 4
Execution mode: llap
Reduce Operator Tree:
Select Operator
@@ -1359,7 +1298,7 @@ STAGE PLANS:
key expressions: _col0 (type: int)
sort order: +
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 6
+ Reducer 5
Execution mode: llap
Reduce Operator Tree:
Select Operator
@@ -1376,7 +1315,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
- Reducer 7
+ Reducer 6
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -1392,7 +1331,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 9
+ Reducer 8
Execution mode: llap
Reduce Operator Tree:
Select Operator
@@ -1428,6 +1367,20 @@ STAGE PLANS:
sort order: +
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
+ Reducer 9
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 1
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
Stage: Stage-0
Fetch Operator
@@ -1435,8 +1388,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[38][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[36][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select p_mfgr, p_name, p_size from part
where part.p_size >
(select first_value(p_size) over(partition by p_mfgr order by p_size) as fv from part order by fv limit 1)
@@ -1474,8 +1426,7 @@ Manufacturer#5 almond antique medium spring khaki 6
Manufacturer#5 almond antique sky peru orange 2
Manufacturer#5 almond aquamarine dodger light gainsboro 46
Manufacturer#5 almond azure blanched chiffon midnight 23
-Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[32][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain select * from part where (p_partkey*p_size) <> (select min(p_partkey) from part)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where (p_partkey*p_size) <> (select min(p_partkey) from part)
@@ -1489,10 +1440,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
- Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
- Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1510,7 +1460,7 @@ STAGE PLANS:
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 4
+ Map 3
Map Operator Tree:
TableScan
alias: part
@@ -1530,7 +1480,7 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Map 6
+ Map 5
Map Operator Tree:
TableScan
alias: part
@@ -1556,24 +1506,11 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- Reducer 3
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0
- 1
+ 2
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10
Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
@@ -1590,7 +1527,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 5
+ Reducer 4
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -1613,7 +1550,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 7
+ Reducer 6
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -1632,8 +1569,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[32][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select * from part where (p_partkey*p_size) <> (select min(p_partkey) from part)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -1710,18 +1646,18 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_name = p_name) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_name is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_name (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 6
@@ -1730,19 +1666,19 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_name = p_name) (type: boolean)
- Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_name is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(p_partkey)
keys: p_name (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -1758,7 +1694,7 @@ STAGE PLANS:
1 _col0 (type: string)
2 _col2 (type: string)
outputColumnNames: _col1, _col4, _col5
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((_col1 + 100) < CASE WHEN (_col5 is null) THEN (null) ELSE (_col4) END) (type: boolean)
Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
@@ -1795,25 +1731,25 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 774 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1677 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 258 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 258 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 258 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 7
Execution mode: llap
Reduce Operator Tree:
@@ -1822,16 +1758,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), true (type: boolean), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 774 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1677 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 6 Data size: 774 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1677 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: boolean)
Stage: Stage-0
@@ -1890,18 +1826,18 @@ STAGE PLANS:
alias: part_null
Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Map 5
@@ -1910,19 +1846,19 @@ STAGE PLANS:
alias: part_null
Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: avg(p_size)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: struct)
Execution mode: llap
LLAP IO: no inputs
@@ -1960,25 +1896,25 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 407 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -1987,16 +1923,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 735 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: double), true (type: boolean), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 7 Data size: 735 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 7 Data size: 735 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: double), _col1 (type: boolean)
Stage: Stage-0
@@ -2083,18 +2019,18 @@ STAGE PLANS:
alias: part_null
Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Map 7
@@ -2103,19 +2039,19 @@ STAGE PLANS:
alias: part_null
Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: min(p_size)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -2238,25 +2174,25 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 407 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Reducer 8
Execution mode: llap
Reduce Operator Tree:
@@ -2265,16 +2201,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 735 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: int), true (type: boolean), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 7 Data size: 735 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 7 Data size: 735 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: boolean)
Stage: Stage-0
@@ -2386,18 +2322,18 @@ STAGE PLANS:
alias: part_null
Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Map 6
@@ -2406,19 +2342,19 @@ STAGE PLANS:
alias: part_null
Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: min(p_size)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -2512,25 +2448,25 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 407 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Reducer 7
Execution mode: llap
Reduce Operator Tree:
@@ -2539,16 +2475,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 735 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: int), true (type: boolean), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 7 Data size: 735 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 7 Data size: 735 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: boolean)
Reducer 9
Execution mode: llap
@@ -2702,18 +2638,18 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string), p_size (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -2798,16 +2734,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: int)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -3034,10 +2970,8 @@ POSTHOOK: Input: default@part
191709 almond antique violet turquoise frosted Manufacturer#2 Brand#22 ECONOMY POLISHED STEEL 40 MED BOX 1800.7 haggle
192697 almond antique blue firebrick mint Manufacturer#5 Brand#52 MEDIUM BURNISHED TIN 31 LG DRUM 1789.69 ickly ir
195606 almond aquamarine sandy cyan gainsboro Manufacturer#2 Brand#25 STANDARD PLATED TIN 18 SM PKG 1701.6 ic de
-Warning: Shuffle Join MERGEJOIN[68][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[69][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
-Warning: Shuffle Join MERGEJOIN[70][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 5' is a cross product
-Warning: Shuffle Join MERGEJOIN[71][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 6' is a cross product
+Warning: Shuffle Join MERGEJOIN[64][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[65][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
PREHOOK: query: explain select key, count(*) from src where value <> (select max(value) from src) group by key having count(*) > (select count(*) from src s1 where s1.key = '90' group by s1.key )
PREHOOK: type: QUERY
POSTHOOK: query: explain select key, count(*) from src where value <> (select max(value) from src) group by key having count(*) > (select count(*) from src s1 where s1.key = '90' group by s1.key )
@@ -3051,15 +2985,13 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE)
- Reducer 12 <- Map 11 (SIMPLE_EDGE)
- Reducer 13 <- Reducer 12 (CUSTOM_SIMPLE_EDGE)
- Reducer 15 <- Map 14 (SIMPLE_EDGE)
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE)
- Reducer 3 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE)
- Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
- Reducer 5 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
- Reducer 6 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
+ Reducer 10 <- Map 9 (SIMPLE_EDGE)
+ Reducer 11 <- Reducer 10 (CUSTOM_SIMPLE_EDGE)
+ Reducer 13 <- Map 12 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE)
Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
@@ -3078,29 +3010,7 @@ STAGE PLANS:
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 11
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (key = '90') (type: boolean)
- Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: '90' (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
- Execution mode: llap
- LLAP IO: no inputs
- Map 14
+ Map 12
Map Operator Tree:
TableScan
alias: s1
@@ -3124,7 +3034,7 @@ STAGE PLANS:
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Map 7
+ Map 5
Map Operator Tree:
TableScan
alias: src
@@ -3144,7 +3054,7 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Map 9
+ Map 7
Map Operator Tree:
TableScan
alias: src
@@ -3164,19 +3074,29 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Reducer 10
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: s1
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (key = '90') (type: boolean)
+ Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: '90' (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- aggregations: max(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string)
- Reducer 12
+ LLAP IO: no inputs
+ Reducer 10
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3195,7 +3115,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
- Reducer 13
+ Reducer 11
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3211,7 +3131,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 15
+ Reducer 13
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3234,24 +3154,11 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reducer 3
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0
- 1
+ 2
outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
@@ -3273,7 +3180,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
- Reducer 4
+ Reducer 3
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3286,30 +3193,17 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: bigint)
- Reducer 5
+ Reducer 4
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: bigint)
- Reducer 6
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0
- 1
+ 2
outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 205 Data size: 21115 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
@@ -3326,7 +3220,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 8
+ Reducer 6
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3349,6 +3243,18 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 8
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: max(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string)
Stage: Stage-0
Fetch Operator
@@ -3356,10 +3262,8 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[68][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[69][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
-Warning: Shuffle Join MERGEJOIN[70][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 5' is a cross product
-Warning: Shuffle Join MERGEJOIN[71][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 6' is a cross product
+Warning: Shuffle Join MERGEJOIN[64][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[65][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
PREHOOK: query: select key, count(*) from src where value <> (select max(value) from src) group by key having count(*) > (select count(*) from src s1 where s1.key = '90' group by s1.key )
PREHOOK: type: QUERY
PREHOOK: Input: default@src
@@ -3378,8 +3282,7 @@ POSTHOOK: Input: default@src
468 4
469 5
489 4
-Warning: Shuffle Join MERGEJOIN[35][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product
-Warning: Shuffle Join MERGEJOIN[36][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[33][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: explain select sum(p_retailprice) from part group by p_type having sum(p_retailprice) > (select max(pp.p_retailprice) from part pp)
PREHOOK: type: QUERY
POSTHOOK: query: explain select sum(p_retailprice) from part group by p_type having sum(p_retailprice) > (select max(pp.p_retailprice) from part pp)
@@ -3394,10 +3297,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE)
- Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE)
- Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE)
- Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -3423,7 +3325,7 @@ STAGE PLANS:
value expressions: _col1 (type: double)
Execution mode: llap
LLAP IO: no inputs
- Map 5
+ Map 4
Map Operator Tree:
TableScan
alias: pp
@@ -3443,7 +3345,7 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Map 7
+ Map 6
Map Operator Tree:
TableScan
alias: pp
@@ -3486,24 +3388,11 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col1
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: double)
- Reducer 4
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0
- 1
+ 2
outputColumnNames: _col1, _col3
Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
@@ -3520,7 +3409,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 6
+ Reducer 5
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3543,7 +3432,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 8
+ Reducer 7
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3562,8 +3451,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[35][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product
-Warning: Shuffle Join MERGEJOIN[36][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[33][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: select sum(p_retailprice) from part group by p_type having sum(p_retailprice) > (select max(pp.p_retailprice) from part pp)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -3574,8 +3462,7 @@ POSTHOOK: Input: default@part
#### A masked pattern was here ####
3461.37
2346.3
-Warning: Shuffle Join MERGEJOIN[79][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[80][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[77][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain select * from part where p_size > (select count(p_name) from part INTERSECT select count(p_brand) from part)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where p_size > (select count(p_name) from part INTERSECT select count(p_brand) from part)
@@ -3589,19 +3476,18 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE)
- Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Union 7 (CONTAINS)
- Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE)
- Reducer 15 <- Reducer 14 (SIMPLE_EDGE), Union 16 (CONTAINS)
- Reducer 17 <- Union 16 (SIMPLE_EDGE)
- Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE)
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE)
- Reducer 20 <- Reducer 19 (SIMPLE_EDGE), Union 16 (CONTAINS)
- Reducer 3 <- Reducer 17 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE)
- Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
- Reducer 6 <- Reducer 5 (SIMPLE_EDGE), Union 7 (CONTAINS)
- Reducer 8 <- Union 7 (SIMPLE_EDGE)
- Reducer 9 <- Reducer 8 (CUSTOM_SIMPLE_EDGE)
+ Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE)
+ Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Union 6 (CONTAINS)
+ Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE)
+ Reducer 14 <- Reducer 13 (SIMPLE_EDGE), Union 15 (CONTAINS)
+ Reducer 16 <- Union 15 (SIMPLE_EDGE)
+ Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE)
+ Reducer 19 <- Reducer 18 (SIMPLE_EDGE), Union 15 (CONTAINS)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 16 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Reducer 4 (SIMPLE_EDGE), Union 6 (CONTAINS)
+ Reducer 7 <- Union 6 (SIMPLE_EDGE)
+ Reducer 8 <- Reducer 7 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -3610,36 +3496,16 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- Execution mode: llap
- LLAP IO: no inputs
- Map 10
- Map Operator Tree:
- TableScan
- alias: part
- Statistics: Num rows: 26 Data size: 2392 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: p_brand (type: string)
- outputColumnNames: p_brand
- Statistics: Num rows: 26 Data size: 2392 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count(p_brand)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint)
+ expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 13
+ Map 12
Map Operator Tree:
TableScan
alias: part
@@ -3659,7 +3525,7 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Map 18
+ Map 17
Map Operator Tree:
TableScan
alias: part
@@ -3679,7 +3545,7 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Map 4
+ Map 3
Map Operator Tree:
TableScan
alias: part
@@ -3699,7 +3565,27 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Reducer 11
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 2392 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: p_brand (type: string)
+ outputColumnNames: p_brand
+ Statistics: Num rows: 26 Data size: 2392 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(p_brand)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 10
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3719,7 +3605,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: bigint)
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
- Reducer 12
+ Reducer 11
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3740,7 +3626,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: bigint)
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
- Reducer 14
+ Reducer 13
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3760,7 +3646,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: bigint)
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
- Reducer 15
+ Reducer 14
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3781,7 +3667,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: bigint)
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
- Reducer 17
+ Reducer 16
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3801,7 +3687,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
- Reducer 19
+ Reducer 18
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3821,22 +3707,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: bigint)
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
- Reducer 2
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- Reducer 20
+ Reducer 19
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3857,15 +3728,17 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: bigint)
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
- Reducer 3
+ Reducer 2
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
+ 2
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10
Statistics: Num rows: 26 Data size: 16302 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
@@ -3882,7 +3755,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 5
+ Reducer 4
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3902,7 +3775,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: bigint)
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
- Reducer 6
+ Reducer 5
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3923,7 +3796,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: bigint)
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
- Reducer 8
+ Reducer 7
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3950,7 +3823,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
- Reducer 9
+ Reducer 8
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3966,10 +3839,10 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Union 16
- Vertex: Union 16
- Union 7
- Vertex: Union 7
+ Union 15
+ Vertex: Union 15
+ Union 6
+ Vertex: Union 6
Stage: Stage-0
Fetch Operator
@@ -3977,8 +3850,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[79][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[80][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[77][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select * from part where p_size > (select count(p_name) from part INTERSECT select count(p_brand) from part)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -4039,17 +3911,17 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((p_size = p_size) and p_type is not null) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (p_size is not null and p_type is not null) (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_type (type: string), p_size (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -4078,17 +3950,17 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((p_size = p_size) and p_type is not null) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (p_size is not null and p_type is not null) (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_type (type: string), p_size (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -4124,17 +3996,17 @@ STAGE PLANS:
1 _col0 (type: int)
2 _col2 (type: int)
outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 1 Data size: 313 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 1252 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (_col1 like CASE WHEN (_col6 is null) THEN (null) ELSE (_col5) END) (type: boolean)
- Statistics: Num rows: 1 Data size: 313 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 626 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4149,17 +4021,17 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col0 (type: string)
outputColumnNames: _col3
- Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col3 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -4167,25 +4039,25 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 8
Execution mode: llap
Reduce Operator Tree:
@@ -4196,18 +4068,18 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col3
- Statistics: Num rows: 12 Data size: 1500 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 24 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(_col0)
keys: _col3 (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 2256 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 2256 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Reducer 9
Execution mode: llap
@@ -4217,16 +4089,16 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 2256 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), true (type: boolean), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 1152 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 2304 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 6 Data size: 1152 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 12 Data size: 2304 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: boolean)
Stage: Stage-0
@@ -4614,19 +4486,19 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 16 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 8 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 16 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: min(p_name)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 8 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 8 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -4673,18 +4545,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Reducer 10
@@ -4694,25 +4566,25 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 407 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
Reducer 12
Execution mode: llap
Reduce Operator Tree:
@@ -4721,16 +4593,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 814 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: string), true (type: boolean), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 4 Data size: 814 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 4 Data size: 814 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string), _col1 (type: boolean)
Reducer 2
Execution mode: llap
@@ -4785,17 +4657,17 @@ STAGE PLANS:
1 _col0 (type: string)
2 _col2 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col15, _col16
- Statistics: Num rows: 15 Data size: 1964 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 3581 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (not (_col1 like CASE WHEN (_col16 is null) THEN (null) ELSE (_col15) END)) (type: boolean)
- Statistics: Num rows: 8 Data size: 1047 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1895 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 8 Data size: 1047 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1895 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 8 Data size: 1047 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1895 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -5441,18 +5313,18 @@ STAGE PLANS:
alias: lineitem
Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (l_partkey = l_partkey) (type: boolean)
- Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: l_partkey is not null (type: boolean)
+ Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: l_partkey (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 7
@@ -5461,19 +5333,19 @@ STAGE PLANS:
alias: lineitem
Statistics: Num rows: 100 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (l_partkey = l_partkey) (type: boolean)
- Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: l_partkey is not null (type: boolean)
+ Statistics: Num rows: 100 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: avg(l_quantity)
keys: l_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 25 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: struct)
Execution mode: llap
LLAP IO: no inputs
@@ -5528,25 +5400,25 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 16 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 16 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 16 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 8
Execution mode: llap
Reduce Operator Tree:
@@ -5555,16 +5427,16 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: double), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 25 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Stage: Stage-0
@@ -5626,17 +5498,17 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 8242 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 4121 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 8242 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_name (type: string), p_brand (type: string), p_type (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 4121 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 8242 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 13 Data size: 4121 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 26 Data size: 8242 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -5646,18 +5518,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 7
@@ -5666,19 +5538,19 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5096 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: min(p_brand)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -5737,25 +5609,25 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 8
Execution mode: llap
Reduce Operator Tree:
@@ -5764,16 +5636,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), true (type: boolean), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 3796 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 6 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 3796 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: boolean)
Stage: Stage-0
@@ -5978,18 +5850,18 @@ STAGE PLANS:
alias: depts
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (name = name) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ predicate: name is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: name (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Map 5
@@ -5998,19 +5870,19 @@ STAGE PLANS:
alias: depts
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (name = name) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ predicate: name is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(deptno)
keys: name (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -6149,18 +6021,18 @@ STAGE PLANS:
alias: depts
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (deptno = deptno) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ predicate: deptno is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: deptno (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Map 5
@@ -6169,19 +6041,19 @@ STAGE PLANS:
alias: depts
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (deptno = deptno) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ predicate: deptno is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: min(name)
keys: deptno (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -6319,19 +6191,19 @@ STAGE PLANS:
alias: depts
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (deptno = deptno) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ predicate: deptno is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(name)
keys: deptno (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -6341,18 +6213,18 @@ STAGE PLANS:
alias: depts
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (name = name) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ predicate: name is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: name (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Map 6
@@ -6361,19 +6233,19 @@ STAGE PLANS:
alias: depts
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (name = name) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ predicate: name is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(deptno)
keys: name (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -6383,18 +6255,18 @@ STAGE PLANS:
alias: depts
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (deptno = deptno) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ predicate: deptno is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: deptno (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Reducer 11
@@ -6627,18 +6499,18 @@ STAGE PLANS:
alias: depts
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (name = name) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ predicate: name is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: name (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: no inputs
Map 6
@@ -6647,19 +6519,19 @@ STAGE PLANS:
alias: depts
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (name = name) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ predicate: name is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(deptno)
keys: name (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -6853,8 +6725,7 @@ POSTHOOK: query: drop table EMPS
POSTHOOK: type: DROPTABLE
POSTHOOK: Input: default@emps
POSTHOOK: Output: default@emps
-Warning: Shuffle Join MERGEJOIN[39][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product
-Warning: Shuffle Join MERGEJOIN[40][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[37][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: explain
select key, count(*)
from src
@@ -6877,10 +6748,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE)
- Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE)
- Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE)
- Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -6906,7 +6776,7 @@ STAGE PLANS:
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Map 5
+ Map 4
Map Operator Tree:
TableScan
alias: s1
@@ -6925,7 +6795,7 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Map 7
+ Map 6
Map Operator Tree:
TableScan
alias: s1
@@ -6965,24 +6835,11 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: bigint)
- Reducer 4
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0
- 1
+ 2
outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 205 Data size: 21115 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
@@ -6999,7 +6856,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 6
+ Reducer 5
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -7022,7 +6879,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 8
+ Reducer 7
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -7041,8 +6898,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[39][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product
-Warning: Shuffle Join MERGEJOIN[40][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[37][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: select key, count(*)
from src
group by key
@@ -7067,8 +6923,7 @@ POSTHOOK: Input: default@src
468 4
469 5
489 4
-Warning: Shuffle Join MERGEJOIN[56][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 4' is a cross product
-Warning: Shuffle Join MERGEJOIN[57][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product
+Warning: Shuffle Join MERGEJOIN[54][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
PREHOOK: query: explain
select key, value, count(*)
from src b
@@ -7092,13 +6947,12 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE)
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
+ Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
- Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE)
- Reducer 5 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
- Reducer 7 <- Map 6 (SIMPLE_EDGE)
- Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE)
+ Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -7121,28 +6975,7 @@ STAGE PLANS:
value expressions: _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 10
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (key > '9') (type: boolean)
- Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint)
- Execution mode: llap
- LLAP IO: no inputs
- Map 6
+ Map 5
Map Operator Tree:
TableScan
alias: src
@@ -7162,7 +6995,7 @@ STAGE PLANS:
Statistics: Num rows: 69 Data size: 6003 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 8
+ Map 7
Map Operator Tree:
TableScan
alias: s1
@@ -7181,7 +7014,28 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Reducer 11
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: s1
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (key > '9') (type: boolean)
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 10
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -7235,24 +7089,11 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- Reducer 5
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0
- 1
+ 2
outputColumnNames: _col0, _col1, _col2, _col4
Statistics: Num rows: 83 Data size: 16102 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
@@ -7269,7 +7110,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 7
+ Reducer 6
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -7282,7 +7123,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 69 Data size: 6003 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 9
+ Reducer 8
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -7312,8 +7153,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[56][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 4' is a cross product
-Warning: Shuffle Join MERGEJOIN[57][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product
+Warning: Shuffle Join MERGEJOIN[54][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
PREHOOK: query: select key, value, count(*)
from src b
where b.key in (select key from src where src.key > '8')
diff --git a/ql/src/test/results/clientpositive/llap/subquery_select.q.out b/ql/src/test/results/clientpositive/llap/subquery_select.q.out
index 945603f..8eaec9e 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_select.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_select.q.out
@@ -1,4 +1,4 @@
-Warning: Shuffle Join MERGEJOIN[34][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain SELECT p_size, p_size IN (
SELECT MAX(p_size) FROM part)
FROM part
@@ -17,10 +17,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
- Reducer 8 <- Reducer 7 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -142,24 +141,6 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 8
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), true (type: boolean)
outputColumnNames: _col0, _col1
@@ -177,7 +158,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[34][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: SELECT p_size, p_size IN (
SELECT MAX(p_size) FROM part)
FROM part
@@ -234,10 +215,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (SIMPLE_EDGE)
Reducer 7 <- Map 6 (SIMPLE_EDGE)
- Reducer 8 <- Reducer 7 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -263,19 +243,19 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(p_size)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -285,19 +265,19 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(p_size)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -348,18 +328,18 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(_col1)
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Reducer 7
Execution mode: llap
@@ -369,41 +349,23 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 8
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: int)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Stage: Stage-0
@@ -450,7 +412,7 @@ POSTHOOK: Input: default@part
6 true
18 true
45 true
-Warning: Shuffle Join MERGEJOIN[34][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain SELECT p_size, p_size NOT IN (
SELECT MAX(p_size) FROM part)
FROM part
@@ -469,10 +431,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
- Reducer 8 <- Reducer 7 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -594,24 +555,6 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 8
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), true (type: boolean)
outputColumnNames: _col0, _col1
@@ -629,7 +572,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[34][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: SELECT p_size, p_size NOT IN (
SELECT MAX(p_size) FROM part)
FROM part
@@ -686,10 +629,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 10 <- Map 9 (SIMPLE_EDGE)
- Reducer 11 <- Reducer 10 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
- Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 6 <- Map 5 (SIMPLE_EDGE)
Reducer 8 <- Map 7 (SIMPLE_EDGE)
#### A masked pattern was here ####
@@ -717,18 +659,18 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 7
@@ -737,19 +679,19 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(p_size)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -759,19 +701,19 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(p_size)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -783,41 +725,23 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 11
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: int)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: boolean)
Reducer 2
Execution mode: llap
@@ -889,18 +813,18 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 8
Execution mode: llap
@@ -910,18 +834,18 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(_col1)
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Stage: Stage-0
@@ -1142,18 +1066,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1185,16 +1109,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: boolean)
Stage: Stage-0
@@ -1413,18 +1337,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1456,16 +1380,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: boolean)
Stage: Stage-0
@@ -1551,18 +1475,18 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
@@ -1571,19 +1495,19 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(p_name)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -1618,25 +1542,25 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -1645,16 +1569,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 6 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: boolean)
Stage: Stage-0
@@ -1738,18 +1662,18 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
@@ -1758,19 +1682,19 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 2925 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(p_name)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -1805,25 +1729,25 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -1832,16 +1756,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 3744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), true (type: boolean), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 3796 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 6 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 3796 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: boolean)
Stage: Stage-0
@@ -2397,18 +2321,18 @@ STAGE PLANS:
alias: sc
Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (value = value) (type: boolean)
- Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: value (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 107 Data size: 9737 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 107 Data size: 9737 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 7
@@ -2417,19 +2341,19 @@ STAGE PLANS:
alias: sc
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (value = value) (type: boolean)
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(key)
keys: value (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 107 Data size: 29425 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 58850 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 107 Data size: 29425 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 58850 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -2463,21 +2387,21 @@ STAGE PLANS:
1 _col0 (type: string)
2 _col2 (type: string)
outputColumnNames: _col1, _col4, _col5
- Statistics: Num rows: 80 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: CASE WHEN (_col5 is null) THEN (null) ELSE (_col4) END (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 80 Data size: 22000 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 83 Data size: 22825 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 40 Data size: 11000 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 41 Data size: 11275 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 40 Data size: 11000 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 41 Data size: 11275 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -2485,25 +2409,25 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 107 Data size: 9737 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 107 Data size: 10593 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 21186 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 35 Data size: 3465 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 71 Data size: 7029 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 35 Data size: 3465 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 71 Data size: 7029 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 35 Data size: 3465 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 71 Data size: 7029 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 8
Execution mode: llap
Reduce Operator Tree:
@@ -2512,16 +2436,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 107 Data size: 29425 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 58850 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), true (type: boolean), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 107 Data size: 29853 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 59706 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 107 Data size: 29853 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 214 Data size: 59706 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: boolean)
Stage: Stage-0
@@ -3210,18 +3134,18 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
@@ -3230,19 +3154,19 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(p_size)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -3277,25 +3201,25 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -3304,16 +3228,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), true (type: boolean), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: boolean)
Stage: Stage-0
@@ -3401,18 +3325,18 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
@@ -3421,19 +3345,19 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(p_size)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -3468,25 +3392,25 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -3495,16 +3419,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 6 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1508 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: boolean)
Stage: Stage-0
@@ -3744,7 +3668,7 @@ STANDARD BURNISHED TIN true
SMALL PLATED BRASS true
ECONOMY BURNISHED STEEL true
LARGE BRUSHED BRASS true
-Warning: Shuffle Join MERGEJOIN[74][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[63][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product
PREHOOK: query: EXPLAIN SELECT p_size, p_size IN (
SELECT MAX(p_size) FROM part p where p.p_type = part.p_type) AND
p_name IN (SELECT min(p_name) from part)
@@ -3764,14 +3688,12 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 10 <- Reducer 9 (SIMPLE_EDGE)
- Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE)
- Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE)
- Reducer 15 <- Reducer 14 (SIMPLE_EDGE)
+ Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE)
+ Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
- Reducer 4 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE)
- Reducer 5 <- Reducer 15 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Reducer 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
Reducer 7 <- Map 6 (SIMPLE_EDGE)
Reducer 9 <- Map 8 (SIMPLE_EDGE)
#### A masked pattern was here ####
@@ -3793,7 +3715,7 @@ STAGE PLANS:
value expressions: _col0 (type: string), _col2 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 11
+ Map 10
Map Operator Tree:
TableScan
alias: part
@@ -3813,7 +3735,7 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 13
+ Map 12
Map Operator Tree:
TableScan
alias: part
@@ -3839,19 +3761,19 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(p_size)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -3861,48 +3783,23 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(p_size)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Reducer 10
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: int), _col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), true (type: boolean)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col1 (type: string), _col0 (type: int)
- sort order: ++
- Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col2 (type: boolean)
- Reducer 12
+ Reducer 11
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3919,7 +3816,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: bigint)
- Reducer 14
+ Reducer 13
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3927,24 +3824,6 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 15
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1
@@ -4034,18 +3913,18 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(_col1)
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Reducer 9
Execution mode: llap
@@ -4055,17 +3934,24 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: int)
- mode: hash
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), true (type: boolean)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: string), _col0 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: boolean)
Stage: Stage-0
Fetch Operator
@@ -4073,7 +3959,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[74][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[63][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product
PREHOOK: query: SELECT p_size, p_size IN (
SELECT MAX(p_size) FROM part p where p.p_type = part.p_type) AND
p_name IN (SELECT min(p_name) from part)
@@ -4156,18 +4042,18 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -4199,16 +4085,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: boolean)
Stage: Stage-0
@@ -4253,11 +4139,11 @@ POSTHOOK: Input: default@part
6 false
18 false
45 false
-Warning: Shuffle Join MERGEJOIN[90][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product
-Warning: Shuffle Join MERGEJOIN[91][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 6' is a cross product
-Warning: Shuffle Join MERGEJOIN[92][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[93][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 14' is a cross product
-Warning: Shuffle Join MERGEJOIN[94][tables = [$hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 15' is a cross product
+Warning: Shuffle Join MERGEJOIN[85][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product
+Warning: Shuffle Join MERGEJOIN[86][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 6' is a cross product
+Warning: Shuffle Join MERGEJOIN[87][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[88][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 14' is a cross product
+Warning: Shuffle Join MERGEJOIN[89][tables = [$hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 15' is a cross product
PREHOOK: query: explain select p_size, (p_size IN
(select (select max(p_size) from part) as sb from part order by sb limit 1)) = true
from part
@@ -4277,14 +4163,13 @@ STAGE PLANS:
Edges:
Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE)
Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE)
- Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE), Reducer 19 (CUSTOM_SIMPLE_EDGE)
- Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE), Reducer 21 (CUSTOM_SIMPLE_EDGE)
+ Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE), Reducer 18 (CUSTOM_SIMPLE_EDGE)
+ Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE), Reducer 20 (CUSTOM_SIMPLE_EDGE)
Reducer 16 <- Reducer 15 (SIMPLE_EDGE)
- Reducer 17 <- Reducer 16 (SIMPLE_EDGE)
- Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE)
+ Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE)
Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE)
- Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE)
- Reducer 3 <- Reducer 17 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+ Reducer 20 <- Map 19 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE), Reducer 10 (CUSTOM_SIMPLE_EDGE)
Reducer 6 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
@@ -4338,7 +4223,7 @@ STAGE PLANS:
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 18
+ Map 17
Map Operator Tree:
TableScan
alias: part
@@ -4358,7 +4243,7 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Map 20
+ Map 19
Map Operator Tree:
TableScan
alias: part
@@ -4477,6 +4362,7 @@ STAGE PLANS:
key expressions: _col0 (type: int)
sort order: +
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
Reducer 16
Execution mode: llap
Reduce Operator Tree:
@@ -4487,35 +4373,17 @@ STAGE PLANS:
Limit
Number of rows: 1
Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), true (type: boolean)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 17
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: int), true (type: boolean)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: boolean)
- Reducer 19
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: boolean)
+ Reducer 18
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -4555,7 +4423,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 26 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
- Reducer 21
+ Reducer 20
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -4659,11 +4527,11 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[90][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product
-Warning: Shuffle Join MERGEJOIN[91][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 6' is a cross product
-Warning: Shuffle Join MERGEJOIN[92][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[93][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 14' is a cross product
-Warning: Shuffle Join MERGEJOIN[94][tables = [$hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 15' is a cross product
+Warning: Shuffle Join MERGEJOIN[85][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product
+Warning: Shuffle Join MERGEJOIN[86][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 6' is a cross product
+Warning: Shuffle Join MERGEJOIN[87][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[88][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 14' is a cross product
+Warning: Shuffle Join MERGEJOIN[89][tables = [$hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 15' is a cross product
PREHOOK: query: select p_size, (p_size IN
(select (select max(p_size) from part) as sb from part order by sb limit 1)) = true
from part
@@ -5387,18 +5255,18 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_partkey (type: int), p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 3
@@ -5462,18 +5330,18 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_partkey (type: int), p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 10
@@ -5483,34 +5351,34 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 12
Execution mode: llap
Reduce Operator Tree:
@@ -5518,22 +5386,22 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(_col1)
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: boolean)
Reducer 2
Execution mode: llap
@@ -5549,14 +5417,14 @@ STAGE PLANS:
2 _col0 (type: int)
3 _col2 (type: int)
outputColumnNames: _col1, _col5, _col6
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), CASE WHEN (_col6 is null) THEN (0) ELSE (_col5) END (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -6517,19 +6385,19 @@ STAGE PLANS:
alias: a1
Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(p_size)
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -6578,18 +6446,18 @@ STAGE PLANS:
alias: a1
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 20
@@ -6598,19 +6466,19 @@ STAGE PLANS:
alias: a1
Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(p_size)
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -6659,18 +6527,18 @@ STAGE PLANS:
alias: a1
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 10
@@ -6680,25 +6548,25 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 12
Execution mode: llap
Reduce Operator Tree:
@@ -6707,16 +6575,16 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: boolean)
Reducer 14
Execution mode: llap
@@ -6780,25 +6648,25 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -6822,16 +6690,16 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: boolean)
Reducer 3
Execution mode: llap
@@ -7058,18 +6926,18 @@ STAGE PLANS:
alias: a1
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 16
@@ -7078,19 +6946,19 @@ STAGE PLANS:
alias: a1
Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(p_size)
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -7139,18 +7007,18 @@ STAGE PLANS:
alias: a1
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 25
@@ -7159,19 +7027,19 @@ STAGE PLANS:
alias: a1
Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(p_size)
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -7181,18 +7049,18 @@ STAGE PLANS:
alias: t2
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 7
@@ -7201,19 +7069,19 @@ STAGE PLANS:
alias: t2
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
@@ -7312,25 +7180,25 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 17
Execution mode: llap
Reduce Operator Tree:
@@ -7339,16 +7207,16 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: boolean)
Reducer 19
Execution mode: llap
@@ -7378,10 +7246,10 @@ STAGE PLANS:
1 _col0 (type: int)
2 _col2 (type: int)
outputColumnNames: _col1, _col4, _col5
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int), _col4 (type: bigint), _col5 (type: boolean)
Reducer 20
Execution mode: llap
@@ -7429,25 +7297,25 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 26
Execution mode: llap
Reduce Operator Tree:
@@ -7456,16 +7324,16 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: boolean)
Reducer 3
Execution mode: llap
@@ -7477,10 +7345,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col1, _col4, _col5
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int), _col4 (type: bigint), _col5 (type: boolean)
Reducer 4
Execution mode: llap
@@ -7492,14 +7360,14 @@ STAGE PLANS:
0
1
outputColumnNames: _col1, _col4, _col5, _col8
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), CASE WHEN (_col5 is null) THEN (0) ELSE (_col4) END (type: bigint), _col8 (type: bigint)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 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
@@ -7511,25 +7379,25 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 8
Execution mode: llap
Reduce Operator Tree:
@@ -7538,16 +7406,16 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: boolean)
Stage: Stage-0
@@ -7643,18 +7511,18 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
@@ -7663,19 +7531,19 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(p_size)
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
@@ -7710,25 +7578,25 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (sq_count_check(_col1) <= 1) (type: boolean)
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -7737,16 +7605,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1404 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: int), true (type: boolean), _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: string)
sort order: +
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 6 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: boolean)
Stage: Stage-0
diff --git a/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out
index 10bd85e..a0ac248 100644
--- a/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out
@@ -1273,8 +1273,8 @@ STAGE PLANS:
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: SelectColumnIsNotNull(col 2)(children: LongColAddLongScalar(col 0, val 1) -> 2:long) -> boolean
- predicate: (key + 1) is not null (type: boolean)
+ predicateExpression: SelectColumnIsNotNull(col 0) -> boolean
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
@@ -1316,8 +1316,8 @@ STAGE PLANS:
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: SelectColumnIsNotNull(col 2)(children: LongColAddLongScalar(col 0, val 1) -> 2:long) -> boolean
- predicate: (key + 1) is not null (type: boolean)
+ predicateExpression: SelectColumnIsNotNull(col 0) -> boolean
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
diff --git a/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out b/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out
index 923e579..cb9674c 100644
--- a/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out
@@ -115,13 +115,13 @@ STAGE PLANS:
1 Map 2
Statistics: Num rows: 25 Data size: 385 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), _col3 (type: smallint), CASE WHEN (_col1 BETWEEN _col3 AND _col3) THEN ('Ok') ELSE ('NoOk') END (type: string)
+ expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), _col3 (type: smallint), CASE WHEN (_col1 BETWEEN UDFToInteger(_col3) AND UDFToInteger(_col3)) THEN ('Ok') ELSE ('NoOk') END (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
Select Vectorization:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 2, 1, 3, 5]
- selectExpressions: IfExprStringScalarStringScalar(col 4, val Ok, val NoOk)(children: VectorUDFAdaptor(_col1 BETWEEN _col3 AND _col3) -> 4:boolean) -> 5:String
+ selectExpressions: IfExprStringScalarStringScalar(col 4, val Ok, val NoOk)(children: VectorUDFAdaptor(_col1 BETWEEN UDFToInteger(_col3) AND UDFToInteger(_col3))(children: col 3, col 3) -> 4:boolean) -> 5:String
Statistics: Num rows: 25 Data size: 385 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -279,8 +279,8 @@ STAGE PLANS:
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: SelectColumnIsTrue(col 4)(children: VectorUDFAdaptor(_col1 BETWEEN _col3 AND _col3) -> 4:boolean) -> boolean
- predicate: _col1 BETWEEN _col3 AND _col3 (type: boolean)
+ predicateExpression: SelectColumnIsTrue(col 4)(children: VectorUDFAdaptor(_col1 BETWEEN UDFToInteger(_col3) AND UDFToInteger(_col3))(children: col 3, col 3) -> 4:boolean) -> boolean
+ predicate: _col1 BETWEEN UDFToInteger(_col3) AND UDFToInteger(_col3) (type: boolean)
Statistics: Num rows: 2 Data size: 30 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), _col3 (type: smallint)
diff --git a/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out
index eee37d0..6d828a5 100644
--- a/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out
@@ -208,8 +208,8 @@ STAGE PLANS:
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 8) -> boolean, SelectColumnIsNotNull(col 14)(children: DateColSubtractDateColumn(col 12, col 13)(children: CastTimestampToDate(col 10) -> 13:date) -> 14:timestamp) -> boolean) -> boolean
- predicate: (s is not null and (dt - CAST( ts AS DATE)) is not null) (type: boolean)
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 8) -> boolean, SelectColumnIsNotNull(col 12) -> boolean, SelectColumnIsNotNull(col 10) -> boolean) -> boolean
+ predicate: (s is not null and dt is not null and ts is not null) (type: boolean)
Statistics: Num rows: 1000 Data size: 460264 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time)
@@ -274,8 +274,8 @@ STAGE PLANS:
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 8) -> boolean, SelectColumnIsNotNull(col 14)(children: DateColSubtractDateColumn(col 12, col 13)(children: CastTimestampToDate(col 10) -> 13:date) -> 14:timestamp) -> boolean) -> boolean
- predicate: (s is not null and (dt - CAST( ts AS DATE)) is not null) (type: boolean)
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 8) -> boolean, SelectColumnIsNotNull(col 12) -> boolean, SelectColumnIsNotNull(col 10) -> boolean) -> boolean
+ predicate: (s is not null and dt is not null and ts is not null) (type: boolean)
Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time)
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_0.q.out b/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
index 381815d..d2897ba 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
@@ -30532,18 +30532,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean)
- Statistics: Num rows: 6 Data size: 1630 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (struct(cint,cfloat)) IN (const struct(49,3.5), const struct(47,2.09), const struct(45,3.02)) (type: boolean)
+ Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 6 Data size: 1630 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 6 Data size: 1630 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -30560,7 +30560,7 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: false
MultiFileSpray: false
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: all inputs
Path -> Alias:
#### A masked pattern was here ####
diff --git a/ql/src/test/results/clientpositive/louter_join_ppr.q.out b/ql/src/test/results/clientpositive/louter_join_ppr.q.out
index 2f6cdfd..a4de667 100644
--- a/ql/src/test/results/clientpositive/louter_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/louter_join_ppr.q.out
@@ -30,18 +30,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -51,18 +51,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -219,38 +219,34 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -324,24 +320,24 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 12 Data size: 127 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: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 0
- value expressions: _col1 (type: string), _col2 (type: string)
+ value expressions: _col1 (type: string)
auto parallelism: false
TableScan
alias: b
@@ -349,18 +345,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -509,153 +505,46 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart
name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
Truncated Path -> Alias:
/src [$hdt$_1:b]
/srcpart/ds=2008-04-08/hr=11 [$hdt$_0:a]
/srcpart/ds=2008-04-08/hr=12 [$hdt$_0:a]
- /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:a]
- /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:a]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
- filter mappings:
- 0 [1, 1]
- filter predicates:
- 0 {(VALUE._col1 = '2008-04-08')}
- 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 25.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -675,8 +564,6 @@ PREHOOK: Input: default@src
PREHOOK: Input: default@srcpart
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
POSTHOOK: query: FROM
srcpart a
@@ -690,8 +577,6 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
17 val_17 17 val_17
17 val_17 17 val_17
@@ -1031,18 +916,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -1052,18 +937,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -1220,42 +1105,38 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 25.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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/mapjoin1.q.out b/ql/src/test/results/clientpositive/mapjoin1.q.out
index e103eff..dc74634 100644
--- a/ql/src/test/results/clientpositive/mapjoin1.q.out
+++ b/ql/src/test/results/clientpositive/mapjoin1.q.out
@@ -138,7 +138,7 @@ STAGE PLANS:
HashTable Sink Operator
filter predicates:
0
- 1 {((UDFToDouble(_col0) * UDFToDouble(10)) < UDFToDouble('1000'))}
+ 1 {((UDFToDouble(_col0) * 10.0) < 1000.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -158,7 +158,7 @@ STAGE PLANS:
Right Outer Join0 to 1
filter predicates:
0
- 1 {((UDFToDouble(_col0) * UDFToDouble(10)) < UDFToDouble('1000'))}
+ 1 {((UDFToDouble(_col0) * 10.0) < 1000.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -233,7 +233,7 @@ STAGE PLANS:
HashTable Sink Operator
filter predicates:
0
- 1 {(UDFToDouble(_col1.key) > UDFToDouble(200))}
+ 1 {(UDFToDouble(_col1.key) > 200.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -253,7 +253,7 @@ STAGE PLANS:
Right Outer Join0 to 1
filter predicates:
0
- 1 {(UDFToDouble(_col1.key) > UDFToDouble(200))}
+ 1 {(UDFToDouble(_col1.key) > 200.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -415,7 +415,7 @@ STAGE PLANS:
HashTable Sink Operator
filter predicates:
0
- 1 {((UDFToDouble(_col0) * UDFToDouble(10)) < UDFToDouble('1000'))}
+ 1 {((UDFToDouble(_col0) * 10.0) < 1000.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -435,7 +435,7 @@ STAGE PLANS:
Right Outer Join0 to 1
filter predicates:
0
- 1 {((UDFToDouble(_col0) * UDFToDouble(10)) < UDFToDouble('1000'))}
+ 1 {((UDFToDouble(_col0) * 10.0) < 1000.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -510,7 +510,7 @@ STAGE PLANS:
HashTable Sink Operator
filter predicates:
0
- 1 {(UDFToDouble(_col1.key) > UDFToDouble(200))}
+ 1 {(UDFToDouble(_col1.key) > 200.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -530,7 +530,7 @@ STAGE PLANS:
Right Outer Join0 to 1
filter predicates:
0
- 1 {(UDFToDouble(_col1.key) > UDFToDouble(200))}
+ 1 {(UDFToDouble(_col1.key) > 200.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
diff --git a/ql/src/test/results/clientpositive/mergejoin.q.out b/ql/src/test/results/clientpositive/mergejoin.q.out
index 0ceb0e3..025de3c 100644
--- a/ql/src/test/results/clientpositive/mergejoin.q.out
+++ b/ql/src/test/results/clientpositive/mergejoin.q.out
@@ -2701,16 +2701,14 @@ POSTHOOK: Input: default@tab_part@ds=2008-04-08
#### A masked pattern was here ####
NULL NULL NULL 98 val_98 2008-04-08
NULL NULL NULL 98 val_98 2008-04-08
-Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: select * from
(select * from tab where tab.key = 0)a
full outer join
(select * from tab_part where tab_part.key = 98)b join tab_part c on a.key = b.key and b.key = c.key
PREHOOK: type: QUERY
PREHOOK: Input: default@tab
-PREHOOK: Input: default@tab@ds=2008-04-08
PREHOOK: Input: default@tab_part
-PREHOOK: Input: default@tab_part@ds=2008-04-08
#### A masked pattern was here ####
POSTHOOK: query: select * from
(select * from tab where tab.key = 0)a
@@ -2718,9 +2716,7 @@ full outer join
(select * from tab_part where tab_part.key = 98)b join tab_part c on a.key = b.key and b.key = c.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab
-POSTHOOK: Input: default@tab@ds=2008-04-08
POSTHOOK: Input: default@tab_part
-POSTHOOK: Input: default@tab_part@ds=2008-04-08
#### A masked pattern was here ####
Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product
Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
@@ -3274,15 +3270,14 @@ NULL NULL NULL NULL NULL NULL 97 val_97 2008-04-08
NULL NULL NULL NULL NULL NULL 97 val_97 2008-04-08
NULL NULL NULL NULL NULL NULL 98 val_98 2008-04-08
NULL NULL NULL NULL NULL NULL 98 val_98 2008-04-08
-Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product
-Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: select * from
(select * from tab where tab.key = 0)a
join
(select * from tab_part where tab_part.key = 98)b on a.key = b.key full outer join tab_part c on b.key = c.key
PREHOOK: type: QUERY
PREHOOK: Input: default@tab
-PREHOOK: Input: default@tab@ds=2008-04-08
PREHOOK: Input: default@tab_part
PREHOOK: Input: default@tab_part@ds=2008-04-08
#### A masked pattern was here ####
@@ -3292,7 +3287,6 @@ join
(select * from tab_part where tab_part.key = 98)b on a.key = b.key full outer join tab_part c on b.key = c.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab
-POSTHOOK: Input: default@tab@ds=2008-04-08
POSTHOOK: Input: default@tab_part
POSTHOOK: Input: default@tab_part@ds=2008-04-08
#### A masked pattern was here ####
diff --git a/ql/src/test/results/clientpositive/mergejoins.q.out b/ql/src/test/results/clientpositive/mergejoins.q.out
index 1023f61..4a290a1 100644
--- a/ql/src/test/results/clientpositive/mergejoins.q.out
+++ b/ql/src/test/results/clientpositive/mergejoins.q.out
@@ -251,7 +251,7 @@ STAGE PLANS:
Left Outer Join1 to 2
filter predicates:
0
- 1 {(UDFToDouble(KEY.reducesinkkey0) < UDFToDouble(10))}
+ 1 {(UDFToDouble(KEY.reducesinkkey0) < 10.0)}
2
keys:
0 _col0 (type: string)
diff --git a/ql/src/test/results/clientpositive/optimize_filter_literal.q.out b/ql/src/test/results/clientpositive/optimize_filter_literal.q.out
index 00bb01b..32e2bf6 100644
--- a/ql/src/test/results/clientpositive/optimize_filter_literal.q.out
+++ b/ql/src/test/results/clientpositive/optimize_filter_literal.q.out
@@ -128,16 +128,14 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab
POSTHOOK: Input: default@tab@ds=2008-04-08
#### A masked pattern was here ####
-Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: select * from
(select * from tab where tab.key = 0)a
full outer join
(select * from tab_part where tab_part.key = 98)b join tab_part c on a.key = b.key and b.key = c.key
PREHOOK: type: QUERY
PREHOOK: Input: default@tab
-PREHOOK: Input: default@tab@ds=2008-04-08
PREHOOK: Input: default@tab_part
-PREHOOK: Input: default@tab_part@ds=2008-04-08
#### A masked pattern was here ####
POSTHOOK: query: select * from
(select * from tab where tab.key = 0)a
@@ -145,7 +143,5 @@ full outer join
(select * from tab_part where tab_part.key = 98)b join tab_part c on a.key = b.key and b.key = c.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab
-POSTHOOK: Input: default@tab@ds=2008-04-08
POSTHOOK: Input: default@tab_part
-POSTHOOK: Input: default@tab_part@ds=2008-04-08
#### A masked pattern was here ####
diff --git a/ql/src/test/results/clientpositive/outer_join_ppr.q.out b/ql/src/test/results/clientpositive/outer_join_ppr.q.out
index 2bf6d61..09f30b8 100644
--- a/ql/src/test/results/clientpositive/outer_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/outer_join_ppr.q.out
@@ -28,36 +28,44 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- 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
- 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
- value expressions: _col1 (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
TableScan
alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string), _col2 (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 12 Data size: 127 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: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -203,149 +211,42 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart
name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
Truncated Path -> Alias:
/src [$hdt$_0:a]
/srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b]
/srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b]
- /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:b]
- /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:b]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
- Outer Join 0 to 1
- filter mappings:
- 1 [0, 1]
- filter predicates:
- 0
- 1 {(VALUE._col1 = '2008-04-08')}
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -365,8 +266,6 @@ PREHOOK: Input: default@src
PREHOOK: Input: default@srcpart
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
POSTHOOK: query: FROM
src a
@@ -380,8 +279,6 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
17 val_17 17 val_17
17 val_17 17 val_17
@@ -427,18 +324,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -448,18 +345,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -616,38 +513,34 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Right Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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/perf/query1.q.out b/ql/src/test/results/clientpositive/perf/query1.q.out
index 0b659ac..07828da 100644
--- a/ql/src/test/results/clientpositive/perf/query1.q.out
+++ b/ql/src/test/results/clientpositive/perf/query1.q.out
@@ -80,28 +80,28 @@ Stage-0
<-Reducer 18 [SIMPLE_EDGE]
SHUFFLE [RS_75]
PartitionCols:_col2
- Select Operator [SEL_73] (rows=7918783 width=77)
+ Select Operator [SEL_73] (rows=15837566 width=77)
Output:["_col0","_col1","_col2"]
- Group By Operator [GBY_72] (rows=7918783 width=77)
+ Group By Operator [GBY_72] (rows=15837566 width=77)
Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col1
- Select Operator [SEL_68] (rows=15837566 width=77)
+ Select Operator [SEL_68] (rows=31675133 width=77)
Output:["_col1","_col2"]
- Group By Operator [GBY_67] (rows=15837566 width=77)
+ Group By Operator [GBY_67] (rows=31675133 width=77)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
<-Reducer 17 [SIMPLE_EDGE]
SHUFFLE [RS_66]
PartitionCols:_col0
- Group By Operator [GBY_65] (rows=31675133 width=77)
+ Group By Operator [GBY_65] (rows=63350266 width=77)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1
- Merge Join Operator [MERGEJOIN_112] (rows=31675133 width=77)
+ Merge Join Operator [MERGEJOIN_112] (rows=63350266 width=77)
Conds:RS_61._col0=RS_62._col0(Inner),Output:["_col1","_col2","_col3"]
<-Map 16 [SIMPLE_EDGE]
SHUFFLE [RS_61]
PartitionCols:_col0
- Select Operator [SEL_57] (rows=28795575 width=77)
+ Select Operator [SEL_57] (rows=57591150 width=77)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_106] (rows=28795575 width=77)
- predicate:((sr_store_sk = sr_store_sk) and sr_returned_date_sk is not null)
+ Filter Operator [FIL_106] (rows=57591150 width=77)
+ predicate:(sr_returned_date_sk is not null and sr_store_sk is not null)
TableScan [TS_55] (rows=57591150 width=77)
default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_customer_sk","sr_store_sk","sr_fee"]
<-Map 19 [SIMPLE_EDGE]
@@ -121,32 +121,32 @@ Stage-0
<-Reducer 14 [SIMPLE_EDGE]
SHUFFLE [RS_52]
PartitionCols:_col0
- Select Operator [SEL_44] (rows=1319797 width=77)
+ Select Operator [SEL_44] (rows=2639594 width=77)
Output:["_col0"]
- Filter Operator [FIL_43] (rows=1319797 width=77)
+ Filter Operator [FIL_43] (rows=2639594 width=77)
predicate:(sq_count_check(_col1) <= 1)
- Group By Operator [GBY_42] (rows=3959391 width=77)
+ Group By Operator [GBY_42] (rows=7918783 width=77)
Output:["_col0","_col1"],aggregations:["count()"],keys:_col0
- Group By Operator [GBY_37] (rows=7918783 width=77)
+ Group By Operator [GBY_37] (rows=15837566 width=77)
Output:["_col0"],keys:_col1
- Select Operator [SEL_33] (rows=15837566 width=77)
+ Select Operator [SEL_33] (rows=31675133 width=77)
Output:["_col1"]
- Group By Operator [GBY_32] (rows=15837566 width=77)
+ Group By Operator [GBY_32] (rows=31675133 width=77)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
<-Reducer 13 [SIMPLE_EDGE]
SHUFFLE [RS_31]
PartitionCols:_col0
- Group By Operator [GBY_30] (rows=31675133 width=77)
+ Group By Operator [GBY_30] (rows=63350266 width=77)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1
- Merge Join Operator [MERGEJOIN_111] (rows=31675133 width=77)
+ Merge Join Operator [MERGEJOIN_111] (rows=63350266 width=77)
Conds:RS_26._col0=RS_27._col0(Inner),Output:["_col1","_col2","_col3"]
<-Map 12 [SIMPLE_EDGE]
SHUFFLE [RS_26]
PartitionCols:_col0
- Select Operator [SEL_22] (rows=28795575 width=77)
+ Select Operator [SEL_22] (rows=57591150 width=77)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_104] (rows=28795575 width=77)
- predicate:((sr_store_sk = sr_store_sk) and sr_returned_date_sk is not null)
+ Filter Operator [FIL_104] (rows=57591150 width=77)
+ predicate:(sr_returned_date_sk is not null and sr_store_sk is not null)
TableScan [TS_20] (rows=57591150 width=77)
default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_customer_sk","sr_store_sk","sr_fee"]
<-Map 15 [SIMPLE_EDGE]
diff --git a/ql/src/test/results/clientpositive/perf/query13.q.out b/ql/src/test/results/clientpositive/perf/query13.q.out
index 941a3a1..d67abe2 100644
--- a/ql/src/test/results/clientpositive/perf/query13.q.out
+++ b/ql/src/test/results/clientpositive/perf/query13.q.out
@@ -109,109 +109,105 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
-Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
-Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE)
-Reducer 6 <- Map 10 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
-Reducer 7 <- Map 11 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
-Reducer 8 <- Map 12 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
+Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+Reducer 5 <- Map 11 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+Reducer 6 <- Map 12 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
+Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
- Reducer 3
- File Output Operator [FS_43]
- Group By Operator [GBY_41] (rows=1 width=764)
+ Reducer 7
+ File Output Operator [FS_40]
+ Group By Operator [GBY_38] (rows=1 width=764)
Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(VALUE._col0)","avg(VALUE._col1)","avg(VALUE._col2)","sum(VALUE._col3)"]
- <-Reducer 2 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_40]
- Group By Operator [GBY_39] (rows=1 width=764)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(_col7)","avg(_col9)","avg(_col10)","sum(_col10)"]
- Merge Join Operator [MERGEJOIN_74] (rows=2016666 width=1014)
- Conds:RS_35._col0=RS_36._col0(Inner),Output:["_col7","_col9","_col10"]
- <-Map 1 [SIMPLE_EDGE]
- SHUFFLE [RS_35]
- PartitionCols:_col0
- Select Operator [SEL_2] (rows=36524 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_64] (rows=36524 width=1119)
- predicate:((d_year = 2001) 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_36]
- PartitionCols:_col0
- Select Operator [SEL_34] (rows=1833333 width=1014)
- Output:["_col0","_col5","_col7","_col8"]
- Filter Operator [FIL_33] (rows=1833333 width=1014)
- predicate:(((_col17) IN ('KY', 'GA', 'NM') and _col9 BETWEEN 100 AND 200) or ((_col17) IN ('MT', 'OR', 'IN') and _col9 BETWEEN 150 AND 300) or ((_col17) IN ('WI', 'MO', 'WV') and _col9 BETWEEN 50 AND 250))
- Merge Join Operator [MERGEJOIN_73] (rows=11000000 width=1014)
- Conds:RS_30._col3=RS_31._col0(Inner),Output:["_col0","_col5","_col7","_col8","_col9","_col17"]
- <-Map 12 [SIMPLE_EDGE]
- SHUFFLE [RS_31]
- PartitionCols:_col0
- Select Operator [SEL_29] (rows=10000000 width=1014)
- Output:["_col0","_col1"]
- Filter Operator [FIL_69] (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_27] (rows=40000000 width=1014)
- default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_country"]
- <-Reducer 7 [SIMPLE_EDGE]
- SHUFFLE [RS_30]
- PartitionCols:_col3
- Select Operator [SEL_26] (rows=3549306 width=88)
- Output:["_col0","_col3","_col5","_col7","_col8","_col9"]
- Filter Operator [FIL_25] (rows=3549306 width=88)
- predicate:(((_col12 = 'M') and (_col13 = '4 yr Degree') and _col6 BETWEEN 100 AND 150 and (_col15 = 3)) or ((_col12 = 'D') and (_col13 = 'Primary') and _col6 BETWEEN 50 AND 100 and (_col15 = 1)) or ((_col12 = 'U') and (_col13 = 'Advanced Degree') and _col6 BETWEEN 150 AND 200 and (_col15 = 1)))
- Select Operator [SEL_24] (rows=85183356 width=88)
- Output:["_col0","_col3","_col5","_col6","_col7","_col8","_col9","_col12","_col13","_col15"]
- Merge Join Operator [MERGEJOIN_72] (rows=85183356 width=88)
- Conds:RS_21._col2=RS_22._col0(Inner),Output:["_col1","_col4","_col6","_col7","_col8","_col9","_col10","_col12","_col14","_col15"]
- <-Map 11 [SIMPLE_EDGE]
+ <-Reducer 6 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_37]
+ Group By Operator [GBY_36] (rows=1 width=764)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(_col6)","avg(_col8)","avg(_col9)","sum(_col9)"]
+ Select Operator [SEL_35] (rows=715776 width=88)
+ Output:["_col6","_col8","_col9"]
+ Filter Operator [FIL_34] (rows=715776 width=88)
+ predicate:(((_col19 = 'M') and (_col20 = '4 yr Degree') and _col7 BETWEEN 100 AND 150 and (_col14 = 3)) or ((_col19 = 'D') and (_col20 = 'Primary') and _col7 BETWEEN 50 AND 100 and (_col14 = 1)) or ((_col19 = 'U') and (_col20 = 'Advanced Degree') and _col7 BETWEEN 150 AND 200 and (_col14 = 1)))
+ Merge Join Operator [MERGEJOIN_71] (rows=17178642 width=88)
+ Conds:RS_31._col2=RS_32._col0(Inner),Output:["_col6","_col7","_col8","_col9","_col14","_col19","_col20"]
+ <-Map 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_32]
+ PartitionCols:_col0
+ Select Operator [SEL_17] (rows=1861800 width=385)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_66] (rows=1861800 width=385)
+ predicate:(((cd_marital_status = 'M') or (cd_marital_status = 'D') or (cd_marital_status = 'U')) and ((cd_education_status = '4 yr Degree') or (cd_education_status = 'Primary') or (cd_education_status = 'Advanced Degree')) and cd_demo_sk is not null)
+ TableScan [TS_15] (rows=1861800 width=385)
+ default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"]
+ <-Reducer 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_31]
+ PartitionCols:_col2
+ Filter Operator [FIL_30] (rows=15616947 width=88)
+ predicate:(((_col16) IN ('KY', 'GA', 'NM') and _col10 BETWEEN 100 AND 200) or ((_col16) IN ('MT', 'OR', 'IN') and _col10 BETWEEN 150 AND 300) or ((_col16) IN ('WI', 'MO', 'WV') and _col10 BETWEEN 50 AND 250))
+ Merge Join Operator [MERGEJOIN_70] (rows=93701693 width=88)
+ Conds:RS_27._col4=RS_28._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10","_col14","_col16"]
+ <-Map 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_28]
+ PartitionCols:_col0
+ Select Operator [SEL_14] (rows=10000000 width=1014)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_65] (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_12] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_country"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_27]
+ PartitionCols:_col4
+ Merge Join Operator [MERGEJOIN_69] (rows=85183356 width=88)
+ Conds:RS_24._col3=RS_25._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8","_col9","_col10","_col14"]
+ <-Map 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_25]
+ PartitionCols:_col0
+ Select Operator [SEL_11] (rows=7200 width=107)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_64] (rows=7200 width=107)
+ predicate:(((hd_dep_count = 3) or (hd_dep_count = 1)) and hd_demo_sk is not null)
+ TableScan [TS_9] (rows=7200 width=107)
+ default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_24]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_68] (rows=77439413 width=88)
+ Conds:RS_21._col1=RS_22._col0(Inner),Output:["_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10"]
+ <-Map 9 [SIMPLE_EDGE]
SHUFFLE [RS_22]
PartitionCols:_col0
- Select Operator [SEL_14] (rows=1861800 width=385)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_68] (rows=1861800 width=385)
- predicate:(((cd_marital_status = 'M') or (cd_marital_status = 'D') or (cd_marital_status = 'U')) and ((cd_education_status = '4 yr Degree') or (cd_education_status = 'Primary') or (cd_education_status = 'Advanced Degree')) and cd_demo_sk is not null)
- TableScan [TS_12] (rows=1861800 width=385)
- default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"]
- <-Reducer 6 [SIMPLE_EDGE]
+ Select Operator [SEL_8] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_63] (rows=36524 width=1119)
+ predicate:((d_year = 2001) 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"]
+ <-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_21]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_71] (rows=77439413 width=88)
- Conds:RS_18._col3=RS_19._col0(Inner),Output:["_col1","_col2","_col4","_col6","_col7","_col8","_col9","_col10","_col12"]
- <-Map 10 [SIMPLE_EDGE]
- SHUFFLE [RS_19]
- PartitionCols:_col0
- Select Operator [SEL_11] (rows=7200 width=107)
- Output:["_col0","_col1"]
- Filter Operator [FIL_67] (rows=7200 width=107)
- predicate:(((hd_dep_count = 3) or (hd_dep_count = 1)) and hd_demo_sk is not null)
- TableScan [TS_9] (rows=7200 width=107)
- default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count"]
- <-Reducer 5 [SIMPLE_EDGE]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_67] (rows=70399465 width=88)
+ Conds:RS_18._col0=RS_19._col4(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10"]
+ <-Map 1 [SIMPLE_EDGE]
SHUFFLE [RS_18]
- PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_70] (rows=70399465 width=88)
- Conds:RS_15._col0=RS_16._col4(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10"]
- <-Map 4 [SIMPLE_EDGE]
- SHUFFLE [RS_15]
- PartitionCols:_col0
- Select Operator [SEL_5] (rows=1704 width=1910)
- Output:["_col0"]
- Filter Operator [FIL_65] (rows=1704 width=1910)
- predicate:s_store_sk is not null
- TableScan [TS_3] (rows=1704 width=1910)
- default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"]
- <-Map 9 [SIMPLE_EDGE]
- SHUFFLE [RS_16]
- PartitionCols:_col4
- Select Operator [SEL_8] (rows=63999513 width=88)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"]
- Filter Operator [FIL_66] (rows=63999513 width=88)
- predicate:((ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_net_profit BETWEEN 100 AND 200 or ss_net_profit BETWEEN 150 AND 300 or ss_net_profit BETWEEN 50 AND 250) and ss_store_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_addr_sk is not null and ss_sold_date_sk is not null)
- TableScan [TS_6] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_ext_sales_price","ss_ext_wholesale_cost","ss_net_profit"]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=1704 width=1910)
+ Output:["_col0"]
+ Filter Operator [FIL_61] (rows=1704 width=1910)
+ predicate:s_store_sk is not null
+ TableScan [TS_0] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"]
+ <-Map 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_19]
+ PartitionCols:_col4
+ Select Operator [SEL_5] (rows=63999513 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"]
+ Filter Operator [FIL_62] (rows=63999513 width=88)
+ predicate:((ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_net_profit BETWEEN 100 AND 200 or ss_net_profit BETWEEN 150 AND 300 or ss_net_profit BETWEEN 50 AND 250) and ss_store_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_addr_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_3] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_ext_sales_price","ss_ext_wholesale_cost","ss_net_profit"]
diff --git a/ql/src/test/results/clientpositive/perf/query14.q.out b/ql/src/test/results/clientpositive/perf/query14.q.out
index 051d837..9284353 100644
--- a/ql/src/test/results/clientpositive/perf/query14.q.out
+++ b/ql/src/test/results/clientpositive/perf/query14.q.out
@@ -1,9 +1,6 @@
-Warning: Shuffle Join MERGEJOIN[914][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 61' is a cross product
-Warning: Shuffle Join MERGEJOIN[915][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 62' is a cross product
-Warning: Shuffle Join MERGEJOIN[916][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 114' is a cross product
-Warning: Shuffle Join MERGEJOIN[917][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 115' is a cross product
-Warning: Shuffle Join MERGEJOIN[912][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product
-Warning: Shuffle Join MERGEJOIN[913][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 6' is a cross product
+Warning: Shuffle Join MERGEJOIN[906][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 5' is a cross product
+Warning: Shuffle Join MERGEJOIN[907][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 60' is a cross product
+Warning: Shuffle Join MERGEJOIN[908][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 112' is a cross product
PREHOOK: query: explain
with cross_items as
(select i_item_sk ss_item_sk
@@ -213,598 +210,680 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 100 <- Map 103 (SIMPLE_EDGE), Reducer 99 (SIMPLE_EDGE)
-Reducer 101 <- Reducer 100 (SIMPLE_EDGE), Union 94 (CONTAINS)
-Reducer 105 <- Map 104 (SIMPLE_EDGE), Map 108 (SIMPLE_EDGE)
-Reducer 106 <- Map 109 (SIMPLE_EDGE), Reducer 105 (SIMPLE_EDGE)
-Reducer 107 <- Reducer 106 (SIMPLE_EDGE), Union 94 (CONTAINS)
-Reducer 111 <- Map 110 (SIMPLE_EDGE), Map 116 (SIMPLE_EDGE), Union 112 (CONTAINS)
-Reducer 113 <- Union 112 (CUSTOM_SIMPLE_EDGE)
-Reducer 114 <- Reducer 113 (CUSTOM_SIMPLE_EDGE), Reducer 126 (CUSTOM_SIMPLE_EDGE)
-Reducer 115 <- Reducer 114 (CUSTOM_SIMPLE_EDGE), Reducer 137 (CUSTOM_SIMPLE_EDGE), Union 7 (CONTAINS)
-Reducer 118 <- Map 117 (SIMPLE_EDGE), Map 119 (SIMPLE_EDGE), Union 112 (CONTAINS)
-Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE), Union 3 (CONTAINS)
-Reducer 121 <- Map 120 (SIMPLE_EDGE), Map 122 (SIMPLE_EDGE), Union 112 (CONTAINS)
-Reducer 124 <- Map 123 (SIMPLE_EDGE), Map 127 (SIMPLE_EDGE), Union 125 (CONTAINS)
-Reducer 126 <- Union 125 (CUSTOM_SIMPLE_EDGE)
-Reducer 129 <- Map 128 (SIMPLE_EDGE), Map 130 (SIMPLE_EDGE), Union 125 (CONTAINS)
-Reducer 132 <- Map 131 (SIMPLE_EDGE), Map 133 (SIMPLE_EDGE), Union 125 (CONTAINS)
-Reducer 135 <- Map 134 (SIMPLE_EDGE), Map 138 (SIMPLE_EDGE)
-Reducer 136 <- Map 139 (SIMPLE_EDGE), Reducer 135 (SIMPLE_EDGE), Reducer 142 (SIMPLE_EDGE)
-Reducer 137 <- Reducer 136 (SIMPLE_EDGE)
-Reducer 141 <- Map 140 (SIMPLE_EDGE), Reducer 148 (SIMPLE_EDGE)
-Reducer 142 <- Reducer 141 (SIMPLE_EDGE)
-Reducer 144 <- Map 143 (SIMPLE_EDGE), Map 149 (SIMPLE_EDGE)
-Reducer 145 <- Map 150 (SIMPLE_EDGE), Reducer 144 (SIMPLE_EDGE)
-Reducer 146 <- Reducer 145 (SIMPLE_EDGE), Union 147 (CONTAINS)
-Reducer 148 <- Union 147 (SIMPLE_EDGE)
-Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE), Union 3 (CONTAINS)
-Reducer 152 <- Map 151 (SIMPLE_EDGE), Map 155 (SIMPLE_EDGE)
-Reducer 153 <- Map 156 (SIMPLE_EDGE), Reducer 152 (SIMPLE_EDGE)
-Reducer 154 <- Reducer 153 (SIMPLE_EDGE), Union 147 (CONTAINS)
-Reducer 158 <- Map 157 (SIMPLE_EDGE), Map 161 (SIMPLE_EDGE)
-Reducer 159 <- Map 162 (SIMPLE_EDGE), Reducer 158 (SIMPLE_EDGE)
-Reducer 160 <- Reducer 159 (SIMPLE_EDGE), Union 147 (CONTAINS)
-Reducer 18 <- Map 17 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE), Union 19 (CONTAINS)
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE), Union 3 (CONTAINS)
-Reducer 20 <- Union 19 (CUSTOM_SIMPLE_EDGE)
-Reducer 23 <- Map 22 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE), Union 19 (CONTAINS)
-Reducer 26 <- Map 25 (SIMPLE_EDGE), Map 27 (SIMPLE_EDGE), Union 19 (CONTAINS)
-Reducer 29 <- Map 28 (SIMPLE_EDGE), Map 32 (SIMPLE_EDGE)
-Reducer 30 <- Map 33 (SIMPLE_EDGE), Reducer 29 (SIMPLE_EDGE), Reducer 36 (SIMPLE_EDGE)
-Reducer 31 <- Reducer 30 (SIMPLE_EDGE)
-Reducer 35 <- Map 34 (SIMPLE_EDGE), Reducer 42 (SIMPLE_EDGE)
-Reducer 36 <- Reducer 35 (SIMPLE_EDGE)
-Reducer 38 <- Map 37 (SIMPLE_EDGE), Map 43 (SIMPLE_EDGE)
-Reducer 39 <- Map 44 (SIMPLE_EDGE), Reducer 38 (SIMPLE_EDGE)
+Reducer 103 <- Map 102 (SIMPLE_EDGE), Map 106 (SIMPLE_EDGE)
+Reducer 104 <- Map 107 (SIMPLE_EDGE), Reducer 103 (SIMPLE_EDGE)
+Reducer 105 <- Reducer 104 (SIMPLE_EDGE), Union 92 (CONTAINS)
+Reducer 109 <- Map 108 (SIMPLE_EDGE), Map 113 (SIMPLE_EDGE), Union 110 (CONTAINS)
+Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE), Union 3 (CONTAINS)
+Reducer 111 <- Union 110 (CUSTOM_SIMPLE_EDGE)
+Reducer 112 <- Reducer 111 (CUSTOM_SIMPLE_EDGE), Reducer 123 (CUSTOM_SIMPLE_EDGE), Reducer 134 (CUSTOM_SIMPLE_EDGE), Union 6 (CONTAINS)
+Reducer 115 <- Map 114 (SIMPLE_EDGE), Map 116 (SIMPLE_EDGE), Union 110 (CONTAINS)
+Reducer 118 <- Map 117 (SIMPLE_EDGE), Map 119 (SIMPLE_EDGE), Union 110 (CONTAINS)
+Reducer 121 <- Map 120 (SIMPLE_EDGE), Map 124 (SIMPLE_EDGE), Union 122 (CONTAINS)
+Reducer 123 <- Union 122 (CUSTOM_SIMPLE_EDGE)
+Reducer 126 <- Map 125 (SIMPLE_EDGE), Map 127 (SIMPLE_EDGE), Union 122 (CONTAINS)
+Reducer 129 <- Map 128 (SIMPLE_EDGE), Map 130 (SIMPLE_EDGE), Union 122 (CONTAINS)
+Reducer 132 <- Map 131 (SIMPLE_EDGE), Map 135 (SIMPLE_EDGE)
+Reducer 133 <- Map 136 (SIMPLE_EDGE), Reducer 132 (SIMPLE_EDGE), Reducer 139 (SIMPLE_EDGE)
+Reducer 134 <- Reducer 133 (SIMPLE_EDGE)
+Reducer 138 <- Map 137 (SIMPLE_EDGE), Reducer 145 (SIMPLE_EDGE)
+Reducer 139 <- Reducer 138 (SIMPLE_EDGE)
+Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE), Union 3 (CONTAINS)
+Reducer 141 <- Map 140 (SIMPLE_EDGE), Map 146 (SIMPLE_EDGE)
+Reducer 142 <- Map 147 (SIMPLE_EDGE), Reducer 141 (SIMPLE_EDGE)
+Reducer 143 <- Reducer 142 (SIMPLE_EDGE), Union 144 (CONTAINS)
+Reducer 145 <- Union 144 (SIMPLE_EDGE)
+Reducer 149 <- Map 148 (SIMPLE_EDGE), Map 152 (SIMPLE_EDGE)
+Reducer 150 <- Map 153 (SIMPLE_EDGE), Reducer 149 (SIMPLE_EDGE)
+Reducer 151 <- Reducer 150 (SIMPLE_EDGE), Union 144 (CONTAINS)
+Reducer 155 <- Map 154 (SIMPLE_EDGE), Map 158 (SIMPLE_EDGE)
+Reducer 156 <- Map 159 (SIMPLE_EDGE), Reducer 155 (SIMPLE_EDGE)
+Reducer 157 <- Reducer 156 (SIMPLE_EDGE), Union 144 (CONTAINS)
+Reducer 17 <- Map 16 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE), Union 18 (CONTAINS)
+Reducer 19 <- Union 18 (CUSTOM_SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE), Union 3 (CONTAINS)
+Reducer 22 <- Map 21 (SIMPLE_EDGE), Map 23 (SIMPLE_EDGE), Union 18 (CONTAINS)
+Reducer 25 <- Map 24 (SIMPLE_EDGE), Map 26 (SIMPLE_EDGE), Union 18 (CONTAINS)
+Reducer 28 <- Map 27 (SIMPLE_EDGE), Map 31 (SIMPLE_EDGE)
+Reducer 29 <- Map 32 (SIMPLE_EDGE), Reducer 28 (SIMPLE_EDGE), Reducer 35 (SIMPLE_EDGE)
+Reducer 30 <- Reducer 29 (SIMPLE_EDGE)
+Reducer 34 <- Map 33 (SIMPLE_EDGE), Reducer 41 (SIMPLE_EDGE)
+Reducer 35 <- Reducer 34 (SIMPLE_EDGE)
+Reducer 37 <- Map 36 (SIMPLE_EDGE), Map 42 (SIMPLE_EDGE)
+Reducer 38 <- Map 43 (SIMPLE_EDGE), Reducer 37 (SIMPLE_EDGE)
+Reducer 39 <- Reducer 38 (SIMPLE_EDGE), Union 40 (CONTAINS)
Reducer 4 <- Union 3 (CUSTOM_SIMPLE_EDGE)
-Reducer 40 <- Reducer 39 (SIMPLE_EDGE), Union 41 (CONTAINS)
-Reducer 42 <- Union 41 (SIMPLE_EDGE)
-Reducer 46 <- Map 45 (SIMPLE_EDGE), Map 49 (SIMPLE_EDGE)
-Reducer 47 <- Map 50 (SIMPLE_EDGE), Reducer 46 (SIMPLE_EDGE)
-Reducer 48 <- Reducer 47 (SIMPLE_EDGE), Union 41 (CONTAINS)
-Reducer 5 <- Reducer 20 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
-Reducer 52 <- Map 51 (SIMPLE_EDGE), Map 55 (SIMPLE_EDGE)
-Reducer 53 <- Map 56 (SIMPLE_EDGE), Reducer 52 (SIMPLE_EDGE)
-Reducer 54 <- Reducer 53 (SIMPLE_EDGE), Union 41 (CONTAINS)
-Reducer 58 <- Map 57 (SIMPLE_EDGE), Map 63 (SIMPLE_EDGE), Union 59 (CONTAINS)
-Reducer 6 <- Reducer 31 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE), Union 7 (CONTAINS)
-Reducer 60 <- Union 59 (CUSTOM_SIMPLE_EDGE)
-Reducer 61 <- Reducer 60 (CUSTOM_SIMPLE_EDGE), Reducer 73 (CUSTOM_SIMPLE_EDGE)
-Reducer 62 <- Reducer 61 (CUSTOM_SIMPLE_EDGE), Reducer 84 (CUSTOM_SIMPLE_EDGE), Union 7 (CONTAINS)
-Reducer 65 <- Map 64 (SIMPLE_EDGE), Map 66 (SIMPLE_EDGE), Union 59 (CONTAINS)
-Reducer 68 <- Map 67 (SIMPLE_EDGE), Map 69 (SIMPLE_EDGE), Union 59 (CONTAINS)
-Reducer 71 <- Map 70 (SIMPLE_EDGE), Map 74 (SIMPLE_EDGE), Union 72 (CONTAINS)
-Reducer 73 <- Union 72 (CUSTOM_SIMPLE_EDGE)
-Reducer 76 <- Map 75 (SIMPLE_EDGE), Map 77 (SIMPLE_EDGE), Union 72 (CONTAINS)
-Reducer 79 <- Map 78 (SIMPLE_EDGE), Map 80 (SIMPLE_EDGE), Union 72 (CONTAINS)
-Reducer 8 <- Union 7 (SIMPLE_EDGE)
-Reducer 82 <- Map 81 (SIMPLE_EDGE), Map 85 (SIMPLE_EDGE)
-Reducer 83 <- Map 86 (SIMPLE_EDGE), Reducer 82 (SIMPLE_EDGE), Reducer 89 (SIMPLE_EDGE)
-Reducer 84 <- Reducer 83 (SIMPLE_EDGE)
-Reducer 88 <- Map 87 (SIMPLE_EDGE), Reducer 95 (SIMPLE_EDGE)
-Reducer 89 <- Reducer 88 (SIMPLE_EDGE)
-Reducer 9 <- Reducer 8 (SIMPLE_EDGE)
-Reducer 91 <- Map 90 (SIMPLE_EDGE), Map 96 (SIMPLE_EDGE)
-Reducer 92 <- Map 97 (SIMPLE_EDGE), Reducer 91 (SIMPLE_EDGE)
-Reducer 93 <- Reducer 92 (SIMPLE_EDGE), Union 94 (CONTAINS)
-Reducer 95 <- Union 94 (SIMPLE_EDGE)
-Reducer 99 <- Map 102 (SIMPLE_EDGE), Map 98 (SIMPLE_EDGE)
+Reducer 41 <- Union 40 (SIMPLE_EDGE)
+Reducer 45 <- Map 44 (SIMPLE_EDGE), Map 48 (SIMPLE_EDGE)
+Reducer 46 <- Map 49 (SIMPLE_EDGE), Reducer 45 (SIMPLE_EDGE)
+Reducer 47 <- Reducer 46 (SIMPLE_EDGE), Union 40 (CONTAINS)
+Reducer 5 <- Reducer 19 (CUSTOM_SIMPLE_EDGE), Reducer 30 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE), Union 6 (CONTAINS)
+Reducer 51 <- Map 50 (SIMPLE_EDGE), Map 54 (SIMPLE_EDGE)
+Reducer 52 <- Map 55 (SIMPLE_EDGE), Reducer 51 (SIMPLE_EDGE)
+Reducer 53 <- Reducer 52 (SIMPLE_EDGE), Union 40 (CONTAINS)
+Reducer 57 <- Map 56 (SIMPLE_EDGE), Map 61 (SIMPLE_EDGE), Union 58 (CONTAINS)
+Reducer 59 <- Union 58 (CUSTOM_SIMPLE_EDGE)
+Reducer 60 <- Reducer 59 (CUSTOM_SIMPLE_EDGE), Reducer 71 (CUSTOM_SIMPLE_EDGE), Reducer 82 (CUSTOM_SIMPLE_EDGE), Union 6 (CONTAINS)
+Reducer 63 <- Map 62 (SIMPLE_EDGE), Map 64 (SIMPLE_EDGE), Union 58 (CONTAINS)
+Reducer 66 <- Map 65 (SIMPLE_EDGE), Map 67 (SIMPLE_EDGE), Union 58 (CONTAINS)
+Reducer 69 <- Map 68 (SIMPLE_EDGE), Map 72 (SIMPLE_EDGE), Union 70 (CONTAINS)
+Reducer 7 <- Union 6 (SIMPLE_EDGE)
+Reducer 71 <- Union 70 (CUSTOM_SIMPLE_EDGE)
+Reducer 74 <- Map 73 (SIMPLE_EDGE), Map 75 (SIMPLE_EDGE), Union 70 (CONTAINS)
+Reducer 77 <- Map 76 (SIMPLE_EDGE), Map 78 (SIMPLE_EDGE), Union 70 (CONTAINS)
+Reducer 8 <- Reducer 7 (SIMPLE_EDGE)
+Reducer 80 <- Map 79 (SIMPLE_EDGE), Map 83 (SIMPLE_EDGE)
+Reducer 81 <- Map 84 (SIMPLE_EDGE), Reducer 80 (SIMPLE_EDGE), Reducer 87 (SIMPLE_EDGE)
+Reducer 82 <- Reducer 81 (SIMPLE_EDGE)
+Reducer 86 <- Map 85 (SIMPLE_EDGE), Reducer 93 (SIMPLE_EDGE)
+Reducer 87 <- Reducer 86 (SIMPLE_EDGE)
+Reducer 89 <- Map 88 (SIMPLE_EDGE), Map 94 (SIMPLE_EDGE)
+Reducer 90 <- Map 95 (SIMPLE_EDGE), Reducer 89 (SIMPLE_EDGE)
+Reducer 91 <- Reducer 90 (SIMPLE_EDGE), Union 92 (CONTAINS)
+Reducer 93 <- Union 92 (SIMPLE_EDGE)
+Reducer 97 <- Map 100 (SIMPLE_EDGE), Map 96 (SIMPLE_EDGE)
+Reducer 98 <- Map 101 (SIMPLE_EDGE), Reducer 97 (SIMPLE_EDGE)
+Reducer 99 <- Reducer 98 (SIMPLE_EDGE), Union 92 (CONTAINS)
Stage-0
Fetch Operator
limit:100
Stage-1
- Reducer 9
- File Output Operator [FS_596]
- Limit [LIM_595] (rows=100 width=406)
+ Reducer 8
+ File Output Operator [FS_590]
+ Limit [LIM_589] (rows=100 width=405)
Number of rows:100
- Select Operator [SEL_594] (rows=1016388080 width=406)
+ Select Operator [SEL_588] (rows=1016388080 width=405)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- <-Reducer 8 [SIMPLE_EDGE]
- SHUFFLE [RS_593]
- Select Operator [SEL_592] (rows=1016388080 width=406)
+ <-Reducer 7 [SIMPLE_EDGE]
+ SHUFFLE [RS_587]
+ Select Operator [SEL_586] (rows=1016388080 width=405)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Group By Operator [GBY_591] (rows=1016388080 width=406)
+ Group By Operator [GBY_585] (rows=1016388080 width=405)
Output:["_col0","_col1","_col2","_col3","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4
- <-Union 7 [SIMPLE_EDGE]
- <-Reducer 115 [CONTAINS]
- Reduce Output Operator [RS_590]
+ <-Union 6 [SIMPLE_EDGE]
+ <-Reducer 112 [CONTAINS]
+ Reduce Output Operator [RS_584]
PartitionCols:_col0, _col1, _col2, _col3, _col4
- Group By Operator [GBY_589] (rows=2032776160 width=406)
+ Group By Operator [GBY_583] (rows=2032776160 width=405)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0
- Select Operator [SEL_586] (rows=58081078 width=433)
+ Select Operator [SEL_580] (rows=58081078 width=432)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Filter Operator [FIL_585] (rows=58081078 width=433)
+ Filter Operator [FIL_579] (rows=58081078 width=432)
predicate:(_col5 > _col1)
- Merge Join Operator [MERGEJOIN_917] (rows=174243235 width=433)
- Conds:(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"]
- <-Reducer 114 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_582]
- Merge Join Operator [MERGEJOIN_916] (rows=1 width=297)
- Conds:(Left Outer),Output:["_col1"]
- <-Reducer 113 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_579]
- Select Operator [SEL_436] (rows=1 width=8)
- Filter Operator [FIL_435] (rows=1 width=8)
- predicate:(sq_count_check(_col0) <= 1)
- Group By Operator [GBY_433] (rows=1 width=8)
- Output:["_col0"],aggregations:["count()"]
- Select Operator [SEL_428] (rows=1 width=8)
- Group By Operator [GBY_427] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(VALUE._col0)"]
- <-Union 112 [CUSTOM_SIMPLE_EDGE]
- <-Reducer 111 [CONTAINS]
- Reduce Output Operator [RS_426]
- Group By Operator [GBY_425] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_424] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_401] (rows=633595212 width=88)
- Output:["_col0"]
- Merge Join Operator [MERGEJOIN_897] (rows=633595212 width=88)
- Conds:RS_398._col0=RS_399._col0(Inner),Output:["_col1"]
- <-Map 110 [SIMPLE_EDGE]
- SHUFFLE [RS_398]
- PartitionCols:_col0
- Select Operator [SEL_394] (rows=575995635 width=88)
- Output:["_col0","_col1"]
- Filter Operator [FIL_842] (rows=575995635 width=88)
- predicate:ss_sold_date_sk is not null
- TableScan [TS_392] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"]
- <-Map 116 [SIMPLE_EDGE]
- SHUFFLE [RS_399]
- PartitionCols:_col0
- Select Operator [SEL_397] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_843] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
- TableScan [TS_395] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 118 [CONTAINS]
- Reduce Output Operator [RS_426]
- Group By Operator [GBY_425] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_424] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_411] (rows=316788826 width=135)
- Output:["_col0"]
- Merge Join Operator [MERGEJOIN_898] (rows=316788826 width=135)
- Conds:RS_408._col0=RS_409._col0(Inner),Output:["_col1"]
- <-Map 117 [SIMPLE_EDGE]
- SHUFFLE [RS_408]
- PartitionCols:_col0
- Select Operator [SEL_404] (rows=287989836 width=135)
- Output:["_col0","_col1"]
- Filter Operator [FIL_844] (rows=287989836 width=135)
- predicate:cs_sold_date_sk is not null
- TableScan [TS_402] (rows=287989836 width=135)
- default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity"]
- <-Map 119 [SIMPLE_EDGE]
- SHUFFLE [RS_409]
- PartitionCols:_col0
- Select Operator [SEL_407] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_845] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
- TableScan [TS_405] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 121 [CONTAINS]
- Reduce Output Operator [RS_426]
- Group By Operator [GBY_425] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_424] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_423] (rows=158402938 width=135)
- Output:["_col0"]
- Merge Join Operator [MERGEJOIN_899] (rows=158402938 width=135)
- Conds:RS_420._col0=RS_421._col0(Inner),Output:["_col1"]
- <-Map 120 [SIMPLE_EDGE]
- SHUFFLE [RS_420]
- PartitionCols:_col0
- Select Operator [SEL_416] (rows=144002668 width=135)
- Output:["_col0","_col1"]
- Filter Operator [FIL_846] (rows=144002668 width=135)
- predicate:ws_sold_date_sk is not null
- TableScan [TS_414] (rows=144002668 width=135)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity"]
- <-Map 122 [SIMPLE_EDGE]
- SHUFFLE [RS_421]
- PartitionCols:_col0
- Select Operator [SEL_419] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_847] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
- TableScan [TS_417] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 126 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_580]
- Group By Operator [GBY_473] (rows=1 width=288)
- Output:["_col0"],aggregations:["avg(VALUE._col0)"]
- <-Union 125 [CUSTOM_SIMPLE_EDGE]
- <-Reducer 124 [CONTAINS]
- Reduce Output Operator [RS_472]
- Group By Operator [GBY_471] (rows=1 width=288)
- Output:["_col0"],aggregations:["avg(_col0)"]
- Select Operator [SEL_469] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_446] (rows=633595212 width=88)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_900] (rows=633595212 width=88)
- Conds:RS_443._col0=RS_444._col0(Inner),Output:["_col1","_col2"]
- <-Map 123 [SIMPLE_EDGE]
- SHUFFLE [RS_443]
- PartitionCols:_col0
- Select Operator [SEL_439] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_848] (rows=575995635 width=88)
- predicate:ss_sold_date_sk is not null
- TableScan [TS_437] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity","ss_list_price"]
- <-Map 127 [SIMPLE_EDGE]
- SHUFFLE [RS_444]
- PartitionCols:_col0
- Select Operator [SEL_442] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_849] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
- TableScan [TS_440] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 129 [CONTAINS]
- Reduce Output Operator [RS_472]
- Group By Operator [GBY_471] (rows=1 width=288)
- Output:["_col0"],aggregations:["avg(_col0)"]
- Select Operator [SEL_469] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_456] (rows=316788826 width=135)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_901] (rows=316788826 width=135)
- Conds:RS_453._col0=RS_454._col0(Inner),Output:["_col1","_col2"]
- <-Map 128 [SIMPLE_EDGE]
- SHUFFLE [RS_453]
- PartitionCols:_col0
- Select Operator [SEL_449] (rows=287989836 width=135)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_850] (rows=287989836 width=135)
- predicate:cs_sold_date_sk is not null
- TableScan [TS_447] (rows=287989836 width=135)
- default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity","cs_list_price"]
- <-Map 130 [SIMPLE_EDGE]
- SHUFFLE [RS_454]
- PartitionCols:_col0
- Select Operator [SEL_452] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_851] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
- TableScan [TS_450] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 132 [CONTAINS]
- Reduce Output Operator [RS_472]
- Group By Operator [GBY_471] (rows=1 width=288)
- Output:["_col0"],aggregations:["avg(_col0)"]
- Select Operator [SEL_469] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_468] (rows=158402938 width=135)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_902] (rows=158402938 width=135)
- Conds:RS_465._col0=RS_466._col0(Inner),Output:["_col1","_col2"]
- <-Map 131 [SIMPLE_EDGE]
- SHUFFLE [RS_465]
- PartitionCols:_col0
- Select Operator [SEL_461] (rows=144002668 width=135)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_852] (rows=144002668 width=135)
- predicate:ws_sold_date_sk is not null
- TableScan [TS_459] (rows=144002668 width=135)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity","ws_list_price"]
- <-Map 133 [SIMPLE_EDGE]
- SHUFFLE [RS_466]
- PartitionCols:_col0
- Select Operator [SEL_464] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_853] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
- TableScan [TS_462] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 137 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_583]
- Group By Operator [GBY_577] (rows=174243235 width=135)
+ Merge Join Operator [MERGEJOIN_908] (rows=174243235 width=432)
+ Conds:(Inner),(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"]
+ <-Reducer 111 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_575]
+ Select Operator [SEL_432] (rows=1 width=8)
+ Filter Operator [FIL_431] (rows=1 width=8)
+ predicate:(sq_count_check(_col0) <= 1)
+ Group By Operator [GBY_429] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count()"]
+ Select Operator [SEL_424] (rows=1 width=8)
+ Group By Operator [GBY_423] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(VALUE._col0)"]
+ <-Union 110 [CUSTOM_SIMPLE_EDGE]
+ <-Reducer 109 [CONTAINS]
+ Reduce Output Operator [RS_422]
+ Group By Operator [GBY_421] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(_col0)"]
+ Select Operator [SEL_420] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_397] (rows=633595212 width=88)
+ Output:["_col0"]
+ Merge Join Operator [MERGEJOIN_891] (rows=633595212 width=88)
+ Conds:RS_394._col0=RS_395._col0(Inner),Output:["_col1"]
+ <-Map 108 [SIMPLE_EDGE]
+ SHUFFLE [RS_394]
+ PartitionCols:_col0
+ Select Operator [SEL_390] (rows=575995635 width=88)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_836] (rows=575995635 width=88)
+ predicate:ss_sold_date_sk is not null
+ TableScan [TS_388] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"]
+ <-Map 113 [SIMPLE_EDGE]
+ SHUFFLE [RS_395]
+ PartitionCols:_col0
+ Select Operator [SEL_393] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_837] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
+ TableScan [TS_391] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 115 [CONTAINS]
+ Reduce Output Operator [RS_422]
+ Group By Operator [GBY_421] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(_col0)"]
+ Select Operator [SEL_420] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_407] (rows=316788826 width=135)
+ Output:["_col0"]
+ Merge Join Operator [MERGEJOIN_892] (rows=316788826 width=135)
+ Conds:RS_404._col0=RS_405._col0(Inner),Output:["_col1"]
+ <-Map 114 [SIMPLE_EDGE]
+ SHUFFLE [RS_404]
+ PartitionCols:_col0
+ Select Operator [SEL_400] (rows=287989836 width=135)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_838] (rows=287989836 width=135)
+ predicate:cs_sold_date_sk is not null
+ TableScan [TS_398] (rows=287989836 width=135)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity"]
+ <-Map 116 [SIMPLE_EDGE]
+ SHUFFLE [RS_405]
+ PartitionCols:_col0
+ Select Operator [SEL_403] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_839] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
+ TableScan [TS_401] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 118 [CONTAINS]
+ Reduce Output Operator [RS_422]
+ Group By Operator [GBY_421] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(_col0)"]
+ Select Operator [SEL_420] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_419] (rows=158402938 width=135)
+ Output:["_col0"]
+ Merge Join Operator [MERGEJOIN_893] (rows=158402938 width=135)
+ Conds:RS_416._col0=RS_417._col0(Inner),Output:["_col1"]
+ <-Map 117 [SIMPLE_EDGE]
+ SHUFFLE [RS_416]
+ PartitionCols:_col0
+ Select Operator [SEL_412] (rows=144002668 width=135)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_840] (rows=144002668 width=135)
+ predicate:ws_sold_date_sk is not null
+ TableScan [TS_410] (rows=144002668 width=135)
+ default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity"]
+ <-Map 119 [SIMPLE_EDGE]
+ SHUFFLE [RS_417]
+ PartitionCols:_col0
+ Select Operator [SEL_415] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_841] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
+ TableScan [TS_413] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 123 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_576]
+ Group By Operator [GBY_469] (rows=1 width=288)
+ Output:["_col0"],aggregations:["avg(VALUE._col0)"]
+ <-Union 122 [CUSTOM_SIMPLE_EDGE]
+ <-Reducer 121 [CONTAINS]
+ Reduce Output Operator [RS_468]
+ Group By Operator [GBY_467] (rows=1 width=288)
+ Output:["_col0"],aggregations:["avg(_col0)"]
+ Select Operator [SEL_465] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_442] (rows=633595212 width=88)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_894] (rows=633595212 width=88)
+ Conds:RS_439._col0=RS_440._col0(Inner),Output:["_col1","_col2"]
+ <-Map 120 [SIMPLE_EDGE]
+ SHUFFLE [RS_439]
+ PartitionCols:_col0
+ Select Operator [SEL_435] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_842] (rows=575995635 width=88)
+ predicate:ss_sold_date_sk is not null
+ TableScan [TS_433] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity","ss_list_price"]
+ <-Map 124 [SIMPLE_EDGE]
+ SHUFFLE [RS_440]
+ PartitionCols:_col0
+ Select Operator [SEL_438] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_843] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
+ TableScan [TS_436] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 126 [CONTAINS]
+ Reduce Output Operator [RS_468]
+ Group By Operator [GBY_467] (rows=1 width=288)
+ Output:["_col0"],aggregations:["avg(_col0)"]
+ Select Operator [SEL_465] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_452] (rows=316788826 width=135)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_895] (rows=316788826 width=135)
+ Conds:RS_449._col0=RS_450._col0(Inner),Output:["_col1","_col2"]
+ <-Map 125 [SIMPLE_EDGE]
+ SHUFFLE [RS_449]
+ PartitionCols:_col0
+ Select Operator [SEL_445] (rows=287989836 width=135)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_844] (rows=287989836 width=135)
+ predicate:cs_sold_date_sk is not null
+ TableScan [TS_443] (rows=287989836 width=135)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity","cs_list_price"]
+ <-Map 127 [SIMPLE_EDGE]
+ SHUFFLE [RS_450]
+ PartitionCols:_col0
+ Select Operator [SEL_448] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_845] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
+ TableScan [TS_446] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 129 [CONTAINS]
+ Reduce Output Operator [RS_468]
+ Group By Operator [GBY_467] (rows=1 width=288)
+ Output:["_col0"],aggregations:["avg(_col0)"]
+ Select Operator [SEL_465] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_464] (rows=158402938 width=135)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_896] (rows=158402938 width=135)
+ Conds:RS_461._col0=RS_462._col0(Inner),Output:["_col1","_col2"]
+ <-Map 128 [SIMPLE_EDGE]
+ SHUFFLE [RS_461]
+ PartitionCols:_col0
+ Select Operator [SEL_457] (rows=144002668 width=135)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_846] (rows=144002668 width=135)
+ predicate:ws_sold_date_sk is not null
+ TableScan [TS_455] (rows=144002668 width=135)
+ default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity","ws_list_price"]
+ <-Map 130 [SIMPLE_EDGE]
+ SHUFFLE [RS_462]
+ PartitionCols:_col0
+ Select Operator [SEL_460] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_847] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
+ TableScan [TS_458] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 134 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_577]
+ Group By Operator [GBY_573] (rows=174243235 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 136 [SIMPLE_EDGE]
- SHUFFLE [RS_576]
+ <-Reducer 133 [SIMPLE_EDGE]
+ SHUFFLE [RS_572]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_575] (rows=348486471 width=135)
+ Group By Operator [GBY_571] (rows=348486471 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","count()"],keys:_col0, _col1, _col2
- Select Operator [SEL_573] (rows=348486471 width=135)
+ Select Operator [SEL_569] (rows=348486471 width=135)
Output:["_col0","_col1","_col2","_col3"]
- Merge Join Operator [MERGEJOIN_911] (rows=348486471 width=135)
- Conds:RS_569._col1=RS_570._col0(Inner),RS_569._col1=RS_571._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"]
- <-Map 139 [SIMPLE_EDGE]
- SHUFFLE [RS_570]
+ Merge Join Operator [MERGEJOIN_905] (rows=348486471 width=135)
+ Conds:RS_565._col1=RS_566._col0(Inner),RS_565._col1=RS_567._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"]
+ <-Map 136 [SIMPLE_EDGE]
+ SHUFFLE [RS_566]
PartitionCols:_col0
- Select Operator [SEL_483] (rows=462000 width=1436)
+ Select Operator [SEL_479] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_856] (rows=462000 width=1436)
+ Filter Operator [FIL_850] (rows=462000 width=1436)
predicate:i_item_sk is not null
- TableScan [TS_481] (rows=462000 width=1436)
+ TableScan [TS_477] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 135 [SIMPLE_EDGE]
- SHUFFLE [RS_569]
+ <-Reducer 132 [SIMPLE_EDGE]
+ SHUFFLE [RS_565]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_903] (rows=158402938 width=135)
- Conds:RS_566._col0=RS_567._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 134 [SIMPLE_EDGE]
- SHUFFLE [RS_566]
+ Merge Join Operator [MERGEJOIN_897] (rows=158402938 width=135)
+ Conds:RS_562._col0=RS_563._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 131 [SIMPLE_EDGE]
+ SHUFFLE [RS_562]
PartitionCols:_col0
- Select Operator [SEL_477] (rows=144002668 width=135)
+ Select Operator [SEL_473] (rows=144002668 width=135)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_854] (rows=144002668 width=135)
+ Filter Operator [FIL_848] (rows=144002668 width=135)
predicate:(ws_item_sk is not null and ws_sold_date_sk is not null)
- TableScan [TS_475] (rows=144002668 width=135)
+ TableScan [TS_471] (rows=144002668 width=135)
default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_quantity","ws_list_price"]
- <-Map 138 [SIMPLE_EDGE]
- SHUFFLE [RS_567]
+ <-Map 135 [SIMPLE_EDGE]
+ SHUFFLE [RS_563]
PartitionCols:_col0
- Select Operator [SEL_480] (rows=18262 width=1119)
+ Select Operator [SEL_476] (rows=18262 width=1119)
Output:["_col0"]
- Filter Operator [FIL_855] (rows=18262 width=1119)
+ Filter Operator [FIL_849] (rows=18262 width=1119)
predicate:((d_year = 2000) and (d_moy = 11) and d_date_sk is not null)
- TableScan [TS_478] (rows=73049 width=1119)
+ TableScan [TS_474] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
- <-Reducer 142 [SIMPLE_EDGE]
- SHUFFLE [RS_571]
+ <-Reducer 139 [SIMPLE_EDGE]
+ SHUFFLE [RS_567]
PartitionCols:_col0
- Group By Operator [GBY_564] (rows=254100 width=1436)
+ Group By Operator [GBY_560] (rows=254100 width=1436)
Output:["_col0"],keys:KEY._col0
- <-Reducer 141 [SIMPLE_EDGE]
- SHUFFLE [RS_563]
+ <-Reducer 138 [SIMPLE_EDGE]
+ SHUFFLE [RS_559]
PartitionCols:_col0
- Group By Operator [GBY_562] (rows=508200 width=1436)
+ Group By Operator [GBY_558] (rows=508200 width=1436)
Output:["_col0"],keys:_col0
- Merge Join Operator [MERGEJOIN_910] (rows=508200 width=1436)
- Conds:RS_558._col1, _col2, _col3=RS_559._col0, _col1, _col2(Inner),Output:["_col0"]
- <-Map 140 [SIMPLE_EDGE]
- SHUFFLE [RS_558]
+ Merge Join Operator [MERGEJOIN_904] (rows=508200 width=1436)
+ Conds:RS_554._col1, _col2, _col3=RS_555._col0, _col1, _col2(Inner),Output:["_col0"]
+ <-Map 137 [SIMPLE_EDGE]
+ SHUFFLE [RS_554]
PartitionCols:_col1, _col2, _col3
- Select Operator [SEL_486] (rows=462000 width=1436)
+ Select Operator [SEL_482] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_857] (rows=462000 width=1436)
+ Filter Operator [FIL_851] (rows=462000 width=1436)
predicate:(i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_item_sk is not null)
- TableScan [TS_484] (rows=462000 width=1436)
+ TableScan [TS_480] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 148 [SIMPLE_EDGE]
- SHUFFLE [RS_559]
+ <-Reducer 145 [SIMPLE_EDGE]
+ SHUFFLE [RS_555]
PartitionCols:_col0, _col1, _col2
- Select Operator [SEL_557] (rows=1 width=108)
+ Select Operator [SEL_553] (rows=1 width=108)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_556] (rows=1 width=108)
+ Filter Operator [FIL_552] (rows=1 width=108)
predicate:(_col3 = 3)
- Group By Operator [GBY_555] (rows=304916424 width=108)
+ Group By Operator [GBY_551] (rows=304916424 width=108)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Union 147 [SIMPLE_EDGE]
- <-Reducer 146 [CONTAINS]
- Reduce Output Operator [RS_554]
+ <-Union 144 [SIMPLE_EDGE]
+ <-Reducer 143 [CONTAINS]
+ Reduce Output Operator [RS_550]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_553] (rows=609832849 width=108)
+ Group By Operator [GBY_549] (rows=609832849 width=108)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2
- Group By Operator [GBY_506] (rows=348477374 width=88)
+ Group By Operator [GBY_502] (rows=348477374 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 145 [SIMPLE_EDGE]
- SHUFFLE [RS_505]
+ <-Reducer 142 [SIMPLE_EDGE]
+ SHUFFLE [RS_501]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_504] (rows=696954748 width=88)
+ Group By Operator [GBY_500] (rows=696954748 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2
- Select Operator [SEL_502] (rows=696954748 width=88)
+ Select Operator [SEL_498] (rows=696954748 width=88)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_905] (rows=696954748 width=88)
- Conds:RS_499._col1=RS_500._col0(Inner),Output:["_col5","_col6","_col7"]
- <-Map 150 [SIMPLE_EDGE]
- SHUFFLE [RS_500]
+ Merge Join Operator [MERGEJOIN_899] (rows=696954748 width=88)
+ Conds:RS_495._col1=RS_496._col0(Inner),Output:["_col5","_col6","_col7"]
+ <-Map 147 [SIMPLE_EDGE]
+ SHUFFLE [RS_496]
PartitionCols:_col0
- Select Operator [SEL_495] (rows=462000 width=1436)
+ Select Operator [SEL_491] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_860] (rows=462000 width=1436)
+ Filter Operator [FIL_854] (rows=462000 width=1436)
predicate:(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)
- TableScan [TS_493] (rows=462000 width=1436)
+ TableScan [TS_489] (rows=462000 width=1436)
default@item,iss,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 144 [SIMPLE_EDGE]
- SHUFFLE [RS_499]
+ <-Reducer 141 [SIMPLE_EDGE]
+ SHUFFLE [RS_495]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_904] (rows=633595212 width=88)
- Conds:RS_496._col0=RS_497._col0(Inner),Output:["_col1"]
- <-Map 143 [SIMPLE_EDGE]
- SHUFFLE [RS_496]
+ Merge Join Operator [MERGEJOIN_898] (rows=633595212 width=88)
+ Conds:RS_492._col0=RS_493._col0(Inner),Output:["_col1"]
+ <-Map 140 [SIMPLE_EDGE]
+ SHUFFLE [RS_492]
PartitionCols:_col0
- Select Operator [SEL_489] (rows=575995635 width=88)
+ Select Operator [SEL_485] (rows=575995635 width=88)
Output:["_col0","_col1"]
- Filter Operator [FIL_858] (rows=575995635 width=88)
+ Filter Operator [FIL_852] (rows=575995635 width=88)
predicate:(ss_item_sk is not null and ss_sold_date_sk is not null)
- TableScan [TS_487] (rows=575995635 width=88)
+ TableScan [TS_483] (rows=575995635 width=88)
default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk"]
- <-Map 149 [SIMPLE_EDGE]
- SHUFFLE [RS_497]
+ <-Map 146 [SIMPLE_EDGE]
+ SHUFFLE [RS_493]
PartitionCols:_col0
- Select Operator [SEL_492] (rows=8116 width=1119)
+ Select Operator [SEL_488] (rows=8116 width=1119)
Output:["_col0"]
- Filter Operator [FIL_859] (rows=8116 width=1119)
+ Filter Operator [FIL_853] (rows=8116 width=1119)
predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
- TableScan [TS_490] (rows=73049 width=1119)
+ TableScan [TS_486] (rows=73049 width=1119)
default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 154 [CONTAINS]
- Reduce Output Operator [RS_554]
+ <-Reducer 151 [CONTAINS]
+ Reduce Output Operator [RS_550]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_553] (rows=609832849 width=108)
+ Group By Operator [GBY_549] (rows=609832849 width=108)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2
- Group By Operator [GBY_527] (rows=174233858 width=135)
+ Group By Operator [GBY_523] (rows=174233858 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 153 [SIMPLE_EDGE]
- SHUFFLE [RS_526]
+ <-Reducer 150 [SIMPLE_EDGE]
+ SHUFFLE [RS_522]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_525] (rows=348467716 width=135)
+ Group By Operator [GBY_521] (rows=348467716 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2
- Select Operator [SEL_523] (rows=348467716 width=135)
+ Select Operator [SEL_519] (rows=348467716 width=135)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_907] (rows=348467716 width=135)
- Conds:RS_520._col1=RS_521._col0(Inner),Output:["_col5","_col6","_col7"]
- <-Map 156 [SIMPLE_EDGE]
- SHUFFLE [RS_521]
+ Merge Join Operator [MERGEJOIN_901] (rows=348467716 width=135)
+ Conds:RS_516._col1=RS_517._col0(Inner),Output:["_col5","_col6","_col7"]
+ <-Map 153 [SIMPLE_EDGE]
+ SHUFFLE [RS_517]
PartitionCols:_col0
- Select Operator [SEL_516] (rows=462000 width=1436)
+ Select Operator [SEL_512] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_863] (rows=462000 width=1436)
+ Filter Operator [FIL_857] (rows=462000 width=1436)
predicate:(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)
- TableScan [TS_514] (rows=462000 width=1436)
+ TableScan [TS_510] (rows=462000 width=1436)
default@item,ics,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 152 [SIMPLE_EDGE]
- SHUFFLE [RS_520]
+ <-Reducer 149 [SIMPLE_EDGE]
+ SHUFFLE [RS_516]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_906] (rows=316788826 width=135)
- Conds:RS_517._col0=RS_518._col0(Inner),Output:["_col1"]
- <-Map 151 [SIMPLE_EDGE]
- SHUFFLE [RS_517]
+ Merge Join Operator [MERGEJOIN_900] (rows=316788826 width=135)
+ Conds:RS_513._col0=RS_514._col0(Inner),Output:["_col1"]
+ <-Map 148 [SIMPLE_EDGE]
+ SHUFFLE [RS_513]
PartitionCols:_col0
- Select Operator [SEL_510] (rows=287989836 width=135)
+ Select Operator [SEL_506] (rows=287989836 width=135)
Output:["_col0","_col1"]
- Filter Operator [FIL_861] (rows=287989836 width=135)
+ Filter Operator [FIL_855] (rows=287989836 width=135)
predicate:(cs_item_sk is not null and cs_sold_date_sk is not null)
- TableScan [TS_508] (rows=287989836 width=135)
+ TableScan [TS_504] (rows=287989836 width=135)
default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk"]
- <-Map 155 [SIMPLE_EDGE]
- SHUFFLE [RS_518]
+ <-Map 152 [SIMPLE_EDGE]
+ SHUFFLE [RS_514]
PartitionCols:_col0
- Select Operator [SEL_513] (rows=8116 width=1119)
+ Select Operator [SEL_509] (rows=8116 width=1119)
Output:["_col0"]
- Filter Operator [FIL_862] (rows=8116 width=1119)
+ Filter Operator [FIL_856] (rows=8116 width=1119)
predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
- TableScan [TS_511] (rows=73049 width=1119)
+ TableScan [TS_507] (rows=73049 width=1119)
default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 160 [CONTAINS]
- Reduce Output Operator [RS_554]
+ <-Reducer 157 [CONTAINS]
+ Reduce Output Operator [RS_550]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_553] (rows=609832849 width=108)
+ Group By Operator [GBY_549] (rows=609832849 width=108)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2
- Group By Operator [GBY_549] (rows=87121617 width=135)
+ Group By Operator [GBY_545] (rows=87121617 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 159 [SIMPLE_EDGE]
- SHUFFLE [RS_548]
+ <-Reducer 156 [SIMPLE_EDGE]
+ SHUFFLE [RS_544]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_547] (rows=174243235 width=135)
+ Group By Operator [GBY_543] (rows=174243235 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2
- Select Operator [SEL_545] (rows=174243235 width=135)
+ Select Operator [SEL_541] (rows=174243235 width=135)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_909] (rows=174243235 width=135)
- Conds:RS_542._col1=RS_543._col0(Inner),Output:["_col5","_col6","_col7"]
- <-Map 162 [SIMPLE_EDGE]
- SHUFFLE [RS_543]
+ Merge Join Operator [MERGEJOIN_903] (rows=174243235 width=135)
+ Conds:RS_538._col1=RS_539._col0(Inner),Output:["_col5","_col6","_col7"]
+ <-Map 159 [SIMPLE_EDGE]
+ SHUFFLE [RS_539]
PartitionCols:_col0
- Select Operator [SEL_538] (rows=462000 width=1436)
+ Select Operator [SEL_534] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_866] (rows=462000 width=1436)
+ Filter Operator [FIL_860] (rows=462000 width=1436)
predicate:(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)
- TableScan [TS_536] (rows=462000 width=1436)
+ TableScan [TS_532] (rows=462000 width=1436)
default@item,iws,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 158 [SIMPLE_EDGE]
- SHUFFLE [RS_542]
+ <-Reducer 155 [SIMPLE_EDGE]
+ SHUFFLE [RS_538]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_908] (rows=158402938 width=135)
- Conds:RS_539._col0=RS_540._col0(Inner),Output:["_col1"]
- <-Map 157 [SIMPLE_EDGE]
- SHUFFLE [RS_539]
+ Merge Join Operator [MERGEJOIN_902] (rows=158402938 width=135)
+ Conds:RS_535._col0=RS_536._col0(Inner),Output:["_col1"]
+ <-Map 154 [SIMPLE_EDGE]
+ SHUFFLE [RS_535]
PartitionCols:_col0
- Select Operator [SEL_532] (rows=144002668 width=135)
+ Select Operator [SEL_528] (rows=144002668 width=135)
Output:["_col0","_col1"]
- Filter Operator [FIL_864] (rows=144002668 width=135)
+ Filter Operator [FIL_858] (rows=144002668 width=135)
predicate:(ws_item_sk is not null and ws_sold_date_sk is not null)
- TableScan [TS_530] (rows=144002668 width=135)
+ TableScan [TS_526] (rows=144002668 width=135)
default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk"]
- <-Map 161 [SIMPLE_EDGE]
- SHUFFLE [RS_540]
+ <-Map 158 [SIMPLE_EDGE]
+ SHUFFLE [RS_536]
PartitionCols:_col0
- Select Operator [SEL_535] (rows=8116 width=1119)
+ Select Operator [SEL_531] (rows=8116 width=1119)
Output:["_col0"]
- Filter Operator [FIL_865] (rows=8116 width=1119)
+ Filter Operator [FIL_859] (rows=8116 width=1119)
predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
- TableScan [TS_533] (rows=73049 width=1119)
+ TableScan [TS_529] (rows=73049 width=1119)
default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 6 [CONTAINS]
- Reduce Output Operator [RS_590]
+ <-Reducer 5 [CONTAINS]
+ Reduce Output Operator [RS_584]
PartitionCols:_col0, _col1, _col2, _col3, _col4
- Group By Operator [GBY_589] (rows=2032776160 width=406)
+ Group By Operator [GBY_583] (rows=2032776160 width=405)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0
- Select Operator [SEL_194] (rows=232318249 width=386)
+ Select Operator [SEL_192] (rows=232318249 width=385)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Filter Operator [FIL_193] (rows=232318249 width=386)
+ Filter Operator [FIL_191] (rows=232318249 width=385)
predicate:(_col5 > _col1)
- Merge Join Operator [MERGEJOIN_913] (rows=696954748 width=386)
- Conds:(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"]
- <-Reducer 31 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_191]
+ Merge Join Operator [MERGEJOIN_906] (rows=696954748 width=385)
+ Conds:(Inner),(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"]
+ <-Reducer 19 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_188]
+ Group By Operator [GBY_81] (rows=1 width=288)
+ Output:["_col0"],aggregations:["avg(VALUE._col0)"]
+ <-Union 18 [CUSTOM_SIMPLE_EDGE]
+ <-Reducer 17 [CONTAINS]
+ Reduce Output Operator [RS_80]
+ Group By Operator [GBY_79] (rows=1 width=288)
+ Output:["_col0"],aggregations:["avg(_col0)"]
+ Select Operator [SEL_77] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_54] (rows=633595212 width=88)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_864] (rows=633595212 width=88)
+ Conds:RS_51._col0=RS_52._col0(Inner),Output:["_col1","_col2"]
+ <-Map 16 [SIMPLE_EDGE]
+ SHUFFLE [RS_51]
+ PartitionCols:_col0
+ Select Operator [SEL_47] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_792] (rows=575995635 width=88)
+ predicate:ss_sold_date_sk is not null
+ TableScan [TS_45] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity","ss_list_price"]
+ <-Map 20 [SIMPLE_EDGE]
+ SHUFFLE [RS_52]
+ PartitionCols:_col0
+ Select Operator [SEL_50] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_793] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
+ TableScan [TS_48] (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_80]
+ Group By Operator [GBY_79] (rows=1 width=288)
+ Output:["_col0"],aggregations:["avg(_col0)"]
+ Select Operator [SEL_77] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_64] (rows=316788826 width=135)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_865] (rows=316788826 width=135)
+ Conds:RS_61._col0=RS_62._col0(Inner),Output:["_col1","_col2"]
+ <-Map 21 [SIMPLE_EDGE]
+ SHUFFLE [RS_61]
+ PartitionCols:_col0
+ Select Operator [SEL_57] (rows=287989836 width=135)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_794] (rows=287989836 width=135)
+ predicate:cs_sold_date_sk is not null
+ TableScan [TS_55] (rows=287989836 width=135)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity","cs_list_price"]
+ <-Map 23 [SIMPLE_EDGE]
+ SHUFFLE [RS_62]
+ PartitionCols:_col0
+ Select Operator [SEL_60] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_795] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
+ TableScan [TS_58] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 25 [CONTAINS]
+ Reduce Output Operator [RS_80]
+ Group By Operator [GBY_79] (rows=1 width=288)
+ Output:["_col0"],aggregations:["avg(_col0)"]
+ Select Operator [SEL_77] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_76] (rows=158402938 width=135)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_866] (rows=158402938 width=135)
+ Conds:RS_73._col0=RS_74._col0(Inner),Output:["_col1","_col2"]
+ <-Map 24 [SIMPLE_EDGE]
+ SHUFFLE [RS_73]
+ PartitionCols:_col0
+ Select Operator [SEL_69] (rows=144002668 width=135)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_796] (rows=144002668 width=135)
+ predicate:ws_sold_date_sk is not null
+ TableScan [TS_67] (rows=144002668 width=135)
+ default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity","ws_list_price"]
+ <-Map 26 [SIMPLE_EDGE]
+ SHUFFLE [RS_74]
+ PartitionCols:_col0
+ Select Operator [SEL_72] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_797] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
+ TableScan [TS_70] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 30 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_189]
Group By Operator [GBY_185] (rows=696954748 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 30 [SIMPLE_EDGE]
+ <-Reducer 29 [SIMPLE_EDGE]
SHUFFLE [RS_184]
PartitionCols:_col0, _col1, _col2
Group By Operator [GBY_183] (rows=1393909496 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","count()"],keys:_col0, _col1, _col2
Select Operator [SEL_181] (rows=1393909496 width=88)
Output:["_col0","_col1","_col2","_col3"]
- Merge Join Operator [MERGEJOIN_881] (rows=1393909496 width=88)
+ Merge Join Operator [MERGEJOIN_875] (rows=1393909496 width=88)
Conds:RS_177._col1=RS_178._col0(Inner),RS_177._col1=RS_179._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"]
- <-Map 33 [SIMPLE_EDGE]
+ <-Map 32 [SIMPLE_EDGE]
SHUFFLE [RS_178]
PartitionCols:_col0
Select Operator [SEL_91] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_806] (rows=462000 width=1436)
+ Filter Operator [FIL_800] (rows=462000 width=1436)
predicate:i_item_sk is not null
TableScan [TS_89] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 29 [SIMPLE_EDGE]
+ <-Reducer 28 [SIMPLE_EDGE]
SHUFFLE [RS_177]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_873] (rows=633595212 width=88)
+ Merge Join Operator [MERGEJOIN_867] (rows=633595212 width=88)
Conds:RS_174._col0=RS_175._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 28 [SIMPLE_EDGE]
+ <-Map 27 [SIMPLE_EDGE]
SHUFFLE [RS_174]
PartitionCols:_col0
Select Operator [SEL_85] (rows=575995635 width=88)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_804] (rows=575995635 width=88)
+ Filter Operator [FIL_798] (rows=575995635 width=88)
predicate:(ss_item_sk is not null and ss_sold_date_sk is not null)
TableScan [TS_83] (rows=575995635 width=88)
default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_quantity","ss_list_price"]
- <-Map 32 [SIMPLE_EDGE]
+ <-Map 31 [SIMPLE_EDGE]
SHUFFLE [RS_175]
PartitionCols:_col0
Select Operator [SEL_88] (rows=18262 width=1119)
Output:["_col0"]
- Filter Operator [FIL_805] (rows=18262 width=1119)
+ Filter Operator [FIL_799] (rows=18262 width=1119)
predicate:((d_year = 2000) and (d_moy = 11) and d_date_sk is not null)
TableScan [TS_86] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
- <-Reducer 36 [SIMPLE_EDGE]
+ <-Reducer 35 [SIMPLE_EDGE]
SHUFFLE [RS_179]
PartitionCols:_col0
Group By Operator [GBY_172] (rows=254100 width=1436)
Output:["_col0"],keys:KEY._col0
- <-Reducer 35 [SIMPLE_EDGE]
+ <-Reducer 34 [SIMPLE_EDGE]
SHUFFLE [RS_171]
PartitionCols:_col0
Group By Operator [GBY_170] (rows=508200 width=1436)
Output:["_col0"],keys:_col0
- Merge Join Operator [MERGEJOIN_880] (rows=508200 width=1436)
+ Merge Join Operator [MERGEJOIN_874] (rows=508200 width=1436)
Conds:RS_166._col1, _col2, _col3=RS_167._col0, _col1, _col2(Inner),Output:["_col0"]
- <-Map 34 [SIMPLE_EDGE]
+ <-Map 33 [SIMPLE_EDGE]
SHUFFLE [RS_166]
PartitionCols:_col1, _col2, _col3
Select Operator [SEL_94] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_807] (rows=462000 width=1436)
+ Filter Operator [FIL_801] (rows=462000 width=1436)
predicate:(i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_item_sk is not null)
TableScan [TS_92] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 42 [SIMPLE_EDGE]
+ <-Reducer 41 [SIMPLE_EDGE]
SHUFFLE [RS_167]
PartitionCols:_col0, _col1, _col2
Select Operator [SEL_165] (rows=1 width=108)
@@ -813,756 +892,659 @@ Stage-0
predicate:(_col3 = 3)
Group By Operator [GBY_163] (rows=304916424 width=108)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Union 41 [SIMPLE_EDGE]
- <-Reducer 40 [CONTAINS]
+ <-Union 40 [SIMPLE_EDGE]
+ <-Reducer 39 [CONTAINS]
Reduce Output Operator [RS_162]
PartitionCols:_col0, _col1, _col2
Group By Operator [GBY_161] (rows=609832849 width=108)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2
Group By Operator [GBY_114] (rows=348477374 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 39 [SIMPLE_EDGE]
+ <-Reducer 38 [SIMPLE_EDGE]
SHUFFLE [RS_113]
PartitionCols:_col0, _col1, _col2
Group By Operator [GBY_112] (rows=696954748 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2
Select Operator [SEL_110] (rows=696954748 width=88)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_875] (rows=696954748 width=88)
+ Merge Join Operator [MERGEJOIN_869] (rows=696954748 width=88)
Conds:RS_107._col1=RS_108._col0(Inner),Output:["_col5","_col6","_col7"]
- <-Map 44 [SIMPLE_EDGE]
+ <-Map 43 [SIMPLE_EDGE]
SHUFFLE [RS_108]
PartitionCols:_col0
Select Operator [SEL_103] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_810] (rows=462000 width=1436)
+ Filter Operator [FIL_804] (rows=462000 width=1436)
predicate:(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)
TableScan [TS_101] (rows=462000 width=1436)
default@item,iss,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 38 [SIMPLE_EDGE]
+ <-Reducer 37 [SIMPLE_EDGE]
SHUFFLE [RS_107]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_874] (rows=633595212 width=88)
+ Merge Join Operator [MERGEJOIN_868] (rows=633595212 width=88)
Conds:RS_104._col0=RS_105._col0(Inner),Output:["_col1"]
- <-Map 37 [SIMPLE_EDGE]
+ <-Map 36 [SIMPLE_EDGE]
SHUFFLE [RS_104]
PartitionCols:_col0
Select Operator [SEL_97] (rows=575995635 width=88)
Output:["_col0","_col1"]
- Filter Operator [FIL_808] (rows=575995635 width=88)
+ Filter Operator [FIL_802] (rows=575995635 width=88)
predicate:(ss_item_sk is not null and ss_sold_date_sk is not null)
TableScan [TS_95] (rows=575995635 width=88)
default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk"]
- <-Map 43 [SIMPLE_EDGE]
+ <-Map 42 [SIMPLE_EDGE]
SHUFFLE [RS_105]
PartitionCols:_col0
Select Operator [SEL_100] (rows=8116 width=1119)
Output:["_col0"]
- Filter Operator [FIL_809] (rows=8116 width=1119)
+ Filter Operator [FIL_803] (rows=8116 width=1119)
predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
TableScan [TS_98] (rows=73049 width=1119)
default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 48 [CONTAINS]
+ <-Reducer 47 [CONTAINS]
Reduce Output Operator [RS_162]
PartitionCols:_col0, _col1, _col2
Group By Operator [GBY_161] (rows=609832849 width=108)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2
Group By Operator [GBY_135] (rows=174233858 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 47 [SIMPLE_EDGE]
+ <-Reducer 46 [SIMPLE_EDGE]
SHUFFLE [RS_134]
PartitionCols:_col0, _col1, _col2
Group By Operator [GBY_133] (rows=348467716 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2
Select Operator [SEL_131] (rows=348467716 width=135)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_877] (rows=348467716 width=135)
+ Merge Join Operator [MERGEJOIN_871] (rows=348467716 width=135)
Conds:RS_128._col1=RS_129._col0(Inner),Output:["_col5","_col6","_col7"]
- <-Map 50 [SIMPLE_EDGE]
+ <-Map 49 [SIMPLE_EDGE]
SHUFFLE [RS_129]
PartitionCols:_col0
Select Operator [SEL_124] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_813] (rows=462000 width=1436)
+ Filter Operator [FIL_807] (rows=462000 width=1436)
predicate:(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)
TableScan [TS_122] (rows=462000 width=1436)
default@item,ics,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 46 [SIMPLE_EDGE]
+ <-Reducer 45 [SIMPLE_EDGE]
SHUFFLE [RS_128]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_876] (rows=316788826 width=135)
+ Merge Join Operator [MERGEJOIN_870] (rows=316788826 width=135)
Conds:RS_125._col0=RS_126._col0(Inner),Output:["_col1"]
- <-Map 45 [SIMPLE_EDGE]
+ <-Map 44 [SIMPLE_EDGE]
SHUFFLE [RS_125]
PartitionCols:_col0
Select Operator [SEL_118] (rows=287989836 width=135)
Output:["_col0","_col1"]
- Filter Operator [FIL_811] (rows=287989836 width=135)
+ Filter Operator [FIL_805] (rows=287989836 width=135)
predicate:(cs_item_sk is not null and cs_sold_date_sk is not null)
TableScan [TS_116] (rows=287989836 width=135)
default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk"]
- <-Map 49 [SIMPLE_EDGE]
+ <-Map 48 [SIMPLE_EDGE]
SHUFFLE [RS_126]
PartitionCols:_col0
Select Operator [SEL_121] (rows=8116 width=1119)
Output:["_col0"]
- Filter Operator [FIL_812] (rows=8116 width=1119)
+ Filter Operator [FIL_806] (rows=8116 width=1119)
predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
TableScan [TS_119] (rows=73049 width=1119)
default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 54 [CONTAINS]
+ <-Reducer 53 [CONTAINS]
Reduce Output Operator [RS_162]
PartitionCols:_col0, _col1, _col2
Group By Operator [GBY_161] (rows=609832849 width=108)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2
Group By Operator [GBY_157] (rows=87121617 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 53 [SIMPLE_EDGE]
+ <-Reducer 52 [SIMPLE_EDGE]
SHUFFLE [RS_156]
PartitionCols:_col0, _col1, _col2
Group By Operator [GBY_155] (rows=174243235 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2
Select Operator [SEL_153] (rows=174243235 width=135)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_879] (rows=174243235 width=135)
+ Merge Join Operator [MERGEJOIN_873] (rows=174243235 width=135)
Conds:RS_150._col1=RS_151._col0(Inner),Output:["_col5","_col6","_col7"]
- <-Map 56 [SIMPLE_EDGE]
+ <-Map 55 [SIMPLE_EDGE]
SHUFFLE [RS_151]
PartitionCols:_col0
Select Operator [SEL_146] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_816] (rows=462000 width=1436)
+ Filter Operator [FIL_810] (rows=462000 width=1436)
predicate:(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)
TableScan [TS_144] (rows=462000 width=1436)
default@item,iws,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 52 [SIMPLE_EDGE]
+ <-Reducer 51 [SIMPLE_EDGE]
SHUFFLE [RS_150]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_878] (rows=158402938 width=135)
+ Merge Join Operator [MERGEJOIN_872] (rows=158402938 width=135)
Conds:RS_147._col0=RS_148._col0(Inner),Output:["_col1"]
- <-Map 51 [SIMPLE_EDGE]
+ <-Map 50 [SIMPLE_EDGE]
SHUFFLE [RS_147]
PartitionCols:_col0
Select Operator [SEL_140] (rows=144002668 width=135)
Output:["_col0","_col1"]
- Filter Operator [FIL_814] (rows=144002668 width=135)
+ Filter Operator [FIL_808] (rows=144002668 width=135)
predicate:(ws_item_sk is not null and ws_sold_date_sk is not null)
TableScan [TS_138] (rows=144002668 width=135)
default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk"]
- <-Map 55 [SIMPLE_EDGE]
+ <-Map 54 [SIMPLE_EDGE]
SHUFFLE [RS_148]
PartitionCols:_col0
Select Operator [SEL_143] (rows=8116 width=1119)
Output:["_col0"]
- Filter Operator [FIL_815] (rows=8116 width=1119)
+ Filter Operator [FIL_809] (rows=8116 width=1119)
predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
TableScan [TS_141] (rows=73049 width=1119)
default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 5 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_190]
- Merge Join Operator [MERGEJOIN_912] (rows=1 width=297)
- Conds:(Left Outer),Output:["_col1"]
- <-Reducer 20 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_188]
- Group By Operator [GBY_81] (rows=1 width=288)
- Output:["_col0"],aggregations:["avg(VALUE._col0)"]
- <-Union 19 [CUSTOM_SIMPLE_EDGE]
- <-Reducer 18 [CONTAINS]
- Reduce Output Operator [RS_80]
- Group By Operator [GBY_79] (rows=1 width=288)
- Output:["_col0"],aggregations:["avg(_col0)"]
- Select Operator [SEL_77] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_54] (rows=633595212 width=88)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_870] (rows=633595212 width=88)
- Conds:RS_51._col0=RS_52._col0(Inner),Output:["_col1","_col2"]
- <-Map 17 [SIMPLE_EDGE]
- SHUFFLE [RS_51]
- PartitionCols:_col0
- Select Operator [SEL_47] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_798] (rows=575995635 width=88)
- predicate:ss_sold_date_sk is not null
- TableScan [TS_45] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity","ss_list_price"]
- <-Map 21 [SIMPLE_EDGE]
- SHUFFLE [RS_52]
- PartitionCols:_col0
- Select Operator [SEL_50] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_799] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
- TableScan [TS_48] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 23 [CONTAINS]
- Reduce Output Operator [RS_80]
- Group By Operator [GBY_79] (rows=1 width=288)
- Output:["_col0"],aggregations:["avg(_col0)"]
- Select Operator [SEL_77] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_64] (rows=316788826 width=135)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_871] (rows=316788826 width=135)
- Conds:RS_61._col0=RS_62._col0(Inner),Output:["_col1","_col2"]
- <-Map 22 [SIMPLE_EDGE]
- SHUFFLE [RS_61]
- PartitionCols:_col0
- Select Operator [SEL_57] (rows=287989836 width=135)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_800] (rows=287989836 width=135)
- predicate:cs_sold_date_sk is not null
- TableScan [TS_55] (rows=287989836 width=135)
- default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity","cs_list_price"]
- <-Map 24 [SIMPLE_EDGE]
- SHUFFLE [RS_62]
- PartitionCols:_col0
- Select Operator [SEL_60] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_801] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
- TableScan [TS_58] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 26 [CONTAINS]
- Reduce Output Operator [RS_80]
- Group By Operator [GBY_79] (rows=1 width=288)
- Output:["_col0"],aggregations:["avg(_col0)"]
- Select Operator [SEL_77] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_76] (rows=158402938 width=135)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_872] (rows=158402938 width=135)
- Conds:RS_73._col0=RS_74._col0(Inner),Output:["_col1","_col2"]
- <-Map 25 [SIMPLE_EDGE]
- SHUFFLE [RS_73]
- PartitionCols:_col0
- Select Operator [SEL_69] (rows=144002668 width=135)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_802] (rows=144002668 width=135)
- predicate:ws_sold_date_sk is not null
- TableScan [TS_67] (rows=144002668 width=135)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity","ws_list_price"]
- <-Map 27 [SIMPLE_EDGE]
- SHUFFLE [RS_74]
- PartitionCols:_col0
- Select Operator [SEL_72] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_803] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
- TableScan [TS_70] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 4 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_187]
- Select Operator [SEL_44] (rows=1 width=8)
- Filter Operator [FIL_43] (rows=1 width=8)
- predicate:(sq_count_check(_col0) <= 1)
- Group By Operator [GBY_41] (rows=1 width=8)
- Output:["_col0"],aggregations:["count()"]
- Select Operator [SEL_36] (rows=1 width=8)
- Group By Operator [GBY_35] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(VALUE._col0)"]
- <-Union 3 [CUSTOM_SIMPLE_EDGE]
- <-Reducer 12 [CONTAINS]
- Reduce Output Operator [RS_34]
- Group By Operator [GBY_33] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_32] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_19] (rows=316788826 width=135)
- Output:["_col0"]
- Merge Join Operator [MERGEJOIN_868] (rows=316788826 width=135)
- Conds:RS_16._col0=RS_17._col0(Inner),Output:["_col1"]
- <-Map 11 [SIMPLE_EDGE]
- SHUFFLE [RS_16]
- PartitionCols:_col0
- Select Operator [SEL_12] (rows=287989836 width=135)
- Output:["_col0","_col1"]
- Filter Operator [FIL_794] (rows=287989836 width=135)
- predicate:cs_sold_date_sk is not null
- TableScan [TS_10] (rows=287989836 width=135)
- default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity"]
- <-Map 13 [SIMPLE_EDGE]
- SHUFFLE [RS_17]
- PartitionCols:_col0
- Select Operator [SEL_15] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_795] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
- TableScan [TS_13] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 15 [CONTAINS]
- Reduce Output Operator [RS_34]
- Group By Operator [GBY_33] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_32] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_31] (rows=158402938 width=135)
- Output:["_col0"]
- Merge Join Operator [MERGEJOIN_869] (rows=158402938 width=135)
- Conds:RS_28._col0=RS_29._col0(Inner),Output:["_col1"]
- <-Map 14 [SIMPLE_EDGE]
- SHUFFLE [RS_28]
- PartitionCols:_col0
- Select Operator [SEL_24] (rows=144002668 width=135)
- Output:["_col0","_col1"]
- Filter Operator [FIL_796] (rows=144002668 width=135)
- predicate:ws_sold_date_sk is not null
- TableScan [TS_22] (rows=144002668 width=135)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity"]
- <-Map 16 [SIMPLE_EDGE]
- SHUFFLE [RS_29]
- PartitionCols:_col0
- Select Operator [SEL_27] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_797] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1998 AND 2000 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 2 [CONTAINS]
- Reduce Output Operator [RS_34]
- Group By Operator [GBY_33] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_32] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_9] (rows=633595212 width=88)
- Output:["_col0"]
- Merge Join Operator [MERGEJOIN_867] (rows=633595212 width=88)
- Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col1"]
- <-Map 1 [SIMPLE_EDGE]
- SHUFFLE [RS_6]
- PartitionCols:_col0
- Select Operator [SEL_2] (rows=575995635 width=88)
- Output:["_col0","_col1"]
- Filter Operator [FIL_792] (rows=575995635 width=88)
- predicate:ss_sold_date_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_quantity"]
- <-Map 10 [SIMPLE_EDGE]
- SHUFFLE [RS_7]
- PartitionCols:_col0
- Select Operator [SEL_5] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_793] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1999 AND 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"]
- <-Reducer 62 [CONTAINS]
- Reduce Output Operator [RS_590]
+ <-Reducer 4 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_187]
+ Select Operator [SEL_44] (rows=1 width=8)
+ Filter Operator [FIL_43] (rows=1 width=8)
+ predicate:(sq_count_check(_col0) <= 1)
+ Group By Operator [GBY_41] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count()"]
+ Select Operator [SEL_36] (rows=1 width=8)
+ Group By Operator [GBY_35] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(VALUE._col0)"]
+ <-Union 3 [CUSTOM_SIMPLE_EDGE]
+ <-Reducer 11 [CONTAINS]
+ Reduce Output Operator [RS_34]
+ Group By Operator [GBY_33] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(_col0)"]
+ Select Operator [SEL_32] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_19] (rows=316788826 width=135)
+ Output:["_col0"]
+ Merge Join Operator [MERGEJOIN_862] (rows=316788826 width=135)
+ Conds:RS_16._col0=RS_17._col0(Inner),Output:["_col1"]
+ <-Map 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_16]
+ PartitionCols:_col0
+ Select Operator [SEL_12] (rows=287989836 width=135)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_788] (rows=287989836 width=135)
+ predicate:cs_sold_date_sk is not null
+ TableScan [TS_10] (rows=287989836 width=135)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity"]
+ <-Map 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_17]
+ PartitionCols:_col0
+ Select Operator [SEL_15] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_789] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
+ TableScan [TS_13] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 14 [CONTAINS]
+ Reduce Output Operator [RS_34]
+ Group By Operator [GBY_33] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(_col0)"]
+ Select Operator [SEL_32] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_31] (rows=158402938 width=135)
+ Output:["_col0"]
+ Merge Join Operator [MERGEJOIN_863] (rows=158402938 width=135)
+ Conds:RS_28._col0=RS_29._col0(Inner),Output:["_col1"]
+ <-Map 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_28]
+ PartitionCols:_col0
+ Select Operator [SEL_24] (rows=144002668 width=135)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_790] (rows=144002668 width=135)
+ predicate:ws_sold_date_sk is not null
+ TableScan [TS_22] (rows=144002668 width=135)
+ default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity"]
+ <-Map 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_29]
+ PartitionCols:_col0
+ Select Operator [SEL_27] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_791] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1998 AND 2000 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 2 [CONTAINS]
+ Reduce Output Operator [RS_34]
+ Group By Operator [GBY_33] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(_col0)"]
+ Select Operator [SEL_32] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_9] (rows=633595212 width=88)
+ Output:["_col0"]
+ Merge Join Operator [MERGEJOIN_861] (rows=633595212 width=88)
+ Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col1"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_6]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=575995635 width=88)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_786] (rows=575995635 width=88)
+ predicate:ss_sold_date_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_quantity"]
+ <-Map 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_7]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_787] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1999 AND 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"]
+ <-Reducer 60 [CONTAINS]
+ Reduce Output Operator [RS_584]
PartitionCols:_col0, _col1, _col2, _col3, _col4
- Group By Operator [GBY_589] (rows=2032776160 width=406)
+ Group By Operator [GBY_583] (rows=2032776160 width=405)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0
- Select Operator [SEL_389] (rows=116155905 width=433)
+ Select Operator [SEL_385] (rows=116155905 width=432)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Filter Operator [FIL_388] (rows=116155905 width=433)
+ Filter Operator [FIL_384] (rows=116155905 width=432)
predicate:(_col5 > _col1)
- Merge Join Operator [MERGEJOIN_915] (rows=348467716 width=433)
- Conds:(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"]
- <-Reducer 61 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_385]
- Merge Join Operator [MERGEJOIN_914] (rows=1 width=297)
- Conds:(Left Outer),Output:["_col1"]
- <-Reducer 60 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_382]
- Select Operator [SEL_239] (rows=1 width=8)
- Filter Operator [FIL_238] (rows=1 width=8)
- predicate:(sq_count_check(_col0) <= 1)
- Group By Operator [GBY_236] (rows=1 width=8)
- Output:["_col0"],aggregations:["count()"]
- Select Operator [SEL_231] (rows=1 width=8)
- Group By Operator [GBY_230] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(VALUE._col0)"]
- <-Union 59 [CUSTOM_SIMPLE_EDGE]
- <-Reducer 58 [CONTAINS]
- Reduce Output Operator [RS_229]
- Group By Operator [GBY_228] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_227] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_204] (rows=633595212 width=88)
- Output:["_col0"]
- Merge Join Operator [MERGEJOIN_882] (rows=633595212 width=88)
- Conds:RS_201._col0=RS_202._col0(Inner),Output:["_col1"]
- <-Map 57 [SIMPLE_EDGE]
- SHUFFLE [RS_201]
- PartitionCols:_col0
- Select Operator [SEL_197] (rows=575995635 width=88)
- Output:["_col0","_col1"]
- Filter Operator [FIL_817] (rows=575995635 width=88)
- predicate:ss_sold_date_sk is not null
- TableScan [TS_195] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"]
- <-Map 63 [SIMPLE_EDGE]
- SHUFFLE [RS_202]
- PartitionCols:_col0
- Select Operator [SEL_200] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_818] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
- TableScan [TS_198] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 65 [CONTAINS]
- Reduce Output Operator [RS_229]
- Group By Operator [GBY_228] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_227] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_214] (rows=316788826 width=135)
- Output:["_col0"]
- Merge Join Operator [MERGEJOIN_883] (rows=316788826 width=135)
- Conds:RS_211._col0=RS_212._col0(Inner),Output:["_col1"]
- <-Map 64 [SIMPLE_EDGE]
- SHUFFLE [RS_211]
- PartitionCols:_col0
- Select Operator [SEL_207] (rows=287989836 width=135)
- Output:["_col0","_col1"]
- Filter Operator [FIL_819] (rows=287989836 width=135)
- predicate:cs_sold_date_sk is not null
- TableScan [TS_205] (rows=287989836 width=135)
- default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity"]
- <-Map 66 [SIMPLE_EDGE]
- SHUFFLE [RS_212]
- PartitionCols:_col0
- Select Operator [SEL_210] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_820] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
- TableScan [TS_208] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 68 [CONTAINS]
- Reduce Output Operator [RS_229]
- Group By Operator [GBY_228] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_227] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_226] (rows=158402938 width=135)
- Output:["_col0"]
- Merge Join Operator [MERGEJOIN_884] (rows=158402938 width=135)
- Conds:RS_223._col0=RS_224._col0(Inner),Output:["_col1"]
- <-Map 67 [SIMPLE_EDGE]
- SHUFFLE [RS_223]
- PartitionCols:_col0
- Select Operator [SEL_219] (rows=144002668 width=135)
- Output:["_col0","_col1"]
- Filter Operator [FIL_821] (rows=144002668 width=135)
- predicate:ws_sold_date_sk is not null
- TableScan [TS_217] (rows=144002668 width=135)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity"]
- <-Map 69 [SIMPLE_EDGE]
- SHUFFLE [RS_224]
- PartitionCols:_col0
- Select Operator [SEL_222] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_822] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
- TableScan [TS_220] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 73 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_383]
- Group By Operator [GBY_276] (rows=1 width=288)
- Output:["_col0"],aggregations:["avg(VALUE._col0)"]
- <-Union 72 [CUSTOM_SIMPLE_EDGE]
- <-Reducer 71 [CONTAINS]
- Reduce Output Operator [RS_275]
- Group By Operator [GBY_274] (rows=1 width=288)
- Output:["_col0"],aggregations:["avg(_col0)"]
- Select Operator [SEL_272] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_249] (rows=633595212 width=88)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_885] (rows=633595212 width=88)
- Conds:RS_246._col0=RS_247._col0(Inner),Output:["_col1","_col2"]
- <-Map 70 [SIMPLE_EDGE]
- SHUFFLE [RS_246]
- PartitionCols:_col0
- Select Operator [SEL_242] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_823] (rows=575995635 width=88)
- predicate:ss_sold_date_sk is not null
- TableScan [TS_240] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity","ss_list_price"]
- <-Map 74 [SIMPLE_EDGE]
- SHUFFLE [RS_247]
- PartitionCols:_col0
- Select Operator [SEL_245] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_824] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
- TableScan [TS_243] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 76 [CONTAINS]
- Reduce Output Operator [RS_275]
- Group By Operator [GBY_274] (rows=1 width=288)
- Output:["_col0"],aggregations:["avg(_col0)"]
- Select Operator [SEL_272] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_259] (rows=316788826 width=135)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_886] (rows=316788826 width=135)
- Conds:RS_256._col0=RS_257._col0(Inner),Output:["_col1","_col2"]
- <-Map 75 [SIMPLE_EDGE]
- SHUFFLE [RS_256]
- PartitionCols:_col0
- Select Operator [SEL_252] (rows=287989836 width=135)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_825] (rows=287989836 width=135)
- predicate:cs_sold_date_sk is not null
- TableScan [TS_250] (rows=287989836 width=135)
- default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity","cs_list_price"]
- <-Map 77 [SIMPLE_EDGE]
- SHUFFLE [RS_257]
- PartitionCols:_col0
- Select Operator [SEL_255] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_826] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
- TableScan [TS_253] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 79 [CONTAINS]
- Reduce Output Operator [RS_275]
- Group By Operator [GBY_274] (rows=1 width=288)
- Output:["_col0"],aggregations:["avg(_col0)"]
- Select Operator [SEL_272] (rows=1108786976 width=108)
- Output:["_col0"]
- Select Operator [SEL_271] (rows=158402938 width=135)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_887] (rows=158402938 width=135)
- Conds:RS_268._col0=RS_269._col0(Inner),Output:["_col1","_col2"]
- <-Map 78 [SIMPLE_EDGE]
- SHUFFLE [RS_268]
- PartitionCols:_col0
- Select Operator [SEL_264] (rows=144002668 width=135)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_827] (rows=144002668 width=135)
- predicate:ws_sold_date_sk is not null
- TableScan [TS_262] (rows=144002668 width=135)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity","ws_list_price"]
- <-Map 80 [SIMPLE_EDGE]
- SHUFFLE [RS_269]
- PartitionCols:_col0
- Select Operator [SEL_267] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_828] (rows=8116 width=1119)
- predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
- TableScan [TS_265] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 84 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_386]
- Group By Operator [GBY_380] (rows=348467716 width=135)
+ Merge Join Operator [MERGEJOIN_907] (rows=348467716 width=432)
+ Conds:(Inner),(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"]
+ <-Reducer 59 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_380]
+ Select Operator [SEL_237] (rows=1 width=8)
+ Filter Operator [FIL_236] (rows=1 width=8)
+ predicate:(sq_count_check(_col0) <= 1)
+ Group By Operator [GBY_234] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count()"]
+ Select Operator [SEL_229] (rows=1 width=8)
+ Group By Operator [GBY_228] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(VALUE._col0)"]
+ <-Union 58 [CUSTOM_SIMPLE_EDGE]
+ <-Reducer 57 [CONTAINS]
+ Reduce Output Operator [RS_227]
+ Group By Operator [GBY_226] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(_col0)"]
+ Select Operator [SEL_225] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_202] (rows=633595212 width=88)
+ Output:["_col0"]
+ Merge Join Operator [MERGEJOIN_876] (rows=633595212 width=88)
+ Conds:RS_199._col0=RS_200._col0(Inner),Output:["_col1"]
+ <-Map 56 [SIMPLE_EDGE]
+ SHUFFLE [RS_199]
+ PartitionCols:_col0
+ Select Operator [SEL_195] (rows=575995635 width=88)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_811] (rows=575995635 width=88)
+ predicate:ss_sold_date_sk is not null
+ TableScan [TS_193] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"]
+ <-Map 61 [SIMPLE_EDGE]
+ SHUFFLE [RS_200]
+ PartitionCols:_col0
+ Select Operator [SEL_198] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_812] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
+ TableScan [TS_196] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 63 [CONTAINS]
+ Reduce Output Operator [RS_227]
+ Group By Operator [GBY_226] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(_col0)"]
+ Select Operator [SEL_225] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_212] (rows=316788826 width=135)
+ Output:["_col0"]
+ Merge Join Operator [MERGEJOIN_877] (rows=316788826 width=135)
+ Conds:RS_209._col0=RS_210._col0(Inner),Output:["_col1"]
+ <-Map 62 [SIMPLE_EDGE]
+ SHUFFLE [RS_209]
+ PartitionCols:_col0
+ Select Operator [SEL_205] (rows=287989836 width=135)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_813] (rows=287989836 width=135)
+ predicate:cs_sold_date_sk is not null
+ TableScan [TS_203] (rows=287989836 width=135)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity"]
+ <-Map 64 [SIMPLE_EDGE]
+ SHUFFLE [RS_210]
+ PartitionCols:_col0
+ Select Operator [SEL_208] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_814] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
+ TableScan [TS_206] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 66 [CONTAINS]
+ Reduce Output Operator [RS_227]
+ Group By Operator [GBY_226] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(_col0)"]
+ Select Operator [SEL_225] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_224] (rows=158402938 width=135)
+ Output:["_col0"]
+ Merge Join Operator [MERGEJOIN_878] (rows=158402938 width=135)
+ Conds:RS_221._col0=RS_222._col0(Inner),Output:["_col1"]
+ <-Map 65 [SIMPLE_EDGE]
+ SHUFFLE [RS_221]
+ PartitionCols:_col0
+ Select Operator [SEL_217] (rows=144002668 width=135)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_815] (rows=144002668 width=135)
+ predicate:ws_sold_date_sk is not null
+ TableScan [TS_215] (rows=144002668 width=135)
+ default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity"]
+ <-Map 67 [SIMPLE_EDGE]
+ SHUFFLE [RS_222]
+ PartitionCols:_col0
+ Select Operator [SEL_220] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_816] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
+ TableScan [TS_218] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 71 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_381]
+ Group By Operator [GBY_274] (rows=1 width=288)
+ Output:["_col0"],aggregations:["avg(VALUE._col0)"]
+ <-Union 70 [CUSTOM_SIMPLE_EDGE]
+ <-Reducer 69 [CONTAINS]
+ Reduce Output Operator [RS_273]
+ Group By Operator [GBY_272] (rows=1 width=288)
+ Output:["_col0"],aggregations:["avg(_col0)"]
+ Select Operator [SEL_270] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_247] (rows=633595212 width=88)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_879] (rows=633595212 width=88)
+ Conds:RS_244._col0=RS_245._col0(Inner),Output:["_col1","_col2"]
+ <-Map 68 [SIMPLE_EDGE]
+ SHUFFLE [RS_244]
+ PartitionCols:_col0
+ Select Operator [SEL_240] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_817] (rows=575995635 width=88)
+ predicate:ss_sold_date_sk is not null
+ TableScan [TS_238] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity","ss_list_price"]
+ <-Map 72 [SIMPLE_EDGE]
+ SHUFFLE [RS_245]
+ PartitionCols:_col0
+ Select Operator [SEL_243] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_818] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
+ TableScan [TS_241] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 74 [CONTAINS]
+ Reduce Output Operator [RS_273]
+ Group By Operator [GBY_272] (rows=1 width=288)
+ Output:["_col0"],aggregations:["avg(_col0)"]
+ Select Operator [SEL_270] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_257] (rows=316788826 width=135)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_880] (rows=316788826 width=135)
+ Conds:RS_254._col0=RS_255._col0(Inner),Output:["_col1","_col2"]
+ <-Map 73 [SIMPLE_EDGE]
+ SHUFFLE [RS_254]
+ PartitionCols:_col0
+ Select Operator [SEL_250] (rows=287989836 width=135)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_819] (rows=287989836 width=135)
+ predicate:cs_sold_date_sk is not null
+ TableScan [TS_248] (rows=287989836 width=135)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity","cs_list_price"]
+ <-Map 75 [SIMPLE_EDGE]
+ SHUFFLE [RS_255]
+ PartitionCols:_col0
+ Select Operator [SEL_253] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_820] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
+ TableScan [TS_251] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 77 [CONTAINS]
+ Reduce Output Operator [RS_273]
+ Group By Operator [GBY_272] (rows=1 width=288)
+ Output:["_col0"],aggregations:["avg(_col0)"]
+ Select Operator [SEL_270] (rows=1108786976 width=108)
+ Output:["_col0"]
+ Select Operator [SEL_269] (rows=158402938 width=135)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_881] (rows=158402938 width=135)
+ Conds:RS_266._col0=RS_267._col0(Inner),Output:["_col1","_col2"]
+ <-Map 76 [SIMPLE_EDGE]
+ SHUFFLE [RS_266]
+ PartitionCols:_col0
+ Select Operator [SEL_262] (rows=144002668 width=135)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_821] (rows=144002668 width=135)
+ predicate:ws_sold_date_sk is not null
+ TableScan [TS_260] (rows=144002668 width=135)
+ default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity","ws_list_price"]
+ <-Map 78 [SIMPLE_EDGE]
+ SHUFFLE [RS_267]
+ PartitionCols:_col0
+ Select Operator [SEL_265] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_822] (rows=8116 width=1119)
+ predicate:(d_year BETWEEN 1998 AND 2000 and d_date_sk is not null)
+ TableScan [TS_263] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 82 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_382]
+ Group By Operator [GBY_378] (rows=348467716 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 83 [SIMPLE_EDGE]
- SHUFFLE [RS_379]
+ <-Reducer 81 [SIMPLE_EDGE]
+ SHUFFLE [RS_377]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_378] (rows=696935432 width=135)
+ Group By Operator [GBY_376] (rows=696935432 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","count()"],keys:_col0, _col1, _col2
- Select Operator [SEL_376] (rows=696935432 width=135)
+ Select Operator [SEL_374] (rows=696935432 width=135)
Output:["_col0","_col1","_col2","_col3"]
- Merge Join Operator [MERGEJOIN_896] (rows=696935432 width=135)
- Conds:RS_372._col1=RS_373._col0(Inner),RS_372._col1=RS_374._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"]
- <-Map 86 [SIMPLE_EDGE]
- SHUFFLE [RS_373]
+ Merge Join Operator [MERGEJOIN_890] (rows=696935432 width=135)
+ Conds:RS_370._col1=RS_371._col0(Inner),RS_370._col1=RS_372._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"]
+ <-Map 84 [SIMPLE_EDGE]
+ SHUFFLE [RS_371]
PartitionCols:_col0
- Select Operator [SEL_286] (rows=462000 width=1436)
+ Select Operator [SEL_284] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_831] (rows=462000 width=1436)
+ Filter Operator [FIL_825] (rows=462000 width=1436)
predicate:i_item_sk is not null
- TableScan [TS_284] (rows=462000 width=1436)
+ TableScan [TS_282] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 82 [SIMPLE_EDGE]
- SHUFFLE [RS_372]
+ <-Reducer 80 [SIMPLE_EDGE]
+ SHUFFLE [RS_370]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_888] (rows=316788826 width=135)
- Conds:RS_369._col0=RS_370._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 81 [SIMPLE_EDGE]
- SHUFFLE [RS_369]
+ Merge Join Operator [MERGEJOIN_882] (rows=316788826 width=135)
+ Conds:RS_367._col0=RS_368._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 79 [SIMPLE_EDGE]
+ SHUFFLE [RS_367]
PartitionCols:_col0
- Select Operator [SEL_280] (rows=287989836 width=135)
+ Select Operator [SEL_278] (rows=287989836 width=135)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_829] (rows=287989836 width=135)
+ Filter Operator [FIL_823] (rows=287989836 width=135)
predicate:(cs_item_sk is not null and cs_sold_date_sk is not null)
- TableScan [TS_278] (rows=287989836 width=135)
+ TableScan [TS_276] (rows=287989836 width=135)
default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_quantity","cs_list_price"]
- <-Map 85 [SIMPLE_EDGE]
- SHUFFLE [RS_370]
+ <-Map 83 [SIMPLE_EDGE]
+ SHUFFLE [RS_368]
PartitionCols:_col0
- Select Operator [SEL_283] (rows=18262 width=1119)
+ Select Operator [SEL_281] (rows=18262 width=1119)
Output:["_col0"]
- Filter Operator [FIL_830] (rows=18262 width=1119)
+ Filter Operator [FIL_824] (rows=18262 width=1119)
predicate:((d_year = 2000) and (d_moy = 11) and d_date_sk is not null)
- TableScan [TS_281] (rows=73049 width=1119)
+ TableScan [TS_279] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
- <-Reducer 89 [SIMPLE_EDGE]
- SHUFFLE [RS_374]
+ <-Reducer 87 [SIMPLE_EDGE]
+ SHUFFLE [RS_372]
PartitionCols:_col0
- Group By Operator [GBY_367] (rows=254100 width=1436)
+ Group By Operator [GBY_365] (rows=254100 width=1436)
Output:["_col0"],keys:KEY._col0
- <-Reducer 88 [SIMPLE_EDGE]
- SHUFFLE [RS_366]
+ <-Reducer 86 [SIMPLE_EDGE]
+ SHUFFLE [RS_364]
PartitionCols:_col0
- Group By Operator [GBY_365] (rows=508200 width=1436)
+ Group By Operator [GBY_363] (rows=508200 width=1436)
Output:["_col0"],keys:_col0
- Merge Join Operator [MERGEJOIN_895] (rows=508200 width=1436)
- Conds:RS_361._col1, _col2, _col3=RS_362._col0, _col1, _col2(Inner),Output:["_col0"]
- <-Map 87 [SIMPLE_EDGE]
- SHUFFLE [RS_361]
+ Merge Join Operator [MERGEJOIN_889] (rows=508200 width=1436)
+ Conds:RS_359._col1, _col2, _col3=RS_360._col0, _col1, _col2(Inner),Output:["_col0"]
+ <-Map 85 [SIMPLE_EDGE]
+ SHUFFLE [RS_359]
PartitionCols:_col1, _col2, _col3
- Select Operator [SEL_289] (rows=462000 width=1436)
+ Select Operator [SEL_287] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_832] (rows=462000 width=1436)
+ Filter Operator [FIL_826] (rows=462000 width=1436)
predicate:(i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_item_sk is not null)
- TableScan [TS_287] (rows=462000 width=1436)
+ TableScan [TS_285] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 95 [SIMPLE_EDGE]
- SHUFFLE [RS_362]
+ <-Reducer 93 [SIMPLE_EDGE]
+ SHUFFLE [RS_360]
PartitionCols:_col0, _col1, _col2
- Select Operator [SEL_360] (rows=1 width=108)
+ Select Operator [SEL_358] (rows=1 width=108)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_359] (rows=1 width=108)
+ Filter Operator [FIL_357] (rows=1 width=108)
predicate:(_col3 = 3)
- Group By Operator [GBY_358] (rows=304916424 width=108)
+ Group By Operator [GBY_356] (rows=304916424 width=108)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Union 94 [SIMPLE_EDGE]
- <-Reducer 101 [CONTAINS]
- Reduce Output Operator [RS_357]
+ <-Union 92 [SIMPLE_EDGE]
+ <-Reducer 105 [CONTAINS]
+ Reduce Output Operator [RS_355]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_356] (rows=609832849 width=108)
+ Group By Operator [GBY_354] (rows=609832849 width=108)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2
- Group By Operator [GBY_330] (rows=174233858 width=135)
+ Group By Operator [GBY_350] (rows=87121617 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 100 [SIMPLE_EDGE]
- SHUFFLE [RS_329]
+ <-Reducer 104 [SIMPLE_EDGE]
+ SHUFFLE [RS_349]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_328] (rows=348467716 width=135)
+ Group By Operator [GBY_348] (rows=174243235 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2
- Select Operator [SEL_326] (rows=348467716 width=135)
+ Select Operator [SEL_346] (rows=174243235 width=135)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_892] (rows=348467716 width=135)
- Conds:RS_323._col1=RS_324._col0(Inner),Output:["_col5","_col6","_col7"]
- <-Map 103 [SIMPLE_EDGE]
- SHUFFLE [RS_324]
+ Merge Join Operator [MERGEJOIN_888] (rows=174243235 width=135)
+ Conds:RS_343._col1=RS_344._col0(Inner),Output:["_col5","_col6","_col7"]
+ <-Map 107 [SIMPLE_EDGE]
+ SHUFFLE [RS_344]
PartitionCols:_col0
- Select Operator [SEL_319] (rows=462000 width=1436)
+ Select Operator [SEL_339] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_838] (rows=462000 width=1436)
+ Filter Operator [FIL_835] (rows=462000 width=1436)
predicate:(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)
- TableScan [TS_317] (rows=462000 width=1436)
- default@item,ics,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 99 [SIMPLE_EDGE]
- SHUFFLE [RS_323]
+ TableScan [TS_337] (rows=462000 width=1436)
+ default@item,iws,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
+ <-Reducer 103 [SIMPLE_EDGE]
+ SHUFFLE [RS_343]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_891] (rows=316788826 width=135)
- Conds:RS_320._col0=RS_321._col0(Inner),Output:["_col1"]
+ Merge Join Operator [MERGEJOIN_887] (rows=158402938 width=135)
+ Conds:RS_340._col0=RS_341._col0(Inner),Output:["_col1"]
<-Map 102 [SIMPLE_EDGE]
- SHUFFLE [RS_321]
+ SHUFFLE [RS_340]
+ PartitionCols:_col0
+ Select Operator [SEL_333] (rows=144002668 width=135)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_833] (rows=144002668 width=135)
+ predicate:(ws_item_sk is not null and ws_sold_date_sk is not null)
+ TableScan [TS_331] (rows=144002668 width=135)
+ default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk"]
+ <-Map 106 [SIMPLE_EDGE]
+ SHUFFLE [RS_341]
PartitionCols:_col0
- Select Operator [SEL_316] (rows=8116 width=1119)
+ Select Operator [SEL_336] (rows=8116 width=1119)
Output:["_col0"]
- Filter Operator [FIL_837] (rows=8116 width=1119)
+ Filter Operator [FIL_834] (rows=8116 width=1119)
predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
- TableScan [TS_314] (rows=73049 width=1119)
- default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Map 98 [SIMPLE_EDGE]
- SHUFFLE [RS_320]
- PartitionCols:_col0
- Select Operator [SEL_313] (rows=287989836 width=135)
- Output:["_col0","_col1"]
- Filter Operator [FIL_836] (rows=287989836 width=135)
- predicate:(cs_item_sk is not null and cs_sold_date_sk is not null)
- TableScan [TS_311] (rows=287989836 width=135)
- default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk"]
- <-Reducer 107 [CONTAINS]
- Reduce Output Operator [RS_357]
+ TableScan [TS_334] (rows=73049 width=1119)
+ default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 91 [CONTAINS]
+ Reduce Output Operator [RS_355]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_356] (rows=609832849 width=108)
+ Group By Operator [GBY_354] (rows=609832849 width=108)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2
- Group By Operator [GBY_352] (rows=87121617 width=135)
+ Group By Operator [GBY_307] (rows=348477374 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 106 [SIMPLE_EDGE]
- SHUFFLE [RS_351]
+ <-Reducer 90 [SIMPLE_EDGE]
+ SHUFFLE [RS_306]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_350] (rows=174243235 width=135)
+ Group By Operator [GBY_305] (rows=696954748 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2
- Select Operator [SEL_348] (rows=174243235 width=135)
+ Select Operator [SEL_303] (rows=696954748 width=88)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_894] (rows=174243235 width=135)
- Conds:RS_345._col1=RS_346._col0(Inner),Output:["_col5","_col6","_col7"]
- <-Map 109 [SIMPLE_EDGE]
- SHUFFLE [RS_346]
+ Merge Join Operator [MERGEJOIN_884] (rows=696954748 width=88)
+ Conds:RS_300._col1=RS_301._col0(Inner),Output:["_col5","_col6","_col7"]
+ <-Map 95 [SIMPLE_EDGE]
+ SHUFFLE [RS_301]
PartitionCols:_col0
- Select Operator [SEL_341] (rows=462000 width=1436)
+ Select Operator [SEL_296] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_841] (rows=462000 width=1436)
+ Filter Operator [FIL_829] (rows=462000 width=1436)
predicate:(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)
- TableScan [TS_339] (rows=462000 width=1436)
- default@item,iws,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 105 [SIMPLE_EDGE]
- SHUFFLE [RS_345]
+ TableScan [TS_294] (rows=462000 width=1436)
+ default@item,iss,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
+ <-Reducer 89 [SIMPLE_EDGE]
+ SHUFFLE [RS_300]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_893] (rows=158402938 width=135)
- Conds:RS_342._col0=RS_343._col0(Inner),Output:["_col1"]
- <-Map 104 [SIMPLE_EDGE]
- SHUFFLE [RS_342]
+ Merge Join Operator [MERGEJOIN_883] (rows=633595212 width=88)
+ Conds:RS_297._col0=RS_298._col0(Inner),Output:["_col1"]
+ <-Map 88 [SIMPLE_EDGE]
+ SHUFFLE [RS_297]
PartitionCols:_col0
- Select Operator [SEL_335] (rows=144002668 width=135)
+ Select Operator [SEL_290] (rows=575995635 width=88)
Output:["_col0","_col1"]
- Filter Operator [FIL_839] (rows=144002668 width=135)
- predicate:(ws_item_sk is not null and ws_sold_date_sk is not null)
- TableScan [TS_333] (rows=144002668 width=135)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk"]
- <-Map 108 [SIMPLE_EDGE]
- SHUFFLE [RS_343]
+ Filter Operator [FIL_827] (rows=575995635 width=88)
+ predicate:(ss_item_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_288] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk"]
+ <-Map 94 [SIMPLE_EDGE]
+ SHUFFLE [RS_298]
PartitionCols:_col0
- Select Operator [SEL_338] (rows=8116 width=1119)
+ Select Operator [SEL_293] (rows=8116 width=1119)
Output:["_col0"]
- Filter Operator [FIL_840] (rows=8116 width=1119)
+ Filter Operator [FIL_828] (rows=8116 width=1119)
predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
- TableScan [TS_336] (rows=73049 width=1119)
- default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 93 [CONTAINS]
- Reduce Output Operator [RS_357]
+ TableScan [TS_291] (rows=73049 width=1119)
+ default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 99 [CONTAINS]
+ Reduce Output Operator [RS_355]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_356] (rows=609832849 width=108)
+ Group By Operator [GBY_354] (rows=609832849 width=108)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2
- Group By Operator [GBY_309] (rows=348477374 width=88)
+ Group By Operator [GBY_328] (rows=174233858 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 92 [SIMPLE_EDGE]
- SHUFFLE [RS_308]
+ <-Reducer 98 [SIMPLE_EDGE]
+ SHUFFLE [RS_327]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_307] (rows=696954748 width=88)
+ Group By Operator [GBY_326] (rows=348467716 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2
- Select Operator [SEL_305] (rows=696954748 width=88)
+ Select Operator [SEL_324] (rows=348467716 width=135)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_890] (rows=696954748 width=88)
- Conds:RS_302._col1=RS_303._col0(Inner),Output:["_col5","_col6","_col7"]
- <-Map 97 [SIMPLE_EDGE]
- SHUFFLE [RS_303]
+ Merge Join Operator [MERGEJOIN_886] (rows=348467716 width=135)
+ Conds:RS_321._col1=RS_322._col0(Inner),Output:["_col5","_col6","_col7"]
+ <-Map 101 [SIMPLE_EDGE]
+ SHUFFLE [RS_322]
PartitionCols:_col0
- Select Operator [SEL_298] (rows=462000 width=1436)
+ Select Operator [SEL_317] (rows=462000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_835] (rows=462000 width=1436)
+ Filter Operator [FIL_832] (rows=462000 width=1436)
predicate:(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)
- TableScan [TS_296] (rows=462000 width=1436)
- default@item,iss,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
- <-Reducer 91 [SIMPLE_EDGE]
- SHUFFLE [RS_302]
+ TableScan [TS_315] (rows=462000 width=1436)
+ default@item,ics,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"]
+ <-Reducer 97 [SIMPLE_EDGE]
+ SHUFFLE [RS_321]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_889] (rows=633595212 width=88)
- Conds:RS_299._col0=RS_300._col0(Inner),Output:["_col1"]
- <-Map 90 [SIMPLE_EDGE]
- SHUFFLE [RS_299]
+ Merge Join Operator [MERGEJOIN_885] (rows=316788826 width=135)
+ Conds:RS_318._col0=RS_319._col0(Inner),Output:["_col1"]
+ <-Map 100 [SIMPLE_EDGE]
+ SHUFFLE [RS_319]
PartitionCols:_col0
- Select Operator [SEL_292] (rows=575995635 width=88)
- Output:["_col0","_col1"]
- Filter Operator [FIL_833] (rows=575995635 width=88)
- predicate:(ss_item_sk is not null and ss_sold_date_sk is not null)
- TableScan [TS_290] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk"]
- <-Map 96 [SIMPLE_EDGE]
- SHUFFLE [RS_300]
- PartitionCols:_col0
- Select Operator [SEL_295] (rows=8116 width=1119)
+ Select Operator [SEL_314] (rows=8116 width=1119)
Output:["_col0"]
- Filter Operator [FIL_834] (rows=8116 width=1119)
+ Filter Operator [FIL_831] (rows=8116 width=1119)
predicate:(d_year BETWEEN 1999 AND 2001 and d_date_sk is not null)
- TableScan [TS_293] (rows=73049 width=1119)
- default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ TableScan [TS_312] (rows=73049 width=1119)
+ default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Map 96 [SIMPLE_EDGE]
+ SHUFFLE [RS_318]
+ PartitionCols:_col0
+ Select Operator [SEL_311] (rows=287989836 width=135)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_830] (rows=287989836 width=135)
+ predicate:(cs_item_sk is not null and cs_sold_date_sk is not null)
+ TableScan [TS_309] (rows=287989836 width=135)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk"]
diff --git a/ql/src/test/results/clientpositive/perf/query15.q.out b/ql/src/test/results/clientpositive/perf/query15.q.out
index 064333f..adec728 100644
--- a/ql/src/test/results/clientpositive/perf/query15.q.out
+++ b/ql/src/test/results/clientpositive/perf/query15.q.out
@@ -5,81 +5,81 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
-Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 4 <- Map 9 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
+Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
-Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
+Reducer 8 <- Map 7 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:100
Stage-1
- Reducer 6
+ Reducer 5
File Output Operator [FS_31]
Limit [LIM_30] (rows=100 width=135)
Number of rows:100
Select Operator [SEL_29] (rows=174233858 width=135)
Output:["_col0","_col1"]
- <-Reducer 5 [SIMPLE_EDGE]
+ <-Reducer 4 [SIMPLE_EDGE]
SHUFFLE [RS_28]
Group By Operator [GBY_26] (rows=174233858 width=135)
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 4 [SIMPLE_EDGE]
+ <-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_25]
PartitionCols:_col0
Group By Operator [GBY_24] (rows=348467716 width=135)
- Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7
- Merge Join Operator [MERGEJOIN_47] (rows=348467716 width=135)
- Conds:RS_20._col0=RS_21._col0(Inner),Output:["_col2","_col7"]
- <-Map 9 [SIMPLE_EDGE]
- SHUFFLE [RS_21]
- PartitionCols:_col0
- Select Operator [SEL_19] (rows=18262 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_44] (rows=18262 width=1119)
- predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null)
- TableScan [TS_17] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_20]
- PartitionCols:_col0
- Select Operator [SEL_16] (rows=316788826 width=135)
- Output:["_col0","_col2","_col7"]
- Filter Operator [FIL_15] (rows=316788826 width=135)
- predicate:((substr(_col4, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') or (_col3) IN ('CA', 'WA', 'GA') or (_col7 > 500))
- Merge Join Operator [MERGEJOIN_46] (rows=316788826 width=135)
- Conds:RS_12._col0=RS_13._col1(Inner),Output:["_col3","_col4","_col5","_col7"]
- <-Map 8 [SIMPLE_EDGE]
- SHUFFLE [RS_13]
+ Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col4
+ Select Operator [SEL_23] (rows=348467716 width=135)
+ Output:["_col4","_col7"]
+ Filter Operator [FIL_22] (rows=348467716 width=135)
+ predicate:((substr(_col4, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') or (_col3) IN ('CA', 'WA', 'GA') or (_col7 > 500))
+ Merge Join Operator [MERGEJOIN_46] (rows=348467716 width=135)
+ Conds:RS_19._col0=RS_20._col1(Inner),Output:["_col3","_col4","_col7"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_19]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_44] (rows=88000001 width=860)
+ Conds:RS_16._col1=RS_17._col0(Inner),Output:["_col0","_col3","_col4"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_16]
PartitionCols:_col1
+ Select Operator [SEL_2] (rows=80000000 width=860)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_40] (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_current_addr_sk"]
+ <-Map 6 [SIMPLE_EDGE]
+ SHUFFLE [RS_17]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=40000000 width=1014)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_41] (rows=40000000 width=1014)
+ predicate: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_zip"]
+ <-Reducer 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_20]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_45] (rows=316788826 width=135)
+ Conds:RS_12._col0=RS_13._col0(Inner),Output:["_col1","_col2"]
+ <-Map 7 [SIMPLE_EDGE]
+ SHUFFLE [RS_12]
+ PartitionCols:_col0
Select Operator [SEL_8] (rows=287989836 width=135)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_43] (rows=287989836 width=135)
+ Filter Operator [FIL_42] (rows=287989836 width=135)
predicate:(cs_bill_customer_sk is not null and cs_sold_date_sk is not null)
TableScan [TS_6] (rows=287989836 width=135)
default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_sales_price"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_12]
+ <-Map 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_13]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_45] (rows=88000001 width=860)
- Conds:RS_9._col1=RS_10._col0(Inner),Output:["_col0","_col3","_col4"]
- <-Map 1 [SIMPLE_EDGE]
- SHUFFLE [RS_9]
- PartitionCols:_col1
- Select Operator [SEL_2] (rows=80000000 width=860)
- Output:["_col0","_col1"]
- Filter Operator [FIL_41] (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_current_addr_sk"]
- <-Map 7 [SIMPLE_EDGE]
- SHUFFLE [RS_10]
- PartitionCols:_col0
- Select Operator [SEL_5] (rows=40000000 width=1014)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_42] (rows=40000000 width=1014)
- predicate: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_zip"]
+ Select Operator [SEL_11] (rows=18262 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_43] (rows=18262 width=1119)
+ predicate:((d_qoy = 2) and (d_year = 2000) 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","d_qoy"]
diff --git a/ql/src/test/results/clientpositive/perf/query16.q.out b/ql/src/test/results/clientpositive/perf/query16.q.out
index 3bc9ca0..05b1871 100644
--- a/ql/src/test/results/clientpositive/perf/query16.q.out
+++ b/ql/src/test/results/clientpositive/perf/query16.q.out
@@ -165,17 +165,17 @@ Stage-0
<-Reducer 13 [SIMPLE_EDGE]
SHUFFLE [RS_58]
PartitionCols:_col0
- Select Operator [SEL_18] (rows=7199720 width=106)
+ Select Operator [SEL_18] (rows=14399440 width=106)
Output:["_col0","_col1"]
- Group By Operator [GBY_17] (rows=7199720 width=106)
+ Group By Operator [GBY_17] (rows=14399440 width=106)
Output:["_col0"],keys:KEY._col0
<-Map 12 [SIMPLE_EDGE]
SHUFFLE [RS_16]
PartitionCols:_col0
- Group By Operator [GBY_15] (rows=14399440 width=106)
+ Group By Operator [GBY_15] (rows=28798881 width=106)
Output:["_col0"],keys:cr_order_number
- Filter Operator [FIL_103] (rows=14399440 width=106)
- predicate:(cr_order_number = cr_order_number)
+ Filter Operator [FIL_103] (rows=28798881 width=106)
+ predicate:cr_order_number is not null
TableScan [TS_12] (rows=28798881 width=106)
default@catalog_returns,cr1,Tbl:COMPLETE,Col:NONE,Output:["cr_order_number"]
<-Reducer 4 [SIMPLE_EDGE]
@@ -226,7 +226,7 @@ Stage-0
Select Operator [SEL_5] (rows=8116 width=1119)
Output:["_col0"]
Filter Operator [FIL_100] (rows=8116 width=1119)
- predicate:(d_date BETWEEN '2001-4-01' AND 2001-05-31 01:00:00.0 and d_date_sk is not null)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN 2001-04-01 00:00:00.0 AND 2001-05-31 01:00:00.0 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_date"]
diff --git a/ql/src/test/results/clientpositive/perf/query19.q.out b/ql/src/test/results/clientpositive/perf/query19.q.out
index 77f7576..cebfc3a 100644
--- a/ql/src/test/results/clientpositive/perf/query19.q.out
+++ b/ql/src/test/results/clientpositive/perf/query19.q.out
@@ -5,115 +5,113 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 10 <- Map 13 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
+Reducer 10 <- Map 12 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
+Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
-Reducer 8 <- Map 11 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
-Reducer 9 <- Map 12 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
+Reducer 9 <- Map 11 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:100
Stage-1
- Reducer 5
- File Output Operator [FS_45]
- Limit [LIM_44] (rows=100 width=88)
+ Reducer 6
+ File Output Operator [FS_44]
+ Limit [LIM_43] (rows=100 width=88)
Number of rows:100
- Select Operator [SEL_43] (rows=421657640 width=88)
+ Select Operator [SEL_42] (rows=421657640 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"]
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_42]
- Select Operator [SEL_40] (rows=421657640 width=88)
+ <-Reducer 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_41]
+ Select Operator [SEL_39] (rows=421657640 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Group By Operator [GBY_39] (rows=421657640 width=88)
+ Group By Operator [GBY_38] (rows=421657640 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_38]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_37]
PartitionCols:_col0, _col1, _col2, _col3
- Group By Operator [GBY_37] (rows=843315281 width=88)
- Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col7)"],keys:_col10, _col9, _col11, _col12
- Select Operator [SEL_36] (rows=843315281 width=88)
- Output:["_col7","_col9","_col10","_col11","_col12"]
- Filter Operator [FIL_35] (rows=843315281 width=88)
- predicate:(substr(_col17, 1, 5) <> substr(_col19, 1, 5))
- Select Operator [SEL_34] (rows=843315281 width=88)
- Output:["_col7","_col9","_col10","_col11","_col12","_col17","_col19"]
- Merge Join Operator [MERGEJOIN_73] (rows=843315281 width=88)
- Conds:RS_31._col0=RS_32._col2(Inner),Output:["_col3","_col8","_col13","_col14","_col15","_col16","_col19"]
- <-Reducer 10 [SIMPLE_EDGE]
- SHUFFLE [RS_32]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_72] (rows=766650239 width=88)
- Conds:RS_24._col3=RS_25._col0(Inner),Output:["_col2","_col4","_col9","_col10","_col11","_col12","_col15"]
- <-Map 13 [SIMPLE_EDGE]
- SHUFFLE [RS_25]
- PartitionCols:_col0
- Select Operator [SEL_17] (rows=1704 width=1910)
- Output:["_col0","_col1"]
- Filter Operator [FIL_68] (rows=1704 width=1910)
- predicate:s_store_sk is not null
- TableScan [TS_15] (rows=1704 width=1910)
- default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_zip"]
- <-Reducer 9 [SIMPLE_EDGE]
- SHUFFLE [RS_24]
- PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_71] (rows=696954748 width=88)
- Conds:RS_21._col1=RS_22._col0(Inner),Output:["_col2","_col3","_col4","_col9","_col10","_col11","_col12"]
- <-Map 12 [SIMPLE_EDGE]
- SHUFFLE [RS_22]
- PartitionCols:_col0
- Select Operator [SEL_14] (rows=231000 width=1436)
- Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_67] (rows=231000 width=1436)
- predicate:((i_manager_id = 7) and i_item_sk is not null)
- TableScan [TS_12] (rows=462000 width=1436)
- default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_brand","i_manufact_id","i_manufact","i_manager_id"]
- <-Reducer 8 [SIMPLE_EDGE]
- SHUFFLE [RS_21]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_70] (rows=633595212 width=88)
- Conds:RS_18._col0=RS_19._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
- <-Map 11 [SIMPLE_EDGE]
- SHUFFLE [RS_19]
- PartitionCols:_col0
- Select Operator [SEL_11] (rows=18262 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_66] (rows=18262 width=1119)
- predicate:((d_moy = 11) and (d_year = 1999) 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","d_moy"]
- <-Map 7 [SIMPLE_EDGE]
- SHUFFLE [RS_18]
- PartitionCols:_col0
- Select Operator [SEL_8] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_65] (rows=575995635 width=88)
- predicate:(ss_sold_date_sk is not null and ss_item_sk is not null and ss_customer_sk is not null and ss_store_sk is not null)
- TableScan [TS_6] (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_store_sk","ss_ext_sales_price"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_31]
- PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_69] (rows=88000001 width=860)
- Conds:RS_28._col1=RS_29._col0(Inner),Output:["_col0","_col3"]
- <-Map 1 [SIMPLE_EDGE]
- SHUFFLE [RS_28]
- PartitionCols:_col1
- Select Operator [SEL_2] (rows=80000000 width=860)
- Output:["_col0","_col1"]
- Filter Operator [FIL_63] (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_current_addr_sk"]
- <-Map 6 [SIMPLE_EDGE]
- SHUFFLE [RS_29]
- PartitionCols:_col0
- Select Operator [SEL_5] (rows=40000000 width=1014)
- Output:["_col0","_col1"]
- Filter Operator [FIL_64] (rows=40000000 width=1014)
- predicate: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_zip"]
+ Group By Operator [GBY_36] (rows=843315281 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col8)"],keys:_col14, _col13, _col15, _col16
+ Select Operator [SEL_35] (rows=843315281 width=88)
+ Output:["_col8","_col13","_col14","_col15","_col16"]
+ Filter Operator [FIL_34] (rows=843315281 width=88)
+ predicate:(substr(_col3, 1, 5) <> substr(_col19, 1, 5))
+ Merge Join Operator [MERGEJOIN_73] (rows=843315281 width=88)
+ Conds:RS_31._col7=RS_32._col0(Inner),Output:["_col3","_col8","_col13","_col14","_col15","_col16","_col19"]
+ <-Map 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_32]
+ PartitionCols:_col0
+ Select Operator [SEL_24] (rows=1704 width=1910)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_68] (rows=1704 width=1910)
+ predicate:s_store_sk is not null
+ TableScan [TS_22] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_zip"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_31]
+ PartitionCols:_col7
+ Merge Join Operator [MERGEJOIN_72] (rows=766650239 width=88)
+ Conds:RS_28._col0=RS_29._col2(Inner),Output:["_col3","_col7","_col8","_col13","_col14","_col15","_col16"]
+ <-Reducer 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_29]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_71] (rows=696954748 width=88)
+ Conds:RS_18._col1=RS_19._col0(Inner),Output:["_col2","_col3","_col4","_col9","_col10","_col11","_col12"]
+ <-Map 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_19]
+ PartitionCols:_col0
+ Select Operator [SEL_14] (rows=231000 width=1436)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_67] (rows=231000 width=1436)
+ predicate:((i_manager_id = 7) and i_item_sk is not null)
+ TableScan [TS_12] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_brand","i_manufact_id","i_manufact","i_manager_id"]
+ <-Reducer 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_18]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_70] (rows=633595212 width=88)
+ Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
+ <-Map 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_16]
+ PartitionCols:_col0
+ Select Operator [SEL_11] (rows=18262 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_66] (rows=18262 width=1119)
+ predicate:((d_moy = 11) and (d_year = 1999) 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","d_moy"]
+ <-Map 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_15]
+ PartitionCols:_col0
+ Select Operator [SEL_8] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_65] (rows=575995635 width=88)
+ predicate:(ss_sold_date_sk is not null and ss_item_sk is not null and ss_customer_sk is not null and ss_store_sk is not null)
+ TableScan [TS_6] (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_store_sk","ss_ext_sales_price"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_28]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_69] (rows=88000001 width=860)
+ Conds:RS_25._col1=RS_26._col0(Inner),Output:["_col0","_col3"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_25]
+ PartitionCols:_col1
+ Select Operator [SEL_2] (rows=80000000 width=860)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_63] (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_current_addr_sk"]
+ <-Map 7 [SIMPLE_EDGE]
+ SHUFFLE [RS_26]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=40000000 width=1014)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_64] (rows=40000000 width=1014)
+ predicate: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_zip"]
diff --git a/ql/src/test/results/clientpositive/perf/query21.q.out b/ql/src/test/results/clientpositive/perf/query21.q.out
index 67a49e2..292fc4f 100644
--- a/ql/src/test/results/clientpositive/perf/query21.q.out
+++ b/ql/src/test/results/clientpositive/perf/query21.q.out
@@ -133,7 +133,7 @@ Stage-0
Select Operator [SEL_5] (rows=8116 width=1119)
Output:["_col0","_col1"]
Filter Operator [FIL_42] (rows=8116 width=1119)
- predicate:(d_date BETWEEN 1998-03-08 23:00:00.0 AND 1998-05-08 00:00:00.0 and d_date_sk is not null)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN 1998-03-08 23:00:00.0 AND 1998-05-08 00:00:00.0 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_date"]
diff --git a/ql/src/test/results/clientpositive/perf/query23.q.out b/ql/src/test/results/clientpositive/perf/query23.q.out
index 85cee23..a04e5cd 100644
--- a/ql/src/test/results/clientpositive/perf/query23.q.out
+++ b/ql/src/test/results/clientpositive/perf/query23.q.out
@@ -1,7 +1,5 @@
-Warning: Shuffle Join MERGEJOIN[379][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 19' is a cross product
-Warning: Shuffle Join MERGEJOIN[380][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 20' is a cross product
-Warning: Shuffle Join MERGEJOIN[382][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 51' is a cross product
-Warning: Shuffle Join MERGEJOIN[383][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 52' is a cross product
+Warning: Shuffle Join MERGEJOIN[367][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 19' is a cross product
+Warning: Shuffle Join MERGEJOIN[369][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 49' is a cross product
PREHOOK: query: explain with frequent_ss_items as
(select substr(i_item_desc,1,30) itemdesc,i_item_sk item_sk,d_date solddate,count(*) cnt
from store_sales
@@ -107,42 +105,38 @@ Plan optimized by CBO.
Vertex dependency in root stage
Reducer 10 <- Map 13 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
Reducer 11 <- Reducer 10 (SIMPLE_EDGE)
-Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE)
-Reducer 16 <- Map 23 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE)
+Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE)
+Reducer 16 <- Map 21 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE)
Reducer 17 <- Reducer 16 (SIMPLE_EDGE)
Reducer 18 <- Reducer 17 (CUSTOM_SIMPLE_EDGE)
-Reducer 19 <- Reducer 18 (CUSTOM_SIMPLE_EDGE), Reducer 28 (CUSTOM_SIMPLE_EDGE)
+Reducer 19 <- Reducer 18 (CUSTOM_SIMPLE_EDGE), Reducer 26 (CUSTOM_SIMPLE_EDGE), Reducer 31 (CUSTOM_SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
-Reducer 20 <- Reducer 19 (CUSTOM_SIMPLE_EDGE), Reducer 33 (CUSTOM_SIMPLE_EDGE)
-Reducer 21 <- Reducer 20 (SIMPLE_EDGE)
-Reducer 25 <- Map 24 (SIMPLE_EDGE), Map 29 (SIMPLE_EDGE)
-Reducer 26 <- Map 30 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE)
-Reducer 27 <- Reducer 26 (SIMPLE_EDGE)
-Reducer 28 <- Reducer 27 (CUSTOM_SIMPLE_EDGE)
+Reducer 23 <- Map 22 (SIMPLE_EDGE), Map 27 (SIMPLE_EDGE)
+Reducer 24 <- Map 28 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE)
+Reducer 25 <- Reducer 24 (SIMPLE_EDGE)
+Reducer 26 <- Reducer 25 (CUSTOM_SIMPLE_EDGE)
Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 32 <- Map 31 (SIMPLE_EDGE), Map 34 (SIMPLE_EDGE)
-Reducer 33 <- Reducer 32 (SIMPLE_EDGE)
-Reducer 36 <- Map 35 (SIMPLE_EDGE), Map 39 (SIMPLE_EDGE)
-Reducer 37 <- Reducer 36 (SIMPLE_EDGE), Reducer 43 (SIMPLE_EDGE)
-Reducer 38 <- Reducer 37 (SIMPLE_EDGE), Reducer 53 (SIMPLE_EDGE), Union 5 (CONTAINS)
-Reducer 4 <- Reducer 21 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS)
-Reducer 41 <- Map 40 (SIMPLE_EDGE), Map 44 (SIMPLE_EDGE)
-Reducer 42 <- Map 45 (SIMPLE_EDGE), Reducer 41 (SIMPLE_EDGE)
-Reducer 43 <- Reducer 42 (SIMPLE_EDGE)
-Reducer 47 <- Map 46 (SIMPLE_EDGE), Map 54 (SIMPLE_EDGE)
-Reducer 48 <- Map 55 (SIMPLE_EDGE), Reducer 47 (SIMPLE_EDGE)
-Reducer 49 <- Reducer 48 (SIMPLE_EDGE)
-Reducer 50 <- Reducer 49 (CUSTOM_SIMPLE_EDGE)
-Reducer 51 <- Reducer 50 (CUSTOM_SIMPLE_EDGE), Reducer 60 (CUSTOM_SIMPLE_EDGE)
-Reducer 52 <- Reducer 51 (CUSTOM_SIMPLE_EDGE), Reducer 65 (CUSTOM_SIMPLE_EDGE)
-Reducer 53 <- Reducer 52 (SIMPLE_EDGE)
-Reducer 57 <- Map 56 (SIMPLE_EDGE), Map 61 (SIMPLE_EDGE)
-Reducer 58 <- Map 62 (SIMPLE_EDGE), Reducer 57 (SIMPLE_EDGE)
-Reducer 59 <- Reducer 58 (SIMPLE_EDGE)
+Reducer 30 <- Map 29 (SIMPLE_EDGE), Map 32 (SIMPLE_EDGE)
+Reducer 31 <- Reducer 30 (SIMPLE_EDGE)
+Reducer 34 <- Map 33 (SIMPLE_EDGE), Map 37 (SIMPLE_EDGE)
+Reducer 35 <- Reducer 34 (SIMPLE_EDGE), Reducer 41 (SIMPLE_EDGE)
+Reducer 36 <- Reducer 35 (SIMPLE_EDGE), Reducer 49 (SIMPLE_EDGE), Union 5 (CONTAINS)
+Reducer 39 <- Map 38 (SIMPLE_EDGE), Map 42 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 19 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS)
+Reducer 40 <- Map 43 (SIMPLE_EDGE), Reducer 39 (SIMPLE_EDGE)
+Reducer 41 <- Reducer 40 (SIMPLE_EDGE)
+Reducer 45 <- Map 44 (SIMPLE_EDGE), Map 50 (SIMPLE_EDGE)
+Reducer 46 <- Map 51 (SIMPLE_EDGE), Reducer 45 (SIMPLE_EDGE)
+Reducer 47 <- Reducer 46 (SIMPLE_EDGE)
+Reducer 48 <- Reducer 47 (CUSTOM_SIMPLE_EDGE)
+Reducer 49 <- Reducer 48 (CUSTOM_SIMPLE_EDGE), Reducer 56 (CUSTOM_SIMPLE_EDGE), Reducer 61 (CUSTOM_SIMPLE_EDGE)
+Reducer 53 <- Map 52 (SIMPLE_EDGE), Map 57 (SIMPLE_EDGE)
+Reducer 54 <- Map 58 (SIMPLE_EDGE), Reducer 53 (SIMPLE_EDGE)
+Reducer 55 <- Reducer 54 (SIMPLE_EDGE)
+Reducer 56 <- Reducer 55 (CUSTOM_SIMPLE_EDGE)
Reducer 6 <- Union 5 (CUSTOM_SIMPLE_EDGE)
-Reducer 60 <- Reducer 59 (CUSTOM_SIMPLE_EDGE)
-Reducer 64 <- Map 63 (SIMPLE_EDGE), Map 66 (SIMPLE_EDGE)
-Reducer 65 <- Reducer 64 (SIMPLE_EDGE)
+Reducer 60 <- Map 59 (SIMPLE_EDGE), Map 62 (SIMPLE_EDGE)
+Reducer 61 <- Reducer 60 (SIMPLE_EDGE)
Reducer 9 <- Map 12 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
Stage-0
@@ -150,435 +144,413 @@ Stage-0
limit:100
Stage-1
Reducer 6
- File Output Operator [FS_258]
- Limit [LIM_257] (rows=1 width=112)
+ File Output Operator [FS_246]
+ Limit [LIM_245] (rows=1 width=112)
Number of rows:100
- Group By Operator [GBY_255] (rows=1 width=112)
+ Group By Operator [GBY_243] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(VALUE._col0)"]
<-Union 5 [CUSTOM_SIMPLE_EDGE]
- <-Reducer 38 [CONTAINS]
- Reduce Output Operator [RS_254]
- Group By Operator [GBY_253] (rows=1 width=112)
+ <-Reducer 36 [CONTAINS]
+ Reduce Output Operator [RS_242]
+ Group By Operator [GBY_241] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(_col0)"]
- Select Operator [SEL_249] (rows=191667562 width=135)
+ Select Operator [SEL_237] (rows=191667562 width=135)
Output:["_col0"]
- Merge Join Operator [MERGEJOIN_384] (rows=191667562 width=135)
- Conds:RS_246._col2=RS_247._col0(Inner),Output:["_col3","_col4"]
- <-Reducer 37 [SIMPLE_EDGE]
- SHUFFLE [RS_246]
+ Merge Join Operator [MERGEJOIN_370] (rows=191667562 width=135)
+ Conds:RS_234._col2=RS_235._col0(Inner),Output:["_col3","_col4"]
+ <-Reducer 35 [SIMPLE_EDGE]
+ SHUFFLE [RS_234]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_378] (rows=174243235 width=135)
- Conds:RS_243._col1=RS_244._col0(Inner),Output:["_col2","_col3","_col4"]
- <-Reducer 36 [SIMPLE_EDGE]
- SHUFFLE [RS_243]
+ Merge Join Operator [MERGEJOIN_366] (rows=174243235 width=135)
+ Conds:RS_231._col1=RS_232._col0(Inner),Output:["_col2","_col3","_col4"]
+ <-Reducer 34 [SIMPLE_EDGE]
+ SHUFFLE [RS_231]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_369] (rows=158402938 width=135)
- Conds:RS_240._col0=RS_241._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
- <-Map 35 [SIMPLE_EDGE]
- SHUFFLE [RS_240]
+ Merge Join Operator [MERGEJOIN_357] (rows=158402938 width=135)
+ Conds:RS_228._col0=RS_229._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
+ <-Map 33 [SIMPLE_EDGE]
+ SHUFFLE [RS_228]
PartitionCols:_col0
- Select Operator [SEL_127] (rows=144002668 width=135)
+ Select Operator [SEL_121] (rows=144002668 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_346] (rows=144002668 width=135)
+ Filter Operator [FIL_334] (rows=144002668 width=135)
predicate:(ws_item_sk is not null and ws_bill_customer_sk is not null and ws_sold_date_sk is not null)
- TableScan [TS_125] (rows=144002668 width=135)
+ TableScan [TS_119] (rows=144002668 width=135)
default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_quantity","ws_list_price"]
- <-Map 39 [SIMPLE_EDGE]
- SHUFFLE [RS_241]
+ <-Map 37 [SIMPLE_EDGE]
+ SHUFFLE [RS_229]
PartitionCols:_col0
- Select Operator [SEL_130] (rows=18262 width=1119)
+ Select Operator [SEL_124] (rows=18262 width=1119)
Output:["_col0"]
- Filter Operator [FIL_347] (rows=18262 width=1119)
+ Filter Operator [FIL_335] (rows=18262 width=1119)
predicate:((d_year = 1999) and (d_moy = 1) and d_date_sk is not null)
- TableScan [TS_128] (rows=73049 width=1119)
+ TableScan [TS_122] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
- <-Reducer 43 [SIMPLE_EDGE]
- SHUFFLE [RS_244]
+ <-Reducer 41 [SIMPLE_EDGE]
+ SHUFFLE [RS_232]
PartitionCols:_col0
- Group By Operator [GBY_156] (rows=58079562 width=88)
+ Group By Operator [GBY_150] (rows=58079562 width=88)
Output:["_col0"],keys:_col1
- Select Operator [SEL_152] (rows=116159124 width=88)
+ Select Operator [SEL_146] (rows=116159124 width=88)
Output:["_col1"]
- Filter Operator [FIL_151] (rows=116159124 width=88)
+ Filter Operator [FIL_145] (rows=116159124 width=88)
predicate:(_col3 > 4)
- Select Operator [SEL_360] (rows=348477374 width=88)
+ Select Operator [SEL_348] (rows=348477374 width=88)
Output:["_col0","_col3"]
- Group By Operator [GBY_150] (rows=348477374 width=88)
+ Group By Operator [GBY_144] (rows=348477374 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 42 [SIMPLE_EDGE]
- SHUFFLE [RS_149]
+ <-Reducer 40 [SIMPLE_EDGE]
+ SHUFFLE [RS_143]
PartitionCols:_col0
- Group By Operator [GBY_148] (rows=696954748 width=88)
+ Group By Operator [GBY_142] (rows=696954748 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2
- Select Operator [SEL_146] (rows=696954748 width=88)
+ Select Operator [SEL_140] (rows=696954748 width=88)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_371] (rows=696954748 width=88)
- Conds:RS_143._col1=RS_144._col0(Inner),Output:["_col3","_col5","_col6"]
- <-Map 45 [SIMPLE_EDGE]
- SHUFFLE [RS_144]
+ Merge Join Operator [MERGEJOIN_359] (rows=696954748 width=88)
+ Conds:RS_137._col1=RS_138._col0(Inner),Output:["_col3","_col5","_col6"]
+ <-Map 43 [SIMPLE_EDGE]
+ SHUFFLE [RS_138]
PartitionCols:_col0
- Select Operator [SEL_139] (rows=462000 width=1436)
+ Select Operator [SEL_133] (rows=462000 width=1436)
Output:["_col0","_col1"]
- Filter Operator [FIL_350] (rows=462000 width=1436)
+ Filter Operator [FIL_338] (rows=462000 width=1436)
predicate:i_item_sk is not null
- TableScan [TS_137] (rows=462000 width=1436)
+ TableScan [TS_131] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_desc"]
- <-Reducer 41 [SIMPLE_EDGE]
- SHUFFLE [RS_143]
+ <-Reducer 39 [SIMPLE_EDGE]
+ SHUFFLE [RS_137]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_370] (rows=633595212 width=88)
- Conds:RS_140._col0=RS_141._col0(Inner),Output:["_col1","_col3"]
- <-Map 40 [SIMPLE_EDGE]
- SHUFFLE [RS_140]
+ Merge Join Operator [MERGEJOIN_358] (rows=633595212 width=88)
+ Conds:RS_134._col0=RS_135._col0(Inner),Output:["_col1","_col3"]
+ <-Map 38 [SIMPLE_EDGE]
+ SHUFFLE [RS_134]
PartitionCols:_col0
- Select Operator [SEL_133] (rows=575995635 width=88)
+ Select Operator [SEL_127] (rows=575995635 width=88)
Output:["_col0","_col1"]
- Filter Operator [FIL_348] (rows=575995635 width=88)
+ Filter Operator [FIL_336] (rows=575995635 width=88)
predicate:(ss_sold_date_sk is not null and ss_item_sk is not null)
- TableScan [TS_131] (rows=575995635 width=88)
+ TableScan [TS_125] (rows=575995635 width=88)
default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk"]
- <-Map 44 [SIMPLE_EDGE]
- SHUFFLE [RS_141]
+ <-Map 42 [SIMPLE_EDGE]
+ SHUFFLE [RS_135]
PartitionCols:_col0
- Select Operator [SEL_136] (rows=36525 width=1119)
+ Select Operator [SEL_130] (rows=36525 width=1119)
Output:["_col0","_col1"]
- Filter Operator [FIL_349] (rows=36525 width=1119)
+ Filter Operator [FIL_337] (rows=36525 width=1119)
predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
- TableScan [TS_134] (rows=73049 width=1119)
+ TableScan [TS_128] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_year"]
- <-Reducer 53 [SIMPLE_EDGE]
- SHUFFLE [RS_247]
+ <-Reducer 49 [SIMPLE_EDGE]
+ SHUFFLE [RS_235]
PartitionCols:_col0
- Group By Operator [GBY_238] (rows=52799601 width=322)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 52 [SIMPLE_EDGE]
- SHUFFLE [RS_237]
- PartitionCols:_col0
- Group By Operator [GBY_236] (rows=105599202 width=322)
- Output:["_col0"],keys:_col2
- Select Operator [SEL_235] (rows=105599202 width=322)
- Output:["_col2"]
- Filter Operator [FIL_234] (rows=105599202 width=322)
- predicate:(_col3 > (0.95 * _col1))
- Merge Join Operator [MERGEJOIN_383] (rows=316797606 width=322)
- Conds:(Inner),Output:["_col1","_col2","_col3"]
- <-Reducer 51 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_231]
- Merge Join Operator [MERGEJOIN_382] (rows=1 width=233)
- Conds:(Left Outer),Output:["_col1"]
- <-Reducer 50 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_228]
- Select Operator [SEL_186] (rows=1 width=8)
- Filter Operator [FIL_185] (rows=1 width=8)
- predicate:(sq_count_check(_col0) <= 1)
- Group By Operator [GBY_183] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(VALUE._col0)"]
- <-Reducer 49 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_182]
- Group By Operator [GBY_181] (rows=1 width=8)
- Output:["_col0"],aggregations:["count()"]
- Select Operator [SEL_178] (rows=348477374 width=88)
- Group By Operator [GBY_177] (rows=348477374 width=88)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 48 [SIMPLE_EDGE]
- SHUFFLE [RS_176]
- PartitionCols:_col0
- Group By Operator [GBY_175] (rows=696954748 width=88)
- Output:["_col0"],keys:_col0
- Select Operator [SEL_173] (rows=696954748 width=88)
- Output:["_col0"]
- Merge Join Operator [MERGEJOIN_373] (rows=696954748 width=88)
- Conds:RS_170._col1=RS_171._col0(Inner),Output:["_col6"]
- <-Map 55 [SIMPLE_EDGE]
- SHUFFLE [RS_171]
- PartitionCols:_col0
- Select Operator [SEL_166] (rows=80000000 width=860)
- Output:["_col0"]
- Filter Operator [FIL_353] (rows=80000000 width=860)
- predicate:c_customer_sk is not null
- TableScan [TS_164] (rows=80000000 width=860)
- default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
- <-Reducer 47 [SIMPLE_EDGE]
- SHUFFLE [RS_170]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_372] (rows=633595212 width=88)
- Conds:RS_167._col0=RS_168._col0(Inner),Output:["_col1"]
- <-Map 46 [SIMPLE_EDGE]
- SHUFFLE [RS_167]
- PartitionCols:_col0
- Select Operator [SEL_160] (rows=575995635 width=88)
- Output:["_col0","_col1"]
- Filter Operator [FIL_351] (rows=575995635 width=88)
- predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
- TableScan [TS_158] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"]
- <-Map 54 [SIMPLE_EDGE]
- SHUFFLE [RS_168]
- PartitionCols:_col0
- Select Operator [SEL_163] (rows=36525 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_352] (rows=36525 width=1119)
- predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
- TableScan [TS_161] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 60 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_229]
- Group By Operator [GBY_211] (rows=1 width=224)
- Output:["_col0"],aggregations:["max(VALUE._col0)"]
- <-Reducer 59 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_210]
- Group By Operator [GBY_209] (rows=1 width=224)
- Output:["_col0"],aggregations:["max(_col1)"]
- Select Operator [SEL_207] (rows=348477374 width=88)
- Output:["_col1"]
- Group By Operator [GBY_206] (rows=348477374 width=88)
- Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 58 [SIMPLE_EDGE]
- SHUFFLE [RS_205]
- PartitionCols:_col0
- Group By Operator [GBY_204] (rows=696954748 width=88)
- Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
- Select Operator [SEL_202] (rows=696954748 width=88)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_375] (rows=696954748 width=88)
- Conds:RS_199._col1=RS_200._col0(Inner),Output:["_col2","_col3","_col6"]
- <-Map 62 [SIMPLE_EDGE]
- SHUFFLE [RS_200]
- PartitionCols:_col0
- Select Operator [SEL_195] (rows=80000000 width=860)
- Output:["_col0"]
- Filter Operator [FIL_356] (rows=80000000 width=860)
- predicate:c_customer_sk is not null
- TableScan [TS_193] (rows=80000000 width=860)
- default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
- <-Reducer 57 [SIMPLE_EDGE]
- SHUFFLE [RS_199]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_374] (rows=633595212 width=88)
- Conds:RS_196._col0=RS_197._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 56 [SIMPLE_EDGE]
- SHUFFLE [RS_196]
- PartitionCols:_col0
- Select Operator [SEL_189] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_354] (rows=575995635 width=88)
- predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
- TableScan [TS_187] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"]
- <-Map 61 [SIMPLE_EDGE]
- SHUFFLE [RS_197]
- PartitionCols:_col0
- Select Operator [SEL_192] (rows=36525 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_355] (rows=36525 width=1119)
- predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
- TableScan [TS_190] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 65 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_232]
- Group By Operator [GBY_226] (rows=316797606 width=88)
- Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 64 [SIMPLE_EDGE]
- SHUFFLE [RS_225]
- PartitionCols:_col0
- Group By Operator [GBY_224] (rows=633595212 width=88)
- Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
- Select Operator [SEL_222] (rows=633595212 width=88)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_376] (rows=633595212 width=88)
- Conds:RS_219._col0=RS_220._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 63 [SIMPLE_EDGE]
- SHUFFLE [RS_219]
- PartitionCols:_col0
- Select Operator [SEL_215] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_357] (rows=575995635 width=88)
- predicate:ss_customer_sk is not null
- TableScan [TS_213] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"]
- <-Map 66 [SIMPLE_EDGE]
- SHUFFLE [RS_220]
- PartitionCols:_col0
- Select Operator [SEL_218] (rows=80000000 width=860)
+ Select Operator [SEL_227] (rows=105599202 width=321)
+ Output:["_col0"]
+ Filter Operator [FIL_226] (rows=105599202 width=321)
+ predicate:(_col3 > (0.95 * _col1))
+ Merge Join Operator [MERGEJOIN_369] (rows=316797606 width=321)
+ Conds:(Inner),(Inner),Output:["_col1","_col2","_col3"]
+ <-Reducer 48 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_222]
+ Select Operator [SEL_180] (rows=1 width=8)
+ Filter Operator [FIL_179] (rows=1 width=8)
+ predicate:(sq_count_check(_col0) <= 1)
+ Group By Operator [GBY_177] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(VALUE._col0)"]
+ <-Reducer 47 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_176]
+ Group By Operator [GBY_175] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count()"]
+ Select Operator [SEL_172] (rows=348477374 width=88)
+ Group By Operator [GBY_171] (rows=348477374 width=88)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 46 [SIMPLE_EDGE]
+ SHUFFLE [RS_170]
+ PartitionCols:_col0
+ Group By Operator [GBY_169] (rows=696954748 width=88)
+ Output:["_col0"],keys:_col0
+ Select Operator [SEL_167] (rows=696954748 width=88)
Output:["_col0"]
- Filter Operator [FIL_358] (rows=80000000 width=860)
- predicate:c_customer_sk is not null
- TableScan [TS_216] (rows=80000000 width=860)
- default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ Merge Join Operator [MERGEJOIN_361] (rows=696954748 width=88)
+ Conds:RS_164._col1=RS_165._col0(Inner),Output:["_col6"]
+ <-Map 51 [SIMPLE_EDGE]
+ SHUFFLE [RS_165]
+ PartitionCols:_col0
+ Select Operator [SEL_160] (rows=80000000 width=860)
+ Output:["_col0"]
+ Filter Operator [FIL_341] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_158] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ <-Reducer 45 [SIMPLE_EDGE]
+ SHUFFLE [RS_164]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_360] (rows=633595212 width=88)
+ Conds:RS_161._col0=RS_162._col0(Inner),Output:["_col1"]
+ <-Map 44 [SIMPLE_EDGE]
+ SHUFFLE [RS_161]
+ PartitionCols:_col0
+ Select Operator [SEL_154] (rows=575995635 width=88)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_339] (rows=575995635 width=88)
+ predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_152] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"]
+ <-Map 50 [SIMPLE_EDGE]
+ SHUFFLE [RS_162]
+ PartitionCols:_col0
+ Select Operator [SEL_157] (rows=36525 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_340] (rows=36525 width=1119)
+ predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
+ TableScan [TS_155] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 56 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_223]
+ Group By Operator [GBY_205] (rows=1 width=224)
+ Output:["_col0"],aggregations:["max(VALUE._col0)"]
+ <-Reducer 55 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_204]
+ Group By Operator [GBY_203] (rows=1 width=224)
+ Output:["_col0"],aggregations:["max(_col1)"]
+ Select Operator [SEL_201] (rows=348477374 width=88)
+ Output:["_col1"]
+ Group By Operator [GBY_200] (rows=348477374 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 54 [SIMPLE_EDGE]
+ SHUFFLE [RS_199]
+ PartitionCols:_col0
+ Group By Operator [GBY_198] (rows=696954748 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
+ Select Operator [SEL_196] (rows=696954748 width=88)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_363] (rows=696954748 width=88)
+ Conds:RS_193._col1=RS_194._col0(Inner),Output:["_col2","_col3","_col6"]
+ <-Map 58 [SIMPLE_EDGE]
+ SHUFFLE [RS_194]
+ PartitionCols:_col0
+ Select Operator [SEL_189] (rows=80000000 width=860)
+ Output:["_col0"]
+ Filter Operator [FIL_344] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_187] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ <-Reducer 53 [SIMPLE_EDGE]
+ SHUFFLE [RS_193]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_362] (rows=633595212 width=88)
+ Conds:RS_190._col0=RS_191._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 52 [SIMPLE_EDGE]
+ SHUFFLE [RS_190]
+ PartitionCols:_col0
+ Select Operator [SEL_183] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_342] (rows=575995635 width=88)
+ predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_181] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"]
+ <-Map 57 [SIMPLE_EDGE]
+ SHUFFLE [RS_191]
+ PartitionCols:_col0
+ Select Operator [SEL_186] (rows=36525 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_343] (rows=36525 width=1119)
+ predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
+ TableScan [TS_184] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 61 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_224]
+ Group By Operator [GBY_220] (rows=316797606 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 60 [SIMPLE_EDGE]
+ SHUFFLE [RS_219]
+ PartitionCols:_col0
+ Group By Operator [GBY_218] (rows=633595212 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
+ Select Operator [SEL_216] (rows=633595212 width=88)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_364] (rows=633595212 width=88)
+ Conds:RS_213._col0=RS_214._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 59 [SIMPLE_EDGE]
+ SHUFFLE [RS_213]
+ PartitionCols:_col0
+ Select Operator [SEL_209] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_345] (rows=575995635 width=88)
+ predicate:ss_customer_sk is not null
+ TableScan [TS_207] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"]
+ <-Map 62 [SIMPLE_EDGE]
+ SHUFFLE [RS_214]
+ PartitionCols:_col0
+ Select Operator [SEL_212] (rows=80000000 width=860)
+ Output:["_col0"]
+ Filter Operator [FIL_346] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_210] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
<-Reducer 4 [CONTAINS]
- Reduce Output Operator [RS_254]
- Group By Operator [GBY_253] (rows=1 width=112)
+ Reduce Output Operator [RS_242]
+ Group By Operator [GBY_241] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(_col0)"]
- Select Operator [SEL_124] (rows=383314495 width=135)
+ Select Operator [SEL_118] (rows=383314495 width=135)
Output:["_col0"]
- Merge Join Operator [MERGEJOIN_381] (rows=383314495 width=135)
- Conds:RS_121._col1=RS_122._col0(Inner),Output:["_col3","_col4"]
- <-Reducer 21 [SIMPLE_EDGE]
- SHUFFLE [RS_122]
+ Merge Join Operator [MERGEJOIN_368] (rows=383314495 width=135)
+ Conds:RS_115._col1=RS_116._col0(Inner),Output:["_col3","_col4"]
+ <-Reducer 19 [SIMPLE_EDGE]
+ SHUFFLE [RS_116]
PartitionCols:_col0
- Group By Operator [GBY_113] (rows=52799601 width=322)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 20 [SIMPLE_EDGE]
- SHUFFLE [RS_112]
- PartitionCols:_col0
- Group By Operator [GBY_111] (rows=105599202 width=322)
- Output:["_col0"],keys:_col2
- Select Operator [SEL_110] (rows=105599202 width=322)
- Output:["_col2"]
- Filter Operator [FIL_109] (rows=105599202 width=322)
- predicate:(_col3 > (0.95 * _col1))
- Merge Join Operator [MERGEJOIN_380] (rows=316797606 width=322)
- Conds:(Inner),Output:["_col1","_col2","_col3"]
- <-Reducer 19 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_106]
- Merge Join Operator [MERGEJOIN_379] (rows=1 width=233)
- Conds:(Left Outer),Output:["_col1"]
- <-Reducer 18 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_103]
- Select Operator [SEL_61] (rows=1 width=8)
- Filter Operator [FIL_60] (rows=1 width=8)
- predicate:(sq_count_check(_col0) <= 1)
- Group By Operator [GBY_58] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(VALUE._col0)"]
- <-Reducer 17 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_57]
- Group By Operator [GBY_56] (rows=1 width=8)
- Output:["_col0"],aggregations:["count()"]
- Select Operator [SEL_53] (rows=348477374 width=88)
- Group By Operator [GBY_52] (rows=348477374 width=88)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 16 [SIMPLE_EDGE]
- SHUFFLE [RS_51]
- PartitionCols:_col0
- Group By Operator [GBY_50] (rows=696954748 width=88)
- Output:["_col0"],keys:_col0
- Select Operator [SEL_48] (rows=696954748 width=88)
- Output:["_col0"]
- Merge Join Operator [MERGEJOIN_365] (rows=696954748 width=88)
- Conds:RS_45._col1=RS_46._col0(Inner),Output:["_col6"]
- <-Map 23 [SIMPLE_EDGE]
- SHUFFLE [RS_46]
- PartitionCols:_col0
- Select Operator [SEL_41] (rows=80000000 width=860)
- Output:["_col0"]
- Filter Operator [FIL_340] (rows=80000000 width=860)
- predicate:c_customer_sk is not null
- TableScan [TS_39] (rows=80000000 width=860)
- default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
- <-Reducer 15 [SIMPLE_EDGE]
- SHUFFLE [RS_45]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_364] (rows=633595212 width=88)
- Conds:RS_42._col0=RS_43._col0(Inner),Output:["_col1"]
- <-Map 14 [SIMPLE_EDGE]
- SHUFFLE [RS_42]
- PartitionCols:_col0
- Select Operator [SEL_35] (rows=575995635 width=88)
- Output:["_col0","_col1"]
- Filter Operator [FIL_338] (rows=575995635 width=88)
- predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
- TableScan [TS_33] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"]
- <-Map 22 [SIMPLE_EDGE]
- SHUFFLE [RS_43]
- PartitionCols:_col0
- Select Operator [SEL_38] (rows=36525 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_339] (rows=36525 width=1119)
- predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
- TableScan [TS_36] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 28 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_104]
- Group By Operator [GBY_86] (rows=1 width=224)
- Output:["_col0"],aggregations:["max(VALUE._col0)"]
- <-Reducer 27 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_85]
- Group By Operator [GBY_84] (rows=1 width=224)
- Output:["_col0"],aggregations:["max(_col1)"]
- Select Operator [SEL_82] (rows=348477374 width=88)
- Output:["_col1"]
- Group By Operator [GBY_81] (rows=348477374 width=88)
- Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 26 [SIMPLE_EDGE]
- SHUFFLE [RS_80]
- PartitionCols:_col0
- Group By Operator [GBY_79] (rows=696954748 width=88)
- Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
- Select Operator [SEL_77] (rows=696954748 width=88)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_367] (rows=696954748 width=88)
- Conds:RS_74._col1=RS_75._col0(Inner),Output:["_col2","_col3","_col6"]
- <-Map 30 [SIMPLE_EDGE]
- SHUFFLE [RS_75]
- PartitionCols:_col0
- Select Operator [SEL_70] (rows=80000000 width=860)
- Output:["_col0"]
- Filter Operator [FIL_343] (rows=80000000 width=860)
- predicate:c_customer_sk is not null
- TableScan [TS_68] (rows=80000000 width=860)
- default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
- <-Reducer 25 [SIMPLE_EDGE]
- SHUFFLE [RS_74]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_366] (rows=633595212 width=88)
- Conds:RS_71._col0=RS_72._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 24 [SIMPLE_EDGE]
- SHUFFLE [RS_71]
- PartitionCols:_col0
- Select Operator [SEL_64] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_341] (rows=575995635 width=88)
- predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
- TableScan [TS_62] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"]
- <-Map 29 [SIMPLE_EDGE]
- SHUFFLE [RS_72]
- PartitionCols:_col0
- Select Operator [SEL_67] (rows=36525 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_342] (rows=36525 width=1119)
- predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
- TableScan [TS_65] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
- <-Reducer 33 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_107]
- Group By Operator [GBY_101] (rows=316797606 width=88)
- Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 32 [SIMPLE_EDGE]
- SHUFFLE [RS_100]
- PartitionCols:_col0
- Group By Operator [GBY_99] (rows=633595212 width=88)
- Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
- Select Operator [SEL_97] (rows=633595212 width=88)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_368] (rows=633595212 width=88)
- Conds:RS_94._col0=RS_95._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 31 [SIMPLE_EDGE]
- SHUFFLE [RS_94]
- PartitionCols:_col0
- Select Operator [SEL_90] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_344] (rows=575995635 width=88)
- predicate:ss_customer_sk is not null
- TableScan [TS_88] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"]
- <-Map 34 [SIMPLE_EDGE]
- SHUFFLE [RS_95]
- PartitionCols:_col0
- Select Operator [SEL_93] (rows=80000000 width=860)
+ Select Operator [SEL_108] (rows=105599202 width=321)
+ Output:["_col0"]
+ Filter Operator [FIL_107] (rows=105599202 width=321)
+ predicate:(_col3 > (0.95 * _col1))
+ Merge Join Operator [MERGEJOIN_367] (rows=316797606 width=321)
+ Conds:(Inner),(Inner),Output:["_col1","_col2","_col3"]
+ <-Reducer 18 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_103]
+ Select Operator [SEL_61] (rows=1 width=8)
+ Filter Operator [FIL_60] (rows=1 width=8)
+ predicate:(sq_count_check(_col0) <= 1)
+ Group By Operator [GBY_58] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(VALUE._col0)"]
+ <-Reducer 17 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_57]
+ Group By Operator [GBY_56] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count()"]
+ Select Operator [SEL_53] (rows=348477374 width=88)
+ Group By Operator [GBY_52] (rows=348477374 width=88)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 16 [SIMPLE_EDGE]
+ SHUFFLE [RS_51]
+ PartitionCols:_col0
+ Group By Operator [GBY_50] (rows=696954748 width=88)
+ Output:["_col0"],keys:_col0
+ Select Operator [SEL_48] (rows=696954748 width=88)
Output:["_col0"]
- Filter Operator [FIL_345] (rows=80000000 width=860)
- predicate:c_customer_sk is not null
- TableScan [TS_91] (rows=80000000 width=860)
- default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ Merge Join Operator [MERGEJOIN_353] (rows=696954748 width=88)
+ Conds:RS_45._col1=RS_46._col0(Inner),Output:["_col6"]
+ <-Map 21 [SIMPLE_EDGE]
+ SHUFFLE [RS_46]
+ PartitionCols:_col0
+ Select Operator [SEL_41] (rows=80000000 width=860)
+ Output:["_col0"]
+ Filter Operator [FIL_328] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_39] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ <-Reducer 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_45]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_352] (rows=633595212 width=88)
+ Conds:RS_42._col0=RS_43._col0(Inner),Output:["_col1"]
+ <-Map 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_42]
+ PartitionCols:_col0
+ Select Operator [SEL_35] (rows=575995635 width=88)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_326] (rows=575995635 width=88)
+ predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_33] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"]
+ <-Map 20 [SIMPLE_EDGE]
+ SHUFFLE [RS_43]
+ PartitionCols:_col0
+ Select Operator [SEL_38] (rows=36525 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_327] (rows=36525 width=1119)
+ predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
+ TableScan [TS_36] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 26 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_104]
+ Group By Operator [GBY_86] (rows=1 width=224)
+ Output:["_col0"],aggregations:["max(VALUE._col0)"]
+ <-Reducer 25 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_85]
+ Group By Operator [GBY_84] (rows=1 width=224)
+ Output:["_col0"],aggregations:["max(_col1)"]
+ Select Operator [SEL_82] (rows=348477374 width=88)
+ Output:["_col1"]
+ Group By Operator [GBY_81] (rows=348477374 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 24 [SIMPLE_EDGE]
+ SHUFFLE [RS_80]
+ PartitionCols:_col0
+ Group By Operator [GBY_79] (rows=696954748 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
+ Select Operator [SEL_77] (rows=696954748 width=88)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_355] (rows=696954748 width=88)
+ Conds:RS_74._col1=RS_75._col0(Inner),Output:["_col2","_col3","_col6"]
+ <-Map 28 [SIMPLE_EDGE]
+ SHUFFLE [RS_75]
+ PartitionCols:_col0
+ Select Operator [SEL_70] (rows=80000000 width=860)
+ Output:["_col0"]
+ Filter Operator [FIL_331] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_68] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ <-Reducer 23 [SIMPLE_EDGE]
+ SHUFFLE [RS_74]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_354] (rows=633595212 width=88)
+ Conds:RS_71._col0=RS_72._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 22 [SIMPLE_EDGE]
+ SHUFFLE [RS_71]
+ PartitionCols:_col0
+ Select Operator [SEL_64] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_329] (rows=575995635 width=88)
+ predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_62] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"]
+ <-Map 27 [SIMPLE_EDGE]
+ SHUFFLE [RS_72]
+ PartitionCols:_col0
+ Select Operator [SEL_67] (rows=36525 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_330] (rows=36525 width=1119)
+ predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
+ TableScan [TS_65] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 31 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_105]
+ Group By Operator [GBY_101] (rows=316797606 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 30 [SIMPLE_EDGE]
+ SHUFFLE [RS_100]
+ PartitionCols:_col0
+ Group By Operator [GBY_99] (rows=633595212 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
+ Select Operator [SEL_97] (rows=633595212 width=88)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_356] (rows=633595212 width=88)
+ Conds:RS_94._col0=RS_95._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 29 [SIMPLE_EDGE]
+ SHUFFLE [RS_94]
+ PartitionCols:_col0
+ Select Operator [SEL_90] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_332] (rows=575995635 width=88)
+ predicate:ss_customer_sk is not null
+ TableScan [TS_88] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"]
+ <-Map 32 [SIMPLE_EDGE]
+ SHUFFLE [RS_95]
+ PartitionCols:_col0
+ Select Operator [SEL_93] (rows=80000000 width=860)
+ Output:["_col0"]
+ Filter Operator [FIL_333] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_91] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
<-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_121]
+ SHUFFLE [RS_115]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_377] (rows=348467716 width=135)
- Conds:RS_118._col2=RS_119._col0(Inner),Output:["_col1","_col3","_col4"]
+ Merge Join Operator [MERGEJOIN_365] (rows=348467716 width=135)
+ Conds:RS_112._col2=RS_113._col0(Inner),Output:["_col1","_col3","_col4"]
<-Reducer 11 [SIMPLE_EDGE]
- SHUFFLE [RS_119]
+ SHUFFLE [RS_113]
PartitionCols:_col0
Group By Operator [GBY_31] (rows=58079562 width=88)
Output:["_col0"],keys:_col1
@@ -586,7 +558,7 @@ Stage-0
Output:["_col1"]
Filter Operator [FIL_26] (rows=116159124 width=88)
predicate:(_col3 > 4)
- Select Operator [SEL_359] (rows=348477374 width=88)
+ Select Operator [SEL_347] (rows=348477374 width=88)
Output:["_col0","_col3"]
Group By Operator [GBY_25] (rows=348477374 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
@@ -597,28 +569,28 @@ Stage-0
Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2
Select Operator [SEL_21] (rows=696954748 width=88)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_363] (rows=696954748 width=88)
+ Merge Join Operator [MERGEJOIN_351] (rows=696954748 width=88)
Conds:RS_18._col1=RS_19._col0(Inner),Output:["_col3","_col5","_col6"]
<-Map 13 [SIMPLE_EDGE]
SHUFFLE [RS_19]
PartitionCols:_col0
Select Operator [SEL_14] (rows=462000 width=1436)
Output:["_col0","_col1"]
- Filter Operator [FIL_337] (rows=462000 width=1436)
+ Filter Operator [FIL_325] (rows=462000 width=1436)
predicate:i_item_sk is not null
TableScan [TS_12] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_desc"]
<-Reducer 9 [SIMPLE_EDGE]
SHUFFLE [RS_18]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_362] (rows=633595212 width=88)
+ Merge Join Operator [MERGEJOIN_350] (rows=633595212 width=88)
Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col1","_col3"]
<-Map 12 [SIMPLE_EDGE]
SHUFFLE [RS_16]
PartitionCols:_col0
Select Operator [SEL_11] (rows=36525 width=1119)
Output:["_col0","_col1"]
- Filter Operator [FIL_336] (rows=36525 width=1119)
+ Filter Operator [FIL_324] (rows=36525 width=1119)
predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
TableScan [TS_9] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_year"]
@@ -627,30 +599,30 @@ Stage-0
PartitionCols:_col0
Select Operator [SEL_8] (rows=575995635 width=88)
Output:["_col0","_col1"]
- Filter Operator [FIL_335] (rows=575995635 width=88)
+ Filter Operator [FIL_323] (rows=575995635 width=88)
predicate:(ss_sold_date_sk is not null and ss_item_sk is not null)
TableScan [TS_6] (rows=575995635 width=88)
default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk"]
<-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_118]
+ SHUFFLE [RS_112]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_361] (rows=316788826 width=135)
- Conds:RS_115._col0=RS_116._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
+ Merge Join Operator [MERGEJOIN_349] (rows=316788826 width=135)
+ Conds:RS_109._col0=RS_110._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
<-Map 1 [SIMPLE_EDGE]
- SHUFFLE [RS_115]
+ SHUFFLE [RS_109]
PartitionCols:_col0
Select Operator [SEL_2] (rows=287989836 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_333] (rows=287989836 width=135)
+ Filter Operator [FIL_321] (rows=287989836 width=135)
predicate:(cs_item_sk is not null and cs_bill_customer_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_bill_customer_sk","cs_item_sk","cs_quantity","cs_list_price"]
<-Map 7 [SIMPLE_EDGE]
- SHUFFLE [RS_116]
+ SHUFFLE [RS_110]
PartitionCols:_col0
Select Operator [SEL_5] (rows=18262 width=1119)
Output:["_col0"]
- Filter Operator [FIL_334] (rows=18262 width=1119)
+ Filter Operator [FIL_322] (rows=18262 width=1119)
predicate:((d_year = 1999) and (d_moy = 1) 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"]
diff --git a/ql/src/test/results/clientpositive/perf/query30.q.out b/ql/src/test/results/clientpositive/perf/query30.q.out
index 3f30bca..72871f4 100644
--- a/ql/src/test/results/clientpositive/perf/query30.q.out
+++ b/ql/src/test/results/clientpositive/perf/query30.q.out
@@ -95,28 +95,28 @@ Stage-0
<-Reducer 23 [SIMPLE_EDGE]
SHUFFLE [RS_94]
PartitionCols:_col2
- Select Operator [SEL_92] (rows=5500000 width=1014)
+ Select Operator [SEL_92] (rows=11000000 width=1014)
Output:["_col0","_col1","_col2"]
- Group By Operator [GBY_91] (rows=5500000 width=1014)
+ Group By Operator [GBY_91] (rows=11000000 width=1014)
Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col0
- Select Operator [SEL_87] (rows=11000000 width=1014)
+ Select Operator [SEL_87] (rows=22000000 width=1014)
Output:["_col0","_col2"]
- Group By Operator [GBY_86] (rows=11000000 width=1014)
+ Group By Operator [GBY_86] (rows=22000000 width=1014)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
<-Reducer 22 [SIMPLE_EDGE]
SHUFFLE [RS_85]
PartitionCols:_col0
- Group By Operator [GBY_84] (rows=22000000 width=1014)
+ Group By Operator [GBY_84] (rows=44000000 width=1014)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1
- Merge Join Operator [MERGEJOIN_150] (rows=22000000 width=1014)
+ Merge Join Operator [MERGEJOIN_150] (rows=44000000 width=1014)
Conds:RS_80._col2=RS_81._col0(Inner),Output:["_col1","_col3","_col7"]
<-Map 25 [SIMPLE_EDGE]
SHUFFLE [RS_81]
PartitionCols:_col0
- Select Operator [SEL_76] (rows=20000000 width=1014)
+ Select Operator [SEL_76] (rows=40000000 width=1014)
Output:["_col0","_col1"]
- Filter Operator [FIL_143] (rows=20000000 width=1014)
- predicate:((ca_state = ca_state) and ca_address_sk is not null)
+ Filter Operator [FIL_143] (rows=40000000 width=1014)
+ predicate:(ca_address_sk is not null and ca_state is not null)
TableScan [TS_74] (rows=40000000 width=1014)
default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"]
<-Reducer 21 [SIMPLE_EDGE]
@@ -203,32 +203,32 @@ Stage-0
<-Reducer 17 [SIMPLE_EDGE]
SHUFFLE [RS_58]
PartitionCols:_col0
- Select Operator [SEL_56] (rows=916666 width=1014)
+ Select Operator [SEL_56] (rows=1833333 width=1014)
Output:["_col0"]
- Filter Operator [FIL_55] (rows=916666 width=1014)
+ Filter Operator [FIL_55] (rows=1833333 width=1014)
predicate:(sq_count_check(_col1) <= 1)
- Group By Operator [GBY_54] (rows=2750000 width=1014)
+ Group By Operator [GBY_54] (rows=5500000 width=1014)
Output:["_col0","_col1"],aggregations:["count()"],keys:_col0
- Group By Operator [GBY_49] (rows=5500000 width=1014)
+ Group By Operator [GBY_49] (rows=11000000 width=1014)
Output:["_col0"],keys:_col0
- Select Operator [SEL_45] (rows=11000000 width=1014)
+ Select Operator [SEL_45] (rows=22000000 width=1014)
Output:["_col0"]
- Group By Operator [GBY_44] (rows=11000000 width=1014)
+ Group By Operator [GBY_44] (rows=22000000 width=1014)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
<-Reducer 16 [SIMPLE_EDGE]
SHUFFLE [RS_43]
PartitionCols:_col0
- Group By Operator [GBY_42] (rows=22000000 width=1014)
+ Group By Operator [GBY_42] (rows=44000000 width=1014)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1
- Merge Join Operator [MERGEJOIN_148] (rows=22000000 width=1014)
+ Merge Join Operator [MERGEJOIN_148] (rows=44000000 width=1014)
Conds:RS_38._col2=RS_39._col0(Inner),Output:["_col1","_col3","_col7"]
<-Map 19 [SIMPLE_EDGE]
SHUFFLE [RS_39]
PartitionCols:_col0
- Select Operator [SEL_34] (rows=20000000 width=1014)
+ Select Operator [SEL_34] (rows=40000000 width=1014)
Output:["_col0","_col1"]
- Filter Operator [FIL_140] (rows=20000000 width=1014)
- predicate:((ca_state = ca_state) and ca_address_sk is not null)
+ Filter Operator [FIL_140] (rows=40000000 width=1014)
+ predicate:(ca_address_sk is not null and ca_state is not null)
TableScan [TS_32] (rows=40000000 width=1014)
default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"]
<-Reducer 15 [SIMPLE_EDGE]
diff --git a/ql/src/test/results/clientpositive/perf/query31.q.out b/ql/src/test/results/clientpositive/perf/query31.q.out
index dd21d5c..4de6eb6 100644
--- a/ql/src/test/results/clientpositive/perf/query31.q.out
+++ b/ql/src/test/results/clientpositive/perf/query31.q.out
@@ -2,324 +2,308 @@ PREHOOK: query: explain with ss as (select ca_county,d_qoy, d_year,sum(ss_ext_sa
PREHOOK: type: QUERY
POSTHOOK: query: explain with ss as (select ca_county,d_qoy, d_year,sum(ss_ext_sales_price) as store_sales from store_sales,date_dim,customer_address where ss_sold_date_sk = d_date_sk and ss_addr_sk=ca_address_sk group by ca_county,d_qoy, d_year), ws as (select ca_county,d_qoy, d_year,sum(ws_ext_sales_price) as web_sales from web_sales,date_dim,customer_address where ws_sold_date_sk = d_date_sk and ws_bill_addr_sk=ca_address_sk group by ca_county,d_qoy, d_year) select ss1.ca_county ,ss1.d_year ,ws2.web_sales/ws1.web_sales web_q1_q2_increase ,ss2.store_sales/ss1.store_sales store_q1_q2_increase ,ws3.web_sales/ws2.web_sales web_q2_q3_increase ,ss3.store_sales/ss2.store_sales store_q2_q3_increase from ss ss1 ,ss ss2 ,ss ss3 ,ws ws1 ,ws ws2 ,ws ws3 where ss1.d_qoy = 1 and ss1.d_year = 1998 and ss1.ca_county = ss2.ca_county and ss2.d_qoy = 2 and ss2.d_year = 1998 and ss2.ca_county = ss3.ca_county and ss3.d_qoy = 3 and ss3.d_year = 1998 and ss1.ca_county = ws1.ca_county and ws1.d_qoy = 1 and ws1.d_year = 1998 and ws1.ca_county = ws2.ca_county and ws2.d_qoy = 2 and ws2.d_year = 1998 and ws1.ca_county = ws3.ca_county and ws3.d_qoy = 3 and ws3.d_year =1998 and case when ws1.web_sales > 0 then ws2.web_sales/ws1.web_sales else null end > case when ss1.store_sales > 0 then ss2.store_sales/ss1.store_sales else null end and case when ws2.web_sales > 0 then ws3.web_sales/ws2.web_sales else null end > case when ss2.store_sales > 0 then ss3.store_sales/ss2.store_sales else null end order by web_q1_q2_increase
POSTHOOK: type: QUERY
-Plan optimized by CBO.
+Plan not optimized by CBO.
Vertex dependency in root stage
-Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE)
-Reducer 12 <- Map 15 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE)
-Reducer 13 <- Reducer 12 (SIMPLE_EDGE)
-Reducer 17 <- Map 16 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE)
-Reducer 18 <- Map 21 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE)
-Reducer 19 <- Reducer 18 (SIMPLE_EDGE)
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
-Reducer 23 <- Map 22 (SIMPLE_EDGE), Map 27 (SIMPLE_EDGE)
-Reducer 24 <- Map 28 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE)
-Reducer 25 <- Reducer 24 (SIMPLE_EDGE)
-Reducer 26 <- Reducer 25 (SIMPLE_EDGE), Reducer 32 (SIMPLE_EDGE)
-Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 30 <- Map 29 (SIMPLE_EDGE), Map 33 (SIMPLE_EDGE)
-Reducer 31 <- Map 34 (SIMPLE_EDGE), Reducer 30 (SIMPLE_EDGE)
-Reducer 32 <- Reducer 31 (SIMPLE_EDGE)
-Reducer 36 <- Map 35 (SIMPLE_EDGE), Map 39 (SIMPLE_EDGE)
-Reducer 37 <- Map 40 (SIMPLE_EDGE), Reducer 36 (SIMPLE_EDGE)
-Reducer 38 <- Reducer 37 (SIMPLE_EDGE)
+Reducer 10 <- Map 13 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE)
+Reducer 11 <- Map 14 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE)
+Reducer 12 <- Reducer 11 (SIMPLE_EDGE)
+Reducer 16 <- Map 15 (SIMPLE_EDGE), Map 19 (SIMPLE_EDGE)
+Reducer 17 <- Map 20 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE)
+Reducer 18 <- Reducer 17 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
+Reducer 22 <- Map 21 (SIMPLE_EDGE), Map 25 (SIMPLE_EDGE)
+Reducer 23 <- Map 26 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE)
+Reducer 24 <- Reducer 23 (SIMPLE_EDGE)
+Reducer 28 <- Map 27 (SIMPLE_EDGE), Map 31 (SIMPLE_EDGE)
+Reducer 29 <- Map 32 (SIMPLE_EDGE), Reducer 28 (SIMPLE_EDGE)
+Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 30 <- Reducer 29 (SIMPLE_EDGE)
+Reducer 34 <- Map 33 (SIMPLE_EDGE), Map 37 (SIMPLE_EDGE)
+Reducer 35 <- Map 38 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE)
+Reducer 36 <- Reducer 35 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
-Reducer 5 <- Reducer 13 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
-Reducer 6 <- Reducer 38 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
-Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
+Reducer 5 <- Reducer 12 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE), Reducer 30 (SIMPLE_EDGE), Reducer 36 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
- Reducer 7
- File Output Operator [FS_140]
- Select Operator [SEL_139] (rows=316243230 width=88)
+ Reducer 6
+ File Output Operator [FS_256]
+ Select Operator [SEL_255] (rows=1663737 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- <-Reducer 6 [SIMPLE_EDGE]
- SHUFFLE [RS_138]
- Select Operator [SEL_137] (rows=316243230 width=88)
+ <-Reducer 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_254]
+ Select Operator [SEL_253] (rows=1663737 width=88)
Output:["_col0","_col2","_col3","_col4","_col5"]
- 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_272] (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]
+ Filter Operator [FIL_377] (rows=1663737 width=88)
+ predicate:((_col0 = _col4) and (_col0 = _col12) and (CASE WHEN ((_col15 > 0)) THEN ((_col19 / _col15)) ELSE (null) END > CASE WHEN ((_col3 > 0)) THEN ((_col7 / _col3)) ELSE (null) END) and (CASE WHEN ((_col19 > 0)) THEN ((_col23 / _col19)) ELSE (null) END > CASE WHEN ((_col7 > 0)) THEN ((_col11 / _col7)) ELSE (null) END) and (_col4 = _col8) and (_col12 = _col16) and (_col12 = _col20))
+ Merge Join Operator [MERGEJOIN_414] (rows=479156396 width=88)
+ Conds:RS_240._col0=RS_242._col0(Inner),RS_242._col0=RS_244._col0(Inner),RS_240._col0=RS_246._col0(Inner),RS_246._col0=RS_248._col0(Inner),RS_246._col0=RS_250._col0(Inner),Output:["_col0","_col3","_col4","_col7","_col8","_col11","_col12","_col15","_col16","_col19","_col20","_col23"]
+ <-Reducer 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_242]
PartitionCols:_col0
- Group By Operator [GBY_130] (rows=87121617 width=135)
- Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 37 [SIMPLE_EDGE]
- SHUFFLE [RS_129]
- PartitionCols:_col0
- Group By Operator [GBY_128] (rows=174243235 width=135)
- Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7
- Merge Join Operator [MERGEJOIN_269] (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_257] (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_268] (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_255] (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_256] (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_271] (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
- Merge Join Operator [MERGEJOIN_261] (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_245] (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_260] (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_243] (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_244] (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
- Merge Join Operator [MERGEJOIN_263] (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_248] (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_262] (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_246] (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_247] (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_270] (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
- Merge Join Operator [MERGEJOIN_265] (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_251] (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_264] (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_249] (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_250] (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
- Merge Join Operator [MERGEJOIN_267] (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_254] (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_266] (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_252] (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_253] (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
- Merge Join Operator [MERGEJOIN_259] (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_242] (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_258] (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_240] (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_241] (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"]
+ Select Operator [SEL_162] (rows=87119343 width=88)
+ Output:["_col0","_col3"]
+ Group By Operator [GBY_161] (rows=87119343 width=88)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, 2, 1998
+ <-Reducer 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_160]
+ PartitionCols:_col0, 2, 1998
+ Group By Operator [GBY_159] (rows=174238687 width=88)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col15)"],keys:_col64, 2, 1998
+ Select Operator [SEL_158] (rows=174238687 width=88)
+ Output:["_col15","_col64"]
+ Filter Operator [FIL_382] (rows=174238687 width=88)
+ predicate:((_col0 = _col26) and (_col6 = _col57))
+ Merge Join Operator [MERGEJOIN_405] (rows=696954748 width=88)
+ Conds:RS_153._col6=RS_155.ca_address_sk(Inner),Output:["_col0","_col6","_col15","_col26","_col57","_col64"]
+ <-Map 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_155]
+ PartitionCols:ca_address_sk
+ Filter Operator [FIL_385] (rows=40000000 width=1014)
+ predicate:(ca_address_sk is not null and ca_county is not null)
+ TableScan [TS_146] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"]
+ <-Reducer 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_153]
+ PartitionCols:_col6
+ Merge Join Operator [MERGEJOIN_404] (rows=633595212 width=88)
+ Conds:RS_148.ss_sold_date_sk=RS_150.d_date_sk(Inner),Output:["_col0","_col6","_col15","_col26"]
+ <-Map 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_150]
+ PartitionCols:d_date_sk
+ Filter Operator [FIL_384] (rows=18262 width=1119)
+ predicate:(d_date_sk is not null and (d_qoy = 2) and (d_year = 1998))
+ TableScan [TS_145] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"]
+ <-Map 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_148]
+ PartitionCols:ss_sold_date_sk
+ Filter Operator [FIL_383] (rows=575995635 width=88)
+ predicate:(ss_sold_date_sk is not null and ss_addr_sk is not null)
+ TableScan [TS_144] (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"]
+ <-Reducer 18 [SIMPLE_EDGE]
+ SHUFFLE [RS_244]
+ PartitionCols:_col0
+ Select Operator [SEL_181] (rows=87119343 width=88)
+ Output:["_col0","_col3"]
+ Group By Operator [GBY_180] (rows=87119343 width=88)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, 3, 1998
+ <-Reducer 17 [SIMPLE_EDGE]
+ SHUFFLE [RS_179]
+ PartitionCols:_col0, 3, 1998
+ Group By Operator [GBY_178] (rows=174238687 width=88)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col15)"],keys:_col64, 3, 1998
+ Select Operator [SEL_177] (rows=174238687 width=88)
+ Output:["_col15","_col64"]
+ Filter Operator [FIL_386] (rows=174238687 width=88)
+ predicate:((_col0 = _col26) and (_col6 = _col57))
+ Merge Join Operator [MERGEJOIN_407] (rows=696954748 width=88)
+ Conds:RS_172._col6=RS_174.ca_address_sk(Inner),Output:["_col0","_col6","_col15","_col26","_col57","_col64"]
+ <-Map 20 [SIMPLE_EDGE]
+ SHUFFLE [RS_174]
+ PartitionCols:ca_address_sk
+ Filter Operator [FIL_389] (rows=40000000 width=1014)
+ predicate:(ca_address_sk is not null and ca_county is not null)
+ TableScan [TS_165] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"]
+ <-Reducer 16 [SIMPLE_EDGE]
+ SHUFFLE [RS_172]
+ PartitionCols:_col6
+ Merge Join Operator [MERGEJOIN_406] (rows=633595212 width=88)
+ Conds:RS_167.ss_sold_date_sk=RS_169.d_date_sk(Inner),Output:["_col0","_col6","_col15","_col26"]
+ <-Map 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_167]
+ PartitionCols:ss_sold_date_sk
+ Filter Operator [FIL_387] (rows=575995635 width=88)
+ predicate:(ss_sold_date_sk is not null and ss_addr_sk is not null)
+ TableScan [TS_163] (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 19 [SIMPLE_EDGE]
+ SHUFFLE [RS_169]
+ PartitionCols:d_date_sk
+ Filter Operator [FIL_388] (rows=18262 width=1119)
+ predicate:(d_date_sk is not null and (d_qoy = 3) and (d_year = 1998))
+ TableScan [TS_164] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"]
+ <-Reducer 24 [SIMPLE_EDGE]
+ SHUFFLE [RS_246]
+ PartitionCols:_col0
+ Select Operator [SEL_200] (rows=21780404 width=135)
+ Output:["_col0","_col3"]
+ Group By Operator [GBY_199] (rows=21780404 width=135)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, 1, 1998
+ <-Reducer 23 [SIMPLE_EDGE]
+ SHUFFLE [RS_198]
+ PartitionCols:_col0, 1, 1998
+ Group By Operator [GBY_197] (rows=43560808 width=135)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col23)"],keys:_col75, 1, 1998
+ Select Operator [SEL_196] (rows=43560808 width=135)
+ Output:["_col23","_col75"]
+ Filter Operator [FIL_390] (rows=43560808 width=135)
+ predicate:((_col0 = _col37) and (_col7 = _col68))
+ Merge Join Operator [MERGEJOIN_409] (rows=174243235 width=135)
+ Conds:RS_191._col7=RS_193.ca_address_sk(Inner),Output:["_col0","_col7","_col23","_col37","_col68","_col75"]
+ <-Map 26 [SIMPLE_EDGE]
+ SHUFFLE [RS_193]
+ PartitionCols:ca_address_sk
+ Filter Operator [FIL_393] (rows=40000000 width=1014)
+ predicate:(ca_address_sk is not null and ca_county is not null)
+ TableScan [TS_184] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"]
+ <-Reducer 22 [SIMPLE_EDGE]
+ SHUFFLE [RS_191]
+ PartitionCols:_col7
+ Merge Join Operator [MERGEJOIN_408] (rows=158402938 width=135)
+ Conds:RS_186.ws_sold_date_sk=RS_188.d_date_sk(Inner),Output:["_col0","_col7","_col23","_col37"]
+ <-Map 21 [SIMPLE_EDGE]
+ SHUFFLE [RS_186]
+ PartitionCols:ws_sold_date_sk
+ Filter Operator [FIL_391] (rows=144002668 width=135)
+ predicate:(ws_sold_date_sk is not null and ws_bill_addr_sk is not null)
+ TableScan [TS_182] (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 25 [SIMPLE_EDGE]
+ SHUFFLE [RS_188]
+ PartitionCols:d_date_sk
+ Filter Operator [FIL_392] (rows=18262 width=1119)
+ predicate:(d_date_sk is not null and (d_qoy = 1) and (d_year = 1998))
+ TableScan [TS_183] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"]
+ <-Reducer 30 [SIMPLE_EDGE]
+ SHUFFLE [RS_248]
+ PartitionCols:_col0
+ Select Operator [SEL_219] (rows=21780404 width=135)
+ Output:["_col0","_col3"]
+ Group By Operator [GBY_218] (rows=21780404 width=135)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, 2, 1998
+ <-Reducer 29 [SIMPLE_EDGE]
+ SHUFFLE [RS_217]
+ PartitionCols:_col0, 2, 1998
+ Group By Operator [GBY_216] (rows=43560808 width=135)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col23)"],keys:_col75, 2, 1998
+ Select Operator [SEL_215] (rows=43560808 width=135)
+ Output:["_col23","_col75"]
+ Filter Operator [FIL_394] (rows=43560808 width=135)
+ predicate:((_col0 = _col37) and (_col7 = _col68))
+ Merge Join Operator [MERGEJOIN_411] (rows=174243235 width=135)
+ Conds:RS_210._col7=RS_212.ca_address_sk(Inner),Output:["_col0","_col7","_col23","_col37","_col68","_col75"]
+ <-Map 32 [SIMPLE_EDGE]
+ SHUFFLE [RS_212]
+ PartitionCols:ca_address_sk
+ Filter Operator [FIL_397] (rows=40000000 width=1014)
+ predicate:(ca_address_sk is not null and ca_county is not null)
+ TableScan [TS_203] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"]
+ <-Reducer 28 [SIMPLE_EDGE]
+ SHUFFLE [RS_210]
+ PartitionCols:_col7
+ Merge Join Operator [MERGEJOIN_410] (rows=158402938 width=135)
+ Conds:RS_205.ws_sold_date_sk=RS_207.d_date_sk(Inner),Output:["_col0","_col7","_col23","_col37"]
+ <-Map 27 [SIMPLE_EDGE]
+ SHUFFLE [RS_205]
+ PartitionCols:ws_sold_date_sk
+ Filter Operator [FIL_395] (rows=144002668 width=135)
+ predicate:(ws_sold_date_sk is not null and ws_bill_addr_sk is not null)
+ TableScan [TS_201] (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 31 [SIMPLE_EDGE]
+ SHUFFLE [RS_207]
+ PartitionCols:d_date_sk
+ Filter Operator [FIL_396] (rows=18262 width=1119)
+ predicate:(d_date_sk is not null and (d_qoy = 2) and (d_year = 1998))
+ TableScan [TS_202] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"]
+ <-Reducer 36 [SIMPLE_EDGE]
+ SHUFFLE [RS_250]
+ PartitionCols:_col0
+ Select Operator [SEL_238] (rows=21780404 width=135)
+ Output:["_col0","_col3"]
+ Group By Operator [GBY_237] (rows=21780404 width=135)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, 3, 1998
+ <-Reducer 35 [SIMPLE_EDGE]
+ SHUFFLE [RS_236]
+ PartitionCols:_col0, 3, 1998
+ Group By Operator [GBY_235] (rows=43560808 width=135)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col23)"],keys:_col75, 3, 1998
+ Select Operator [SEL_234] (rows=43560808 width=135)
+ Output:["_col23","_col75"]
+ Filter Operator [FIL_398] (rows=43560808 width=135)
+ predicate:((_col0 = _col37) and (_col7 = _col68))
+ Merge Join Operator [MERGEJOIN_413] (rows=174243235 width=135)
+ Conds:RS_229._col7=RS_231.ca_address_sk(Inner),Output:["_col0","_col7","_col23","_col37","_col68","_col75"]
+ <-Map 38 [SIMPLE_EDGE]
+ SHUFFLE [RS_231]
+ PartitionCols:ca_address_sk
+ Filter Operator [FIL_401] (rows=40000000 width=1014)
+ predicate:(ca_address_sk is not null and ca_county is not null)
+ TableScan [TS_222] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"]
+ <-Reducer 34 [SIMPLE_EDGE]
+ SHUFFLE [RS_229]
+ PartitionCols:_col7
+ Merge Join Operator [MERGEJOIN_412] (rows=158402938 width=135)
+ Conds:RS_224.ws_sold_date_sk=RS_226.d_date_sk(Inner),Output:["_col0","_col7","_col23","_col37"]
+ <-Map 33 [SIMPLE_EDGE]
+ SHUFFLE [RS_224]
+ PartitionCols:ws_sold_date_sk
+ Filter Operator [FIL_399] (rows=144002668 width=135)
+ predicate:(ws_sold_date_sk is not null and ws_bill_addr_sk is not null)
+ TableScan [TS_220] (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 37 [SIMPLE_EDGE]
+ SHUFFLE [RS_226]
+ PartitionCols:d_date_sk
+ Filter Operator [FIL_400] (rows=18262 width=1119)
+ predicate:(d_date_sk is not null and (d_qoy = 3) and (d_year = 1998))
+ TableScan [TS_221] (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_240]
+ PartitionCols:_col0
+ Select Operator [SEL_143] (rows=87119343 width=88)
+ Output:["_col0","_col3"]
+ Group By Operator [GBY_142] (rows=87119343 width=88)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, 1, 1998
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_141]
+ PartitionCols:_col0, 1, 1998
+ Group By Operator [GBY_140] (rows=174238687 width=88)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col15)"],keys:_col64, 1, 1998
+ Select Operator [SEL_139] (rows=174238687 width=88)
+ Output:["_col15","_col64"]
+ Filter Operator [FIL_378] (rows=174238687 width=88)
+ predicate:((_col0 = _col26) and (_col6 = _col57))
+ Merge Join Operator [MERGEJOIN_403] (rows=696954748 width=88)
+ Conds:RS_134._col6=RS_136.ca_address_sk(Inner),Output:["_col0","_col6","_col15","_col26","_col57","_col64"]
+ <-Map 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_136]
+ PartitionCols:ca_address_sk
+ Filter Operator [FIL_381] (rows=40000000 width=1014)
+ predicate:(ca_address_sk is not null and ca_county is not null)
+ TableScan [TS_127] (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_134]
+ PartitionCols:_col6
+ Merge Join Operator [MERGEJOIN_402] (rows=633595212 width=88)
+ Conds:RS_129.ss_sold_date_sk=RS_131.d_date_sk(Inner),Output:["_col0","_col6","_col15","_col26"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_129]
+ PartitionCols:ss_sold_date_sk
+ Filter Operator [FIL_379] (rows=575995635 width=88)
+ predicate:(ss_sold_date_sk is not null and ss_addr_sk is not null)
+ TableScan [TS_125] (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 7 [SIMPLE_EDGE]
+ SHUFFLE [RS_131]
+ PartitionCols:d_date_sk
+ Filter Operator [FIL_380] (rows=18262 width=1119)
+ predicate:(d_date_sk is not null and (d_qoy = 1) and (d_year = 1998))
+ TableScan [TS_126] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"]
diff --git a/ql/src/test/results/clientpositive/perf/query32.q.out b/ql/src/test/results/clientpositive/perf/query32.q.out
index 6311054..5a6514b 100644
--- a/ql/src/test/results/clientpositive/perf/query32.q.out
+++ b/ql/src/test/results/clientpositive/perf/query32.q.out
@@ -50,85 +50,83 @@ Stage-0
limit:-1
Stage-1
Reducer 5
- File Output Operator [FS_38]
- Group By Operator [GBY_36] (rows=1 width=112)
+ File Output Operator [FS_37]
+ Group By Operator [GBY_35] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(VALUE._col0)"]
<-Reducer 4 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_35]
- Group By Operator [GBY_34] (rows=1 width=112)
- Output:["_col0"],aggregations:["sum(_col1)"]
- Select Operator [SEL_33] (rows=232311810 width=135)
- Output:["_col1"]
- Filter Operator [FIL_32] (rows=232311810 width=135)
- predicate:(_col1 > _col5)
- Select Operator [SEL_31] (rows=696935432 width=135)
- Output:["_col1","_col5"]
- Merge Join Operator [MERGEJOIN_60] (rows=696935432 width=135)
- Conds:RS_27._col0=RS_28._col0(Inner),RS_28._col0=RS_29._col0(Inner),Output:["_col1","_col5"]
- <-Map 7 [SIMPLE_EDGE]
- SHUFFLE [RS_28]
- PartitionCols:_col0
- Select Operator [SEL_16] (rows=231000 width=1436)
- Output:["_col0"]
- Filter Operator [FIL_55] (rows=231000 width=1436)
- predicate:((i_manufact_id = 436) and i_item_sk is not null)
- TableScan [TS_14] (rows=462000 width=1436)
- default@item,i,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_manufact_id"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_27]
- PartitionCols:_col0
- Select Operator [SEL_13] (rows=158394413 width=135)
- Output:["_col0","_col1"]
- Group By Operator [GBY_12] (rows=158394413 width=135)
- Output:["_col0","_col1"],aggregations:["avg(VALUE._col0)"],keys:KEY._col0
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_11]
- PartitionCols:_col0
- Group By Operator [GBY_10] (rows=316788826 width=135)
- Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col1
- Merge Join Operator [MERGEJOIN_58] (rows=316788826 width=135)
- Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col1","_col2"]
- <-Map 1 [SIMPLE_EDGE]
- SHUFFLE [RS_6]
- PartitionCols:_col0
- Select Operator [SEL_2] (rows=287989836 width=135)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_53] (rows=287989836 width=135)
- predicate:(cs_sold_date_sk is not null and cs_item_sk is not null)
- TableScan [TS_0] (rows=287989836 width=135)
- default@catalog_sales,cs,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_discount_amt"]
- <-Map 6 [SIMPLE_EDGE]
- SHUFFLE [RS_7]
- PartitionCols:_col0
- Select Operator [SEL_5] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_54] (rows=8116 width=1119)
- predicate:(d_date BETWEEN '2000-01-27' AND '2000-04-27' and d_date_sk is not null)
- TableScan [TS_3] (rows=73049 width=1119)
- default@date_dim,d,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
- <-Reducer 9 [SIMPLE_EDGE]
- SHUFFLE [RS_29]
- PartitionCols:_col0
- Select Operator [SEL_26] (rows=316788826 width=135)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_59] (rows=316788826 width=135)
- Conds:RS_23._col0=RS_24._col0(Inner),Output:["_col1","_col2"]
- <-Map 10 [SIMPLE_EDGE]
- SHUFFLE [RS_24]
- PartitionCols:_col0
- Select Operator [SEL_22] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_57] (rows=8116 width=1119)
- predicate:(d_date BETWEEN '2000-01-27' AND '2000-04-27' and d_date_sk is not null)
- TableScan [TS_20] (rows=73049 width=1119)
- default@date_dim,d,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
- <-Map 8 [SIMPLE_EDGE]
- SHUFFLE [RS_23]
- PartitionCols:_col0
- Select Operator [SEL_19] (rows=287989836 width=135)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_56] (rows=287989836 width=135)
- predicate:(cs_sold_date_sk is not null and cs_item_sk is not null)
- TableScan [TS_17] (rows=287989836 width=135)
- default@catalog_sales,cs,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_discount_amt"]
+ PARTITION_ONLY_SHUFFLE [RS_34]
+ Group By Operator [GBY_33] (rows=1 width=112)
+ Output:["_col0"],aggregations:["sum(_col5)"]
+ Select Operator [SEL_32] (rows=232311810 width=135)
+ Output:["_col5"]
+ Filter Operator [FIL_31] (rows=232311810 width=135)
+ predicate:(_col5 > _col1)
+ Merge Join Operator [MERGEJOIN_59] (rows=696935432 width=135)
+ Conds:RS_27._col0=RS_28._col0(Inner),RS_28._col0=RS_29._col0(Inner),Output:["_col1","_col5"]
+ <-Map 7 [SIMPLE_EDGE]
+ SHUFFLE [RS_28]
+ PartitionCols:_col0
+ Select Operator [SEL_16] (rows=231000 width=1436)
+ Output:["_col0"]
+ Filter Operator [FIL_54] (rows=231000 width=1436)
+ predicate:((i_manufact_id = 436) and i_item_sk is not null)
+ TableScan [TS_14] (rows=462000 width=1436)
+ default@item,i,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_manufact_id"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_27]
+ PartitionCols:_col0
+ Select Operator [SEL_13] (rows=158394413 width=135)
+ Output:["_col0","_col1"]
+ Group By Operator [GBY_12] (rows=158394413 width=135)
+ Output:["_col0","_col1"],aggregations:["avg(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_11]
+ PartitionCols:_col0
+ Group By Operator [GBY_10] (rows=316788826 width=135)
+ Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col1
+ Merge Join Operator [MERGEJOIN_57] (rows=316788826 width=135)
+ Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col1","_col2"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_6]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=287989836 width=135)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_52] (rows=287989836 width=135)
+ predicate:(cs_sold_date_sk is not null and cs_item_sk is not null)
+ TableScan [TS_0] (rows=287989836 width=135)
+ default@catalog_sales,cs,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_discount_amt"]
+ <-Map 6 [SIMPLE_EDGE]
+ SHUFFLE [RS_7]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_53] (rows=8116 width=1119)
+ predicate:(d_date BETWEEN '2000-01-27' AND '2000-04-27' and d_date_sk is not null)
+ TableScan [TS_3] (rows=73049 width=1119)
+ default@date_dim,d,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
+ <-Reducer 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_29]
+ PartitionCols:_col0
+ Select Operator [SEL_26] (rows=316788826 width=135)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_58] (rows=316788826 width=135)
+ Conds:RS_23._col0=RS_24._col0(Inner),Output:["_col1","_col2"]
+ <-Map 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_24]
+ PartitionCols:_col0
+ Select Operator [SEL_22] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_56] (rows=8116 width=1119)
+ predicate:(d_date BETWEEN '2000-01-27' AND '2000-04-27' and d_date_sk is not null)
+ TableScan [TS_20] (rows=73049 width=1119)
+ default@date_dim,d,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
+ <-Map 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_23]
+ PartitionCols:_col0
+ Select Operator [SEL_19] (rows=287989836 width=135)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_55] (rows=287989836 width=135)
+ predicate:(cs_sold_date_sk is not null and cs_item_sk is not null)
+ TableScan [TS_17] (rows=287989836 width=135)
+ default@catalog_sales,cs,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_discount_amt"]
diff --git a/ql/src/test/results/clientpositive/perf/query37.q.out b/ql/src/test/results/clientpositive/perf/query37.q.out
index 1b61198..1c4f715 100644
--- a/ql/src/test/results/clientpositive/perf/query37.q.out
+++ b/ql/src/test/results/clientpositive/perf/query37.q.out
@@ -97,7 +97,7 @@ Stage-0
Select Operator [SEL_11] (rows=8116 width=1119)
Output:["_col0"]
Filter Operator [FIL_42] (rows=8116 width=1119)
- predicate:(d_date BETWEEN 2001-06-02 AND 2001-08-01 00:00:00.0 and d_date_sk is not null)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN 2001-06-02 00:00:00.0 AND 2001-08-01 00:00:00.0 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_date"]
diff --git a/ql/src/test/results/clientpositive/perf/query40.q.out b/ql/src/test/results/clientpositive/perf/query40.q.out
index a45fdaf..919c5c2 100644
--- a/ql/src/test/results/clientpositive/perf/query40.q.out
+++ b/ql/src/test/results/clientpositive/perf/query40.q.out
@@ -119,7 +119,7 @@ Stage-0
Select Operator [SEL_8] (rows=8116 width=1119)
Output:["_col0","_col1"]
Filter Operator [FIL_52] (rows=8116 width=1119)
- predicate:(d_date BETWEEN 1998-03-08 23:00:00.0 AND 1998-05-08 00:00:00.0 and d_date_sk is not null)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN 1998-03-08 23:00:00.0 AND 1998-05-08 00:00:00.0 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_date"]
<-Reducer 2 [SIMPLE_EDGE]
diff --git a/ql/src/test/results/clientpositive/perf/query48.q.out b/ql/src/test/results/clientpositive/perf/query48.q.out
index 3b390f2..e377e3f 100644
--- a/ql/src/test/results/clientpositive/perf/query48.q.out
+++ b/ql/src/test/results/clientpositive/perf/query48.q.out
@@ -5,90 +5,88 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
-Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
-Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
-Reducer 6 <- Map 9 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
-Reducer 7 <- Map 10 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
+Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 4 <- Map 9 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+Reducer 5 <- Map 10 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+Reducer 6 <- Reducer 5 (CUSTOM_SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
- Reducer 3
- File Output Operator [FS_35]
- Group By Operator [GBY_33] (rows=1 width=8)
+ Reducer 6
+ File Output Operator [FS_33]
+ Group By Operator [GBY_31] (rows=1 width=8)
Output:["_col0"],aggregations:["sum(VALUE._col0)"]
- <-Reducer 2 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_32]
- Group By Operator [GBY_31] (rows=1 width=8)
- Output:["_col0"],aggregations:["sum(_col6)"]
- Merge Join Operator [MERGEJOIN_58] (rows=15616946 width=88)
- Conds:RS_27._col0=RS_28._col0(Inner),Output:["_col6"]
- <-Map 1 [SIMPLE_EDGE]
- SHUFFLE [RS_27]
- PartitionCols:_col0
- Select Operator [SEL_2] (rows=36524 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_50] (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 7 [SIMPLE_EDGE]
- SHUFFLE [RS_28]
- PartitionCols:_col0
- Select Operator [SEL_26] (rows=14197224 width=88)
- Output:["_col0","_col4"]
- Filter Operator [FIL_25] (rows=14197224 width=88)
- predicate:(((_col12) IN ('KY', 'GA', 'NM') and _col6 BETWEEN 0 AND 2000) or ((_col12) IN ('MT', 'OR', 'IN') and _col6 BETWEEN 150 AND 3000) or ((_col12) IN ('WI', 'MO', 'WV') and _col6 BETWEEN 50 AND 25000))
- Select Operator [SEL_24] (rows=85183356 width=88)
- Output:["_col0","_col4","_col6","_col12"]
- Merge Join Operator [MERGEJOIN_57] (rows=85183356 width=88)
- Conds:RS_21._col2=RS_22._col0(Inner),Output:["_col1","_col5","_col7","_col9"]
- <-Map 10 [SIMPLE_EDGE]
- SHUFFLE [RS_22]
- PartitionCols:_col0
- Select Operator [SEL_14] (rows=465450 width=385)
- Output:["_col0"]
- Filter Operator [FIL_54] (rows=465450 width=385)
- predicate:((cd_marital_status = 'M') and (cd_education_status = '4 yr 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"]
- <-Reducer 6 [SIMPLE_EDGE]
- SHUFFLE [RS_21]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_56] (rows=77439413 width=88)
- Conds:RS_18._col3=RS_19._col0(Inner),Output:["_col1","_col2","_col5","_col7","_col9"]
- <-Map 9 [SIMPLE_EDGE]
- SHUFFLE [RS_19]
- PartitionCols:_col0
- Select Operator [SEL_11] (rows=10000000 width=1014)
- Output:["_col0","_col1"]
- Filter Operator [FIL_53] (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_9] (rows=40000000 width=1014)
- default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_country"]
- <-Reducer 5 [SIMPLE_EDGE]
- SHUFFLE [RS_18]
- PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_55] (rows=70399465 width=88)
- Conds:RS_15._col0=RS_16._col3(Inner),Output:["_col1","_col2","_col3","_col5","_col7"]
- <-Map 4 [SIMPLE_EDGE]
- SHUFFLE [RS_15]
- PartitionCols:_col0
- Select Operator [SEL_5] (rows=1704 width=1910)
- Output:["_col0"]
- Filter Operator [FIL_51] (rows=1704 width=1910)
- predicate:s_store_sk is not null
- TableScan [TS_3] (rows=1704 width=1910)
- default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"]
- <-Map 8 [SIMPLE_EDGE]
- SHUFFLE [RS_16]
- PartitionCols:_col3
- Select Operator [SEL_8] (rows=63999513 width=88)
- Output:["_col0","_col1","_col2","_col3","_col4","_col6"]
- Filter Operator [FIL_52] (rows=63999513 width=88)
- predicate:((ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_net_profit BETWEEN 0 AND 2000 or ss_net_profit BETWEEN 150 AND 3000 or ss_net_profit BETWEEN 50 AND 25000) and ss_store_sk is not null and ss_cdemo_sk is not null and ss_addr_sk is not null and ss_sold_date_sk is not null)
- TableScan [TS_6] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_net_profit"]
+ <-Reducer 5 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_30]
+ Group By Operator [GBY_29] (rows=1 width=8)
+ Output:["_col0"],aggregations:["sum(_col5)"]
+ Select Operator [SEL_28] (rows=15616947 width=88)
+ Output:["_col5"]
+ Filter Operator [FIL_27] (rows=15616947 width=88)
+ predicate:(((_col14) IN ('KY', 'GA', 'NM') and _col7 BETWEEN 0 AND 2000) or ((_col14) IN ('MT', 'OR', 'IN') and _col7 BETWEEN 150 AND 3000) or ((_col14) IN ('WI', 'MO', 'WV') and _col7 BETWEEN 50 AND 25000))
+ Merge Join Operator [MERGEJOIN_56] (rows=93701693 width=88)
+ Conds:RS_24._col3=RS_25._col0(Inner),Output:["_col5","_col7","_col14"]
+ <-Map 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_25]
+ PartitionCols:_col0
+ Select Operator [SEL_14] (rows=10000000 width=1014)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_52] (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_12] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_country"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_24]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_55] (rows=85183356 width=88)
+ Conds:RS_21._col2=RS_22._col0(Inner),Output:["_col3","_col5","_col7"]
+ <-Map 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_22]
+ PartitionCols:_col0
+ Select Operator [SEL_11] (rows=465450 width=385)
+ Output:["_col0"]
+ Filter Operator [FIL_51] (rows=465450 width=385)
+ predicate:((cd_marital_status = 'M') and (cd_education_status = '4 yr Degree') and cd_demo_sk is not null)
+ TableScan [TS_9] (rows=1861800 width=385)
+ default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_21]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_54] (rows=77439413 width=88)
+ Conds:RS_18._col1=RS_19._col0(Inner),Output:["_col2","_col3","_col5","_col7"]
+ <-Map 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_19]
+ PartitionCols:_col0
+ Select Operator [SEL_8] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_50] (rows=36524 width=1119)
+ predicate:((d_year = 1998) 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"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_18]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_53] (rows=70399465 width=88)
+ Conds:RS_15._col0=RS_16._col3(Inner),Output:["_col1","_col2","_col3","_col5","_col7"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_15]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=1704 width=1910)
+ Output:["_col0"]
+ Filter Operator [FIL_48] (rows=1704 width=1910)
+ predicate:s_store_sk is not null
+ TableScan [TS_0] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"]
+ <-Map 7 [SIMPLE_EDGE]
+ SHUFFLE [RS_16]
+ PartitionCols:_col3
+ Select Operator [SEL_5] (rows=63999513 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col6"]
+ Filter Operator [FIL_49] (rows=63999513 width=88)
+ predicate:((ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_net_profit BETWEEN 0 AND 2000 or ss_net_profit BETWEEN 150 AND 3000 or ss_net_profit BETWEEN 50 AND 25000) and ss_store_sk is not null and ss_cdemo_sk is not null and ss_addr_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_3] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_net_profit"]
diff --git a/ql/src/test/results/clientpositive/perf/query5.q.out b/ql/src/test/results/clientpositive/perf/query5.q.out
index 9f0acc8..ad78d7e 100644
--- a/ql/src/test/results/clientpositive/perf/query5.q.out
+++ b/ql/src/test/results/clientpositive/perf/query5.q.out
@@ -326,7 +326,7 @@ Stage-0
Select Operator [SEL_35] (rows=8116 width=1119)
Output:["_col0"]
Filter Operator [FIL_125] (rows=8116 width=1119)
- predicate:(d_date BETWEEN 1998-08-04 AND 1998-08-18 00:00:00.0 and d_date_sk is not null)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN 1998-08-04 00:00:00.0 AND 1998-08-18 00:00:00.0 and d_date_sk is not null)
TableScan [TS_33] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
<-Union 13 [SIMPLE_EDGE]
@@ -384,7 +384,7 @@ Stage-0
Select Operator [SEL_69] (rows=8116 width=1119)
Output:["_col0"]
Filter Operator [FIL_130] (rows=8116 width=1119)
- predicate:(d_date BETWEEN 1998-08-04 AND 1998-08-18 00:00:00.0 and d_date_sk is not null)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN 1998-08-04 00:00:00.0 AND 1998-08-18 00:00:00.0 and d_date_sk is not null)
TableScan [TS_67] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
<-Union 21 [SIMPLE_EDGE]
@@ -458,7 +458,7 @@ Stage-0
Select Operator [SEL_10] (rows=8116 width=1119)
Output:["_col0"]
Filter Operator [FIL_121] (rows=8116 width=1119)
- predicate:(d_date BETWEEN 1998-08-04 AND 1998-08-18 00:00:00.0 and d_date_sk is not null)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN 1998-08-04 00:00:00.0 AND 1998-08-18 00:00:00.0 and d_date_sk is not null)
TableScan [TS_8] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
<-Union 2 [SIMPLE_EDGE]
diff --git a/ql/src/test/results/clientpositive/perf/query58.q.out b/ql/src/test/results/clientpositive/perf/query58.q.out
index df95c70..d03a736 100644
--- a/ql/src/test/results/clientpositive/perf/query58.q.out
+++ b/ql/src/test/results/clientpositive/perf/query58.q.out
@@ -95,264 +95,256 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 10 <- Map 11 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE)
-Reducer 15 <- Map 14 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE)
+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)
-Reducer 17 <- Map 23 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE)
-Reducer 18 <- Reducer 17 (SIMPLE_EDGE)
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE)
-Reducer 20 <- Map 19 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE)
-Reducer 25 <- Map 24 (SIMPLE_EDGE), Reducer 30 (SIMPLE_EDGE)
+Reducer 17 <- Reducer 16 (SIMPLE_EDGE)
+Reducer 19 <- Map 18 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
+Reducer 24 <- Map 23 (SIMPLE_EDGE), Reducer 29 (SIMPLE_EDGE)
+Reducer 25 <- Map 31 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE)
Reducer 26 <- Map 32 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE)
-Reducer 27 <- Map 33 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE)
-Reducer 28 <- Reducer 27 (SIMPLE_EDGE)
-Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 30 <- Map 29 (SIMPLE_EDGE), Map 31 (SIMPLE_EDGE)
-Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+Reducer 27 <- Reducer 26 (SIMPLE_EDGE)
+Reducer 29 <- Map 28 (SIMPLE_EDGE), Map 30 (SIMPLE_EDGE)
+Reducer 3 <- Map 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
-Reducer 6 <- Reducer 18 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
-Reducer 7 <- Reducer 28 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
-Reducer 8 <- Reducer 7 (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)
Stage-0
Fetch Operator
limit:100
Stage-1
- Reducer 8
+ Reducer 7
File Output Operator [FS_113]
- Limit [LIM_112] (rows=100 width=135)
+ Limit [LIM_112] (rows=100 width=88)
Number of rows:100
- Select Operator [SEL_111] (rows=14606 width=135)
+ Select Operator [SEL_111] (rows=1442 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- <-Reducer 7 [SIMPLE_EDGE]
+ <-Reducer 6 [SIMPLE_EDGE]
SHUFFLE [RS_110]
- Select Operator [SEL_109] (rows=14606 width=135)
+ Select Operator [SEL_109] (rows=1442 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- Filter Operator [FIL_108] (rows=14606 width=135)
- predicate:(_col1 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col3 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_209] (rows=95833780 width=135)
- Conds:RS_104._col0=RS_105._col0(Inner),Output:["_col0","_col1","_col3","_col5"]
- <-Reducer 28 [SIMPLE_EDGE]
- SHUFFLE [RS_105]
+ Filter Operator [FIL_103] (rows=1442 width=88)
+ predicate:(_col5 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col5 BETWEEN (0.9 * _col3) AND (1.1 * _col3) and _col1 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col3 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col1 BETWEEN (0.9 * _col3) AND (1.1 * _col3) and _col3 BETWEEN (0.9 * _col1) AND (1.1 * _col1))
+ Merge Join Operator [MERGEJOIN_213] (rows=766650239 width=88)
+ Conds:RS_99._col0=RS_100._col0(Inner),RS_99._col0=RS_101._col0(Inner),Output:["_col0","_col1","_col3","_col5"]
+ <-Reducer 17 [SIMPLE_EDGE]
+ SHUFFLE [RS_100]
PartitionCols:_col0
- Group By Operator [GBY_102] (rows=87121617 width=135)
+ Group By Operator [GBY_64] (rows=348477374 width=88)
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 27 [SIMPLE_EDGE]
- SHUFFLE [RS_101]
+ <-Reducer 16 [SIMPLE_EDGE]
+ SHUFFLE [RS_63]
PartitionCols:_col0
- Group By Operator [GBY_100] (rows=174243235 width=135)
+ Group By Operator [GBY_62] (rows=696954748 width=88)
Output:["_col0","_col1"],aggregations:["sum(_col5)"],keys:_col7
- Merge Join Operator [MERGEJOIN_207] (rows=174243235 width=135)
- Conds:RS_96._col4=RS_97._col0(Inner),Output:["_col5","_col7"]
- <-Map 33 [SIMPLE_EDGE]
- SHUFFLE [RS_97]
+ Merge Join Operator [MERGEJOIN_208] (rows=696954748 width=88)
+ Conds:RS_58._col4=RS_59._col0(Inner),Output:["_col5","_col7"]
+ <-Map 22 [SIMPLE_EDGE]
+ SHUFFLE [RS_59]
PartitionCols:_col0
- Select Operator [SEL_89] (rows=462000 width=1436)
+ Select Operator [SEL_51] (rows=462000 width=1436)
Output:["_col0","_col1"]
Filter Operator [FIL_195] (rows=462000 width=1436)
predicate:(i_item_sk is not null and i_item_id is not null)
- TableScan [TS_87] (rows=462000 width=1436)
+ TableScan [TS_49] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
- <-Reducer 26 [SIMPLE_EDGE]
- SHUFFLE [RS_96]
+ <-Reducer 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_58]
PartitionCols:_col4
- Merge Join Operator [MERGEJOIN_206] (rows=158402938 width=135)
- Conds:RS_93._col0=RS_94._col0(Inner),Output:["_col4","_col5"]
- <-Map 32 [SIMPLE_EDGE]
- SHUFFLE [RS_94]
+ Merge Join Operator [MERGEJOIN_207] (rows=633595212 width=88)
+ Conds:RS_55._col0=RS_56._col0(Inner),Output:["_col4","_col5"]
+ <-Map 21 [SIMPLE_EDGE]
+ SHUFFLE [RS_56]
PartitionCols:_col0
- Select Operator [SEL_86] (rows=144002668 width=135)
+ Select Operator [SEL_48] (rows=575995635 width=88)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_194] (rows=144002668 width=135)
- predicate:(ws_item_sk is not null and ws_sold_date_sk is not null)
- TableScan [TS_84] (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"]
- <-Reducer 25 [SIMPLE_EDGE]
- SHUFFLE [RS_93]
+ Filter Operator [FIL_194] (rows=575995635 width=88)
+ predicate:(ss_item_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_46] (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 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_55]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_205] (rows=88388 width=1119)
- Conds:RS_90._col1=RS_91._col0(Inner),Output:["_col0"]
- <-Map 24 [SIMPLE_EDGE]
- SHUFFLE [RS_90]
+ Merge Join Operator [MERGEJOIN_206] (rows=88388 width=1119)
+ Conds:RS_52._col1=RS_53._col0(Inner),Output:["_col0"]
+ <-Map 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_52]
PartitionCols:_col1
- Select Operator [SEL_73] (rows=73049 width=1119)
+ Select Operator [SEL_35] (rows=73049 width=1119)
Output:["_col0","_col1"]
Filter Operator [FIL_191] (rows=73049 width=1119)
predicate:(d_date_sk is not null and d_date is not null)
- TableScan [TS_71] (rows=73049 width=1119)
+ TableScan [TS_33] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
- <-Reducer 30 [SIMPLE_EDGE]
- SHUFFLE [RS_91]
+ <-Reducer 19 [SIMPLE_EDGE]
+ SHUFFLE [RS_53]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_204] (rows=80353 width=1119)
- Conds:RS_80._col1=RS_81._col1(Inner),Output:["_col0"]
- <-Map 29 [SIMPLE_EDGE]
- SHUFFLE [RS_80]
+ Merge Join Operator [MERGEJOIN_205] (rows=80353 width=1119)
+ Conds:RS_42._col1=RS_43._col1(Inner),Output:["_col0"]
+ <-Map 18 [SIMPLE_EDGE]
+ SHUFFLE [RS_42]
PartitionCols:_col1
- Select Operator [SEL_76] (rows=73049 width=1119)
+ Select Operator [SEL_38] (rows=73049 width=1119)
Output:["_col0","_col1"]
Filter Operator [FIL_192] (rows=73049 width=1119)
predicate:(d_week_seq is not null and d_date is not null)
- TableScan [TS_74] (rows=73049 width=1119)
+ TableScan [TS_36] (rows=73049 width=1119)
default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"]
- <-Map 31 [SIMPLE_EDGE]
- SHUFFLE [RS_81]
+ <-Map 20 [SIMPLE_EDGE]
+ SHUFFLE [RS_43]
PartitionCols:_col1
- Select Operator [SEL_79] (rows=36524 width=1119)
+ Select Operator [SEL_41] (rows=36524 width=1119)
Output:["_col1"]
Filter Operator [FIL_193] (rows=36524 width=1119)
predicate:((d_date = '1998-08-04') and d_week_seq is not null)
- TableScan [TS_77] (rows=73049 width=1119)
+ TableScan [TS_39] (rows=73049 width=1119)
default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"]
- <-Reducer 6 [SIMPLE_EDGE]
- SHUFFLE [RS_104]
+ <-Reducer 27 [SIMPLE_EDGE]
+ SHUFFLE [RS_101]
PartitionCols:_col0
- Filter Operator [FIL_69] (rows=4732408 width=88)
- predicate:(_col1 BETWEEN (0.9 * _col3) AND (1.1 * _col3) and _col3 BETWEEN (0.9 * _col1) AND (1.1 * _col1))
- Merge Join Operator [MERGEJOIN_208] (rows=383325119 width=88)
- Conds:RS_66._col0=RS_67._col0(Inner),Output:["_col0","_col1","_col3"]
- <-Reducer 18 [SIMPLE_EDGE]
- SHUFFLE [RS_67]
- PartitionCols:_col0
- Group By Operator [GBY_64] (rows=174233858 width=135)
- Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 17 [SIMPLE_EDGE]
- SHUFFLE [RS_63]
+ Group By Operator [GBY_97] (rows=87121617 width=135)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 26 [SIMPLE_EDGE]
+ SHUFFLE [RS_96]
+ PartitionCols:_col0
+ Group By Operator [GBY_95] (rows=174243235 width=135)
+ Output:["_col0","_col1"],aggregations:["sum(_col5)"],keys:_col7
+ Merge Join Operator [MERGEJOIN_212] (rows=174243235 width=135)
+ Conds:RS_91._col4=RS_92._col0(Inner),Output:["_col5","_col7"]
+ <-Map 32 [SIMPLE_EDGE]
+ SHUFFLE [RS_92]
PartitionCols:_col0
- Group By Operator [GBY_62] (rows=348467716 width=135)
- Output:["_col0","_col1"],aggregations:["sum(_col5)"],keys:_col7
- Merge Join Operator [MERGEJOIN_203] (rows=348467716 width=135)
- Conds:RS_58._col4=RS_59._col0(Inner),Output:["_col5","_col7"]
- <-Map 23 [SIMPLE_EDGE]
- SHUFFLE [RS_59]
- PartitionCols:_col0
- Select Operator [SEL_51] (rows=462000 width=1436)
- Output:["_col0","_col1"]
- Filter Operator [FIL_190] (rows=462000 width=1436)
- predicate:(i_item_sk is not null and i_item_id is not null)
- TableScan [TS_49] (rows=462000 width=1436)
- default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
- <-Reducer 16 [SIMPLE_EDGE]
- SHUFFLE [RS_58]
- PartitionCols:_col4
- Merge Join Operator [MERGEJOIN_202] (rows=316788826 width=135)
- Conds:RS_55._col0=RS_56._col0(Inner),Output:["_col4","_col5"]
- <-Map 22 [SIMPLE_EDGE]
- SHUFFLE [RS_56]
- PartitionCols:_col0
- Select Operator [SEL_48] (rows=287989836 width=135)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_189] (rows=287989836 width=135)
- predicate:(cs_item_sk is not null and cs_sold_date_sk is not null)
- TableScan [TS_46] (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"]
- <-Reducer 15 [SIMPLE_EDGE]
- SHUFFLE [RS_55]
- PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_201] (rows=88388 width=1119)
- Conds:RS_52._col1=RS_53._col0(Inner),Output:["_col0"]
- <-Map 14 [SIMPLE_EDGE]
- SHUFFLE [RS_52]
- PartitionCols:_col1
- Select Operator [SEL_35] (rows=73049 width=1119)
- Output:["_col0","_col1"]
- Filter Operator [FIL_186] (rows=73049 width=1119)
- predicate:(d_date_sk is not null and d_date is not null)
- TableScan [TS_33] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
- <-Reducer 20 [SIMPLE_EDGE]
- SHUFFLE [RS_53]
- PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_200] (rows=80353 width=1119)
- Conds:RS_42._col1=RS_43._col1(Inner),Output:["_col0"]
- <-Map 19 [SIMPLE_EDGE]
- SHUFFLE [RS_42]
- PartitionCols:_col1
- Select Operator [SEL_38] (rows=73049 width=1119)
- Output:["_col0","_col1"]
- Filter Operator [FIL_187] (rows=73049 width=1119)
- predicate:(d_week_seq is not null and d_date is not null)
- TableScan [TS_36] (rows=73049 width=1119)
- default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"]
- <-Map 21 [SIMPLE_EDGE]
- SHUFFLE [RS_43]
- PartitionCols:_col1
- Select Operator [SEL_41] (rows=36524 width=1119)
- Output:["_col1"]
- Filter Operator [FIL_188] (rows=36524 width=1119)
- predicate:((d_date = '1998-08-04') and d_week_seq is not null)
- TableScan [TS_39] (rows=73049 width=1119)
- default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"]
- <-Reducer 5 [SIMPLE_EDGE]
- SHUFFLE [RS_66]
- PartitionCols:_col0
- Group By Operator [GBY_31] (rows=348477374 width=88)
- Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_30]
+ Select Operator [SEL_84] (rows=462000 width=1436)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_200] (rows=462000 width=1436)
+ predicate:(i_item_sk is not null and i_item_id is not null)
+ TableScan [TS_82] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
+ <-Reducer 25 [SIMPLE_EDGE]
+ SHUFFLE [RS_91]
+ PartitionCols:_col4
+ Merge Join Operator [MERGEJOIN_211] (rows=158402938 width=135)
+ Conds:RS_88._col0=RS_89._col0(Inner),Output:["_col4","_col5"]
+ <-Map 31 [SIMPLE_EDGE]
+ SHUFFLE [RS_89]
+ PartitionCols:_col0
+ Select Operator [SEL_81] (rows=144002668 width=135)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_199] (rows=144002668 width=135)
+ predicate:(ws_item_sk is not null and ws_sold_date_sk is not null)
+ TableScan [TS_79] (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"]
+ <-Reducer 24 [SIMPLE_EDGE]
+ SHUFFLE [RS_88]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_210] (rows=88388 width=1119)
+ Conds:RS_85._col1=RS_86._col0(Inner),Output:["_col0"]
+ <-Map 23 [SIMPLE_EDGE]
+ SHUFFLE [RS_85]
+ PartitionCols:_col1
+ Select Operator [SEL_68] (rows=73049 width=1119)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_196] (rows=73049 width=1119)
+ predicate:(d_date_sk is not null and d_date is not null)
+ TableScan [TS_66] (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_86]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_209] (rows=80353 width=1119)
+ Conds:RS_75._col1=RS_76._col1(Inner),Output:["_col0"]
+ <-Map 28 [SIMPLE_EDGE]
+ SHUFFLE [RS_75]
+ PartitionCols:_col1
+ Select Operator [SEL_71] (rows=73049 width=1119)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_197] (rows=73049 width=1119)
+ predicate:(d_week_seq is not null and d_date is not null)
+ TableScan [TS_69] (rows=73049 width=1119)
+ default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"]
+ <-Map 30 [SIMPLE_EDGE]
+ SHUFFLE [RS_76]
+ PartitionCols:_col1
+ Select Operator [SEL_74] (rows=36524 width=1119)
+ Output:["_col1"]
+ Filter Operator [FIL_198] (rows=36524 width=1119)
+ predicate:((d_date = '1998-08-04') and d_week_seq is not null)
+ TableScan [TS_72] (rows=73049 width=1119)
+ default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"]
+ <-Reducer 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_99]
+ PartitionCols:_col0
+ Group By Operator [GBY_31] (rows=174233858 width=135)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_30]
+ PartitionCols:_col0
+ Group By Operator [GBY_29] (rows=348467716 width=135)
+ Output:["_col0","_col1"],aggregations:["sum(_col5)"],keys:_col7
+ Merge Join Operator [MERGEJOIN_204] (rows=348467716 width=135)
+ Conds:RS_25._col4=RS_26._col0(Inner),Output:["_col5","_col7"]
+ <-Map 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_26]
PartitionCols:_col0
- Group By Operator [GBY_29] (rows=696954748 width=88)
- Output:["_col0","_col1"],aggregations:["sum(_col5)"],keys:_col7
- Merge Join Operator [MERGEJOIN_199] (rows=696954748 width=88)
- Conds:RS_25._col4=RS_26._col0(Inner),Output:["_col5","_col7"]
- <-Map 13 [SIMPLE_EDGE]
- SHUFFLE [RS_26]
- PartitionCols:_col0
- Select Operator [SEL_18] (rows=462000 width=1436)
- Output:["_col0","_col1"]
- Filter Operator [FIL_185] (rows=462000 width=1436)
- predicate:(i_item_sk is not null and i_item_id is not null)
- TableScan [TS_16] (rows=462000 width=1436)
- default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_25]
- PartitionCols:_col4
- Merge Join Operator [MERGEJOIN_198] (rows=633595212 width=88)
- Conds:RS_22._col0=RS_23._col0(Inner),Output:["_col4","_col5"]
- <-Map 12 [SIMPLE_EDGE]
- SHUFFLE [RS_23]
- PartitionCols:_col0
- Select Operator [SEL_15] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_184] (rows=575995635 width=88)
- predicate:(ss_item_sk is not null and ss_sold_date_sk is not null)
- TableScan [TS_13] (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_22]
- PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_197] (rows=88388 width=1119)
- Conds:RS_19._col1=RS_20._col0(Inner),Output:["_col0"]
- <-Map 1 [SIMPLE_EDGE]
- SHUFFLE [RS_19]
- PartitionCols:_col1
- Select Operator [SEL_2] (rows=73049 width=1119)
- Output:["_col0","_col1"]
- Filter Operator [FIL_181] (rows=73049 width=1119)
- predicate:(d_date_sk is not null and d_date is not null)
- TableScan [TS_0] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
- <-Reducer 10 [SIMPLE_EDGE]
- SHUFFLE [RS_20]
- PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_196] (rows=80353 width=1119)
- Conds:RS_9._col1=RS_10._col1(Inner),Output:["_col0"]
- <-Map 11 [SIMPLE_EDGE]
- SHUFFLE [RS_10]
- PartitionCols:_col1
- Select Operator [SEL_8] (rows=36524 width=1119)
- Output:["_col1"]
- Filter Operator [FIL_183] (rows=36524 width=1119)
- predicate:((d_date = '1998-08-04') and d_week_seq is not null)
- TableScan [TS_6] (rows=73049 width=1119)
- default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"]
- <-Map 9 [SIMPLE_EDGE]
- SHUFFLE [RS_9]
- PartitionCols:_col1
- Select Operator [SEL_5] (rows=73049 width=1119)
- Output:["_col0","_col1"]
- Filter Operator [FIL_182] (rows=73049 width=1119)
- 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"]
+ Select Operator [SEL_18] (rows=462000 width=1436)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_190] (rows=462000 width=1436)
+ predicate:(i_item_sk is not null and i_item_id is not null)
+ TableScan [TS_16] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_25]
+ PartitionCols:_col4
+ Merge Join Operator [MERGEJOIN_203] (rows=316788826 width=135)
+ Conds:RS_22._col0=RS_23._col0(Inner),Output:["_col4","_col5"]
+ <-Map 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_23]
+ PartitionCols:_col0
+ Select Operator [SEL_15] (rows=287989836 width=135)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_189] (rows=287989836 width=135)
+ predicate:(cs_item_sk is not null and cs_sold_date_sk is not null)
+ TableScan [TS_13] (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"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_22]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_202] (rows=88388 width=1119)
+ Conds:RS_19._col1=RS_20._col0(Inner),Output:["_col0"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_19]
+ PartitionCols:_col1
+ Select Operator [SEL_2] (rows=73049 width=1119)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_186] (rows=73049 width=1119)
+ predicate:(d_date_sk is not null and d_date is not null)
+ TableScan [TS_0] (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_20]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_201] (rows=80353 width=1119)
+ Conds:RS_9._col1=RS_10._col1(Inner),Output:["_col0"]
+ <-Map 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_10]
+ PartitionCols:_col1
+ Select Operator [SEL_8] (rows=36524 width=1119)
+ Output:["_col1"]
+ Filter Operator [FIL_188] (rows=36524 width=1119)
+ predicate:((d_date = '1998-08-04') and d_week_seq is not null)
+ TableScan [TS_6] (rows=73049 width=1119)
+ default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"]
+ <-Map 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_9]
+ PartitionCols:_col1
+ Select Operator [SEL_5] (rows=73049 width=1119)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_187] (rows=73049 width=1119)
+ 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"]
diff --git a/ql/src/test/results/clientpositive/perf/query6.q.out b/ql/src/test/results/clientpositive/perf/query6.q.out
index 11b618d..aede0d7 100644
--- a/ql/src/test/results/clientpositive/perf/query6.q.out
+++ b/ql/src/test/results/clientpositive/perf/query6.q.out
@@ -96,17 +96,17 @@ Stage-0
<-Reducer 24 [SIMPLE_EDGE]
SHUFFLE [RS_81]
PartitionCols:_col2
- Select Operator [SEL_79] (rows=115500 width=1436)
+ Select Operator [SEL_79] (rows=231000 width=1436)
Output:["_col0","_col1","_col2"]
- Group By Operator [GBY_78] (rows=115500 width=1436)
+ Group By Operator [GBY_78] (rows=231000 width=1436)
Output:["_col0","_col1"],aggregations:["avg(VALUE._col0)"],keys:KEY._col0
<-Map 23 [SIMPLE_EDGE]
SHUFFLE [RS_77]
PartitionCols:_col0
- Group By Operator [GBY_76] (rows=231000 width=1436)
+ Group By Operator [GBY_76] (rows=462000 width=1436)
Output:["_col0","_col1"],aggregations:["avg(i_current_price)"],keys:i_category
- Filter Operator [FIL_125] (rows=231000 width=1436)
- predicate:(i_category = i_category)
+ Filter Operator [FIL_125] (rows=462000 width=1436)
+ predicate:i_category is not null
TableScan [TS_73] (rows=462000 width=1436)
default@item,j,Tbl:COMPLETE,Col:NONE,Output:["i_current_price","i_category"]
<-Reducer 5 [SIMPLE_EDGE]
@@ -236,21 +236,21 @@ Stage-0
<-Reducer 10 [SIMPLE_EDGE]
SHUFFLE [RS_61]
PartitionCols:_col0
- Select Operator [SEL_15] (rows=19250 width=1436)
+ Select Operator [SEL_15] (rows=38500 width=1436)
Output:["_col0"]
- Filter Operator [FIL_14] (rows=19250 width=1436)
+ Filter Operator [FIL_14] (rows=38500 width=1436)
predicate:(sq_count_check(_col1) <= 1)
- Group By Operator [GBY_13] (rows=57750 width=1436)
+ Group By Operator [GBY_13] (rows=115500 width=1436)
Output:["_col0","_col1"],aggregations:["count()"],keys:_col0
- Group By Operator [GBY_8] (rows=115500 width=1436)
+ Group By Operator [GBY_8] (rows=231000 width=1436)
Output:["_col0"],keys:KEY._col0
<-Map 9 [SIMPLE_EDGE]
SHUFFLE [RS_7]
PartitionCols:_col0
- Group By Operator [GBY_6] (rows=231000 width=1436)
+ Group By Operator [GBY_6] (rows=462000 width=1436)
Output:["_col0"],keys:i_category
- Filter Operator [FIL_118] (rows=231000 width=1436)
- predicate:(i_category = i_category)
+ Filter Operator [FIL_118] (rows=462000 width=1436)
+ predicate:i_category is not null
TableScan [TS_3] (rows=462000 width=1436)
default@item,j,Tbl:COMPLETE,Col:NONE,Output:["i_category"]
diff --git a/ql/src/test/results/clientpositive/perf/query64.q.out b/ql/src/test/results/clientpositive/perf/query64.q.out
index ceb11e7..6b42393 100644
--- a/ql/src/test/results/clientpositive/perf/query64.q.out
+++ b/ql/src/test/results/clientpositive/perf/query64.q.out
@@ -5,653 +5,645 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 10 <- Reducer 21 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
-Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 38 (SIMPLE_EDGE)
-Reducer 12 <- Map 40 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE)
-Reducer 13 <- Map 41 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE)
-Reducer 16 <- Map 15 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE)
-Reducer 17 <- Map 23 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE)
-Reducer 18 <- Map 24 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE)
-Reducer 19 <- Reducer 18 (SIMPLE_EDGE), Reducer 29 (SIMPLE_EDGE)
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
-Reducer 20 <- Map 34 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE)
-Reducer 21 <- Map 35 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE)
-Reducer 26 <- Map 25 (SIMPLE_EDGE), Map 30 (SIMPLE_EDGE)
-Reducer 27 <- Map 31 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE)
+Reducer 10 <- Reducer 50 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
+Reducer 11 <- Reducer 10 (SIMPLE_EDGE)
+Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE)
+Reducer 20 <- Map 19 (SIMPLE_EDGE), Map 25 (SIMPLE_EDGE)
+Reducer 21 <- Reducer 20 (SIMPLE_EDGE), Reducer 30 (SIMPLE_EDGE)
+Reducer 22 <- Reducer 21 (SIMPLE_EDGE), Reducer 37 (SIMPLE_EDGE)
+Reducer 23 <- Map 39 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE)
+Reducer 24 <- Map 40 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE)
+Reducer 27 <- Map 26 (SIMPLE_EDGE), Map 31 (SIMPLE_EDGE)
Reducer 28 <- Map 32 (SIMPLE_EDGE), Reducer 27 (SIMPLE_EDGE)
Reducer 29 <- Map 33 (SIMPLE_EDGE), Reducer 28 (SIMPLE_EDGE)
-Reducer 3 <- Reducer 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 37 <- Map 36 (SIMPLE_EDGE), Map 39 (SIMPLE_EDGE)
-Reducer 38 <- Reducer 37 (SIMPLE_EDGE)
-Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
-Reducer 43 <- Map 42 (SIMPLE_EDGE), Map 46 (SIMPLE_EDGE)
-Reducer 44 <- Reducer 43 (SIMPLE_EDGE), Reducer 52 (SIMPLE_EDGE)
-Reducer 45 <- Reducer 44 (SIMPLE_EDGE)
-Reducer 48 <- Map 47 (SIMPLE_EDGE), Map 53 (SIMPLE_EDGE)
-Reducer 49 <- Reducer 48 (SIMPLE_EDGE), Reducer 60 (SIMPLE_EDGE)
-Reducer 5 <- Reducer 4 (SIMPLE_EDGE), Reducer 45 (SIMPLE_EDGE)
-Reducer 50 <- Reducer 49 (SIMPLE_EDGE), Reducer 77 (SIMPLE_EDGE)
-Reducer 51 <- Map 79 (SIMPLE_EDGE), Reducer 50 (SIMPLE_EDGE)
-Reducer 52 <- Map 80 (SIMPLE_EDGE), Reducer 51 (SIMPLE_EDGE)
-Reducer 55 <- Map 54 (SIMPLE_EDGE), Map 61 (SIMPLE_EDGE)
-Reducer 56 <- Map 62 (SIMPLE_EDGE), Reducer 55 (SIMPLE_EDGE)
-Reducer 57 <- Map 63 (SIMPLE_EDGE), Reducer 56 (SIMPLE_EDGE)
-Reducer 58 <- Reducer 57 (SIMPLE_EDGE), Reducer 68 (SIMPLE_EDGE)
-Reducer 59 <- Map 73 (SIMPLE_EDGE), Reducer 58 (SIMPLE_EDGE)
-Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
-Reducer 60 <- Map 74 (SIMPLE_EDGE), Reducer 59 (SIMPLE_EDGE)
-Reducer 65 <- Map 64 (SIMPLE_EDGE), Map 69 (SIMPLE_EDGE)
-Reducer 66 <- Map 70 (SIMPLE_EDGE), Reducer 65 (SIMPLE_EDGE)
+Reducer 3 <- Map 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 30 <- Map 34 (SIMPLE_EDGE), Reducer 29 (SIMPLE_EDGE)
+Reducer 36 <- Map 35 (SIMPLE_EDGE), Map 38 (SIMPLE_EDGE)
+Reducer 37 <- Reducer 36 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+Reducer 43 <- Map 42 (SIMPLE_EDGE), Map 51 (SIMPLE_EDGE)
+Reducer 44 <- Map 52 (SIMPLE_EDGE), Reducer 43 (SIMPLE_EDGE)
+Reducer 45 <- Reducer 44 (SIMPLE_EDGE), Reducer 54 (SIMPLE_EDGE)
+Reducer 46 <- Map 56 (SIMPLE_EDGE), Reducer 45 (SIMPLE_EDGE)
+Reducer 47 <- Map 57 (SIMPLE_EDGE), Reducer 46 (SIMPLE_EDGE)
+Reducer 48 <- Reducer 47 (SIMPLE_EDGE), Reducer 63 (SIMPLE_EDGE)
+Reducer 49 <- Map 80 (SIMPLE_EDGE), Reducer 48 (SIMPLE_EDGE)
+Reducer 5 <- Map 17 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+Reducer 50 <- Reducer 49 (SIMPLE_EDGE)
+Reducer 54 <- Map 53 (SIMPLE_EDGE), Map 55 (SIMPLE_EDGE)
+Reducer 59 <- Map 58 (SIMPLE_EDGE), Map 64 (SIMPLE_EDGE)
+Reducer 6 <- Map 18 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
+Reducer 60 <- Reducer 59 (SIMPLE_EDGE), Reducer 69 (SIMPLE_EDGE)
+Reducer 61 <- Reducer 60 (SIMPLE_EDGE), Reducer 76 (SIMPLE_EDGE)
+Reducer 62 <- Map 78 (SIMPLE_EDGE), Reducer 61 (SIMPLE_EDGE)
+Reducer 63 <- Map 79 (SIMPLE_EDGE), Reducer 62 (SIMPLE_EDGE)
+Reducer 66 <- Map 65 (SIMPLE_EDGE), Map 70 (SIMPLE_EDGE)
Reducer 67 <- Map 71 (SIMPLE_EDGE), Reducer 66 (SIMPLE_EDGE)
Reducer 68 <- Map 72 (SIMPLE_EDGE), Reducer 67 (SIMPLE_EDGE)
-Reducer 76 <- Map 75 (SIMPLE_EDGE), Map 78 (SIMPLE_EDGE)
-Reducer 77 <- Reducer 76 (SIMPLE_EDGE)
-Reducer 9 <- Map 14 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
+Reducer 69 <- Map 73 (SIMPLE_EDGE), Reducer 68 (SIMPLE_EDGE)
+Reducer 7 <- Reducer 24 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
+Reducer 75 <- Map 74 (SIMPLE_EDGE), Map 77 (SIMPLE_EDGE)
+Reducer 76 <- Reducer 75 (SIMPLE_EDGE)
+Reducer 8 <- Map 41 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
+Reducer 9 <- Reducer 8 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
- Reducer 6
- File Output Operator [FS_267]
- Select Operator [SEL_266] (rows=331415616 width=88)
+ Reducer 11
+ File Output Operator [FS_263]
+ Select Operator [SEL_262] (rows=273897192 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)
+ <-Reducer 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_261]
+ Select Operator [SEL_260] (rows=273897192 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col20"]
- Filter Operator [FIL_263] (rows=331415616 width=88)
+ Filter Operator [FIL_259] (rows=273897192 width=88)
predicate:(_col30 <= _col13)
- Merge Join Operator [MERGEJOIN_658] (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]
+ Merge Join Operator [MERGEJOIN_610] (rows=821691577 width=88)
+ 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]
PartitionCols:_col2, _col1, _col3
- Select Operator [SEL_128] (rows=903860754 width=88)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col13","_col14","_col15","_col16"]
- Group By Operator [GBY_127] (rows=903860754 width=88)
+ Select Operator [SEL_254] (rows=746992327 width=88)
+ Output:["_col1","_col2","_col3","_col13","_col14","_col15","_col16"]
+ Group By Operator [GBY_253] (rows=746992327 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9, KEY._col10, KEY._col11, KEY._col12, KEY._col13
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_126]
+ <-Reducer 49 [SIMPLE_EDGE]
+ SHUFFLE [RS_252]
PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
- 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
- Merge Join Operator [MERGEJOIN_656] (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","_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col18","_col23","_col24","_col25","_col37","_col39","_col41","_col42","_col47","_col50"]
- Merge Join Operator [MERGEJOIN_638] (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_602] (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_637] (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_601] (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_636] (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_635] (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:["_col2","_col5","_col6","_col10","_col11","_col12","_col17","_col18","_col24","_col26","_col28","_col29","_col34","_col37"]
- Merge Join Operator [MERGEJOIN_633] (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]
+ 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)
+ Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col21","_col22","_col23","_col24","_col26","_col27","_col45","_col46","_col47","_col48","_col51"]
+ Filter Operator [FIL_249] (rows=1493984654 width=88)
+ predicate:(_col56 <> _col19)
+ Merge Join Operator [MERGEJOIN_609] (rows=1493984654 width=88)
+ Conds:RS_246._col39=RS_247._col0(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col21","_col22","_col23","_col24","_col26","_col27","_col45","_col46","_col47","_col48","_col51","_col56"]
+ <-Map 80 [SIMPLE_EDGE]
+ SHUFFLE [RS_247]
+ PartitionCols:_col0
+ Select Operator [SEL_227] (rows=1861800 width=385)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_573] (rows=1861800 width=385)
+ predicate:cd_demo_sk is not null
+ TableScan [TS_225] (rows=1861800 width=385)
+ default@customer_demographics,cd1,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"]
+ <-Reducer 48 [SIMPLE_EDGE]
+ SHUFFLE [RS_246]
+ PartitionCols:_col39
+ Merge Join Operator [MERGEJOIN_608] (rows=1358167838 width=88)
+ Conds:RS_243._col0=RS_244._col18(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col21","_col22","_col23","_col24","_col26","_col27","_col39","_col45","_col46","_col47","_col48","_col51"]
+ <-Reducer 47 [SIMPLE_EDGE]
+ SHUFFLE [RS_243]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_597] (rows=128840811 width=860)
+ Conds:RS_240._col1=RS_241._col0(Inner),Output:["_col0","_col7","_col9","_col14","_col15","_col16","_col17","_col19"]
+ <-Map 57 [SIMPLE_EDGE]
+ SHUFFLE [RS_241]
+ PartitionCols:_col0
+ Select Operator [SEL_152] (rows=1861800 width=385)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_561] (rows=1861800 width=385)
+ predicate:cd_demo_sk is not null
+ TableScan [TS_150] (rows=1861800 width=385)
+ default@customer_demographics,cd2,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"]
+ <-Reducer 46 [SIMPLE_EDGE]
+ SHUFFLE [RS_240]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_596] (rows=117128008 width=860)
+ Conds:RS_237._col3=RS_238._col0(Inner),Output:["_col0","_col1","_col7","_col9","_col14","_col15","_col16","_col17"]
+ <-Map 56 [SIMPLE_EDGE]
+ SHUFFLE [RS_238]
+ PartitionCols:_col0
+ Select Operator [SEL_149] (rows=40000000 width=1014)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_560] (rows=40000000 width=1014)
+ predicate:ca_address_sk is not null
+ TableScan [TS_147] (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 45 [SIMPLE_EDGE]
+ SHUFFLE [RS_237]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_595] (rows=106480005 width=860)
+ Conds:RS_234._col2=RS_235._col0(Inner),Output:["_col0","_col1","_col3","_col7","_col9"]
+ <-Reducer 44 [SIMPLE_EDGE]
+ SHUFFLE [RS_234]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_593] (rows=96800003 width=860)
+ Conds:RS_231._col4=RS_232._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col7","_col9"]
+ <-Map 52 [SIMPLE_EDGE]
+ SHUFFLE [RS_232]
PartitionCols:_col0
- Select Operator [SEL_72] (rows=2300 width=1179)
- Output:["_col0"]
- Filter Operator [FIL_598] (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_632] (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]
+ Select Operator [SEL_136] (rows=73049 width=1119)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_557] (rows=73049 width=1119)
+ predicate:d_date_sk is not null
+ TableScan [TS_134] (rows=73049 width=1119)
+ default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 43 [SIMPLE_EDGE]
+ SHUFFLE [RS_231]
+ PartitionCols:_col4
+ Merge Join Operator [MERGEJOIN_592] (rows=88000001 width=860)
+ Conds:RS_228._col5=RS_229._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col7"]
+ <-Map 42 [SIMPLE_EDGE]
+ SHUFFLE [RS_228]
+ PartitionCols:_col5
+ Select Operator [SEL_130] (rows=80000000 width=860)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
+ Filter Operator [FIL_555] (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_128] (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 51 [SIMPLE_EDGE]
+ SHUFFLE [RS_229]
PartitionCols:_col0
- Select Operator [SEL_69] (rows=2851 width=1436)
- Output:["_col0","_col3"]
- Filter Operator [FIL_597] (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","_col4","_col5","_col7","_col9","_col10","_col11","_col16","_col17","_col23","_col25","_col27","_col28"]
- 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_631] (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_626] (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_591] (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_625] (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_590] (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_624] (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_588] (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_589] (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","_col3","_col4","_col6","_col7","_col9","_col11","_col12","_col13","_col19","_col20"]
- Merge Join Operator [MERGEJOIN_630] (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_596] (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_629] (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_595] (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_628] (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_594] (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_627] (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_592] (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_593] (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]
+ Select Operator [SEL_133] (rows=73049 width=1119)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_556] (rows=73049 width=1119)
+ predicate:d_date_sk is not null
+ TableScan [TS_131] (rows=73049 width=1119)
+ default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 54 [SIMPLE_EDGE]
+ SHUFFLE [RS_235]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_594] (rows=7920 width=107)
+ Conds:RS_143._col1=RS_144._col0(Inner),Output:["_col0"]
+ <-Map 53 [SIMPLE_EDGE]
+ SHUFFLE [RS_143]
+ PartitionCols:_col1
+ Select Operator [SEL_139] (rows=7200 width=107)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_558] (rows=7200 width=107)
+ 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
+ Select Operator [SEL_142] (rows=20 width=12)
+ Output:["_col0"]
+ Filter Operator [FIL_559] (rows=20 width=12)
+ predicate:ib_income_band_sk is not null
+ TableScan [TS_140] (rows=20 width=12)
+ default@income_band,ib2,Tbl:COMPLETE,Col:NONE,Output:["ib_income_band_sk"]
+ <-Reducer 63 [SIMPLE_EDGE]
+ SHUFFLE [RS_244]
+ PartitionCols:_col18
+ Select Operator [SEL_224] (rows=1234698008 width=88)
+ Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col18","_col19","_col25","_col26","_col27","_col28","_col31"]
+ Merge Join Operator [MERGEJOIN_607] (rows=1234698008 width=88)
+ Conds:RS_221._col13=RS_222._col0(Inner),Output:["_col10","_col11","_col17","_col18","_col19","_col20","_col23","_col28","_col29","_col31","_col32","_col33","_col34"]
+ <-Map 79 [SIMPLE_EDGE]
+ SHUFFLE [RS_222]
+ PartitionCols:_col0
+ Select Operator [SEL_208] (rows=40000000 width=1014)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_572] (rows=40000000 width=1014)
+ predicate:ca_address_sk is not null
+ TableScan [TS_206] (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 62 [SIMPLE_EDGE]
+ SHUFFLE [RS_221]
+ PartitionCols:_col13
+ Merge Join Operator [MERGEJOIN_606] (rows=1122452711 width=88)
+ Conds:RS_218._col14=RS_219._col0(Inner),Output:["_col10","_col11","_col13","_col17","_col18","_col19","_col20","_col23","_col28","_col29"]
+ <-Map 78 [SIMPLE_EDGE]
+ SHUFFLE [RS_219]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_623] (rows=7920 width=107)
- Conds:RS_102._col1=RS_103._col0(Inner),Output:["_col0"]
- <-Map 14 [SIMPLE_EDGE]
- SHUFFLE [RS_103]
+ Select Operator [SEL_205] (rows=1704 width=1910)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_571] (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_203] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_zip"]
+ <-Reducer 61 [SIMPLE_EDGE]
+ SHUFFLE [RS_218]
+ PartitionCols:_col14
+ Merge Join Operator [MERGEJOIN_605] (rows=1020411534 width=88)
+ Conds:RS_215._col9=RS_216._col0(Inner),Output:["_col10","_col11","_col13","_col14","_col17","_col18","_col19","_col20","_col23"]
+ <-Reducer 60 [SIMPLE_EDGE]
+ SHUFFLE [RS_215]
+ PartitionCols:_col9
+ Merge Join Operator [MERGEJOIN_604] (rows=927646829 width=88)
+ Conds:RS_212._col0=RS_213._col9(Inner),Output:["_col9","_col10","_col11","_col13","_col14","_col17","_col18","_col19","_col20","_col23"]
+ <-Reducer 59 [SIMPLE_EDGE]
+ SHUFFLE [RS_212]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_598] (rows=7920 width=107)
+ Conds:RS_209._col1=RS_210._col0(Inner),Output:["_col0"]
+ <-Map 58 [SIMPLE_EDGE]
+ SHUFFLE [RS_209]
+ PartitionCols:_col1
+ Select Operator [SEL_155] (rows=7200 width=107)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_562] (rows=7200 width=107)
+ predicate:(hd_demo_sk is not null and hd_income_band_sk is not null)
+ TableScan [TS_153] (rows=7200 width=107)
+ default@household_demographics,hd1,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_income_band_sk"]
+ <-Map 64 [SIMPLE_EDGE]
+ SHUFFLE [RS_210]
+ PartitionCols:_col0
+ Select Operator [SEL_158] (rows=20 width=12)
+ Output:["_col0"]
+ Filter Operator [FIL_563] (rows=20 width=12)
+ predicate:ib_income_band_sk is not null
+ TableScan [TS_156] (rows=20 width=12)
+ default@income_band,ib1,Tbl:COMPLETE,Col:NONE,Output:["ib_income_band_sk"]
+ <-Reducer 69 [SIMPLE_EDGE]
+ SHUFFLE [RS_213]
+ PartitionCols:_col9
+ Select Operator [SEL_186] (rows=843315281 width=88)
+ Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col14","_col15","_col16","_col17","_col20"]
+ Merge Join Operator [MERGEJOIN_602] (rows=843315281 width=88)
+ Conds:RS_183._col7=RS_184._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col9","_col10","_col11","_col12","_col15"]
+ <-Map 73 [SIMPLE_EDGE]
+ SHUFFLE [RS_184]
+ PartitionCols:_col0
+ Select Operator [SEL_173] (rows=2300 width=1179)
+ Output:["_col0"]
+ Filter Operator [FIL_568] (rows=2300 width=1179)
+ predicate:p_promo_sk is not null
+ TableScan [TS_171] (rows=2300 width=1179)
+ default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk"]
+ <-Reducer 68 [SIMPLE_EDGE]
+ SHUFFLE [RS_183]
+ PartitionCols:_col7
+ Merge Join Operator [MERGEJOIN_601] (rows=766650239 width=88)
+ Conds:RS_180._col0=RS_181._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col15"]
+ <-Map 72 [SIMPLE_EDGE]
+ SHUFFLE [RS_181]
+ PartitionCols:_col0
+ Select Operator [SEL_170] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_567] (rows=36524 width=1119)
+ predicate:((d_year = 2001) and d_date_sk is not null)
+ TableScan [TS_168] (rows=73049 width=1119)
+ default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 67 [SIMPLE_EDGE]
+ SHUFFLE [RS_180]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_600] (rows=696954748 width=88)
+ Conds:RS_177._col1, _col8=RS_178._col0, _col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col15"]
+ <-Map 71 [SIMPLE_EDGE]
+ SHUFFLE [RS_178]
+ PartitionCols:_col0, _col1
+ Select Operator [SEL_167] (rows=57591150 width=77)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_566] (rows=57591150 width=77)
+ predicate:(sr_item_sk is not null and sr_ticket_number is not null)
+ TableScan [TS_165] (rows=57591150 width=77)
+ default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number"]
+ <-Reducer 66 [SIMPLE_EDGE]
+ SHUFFLE [RS_177]
+ PartitionCols:_col1, _col8
+ Merge Join Operator [MERGEJOIN_599] (rows=633595212 width=88)
+ Conds:RS_174._col1=RS_175._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"]
+ <-Map 65 [SIMPLE_EDGE]
+ SHUFFLE [RS_174]
+ PartitionCols:_col1
+ Select Operator [SEL_161] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"]
+ Filter Operator [FIL_564] (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_159] (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 70 [SIMPLE_EDGE]
+ SHUFFLE [RS_175]
+ PartitionCols:_col0
+ Select Operator [SEL_164] (rows=2851 width=1436)
+ Output:["_col0","_col3"]
+ Filter Operator [FIL_565] (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_162] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_color","i_product_name"]
+ <-Reducer 76 [SIMPLE_EDGE]
+ SHUFFLE [RS_216]
PartitionCols:_col0
- Select Operator [SEL_11] (rows=20 width=12)
+ Select Operator [SEL_202] (rows=52798137 width=135)
Output:["_col0"]
- Filter Operator [FIL_587] (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]
- PartitionCols:_col1
- Select Operator [SEL_8] (rows=7200 width=107)
- Output:["_col0","_col1"]
- Filter Operator [FIL_586] (rows=7200 width=107)
- predicate:(hd_demo_sk is not null and hd_income_band_sk is not null)
- TableScan [TS_6] (rows=7200 width=107)
- default@household_demographics,hd2,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_income_band_sk"]
- <-Reducer 38 [SIMPLE_EDGE]
- SHUFFLE [RS_109]
- PartitionCols:_col0
- Select Operator [SEL_95] (rows=52798137 width=135)
- Output:["_col0"]
- Filter Operator [FIL_94] (rows=52798137 width=135)
- predicate:(_col1 > (2 * _col2))
- Group By Operator [GBY_93] (rows=158394413 width=135)
- Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0
- <-Reducer 37 [SIMPLE_EDGE]
- SHUFFLE [RS_92]
- PartitionCols:_col0
- 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_634] (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_599] (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_600] (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_622] (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_584] (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_585] (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]
+ Filter Operator [FIL_201] (rows=52798137 width=135)
+ predicate:(_col1 > (2 * _col2))
+ Group By Operator [GBY_200] (rows=158394413 width=135)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0
+ <-Reducer 75 [SIMPLE_EDGE]
+ SHUFFLE [RS_199]
+ PartitionCols:_col0
+ Group By Operator [GBY_198] (rows=316788826 width=135)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","sum(_col2)"],keys:_col0
+ Select Operator [SEL_196] (rows=316788826 width=135)
+ Output:["_col0","_col1","_col2"]
+ Merge Join Operator [MERGEJOIN_603] (rows=316788826 width=135)
+ Conds:RS_193._col0, _col1=RS_194._col0, _col1(Inner),Output:["_col0","_col2","_col5","_col6","_col7"]
+ <-Map 74 [SIMPLE_EDGE]
+ SHUFFLE [RS_193]
+ PartitionCols:_col0, _col1
+ Select Operator [SEL_189] (rows=287989836 width=135)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_569] (rows=287989836 width=135)
+ predicate:(cs_order_number is not null and cs_item_sk is not null)
+ TableScan [TS_187] (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 77 [SIMPLE_EDGE]
+ SHUFFLE [RS_194]
+ PartitionCols:_col0, _col1
+ Select Operator [SEL_192] (rows=28798881 width=106)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_570] (rows=28798881 width=106)
+ predicate:(cr_order_number is not null and cr_item_sk is not null)
+ TableScan [TS_190] (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 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_256]
PartitionCols:_col2, _col1, _col3
- Select Operator [SEL_258] (rows=903860754 width=88)
- Output:["_col1","_col2","_col3","_col13","_col14","_col15","_col16"]
- Group By Operator [GBY_257] (rows=903860754 width=88)
+ 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"]
+ Group By Operator [GBY_125] (rows=746992327 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9, KEY._col10, KEY._col11, KEY._col12, KEY._col13
- <-Reducer 44 [SIMPLE_EDGE]
- SHUFFLE [RS_256]
+ <-Reducer 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_124]
PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
- 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
- Merge Join Operator [MERGEJOIN_657] (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_639] (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_603] (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]
+ 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)
+ Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col21","_col22","_col23","_col24","_col26","_col27","_col45","_col46","_col47","_col48","_col51"]
+ Filter Operator [FIL_121] (rows=1493984654 width=88)
+ predicate:(_col56 <> _col19)
+ Merge Join Operator [MERGEJOIN_591] (rows=1493984654 width=88)
+ Conds:RS_118._col39=RS_119._col0(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col21","_col22","_col23","_col24","_col26","_col27","_col45","_col46","_col47","_col48","_col51","_col56"]
+ <-Map 41 [SIMPLE_EDGE]
+ SHUFFLE [RS_119]
PartitionCols:_col0
- Select Operator [SEL_135] (rows=20 width=12)
- Output:["_col0"]
- Filter Operator [FIL_604] (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","_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col18","_col23","_col24","_col25","_col37","_col39","_col41","_col42","_col47","_col50"]
- Merge Join Operator [MERGEJOIN_655] (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_621] (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_654] (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_620] (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_653] (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_652] (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]
+ Select Operator [SEL_99] (rows=1861800 width=385)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_554] (rows=1861800 width=385)
+ predicate:cd_demo_sk is not null
+ TableScan [TS_97] (rows=1861800 width=385)
+ default@customer_demographics,cd1,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"]
+ <-Reducer 7 [SIMPLE_EDGE]
+ SHUFFLE [RS_118]
+ PartitionCols:_col39
+ Merge Join Operator [MERGEJOIN_590] (rows=1358167838 width=88)
+ Conds:RS_115._col0=RS_116._col18(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col21","_col22","_col23","_col24","_col26","_col27","_col39","_col45","_col46","_col47","_col48","_col51"]
+ <-Reducer 24 [SIMPLE_EDGE]
+ SHUFFLE [RS_116]
+ PartitionCols:_col18
+ Select Operator [SEL_96] (rows=1234698008 width=88)
+ Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col18","_col19","_col25","_col26","_col27","_col28","_col31"]
+ Merge Join Operator [MERGEJOIN_589] (rows=1234698008 width=88)
+ Conds:RS_93._col13=RS_94._col0(Inner),Output:["_col10","_col11","_col17","_col18","_col19","_col20","_col23","_col28","_col29","_col31","_col32","_col33","_col34"]
+ <-Map 40 [SIMPLE_EDGE]
+ SHUFFLE [RS_94]
+ PartitionCols:_col0
+ Select Operator [SEL_80] (rows=40000000 width=1014)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_553] (rows=40000000 width=1014)
+ predicate:ca_address_sk is not null
+ TableScan [TS_78] (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 23 [SIMPLE_EDGE]
+ SHUFFLE [RS_93]
+ PartitionCols:_col13
+ Merge Join Operator [MERGEJOIN_588] (rows=1122452711 width=88)
+ Conds:RS_90._col14=RS_91._col0(Inner),Output:["_col10","_col11","_col13","_col17","_col18","_col19","_col20","_col23","_col28","_col29"]
+ <-Map 39 [SIMPLE_EDGE]
+ SHUFFLE [RS_91]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_640] (rows=7920 width=107)
- Conds:RS_232._col1=RS_233._col0(Inner),Output:["_col0"]
- <-Map 47 [SIMPLE_EDGE]
- SHUFFLE [RS_232]
- PartitionCols:_col1
- Select Operator [SEL_138] (rows=7200 width=107)
- Output:["_col0","_col1"]
- Filter Operator [FIL_605] (rows=7200 width=107)
- predicate:(hd_demo_sk is not null and hd_income_band_sk is not null)
- TableScan [TS_136] (rows=7200 width=107)
- default@household_demographics,hd2,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_income_band_sk"]
- <-Map 53 [SIMPLE_EDGE]
- SHUFFLE [RS_233]
+ Select Operator [SEL_77] (rows=1704 width=1910)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_552] (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_75] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_zip"]
+ <-Reducer 22 [SIMPLE_EDGE]
+ SHUFFLE [RS_90]
+ PartitionCols:_col14
+ Merge Join Operator [MERGEJOIN_587] (rows=1020411534 width=88)
+ Conds:RS_87._col9=RS_88._col0(Inner),Output:["_col10","_col11","_col13","_col14","_col17","_col18","_col19","_col20","_col23"]
+ <-Reducer 21 [SIMPLE_EDGE]
+ SHUFFLE [RS_87]
+ PartitionCols:_col9
+ Merge Join Operator [MERGEJOIN_586] (rows=927646829 width=88)
+ Conds:RS_84._col0=RS_85._col9(Inner),Output:["_col9","_col10","_col11","_col13","_col14","_col17","_col18","_col19","_col20","_col23"]
+ <-Reducer 20 [SIMPLE_EDGE]
+ SHUFFLE [RS_84]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_580] (rows=7920 width=107)
+ Conds:RS_81._col1=RS_82._col0(Inner),Output:["_col0"]
+ <-Map 19 [SIMPLE_EDGE]
+ SHUFFLE [RS_81]
+ PartitionCols:_col1
+ Select Operator [SEL_27] (rows=7200 width=107)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_543] (rows=7200 width=107)
+ predicate:(hd_demo_sk is not null and hd_income_band_sk is not null)
+ TableScan [TS_25] (rows=7200 width=107)
+ default@household_demographics,hd1,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_income_band_sk"]
+ <-Map 25 [SIMPLE_EDGE]
+ SHUFFLE [RS_82]
+ PartitionCols:_col0
+ Select Operator [SEL_30] (rows=20 width=12)
+ Output:["_col0"]
+ Filter Operator [FIL_544] (rows=20 width=12)
+ predicate:ib_income_band_sk is not null
+ TableScan [TS_28] (rows=20 width=12)
+ default@income_band,ib1,Tbl:COMPLETE,Col:NONE,Output:["ib_income_band_sk"]
+ <-Reducer 30 [SIMPLE_EDGE]
+ SHUFFLE [RS_85]
+ PartitionCols:_col9
+ Select Operator [SEL_58] (rows=843315281 width=88)
+ Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col14","_col15","_col16","_col17","_col20"]
+ Merge Join Operator [MERGEJOIN_584] (rows=843315281 width=88)
+ Conds:RS_55._col7=RS_56._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col9","_col10","_col11","_col12","_col15"]
+ <-Map 34 [SIMPLE_EDGE]
+ SHUFFLE [RS_56]
+ PartitionCols:_col0
+ Select Operator [SEL_45] (rows=2300 width=1179)
+ Output:["_col0"]
+ Filter Operator [FIL_549] (rows=2300 width=1179)
+ predicate:p_promo_sk is not null
+ TableScan [TS_43] (rows=2300 width=1179)
+ default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk"]
+ <-Reducer 29 [SIMPLE_EDGE]
+ SHUFFLE [RS_55]
+ PartitionCols:_col7
+ Merge Join Operator [MERGEJOIN_583] (rows=766650239 width=88)
+ Conds:RS_52._col0=RS_53._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col15"]
+ <-Map 33 [SIMPLE_EDGE]
+ SHUFFLE [RS_53]
+ PartitionCols:_col0
+ Select Operator [SEL_42] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_548] (rows=36524 width=1119)
+ predicate:((d_year = 2000) and d_date_sk is not null)
+ TableScan [TS_40] (rows=73049 width=1119)
+ default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 28 [SIMPLE_EDGE]
+ SHUFFLE [RS_52]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_582] (rows=696954748 width=88)
+ Conds:RS_49._col1, _col8=RS_50._col0, _col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col15"]
+ <-Map 32 [SIMPLE_EDGE]
+ SHUFFLE [RS_50]
+ PartitionCols:_col0, _col1
+ Select Operator [SEL_39] (rows=57591150 width=77)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_547] (rows=57591150 width=77)
+ predicate:(sr_item_sk is not null and sr_ticket_number is not null)
+ TableScan [TS_37] (rows=57591150 width=77)
+ default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number"]
+ <-Reducer 27 [SIMPLE_EDGE]
+ SHUFFLE [RS_49]
+ PartitionCols:_col1, _col8
+ Merge Join Operator [MERGEJOIN_581] (rows=633595212 width=88)
+ Conds:RS_46._col1=RS_47._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"]
+ <-Map 26 [SIMPLE_EDGE]
+ SHUFFLE [RS_46]
+ PartitionCols:_col1
+ Select Operator [SEL_33] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"]
+ Filter Operator [FIL_545] (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_31] (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 31 [SIMPLE_EDGE]
+ SHUFFLE [RS_47]
+ PartitionCols:_col0
+ Select Operator [SEL_36] (rows=2851 width=1436)
+ Output:["_col0","_col3"]
+ Filter Operator [FIL_546] (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_34] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_color","i_product_name"]
+ <-Reducer 37 [SIMPLE_EDGE]
+ SHUFFLE [RS_88]
PartitionCols:_col0
- Select Operator [SEL_141] (rows=20 width=12)
+ Select Operator [SEL_74] (rows=52798137 width=135)
Output:["_col0"]
- Filter Operator [FIL_606] (rows=20 width=12)
- predicate:ib_income_band_sk is not null
- TableScan [TS_139] (rows=20 width=12)
- default@income_band,ib2,Tbl:COMPLETE,Col:NONE,Output:["ib_income_band_sk"]
- <-Reducer 60 [SIMPLE_EDGE]
- SHUFFLE [RS_236]
- PartitionCols:_col17
- Select Operator [SEL_209] (rows=1122452711 width=88)
- Output:["_col2","_col5","_col6","_col10","_col11","_col12","_col17","_col18","_col24","_col26","_col28","_col29","_col34","_col37"]
- Merge Join Operator [MERGEJOIN_650] (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]
+ Filter Operator [FIL_73] (rows=52798137 width=135)
+ predicate:(_col1 > (2 * _col2))
+ Group By Operator [GBY_72] (rows=158394413 width=135)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0
+ <-Reducer 36 [SIMPLE_EDGE]
+ SHUFFLE [RS_71]
+ PartitionCols:_col0
+ Group By Operator [GBY_70] (rows=316788826 width=135)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","sum(_col2)"],keys:_col0
+ Select Operator [SEL_68] (rows=316788826 width=135)
+ Output:["_col0","_col1","_col2"]
+ Merge Join Operator [MERGEJOIN_585] (rows=316788826 width=135)
+ Conds:RS_65._col0, _col1=RS_66._col0, _col1(Inner),Output:["_col0","_col2","_col5","_col6","_col7"]
+ <-Map 35 [SIMPLE_EDGE]
+ SHUFFLE [RS_65]
+ PartitionCols:_col0, _col1
+ Select Operator [SEL_61] (rows=287989836 width=135)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_550] (rows=287989836 width=135)
+ predicate:(cs_order_number is not null and cs_item_sk is not null)
+ TableScan [TS_59] (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 38 [SIMPLE_EDGE]
+ SHUFFLE [RS_66]
+ PartitionCols:_col0, _col1
+ Select Operator [SEL_64] (rows=28798881 width=106)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_551] (rows=28798881 width=106)
+ predicate:(cr_order_number is not null and cr_item_sk is not null)
+ TableScan [TS_62] (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 6 [SIMPLE_EDGE]
+ SHUFFLE [RS_115]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_579] (rows=128840811 width=860)
+ Conds:RS_112._col1=RS_113._col0(Inner),Output:["_col0","_col7","_col9","_col14","_col15","_col16","_col17","_col19"]
+ <-Map 18 [SIMPLE_EDGE]
+ SHUFFLE [RS_113]
+ PartitionCols:_col0
+ Select Operator [SEL_24] (rows=1861800 width=385)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_542] (rows=1861800 width=385)
+ predicate:cd_demo_sk is not null
+ TableScan [TS_22] (rows=1861800 width=385)
+ default@customer_demographics,cd2,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"]
+ <-Reducer 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_112]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_578] (rows=117128008 width=860)
+ Conds:RS_109._col3=RS_110._col0(Inner),Output:["_col0","_col1","_col7","_col9","_col14","_col15","_col16","_col17"]
+ <-Map 17 [SIMPLE_EDGE]
+ SHUFFLE [RS_110]
+ PartitionCols:_col0
+ Select Operator [SEL_21] (rows=40000000 width=1014)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_541] (rows=40000000 width=1014)
+ predicate:ca_address_sk is not null
+ TableScan [TS_19] (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 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_109]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_577] (rows=106480005 width=860)
+ Conds:RS_106._col2=RS_107._col0(Inner),Output:["_col0","_col1","_col3","_col7","_col9"]
+ <-Reducer 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_107]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_576] (rows=7920 width=107)
+ Conds:RS_15._col1=RS_16._col0(Inner),Output:["_col0"]
+ <-Map 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_15]
+ PartitionCols:_col1
+ Select Operator [SEL_11] (rows=7200 width=107)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_539] (rows=7200 width=107)
+ 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"]
+ <-Map 16 [SIMPLE_EDGE]
+ SHUFFLE [RS_16]
PartitionCols:_col0
- Select Operator [SEL_202] (rows=2300 width=1179)
+ Select Operator [SEL_14] (rows=20 width=12)
Output:["_col0"]
- Filter Operator [FIL_617] (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_649] (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]
+ Filter Operator [FIL_540] (rows=20 width=12)
+ 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"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_106]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_575] (rows=96800003 width=860)
+ Conds:RS_103._col4=RS_104._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col7","_col9"]
+ <-Map 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_104]
+ PartitionCols:_col0
+ Select Operator [SEL_8] (rows=73049 width=1119)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_538] (rows=73049 width=1119)
+ predicate:d_date_sk is not null
+ TableScan [TS_6] (rows=73049 width=1119)
+ default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_103]
+ PartitionCols:_col4
+ Merge Join Operator [MERGEJOIN_574] (rows=88000001 width=860)
+ Conds:RS_100._col5=RS_101._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col7"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_100]
+ PartitionCols:_col5
+ Select Operator [SEL_2] (rows=80000000 width=860)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
+ Filter Operator [FIL_536] (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_0] (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 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_101]
PartitionCols:_col0
- Select Operator [SEL_199] (rows=2851 width=1436)
- Output:["_col0","_col3"]
- Filter Operator [FIL_616] (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","_col4","_col5","_col7","_col9","_col10","_col11","_col16","_col17","_col23","_col25","_col27","_col28"]
- 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_648] (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_643] (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_610] (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_642] (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_609] (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_641] (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_607] (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_608] (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","_col3","_col4","_col6","_col7","_col9","_col11","_col12","_col13","_col19","_col20"]
- Merge Join Operator [MERGEJOIN_647] (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_615] (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_646] (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_614] (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_645] (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_613] (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_644] (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_611] (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_612] (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_651] (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_618] (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_619] (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"]
+ Select Operator [SEL_5] (rows=73049 width=1119)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_537] (rows=73049 width=1119)
+ 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"]
diff --git a/ql/src/test/results/clientpositive/perf/query65.q.out b/ql/src/test/results/clientpositive/perf/query65.q.out
index 901bcfd..db671aa 100644
--- a/ql/src/test/results/clientpositive/perf/query65.q.out
+++ b/ql/src/test/results/clientpositive/perf/query65.q.out
@@ -90,108 +90,106 @@ Stage-0
limit:100
Stage-1
Reducer 6
- File Output Operator [FS_52]
- Limit [LIM_51] (rows=100 width=88)
+ File Output Operator [FS_51]
+ Limit [LIM_50] (rows=100 width=88)
Number of rows:100
- Select Operator [SEL_50] (rows=255550079 width=88)
+ Select Operator [SEL_49] (rows=255550079 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
<-Reducer 5 [SIMPLE_EDGE]
- SHUFFLE [RS_49]
- Select Operator [SEL_48] (rows=255550079 width=88)
+ SHUFFLE [RS_48]
+ Select Operator [SEL_47] (rows=255550079 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Filter Operator [FIL_47] (rows=255550079 width=88)
- predicate:(_col11 <= (0.1 * _col8))
- Select Operator [SEL_46] (rows=766650239 width=88)
- Output:["_col1","_col3","_col4","_col5","_col6","_col8","_col11"]
- Merge Join Operator [MERGEJOIN_82] (rows=766650239 width=88)
- Conds:RS_43._col1=RS_44._col0(Inner),Output:["_col2","_col4","_col6","_col8","_col9","_col10","_col11"]
- <-Map 13 [SIMPLE_EDGE]
- SHUFFLE [RS_44]
- PartitionCols:_col0
- Select Operator [SEL_38] (rows=462000 width=1436)
- Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_78] (rows=462000 width=1436)
- predicate:i_item_sk is not null
- TableScan [TS_36] (rows=462000 width=1436)
- default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_desc","i_current_price","i_wholesale_cost","i_brand"]
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_43]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_81] (rows=696954748 width=88)
- Conds:RS_39._col0=RS_40._col0(Inner),RS_39._col0=RS_41._col0(Inner),Output:["_col1","_col2","_col4","_col6"]
- <-Map 12 [SIMPLE_EDGE]
- SHUFFLE [RS_41]
- PartitionCols:_col0
- Select Operator [SEL_35] (rows=1704 width=1910)
- Output:["_col0","_col1"]
- Filter Operator [FIL_77] (rows=1704 width=1910)
- predicate:s_store_sk is not null
- TableScan [TS_33] (rows=1704 width=1910)
- default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name"]
- <-Reducer 10 [SIMPLE_EDGE]
- SHUFFLE [RS_40]
- PartitionCols:_col0
- Select Operator [SEL_32] (rows=158398803 width=88)
- Output:["_col0","_col1"]
- Group By Operator [GBY_31] (rows=158398803 width=88)
- Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col1
- Select Operator [SEL_27] (rows=316797606 width=88)
- Output:["_col1","_col2"]
- Group By Operator [GBY_26] (rows=316797606 width=88)
- Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
- <-Reducer 9 [SIMPLE_EDGE]
- SHUFFLE [RS_25]
- PartitionCols:_col0
- Group By Operator [GBY_24] (rows=633595212 width=88)
- Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1
- Merge Join Operator [MERGEJOIN_80] (rows=633595212 width=88)
- Conds:RS_20._col0=RS_21._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 11 [SIMPLE_EDGE]
- SHUFFLE [RS_21]
- PartitionCols:_col0
- Select Operator [SEL_19] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_76] (rows=8116 width=1119)
- predicate:(d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null)
- TableScan [TS_17] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"]
- <-Map 8 [SIMPLE_EDGE]
- SHUFFLE [RS_20]
- PartitionCols:_col0
- Select Operator [SEL_16] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_75] (rows=575995635 width=88)
- predicate:(ss_sold_date_sk is not null and ss_store_sk is not null)
- TableScan [TS_14] (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"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_39]
- PartitionCols:_col0
- Group By Operator [GBY_12] (rows=316797606 width=88)
- Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_11]
- PartitionCols:_col0, _col1
- Group By Operator [GBY_10] (rows=633595212 width=88)
- Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1
- Merge Join Operator [MERGEJOIN_79] (rows=633595212 width=88)
- Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 1 [SIMPLE_EDGE]
- SHUFFLE [RS_6]
- PartitionCols:_col0
- Select Operator [SEL_2] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_73] (rows=575995635 width=88)
- predicate:(ss_sold_date_sk is not null and ss_store_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_store_sk","ss_sales_price"]
- <-Map 7 [SIMPLE_EDGE]
- SHUFFLE [RS_7]
- PartitionCols:_col0
- Select Operator [SEL_5] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_74] (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,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"]
+ Merge Join Operator [MERGEJOIN_81] (rows=255550079 width=88)
+ Conds:RS_44._col1=RS_45._col0(Inner),Output:["_col2","_col6","_col8","_col9","_col10","_col11"]
+ <-Map 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_45]
+ PartitionCols:_col0
+ Select Operator [SEL_38] (rows=462000 width=1436)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_77] (rows=462000 width=1436)
+ predicate:i_item_sk is not null
+ TableScan [TS_36] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_desc","i_current_price","i_wholesale_cost","i_brand"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_44]
+ PartitionCols:_col1
+ Filter Operator [FIL_43] (rows=232318249 width=88)
+ predicate:(_col2 <= (0.1 * _col4))
+ Merge Join Operator [MERGEJOIN_80] (rows=696954748 width=88)
+ Conds:RS_39._col0=RS_40._col0(Inner),RS_39._col0=RS_41._col0(Inner),Output:["_col1","_col2","_col4","_col6"]
+ <-Map 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_41]
+ PartitionCols:_col0
+ Select Operator [SEL_35] (rows=1704 width=1910)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_76] (rows=1704 width=1910)
+ predicate:s_store_sk is not null
+ TableScan [TS_33] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name"]
+ <-Reducer 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_40]
+ PartitionCols:_col0
+ Select Operator [SEL_32] (rows=158398803 width=88)
+ Output:["_col0","_col1"]
+ Group By Operator [GBY_31] (rows=158398803 width=88)
+ Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col1
+ Select Operator [SEL_27] (rows=316797606 width=88)
+ Output:["_col1","_col2"]
+ Group By Operator [GBY_26] (rows=316797606 width=88)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
+ <-Reducer 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_25]
+ PartitionCols:_col0
+ Group By Operator [GBY_24] (rows=633595212 width=88)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1
+ Merge Join Operator [MERGEJOIN_79] (rows=633595212 width=88)
+ Conds:RS_20._col0=RS_21._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_21]
+ PartitionCols:_col0
+ Select Operator [SEL_19] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_75] (rows=8116 width=1119)
+ predicate:(d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null)
+ TableScan [TS_17] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"]
+ <-Map 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_20]
+ PartitionCols:_col0
+ Select Operator [SEL_16] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_74] (rows=575995635 width=88)
+ predicate:(ss_sold_date_sk is not null and ss_store_sk is not null)
+ TableScan [TS_14] (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"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_39]
+ PartitionCols:_col0
+ Group By Operator [GBY_12] (rows=316797606 width=88)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_11]
+ PartitionCols:_col0, _col1
+ Group By Operator [GBY_10] (rows=633595212 width=88)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1
+ Merge Join Operator [MERGEJOIN_78] (rows=633595212 width=88)
+ Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_6]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_72] (rows=575995635 width=88)
+ predicate:(ss_sold_date_sk is not null and ss_store_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_store_sk","ss_sales_price"]
+ <-Map 7 [SIMPLE_EDGE]
+ SHUFFLE [RS_7]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_73] (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,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"]
diff --git a/ql/src/test/results/clientpositive/perf/query69.q.out b/ql/src/test/results/clientpositive/perf/query69.q.out
index 8bd154f..87087ac 100644
--- a/ql/src/test/results/clientpositive/perf/query69.q.out
+++ b/ql/src/test/results/clientpositive/perf/query69.q.out
@@ -91,15 +91,15 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 10 <- Map 12 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE)
-Reducer 11 <- Reducer 10 (SIMPLE_EDGE)
-Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE)
-Reducer 15 <- Reducer 14 (SIMPLE_EDGE)
+Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE)
+Reducer 12 <- Reducer 11 (SIMPLE_EDGE)
+Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 17 (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 8 (SIMPLE_EDGE)
Reducer 20 <- Reducer 19 (SIMPLE_EDGE)
-Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 4 <- Map 17 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 12 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 5 <- Reducer 20 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
@@ -112,46 +112,46 @@ Stage-0
File Output Operator [FS_76]
Limit [LIM_75] (rows=100 width=88)
Number of rows:100
- Select Operator [SEL_74] (rows=52707204 width=88)
+ Select Operator [SEL_74] (rows=95831279 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
<-Reducer 6 [SIMPLE_EDGE]
SHUFFLE [RS_73]
- Select Operator [SEL_72] (rows=52707204 width=88)
+ Select Operator [SEL_72] (rows=95831279 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col6"]
- Group By Operator [GBY_71] (rows=52707204 width=88)
+ Group By Operator [GBY_71] (rows=95831279 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4
<-Reducer 5 [SIMPLE_EDGE]
SHUFFLE [RS_70]
PartitionCols:_col0, _col1, _col2, _col3, _col4
- Group By Operator [GBY_69] (rows=105414409 width=88)
+ Group By Operator [GBY_69] (rows=191662559 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count()"],keys:_col6, _col7, _col8, _col9, _col10
- Select Operator [SEL_68] (rows=105414409 width=88)
+ Select Operator [SEL_68] (rows=191662559 width=88)
Output:["_col6","_col7","_col8","_col9","_col10"]
- Filter Operator [FIL_67] (rows=105414409 width=88)
+ Filter Operator [FIL_67] (rows=191662559 width=88)
predicate:_col15 is null
- Merge Join Operator [MERGEJOIN_117] (rows=210828818 width=88)
+ Merge Join Operator [MERGEJOIN_114] (rows=383325119 width=88)
Conds:RS_64._col0=RS_65._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col15"]
<-Reducer 20 [SIMPLE_EDGE]
SHUFFLE [RS_65]
PartitionCols:_col0
- Select Operator [SEL_63] (rows=79197206 width=135)
+ Select Operator [SEL_63] (rows=158394413 width=135)
Output:["_col0","_col1"]
- Group By Operator [GBY_62] (rows=79197206 width=135)
+ Group By Operator [GBY_62] (rows=158394413 width=135)
Output:["_col0"],keys:KEY._col0
<-Reducer 19 [SIMPLE_EDGE]
SHUFFLE [RS_61]
PartitionCols:_col0
- Group By Operator [GBY_60] (rows=158394413 width=135)
+ Group By Operator [GBY_60] (rows=316788826 width=135)
Output:["_col0"],keys:_col1
- Merge Join Operator [MERGEJOIN_116] (rows=158394413 width=135)
+ Merge Join Operator [MERGEJOIN_112] (rows=316788826 width=135)
Conds:RS_56._col0=RS_57._col0(Inner),Output:["_col1"]
<-Map 18 [SIMPLE_EDGE]
SHUFFLE [RS_56]
PartitionCols:_col0
- Select Operator [SEL_52] (rows=143994918 width=135)
+ Select Operator [SEL_52] (rows=287989836 width=135)
Output:["_col0","_col1"]
- Filter Operator [FIL_109] (rows=143994918 width=135)
- predicate:((cs_ship_customer_sk = cs_ship_customer_sk) and cs_sold_date_sk is not null)
+ Filter Operator [FIL_106] (rows=287989836 width=135)
+ predicate:(cs_ship_customer_sk is not null and cs_sold_date_sk is not null)
TableScan [TS_50] (rows=287989836 width=135)
default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_customer_sk"]
<-Map 21 [SIMPLE_EDGE]
@@ -159,108 +159,108 @@ Stage-0
PartitionCols:_col0
Select Operator [SEL_55] (rows=4058 width=1119)
Output:["_col0"]
- Filter Operator [FIL_110] (rows=4058 width=1119)
+ Filter Operator [FIL_107] (rows=4058 width=1119)
predicate:((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null)
TableScan [TS_53] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
<-Reducer 4 [SIMPLE_EDGE]
SHUFFLE [RS_64]
PartitionCols:_col0
- Select Operator [SEL_49] (rows=191662558 width=88)
+ Select Operator [SEL_49] (rows=348477374 width=88)
Output:["_col0","_col6","_col7","_col8","_col9","_col10"]
- Filter Operator [FIL_48] (rows=191662558 width=88)
+ Filter Operator [FIL_48] (rows=348477374 width=88)
predicate:_col13 is null
- Select Operator [SEL_47] (rows=383325116 width=88)
+ Select Operator [SEL_47] (rows=696954748 width=88)
Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col13"]
- Merge Join Operator [MERGEJOIN_115] (rows=383325116 width=88)
- Conds:RS_44._col1=RS_45._col0(Inner),Output:["_col0","_col7","_col9","_col10","_col11","_col12","_col13"]
- <-Map 17 [SIMPLE_EDGE]
+ Merge Join Operator [MERGEJOIN_113] (rows=696954748 width=88)
+ Conds:RS_43._col0=RS_44._col0(Left Outer),RS_43._col0=RS_45._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col12"]
+ <-Reducer 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_44]
+ PartitionCols:_col0
+ Select Operator [SEL_22] (rows=79201469 width=135)
+ Output:["_col0","_col1"]
+ Group By Operator [GBY_21] (rows=79201469 width=135)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_20]
+ PartitionCols:_col0
+ Group By Operator [GBY_19] (rows=158402938 width=135)
+ Output:["_col0"],keys:_col1
+ Merge Join Operator [MERGEJOIN_110] (rows=158402938 width=135)
+ Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col1"]
+ <-Map 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_15]
+ PartitionCols:_col0
+ Select Operator [SEL_11] (rows=144002668 width=135)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_102] (rows=144002668 width=135)
+ predicate:(ws_bill_customer_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_bill_customer_sk"]
+ <-Map 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_16]
+ PartitionCols:_col0
+ Select Operator [SEL_14] (rows=4058 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_103] (rows=4058 width=1119)
+ predicate:((d_year = 1999) and d_moy BETWEEN 1 AND 3 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_year","d_moy"]
+ <-Reducer 16 [SIMPLE_EDGE]
SHUFFLE [RS_45]
PartitionCols:_col0
- Select Operator [SEL_36] (rows=1861800 width=385)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Filter Operator [FIL_108] (rows=1861800 width=385)
- predicate:cd_demo_sk is not null
- TableScan [TS_34] (rows=1861800 width=385)
- default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status","cd_purchase_estimate","cd_credit_rating"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_44]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_114] (rows=348477371 width=88)
- Conds:RS_40._col0=RS_41._col0(Inner),RS_40._col0=RS_42._col0(Left Outer),Output:["_col0","_col1","_col7"]
- <-Reducer 11 [SIMPLE_EDGE]
- SHUFFLE [RS_41]
- PartitionCols:_col0
- Group By Operator [GBY_18] (rows=158398802 width=88)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 10 [SIMPLE_EDGE]
- SHUFFLE [RS_17]
- PartitionCols:_col0
- Group By Operator [GBY_16] (rows=316797605 width=88)
- Output:["_col0"],keys:_col1
- Merge Join Operator [MERGEJOIN_112] (rows=316797605 width=88)
- Conds:RS_12._col0=RS_13._col0(Inner),Output:["_col1"]
- <-Map 12 [SIMPLE_EDGE]
- SHUFFLE [RS_13]
- PartitionCols:_col0
- Select Operator [SEL_11] (rows=4058 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_105] (rows=4058 width=1119)
- predicate:((d_year = 1999) and d_moy BETWEEN 1 AND 3 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","d_moy"]
- <-Map 9 [SIMPLE_EDGE]
- SHUFFLE [RS_12]
- PartitionCols:_col0
- Select Operator [SEL_8] (rows=287997817 width=88)
- Output:["_col0","_col1"]
- Filter Operator [FIL_104] (rows=287997817 width=88)
- predicate:((ss_customer_sk = ss_customer_sk) and ss_sold_date_sk is not null)
- TableScan [TS_6] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"]
+ Group By Operator [GBY_35] (rows=316797606 width=88)
+ Output:["_col0"],keys:KEY._col0
<-Reducer 15 [SIMPLE_EDGE]
- SHUFFLE [RS_42]
+ SHUFFLE [RS_34]
PartitionCols:_col0
- Select Operator [SEL_33] (rows=39600734 width=135)
- Output:["_col0","_col1"]
- Group By Operator [GBY_32] (rows=39600734 width=135)
- Output:["_col0"],keys:KEY._col0
- <-Reducer 14 [SIMPLE_EDGE]
- SHUFFLE [RS_31]
+ Group By Operator [GBY_33] (rows=633595212 width=88)
+ Output:["_col0"],keys:_col1
+ Merge Join Operator [MERGEJOIN_111] (rows=633595212 width=88)
+ Conds:RS_29._col0=RS_30._col0(Inner),Output:["_col1"]
+ <-Map 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_29]
PartitionCols:_col0
- Group By Operator [GBY_30] (rows=79201469 width=135)
- Output:["_col0"],keys:_col1
- Merge Join Operator [MERGEJOIN_113] (rows=79201469 width=135)
- Conds:RS_26._col0=RS_27._col0(Inner),Output:["_col1"]
- <-Map 13 [SIMPLE_EDGE]
- SHUFFLE [RS_26]
- PartitionCols:_col0
- Select Operator [SEL_22] (rows=72001334 width=135)
- Output:["_col0","_col1"]
- Filter Operator [FIL_106] (rows=72001334 width=135)
- predicate:((ws_bill_customer_sk = ws_bill_customer_sk) and ws_sold_date_sk is not null)
- TableScan [TS_20] (rows=144002668 width=135)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"]
- <-Map 16 [SIMPLE_EDGE]
- SHUFFLE [RS_27]
- PartitionCols:_col0
- Select Operator [SEL_25] (rows=4058 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_107] (rows=4058 width=1119)
- predicate:((d_year = 1999) and d_moy BETWEEN 1 AND 3 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_moy"]
+ Select Operator [SEL_25] (rows=575995635 width=88)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_104] (rows=575995635 width=88)
+ predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_23] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"]
+ <-Map 17 [SIMPLE_EDGE]
+ SHUFFLE [RS_30]
+ PartitionCols:_col0
+ Select Operator [SEL_28] (rows=4058 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_105] (rows=4058 width=1119)
+ predicate:((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null)
+ TableScan [TS_26] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_43]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_109] (rows=96800003 width=860)
+ Conds:RS_40._col1=RS_41._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10"]
+ <-Map 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_41]
+ PartitionCols:_col0
+ Select Operator [SEL_8] (rows=1861800 width=385)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
+ Filter Operator [FIL_101] (rows=1861800 width=385)
+ predicate:cd_demo_sk is not null
+ TableScan [TS_6] (rows=1861800 width=385)
+ default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status","cd_purchase_estimate","cd_credit_rating"]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_40]
- PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_111] (rows=88000001 width=860)
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_108] (rows=88000001 width=860)
Conds:RS_37._col2=RS_38._col0(Inner),Output:["_col0","_col1"]
<-Map 1 [SIMPLE_EDGE]
SHUFFLE [RS_37]
PartitionCols:_col2
Select Operator [SEL_2] (rows=80000000 width=860)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_102] (rows=80000000 width=860)
+ Filter Operator [FIL_99] (rows=80000000 width=860)
predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null)
TableScan [TS_0] (rows=80000000 width=860)
default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"]
@@ -269,7 +269,7 @@ Stage-0
PartitionCols:_col0
Select Operator [SEL_5] (rows=20000000 width=1014)
Output:["_col0"]
- Filter Operator [FIL_103] (rows=20000000 width=1014)
+ Filter Operator [FIL_100] (rows=20000000 width=1014)
predicate:((ca_state) IN ('CO', 'IL', 'MN') and ca_address_sk is not null)
TableScan [TS_3] (rows=40000000 width=1014)
default@customer_address,ca,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"]
diff --git a/ql/src/test/results/clientpositive/perf/query70.q.out b/ql/src/test/results/clientpositive/perf/query70.q.out
index 95b740b..8e42fac 100644
--- a/ql/src/test/results/clientpositive/perf/query70.q.out
+++ b/ql/src/test/results/clientpositive/perf/query70.q.out
@@ -91,117 +91,115 @@ Stage-0
limit:100
Stage-1
Reducer 7
- File Output Operator [FS_62]
- Limit [LIM_61] (rows=100 width=88)
+ File Output Operator [FS_60]
+ Limit [LIM_59] (rows=100 width=88)
Number of rows:100
- Select Operator [SEL_60] (rows=1149975358 width=88)
+ Select Operator [SEL_58] (rows=1149975358 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"]
<-Reducer 6 [SIMPLE_EDGE]
- SHUFFLE [RS_59]
- Select Operator [SEL_57] (rows=1149975358 width=88)
+ SHUFFLE [RS_57]
+ Select Operator [SEL_55] (rows=1149975358 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"]
- PTF Operator [PTF_56] (rows=1149975358 width=88)
+ 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_55] (rows=1149975358 width=88)
+ Select Operator [SEL_53] (rows=1149975358 width=88)
Output:["_col0","_col1","_col4","_col5"]
<-Reducer 5 [SIMPLE_EDGE]
- SHUFFLE [RS_54]
+ SHUFFLE [RS_52]
PartitionCols:(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)
+ Select Operator [SEL_51] (rows=1149975358 width=88)
Output:["_col0","_col1","_col4","_col5"]
- Group By Operator [GBY_52] (rows=1149975358 width=88)
+ Group By Operator [GBY_50] (rows=1149975358 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
<-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_51]
+ SHUFFLE [RS_49]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_50] (rows=2299950717 width=88)
+ Group By Operator [GBY_48] (rows=2299950717 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)"],keys:_col0, _col1, 0
- Select Operator [SEL_48] (rows=766650239 width=88)
+ Select Operator [SEL_46] (rows=766650239 width=88)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_90] (rows=766650239 width=88)
- Conds:RS_45._col7=RS_46._col0(Left Semi),Output:["_col2","_col6","_col7"]
+ Merge Join Operator [MERGEJOIN_88] (rows=766650239 width=88)
+ Conds:RS_43._col7=RS_44._col0(Inner),Output:["_col2","_col6","_col7"]
<-Reducer 14 [SIMPLE_EDGE]
- SHUFFLE [RS_46]
+ SHUFFLE [RS_44]
PartitionCols:_col0
- 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_82] (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
- Merge Join Operator [MERGEJOIN_89] (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_85] (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_88] (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_83] (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_84] (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"]
+ Select Operator [SEL_32] (rows=116159124 width=88)
+ Output:["_col0"]
+ Filter Operator [FIL_80] (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
+ Merge Join Operator [MERGEJOIN_87] (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_83] (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_86] (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_81] (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_82] (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"]
<-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_45]
+ SHUFFLE [RS_43]
PartitionCols:_col7
- Merge Join Operator [MERGEJOIN_87] (rows=696954748 width=88)
+ Merge Join Operator [MERGEJOIN_85] (rows=696954748 width=88)
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"]
- Filter Operator [FIL_81] (rows=1704 width=1910)
+ Filter Operator [FIL_79] (rows=1704 width=1910)
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
- Merge Join Operator [MERGEJOIN_86] (rows=633595212 width=88)
+ Merge Join Operator [MERGEJOIN_84] (rows=633595212 width=88)
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"]
- Filter Operator [FIL_79] (rows=575995635 width=88)
+ Filter Operator [FIL_77] (rows=575995635 width=88)
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"]
@@ -210,7 +208,7 @@ Stage-0
PartitionCols:_col0
Select Operator [SEL_5] (rows=8116 width=1119)
Output:["_col0"]
- Filter Operator [FIL_80] (rows=8116 width=1119)
+ Filter Operator [FIL_78] (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/query72.q.out b/ql/src/test/results/clientpositive/perf/query72.q.out
index 58e8174..e178d62 100644
--- a/ql/src/test/results/clientpositive/perf/query72.q.out
+++ b/ql/src/test/results/clientpositive/perf/query72.q.out
@@ -61,192 +61,190 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 10 <- Map 22 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
-Reducer 11 <- Map 23 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE)
-Reducer 12 <- Reducer 11 (SIMPLE_EDGE)
-Reducer 13 <- Reducer 12 (SIMPLE_EDGE)
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE)
-Reducer 3 <- Map 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 4 <- Map 16 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
-Reducer 5 <- Map 17 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
-Reducer 6 <- Map 18 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
-Reducer 7 <- Map 19 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
-Reducer 8 <- Map 20 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
-Reducer 9 <- Map 21 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE)
+Reducer 13 <- Map 18 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE)
+Reducer 14 <- Map 19 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE)
+Reducer 15 <- Map 20 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE)
+Reducer 16 <- Map 21 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
+Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
+Reducer 6 <- Map 10 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+Reducer 7 <- Reducer 16 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
+Reducer 8 <- Map 22 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
+Reducer 9 <- Map 23 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:100
Stage-1
- Reducer 13
- File Output Operator [FS_76]
- Limit [LIM_75] (rows=100 width=135)
+ Reducer 4
+ File Output Operator [FS_75]
+ Limit [LIM_74] (rows=100 width=135)
Number of rows:100
- Select Operator [SEL_74] (rows=41498422 width=135)
+ Select Operator [SEL_73] (rows=37725837 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- <-Reducer 12 [SIMPLE_EDGE]
- SHUFFLE [RS_73]
- Group By Operator [GBY_71] (rows=41498422 width=135)
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_72]
+ Group By Operator [GBY_70] (rows=37725837 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 11 [SIMPLE_EDGE]
- SHUFFLE [RS_70]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_69]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_69] (rows=82996844 width=135)
+ Group By Operator [GBY_68] (rows=75451675 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(_col3)","count(_col4)","count()"],keys:_col0, _col1, _col2
- Select Operator [SEL_67] (rows=82996844 width=135)
+ Select Operator [SEL_66] (rows=75451675 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Merge Join Operator [MERGEJOIN_143] (rows=82996844 width=135)
- Conds:RS_64._col4, _col6=RS_65._col0, _col1(Left Outer),Output:["_col13","_col15","_col22","_col28"]
- <-Map 23 [SIMPLE_EDGE]
- SHUFFLE [RS_65]
+ Merge Join Operator [MERGEJOIN_142] (rows=75451675 width=135)
+ Conds:RS_63._col0, _col1=RS_64._col4, _col6(Right Outer),Output:["_col15","_col17","_col24","_col30"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_63]
PartitionCols:_col0, _col1
- Select Operator [SEL_60] (rows=28798881 width=106)
+ Select Operator [SEL_2] (rows=28798881 width=106)
Output:["_col0","_col1"]
- Filter Operator [FIL_133] (rows=28798881 width=106)
+ Filter Operator [FIL_122] (rows=28798881 width=106)
predicate:cr_item_sk is not null
- TableScan [TS_58] (rows=28798881 width=106)
+ TableScan [TS_0] (rows=28798881 width=106)
default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number"]
- <-Reducer 10 [SIMPLE_EDGE]
+ <-Reducer 9 [SIMPLE_EDGE]
SHUFFLE [RS_64]
PartitionCols:_col4, _col6
- Merge Join Operator [MERGEJOIN_142] (rows=75451675 width=135)
- Conds:RS_61._col5=RS_62._col0(Left Outer),Output:["_col4","_col6","_col13","_col15","_col22","_col28"]
- <-Map 22 [SIMPLE_EDGE]
- SHUFFLE [RS_62]
- PartitionCols:_col0
- Select Operator [SEL_57] (rows=2300 width=1179)
- Output:["_col0"]
- TableScan [TS_56] (rows=2300 width=1179)
- default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk"]
- <-Reducer 9 [SIMPLE_EDGE]
- SHUFFLE [RS_61]
- PartitionCols:_col5
- Select Operator [SEL_55] (rows=68592431 width=135)
- Output:["_col4","_col5","_col6","_col13","_col15","_col22"]
- Filter Operator [FIL_54] (rows=68592431 width=135)
- predicate:(UDFToDouble(_col27) > (UDFToDouble(_col21) + 5.0))
- Select Operator [SEL_53] (rows=205777294 width=135)
- Output:["_col4","_col5","_col6","_col13","_col15","_col21","_col22","_col27"]
- Merge Join Operator [MERGEJOIN_141] (rows=205777294 width=135)
- Conds:RS_50._col10=RS_51._col0(Inner),Output:["_col4","_col5","_col6","_col13","_col14","_col23","_col25","_col27"]
- <-Map 21 [SIMPLE_EDGE]
- SHUFFLE [RS_51]
- PartitionCols:_col0
- Select Operator [SEL_31] (rows=27 width=1029)
- Output:["_col0","_col1"]
- Filter Operator [FIL_131] (rows=27 width=1029)
- predicate:w_warehouse_sk is not null
- TableScan [TS_29] (rows=27 width=1029)
- default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_warehouse_name"]
- <-Reducer 8 [SIMPLE_EDGE]
- SHUFFLE [RS_50]
- PartitionCols:_col10
- Merge Join Operator [MERGEJOIN_140] (rows=187070264 width=135)
- Conds:RS_47._col1=RS_48._col0(Inner),Output:["_col4","_col5","_col6","_col10","_col13","_col14","_col23","_col25"]
- <-Map 20 [SIMPLE_EDGE]
- SHUFFLE [RS_48]
- PartitionCols:_col0
- Select Operator [SEL_28] (rows=73049 width=1119)
- Output:["_col0","_col1"]
- Filter Operator [FIL_130] (rows=73049 width=1119)
- predicate:d_date_sk is not null
- TableScan [TS_26] (rows=73049 width=1119)
- default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
- <-Reducer 7 [SIMPLE_EDGE]
- SHUFFLE [RS_47]
+ Select Operator [SEL_62] (rows=68592431 width=135)
+ Output:["_col4","_col6","_col13","_col15","_col22","_col28"]
+ Filter Operator [FIL_61] (rows=68592431 width=135)
+ predicate:(UDFToDouble(_col28) > (UDFToDouble(_col17) + 5.0))
+ Merge Join Operator [MERGEJOIN_141] (rows=205777295 width=135)
+ Conds:RS_58._col9=RS_59._col0(Inner),Output:["_col5","_col7","_col12","_col14","_col17","_col18","_col24","_col28"]
+ <-Map 23 [SIMPLE_EDGE]
+ SHUFFLE [RS_59]
+ PartitionCols:_col0
+ Select Operator [SEL_47] (rows=73049 width=1119)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_132] (rows=73049 width=1119)
+ predicate:d_date_sk is not null
+ TableScan [TS_45] (rows=73049 width=1119)
+ default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
+ <-Reducer 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_58]
+ PartitionCols:_col9
+ Merge Join Operator [MERGEJOIN_140] (rows=187070265 width=135)
+ Conds:RS_55._col0, _col18=RS_56._col0, _col1(Inner),Output:["_col5","_col7","_col9","_col12","_col14","_col17","_col18","_col24"]
+ <-Map 22 [SIMPLE_EDGE]
+ SHUFFLE [RS_56]
+ PartitionCols:_col0, _col1
+ Select Operator [SEL_44] (rows=73049 width=1119)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_131] (rows=73049 width=1119)
+ predicate:(d_date_sk is not null and d_week_seq is not null)
+ TableScan [TS_42] (rows=73049 width=1119)
+ default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_week_seq"]
+ <-Reducer 7 [SIMPLE_EDGE]
+ SHUFFLE [RS_55]
+ PartitionCols:_col0, _col18
+ Filter Operator [FIL_54] (rows=170063874 width=135)
+ predicate:(_col3 < _col15)
+ Merge Join Operator [MERGEJOIN_139] (rows=510191624 width=135)
+ Conds:RS_51._col1=RS_52._col6(Inner),Output:["_col0","_col3","_col5","_col7","_col9","_col12","_col14","_col15","_col17","_col18","_col24"]
+ <-Reducer 16 [SIMPLE_EDGE]
+ SHUFFLE [RS_52]
+ PartitionCols:_col6
+ Select Operator [SEL_41] (rows=463810558 width=135)
+ Output:["_col1","_col3","_col6","_col8","_col9","_col11","_col12","_col18"]
+ Merge Join Operator [MERGEJOIN_138] (rows=463810558 width=135)
+ Conds:RS_38._col4=RS_39._col0(Inner),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16","_col18"]
+ <-Map 21 [SIMPLE_EDGE]
+ SHUFFLE [RS_39]
+ PartitionCols:_col0
+ Select Operator [SEL_25] (rows=462000 width=1436)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_130] (rows=462000 width=1436)
+ predicate:i_item_sk is not null
+ TableScan [TS_23] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_desc"]
+ <-Reducer 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_38]
+ PartitionCols:_col4
+ Merge Join Operator [MERGEJOIN_137] (rows=421645953 width=135)
+ Conds:RS_35._col5=RS_36._col0(Left Outer),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16"]
+ <-Map 20 [SIMPLE_EDGE]
+ SHUFFLE [RS_36]
+ PartitionCols:_col0
+ Select Operator [SEL_22] (rows=2300 width=1179)
+ Output:["_col0"]
+ TableScan [TS_21] (rows=2300 width=1179)
+ default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk"]
+ <-Reducer 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_35]
+ PartitionCols:_col5
+ Merge Join Operator [MERGEJOIN_136] (rows=383314495 width=135)
+ Conds:RS_32._col3=RS_33._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col9","_col10"]
+ <-Map 19 [SIMPLE_EDGE]
+ SHUFFLE [RS_33]
+ PartitionCols:_col0
+ Select Operator [SEL_20] (rows=3600 width=107)
+ Output:["_col0"]
+ Filter Operator [FIL_128] (rows=3600 width=107)
+ predicate:((hd_buy_potential = '1001-5000') 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 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_32]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_135] (rows=348467716 width=135)
+ Conds:RS_29._col2=RS_30._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col9","_col10"]
+ <-Map 18 [SIMPLE_EDGE]
+ SHUFFLE [RS_30]
+ PartitionCols:_col0
+ Select Operator [SEL_17] (rows=930900 width=385)
+ Output:["_col0"]
+ Filter Operator [FIL_127] (rows=930900 width=385)
+ predicate:((cd_marital_status = 'M') and cd_demo_sk is not null)
+ TableScan [TS_15] (rows=1861800 width=385)
+ default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"]
+ <-Reducer 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_29]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_134] (rows=316788826 width=135)
+ Conds:RS_26._col0=RS_27._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10"]
+ <-Map 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_26]
+ PartitionCols:_col0
+ Select Operator [SEL_11] (rows=287989836 width=135)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
+ Filter Operator [FIL_125] (rows=287989836 width=135)
+ predicate:(cs_item_sk is not null and cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_sold_date_sk is not null and cs_ship_date_sk is not null)
+ TableScan [TS_9] (rows=287989836 width=135)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_bill_cdemo_sk","cs_bill_hdemo_sk","cs_item_sk","cs_promo_sk","cs_order_number","cs_quantity"]
+ <-Map 17 [SIMPLE_EDGE]
+ SHUFFLE [RS_27]
+ PartitionCols:_col0
+ Select Operator [SEL_14] (rows=36524 width=1119)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_126] (rows=36524 width=1119)
+ predicate:((d_year = 2001) and d_date_sk is not null and d_week_seq is not null)
+ TableScan [TS_12] (rows=73049 width=1119)
+ default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_week_seq","d_year"]
+ <-Reducer 6 [SIMPLE_EDGE]
+ SHUFFLE [RS_51]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_139] (rows=170063873 width=135)
- Conds:RS_44._col4=RS_45._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col10","_col13","_col14","_col23"]
- <-Map 19 [SIMPLE_EDGE]
- SHUFFLE [RS_45]
+ Merge Join Operator [MERGEJOIN_133] (rows=41342400 width=15)
+ Conds:RS_48._col2=RS_49._col0(Inner),Output:["_col0","_col1","_col3","_col5"]
+ <-Map 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_49]
PartitionCols:_col0
- Select Operator [SEL_25] (rows=462000 width=1436)
+ Select Operator [SEL_8] (rows=27 width=1029)
Output:["_col0","_col1"]
- Filter Operator [FIL_129] (rows=462000 width=1436)
- predicate:i_item_sk is not null
- TableScan [TS_23] (rows=462000 width=1436)
- default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_desc"]
- <-Reducer 6 [SIMPLE_EDGE]
- SHUFFLE [RS_44]
- PartitionCols:_col4
- Merge Join Operator [MERGEJOIN_138] (rows=154603518 width=135)
- Conds:RS_41._col3=RS_42._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col10","_col13","_col14"]
- <-Map 18 [SIMPLE_EDGE]
- SHUFFLE [RS_42]
- PartitionCols:_col0
- Select Operator [SEL_22] (rows=3600 width=107)
- Output:["_col0"]
- Filter Operator [FIL_128] (rows=3600 width=107)
- predicate:((hd_buy_potential = '1001-5000') and hd_demo_sk is not null)
- TableScan [TS_20] (rows=7200 width=107)
- default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_buy_potential"]
- <-Reducer 5 [SIMPLE_EDGE]
- SHUFFLE [RS_41]
- PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_137] (rows=140548650 width=135)
- Conds:RS_38._col2=RS_39._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col10","_col13","_col14"]
- <-Map 17 [SIMPLE_EDGE]
- SHUFFLE [RS_39]
- PartitionCols:_col0
- Select Operator [SEL_19] (rows=930900 width=385)
- Output:["_col0"]
- Filter Operator [FIL_127] (rows=930900 width=385)
- predicate:((cd_marital_status = 'M') and cd_demo_sk is not null)
- TableScan [TS_17] (rows=1861800 width=385)
- default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"]
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_38]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_136] (rows=127771498 width=135)
- Conds:RS_35._col8, _col14=RS_36._col0, _col1(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col10","_col13","_col14"]
- <-Map 16 [SIMPLE_EDGE]
- SHUFFLE [RS_36]
- PartitionCols:_col0, _col1
- Select Operator [SEL_16] (rows=73049 width=1119)
- Output:["_col0","_col1"]
- Filter Operator [FIL_126] (rows=73049 width=1119)
- predicate:(d_date_sk is not null and d_week_seq is not null)
- TableScan [TS_14] (rows=73049 width=1119)
- default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_week_seq"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_35]
- PartitionCols:_col8, _col14
- Merge Join Operator [MERGEJOIN_135] (rows=116155905 width=135)
- Conds:RS_32._col0=RS_33._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col10","_col13","_col14"]
- <-Map 15 [SIMPLE_EDGE]
- SHUFFLE [RS_33]
- PartitionCols:_col0
- Select Operator [SEL_13] (rows=36524 width=1119)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_125] (rows=36524 width=1119)
- predicate:((d_year = 2001) and d_date_sk is not null and d_week_seq is not null)
- TableScan [TS_11] (rows=73049 width=1119)
- default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_week_seq","d_year"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_32]
- PartitionCols:_col0
- Select Operator [SEL_10] (rows=105596275 width=135)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col10"]
- Filter Operator [FIL_9] (rows=105596275 width=135)
- predicate:(_col11 < _col7)
- Merge Join Operator [MERGEJOIN_134] (rows=316788826 width=135)
- Conds:RS_6._col4=RS_7._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col10","_col11"]
- <-Map 1 [SIMPLE_EDGE]
- SHUFFLE [RS_6]
- PartitionCols:_col4
- Select Operator [SEL_2] (rows=287989836 width=135)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- Filter Operator [FIL_123] (rows=287989836 width=135)
- predicate:(cs_item_sk is not null and cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_sold_date_sk is not null and cs_ship_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_ship_date_sk","cs_bill_cdemo_sk","cs_bill_hdemo_sk","cs_item_sk","cs_promo_sk","cs_order_number","cs_quantity"]
- <-Map 14 [SIMPLE_EDGE]
- SHUFFLE [RS_7]
- PartitionCols:_col1
- Select Operator [SEL_5] (rows=37584000 width=15)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_124] (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_3] (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"]
+ Filter Operator [FIL_124] (rows=27 width=1029)
+ predicate:w_warehouse_sk is not null
+ TableScan [TS_6] (rows=27 width=1029)
+ default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_warehouse_name"]
+ <-Map 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_48]
+ PartitionCols:_col2
+ Select Operator [SEL_5] (rows=37584000 width=15)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_123] (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_3] (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"]
diff --git a/ql/src/test/results/clientpositive/perf/query75.q.out b/ql/src/test/results/clientpositive/perf/query75.q.out
index f78ce8a..b1e236d 100644
--- a/ql/src/test/results/clientpositive/perf/query75.q.out
+++ b/ql/src/test/results/clientpositive/perf/query75.q.out
@@ -43,7 +43,7 @@ Stage-0
Select Operator [SEL_152] (rows=245965926 width=108)
Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"]
Filter Operator [FIL_151] (rows=245965926 width=108)
- predicate:((CAST( _col4 AS decimal(17,2)) / CAST( _col10 AS decimal(17,2))) < 0.9)
+ predicate:((CAST( _col10 AS decimal(17,2)) / CAST( _col4 AS decimal(17,2))) < 0.9)
Merge Join Operator [MERGEJOIN_259] (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]
@@ -104,7 +104,7 @@ Stage-0
Select Operator [SEL_79] (rows=36524 width=1119)
Output:["_col0"]
Filter Operator [FIL_230] (rows=36524 width=1119)
- predicate:((d_year = 2001) and d_date_sk is not null)
+ predicate:((d_year = 2002) 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]
@@ -159,7 +159,7 @@ Stage-0
Select Operator [SEL_101] (rows=36524 width=1119)
Output:["_col0"]
Filter Operator [FIL_234] (rows=36524 width=1119)
- predicate:((d_year = 2001) and d_date_sk is not null)
+ predicate:((d_year = 2002) 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]
@@ -214,7 +214,7 @@ Stage-0
Select Operator [SEL_125] (rows=36524 width=1119)
Output:["_col0"]
Filter Operator [FIL_238] (rows=36524 width=1119)
- predicate:((d_year = 2001) and d_date_sk is not null)
+ predicate:((d_year = 2002) 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]
@@ -275,7 +275,7 @@ Stage-0
Select Operator [SEL_27] (rows=36524 width=1119)
Output:["_col0"]
Filter Operator [FIL_222] (rows=36524 width=1119)
- predicate:((d_year = 2002) and d_date_sk is not null)
+ predicate:((d_year = 2001) 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]
@@ -330,7 +330,7 @@ Stage-0
Select Operator [SEL_51] (rows=36524 width=1119)
Output:["_col0"]
Filter Operator [FIL_226] (rows=36524 width=1119)
- predicate:((d_year = 2002) and d_date_sk is not null)
+ predicate:((d_year = 2001) 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]
@@ -385,7 +385,7 @@ Stage-0
Select Operator [SEL_5] (rows=36524 width=1119)
Output:["_col0"]
Filter Operator [FIL_218] (rows=36524 width=1119)
- predicate:((d_year = 2002) and d_date_sk is not null)
+ 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"]
diff --git a/ql/src/test/results/clientpositive/perf/query80.q.out b/ql/src/test/results/clientpositive/perf/query80.q.out
index 7338d9c..be7ecda 100644
--- a/ql/src/test/results/clientpositive/perf/query80.q.out
+++ b/ql/src/test/results/clientpositive/perf/query80.q.out
@@ -295,7 +295,7 @@ Stage-0
Select Operator [SEL_47] (rows=8116 width=1119)
Output:["_col0"]
Filter Operator [FIL_194] (rows=8116 width=1119)
- predicate:(d_date BETWEEN 1998-08-04 AND 1998-09-03 00:00:00.0 and d_date_sk is not null)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN 1998-08-04 00:00:00.0 AND 1998-09-03 00:00:00.0 and d_date_sk is not null)
TableScan [TS_45] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
<-Reducer 17 [SIMPLE_EDGE]
@@ -387,7 +387,7 @@ Stage-0
Select Operator [SEL_88] (rows=8116 width=1119)
Output:["_col0"]
Filter Operator [FIL_200] (rows=8116 width=1119)
- predicate:(d_date BETWEEN 1998-08-04 AND 1998-09-03 00:00:00.0 and d_date_sk is not null)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN 1998-08-04 00:00:00.0 AND 1998-09-03 00:00:00.0 and d_date_sk is not null)
TableScan [TS_86] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
<-Reducer 29 [SIMPLE_EDGE]
@@ -479,7 +479,7 @@ Stage-0
Select Operator [SEL_8] (rows=8116 width=1119)
Output:["_col0"]
Filter Operator [FIL_188] (rows=8116 width=1119)
- predicate:(d_date BETWEEN 1998-08-04 AND 1998-09-03 00:00:00.0 and d_date_sk is not null)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN 1998-08-04 00:00:00.0 AND 1998-09-03 00:00:00.0 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_date"]
<-Reducer 2 [SIMPLE_EDGE]
diff --git a/ql/src/test/results/clientpositive/perf/query81.q.out b/ql/src/test/results/clientpositive/perf/query81.q.out
index 192b151..a09d5c9 100644
--- a/ql/src/test/results/clientpositive/perf/query81.q.out
+++ b/ql/src/test/results/clientpositive/perf/query81.q.out
@@ -95,28 +95,28 @@ Stage-0
<-Reducer 23 [SIMPLE_EDGE]
SHUFFLE [RS_94]
PartitionCols:_col2
- Select Operator [SEL_92] (rows=8711661 width=106)
+ Select Operator [SEL_92] (rows=11000000 width=1014)
Output:["_col0","_col1","_col2"]
- Group By Operator [GBY_91] (rows=8711661 width=106)
+ Group By Operator [GBY_91] (rows=11000000 width=1014)
Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col0
- Select Operator [SEL_87] (rows=17423323 width=106)
+ Select Operator [SEL_87] (rows=22000000 width=1014)
Output:["_col0","_col2"]
- Group By Operator [GBY_86] (rows=17423323 width=106)
+ Group By Operator [GBY_86] (rows=22000000 width=1014)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
<-Reducer 22 [SIMPLE_EDGE]
SHUFFLE [RS_85]
PartitionCols:_col0
- Group By Operator [GBY_84] (rows=34846646 width=106)
+ Group By Operator [GBY_84] (rows=44000000 width=1014)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1
- Merge Join Operator [MERGEJOIN_150] (rows=34846646 width=106)
+ Merge Join Operator [MERGEJOIN_150] (rows=44000000 width=1014)
Conds:RS_80._col2=RS_81._col0(Inner),Output:["_col1","_col3","_col7"]
<-Map 25 [SIMPLE_EDGE]
SHUFFLE [RS_81]
PartitionCols:_col0
- Select Operator [SEL_76] (rows=20000000 width=1014)
+ Select Operator [SEL_76] (rows=40000000 width=1014)
Output:["_col0","_col1"]
- Filter Operator [FIL_143] (rows=20000000 width=1014)
- predicate:((ca_state = ca_state) and ca_address_sk is not null)
+ Filter Operator [FIL_143] (rows=40000000 width=1014)
+ predicate:(ca_address_sk is not null and ca_state is not null)
TableScan [TS_74] (rows=40000000 width=1014)
default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"]
<-Reducer 21 [SIMPLE_EDGE]
@@ -203,32 +203,32 @@ Stage-0
<-Reducer 17 [SIMPLE_EDGE]
SHUFFLE [RS_58]
PartitionCols:_col0
- Select Operator [SEL_56] (rows=1451943 width=106)
+ Select Operator [SEL_56] (rows=1833333 width=1014)
Output:["_col0"]
- Filter Operator [FIL_55] (rows=1451943 width=106)
+ Filter Operator [FIL_55] (rows=1833333 width=1014)
predicate:(sq_count_check(_col1) <= 1)
- Group By Operator [GBY_54] (rows=4355830 width=106)
+ Group By Operator [GBY_54] (rows=5500000 width=1014)
Output:["_col0","_col1"],aggregations:["count()"],keys:_col0
- Group By Operator [GBY_49] (rows=8711661 width=106)
+ Group By Operator [GBY_49] (rows=11000000 width=1014)
Output:["_col0"],keys:_col0
- Select Operator [SEL_45] (rows=17423323 width=106)
+ Select Operator [SEL_45] (rows=22000000 width=1014)
Output:["_col0"]
- Group By Operator [GBY_44] (rows=17423323 width=106)
+ Group By Operator [GBY_44] (rows=22000000 width=1014)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
<-Reducer 16 [SIMPLE_EDGE]
SHUFFLE [RS_43]
PartitionCols:_col0
- Group By Operator [GBY_42] (rows=34846646 width=106)
+ Group By Operator [GBY_42] (rows=44000000 width=1014)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1
- Merge Join Operator [MERGEJOIN_148] (rows=34846646 width=106)
+ Merge Join Operator [MERGEJOIN_148] (rows=44000000 width=1014)
Conds:RS_38._col2=RS_39._col0(Inner),Output:["_col1","_col3","_col7"]
<-Map 19 [SIMPLE_EDGE]
SHUFFLE [RS_39]
PartitionCols:_col0
- Select Operator [SEL_34] (rows=20000000 width=1014)
+ Select Operator [SEL_34] (rows=40000000 width=1014)
Output:["_col0","_col1"]
- Filter Operator [FIL_140] (rows=20000000 width=1014)
- predicate:((ca_state = ca_state) and ca_address_sk is not null)
+ Filter Operator [FIL_140] (rows=40000000 width=1014)
+ predicate:(ca_address_sk is not null and ca_state is not null)
TableScan [TS_32] (rows=40000000 width=1014)
default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"]
<-Reducer 15 [SIMPLE_EDGE]
diff --git a/ql/src/test/results/clientpositive/perf/query82.q.out b/ql/src/test/results/clientpositive/perf/query82.q.out
index 9c0042c..881070e 100644
--- a/ql/src/test/results/clientpositive/perf/query82.q.out
+++ b/ql/src/test/results/clientpositive/perf/query82.q.out
@@ -97,7 +97,7 @@ Stage-0
Select Operator [SEL_11] (rows=8116 width=1119)
Output:["_col0"]
Filter Operator [FIL_42] (rows=8116 width=1119)
- predicate:(d_date BETWEEN 2002-05-30 AND 2002-07-29 00:00:00.0 and d_date_sk is not null)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN 2002-05-30 00:00:00.0 AND 2002-07-29 00:00:00.0 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_date"]
diff --git a/ql/src/test/results/clientpositive/perf/query85.q.out b/ql/src/test/results/clientpositive/perf/query85.q.out
index 67b7993..168bcd2 100644
--- a/ql/src/test/results/clientpositive/perf/query85.q.out
+++ b/ql/src/test/results/clientpositive/perf/query85.q.out
@@ -5,151 +5,143 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 10 <- Map 13 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE)
-Reducer 11 <- Map 14 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE)
-Reducer 12 <- Map 15 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE)
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
-Reducer 3 <- Map 17 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
-Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
-Reducer 7 <- Map 6 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE)
-Reducer 8 <- Map 16 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
+Reducer 10 <- Reducer 9 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE)
+Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+Reducer 6 <- Map 15 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
+Reducer 7 <- Map 16 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
+Reducer 8 <- Map 17 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
+Reducer 9 <- Reducer 8 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:100
Stage-1
- Reducer 5
- File Output Operator [FS_59]
- Limit [LIM_58] (rows=100 width=1014)
+ Reducer 10
+ File Output Operator [FS_55]
+ Limit [LIM_54] (rows=100 width=385)
Number of rows:100
- Select Operator [SEL_57] (rows=1220082 width=1014)
+ Select Operator [SEL_53] (rows=1023990 width=385)
Output:["_col0","_col1","_col2","_col3"]
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_56]
- Select Operator [SEL_55] (rows=1220082 width=1014)
+ <-Reducer 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_52]
+ Select Operator [SEL_51] (rows=1023990 width=385)
Output:["_col0","_col1","_col2","_col3"]
- Group By Operator [GBY_54] (rows=1220082 width=1014)
+ Group By Operator [GBY_50] (rows=1023990 width=385)
Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(VALUE._col0)","avg(VALUE._col1)","avg(VALUE._col2)"],keys:KEY._col0
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_53]
+ <-Reducer 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_49]
PartitionCols:_col0
- Group By Operator [GBY_52] (rows=2440165 width=1014)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(_col6)","avg(_col16)","avg(_col15)"],keys:_col28
- Merge Join Operator [MERGEJOIN_109] (rows=2440165 width=1014)
- Conds:RS_48._col13=RS_49._col0(Inner),Output:["_col6","_col15","_col16","_col28"]
+ 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)
+ Conds:RS_44._col13, _col24, _col25=RS_45._col0, _col1, _col2(Inner),Output:["_col5","_col16","_col17","_col19"]
<-Map 17 [SIMPLE_EDGE]
- SHUFFLE [RS_49]
- PartitionCols:_col0
- Select Operator [SEL_44] (rows=72 width=200)
- Output:["_col0","_col1"]
- Filter Operator [FIL_102] (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_108] (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_95] (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","_col4","_col11","_col13","_col14"]
- 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_107] (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_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_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_106] (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_96] (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","_col4","_col6","_col9","_col10","_col11","_col13","_col14","_col17","_col18"]
- 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_105] (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_100] (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_45]
+ PartitionCols:_col0, _col1, _col2
+ Select Operator [SEL_23] (rows=1861800 width=385)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_98] (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_21] (rows=1861800 width=385)
+ default@customer_demographics,cd2,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"]
+ <-Reducer 7 [SIMPLE_EDGE]
+ SHUFFLE [RS_44]
+ PartitionCols:_col13, _col24, _col25
+ Filter Operator [FIL_43] (rows=393687 width=135)
+ predicate:(((_col24 = 'M') and (_col25 = '4 yr Degree') and _col6 BETWEEN 100 AND 150) or ((_col24 = 'D') and (_col25 = 'Primary') and _col6 BETWEEN 50 AND 100) or ((_col24 = 'U') and (_col25 = 'Advanced Degree') and _col6 BETWEEN 150 AND 200))
+ Merge Join Operator [MERGEJOIN_104] (rows=4724247 width=135)
+ Conds:RS_40._col11=RS_41._col0(Inner),Output:["_col5","_col6","_col13","_col16","_col17","_col19","_col24","_col25"]
+ <-Map 16 [SIMPLE_EDGE]
+ SHUFFLE [RS_41]
+ PartitionCols:_col0
+ Select Operator [SEL_20] (rows=1861800 width=385)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_97] (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_18] (rows=1861800 width=385)
+ default@customer_demographics,cd1,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"]
+ <-Reducer 6 [SIMPLE_EDGE]
+ SHUFFLE [RS_40]
+ PartitionCols:_col11
+ Filter Operator [FIL_39] (rows=4294770 width=135)
+ predicate:(((_col21) IN ('KY', 'GA', 'NM') and _col7 BETWEEN 100 AND 200) or ((_col21) IN ('MT', 'OR', 'IN') and _col7 BETWEEN 150 AND 300) or ((_col21) IN ('WI', 'MO', 'WV') and _col7 BETWEEN 50 AND 250))
+ Merge Join Operator [MERGEJOIN_103] (rows=25768635 width=135)
+ Conds:RS_36._col12=RS_37._col0(Inner),Output:["_col5","_col6","_col7","_col11","_col13","_col16","_col17","_col19","_col21"]
+ <-Map 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_37]
+ PartitionCols:_col0
+ Select Operator [SEL_17] (rows=10000000 width=1014)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_96] (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_15] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_country"]
+ <-Reducer 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_36]
+ PartitionCols:_col12
+ Merge Join Operator [MERGEJOIN_102] (rows=23426032 width=135)
+ Conds:RS_33._col14=RS_34._col0(Inner),Output:["_col5","_col6","_col7","_col11","_col12","_col13","_col16","_col17","_col19"]
+ <-Map 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_34]
+ PartitionCols:_col0
+ Select Operator [SEL_14] (rows=72 width=200)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_95] (rows=72 width=200)
+ predicate:r_reason_sk is not null
+ TableScan [TS_12] (rows=72 width=200)
+ default@reason,reason,Tbl:COMPLETE,Col:NONE,Output:["r_reason_sk","r_reason_desc"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_33]
+ PartitionCols:_col14
+ Merge Join Operator [MERGEJOIN_101] (rows=21296393 width=135)
+ Conds:RS_30._col2, _col4=RS_31._col0, _col5(Inner),Output:["_col5","_col6","_col7","_col11","_col12","_col13","_col14","_col16","_col17"]
+ <-Map 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_31]
+ PartitionCols:_col0, _col5
+ Select Operator [SEL_11] (rows=14398467 width=92)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
+ Filter Operator [FIL_94] (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_9] (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 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_30]
+ PartitionCols:_col2, _col4
+ Merge Join Operator [MERGEJOIN_100] (rows=19360357 width=135)
+ Conds:RS_27._col1=RS_28._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7"]
+ <-Map 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_28]
+ PartitionCols:_col0
+ Select Operator [SEL_8] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_93] (rows=36524 width=1119)
+ predicate:((d_year = 1998) 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"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_27]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_99] (rows=17600325 width=135)
+ Conds:RS_24._col0=RS_25._col2(Inner),Output:["_col1","_col2","_col4","_col5","_col6","_col7"]
+ <-Map 1 [SIMPLE_EDGE]
SHUFFLE [RS_24]
- PartitionCols:_col9
- Merge Join Operator [MERGEJOIN_104] (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_99] (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_103] (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_98] (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_97] (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"]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=4602 width=585)
+ Output:["_col0"]
+ Filter Operator [FIL_91] (rows=4602 width=585)
+ predicate:wp_web_page_sk is not null
+ TableScan [TS_0] (rows=4602 width=585)
+ default@web_page,web_page,Tbl:COMPLETE,Col:NONE,Output:["wp_web_page_sk"]
+ <-Map 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_25]
+ PartitionCols:_col2
+ Select Operator [SEL_5] (rows=16000296 width=135)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
+ Filter Operator [FIL_92] (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_3] (rows=144002668 width=135)
+ default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_page_sk","ws_order_number","ws_quantity","ws_sales_price","ws_net_profit"]
diff --git a/ql/src/test/results/clientpositive/perf/query98.q.out b/ql/src/test/results/clientpositive/perf/query98.q.out
index 04d8116..2894f7e 100644
--- a/ql/src/test/results/clientpositive/perf/query98.q.out
+++ b/ql/src/test/results/clientpositive/perf/query98.q.out
@@ -80,7 +80,7 @@ Stage-0
Select Operator [SEL_5] (rows=8116 width=1119)
Output:["_col0"]
Filter Operator [FIL_34] (rows=8116 width=1119)
- predicate:(d_date BETWEEN 2001-01-12 AND 2001-02-11 00:00:00.0 and d_date_sk is not null)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN 2001-01-12 00:00:00.0 AND 2001-02-11 00:00:00.0 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_date"]
diff --git a/ql/src/test/results/clientpositive/ppd_join2.q.out b/ql/src/test/results/clientpositive/ppd_join2.q.out
index d5f5016..279435a 100644
--- a/ql/src/test/results/clientpositive/ppd_join2.q.out
+++ b/ql/src/test/results/clientpositive/ppd_join2.q.out
@@ -23,19 +23,19 @@ ON src1.c2 = src3.c6
WHERE src1.c1 <> '311' and (src1.c2 <> 'val_50' or src1.c1 > '1') and (src2.c3 <> '10' or src1.c1 <> '10') and (src2.c3 <> '14') and (sqrt(src3.c5) <> 13)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
- Stage-0 depends on stages: Stage-1
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Map Reduce
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '302') and (key < '400') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14') and value is not null) (type: boolean)
+ predicate: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
@@ -51,7 +51,7 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean)
+ predicate: ((key <> '302') and (key < '400') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14') and value is not null) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
@@ -73,23 +73,26 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col2 <> '10') or (_col0 <> '10')) (type: boolean)
+ predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean)
Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 182 Data size: 1939 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
+ 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-1
+ Stage: Stage-2
Map Reduce
Map Operator Tree:
TableScan
+ Reduce Output Operator
+ key expressions: _col3 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col3 (type: string)
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string)
+ TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -104,24 +107,17 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- TableScan
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col3 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col1, _col4
+ 0 _col3 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col1 (type: string), _col4 (type: string)
+ expressions: _col2 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -1707,19 +1703,19 @@ ON src1.c2 = src3.c6
WHERE src1.c1 <> '311' and (src1.c2 <> 'val_50' or src1.c1 > '1') and (src2.c3 <> '10' or src1.c1 <> '10') and (src2.c3 <> '14') and (sqrt(src3.c5) <> 13)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
- Stage-0 depends on stages: Stage-1
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Map Reduce
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '302') and (key < '400') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14') and value is not null) (type: boolean)
+ predicate: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
@@ -1735,7 +1731,7 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean)
+ predicate: ((key <> '302') and (key < '400') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14') and value is not null) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
@@ -1757,23 +1753,26 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col2 <> '10') or (_col0 <> '10')) (type: boolean)
+ predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean)
Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 182 Data size: 1939 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
+ 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-1
+ Stage: Stage-2
Map Reduce
Map Operator Tree:
TableScan
+ Reduce Output Operator
+ key expressions: _col3 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col3 (type: string)
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string)
+ TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -1788,24 +1787,17 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- TableScan
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col3 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col1, _col4
+ 0 _col3 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col1 (type: string), _col4 (type: string)
+ expressions: _col2 (type: string), _col1 (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/ppd_join3.q.out b/ql/src/test/results/clientpositive/ppd_join3.q.out
index 3a8c1d7..cdf887e 100644
--- a/ql/src/test/results/clientpositive/ppd_join3.q.out
+++ b/ql/src/test/results/clientpositive/ppd_join3.q.out
@@ -23,19 +23,18 @@ ON src1.c1 = src3.c5
WHERE src1.c1 > '0' and (src1.c2 <> 'val_500' or src1.c1 > '1') and (src2.c3 > '10' or src1.c1 <> '10') and (src2.c3 <> '4') and (src3.c5 <> '1')
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Map Reduce
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '11') and (key < '400') and (key <> '12') and (key <> '13') and (key > '0') and ((value <> 'val_500') or (key > '1')) and (key <> '4') and (key <> '1')) (type: boolean)
+ predicate: ((key <> '13') and (key <> '11') and (key < '400') and (key <> '12') and (key <> '1') and (key > '0') and (key <> '4')) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
@@ -50,86 +49,58 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '12') and (key <> '11') and (key < '400') and (key <> '13') and (key <> '4') and (key > '0') and (key <> '1')) (type: boolean)
+ predicate: ((key <> '11') and (key < '400') and (key <> '12') and (key <> '13') and (key > '0') and ((value <> 'val_500') or (key > '1')) and (key <> '4') and (key <> '1')) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
+ expressions: key (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col1 > '10') or (_col0 <> '10')) (type: boolean)
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col2
- Statistics: Num rows: 60 Data size: 642 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-1
- Map Reduce
- Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '13') and (key <> '11') and (key < '400') and (key <> '12') and (key <> '1') and (key > '0') and (key <> '4')) (type: boolean)
+ predicate: ((key <> '12') and (key <> '11') and (key < '400') and (key <> '13') and (key <> '4') and (key > '0') and (key <> '1')) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: string)
+ value expressions: _col1 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 1 to 2
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col1, _col3
- Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 66 Data size: 706 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
+ 2 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col2 > '10') or (_col1 <> '10')) (type: boolean)
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 121 Data size: 1284 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
@@ -1763,19 +1734,18 @@ ON src1.c1 = src3.c5
WHERE src1.c1 > '0' and (src1.c2 <> 'val_500' or src1.c1 > '1') and (src2.c3 > '10' or src1.c1 <> '10') and (src2.c3 <> '4') and (src3.c5 <> '1')
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Map Reduce
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '11') and (key < '400') and (key <> '12') and (key <> '13') and (key > '0') and ((value <> 'val_500') or (key > '1')) and (key <> '4') and (key <> '1')) (type: boolean)
+ predicate: ((key <> '13') and (key <> '11') and (key < '400') and (key <> '12') and (key <> '1') and (key > '0') and (key <> '4')) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
@@ -1790,86 +1760,58 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '12') and (key <> '11') and (key < '400') and (key <> '13') and (key <> '4') and (key > '0') and (key <> '1')) (type: boolean)
+ predicate: ((key <> '11') and (key < '400') and (key <> '12') and (key <> '13') and (key > '0') and ((value <> 'val_500') or (key > '1')) and (key <> '4') and (key <> '1')) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
+ expressions: key (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col1 > '10') or (_col0 <> '10')) (type: boolean)
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col2
- Statistics: Num rows: 60 Data size: 642 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-1
- Map Reduce
- Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '13') and (key <> '11') and (key < '400') and (key <> '12') and (key <> '1') and (key > '0') and (key <> '4')) (type: boolean)
+ predicate: ((key <> '12') and (key <> '11') and (key < '400') and (key <> '13') and (key <> '4') and (key > '0') and (key <> '1')) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: string)
+ value expressions: _col1 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 1 to 2
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col1, _col3
- Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 66 Data size: 706 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
+ 2 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col2 > '10') or (_col1 <> '10')) (type: boolean)
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 121 Data size: 1284 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/ppd_outer_join1.q.out b/ql/src/test/results/clientpositive/ppd_outer_join1.q.out
index 8ec267c..f4d8089 100644
--- a/ql/src/test/results/clientpositive/ppd_outer_join1.q.out
+++ b/ql/src/test/results/clientpositive/ppd_outer_join1.q.out
@@ -28,53 +28,50 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
TableScan
alias: b
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
- Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 6 Data size: 64 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
+ Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 6 Data size: 69 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
@@ -138,53 +135,50 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
TableScan
alias: b
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
- Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 6 Data size: 64 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
+ Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 6 Data size: 69 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/reduce_deduplicate_extended2.q.out b/ql/src/test/results/clientpositive/reduce_deduplicate_extended2.q.out
index 3cfa58b..124c908 100644
--- a/ql/src/test/results/clientpositive/reduce_deduplicate_extended2.q.out
+++ b/ql/src/test/results/clientpositive/reduce_deduplicate_extended2.q.out
@@ -544,11 +544,11 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (type: string)
- outputColumnNames: value
+ expressions: key (type: string)
+ outputColumnNames: key
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- keys: value (type: string)
+ keys: key (type: string)
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
@@ -592,17 +592,12 @@ STAGE PLANS:
1
outputColumnNames: _col0, _col1
Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col1 (type: string), _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 62500 Data size: 1390500 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
+ 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-3
Map Reduce
@@ -611,17 +606,15 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: -+
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 31250 Data size: 695250 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 31250 Data size: 695250 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -634,11 +627,11 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: key
+ expressions: value (type: string)
+ outputColumnNames: value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- keys: key (type: string)
+ keys: value (type: string)
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
diff --git a/ql/src/test/results/clientpositive/router_join_ppr.q.out b/ql/src/test/results/clientpositive/router_join_ppr.q.out
index cc2b07e..f17959b 100644
--- a/ql/src/test/results/clientpositive/router_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/router_join_ppr.q.out
@@ -30,41 +30,41 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
TableScan
alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 12 Data size: 127 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: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 1
- value expressions: _col1 (type: string), _col2 (type: string)
+ value expressions: _col1 (type: string)
auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
@@ -211,149 +211,42 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart
name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
Truncated Path -> Alias:
/src [$hdt$_0:a]
/srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b]
/srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b]
- /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:b]
- /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:b]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
- Right Outer Join0 to 1
- filter mappings:
- 1 [0, 1]
- filter predicates:
- 0
- 1 {(VALUE._col1 = '2008-04-08')}
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -373,8 +266,6 @@ PREHOOK: Input: default@src
PREHOOK: Input: default@srcpart
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
POSTHOOK: query: FROM
src a
@@ -388,8 +279,6 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
17 val_17 17 val_17
17 val_17 17 val_17
@@ -435,18 +324,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -456,18 +345,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -624,42 +513,38 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Right Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -737,18 +622,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -758,18 +643,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -926,38 +811,34 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Right Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ 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/semijoin5.q.out b/ql/src/test/results/clientpositive/semijoin5.q.out
index fd8e372..db4f551 100644
--- a/ql/src/test/results/clientpositive/semijoin5.q.out
+++ b/ql/src/test/results/clientpositive/semijoin5.q.out
@@ -255,7 +255,7 @@ STAGE PLANS:
alias: tt2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: ((timestamp_col_18 = timestamp_col_18) and decimal1911_col_16 is not null) (type: boolean)
+ predicate: (timestamp_col_18 is not null and decimal1911_col_16 is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: decimal1911_col_16 (type: decimal(19,11)), timestamp_col_18 (type: timestamp)
diff --git a/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out
index 3b0d96c..602ccb2 100644
--- a/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out
@@ -898,7 +898,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
@@ -915,7 +915,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out
index 2b09fcf..cdb69db 100644
--- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out
@@ -1033,7 +1033,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
@@ -1058,7 +1058,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
diff --git a/ql/src/test/results/clientpositive/spark/constprog_semijoin.q.out b/ql/src/test/results/clientpositive/spark/constprog_semijoin.q.out
index 89c2735..be33189 100644
--- a/ql/src/test/results/clientpositive/spark/constprog_semijoin.q.out
+++ b/ql/src/test/results/clientpositive/spark/constprog_semijoin.q.out
@@ -446,7 +446,7 @@ STAGE PLANS:
alias: table3
Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((id = 100) and (id = 100) is not null) (type: boolean)
+ predicate: (id = 100) (type: boolean)
Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: 100 (type: int), true (type: boolean)
@@ -517,7 +517,7 @@ STAGE PLANS:
alias: table1
Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((dimid = 100) and (dimid = 100) is not null) (type: boolean)
+ predicate: (dimid = 100) (type: boolean)
Statistics: Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: id (type: int), val (type: string), val1 (type: string)
@@ -535,7 +535,7 @@ STAGE PLANS:
alias: table3
Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((id = 100) and (id = 100) is not null) (type: boolean)
+ predicate: (id = 100) (type: boolean)
Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: 100 (type: int), true (type: boolean)
@@ -626,7 +626,7 @@ STAGE PLANS:
alias: table3
Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((id = 100) and (id = 100) is not null) (type: boolean)
+ predicate: (id = 100) (type: boolean)
Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: 100 (type: int), true (type: boolean)
@@ -697,7 +697,7 @@ STAGE PLANS:
alias: table1
Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((dimid = 100) and (dimid = 100) is not null) (type: boolean)
+ predicate: (dimid = 100) (type: boolean)
Statistics: Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: id (type: int), val (type: string), val1 (type: string)
@@ -715,7 +715,7 @@ STAGE PLANS:
alias: table3
Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((id = 100) and (id = 100) is not null) (type: boolean)
+ predicate: (id = 100) (type: boolean)
Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: 100 (type: int), true (type: boolean)
@@ -788,7 +788,7 @@ STAGE PLANS:
alias: table1
Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((dimid = 100) and (dimid = 100) is not null) (type: boolean)
+ predicate: (dimid = 100) (type: boolean)
Statistics: Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: id (type: int), val (type: string), val1 (type: string)
@@ -806,7 +806,7 @@ STAGE PLANS:
alias: table3
Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((id = 100) and (id = 100) is not null) (type: boolean)
+ predicate: (id = 100) (type: boolean)
Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: 100 (type: int), true (type: boolean)
diff --git a/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out b/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out
index 7a9baca..f1728ce 100644
--- a/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out
+++ b/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out
@@ -258,7 +258,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
+Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product
PREHOOK: query: explain select p1.p_name, p2.p_name, p3.p_name
from part p1 , part p2 , part p3
where p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name
@@ -275,26 +275,13 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: p1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_partkey (type: int), p_name (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string)
- Map 4
- Map Operator Tree:
- TableScan
alias: p2
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -305,10 +292,12 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- sort order:
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string)
- Map 5
+ value expressions: _col0 (type: int)
+ Map 4
Map Operator Tree:
TableScan
alias: p3
@@ -325,50 +314,57 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: p1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_partkey (type: int), p_name (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 676 Data size: 164320 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col2 + _col0) = _col0) (type: boolean)
- Statistics: Num rows: 338 Data size: 82160 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col1, _col3
- Statistics: Num rows: 338 Data size: 82160 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col3 (type: string)
- sort order: +
- Map-reduce partition columns: _col3 (type: string)
- Statistics: Num rows: 338 Data size: 82160 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
Reducer 3
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col3 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col1, _col3, _col4
- Statistics: Num rows: 371 Data size: 90376 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 371 Data size: 90376 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 371 Data size: 90376 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
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 + _col3) = _col3) (type: boolean)
+ Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col4 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 364 Data size: 89415 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/spark/join_cond_pushdown_1.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_1.q.out
index 11d235b..4c63e95 100644
--- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_1.q.out
+++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_1.q.out
@@ -192,7 +192,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
+Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product
PREHOOK: query: explain select *
from part p1 join part p2 join part p3 on p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name
PREHOOK: type: QUERY
@@ -207,26 +207,13 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: p1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- Map 4
- Map Operator Tree:
- TableScan
alias: p2
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -237,10 +224,12 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- sort order:
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- Map 5
+ value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
+ Map 4
Map Operator Tree:
TableScan
alias: p3
@@ -258,42 +247,57 @@ STAGE PLANS:
Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: p1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0
- 1
+ 0 _col1 (type: string)
+ 1 _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17
- Statistics: Num rows: 676 Data size: 164320 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col9 + _col0) = _col0) (type: boolean)
- Statistics: Num rows: 338 Data size: 82160 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col10 (type: string)
- sort order: +
- Map-reduce partition columns: _col10 (type: string)
- Statistics: Num rows: 338 Data size: 82160 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
Reducer 3
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col10 (type: string)
- 1 _col1 (type: string)
+ 0
+ 1
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
- Statistics: Num rows: 371 Data size: 90376 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 371 Data size: 90376 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
+ Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 + _col18) = _col18) (type: boolean)
+ Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
+ Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 364 Data size: 89415 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/spark/join_cond_pushdown_3.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_3.q.out
index a53db90..380629a 100644
--- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_3.q.out
+++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_3.q.out
@@ -196,7 +196,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
+Warning: Shuffle Join JOIN[13][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product
PREHOOK: query: explain select *
from part p1 join part p2 join part p3
where p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name
@@ -213,26 +213,13 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: p1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- Map 4
- Map Operator Tree:
- TableScan
alias: p2
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -243,10 +230,12 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- sort order:
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- Map 5
+ value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
+ Map 4
Map Operator Tree:
TableScan
alias: p3
@@ -264,42 +253,57 @@ STAGE PLANS:
Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: p1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0
- 1
+ 0 _col1 (type: string)
+ 1 _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17
- Statistics: Num rows: 676 Data size: 164320 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col9 + _col0) = _col0) (type: boolean)
- Statistics: Num rows: 338 Data size: 82160 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col10 (type: string)
- sort order: +
- Map-reduce partition columns: _col10 (type: string)
- Statistics: Num rows: 338 Data size: 82160 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
Reducer 3
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col10 (type: string)
- 1 _col1 (type: string)
+ 0
+ 1
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
- Statistics: Num rows: 371 Data size: 90376 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 371 Data size: 90376 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
+ Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 + _col18) = _col18) (type: boolean)
+ Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
+ Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 364 Data size: 89415 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/spark/join_cond_pushdown_unqual1.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out
index 949d442..40695ef 100644
--- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out
+++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual1.q.out
@@ -248,7 +248,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
+Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
PREHOOK: query: explain select *
from part p1 join part2 p2 join part3 p3 on p2_partkey + p_partkey = p1.p_partkey and p3_name = p2_name
PREHOOK: type: QUERY
diff --git a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out
index b5c91b6..248512a 100644
--- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out
+++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_unqual3.q.out
@@ -252,7 +252,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
+Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
PREHOOK: query: explain select *
from part p1 join part2 p2 join part3 p3
where p2_partkey + p1.p_partkey = p1.p_partkey and p3_name = p2_name
diff --git a/ql/src/test/results/clientpositive/spark/join_merging.q.out b/ql/src/test/results/clientpositive/spark/join_merging.q.out
index fcf80bd..aec6454 100644
--- a/ql/src/test/results/clientpositive/spark/join_merging.q.out
+++ b/ql/src/test/results/clientpositive/spark/join_merging.q.out
@@ -114,31 +114,16 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: p3
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_partkey (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Map 3
- Map Operator Tree:
- TableScan
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_size > 10) (type: boolean)
+ predicate: ((p_size > 10) and p_partkey is not null) (type: boolean)
Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_partkey (type: int), p_size (type: int)
@@ -150,61 +135,62 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
- Map 5
+ Map 3
Map Operator Tree:
TableScan
alias: p2
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_partkey (type: int), p_size (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: p3
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: p_partkey (type: int), p_size (type: int)
- outputColumnNames: _col0, _col1
+ expressions: p_partkey (type: int)
+ outputColumnNames: _col0
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: int)
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
+ Right Outer Join1 to 2
keys:
0 _col0 (type: int)
- 1 _col2 (type: int)
- outputColumnNames: _col2, _col4
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ 1 _col0 (type: int)
+ 2 _col0 (type: int)
+ outputColumnNames: _col1, _col3
+ residual filter predicates: {(_col1 > (_col3 + 10))}
+ Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: int), _col4 (type: int)
+ expressions: _col1 (type: int), _col3 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 4
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col1, _col2, _col3
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col1 > (_col3 + 10)) (type: boolean)
- Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col2 (type: int)
- sort order: +
- Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: int), _col3 (type: int)
Stage: Stage-0
Fetch Operator
diff --git a/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out b/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out
index 2e1c74d..71e06bb 100644
--- a/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out
@@ -35,18 +35,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -109,18 +109,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -231,38 +231,34 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -341,24 +337,24 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 12 Data size: 127 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: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 0
- value expressions: _col1 (type: string), _col2 (type: string)
+ value expressions: _col1 (type: string)
auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
@@ -459,107 +455,9 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart
name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
Truncated Path -> Alias:
/srcpart/ds=2008-04-08/hr=11 [a]
/srcpart/ds=2008-04-08/hr=12 [a]
- /srcpart/ds=2008-04-09/hr=11 [a]
- /srcpart/ds=2008-04-09/hr=12 [a]
Map 3
Map Operator Tree:
TableScan
@@ -568,18 +466,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -639,47 +537,38 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
- filter mappings:
- 0 [1, 1]
- filter predicates:
- 0 {(VALUE._col1 = '2008-04-08')}
- 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 25.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -699,8 +588,6 @@ PREHOOK: Input: default@src
PREHOOK: Input: default@srcpart
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
POSTHOOK: query: FROM
srcpart a
@@ -714,8 +601,6 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
17 val_17 17 val_17
17 val_17 17 val_17
@@ -1072,18 +957,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -1197,18 +1082,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -1268,42 +1153,38 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 25.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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/spark/mapjoin1.q.out b/ql/src/test/results/clientpositive/spark/mapjoin1.q.out
index aa96fc5..13ebfb6 100644
--- a/ql/src/test/results/clientpositive/spark/mapjoin1.q.out
+++ b/ql/src/test/results/clientpositive/spark/mapjoin1.q.out
@@ -141,7 +141,7 @@ STAGE PLANS:
Spark HashTable Sink Operator
filter predicates:
0
- 1 {((UDFToDouble(_col0) * UDFToDouble(10)) < UDFToDouble('1000'))}
+ 1 {((UDFToDouble(_col0) * 10.0) < 1000.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -166,7 +166,7 @@ STAGE PLANS:
Right Outer Join0 to 1
filter predicates:
0
- 1 {((UDFToDouble(_col0) * UDFToDouble(10)) < UDFToDouble('1000'))}
+ 1 {((UDFToDouble(_col0) * 10.0) < 1000.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -241,7 +241,7 @@ STAGE PLANS:
Spark HashTable Sink Operator
filter predicates:
0
- 1 {(UDFToDouble(_col1.key) > UDFToDouble(200))}
+ 1 {(UDFToDouble(_col1.key) > 200.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -266,7 +266,7 @@ STAGE PLANS:
Right Outer Join0 to 1
filter predicates:
0
- 1 {(UDFToDouble(_col1.key) > UDFToDouble(200))}
+ 1 {(UDFToDouble(_col1.key) > 200.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -433,7 +433,7 @@ STAGE PLANS:
Spark HashTable Sink Operator
filter predicates:
0
- 1 {((UDFToDouble(_col0) * UDFToDouble(10)) < UDFToDouble('1000'))}
+ 1 {((UDFToDouble(_col0) * 10.0) < 1000.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -458,7 +458,7 @@ STAGE PLANS:
Right Outer Join0 to 1
filter predicates:
0
- 1 {((UDFToDouble(_col0) * UDFToDouble(10)) < UDFToDouble('1000'))}
+ 1 {((UDFToDouble(_col0) * 10.0) < 1000.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -533,7 +533,7 @@ STAGE PLANS:
Spark HashTable Sink Operator
filter predicates:
0
- 1 {(UDFToDouble(_col1.key) > UDFToDouble(200))}
+ 1 {(UDFToDouble(_col1.key) > 200.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -558,7 +558,7 @@ STAGE PLANS:
Right Outer Join0 to 1
filter predicates:
0
- 1 {(UDFToDouble(_col1.key) > UDFToDouble(200))}
+ 1 {(UDFToDouble(_col1.key) > 200.0)}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
diff --git a/ql/src/test/results/clientpositive/spark/mergejoins.q.out b/ql/src/test/results/clientpositive/spark/mergejoins.q.out
index a3f8f8d..5b84a28 100644
--- a/ql/src/test/results/clientpositive/spark/mergejoins.q.out
+++ b/ql/src/test/results/clientpositive/spark/mergejoins.q.out
@@ -265,7 +265,7 @@ STAGE PLANS:
Left Outer Join1 to 2
filter predicates:
0
- 1 {(UDFToDouble(KEY.reducesinkkey0) < UDFToDouble(10))}
+ 1 {(UDFToDouble(KEY.reducesinkkey0) < 10.0)}
2
keys:
0 _col0 (type: string)
diff --git a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out b/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out
index 2d0270b..497a29e 100644
--- a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out
@@ -33,19 +33,23 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- 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
- 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
- value expressions: _col1 (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -101,21 +105,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string), _col2 (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 12 Data size: 127 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: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -215,149 +223,42 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart
name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
Truncated Path -> Alias:
/srcpart/ds=2008-04-08/hr=11 [b]
/srcpart/ds=2008-04-08/hr=12 [b]
- /srcpart/ds=2008-04-09/hr=11 [b]
- /srcpart/ds=2008-04-09/hr=12 [b]
Reducer 2
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
- Outer Join 0 to 1
- filter mappings:
- 1 [0, 1]
- filter predicates:
- 0
- 1 {(VALUE._col1 = '2008-04-08')}
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -377,8 +278,6 @@ PREHOOK: Input: default@src
PREHOOK: Input: default@srcpart
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
POSTHOOK: query: FROM
src a
@@ -392,8 +291,6 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
17 val_17 17 val_17
17 val_17 17 val_17
@@ -444,18 +341,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -518,18 +415,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -640,38 +537,34 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Right Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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/spark/ppd_join2.q.out b/ql/src/test/results/clientpositive/spark/ppd_join2.q.out
index 8d97034..024e962 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_join2.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_join2.q.out
@@ -30,8 +30,8 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -40,18 +40,19 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '306') and (sqrt(key) <> 13.0) and value is not null) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 1763 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
- Map 3
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Map 4
Map Operator Tree:
TableScan
alias: src
@@ -75,18 +76,17 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((key <> '306') and (sqrt(key) <> 13.0) and value 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ expressions: value (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)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -94,11 +94,30 @@ STAGE PLANS:
Inner Join 0 to 1
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col1, _col4
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean)
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col3 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col3 (type: string)
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col1 (type: string), _col4 (type: string)
+ expressions: _col2 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -108,29 +127,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 4
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col2 <> '10') or (_col0 <> '10')) (type: boolean)
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col3 (type: string)
Stage: Stage-0
Fetch Operator
@@ -1714,8 +1710,8 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1724,18 +1720,19 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '306') and (sqrt(key) <> 13.0) and value is not null) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 1763 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
- Map 3
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Map 4
Map Operator Tree:
TableScan
alias: src
@@ -1759,18 +1756,17 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((key <> '306') and (sqrt(key) <> 13.0) and value 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ expressions: value (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)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -1778,11 +1774,30 @@ STAGE PLANS:
Inner Join 0 to 1
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col1, _col4
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean)
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col3 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col3 (type: string)
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col1 (type: string), _col4 (type: string)
+ expressions: _col2 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -1792,29 +1807,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 4
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col2 <> '10') or (_col0 <> '10')) (type: boolean)
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col3 (type: string)
Stage: Stage-0
Fetch Operator
diff --git a/ql/src/test/results/clientpositive/spark/ppd_join3.q.out b/ql/src/test/results/clientpositive/spark/ppd_join3.q.out
index 99ded53..6706153 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_join3.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_join3.q.out
@@ -30,8 +30,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -68,7 +67,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Map 5
+ Map 4
Map Operator Tree:
TableScan
alias: src
@@ -91,45 +90,27 @@ STAGE PLANS:
Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 1 to 2
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col1, _col3
- Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 4
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+ 2 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col1 > '10') or (_col0 <> '10')) (type: boolean)
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col2 > '10') or (_col1 <> '10')) (type: boolean)
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col0 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col2
- Statistics: Num rows: 60 Data size: 642 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: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: string)
+ expressions: _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 121 Data size: 1284 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
@@ -1770,8 +1751,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1808,7 +1788,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Map 5
+ Map 4
Map Operator Tree:
TableScan
alias: src
@@ -1831,45 +1811,27 @@ STAGE PLANS:
Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 1 to 2
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col1, _col3
- Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 4
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+ 2 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col1 > '10') or (_col0 <> '10')) (type: boolean)
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col2 > '10') or (_col1 <> '10')) (type: boolean)
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col0 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col2
- Statistics: Num rows: 60 Data size: 642 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: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: string)
+ expressions: _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 121 Data size: 1284 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/spark/ppd_outer_join1.q.out b/ql/src/test/results/clientpositive/spark/ppd_outer_join1.q.out
index 1fc8232..7f60d98 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_outer_join1.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_outer_join1.q.out
@@ -33,17 +33,17 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Map 3
Map Operator Tree:
@@ -51,38 +51,35 @@ STAGE PLANS:
alias: b
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
- Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 6 Data size: 64 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
+ Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 6 Data size: 69 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
@@ -151,17 +148,17 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Map 3
Map Operator Tree:
@@ -169,38 +166,35 @@ STAGE PLANS:
alias: b
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
- Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 6 Data size: 64 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
+ Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 6 Data size: 69 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/spark/router_join_ppr.q.out b/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out
index 771609a..641af3c 100644
--- a/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out
@@ -35,18 +35,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -105,24 +105,24 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 12 Data size: 127 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: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 1
- value expressions: _col1 (type: string), _col2 (type: string)
+ value expressions: _col1 (type: string)
auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
@@ -223,149 +223,42 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart
name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
Truncated Path -> Alias:
/srcpart/ds=2008-04-08/hr=11 [b]
/srcpart/ds=2008-04-08/hr=12 [b]
- /srcpart/ds=2008-04-09/hr=11 [b]
- /srcpart/ds=2008-04-09/hr=12 [b]
Reducer 2
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
- Right Outer Join0 to 1
- filter mappings:
- 1 [0, 1]
- filter predicates:
- 0
- 1 {(VALUE._col1 = '2008-04-08')}
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -385,8 +278,6 @@ PREHOOK: Input: default@src
PREHOOK: Input: default@srcpart
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
POSTHOOK: query: FROM
src a
@@ -400,8 +291,6 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
17 val_17 17 val_17
17 val_17 17 val_17
@@ -452,18 +341,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -577,18 +466,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -648,42 +537,38 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Right Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
+ columns.types string:string:string:string
+ 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
@@ -766,18 +651,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -840,18 +725,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0) and (UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
tag: 1
value expressions: _col1 (type: string)
auto parallelism: false
@@ -962,38 +847,34 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Right Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 139 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,_col2,_col3
- columns.types string:string:string:string
- 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
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ 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/spark/smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out
index b5cef85..56d6bb9 100644
--- a/ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out
+++ b/ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out
@@ -1013,7 +1013,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
@@ -1030,7 +1030,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key + 1) is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (key + 1) (type: int)
diff --git a/ql/src/test/results/clientpositive/spark/subquery_exists.q.out b/ql/src/test/results/clientpositive/spark/subquery_exists.q.out
index 1901dba..8768b45 100644
--- a/ql/src/test/results/clientpositive/spark/subquery_exists.q.out
+++ b/ql/src/test/results/clientpositive/spark/subquery_exists.q.out
@@ -246,22 +246,22 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (value = value) (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: value (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -929,7 +929,7 @@ POSTHOOK: query: insert into t values(0)
POSTHOOK: type: QUERY
POSTHOOK: Output: default@t
POSTHOOK: Lineage: t.i EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
-Warning: Shuffle Join JOIN[18][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
+Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
PREHOOK: query: explain select * from t where exists (select count(*) from src where 1=2)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from t where exists (select count(*) from src where 1=2)
@@ -943,7 +943,7 @@ STAGE PLANS:
Spark
Edges:
Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1)
- Reducer 4 <- Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Map 3 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -975,9 +975,7 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: true (type: boolean)
- sort order: +
- Map-reduce partition columns: true (type: boolean)
+ sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 2
@@ -989,10 +987,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1006,16 +1004,9 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: true (type: boolean)
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -1023,7 +1014,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[18][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
+Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
PREHOOK: query: select * from t where exists (select count(*) from src where 1=2)
PREHOOK: type: QUERY
PREHOOK: Input: default@src
diff --git a/ql/src/test/results/clientpositive/spark/subquery_in.q.out b/ql/src/test/results/clientpositive/spark/subquery_in.q.out
index 314be60..fa184d8 100644
--- a/ql/src/test/results/clientpositive/spark/subquery_in.q.out
+++ b/ql/src/test/results/clientpositive/spark/subquery_in.q.out
@@ -290,7 +290,7 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Left Semi Join 0 to 1
+ Inner Join 0 to 1
keys:
0 UDFToDouble(_col1) (type: double)
1 _col0 (type: double)
@@ -356,16 +356,11 @@ STAGE PLANS:
Filter Operator
predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: double)
- mode: hash
- outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions: _col0 (type: double)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: double)
Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- sort order: +
- Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -419,10 +414,9 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2)
Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 2)
Reducer 5 <- Reducer 4 (GROUP, 2)
- Reducer 6 <- Reducer 5 (GROUP, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -529,32 +523,15 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Reducer 6
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: int), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: int)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -612,8 +589,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
- Reducer 4 <- Map 3 (GROUP, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -638,16 +614,20 @@ STAGE PLANS:
Filter Operator
predicate: ((value = value) and (key > '9')) (type: boolean)
Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: key (type: string), value (type: string)
- mode: hash
+ Select Operator
+ expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Group By Operator
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -665,23 +645,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 4
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -932,10 +895,9 @@ STAGE PLANS:
Spark
Edges:
Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2)
- Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 8 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 7 (PARTITION-LEVEL SORT, 2)
Reducer 4 <- Reducer 3 (GROUP, 1)
Reducer 7 <- Map 6 (GROUP, 2)
- Reducer 8 <- Reducer 7 (GROUP, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -979,19 +941,19 @@ STAGE PLANS:
alias: lineitem
Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (l_partkey = l_partkey) (type: boolean)
- Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
+ predicate: l_partkey is not null (type: boolean)
+ Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: avg(l_quantity)
keys: l_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: struct)
Reducer 2
Reduce Operator Tree:
@@ -1049,29 +1011,16 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col1 (type: double), _col0 (type: int)
- mode: hash
+ Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: double), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: double), _col1 (type: int)
- Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE
- Reducer 8
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: double), KEY._col1 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: double), _col1 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: double), _col1 (type: int)
- Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -1103,7 +1052,7 @@ STAGE PLANS:
Spark
Edges:
Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
- Reducer 4 <- Map 3 (GROUP PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Map 3 (GROUP, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1130,18 +1079,18 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: p_type (type: string), p_size (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -1165,21 +1114,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: int)
- mode: complete
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: int), _col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: string), _col0 (type: int)
- sort order: ++
- Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string), _col0 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -1517,18 +1461,18 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_name = p_name) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_name is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: p_name (type: string), p_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -1567,16 +1511,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: int), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: int)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -2043,18 +1987,18 @@ STAGE PLANS:
alias: part
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_brand = p_brand) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_brand is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: p_type (type: string), p_brand (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -2078,12 +2022,12 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -2544,18 +2488,18 @@ STAGE PLANS:
alias: sc
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key = key) (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: key (type: string), value (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Map 7
Map Operator Tree:
TableScan
@@ -2640,16 +2584,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: string)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Reducer 8
Reduce Operator Tree:
Group By Operator
@@ -3295,17 +3239,17 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((p_size = p_size) and p_type is not null) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: (p_size is not null and p_type is not null) (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_type (type: string), p_size (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
Reducer 2
Reduce Operator Tree:
@@ -3428,17 +3372,17 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((p_size = p_size) and p_type is not null) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: (p_size is not null and p_type is not null) (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_name (type: string), p_type (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string)
Map 5
Map Operator Tree:
@@ -3446,17 +3390,17 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((p_size = p_size) and p_type is not null) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: (p_size is not null and p_type is not null) (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_type (type: string), p_size (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
Reducer 2
Reduce Operator Tree:
@@ -3467,10 +3411,10 @@ STAGE PLANS:
0 _col1 (type: string), _col2 (type: int)
1 _col0 (type: string), _col1 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -3484,21 +3428,21 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col4
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col4 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: string), _col1 (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -3581,17 +3525,17 @@ STAGE PLANS:
alias: p
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_name (type: string), p_type (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string)
Map 5
Map Operator Tree:
@@ -3599,17 +3543,17 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((p_size = p_size) and p_type is not null) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: (p_size is not null and p_type is not null) (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_type (type: string), p_size (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
Reducer 2
Reduce Operator Tree:
@@ -3620,10 +3564,10 @@ STAGE PLANS:
0 _col1 (type: string), _col2 (type: string), _col3 (type: int)
1 _col0 (type: string), _col1 (type: string), _col2 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -3637,21 +3581,21 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: string), _col1 (type: string), _col2 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -3716,17 +3660,17 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((p_size = p_size) and p_type is not null) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: (p_size is not null and p_type is not null) (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_type (type: string), p_size (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
Reducer 2
Reduce Operator Tree:
@@ -3825,10 +3769,9 @@ STAGE PLANS:
Spark
Edges:
Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2)
- Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 8 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 7 (PARTITION-LEVEL SORT, 2)
Reducer 5 <- Map 4 (GROUP PARTITION-LEVEL SORT, 2)
Reducer 7 <- Map 6 (GROUP, 2)
- Reducer 8 <- Reducer 7 (GROUP, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -3852,37 +3795,37 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Map 6
Map Operator Tree:
TableScan
alias: pp
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 2
Reduce Operator Tree:
@@ -3916,10 +3859,10 @@ STAGE PLANS:
0 _col4 (type: string), UDFToLong(_col5) (type: bigint)
1 _col1 (type: string), _col0 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 9 Data size: 1223 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 9 Data size: 1223 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -3930,18 +3873,18 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 7
Reduce Operator Tree:
@@ -3950,33 +3893,16 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: bigint)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Reducer 8
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: bigint), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: bigint)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: bigint)
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -4007,9 +3933,8 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
Reducer 4 <- Map 3 (GROUP, 2)
- Reducer 5 <- Reducer 4 (GROUP, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -4033,19 +3958,19 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: avg(p_size)
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: struct)
Reducer 2
Reduce Operator Tree:
@@ -4071,33 +3996,16 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: int), _col1 (type: double)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: double)
- sort order: ++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: double)
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Reducer 5
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: int), KEY._col1 (type: double)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: double), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: int), _col0 (type: double)
sort order: ++
Map-reduce partition columns: _col1 (type: int), _col0 (type: double)
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -4152,11 +4060,10 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2)
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 1), Reducer 8 (PARTITION-LEVEL SORT, 1)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 1), Reducer 7 (PARTITION-LEVEL SORT, 1)
Reducer 5 <- Reducer 4 (GROUP, 2)
- Reducer 6 <- Reducer 5 (GROUP, 2)
- Reducer 8 <- Map 7 (GROUP, 2)
+ Reducer 7 <- Map 6 (GROUP, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -4187,7 +4094,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: int)
- Map 7
+ Map 6
Map Operator Tree:
TableScan
alias: part
@@ -4215,10 +4122,10 @@ STAGE PLANS:
0 _col0 (type: int), _col5 (type: int)
1 _col1 (type: int), _col0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 30 Data size: 7485 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 61 Data size: 14971 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 30 Data size: 7485 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 61 Data size: 14971 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4260,33 +4167,16 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 56 Data size: 13610 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: int), _col1 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 56 Data size: 13610 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
- Statistics: Num rows: 56 Data size: 13610 Basic stats: COMPLETE Column stats: NONE
- Reducer 6
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: int), KEY._col1 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 28 Data size: 6805 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: int), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 28 Data size: 6805 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 13610 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: int), _col0 (type: int)
sort order: ++
Map-reduce partition columns: _col1 (type: int), _col0 (type: int)
- Statistics: Num rows: 28 Data size: 6805 Basic stats: COMPLETE Column stats: NONE
- Reducer 8
+ Statistics: Num rows: 56 Data size: 13610 Basic stats: COMPLETE Column stats: NONE
+ Reducer 7
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int)
@@ -4329,10 +4219,9 @@ STAGE PLANS:
Spark
Edges:
Reducer 10 <- Map 7 (GROUP, 2)
- Reducer 11 <- Reducer 10 (GROUP, 2)
Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2)
Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 8 (PARTITION-LEVEL SORT, 2)
- Reducer 4 <- Reducer 11 (PARTITION-LEVEL SORT, 2), Reducer 3 (PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Reducer 10 (PARTITION-LEVEL SORT, 2), Reducer 3 (PARTITION-LEVEL SORT, 2)
Reducer 6 <- Map 5 (GROUP PARTITION-LEVEL SORT, 2)
Reducer 8 <- Map 7 (GROUP PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
@@ -4358,37 +4247,37 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Map 7
Map Operator Tree:
TableScan
alias: pp
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_type = p_type) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: p_type (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 10
Reduce Operator Tree:
@@ -4397,40 +4286,23 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: bigint)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Reducer 11
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: bigint), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: bigint), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: string), _col0 (type: bigint)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col0 (type: bigint)
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: boolean)
Reducer 2
Reduce Operator Tree:
@@ -4480,17 +4352,17 @@ STAGE PLANS:
0 _col4 (type: string), UDFToLong(_col5) (type: bigint)
1 _col1 (type: string), _col0 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12, _col13, _col16
- Statistics: Num rows: 9 Data size: 1345 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (not CASE WHEN ((_col12 = 0)) THEN (false) WHEN (_col12 is null) THEN (false) WHEN (_col16 is not null) THEN (true) WHEN (_col5 is null) THEN (null) WHEN ((_col13 < _col12)) THEN (true) ELSE (false) END) (type: boolean)
- Statistics: Num rows: 5 Data size: 747 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 5 Data size: 747 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 747 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4501,18 +4373,18 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 8
Reduce Operator Tree:
@@ -4521,18 +4393,18 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(), count(_col1)
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Stage: Stage-0
@@ -4585,10 +4457,9 @@ STAGE PLANS:
Spark
Edges:
Reducer 10 <- Map 7 (GROUP, 2)
- Reducer 11 <- Reducer 10 (GROUP, 2)
Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2)
Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 8 (PARTITION-LEVEL SORT, 2)
- Reducer 4 <- Reducer 11 (PARTITION-LEVEL SORT, 2), Reducer 3 (PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Reducer 10 (PARTITION-LEVEL SORT, 2), Reducer 3 (PARTITION-LEVEL SORT, 2)
Reducer 6 <- Map 5 (GROUP PARTITION-LEVEL SORT, 2)
Reducer 8 <- Map 7 (GROUP PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
@@ -4614,37 +4485,37 @@ STAGE PLANS:
alias: pp
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Map 7
Map Operator Tree:
TableScan
alias: pp
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_partkey = p_partkey) (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: avg(p_size)
keys: p_partkey (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: struct)
Reducer 10
Reduce Operator Tree:
@@ -4653,40 +4524,23 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: int), _col1 (type: double)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: double)
- sort order: ++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: double)
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Reducer 11
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: int), KEY._col1 (type: double)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col1 (type: double), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: double), _col1 (type: int), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: int), _col0 (type: double)
sort order: ++
Map-reduce partition columns: _col1 (type: int), _col0 (type: double)
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: boolean)
Reducer 2
Reduce Operator Tree:
@@ -4736,17 +4590,17 @@ STAGE PLANS:
0 _col0 (type: int), UDFToDouble(_col5) (type: double)
1 _col1 (type: int), _col0 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12, _col13, _col16
- Statistics: Num rows: 9 Data size: 1345 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (not CASE WHEN ((_col12 = 0)) THEN (false) WHEN (_col12 is null) THEN (false) WHEN (_col16 is not null) THEN (true) WHEN (_col5 is null) THEN (null) WHEN ((_col13 < _col12)) THEN (true) ELSE (false) END) (type: boolean)
- Statistics: Num rows: 5 Data size: 747 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 5 Data size: 747 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 747 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4757,18 +4611,18 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 8
Reduce Operator Tree:
@@ -4777,18 +4631,18 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(), count(_col1)
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 363 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Stage: Stage-0
@@ -4889,7 +4743,7 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Left Semi Join 0 to 1
+ Inner Join 0 to 1
keys:
0 UDFToLong(_col0) (type: bigint)
1 _col0 (type: bigint)
@@ -4912,16 +4766,11 @@ STAGE PLANS:
Filter Operator
predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: bigint)
- mode: hash
- outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: bigint)
- sort order: +
- Map-reduce partition columns: _col0 (type: bigint)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -5053,9 +4902,8 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
Reducer 4 <- Map 3 (GROUP, 2)
- Reducer 5 <- Reducer 4 (GROUP, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -5079,7 +4927,7 @@ STAGE PLANS:
alias: tt
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (j = j) (type: boolean)
+ predicate: j is not null (type: boolean)
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(i)
@@ -5118,9 +4966,8 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col1 (type: bigint), _col0 (type: int)
- mode: hash
+ Select Operator
+ expressions: _col1 (type: bigint), _col0 (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
@@ -5128,18 +4975,6 @@ STAGE PLANS:
sort order: ++
Map-reduce partition columns: _col0 (type: bigint), _col1 (type: int)
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
- Reducer 5
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: bigint), KEY._col1 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: bigint), _col1 (type: int)
- sort order: ++
- Map-reduce partition columns: _col0 (type: bigint), _col1 (type: int)
- Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out
index 7770404..eda5612 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_0.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_0.q.out
@@ -30505,18 +30505,18 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean)
- Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE
+ predicate: (struct(cint,cfloat)) IN (const struct(49,3.5), const struct(47,2.09), const struct(45,3.02)) (type: boolean)
+ Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 9216 Data size: 282927 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -30533,7 +30533,6 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: false
MultiFileSpray: false
- Execution mode: vectorized
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
diff --git a/ql/src/test/results/clientpositive/subq_where_serialization.q.out b/ql/src/test/results/clientpositive/subq_where_serialization.q.out
index f689651..45ceeaa 100644
--- a/ql/src/test/results/clientpositive/subq_where_serialization.q.out
+++ b/ql/src/test/results/clientpositive/subq_where_serialization.q.out
@@ -3,67 +3,38 @@ PREHOOK: type: QUERY
POSTHOOK: query: explain select src.key from src where src.key in ( select distinct key from src)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-4 depends on stages: Stage-2 , consists of Stage-5, Stage-1
- Stage-5 has a backup stage: Stage-1
- Stage-3 depends on stages: Stage-5
- Stage-1
- Stage-0 depends on stages: Stage-3, Stage-1
+ Stage-4 is a root stage
+ Stage-3 depends on stages: Stage-4
+ Stage-0 depends on stages: Stage-3
STAGE PLANS:
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
+ Stage: Stage-4
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $hdt$_1:src
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $hdt$_1:src
TableScan
alias: src
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
- Group By Operator
- keys: key (type: string)
- mode: hash
+ 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)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 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-4
- Conditional Operator
-
- Stage: Stage-5
- Map Reduce Local Work
- Alias -> Map Local Tables:
- $INTNAME
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- $INTNAME
- TableScan
- HashTable Sink Operator
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
Stage: Stage-3
Map Reduce
@@ -96,47 +67,6 @@ STAGE PLANS:
Local Work:
Map Reduce Local Work
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- 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
- 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
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 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
diff --git a/ql/src/test/results/clientpositive/subquery_exists.q.out b/ql/src/test/results/clientpositive/subquery_exists.q.out
index b271529..cfc7652 100644
--- a/ql/src/test/results/clientpositive/subquery_exists.q.out
+++ b/ql/src/test/results/clientpositive/subquery_exists.q.out
@@ -231,22 +231,22 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (value = value) (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: value (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
@@ -915,7 +915,7 @@ POSTHOOK: query: insert into t values(0)
POSTHOOK: type: QUERY
POSTHOOK: Output: default@t
POSTHOOK: Lineage: t.i EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
-Warning: Shuffle Join JOIN[18][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: explain select * from t where exists (select count(*) from src where 1=2)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from t where exists (select count(*) from src where 1=2)
@@ -943,9 +943,7 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: true (type: boolean)
- sort order: +
- Map-reduce partition columns: true (type: boolean)
+ sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reduce Operator Tree:
@@ -956,19 +954,12 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: true (type: boolean)
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- 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
+ 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-1
Map Reduce
@@ -987,7 +978,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Operator Tree:
Join Operator
condition map:
@@ -996,10 +987,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1011,7 +1002,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[18][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: select * from t where exists (select count(*) from src where 1=2)
PREHOOK: type: QUERY
PREHOOK: Input: default@src
diff --git a/ql/src/test/results/clientpositive/subquery_in_having.q.out b/ql/src/test/results/clientpositive/subquery_in_having.q.out
index 8572770..2b3af79 100644
--- a/ql/src/test/results/clientpositive/subquery_in_having.q.out
+++ b/ql/src/test/results/clientpositive/subquery_in_having.q.out
@@ -328,7 +328,7 @@ STAGE PLANS:
Reduce Operator Tree:
Join Operator
condition map:
- Left Semi Join 0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -377,17 +377,12 @@ STAGE PLANS:
expressions: _col0 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 5 Data size: 528 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 528 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
+ 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
@@ -474,7 +469,7 @@ STAGE PLANS:
Statistics: Num rows: 40 Data size: 4230 Basic stats: COMPLETE Column stats: NONE
Join Operator
condition map:
- Left Semi Join 0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -504,7 +499,7 @@ STAGE PLANS:
Statistics: Num rows: 40 Data size: 4230 Basic stats: COMPLETE Column stats: NONE
Join Operator
condition map:
- Left Semi Join 0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -1119,23 +1114,23 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (value = value) (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: key (type: string), value (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Demux Operator
- Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Mux Operator
- Statistics: Num rows: 1125 Data size: 11952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
Join Operator
condition map:
Inner Join 0 to 1
@@ -1165,9 +1160,9 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Mux Operator
- Statistics: Num rows: 1125 Data size: 11952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE
Join Operator
condition map:
Inner Join 0 to 1
@@ -2157,7 +2152,7 @@ STAGE PLANS:
Demux Operator
Statistics: Num rows: 6 Data size: 1249 Basic stats: COMPLETE Column stats: NONE
Mux Operator
- Statistics: Num rows: 7 Data size: 1457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1873 Basic stats: COMPLETE Column stats: NONE
Join Operator
condition map:
Left Outer Join0 to 1
@@ -2190,14 +2185,14 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 3 Data size: 624 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 624 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: bigint), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 624 Basic stats: COMPLETE Column stats: NONE
Mux Operator
- Statistics: Num rows: 7 Data size: 1457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1873 Basic stats: COMPLETE Column stats: NONE
Join Operator
condition map:
Left Outer Join0 to 1
diff --git a/ql/src/test/results/clientpositive/subquery_notin_having.q.out b/ql/src/test/results/clientpositive/subquery_notin_having.q.out
index d7ae742..6d4608d 100644
--- a/ql/src/test/results/clientpositive/subquery_notin_having.q.out
+++ b/ql/src/test/results/clientpositive/subquery_notin_having.q.out
@@ -228,11 +228,10 @@ POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1, Stage-5
- Stage-3 depends on stages: Stage-2, Stage-7
+ Stage-3 depends on stages: Stage-2, Stage-6
Stage-4 is a root stage
Stage-5 depends on stages: Stage-4
Stage-6 is a root stage
- Stage-7 depends on stages: Stage-6
Stage-0 depends on stages: Stage-3
STAGE PLANS:
@@ -320,7 +319,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: double)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: double)
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: boolean)
Reduce Operator Tree:
Join Operator
@@ -455,46 +454,19 @@ STAGE PLANS:
expressions: _col0 (type: string), _col1 (type: double)
outputColumnNames: _col0, _col1
Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: double)
- mode: hash
- outputColumnNames: _col0, _col1
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
Statistics: Num rows: 2 Data size: 242 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-7
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: double)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: double)
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: double)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: double), true (type: boolean)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 121 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: _col0 (type: string), _col1 (type: double), true (type: boolean)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2 Data size: 242 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
@@ -526,7 +498,7 @@ POSTHOOK: Input: default@part
#### A masked pattern was here ####
Manufacturer#1 1173.15
Manufacturer#2 1690.68
-Warning: Shuffle Join JOIN[32][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[27][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
PREHOOK: query: explain
select b.p_mfgr, min(p_retailprice)
from part b
@@ -639,7 +611,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: boolean)
Reduce Operator Tree:
Join Operator
@@ -767,24 +739,15 @@ STAGE PLANS:
predicate: ((_col1 - _col2) > 600.0) (type: boolean)
Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
+ expressions: _col0 (type: string), true (type: boolean)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string)
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), true (type: boolean)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 242 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
+ 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
@@ -792,7 +755,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[32][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[27][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
PREHOOK: query: select b.p_mfgr, min(p_retailprice)
from part b
group by b.p_mfgr
@@ -1121,7 +1084,7 @@ STAGE PLANS:
key expressions: _col3 (type: int)
sort order: +
Map-reduce partition columns: _col3 (type: int)
- Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 171 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: boolean)
Reduce Operator Tree:
Join Operator
@@ -1156,19 +1119,19 @@ STAGE PLANS:
alias: t2
Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (c1 = c1) (type: boolean)
- Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
+ predicate: c1 is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(), count(c1)
keys: c1 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Reduce Operator Tree:
Group By Operator
@@ -1191,18 +1154,18 @@ STAGE PLANS:
alias: t2
Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (c1 = c1) (type: boolean)
- Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
+ predicate: c1 is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: c1 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int)
@@ -1235,7 +1198,7 @@ STAGE PLANS:
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 78 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 156 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
@@ -1244,7 +1207,7 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
outputColumnNames: _col2, _col3
- Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 171 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -1278,17 +1241,12 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 2 Data size: 156 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: int)
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 78 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
+ 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
diff --git a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out
index 40e64d2..0a7a36f 100644
--- a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out
+++ b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out
@@ -187,48 +187,10 @@ where b.key in
)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((value = value) and (key > '9')) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: key (type: string), value (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 41 Data size: 435 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-1
Map Reduce
Map Operator Tree:
@@ -245,11 +207,25 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((value = value) and (key > '9')) (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
@@ -441,7 +417,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: boolean)
Reduce Operator Tree:
Join Operator
@@ -544,12 +520,12 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col0 = _col0) (type: boolean)
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), true (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
diff --git a/ql/src/test/results/clientpositive/udf_between.q.out b/ql/src/test/results/clientpositive/udf_between.q.out
index 2bb7264..8070735 100644
--- a/ql/src/test/results/clientpositive/udf_between.q.out
+++ b/ql/src/test/results/clientpositive/udf_between.q.out
@@ -26,7 +26,7 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (UDFToDouble(key) + 100.0) BETWEEN 100 AND 200 (type: boolean)
+ predicate: (UDFToDouble(key) + 100.0) BETWEEN 100.0 AND 200.0 (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
@@ -81,7 +81,7 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (not (UDFToDouble(key) + 100.0) BETWEEN 100 AND 200) (type: boolean)
+ predicate: (not (UDFToDouble(key) + 100.0) BETWEEN 100.0 AND 200.0) (type: boolean)
Statistics: Num rows: 445 Data size: 4727 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
diff --git a/ql/src/test/results/clientpositive/vector_between_columns.q.out b/ql/src/test/results/clientpositive/vector_between_columns.q.out
index 8a79a51..9f64260 100644
--- a/ql/src/test/results/clientpositive/vector_between_columns.q.out
+++ b/ql/src/test/results/clientpositive/vector_between_columns.q.out
@@ -129,13 +129,13 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 25 Data size: 385 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), _col3 (type: smallint), CASE WHEN (_col1 BETWEEN _col3 AND _col3) THEN ('Ok') ELSE ('NoOk') END (type: string)
+ expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), _col3 (type: smallint), CASE WHEN (_col1 BETWEEN UDFToInteger(_col3) AND UDFToInteger(_col3)) THEN ('Ok') ELSE ('NoOk') END (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
Select Vectorization:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 2, 1, 3, 5]
- selectExpressions: IfExprStringScalarStringScalar(col 4, val Ok, val NoOk)(children: VectorUDFAdaptor(_col1 BETWEEN _col3 AND _col3) -> 4:boolean) -> 5:String
+ selectExpressions: IfExprStringScalarStringScalar(col 4, val Ok, val NoOk)(children: VectorUDFAdaptor(_col1 BETWEEN UDFToInteger(_col3) AND UDFToInteger(_col3))(children: col 3, col 3) -> 4:boolean) -> 5:String
Statistics: Num rows: 25 Data size: 385 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -274,8 +274,8 @@ STAGE PLANS:
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: SelectColumnIsTrue(col 4)(children: VectorUDFAdaptor(_col1 BETWEEN _col3 AND _col3) -> 4:boolean) -> boolean
- predicate: _col1 BETWEEN _col3 AND _col3 (type: boolean)
+ predicateExpression: SelectColumnIsTrue(col 4)(children: VectorUDFAdaptor(_col1 BETWEEN UDFToInteger(_col3) AND UDFToInteger(_col3))(children: col 3, col 3) -> 4:boolean) -> boolean
+ predicate: _col1 BETWEEN UDFToInteger(_col3) AND UDFToInteger(_col3) (type: boolean)
Statistics: Num rows: 2 Data size: 30 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), _col3 (type: smallint)
diff --git a/ql/src/test/results/clientpositive/vector_interval_mapjoin.q.out b/ql/src/test/results/clientpositive/vector_interval_mapjoin.q.out
index d2a879d..84b9250 100644
--- a/ql/src/test/results/clientpositive/vector_interval_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/vector_interval_mapjoin.q.out
@@ -202,7 +202,7 @@ STAGE PLANS:
alias: vectortab_b_1korc
Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (s is not null and (dt - CAST( ts AS DATE)) is not null) (type: boolean)
+ predicate: (s is not null and dt is not null and ts is not null) (type: boolean)
Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time)
@@ -226,8 +226,8 @@ STAGE PLANS:
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 8) -> boolean, SelectColumnIsNotNull(col 14)(children: DateColSubtractDateColumn(col 12, col 13)(children: CastTimestampToDate(col 10) -> 13:date) -> 14:timestamp) -> boolean) -> boolean
- predicate: (s is not null and (dt - CAST( ts AS DATE)) is not null) (type: boolean)
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 8) -> boolean, SelectColumnIsNotNull(col 12) -> boolean, SelectColumnIsNotNull(col 10) -> boolean) -> boolean
+ predicate: (s is not null and dt is not null and ts is not null) (type: boolean)
Statistics: Num rows: 1000 Data size: 460264 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time)
diff --git a/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out b/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out
index d9591d0..da67386 100644
--- a/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out
+++ b/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out
@@ -18,7 +18,7 @@ STAGE PLANS:
alias: alltypesorc
Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (cint) IN (ctinyint, cbigint) (type: boolean)
+ predicate: (cint) IN (UDFToInteger(ctinyint), UDFToInteger(cbigint)) (type: boolean)
Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)
@@ -35,7 +35,7 @@ STAGE PLANS:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- notVectorizedReason: Predicate expression for FILTER operator: Cannot vectorize IN() - casting a column is not supported. Column type is int but the common type is bigint
+ notVectorizedReason: Predicate expression for FILTER operator: Vectorizing IN expression only supported for constant values
vectorized: false
Stage: Stage-0
diff --git a/ql/src/test/results/clientpositive/vector_string_decimal.q.out b/ql/src/test/results/clientpositive/vector_string_decimal.q.out
index 3540635..9b3684c 100644
--- a/ql/src/test/results/clientpositive/vector_string_decimal.q.out
+++ b/ql/src/test/results/clientpositive/vector_string_decimal.q.out
@@ -59,26 +59,43 @@ STAGE PLANS:
TableScan
alias: orc_decimal
Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0]
Filter Operator
- predicate: (id) IN ('100000000', '200000000') (type: boolean)
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterDoubleColumnInList(col 1, values [1.0E8, 2.0E8])(children: CastDecimalToDouble(col 0) -> 1:double) -> boolean
+ predicate: (UDFToDouble(id)) IN (1.0E8, 2.0E8) (type: boolean)
Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: id (type: decimal(18,0))
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0]
Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 2 Data size: 224 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
+ Execution mode: vectorized
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- notVectorizedReason: Predicate expression for FILTER operator: Cannot vectorize IN() - casting a column is not supported. Column type is decimal(18,0) but the common type is string
- vectorized: false
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
Stage: Stage-0
Fetch Operator