diff --git a/accumulo-handler/src/test/results/positive/accumulo_queries.q.out b/accumulo-handler/src/test/results/positive/accumulo_queries.q.out index bd79eefb87..a21a099334 100644 --- a/accumulo-handler/src/test/results/positive/accumulo_queries.q.out +++ b/accumulo-handler/src/test/results/positive/accumulo_queries.q.out @@ -289,7 +289,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: accumulo_table_1 - filterExpr: (key < 120) (type: boolean) + filterExpr: ((100 < key) and (key < 120)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) diff --git a/hbase-handler/src/test/results/positive/hbase_queries.q.out b/hbase-handler/src/test/results/positive/hbase_queries.q.out index d6ec14e375..0fce6c8e24 100644 --- a/hbase-handler/src/test/results/positive/hbase_queries.q.out +++ b/hbase-handler/src/test/results/positive/hbase_queries.q.out @@ -291,7 +291,7 @@ STAGE PLANS: alias: hbase_table_1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (key < 120) (type: boolean) + predicate: ((100 < key) and (key < 120)) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) diff --git a/pom.xml b/pom.xml index a6b5663b76..6d16675852 100644 --- a/pom.xml +++ b/pom.xml @@ -121,7 +121,7 @@ 1.10.0 1.7.7 0.8.0.RELEASE - 1.14.0 + 1.15.0 4.2.4 4.1.17 4.1.19 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 77a7b0f26b..f8825a27ca 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 @@ -35,7 +35,6 @@ 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; @@ -72,6 +71,7 @@ import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoFactory; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils; +import org.joda.time.Interval; import org.slf4j.Logger; import org.slf4j.LoggerFactory; @@ -311,9 +311,8 @@ private static RelNode createTableScan(Table viewTable) { } metrics.add(field.getName()); } - // TODO: Default interval will be an Interval once Calcite 1.15.0 is released. - // We will need to update the type of this list. - 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, diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRelDistribution.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRelDistribution.java index 653f1c535c..7e5beee573 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRelDistribution.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRelDistribution.java @@ -19,6 +19,7 @@ import java.util.List; +import org.apache.calcite.plan.RelMultipleTrait; import org.apache.calcite.plan.RelOptPlanner; import org.apache.calcite.plan.RelTrait; import org.apache.calcite.plan.RelTraitDef; @@ -26,8 +27,13 @@ import org.apache.calcite.rel.RelDistributionTraitDef; import org.apache.calcite.util.mapping.Mappings.TargetMapping; +import com.google.common.collect.Ordering; + public class HiveRelDistribution implements RelDistribution { + private static final Ordering> ORDERING = + Ordering.natural().lexicographical(); + List keys; RelDistribution.Type type; @@ -77,4 +83,21 @@ public Type getType() { return type; } + @Override + public boolean isTop() { + return type == Type.ANY; + } + + @Override + public int compareTo(RelMultipleTrait o) { + final RelDistribution distribution = (RelDistribution) o; + if (type == distribution.getType() + && (type == Type.HASH_DISTRIBUTED + || type == Type.RANGE_DISTRIBUTED)) { + return ORDERING.compare(getKeys(), distribution.getKeys()); + } + + return type.compareTo(distribution.getType()); + } + } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateProjectMergeRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateProjectMergeRule.java index b5f17754cb..ec182cd43a 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateProjectMergeRule.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateProjectMergeRule.java @@ -16,28 +16,15 @@ */ package org.apache.hadoop.hive.ql.optimizer.calcite.rules; -import java.util.HashMap; -import java.util.List; -import java.util.Map; - import org.apache.calcite.plan.RelOptRuleCall; -import org.apache.calcite.rel.RelNode; import org.apache.calcite.rel.core.Aggregate; -import org.apache.calcite.rel.core.Aggregate.Group; import org.apache.calcite.rel.core.AggregateCall; import org.apache.calcite.rel.rules.AggregateProjectMergeRule; -import org.apache.calcite.rex.RexInputRef; -import org.apache.calcite.rex.RexNode; -import org.apache.calcite.tools.RelBuilder; -import org.apache.calcite.util.ImmutableBitSet; import org.apache.hadoop.hive.ql.optimizer.calcite.HiveRelFactories; import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveAggregate; import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveGroupingID; import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject; -import com.google.common.collect.ImmutableList; -import com.google.common.collect.Lists; - /** * Planner rule that recognizes a {@link HiveAggregate} * on top of a {@link HiveProject} and if possible @@ -71,95 +58,6 @@ public boolean matches(RelOptRuleCall call) { return super.matches(call); } - public void onMatch(RelOptRuleCall call) { - final HiveAggregate aggregate = call.rel(0); - final HiveProject project = call.rel(1); - RelNode x = apply(call, aggregate, project); - if (x != null) { - call.transformTo(x); - } - } - - public static RelNode apply(RelOptRuleCall call, HiveAggregate aggregate, - HiveProject project) { - final List newKeys = Lists.newArrayList(); - final Map map = new HashMap<>(); - for (int key : aggregate.getGroupSet()) { - final RexNode rex = project.getProjects().get(key); - if (rex instanceof RexInputRef) { - final int newKey = ((RexInputRef) rex).getIndex(); - newKeys.add(newKey); - map.put(key, newKey); - } else { - // Cannot handle "GROUP BY expression" - return null; - } - } - - final ImmutableBitSet newGroupSet = aggregate.getGroupSet().permute(map); - ImmutableList newGroupingSets = null; - if (aggregate.getGroupType() != Group.SIMPLE) { - newGroupingSets = - ImmutableBitSet.ORDERING.immutableSortedCopy( - ImmutableBitSet.permute(aggregate.getGroupSets(), map)); - } - - final ImmutableList.Builder aggCalls = - ImmutableList.builder(); - for (AggregateCall aggregateCall : aggregate.getAggCallList()) { - final ImmutableList.Builder newArgs = ImmutableList.builder(); - for (int arg : aggregateCall.getArgList()) { - final RexNode rex = project.getProjects().get(arg); - if (rex instanceof RexInputRef) { - newArgs.add(((RexInputRef) rex).getIndex()); - } else { - // Cannot handle "AGG(expression)" - return null; - } - } - final int newFilterArg; - if (aggregateCall.filterArg >= 0) { - final RexNode rex = project.getProjects().get(aggregateCall.filterArg); - if (!(rex instanceof RexInputRef)) { - return null; - } - newFilterArg = ((RexInputRef) rex).getIndex(); - } else { - newFilterArg = -1; - } - aggCalls.add(aggregateCall.copy(newArgs.build(), newFilterArg)); - } - - final Aggregate newAggregate = - aggregate.copy(aggregate.getTraitSet(), project.getInput(), - aggregate.indicator, newGroupSet, newGroupingSets, - aggCalls.build()); - - // Add a project if the group set is not in the same order or - // contains duplicates. - final RelBuilder relBuilder = call.builder(); - relBuilder.push(newAggregate); - if (!newKeys.equals(newGroupSet.asList())) { - final List posList = Lists.newArrayList(); - for (int newKey : newKeys) { - posList.add(newGroupSet.indexOf(newKey)); - } - if (aggregate.indicator) { - for (int newKey : newKeys) { - posList.add(aggregate.getGroupCount() + newGroupSet.indexOf(newKey)); - } - } - for (int i = newAggregate.getGroupCount() - + newAggregate.getIndicatorCount(); - i < newAggregate.getRowType().getFieldCount(); i++) { - posList.add(i); - } - relBuilder.project(relBuilder.fields(posList)); - } - - return relBuilder.build(); - } - } // End HiveAggregateProjectMergeRule.java diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregatePullUpConstantsRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregatePullUpConstantsRule.java index 370c0eca47..564da1d45c 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregatePullUpConstantsRule.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregatePullUpConstantsRule.java @@ -20,6 +20,7 @@ import org.apache.calcite.plan.RelOptRuleCall; import org.apache.calcite.rel.RelNode; import org.apache.calcite.rel.core.Aggregate; +import org.apache.calcite.rel.core.Aggregate.Group; import org.apache.calcite.rel.rules.AggregateProjectPullUpConstantsRule; import org.apache.hadoop.hive.ql.optimizer.calcite.HiveRelFactories; import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveAggregate; @@ -38,7 +39,7 @@ public HiveAggregatePullUpConstantsRule() { public boolean matches(RelOptRuleCall call) { final Aggregate aggregate = call.rel(0); // Rule cannot be applied if there are GroupingSets - if (aggregate.indicator) { + if (aggregate.getGroupType() != Group.SIMPLE) { return false; } return super.matches(call); diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveReduceExpressionsRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveReduceExpressionsRule.java index 9a5d8e2826..d97696105e 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveReduceExpressionsRule.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveReduceExpressionsRule.java @@ -77,7 +77,7 @@ * {@link org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveJoin}. */ public static final ReduceExpressionsRule JOIN_INSTANCE = - new JoinReduceExpressionsRule(HiveJoin.class, HiveRelFactories.HIVE_BUILDER); + new JoinReduceExpressionsRule(HiveJoin.class, false, HiveRelFactories.HIVE_BUILDER); //~ Constructors ----------------------------------------------------------- @@ -112,7 +112,7 @@ public FilterReduceExpressionsRule(Class filterClass, final RelMetadataQuery mq = call.getMetadataQuery(); final RelOptPredicateList predicates = mq.getPulledUpPredicates(filter.getInput()); - if (reduceExpressions(filter, expList, predicates, true)) { + if (reduceExpressions(filter, expList, predicates, true, false)) { assert expList.size() == 1; newConditionExp = expList.get(0); reduced = true; 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 ba64f97105..20386f1480 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 @@ -52,7 +52,6 @@ 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.CalciteConnectionConfig; import org.apache.calcite.config.CalciteConnectionConfigImpl; import org.apache.calcite.config.CalciteConnectionProperty; @@ -259,6 +258,7 @@ 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; @@ -2425,9 +2425,8 @@ private RelNode genTableLogicalPlan(String tableAlias, QB qb) throws SemanticExc } metrics.add(field.getName()); } - // TODO: Default interval will be an Interval once Calcite 1.15.0 is released. - // We will need to update the type of this list. - 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, diff --git a/ql/src/test/results/clientpositive/druid/druidmini_test1.q.out b/ql/src/test/results/clientpositive/druid/druidmini_test1.q.out index 9577e72ee4..2cbd5fb954 100644 --- a/ql/src/test/results/clientpositive/druid/druidmini_test1.q.out +++ b/ql/src/test/results/clientpositive/druid/druidmini_test1.q.out @@ -64,7 +64,7 @@ STAGE PLANS: TableScan alias: druid_table properties: - druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"all","aggregations":[{"type":"count","name":"$f0"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}} + druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"all","aggregations":[{"type":"count","name":"$f0"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 9173 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -99,7 +99,7 @@ STAGE PLANS: TableScan alias: druid_table properties: - druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"year","aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"cfloat"},{"type":"doubleSum","name":"$f2","fieldName":"cdouble"},{"type":"longSum","name":"$f3","fieldName":"ctinyint"},{"type":"longSum","name":"$f4","fieldName":"csmallint"},{"type":"longSum","name":"$f5","fieldName":"cint"},{"type":"longSum","name":"$f6","fieldName":"cbigint"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}} + druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"year","aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"cfloat"},{"type":"doubleSum","name":"$f2","fieldName":"cdouble"},{"type":"longSum","name":"$f3","fieldName":"ctinyint"},{"type":"longSum","name":"$f4","fieldName":"csmallint"},{"type":"longSum","name":"$f5","fieldName":"cint"},{"type":"longSum","name":"$f6","fieldName":"cbigint"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 9173 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -137,7 +137,7 @@ STAGE PLANS: TableScan alias: druid_table properties: - druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"year","aggregations":[{"type":"doubleMin","name":"$f1","fieldName":"cfloat"},{"type":"doubleMin","name":"$f2","fieldName":"cdouble"},{"type":"longMin","name":"$f3","fieldName":"ctinyint"},{"type":"longMin","name":"$f4","fieldName":"csmallint"},{"type":"longMin","name":"$f5","fieldName":"cint"},{"type":"longMin","name":"$f6","fieldName":"cbigint"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}} + druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"year","aggregations":[{"type":"doubleMin","name":"$f1","fieldName":"cfloat"},{"type":"doubleMin","name":"$f2","fieldName":"cdouble"},{"type":"longMin","name":"$f3","fieldName":"ctinyint"},{"type":"longMin","name":"$f4","fieldName":"csmallint"},{"type":"longMin","name":"$f5","fieldName":"cint"},{"type":"longMin","name":"$f6","fieldName":"cbigint"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 9173 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -175,7 +175,7 @@ STAGE PLANS: TableScan alias: druid_table properties: - druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"year","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"cfloat"},{"type":"doubleMax","name":"$f2","fieldName":"cdouble"},{"type":"longMax","name":"$f3","fieldName":"ctinyint"},{"type":"longMax","name":"$f4","fieldName":"csmallint"},{"type":"longMax","name":"$f5","fieldName":"cint"},{"type":"longMax","name":"$f6","fieldName":"cbigint"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"context":{"skipEmptyBuckets":true}} + druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"year","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"cfloat"},{"type":"doubleMax","name":"$f2","fieldName":"cdouble"},{"type":"longMax","name":"$f3","fieldName":"ctinyint"},{"type":"longMax","name":"$f4","fieldName":"csmallint"},{"type":"longMax","name":"$f5","fieldName":"cint"},{"type":"longMax","name":"$f6","fieldName":"cbigint"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 9173 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -211,7 +211,7 @@ STAGE PLANS: TableScan alias: druid_table properties: - druid.query.json {"queryType":"groupBy","dataSource":"default.druid_table","granularity":"all","dimensions":[{"type":"default","dimension":"cstring1"}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f1","direction":"ascending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"cdouble"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"default.druid_table","granularity":"all","dimensions":[{"type":"default","dimension":"cstring1"}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f1","direction":"ascending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"cdouble"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]} druid.query.type groupBy Statistics: Num rows: 9173 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -253,7 +253,7 @@ STAGE PLANS: TableScan alias: druid_table properties: - druid.query.json {"queryType":"groupBy","dataSource":"default.druid_table","granularity":"all","dimensions":[{"type":"default","dimension":"cstring2"}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"cstring2","direction":"ascending","dimensionOrder":"alphanumeric"}]},"aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"cdouble"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"default.druid_table","granularity":"all","dimensions":[{"type":"default","dimension":"cstring2"}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"cstring2","direction":"ascending","dimensionOrder":"alphanumeric"}]},"aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"cdouble"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]} druid.query.type groupBy Statistics: Num rows: 9173 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -299,7 +299,7 @@ STAGE PLANS: TableScan alias: druid_table properties: - druid.query.json {"queryType":"select","dataSource":"default.druid_table","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.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} druid.query.type select Statistics: Num rows: 9173 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -374,7 +374,7 @@ STAGE PLANS: TableScan alias: druid_table properties: - druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1900-01-01T00:00:00.000/1970-03-01T08:00:00.000"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1900-01-01T00:00:00.000Z/1970-03-01T08:00:00.000Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} druid.query.type select Statistics: Num rows: 9173 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -451,7 +451,7 @@ STAGE PLANS: TableScan alias: druid_table properties: - druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1968-01-01T08:00:00.000/1970-03-01T08:00:00.001"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1968-01-01T08:00:00.000Z/1970-03-01T08:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} druid.query.type select Statistics: Num rows: 9173 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -530,7 +530,7 @@ STAGE PLANS: TableScan alias: druid_table properties: - druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1968-01-01T08:00:00.000/1970-03-01T08:00:00.001"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1968-01-01T08:00:00.000Z/1970-03-01T08:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} druid.query.type select Statistics: Num rows: 9173 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -609,7 +609,7 @@ STAGE PLANS: TableScan alias: druid_table properties: - druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1968-01-01T08:00:00.000/1970-01-01T08:00:00.001"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1968-01-01T08:00:00.000Z/1970-01-01T08:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} druid.query.type select Statistics: Num rows: 9173 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -688,7 +688,7 @@ STAGE PLANS: TableScan alias: druid_table properties: - druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1968-01-01T08:00:00.000/1970-04-01T08:00:00.001"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1968-01-01T08:00:00.000Z/1970-04-01T08:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} druid.query.type select Statistics: Num rows: 9173 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator diff --git a/ql/src/test/results/clientpositive/druid_basic2.q.out b/ql/src/test/results/clientpositive/druid_basic2.q.out index 5a5f7541ec..64e494d71a 100644 --- a/ql/src/test/results/clientpositive/druid_basic2.q.out +++ b/ql/src/test/results/clientpositive/druid_basic2.q.out @@ -76,7 +76,7 @@ STAGE PLANS: TableScan alias: druid_table_1 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"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + 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,"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 @@ -103,7 +103,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.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,"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 @@ -134,7 +134,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.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,"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 @@ -165,7 +165,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"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.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"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.type groupBy Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE GatherStats: false @@ -209,53 +209,39 @@ STAGE PLANS: Map Operator Tree: TableScan alias: druid_table_1 - filterExpr: language is not null (type: boolean) properties: - druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","language"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"not","field":{"type":"selector","dimension":"language","value":null}},"dimensions":["robot","language"],"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 - Filter Operator - isSamplingPred: false - predicate: language is not null (type: boolean) + Select Operator + expressions: robot (type: string), language (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: robot (type: string), language (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - tag: 0 - value expressions: _col0 (type: string) - auto parallelism: false + tag: 0 + value expressions: _col0 (type: string) + auto parallelism: false TableScan alias: druid_table_1 - filterExpr: language is not null (type: boolean) properties: - druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["language"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"not","field":{"type":"selector","dimension":"language","value":null}},"dimensions":["language"],"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 - Filter Operator - isSamplingPred: false - predicate: language is not null (type: boolean) + Reduce Output Operator + key expressions: language (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: language (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: language (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - tag: 1 - auto parallelism: false + tag: 1 + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -273,7 +259,7 @@ 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 with local time zone: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":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["robot","language"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"not","field":{"type":"selector","dimension":"language","value":null}},"dimensions":["robot","language"],"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 @@ -299,7 +285,7 @@ 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 with local time zone: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":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["language"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"not","field":{"type":"selector","dimension":"language","value":null}},"dimensions":["language"],"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 @@ -316,7 +302,7 @@ STAGE PLANS: name: default.druid_table_1 name: default.druid_table_1 Truncated Path -> Alias: - /druid_table_1 [$hdt$_0:druid_table_1, $hdt$_1:druid_table_1] + /druid_table_1 [$hdt$_0:druid_table_1, druid_table_1] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -324,11 +310,11 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 + 1 language (type: string) + outputColumnNames: _col0, _col3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col0 (type: string), _col2 (type: string) + expressions: _col0 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator @@ -398,7 +384,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.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,"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 @@ -413,7 +399,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.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,"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 @@ -441,7 +427,7 @@ 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 with local time zone: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":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.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,"fromNext":true},"context":{"druid.query.fetch":false}} druid.query.type select #### A masked pattern was here #### name default.druid_table_1 @@ -467,7 +453,7 @@ 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 with local time zone: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":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.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,"fromNext":true},"context":{"druid.query.fetch":false}} druid.query.type select #### A masked pattern was here #### name default.druid_table_1 @@ -553,7 +539,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"day","timeZone":"US/Pacific","locale":"en-US"}}],"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.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"day","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]} druid.query.type groupBy Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE GatherStats: false @@ -588,7 +574,7 @@ 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 with local time zone:string:string:string:string:string:string:string:string:float:float:float:float:float druid.datasource wikipedia - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"day","timeZone":"US/Pacific","locale":"en-US"}}],"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.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"day","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]} druid.query.type groupBy #### A masked pattern was here #### name default.druid_table_1 @@ -614,7 +600,7 @@ 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 with local time zone:string:string:string:string:string:string:string:string:float:float:float:float:float druid.datasource wikipedia - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"day","timeZone":"US/Pacific","locale":"en-US"}}],"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.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"day","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]} druid.query.type groupBy #### A masked pattern was here #### name default.druid_table_1 @@ -689,7 +675,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"],"dimensions":["namespace"],"metrics":["deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["namespace"],"metrics":["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 Select Operator @@ -739,7 +725,7 @@ STAGE PLANS: alias: druid_table_1 filterExpr: floor_day(__time) BETWEEN 1999-11-01 00:00:00.0 US/Pacific AND 1999-11-10 00:00:00.0 US/Pacific (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"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + 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,"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 @@ -833,7 +819,7 @@ STAGE PLANS: alias: druid_table_1 filterExpr: floor_day(extract) BETWEEN 1999-11-01 00:00:00.0 US/Pacific AND 1999-11-10 00:00:00.0 US/Pacific (type: boolean) properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"extraction","dimension":"__time","outputName":"extract","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","timeZone":"US/Pacific"}},{"type":"default","dimension":"robot"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"extraction","dimension":"__time","outputName":"extract","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","timeZone":"US/Pacific"}},{"type":"default","dimension":"robot"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"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 Filter Operator @@ -898,7 +884,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"day","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"robot","direction":"ascending","dimensionOrder":"alphanumeric"}]},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"intervals":["1999-11-01T08:00:00.000/1999-11-10T08:00:00.001"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"day","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"robot","direction":"ascending","dimensionOrder":"alphanumeric"}]},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"intervals":["1999-11-01T08:00:00.000Z/1999-11-10T08:00:00.001Z"]} druid.query.type groupBy Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator diff --git a/ql/src/test/results/clientpositive/druid_basic3.q.out b/ql/src/test/results/clientpositive/druid_basic3.q.out index c174a5cc54..ce6d0aafed 100644 --- a/ql/src/test/results/clientpositive/druid_basic3.q.out +++ b/ql/src/test/results/clientpositive/druid_basic3.q.out @@ -33,7 +33,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","columns":[{"dimension":"postagg#0","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"}],"postAggregations":[{"type":"arithmetic","name":"postagg#0","fn":"+","fields":[{"type":"fieldAccess","name":"","fieldName":"$f1"},{"type":"fieldAccess","name":"","fieldName":"$f2"}]}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","columns":[{"dimension":"postagg#0","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"}],"postAggregations":[{"type":"arithmetic","name":"postagg#0","fn":"+","fields":[{"type":"fieldAccess","name":"","fieldName":"$f1"},{"type":"fieldAccess","name":"","fieldName":"$f2"}]}],"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 @@ -65,7 +65,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","columns":[{"dimension":"postagg#0","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"delta"},{"type":"doubleSum","name":"$f2","fieldName":"added"}],"postAggregations":[{"type":"arithmetic","name":"postagg#0","fn":"+","fields":[{"type":"fieldAccess","name":"","fieldName":"$f2"},{"type":"fieldAccess","name":"","fieldName":"$f1"}]}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","columns":[{"dimension":"postagg#0","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"delta"},{"type":"doubleSum","name":"$f2","fieldName":"added"}],"postAggregations":[{"type":"arithmetic","name":"postagg#0","fn":"+","fields":[{"type":"fieldAccess","name":"","fieldName":"$f2"},{"type":"fieldAccess","name":"","fieldName":"$f1"}]}],"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 @@ -97,7 +97,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","columns":[{"dimension":"postagg#0","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"}],"postAggregations":[{"type":"arithmetic","name":"postagg#0","fn":"quotient","fields":[{"type":"fieldAccess","name":"","fieldName":"$f1"},{"type":"fieldAccess","name":"","fieldName":"$f2"}]}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","columns":[{"dimension":"postagg#0","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"}],"postAggregations":[{"type":"arithmetic","name":"postagg#0","fn":"quotient","fields":[{"type":"fieldAccess","name":"","fieldName":"$f1"},{"type":"fieldAccess","name":"","fieldName":"$f2"}]}],"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 @@ -129,7 +129,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","columns":[{"dimension":"postagg#0","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"}],"postAggregations":[{"type":"arithmetic","name":"postagg#0","fn":"*","fields":[{"type":"fieldAccess","name":"","fieldName":"$f1"},{"type":"fieldAccess","name":"","fieldName":"$f2"}]}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","columns":[{"dimension":"postagg#0","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"}],"postAggregations":[{"type":"arithmetic","name":"postagg#0","fn":"*","fields":[{"type":"fieldAccess","name":"","fieldName":"$f1"},{"type":"fieldAccess","name":"","fieldName":"$f2"}]}],"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 @@ -161,7 +161,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","columns":[{"dimension":"postagg#0","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"}],"postAggregations":[{"type":"arithmetic","name":"postagg#0","fn":"-","fields":[{"type":"fieldAccess","name":"","fieldName":"$f1"},{"type":"fieldAccess","name":"","fieldName":"$f2"}]}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","columns":[{"dimension":"postagg#0","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"}],"postAggregations":[{"type":"arithmetic","name":"postagg#0","fn":"-","fields":[{"type":"fieldAccess","name":"","fieldName":"$f1"},{"type":"fieldAccess","name":"","fieldName":"$f2"}]}],"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 @@ -193,7 +193,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"}],"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 @@ -251,7 +251,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"},{"type":"count","name":"$f3"},{"type":"doubleSum","name":"$f4","fieldName":"deleted"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"},{"type":"count","name":"$f3"},{"type":"doubleSum","name":"$f4","fieldName":"deleted"}],"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 @@ -305,7 +305,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"}],"limitSpec":{"type":"default"},"filter":{"type":"in","dimension":"__time","values":["10","11"],"extractionFn":{"type":"timeFormat","format":"w","timeZone":"US/Pacific","locale":"en-US"}},"aggregations":[{"type":"doubleSum","name":"$f2","fieldName":"added"},{"type":"doubleSum","name":"$f3","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"}],"limitSpec":{"type":"default"},"filter":{"type":"in","dimension":"__time","values":["10","11"],"extractionFn":{"type":"timeFormat","format":"w","timeZone":"US/Pacific","locale":"en-US"}},"aggregations":[{"type":"doubleSum","name":"$f2","fieldName":"added"},{"type":"doubleSum","name":"$f3","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]} druid.query.type groupBy Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -349,7 +349,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"delta"},{"type":"count","name":"$f2"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"delta"},{"type":"count","name":"$f2"}],"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 @@ -405,7 +405,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","columns":[{"dimension":"postagg#0","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"},{"type":"doubleSum","name":"$f3","fieldName":"deleted"}],"postAggregations":[{"type":"arithmetic","name":"postagg#0","fn":"quotient","fields":[{"type":"fieldAccess","name":"","fieldName":"$f1"},{"type":"fieldAccess","name":"","fieldName":"$f2"}]}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","columns":[{"dimension":"postagg#0","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"},{"type":"doubleSum","name":"$f3","fieldName":"deleted"}],"postAggregations":[{"type":"arithmetic","name":"postagg#0","fn":"quotient","fields":[{"type":"fieldAccess","name":"","fieldName":"$f1"},{"type":"fieldAccess","name":"","fieldName":"$f2"}]}],"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 @@ -453,7 +453,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"language"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]} druid.query.type groupBy Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -513,7 +513,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"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 @@ -554,7 +554,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","limit":5,"columns":[{"dimension":"robot","direction":"ascending","dimensionOrder":"alphanumeric"},{"dimension":"language","direction":"ascending","dimensionOrder":"alphanumeric"}]},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"}],"limitSpec":{"type":"default","limit":5,"columns":[{"dimension":"robot","direction":"ascending","dimensionOrder":"alphanumeric"},{"dimension":"language","direction":"ascending","dimensionOrder":"alphanumeric"}]},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"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 diff --git a/ql/src/test/results/clientpositive/druid_intervals.q.out b/ql/src/test/results/clientpositive/druid_intervals.q.out index 3cd28b5131..c94cbe9bd4 100644 --- a/ql/src/test/results/clientpositive/druid_intervals.q.out +++ b/ql/src/test/results/clientpositive/druid_intervals.q.out @@ -78,7 +78,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.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,"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 @@ -108,7 +108,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/2012-03-01T08:00:00.000Z"],"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 @@ -138,7 +138,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000Z/2012-03-01T08:00:00.001Z"],"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 @@ -170,7 +170,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000Z/2011-01-01T08:00:00.000Z"],"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 @@ -200,7 +200,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000/2011-01-01T08:00:00.001"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000Z/2011-01-01T08:00:00.001Z"],"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 @@ -232,7 +232,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000/2011-01-01T08:00:00.001","2012-01-01T08:00:00.000/2013-01-01T08:00:00.001"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000Z/2011-01-01T08:00:00.001Z","2012-01-01T08:00:00.000Z/2013-01-01T08:00:00.001Z"],"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 @@ -264,7 +264,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000/2012-01-01T08:00:00.001"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000Z/2012-01-01T08:00:00.001Z"],"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 @@ -294,7 +294,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000/2010-01-01T08:00:00.001","2011-01-01T08:00:00.000/2011-01-01T08:00:00.001"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000Z/2010-01-01T08:00:00.001Z","2011-01-01T08:00:00.000Z/2011-01-01T08:00:00.001Z"],"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 @@ -324,7 +324,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000/2010-01-01T08:00:00.001","2011-01-01T08:00:00.000/2011-01-01T08:00:00.001"],"filter":{"type":"selector","dimension":"robot","value":"user1"},"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["2010-01-01T08:00:00.000Z/2010-01-01T08:00:00.001Z","2011-01-01T08:00:00.000Z/2011-01-01T08:00:00.001Z"],"filter":{"type":"selector","dimension":"robot","value":"user1"},"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 @@ -355,7 +355,7 @@ STAGE PLANS: alias: druid_table_1 filterExpr: ((__time) IN (2010-01-01 00:00:00.0 US/Pacific, 2011-01-01 00:00:00.0 US/Pacific) or (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"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + 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,"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_timeseries.q.out b/ql/src/test/results/clientpositive/druid_timeseries.q.out index 330c068a02..264d2d1790 100644 --- a/ql/src/test/results/clientpositive/druid_timeseries.q.out +++ b/ql/src/test/results/clientpositive/druid_timeseries.q.out @@ -78,7 +78,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"all","aggregations":[{"type":"doubleMax","name":"$f0","fieldName":"added"},{"type":"doubleSum","name":"$f1","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -108,7 +108,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"extraction","dimension":"__time","outputName":"extract","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","timeZone":"US/Pacific"}}],"limitSpec":{"type":"default"},"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.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"extraction","dimension":"__time","outputName":"extract","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","timeZone":"US/Pacific"}}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","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.type groupBy Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -138,7 +138,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"year","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -168,7 +168,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"quarter","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -198,7 +198,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"month","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -228,7 +228,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"week","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -258,7 +258,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"day","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -288,7 +288,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"hour","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -318,7 +318,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"minute","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -348,7 +348,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - 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.json {"queryType":"timeseries","dataSource":"wikipedia","descending":false,"granularity":"second","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -380,7 +380,7 @@ 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":"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.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":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -417,7 +417,7 @@ STAGE PLANS: alias: druid_table_1 filterExpr: floor_hour(__time) BETWEEN 2010-01-01 00:00:00.0 US/Pacific AND 2014-01-01 00:00:00.0 US/Pacific (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":[],"metrics":["added","variation"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":[],"metrics":["added","variation"],"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 @@ -494,7 +494,7 @@ STAGE PLANS: alias: druid_table_1 filterExpr: floor_hour(__time) BETWEEN 2010-01-01 00:00:00.0 US/Pacific AND 2014-01-01 00:00:00.0 US/Pacific (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":[],"metrics":["added","variation"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":[],"metrics":["added","variation"],"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 3e2b477dfc..90eec3dd49 100644 --- a/ql/src/test/results/clientpositive/druid_topn.q.out +++ b/ql/src/test/results/clientpositive/druid_topn.q.out @@ -84,7 +84,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"}],"limitSpec":{"type":"default","limit":100,"columns":[{"dimension":"$f1","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"added"},{"type":"doubleSum","name":"$f2","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"}],"limitSpec":{"type":"default","limit":100,"columns":[{"dimension":"$f1","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleMax","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.type groupBy Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -118,7 +118,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"extraction","dimension":"__time","outputName":"extract","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","timeZone":"US/Pacific"}},{"type":"default","dimension":"robot"}],"limitSpec":{"type":"default","limit":100,"columns":[{"dimension":"$f3","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleMax","name":"$f2","fieldName":"added"},{"type":"doubleSum","name":"$f3","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"extraction","dimension":"__time","outputName":"extract","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","timeZone":"US/Pacific"}},{"type":"default","dimension":"robot"}],"limitSpec":{"type":"default","limit":100,"columns":[{"dimension":"$f3","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleMax","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 @@ -152,7 +152,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"extraction","dimension":"__time","outputName":"floor_year","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"year","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f3","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleMax","name":"$f2","fieldName":"added"},{"type":"doubleSum","name":"$f3","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"extraction","dimension":"__time","outputName":"floor_year","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"year","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f3","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleMax","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 @@ -186,7 +186,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"extraction","dimension":"__time","outputName":"floor_month","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"month","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f3","direction":"ascending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleMax","name":"$f2","fieldName":"added"},{"type":"doubleSum","name":"$f3","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"extraction","dimension":"__time","outputName":"floor_month","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"month","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f3","direction":"ascending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleMax","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 @@ -220,7 +220,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"namespace"},{"type":"extraction","dimension":"__time","outputName":"floor_month","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"month","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f4","direction":"descending","dimensionOrder":"numeric"},{"dimension":"$f3","direction":"descending","dimensionOrder":"numeric"}]},"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.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"namespace"},{"type":"extraction","dimension":"__time","outputName":"floor_month","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"month","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f4","direction":"descending","dimensionOrder":"numeric"},{"dimension":"$f3","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleMax","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 @@ -254,7 +254,7 @@ STAGE PLANS: TableScan alias: druid_table_1 properties: - druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"namespace"},{"type":"extraction","dimension":"__time","outputName":"floor_month","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"month","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"robot","direction":"ascending","dimensionOrder":"alphanumeric"},{"dimension":"$f3","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"variation"}],"intervals":["1900-01-01T00:00:00.000/3000-01-01T00:00:00.000"]} + druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"namespace"},{"type":"extraction","dimension":"__time","outputName":"floor_month","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"month","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"robot","direction":"ascending","dimensionOrder":"alphanumeric"},{"dimension":"$f3","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleMax","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 @@ -290,7 +290,7 @@ STAGE PLANS: 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.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":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}} druid.query.type timeseries Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator @@ -362,7 +362,7 @@ STAGE PLANS: alias: druid_table_1 filterExpr: floor_hour(__time) BETWEEN 2010-01-01 00:00:00.0 US/Pacific AND 2014-01-01 00:00:00.0 US/Pacific (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"],"metrics":["added","variation"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}} + 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":["added","variation"],"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/llap/explainuser_1.q.out b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out index 5adf401b25..d500844049 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out @@ -447,7 +447,7 @@ Stage-0 Select Operator [SEL_23] (rows=1 width=20) Output:["_col1","_col4"] Merge Join Operator [MERGEJOIN_41] (rows=1 width=20) - Conds:RS_19._col0=RS_20._col0(Inner),RS_20._col0=RS_21._col0(Inner),Output:["_col1","_col3","_col4","_col6"],residual filter predicates:{((_col3 > 0) or (_col1 >= 0))} {((_col1 >= 1) or (_col4 >= 1))} {((UDFToLong(_col1) + _col4) >= 0)} {((_col3 + _col6) >= 0)} + Conds:RS_19._col0=RS_20._col0(Inner),RS_20._col0=RS_21._col0(Inner),Output:["_col1","_col3","_col4","_col6"],residual filter predicates:{((_col1 >= 1) or (_col4 >= 1))} {((UDFToLong(_col1) + _col4) >= 0)} {((_col3 + _col6) >= 0)} <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_19] PartitionCols:_col0 @@ -594,7 +594,7 @@ Stage-0 Select Operator [SEL_23] (rows=1 width=20) Output:["_col1","_col4"] Merge Join Operator [MERGEJOIN_40] (rows=1 width=20) - Conds:RS_19._col0=RS_20._col0(Inner),RS_20._col0=RS_21._col0(Inner),Output:["_col1","_col3","_col4","_col6"],residual filter predicates:{((_col3 > 0) or (_col1 >= 0))} {((_col1 >= 1) or (_col4 >= 1))} {((UDFToLong(_col1) + _col4) >= 0)} {((_col3 + _col6) >= 0)} + Conds:RS_19._col0=RS_20._col0(Inner),RS_20._col0=RS_21._col0(Inner),Output:["_col1","_col3","_col4","_col6"],residual filter predicates:{((_col1 >= 1) or (_col4 >= 1))} {((UDFToLong(_col1) + _col4) >= 0)} {((_col3 + _col6) >= 0)} <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_19] PartitionCols:_col0 diff --git a/ql/src/test/results/clientpositive/masking_10.q.out b/ql/src/test/results/clientpositive/masking_10.q.out index e1a398af99..029dce5b0b 100644 --- a/ql/src/test/results/clientpositive/masking_10.q.out +++ b/ql/src/test/results/clientpositive/masking_10.q.out @@ -80,7 +80,7 @@ POSTHOOK: Input: default@masking_test 2017 2_lav 2017 4_lav 2017 8_lav -Warning: Shuffle Join JOIN[34][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from masking_test alias01 @@ -106,13 +106,12 @@ select * from on alias01.key = alias03.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-1 depends on stages: Stage-3 + Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: - Stage: Stage-3 + Stage: Stage-1 Map Reduce Map Operator Tree: TableScan @@ -122,70 +121,36 @@ STAGE PLANS: predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: reverse(value) (type: string) - outputColumnNames: _col0 + expressions: key (type: int), reverse(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) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + sort order: Statistics: Num rows: 83 Data size: 881 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: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 2017 (type: int), _col0 (type: string) - 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: + value expressions: _col0 (type: int), _col1 (type: string) TableScan alias: masking_test Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: false (type: boolean) + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), reverse(value) (type: string) + expressions: 2017 (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string) - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Left Outer Join 0 to 1 - filter predicates: - 0 {(VALUE._col0 = 2017)} - 1 keys: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3403 Data size: 75629 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 1794 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -201,7 +166,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3403 Data size: 75629 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 1794 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) TableScan alias: masking_test @@ -227,10 +192,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 3743 Data size: 83191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 91 Data size: 1973 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3743 Data size: 83191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 91 Data size: 1973 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/perf/spark/query11.q.out b/ql/src/test/results/clientpositive/perf/spark/query11.q.out index 17b2309379..f8739ad405 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query11.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query11.q.out @@ -157,13 +157,13 @@ STAGE PLANS: Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) Reducer 11 <- Map 14 (PARTITION-LEVEL SORT, 975), Reducer 10 (PARTITION-LEVEL SORT, 975) Reducer 12 <- Reducer 11 (GROUP, 481) - Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 154), Map 19 (PARTITION-LEVEL SORT, 154) - Reducer 17 <- Map 20 (PARTITION-LEVEL SORT, 706), Reducer 16 (PARTITION-LEVEL SORT, 706) - Reducer 18 <- Reducer 17 (GROUP, 186) + Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 398), Map 19 (PARTITION-LEVEL SORT, 398) + Reducer 17 <- Map 20 (PARTITION-LEVEL SORT, 975), Reducer 16 (PARTITION-LEVEL SORT, 975) + Reducer 18 <- Reducer 17 (GROUP, 481) Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 154), Map 7 (PARTITION-LEVEL SORT, 154) - Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 398), Map 25 (PARTITION-LEVEL SORT, 398) - Reducer 23 <- Map 26 (PARTITION-LEVEL SORT, 975), Reducer 22 (PARTITION-LEVEL SORT, 975) - Reducer 24 <- Reducer 23 (GROUP, 481) + Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 154), Map 25 (PARTITION-LEVEL SORT, 154) + Reducer 23 <- Map 26 (PARTITION-LEVEL SORT, 706), Reducer 22 (PARTITION-LEVEL SORT, 706) + Reducer 24 <- Reducer 23 (GROUP, 186) Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 706), Reducer 2 (PARTITION-LEVEL SORT, 706) Reducer 4 <- Reducer 3 (GROUP, 186) Reducer 5 <- Reducer 12 (PARTITION-LEVEL SORT, 444), Reducer 18 (PARTITION-LEVEL SORT, 444), Reducer 24 (PARTITION-LEVEL SORT, 444), Reducer 4 (PARTITION-LEVEL SORT, 444) @@ -226,20 +226,20 @@ STAGE PLANS: Map 15 Map Operator Tree: TableScan - alias: web_sales - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) + expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_discount_amt (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 50814502088 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: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) Map 19 Map Operator Tree: @@ -247,7 +247,7 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int) @@ -279,20 +279,20 @@ STAGE PLANS: Map 21 Map Operator Tree: TableScan - alias: store_sales - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: web_sales + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_discount_amt (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)) + expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 19580198212 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: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) Map 25 Map Operator Tree: @@ -300,7 +300,7 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int) @@ -458,12 +458,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) Reducer 17 Reduce Operator Tree: @@ -474,22 +474,22 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), (_col3 - _col2) (type: decimal(8,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(18,2)) Reducer 18 Reduce Operator Tree: @@ -498,20 +498,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col7 (type: decimal(18,2)) - outputColumnNames: _col0, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col7 > 0) (type: boolean) - Statistics: Num rows: 29040539 Data size: 3948673454 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: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: decimal(18,2)) + expressions: _col0 (type: string), _col3 (type: string), _col7 (type: decimal(18,2)) + outputColumnNames: _col0, _col3, _col7 + Statistics: Num rows: 348477374 Data size: 30742775095 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: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: string), _col7 (type: decimal(18,2)) Reducer 2 Reduce Operator Tree: Join Operator @@ -537,12 +534,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) Reducer 23 Reduce Operator Tree: @@ -553,22 +550,22 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), (_col3 - _col2) (type: decimal(8,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(18,2)) Reducer 24 Reduce Operator Tree: @@ -577,17 +574,20 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string), _col7 (type: decimal(18,2)) - outputColumnNames: _col0, _col3, _col7 - Statistics: Num rows: 348477374 Data size: 30742775095 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: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: string), _col7 (type: decimal(18,2)) + expressions: _col0 (type: string), _col7 (type: decimal(18,2)) + outputColumnNames: _col0, _col7 + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col7 > 0) (type: boolean) + Statistics: Num rows: 29040539 Data size: 3948673454 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: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + value expressions: _col7 (type: decimal(18,2)) Reducer 3 Reduce Operator Tree: Join Operator @@ -644,26 +644,26 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) 3 _col0 (type: string) - outputColumnNames: _col7, _col14, _col22, _col26, _col30 + outputColumnNames: _col7, _col14, _col18, _col22, _col30 Statistics: Num rows: 1149975359 Data size: 101451160012 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: CASE WHEN ((_col14 > 0)) THEN (CASE WHEN ((_col22 > 0)) THEN (((_col7 / _col22) > (_col30 / _col14))) ELSE ((null > (_col30 / _col14))) END) ELSE (CASE WHEN ((_col22 > 0)) THEN (((_col7 / _col22) > null)) ELSE (null) END) END (type: boolean) - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + predicate: ((_col7 / _col30) > (_col22 / _col14)) (type: boolean) + Statistics: Num rows: 383325119 Data size: 33817053278 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col26 (type: string) + expressions: _col18 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 383325119 Data size: 33817053278 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 383325119 Data size: 33817053278 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Reducer 6 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 383325119 Data size: 33817053278 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/perf/spark/query4.q.out b/ql/src/test/results/clientpositive/perf/spark/query4.q.out index 71154ff8a7..5933d0e815 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query4.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query4.q.out @@ -225,21 +225,21 @@ STAGE PLANS: Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) Reducer 11 <- Map 14 (PARTITION-LEVEL SORT, 975), Reducer 10 (PARTITION-LEVEL SORT, 975) Reducer 12 <- Reducer 11 (GROUP, 481) - Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 306), Map 19 (PARTITION-LEVEL SORT, 306) - Reducer 17 <- Map 20 (PARTITION-LEVEL SORT, 873), Reducer 16 (PARTITION-LEVEL SORT, 873) - Reducer 18 <- Reducer 17 (GROUP, 369) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 154), Map 7 (PARTITION-LEVEL SORT, 154) - Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 154), Map 25 (PARTITION-LEVEL SORT, 154) - Reducer 23 <- Map 26 (PARTITION-LEVEL SORT, 706), Reducer 22 (PARTITION-LEVEL SORT, 706) - Reducer 24 <- Reducer 23 (GROUP, 186) - Reducer 28 <- Map 27 (PARTITION-LEVEL SORT, 306), Map 31 (PARTITION-LEVEL SORT, 306) - Reducer 29 <- Map 32 (PARTITION-LEVEL SORT, 873), Reducer 28 (PARTITION-LEVEL SORT, 873) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 706), Reducer 2 (PARTITION-LEVEL SORT, 706) - Reducer 30 <- Reducer 29 (GROUP, 369) - Reducer 34 <- Map 33 (PARTITION-LEVEL SORT, 398), Map 37 (PARTITION-LEVEL SORT, 398) - Reducer 35 <- Map 38 (PARTITION-LEVEL SORT, 975), Reducer 34 (PARTITION-LEVEL SORT, 975) - Reducer 36 <- Reducer 35 (GROUP, 481) - Reducer 4 <- Reducer 3 (GROUP, 186) + Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 398), Map 19 (PARTITION-LEVEL SORT, 398) + Reducer 17 <- Map 20 (PARTITION-LEVEL SORT, 975), Reducer 16 (PARTITION-LEVEL SORT, 975) + Reducer 18 <- Reducer 17 (GROUP, 481) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 306), Map 7 (PARTITION-LEVEL SORT, 306) + Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 306), Map 25 (PARTITION-LEVEL SORT, 306) + Reducer 23 <- Map 26 (PARTITION-LEVEL SORT, 873), Reducer 22 (PARTITION-LEVEL SORT, 873) + Reducer 24 <- Reducer 23 (GROUP, 369) + Reducer 28 <- Map 27 (PARTITION-LEVEL SORT, 154), Map 31 (PARTITION-LEVEL SORT, 154) + Reducer 29 <- Map 32 (PARTITION-LEVEL SORT, 706), Reducer 28 (PARTITION-LEVEL SORT, 706) + Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 873), Reducer 2 (PARTITION-LEVEL SORT, 873) + Reducer 30 <- Reducer 29 (GROUP, 186) + Reducer 34 <- Map 33 (PARTITION-LEVEL SORT, 154), Map 37 (PARTITION-LEVEL SORT, 154) + Reducer 35 <- Map 38 (PARTITION-LEVEL SORT, 706), Reducer 34 (PARTITION-LEVEL SORT, 706) + Reducer 36 <- Reducer 35 (GROUP, 186) + Reducer 4 <- Reducer 3 (GROUP, 369) Reducer 5 <- Reducer 12 (PARTITION-LEVEL SORT, 690), Reducer 18 (PARTITION-LEVEL SORT, 690), Reducer 24 (PARTITION-LEVEL SORT, 690), Reducer 30 (PARTITION-LEVEL SORT, 690), Reducer 36 (PARTITION-LEVEL SORT, 690), Reducer 4 (PARTITION-LEVEL SORT, 690) Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### @@ -247,20 +247,20 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: web_sales - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: catalog_sales + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_sales_price (type: decimal(7,2)), ws_ext_wholesale_cost (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) + expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_ext_discount_amt (type: decimal(7,2)), cs_ext_sales_price (type: decimal(7,2)), cs_ext_wholesale_cost (type: decimal(7,2)), cs_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 38999608952 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: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Map 13 Map Operator Tree: @@ -300,20 +300,20 @@ STAGE PLANS: Map 15 Map Operator Tree: TableScan - alias: catalog_sales - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_ext_discount_amt (type: decimal(7,2)), cs_ext_sales_price (type: decimal(7,2)), cs_ext_wholesale_cost (type: decimal(7,2)), cs_ext_list_price (type: decimal(7,2)) + expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_discount_amt (type: decimal(7,2)), ss_ext_sales_price (type: decimal(7,2)), ss_ext_wholesale_cost (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 50814502088 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: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Map 19 Map Operator Tree: @@ -321,7 +321,7 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int) @@ -353,20 +353,20 @@ STAGE PLANS: Map 21 Map Operator Tree: TableScan - alias: web_sales - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: catalog_sales + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_sales_price (type: decimal(7,2)), ws_ext_wholesale_cost (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) + expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_ext_discount_amt (type: decimal(7,2)), cs_ext_sales_price (type: decimal(7,2)), cs_ext_wholesale_cost (type: decimal(7,2)), cs_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 38999608952 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: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Map 25 Map Operator Tree: @@ -406,20 +406,20 @@ STAGE PLANS: Map 27 Map Operator Tree: TableScan - alias: catalog_sales - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + alias: web_sales + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_ext_discount_amt (type: decimal(7,2)), cs_ext_sales_price (type: decimal(7,2)), cs_ext_wholesale_cost (type: decimal(7,2)), cs_ext_list_price (type: decimal(7,2)) + expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_sales_price (type: decimal(7,2)), ws_ext_wholesale_cost (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 19580198212 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: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Map 31 Map Operator Tree: @@ -459,20 +459,20 @@ STAGE PLANS: Map 33 Map Operator Tree: TableScan - alias: store_sales - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: web_sales + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_discount_amt (type: decimal(7,2)), ss_ext_sales_price (type: decimal(7,2)), ss_ext_wholesale_cost (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)) + expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_sales_price (type: decimal(7,2)), ws_ext_wholesale_cost (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 19580198212 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: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Map 37 Map Operator Tree: @@ -480,7 +480,7 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int) @@ -634,12 +634,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Reducer 17 Reduce Operator Tree: @@ -650,22 +650,22 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(24,6)) Reducer 18 Reduce Operator Tree: @@ -674,20 +674,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col7 (type: decimal(24,6)) - outputColumnNames: _col0, _col7 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col7 > 0) (type: boolean) - Statistics: Num rows: 58077952 Data size: 7864921389 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: 58077952 Data size: 7864921389 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: decimal(24,6)) + expressions: _col0 (type: string), _col3 (type: string), _col7 (type: decimal(24,6)) + outputColumnNames: _col0, _col3, _col7 + Statistics: Num rows: 348477374 Data size: 30742775095 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: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: string), _col7 (type: decimal(24,6)) Reducer 2 Reduce Operator Tree: Join Operator @@ -697,12 +694,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Reducer 22 Reduce Operator Tree: @@ -713,12 +710,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Reducer 23 Reduce Operator Tree: @@ -729,22 +726,22 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(24,6)) Reducer 24 Reduce Operator Tree: @@ -753,19 +750,19 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) outputColumnNames: _col0, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col7 > 0) (type: boolean) - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58077952 Data size: 7864921389 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: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58077952 Data size: 7864921389 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(24,6)) Reducer 28 Reduce Operator Tree: @@ -776,12 +773,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Reducer 29 Reduce Operator Tree: @@ -792,22 +789,22 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(24,6)) Reducer 3 Reduce Operator Tree: @@ -818,22 +815,22 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(24,6)) Reducer 30 Reduce Operator Tree: @@ -842,16 +839,16 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) outputColumnNames: _col0, _col7 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87121617 Data size: 11846020363 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: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(24,6)) Reducer 34 Reduce Operator Tree: @@ -862,12 +859,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Reducer 35 Reduce Operator Tree: @@ -878,22 +875,22 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(24,6)) Reducer 36 Reduce Operator Tree: @@ -902,17 +899,20 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string), _col7 (type: decimal(24,6)) - outputColumnNames: _col0, _col3, _col7 - Statistics: Num rows: 348477374 Data size: 30742775095 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: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: string), _col7 (type: decimal(24,6)) + expressions: _col0 (type: string), _col7 (type: decimal(24,6)) + outputColumnNames: _col0, _col7 + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col7 > 0) (type: boolean) + Statistics: Num rows: 29040539 Data size: 3948673454 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: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + value expressions: _col7 (type: decimal(24,6)) Reducer 4 Reduce Operator Tree: Group By Operator @@ -920,16 +920,16 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) outputColumnNames: _col0, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174233858 Data size: 23594764438 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: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(24,6)) Reducer 5 Reduce Operator Tree: @@ -947,26 +947,26 @@ STAGE PLANS: 3 _col0 (type: string) 4 _col0 (type: string) 5 _col0 (type: string) - outputColumnNames: _col7, _col15, _col23, _col31, _col39, _col43, _col47 + outputColumnNames: _col7, _col15, _col19, _col23, _col31, _col39, _col47 Statistics: Num rows: 1916625598 Data size: 169085266687 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (CASE WHEN ((_col15 > 0)) THEN (CASE WHEN ((_col23 > 0)) THEN (((_col39 / _col23) > (_col47 / _col15))) ELSE ((null > (_col47 / _col15))) END) ELSE (CASE WHEN ((_col23 > 0)) THEN (((_col39 / _col23) > null)) ELSE (null) END) END and CASE WHEN ((_col31 > 0)) THEN (CASE WHEN ((_col23 > 0)) THEN (((_col39 / _col23) > (_col7 / _col31))) ELSE ((null > (_col7 / _col31))) END) ELSE (CASE WHEN ((_col23 > 0)) THEN (((_col39 / _col23) > null)) ELSE (null) END) END) (type: boolean) - Statistics: Num rows: 479156399 Data size: 42271316627 Basic stats: COMPLETE Column stats: NONE + predicate: (((_col7 / _col31) > (_col23 / _col15)) and ((_col7 / _col31) > (_col39 / _col47))) (type: boolean) + Statistics: Num rows: 212958399 Data size: 18787251785 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col43 (type: string) + expressions: _col19 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 479156399 Data size: 42271316627 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 212958399 Data size: 18787251785 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 479156399 Data size: 42271316627 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 212958399 Data size: 18787251785 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Reducer 6 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 479156399 Data size: 42271316627 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 212958399 Data size: 18787251785 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/perf/spark/query74.q.out b/ql/src/test/results/clientpositive/perf/spark/query74.q.out index 497e792bc2..24cb881036 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query74.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query74.q.out @@ -129,13 +129,13 @@ STAGE PLANS: Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) Reducer 11 <- Map 14 (PARTITION-LEVEL SORT, 975), Reducer 10 (PARTITION-LEVEL SORT, 975) Reducer 12 <- Reducer 11 (GROUP, 481) - Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 154), Map 19 (PARTITION-LEVEL SORT, 154) - Reducer 17 <- Map 20 (PARTITION-LEVEL SORT, 706), Reducer 16 (PARTITION-LEVEL SORT, 706) - Reducer 18 <- Reducer 17 (GROUP, 186) + Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 398), Map 19 (PARTITION-LEVEL SORT, 398) + Reducer 17 <- Map 20 (PARTITION-LEVEL SORT, 975), Reducer 16 (PARTITION-LEVEL SORT, 975) + Reducer 18 <- Reducer 17 (GROUP, 481) Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 154), Map 7 (PARTITION-LEVEL SORT, 154) - Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 398), Map 25 (PARTITION-LEVEL SORT, 398) - Reducer 23 <- Map 26 (PARTITION-LEVEL SORT, 975), Reducer 22 (PARTITION-LEVEL SORT, 975) - Reducer 24 <- Reducer 23 (GROUP, 481) + Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 154), Map 25 (PARTITION-LEVEL SORT, 154) + Reducer 23 <- Map 26 (PARTITION-LEVEL SORT, 706), Reducer 22 (PARTITION-LEVEL SORT, 706) + Reducer 24 <- Reducer 23 (GROUP, 186) Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 706), Reducer 2 (PARTITION-LEVEL SORT, 706) Reducer 4 <- Reducer 3 (GROUP, 186) Reducer 5 <- Reducer 12 (PARTITION-LEVEL SORT, 444), Reducer 18 (PARTITION-LEVEL SORT, 444), Reducer 24 (PARTITION-LEVEL SORT, 444), Reducer 4 (PARTITION-LEVEL SORT, 444) @@ -199,20 +199,20 @@ STAGE PLANS: Map 15 Map Operator Tree: TableScan - alias: web_sales - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_net_paid (type: decimal(7,2)) + expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_net_paid (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 50814502088 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: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) Map 19 Map Operator Tree: @@ -220,10 +220,10 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) (type: boolean) + predicate: ((d_year = 2002) and (d_year) IN (2001, 2002) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: d_date_sk (type: int), 2001 (type: int) + expressions: d_date_sk (type: int), 2002 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -253,20 +253,20 @@ STAGE PLANS: Map 21 Map Operator Tree: TableScan - alias: store_sales - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: web_sales + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_net_paid (type: decimal(7,2)) + expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_net_paid (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 19580198212 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: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) Map 25 Map Operator Tree: @@ -310,10 +310,10 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d_year = 2002) and (d_year) IN (2001, 2002) and d_date_sk is not null) (type: boolean) + predicate: ((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: d_date_sk (type: int), 2002 (type: int) + expressions: d_date_sk (type: int), 2001 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -426,12 +426,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) Reducer 17 Reduce Operator Tree: @@ -442,18 +442,18 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col4, _col6, _col7, _col8 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col2) keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col4 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE value expressions: _col4 (type: decimal(7,2)) Reducer 18 Reduce Operator Tree: @@ -462,20 +462,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col4 (type: decimal(7,2)) - outputColumnNames: _col0, _col4 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col4 > 0) (type: boolean) - Statistics: Num rows: 29040539 Data size: 3948673454 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: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(7,2)) + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col4 + Statistics: Num rows: 348477374 Data size: 30742775095 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: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col4 (type: decimal(7,2)) Reducer 2 Reduce Operator Tree: Join Operator @@ -501,12 +498,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) Reducer 23 Reduce Operator Tree: @@ -517,18 +514,18 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col4, _col6, _col7, _col8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col2) keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col4 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE value expressions: _col4 (type: decimal(7,2)) Reducer 24 Reduce Operator Tree: @@ -537,17 +534,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + expressions: _col0 (type: string), _col4 (type: decimal(7,2)) + outputColumnNames: _col0, _col4 + Statistics: Num rows: 87121617 Data size: 11846020363 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: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col4 (type: decimal(7,2)) + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + value expressions: _col4 (type: decimal(7,2)) Reducer 3 Reduce Operator Tree: Join Operator @@ -582,12 +579,15 @@ STAGE PLANS: expressions: _col0 (type: string), _col4 (type: decimal(7,2)) outputColumnNames: _col0, _col4 Statistics: Num rows: 87121617 Data size: 11846020363 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: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(7,2)) + Filter Operator + predicate: (_col4 > 0) (type: boolean) + Statistics: Num rows: 29040539 Data size: 3948673454 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: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + value expressions: _col4 (type: decimal(7,2)) Reducer 5 Reduce Operator Tree: Join Operator @@ -600,26 +600,26 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) 3 _col0 (type: string) - outputColumnNames: _col4, _col9, _col14, _col15, _col16, _col17, _col19 + outputColumnNames: _col4, _col9, _col10, _col11, _col12, _col14, _col19 Statistics: Num rows: 1149975359 Data size: 101451160012 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: CASE WHEN ((_col9 > 0)) THEN (CASE WHEN ((_col14 > 0)) THEN (((_col4 / _col14) > (_col19 / _col9))) ELSE ((null > (_col19 / _col9))) END) ELSE (CASE WHEN ((_col14 > 0)) THEN (((_col4 / _col14) > null)) ELSE (null) END) END (type: boolean) - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + predicate: ((_col19 / _col4) > (_col14 / _col9)) (type: boolean) + Statistics: Num rows: 383325119 Data size: 33817053278 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col15 (type: string), _col16 (type: string), _col17 (type: string) + expressions: _col10 (type: string), _col11 (type: string), _col12 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 383325119 Data size: 33817053278 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) sort order: +++ - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 383325119 Data size: 33817053278 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Reducer 6 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 383325119 Data size: 33817053278 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/perf/tez/query11.q.out b/ql/src/test/results/clientpositive/perf/tez/query11.q.out index 69ced2611c..1dd63be54c 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query11.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query11.q.out @@ -172,63 +172,63 @@ Stage-0 File Output Operator [FS_96] Limit [LIM_95] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_94] (rows=574987679 width=88) + Select Operator [SEL_94] (rows=383325119 width=88) Output:["_col0"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_93] - Select Operator [SEL_92] (rows=574987679 width=88) + Select Operator [SEL_92] (rows=383325119 width=88) Output:["_col0"] - Filter Operator [FIL_91] (rows=574987679 width=88) - predicate:CASE WHEN ((_col14 > 0)) THEN (CASE WHEN ((_col22 > 0)) THEN (((_col7 / _col22) > (_col30 / _col14))) ELSE ((null > (_col30 / _col14))) END) ELSE (CASE WHEN ((_col22 > 0)) THEN (((_col7 / _col22) > null)) ELSE (null) END) END + Filter Operator [FIL_91] (rows=383325119 width=88) + predicate:((_col7 / _col30) > (_col22 / _col14)) Merge Join Operator [MERGEJOIN_175] (rows=1149975359 width=88) - Conds:RS_86._col0=RS_87._col0(Inner),RS_87._col0=RS_88._col0(Inner),RS_87._col0=RS_89._col0(Inner),Output:["_col7","_col14","_col22","_col26","_col30"] + Conds:RS_86._col0=RS_87._col0(Inner),RS_87._col0=RS_88._col0(Inner),RS_87._col0=RS_89._col0(Inner),Output:["_col7","_col14","_col18","_col22","_col30"] <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_89] + SHUFFLE [RS_88] PartitionCols:_col0 - Select Operator [SEL_85] (rows=348477374 width=88) + Select Operator [SEL_63] (rows=348477374 width=88) Output:["_col0","_col3","_col7"] - Group By Operator [GBY_84] (rows=348477374 width=88) + Group By Operator [GBY_62] (rows=348477374 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_83] + SHUFFLE [RS_61] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_82] (rows=696954748 width=88) + Group By Operator [GBY_60] (rows=696954748 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_80] (rows=696954748 width=88) + Select Operator [SEL_58] (rows=696954748 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_174] (rows=696954748 width=88) - Conds:RS_77._col1=RS_78._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + Merge Join Operator [MERGEJOIN_172] (rows=696954748 width=88) + Conds:RS_55._col1=RS_56._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Map 18 [SIMPLE_EDGE] - SHUFFLE [RS_78] + SHUFFLE [RS_56] PartitionCols:_col0 - Select Operator [SEL_73] (rows=80000000 width=860) + Select Operator [SEL_51] (rows=80000000 width=860) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_164] (rows=80000000 width=860) + Filter Operator [FIL_161] (rows=80000000 width=860) predicate:(c_customer_id is not null and c_customer_sk is not null) - TableScan [TS_71] (rows=80000000 width=860) + TableScan [TS_49] (rows=80000000 width=860) default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_country","c_login","c_email_address"] <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_77] + SHUFFLE [RS_55] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_173] (rows=633595212 width=88) - Conds:RS_74._col0=RS_75._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_171] (rows=633595212 width=88) + Conds:RS_52._col0=RS_53._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 17 [SIMPLE_EDGE] - SHUFFLE [RS_75] + SHUFFLE [RS_53] PartitionCols:_col0 - Select Operator [SEL_70] (rows=36524 width=1119) + Select Operator [SEL_48] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_163] (rows=36524 width=1119) + Filter Operator [FIL_160] (rows=36524 width=1119) predicate:((d_year = 2002) and d_date_sk is not null) - TableScan [TS_68] (rows=73049 width=1119) + TableScan [TS_46] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] <-Map 10 [SIMPLE_EDGE] - SHUFFLE [RS_74] + SHUFFLE [RS_52] PartitionCols:_col0 - Select Operator [SEL_67] (rows=575995635 width=88) + Select Operator [SEL_45] (rows=575995635 width=88) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_162] (rows=575995635 width=88) + Filter Operator [FIL_159] (rows=575995635 width=88) predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_65] (rows=575995635 width=88) + TableScan [TS_43] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"] <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_87] @@ -253,7 +253,7 @@ Stage-0 <-Map 18 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_73] + Please refer to the previous Select Operator [SEL_51] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_33] PartitionCols:_col1 @@ -266,11 +266,11 @@ Stage-0 Output:["_col0"] Filter Operator [FIL_157] (rows=36524 width=1119) predicate:((d_year = 2001) and d_date_sk is not null) - Please refer to the previous TableScan [TS_68] + Please refer to the previous TableScan [TS_46] <-Map 10 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_67] + Please refer to the previous Select Operator [SEL_45] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_86] PartitionCols:_col0 @@ -290,7 +290,7 @@ Stage-0 <-Map 18 [SIMPLE_EDGE] SHUFFLE [RS_13] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_73] + Please refer to the previous Select Operator [SEL_51] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 @@ -299,7 +299,7 @@ Stage-0 <-Map 17 [SIMPLE_EDGE] SHUFFLE [RS_10] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_70] + Please refer to the previous Select Operator [SEL_48] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_9] PartitionCols:_col0 @@ -310,42 +310,42 @@ Stage-0 TableScan [TS_0] (rows=144002668 width=135) default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"] <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_88] + SHUFFLE [RS_89] PartitionCols:_col0 - Filter Operator [FIL_63] (rows=29040539 width=135) + Filter Operator [FIL_84] (rows=29040539 width=135) predicate:(_col7 > 0) Select Operator [SEL_165] (rows=87121617 width=135) Output:["_col0","_col7"] - Group By Operator [GBY_62] (rows=87121617 width=135) + Group By Operator [GBY_83] (rows=87121617 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_61] + SHUFFLE [RS_82] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_60] (rows=174243235 width=135) + Group By Operator [GBY_81] (rows=174243235 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_58] (rows=174243235 width=135) + Select Operator [SEL_79] (rows=174243235 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_172] (rows=174243235 width=135) - Conds:RS_55._col1=RS_56._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + Merge Join Operator [MERGEJOIN_174] (rows=174243235 width=135) + Conds:RS_76._col1=RS_77._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Map 18 [SIMPLE_EDGE] - SHUFFLE [RS_56] + SHUFFLE [RS_77] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_73] + Please refer to the previous Select Operator [SEL_51] <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_55] + SHUFFLE [RS_76] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_171] (rows=158402938 width=135) - Conds:RS_52._col0=RS_53._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_173] (rows=158402938 width=135) + Conds:RS_73._col0=RS_74._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 17 [SIMPLE_EDGE] - SHUFFLE [RS_53] + SHUFFLE [RS_74] PartitionCols:_col0 - Select Operator [SEL_48] (rows=36524 width=1119) + Select Operator [SEL_69] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_160] (rows=36524 width=1119) + Filter Operator [FIL_163] (rows=36524 width=1119) predicate:((d_year = 2001) and d_date_sk is not null) - Please refer to the previous TableScan [TS_68] + Please refer to the previous TableScan [TS_46] <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_52] + SHUFFLE [RS_73] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_2] diff --git a/ql/src/test/results/clientpositive/perf/tez/query4.q.out b/ql/src/test/results/clientpositive/perf/tez/query4.q.out index 81867b9675..c56fae06bf 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query4.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query4.q.out @@ -246,255 +246,255 @@ Stage-0 File Output Operator [FS_142] Limit [LIM_141] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_140] (rows=479156399 width=88) + Select Operator [SEL_140] (rows=212958399 width=88) Output:["_col0"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_139] - Select Operator [SEL_138] (rows=479156399 width=88) + Select Operator [SEL_138] (rows=212958399 width=88) Output:["_col0"] - Filter Operator [FIL_136] (rows=479156399 width=88) - predicate:(CASE WHEN ((_col15 > 0)) THEN (CASE WHEN ((_col23 > 0)) THEN (((_col39 / _col23) > (_col47 / _col15))) ELSE ((null > (_col47 / _col15))) END) ELSE (CASE WHEN ((_col23 > 0)) THEN (((_col39 / _col23) > null)) ELSE (null) END) END and CASE WHEN ((_col31 > 0)) THEN (CASE WHEN ((_col23 > 0)) THEN (((_col39 / _col23) > (_col7 / _col31))) ELSE ((null > (_col7 / _col31))) END) ELSE (CASE WHEN ((_col23 > 0)) THEN (((_col39 / _col23) > null)) ELSE (null) END) END) + Filter Operator [FIL_136] (rows=212958399 width=88) + predicate:(((_col7 / _col31) > (_col23 / _col15)) and ((_col7 / _col31) > (_col39 / _col47))) Merge Join Operator [MERGEJOIN_296] (rows=1916625598 width=88) - Conds:RS_129._col0=RS_130._col0(Inner),RS_130._col0=RS_131._col0(Inner),RS_130._col0=RS_132._col0(Inner),RS_130._col0=RS_133._col0(Inner),RS_130._col0=RS_134._col0(Inner),Output:["_col7","_col15","_col23","_col31","_col39","_col43","_col47"] + Conds:RS_129._col0=RS_130._col0(Inner),RS_130._col0=RS_131._col0(Inner),RS_130._col0=RS_132._col0(Inner),RS_130._col0=RS_133._col0(Inner),RS_130._col0=RS_134._col0(Inner),Output:["_col7","_col15","_col19","_col23","_col31","_col39","_col47"] <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_133] + SHUFFLE [RS_131] PartitionCols:_col0 - Select Operator [SEL_107] (rows=174233858 width=135) - Output:["_col0","_col7"] - Group By Operator [GBY_106] (rows=174233858 width=135) + Select Operator [SEL_63] (rows=348477374 width=88) + Output:["_col0","_col3","_col7"] + Group By Operator [GBY_62] (rows=348477374 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_105] + SHUFFLE [RS_61] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_104] (rows=348467716 width=135) + Group By Operator [GBY_60] (rows=696954748 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_102] (rows=348467716 width=135) + Select Operator [SEL_58] (rows=696954748 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_293] (rows=348467716 width=135) - Conds:RS_99._col1=RS_100._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + Merge Join Operator [MERGEJOIN_289] (rows=696954748 width=88) + Conds:RS_55._col1=RS_56._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Map 25 [SIMPLE_EDGE] - SHUFFLE [RS_100] + SHUFFLE [RS_56] PartitionCols:_col0 - Select Operator [SEL_116] (rows=80000000 width=860) + Select Operator [SEL_94] (rows=80000000 width=860) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_280] (rows=80000000 width=860) + Filter Operator [FIL_277] (rows=80000000 width=860) predicate:(c_customer_id is not null and c_customer_sk is not null) - TableScan [TS_114] (rows=80000000 width=860) + TableScan [TS_92] (rows=80000000 width=860) default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_country","c_login","c_email_address"] <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_99] + SHUFFLE [RS_55] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_292] (rows=316788826 width=135) - Conds:RS_96._col0=RS_97._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_288] (rows=633595212 width=88) + Conds:RS_52._col0=RS_53._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 24 [SIMPLE_EDGE] - SHUFFLE [RS_97] + SHUFFLE [RS_53] PartitionCols:_col0 - Select Operator [SEL_113] (rows=36524 width=1119) + Select Operator [SEL_91] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_279] (rows=36524 width=1119) + Filter Operator [FIL_276] (rows=36524 width=1119) predicate:((d_year = 2002) and d_date_sk is not null) - TableScan [TS_111] (rows=73049 width=1119) + TableScan [TS_89] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] <-Map 10 [SIMPLE_EDGE] - SHUFFLE [RS_96] + SHUFFLE [RS_52] PartitionCols:_col0 - Select Operator [SEL_89] (rows=287989836 width=135) + Select Operator [SEL_45] (rows=575995635 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_275] (rows=287989836 width=135) - predicate:(cs_bill_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_87] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_ext_discount_amt","cs_ext_sales_price","cs_ext_wholesale_cost","cs_ext_list_price"] + Filter Operator [FIL_269] (rows=575995635 width=88) + predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_43] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_sales_price","ss_ext_wholesale_cost","ss_ext_list_price"] <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_131] + SHUFFLE [RS_130] PartitionCols:_col0 - Filter Operator [FIL_63] (rows=58077952 width=135) + Filter Operator [FIL_41] (rows=116159124 width=88) predicate:(_col7 > 0) - Select Operator [SEL_281] (rows=174233858 width=135) + Select Operator [SEL_283] (rows=348477374 width=88) Output:["_col0","_col7"] - Group By Operator [GBY_62] (rows=174233858 width=135) + Group By Operator [GBY_40] (rows=348477374 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_61] + SHUFFLE [RS_39] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_60] (rows=348467716 width=135) + Group By Operator [GBY_38] (rows=696954748 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_58] (rows=348467716 width=135) + Select Operator [SEL_36] (rows=696954748 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_289] (rows=348467716 width=135) - Conds:RS_55._col1=RS_56._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + Merge Join Operator [MERGEJOIN_287] (rows=696954748 width=88) + Conds:RS_33._col1=RS_34._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Map 25 [SIMPLE_EDGE] - SHUFFLE [RS_56] + SHUFFLE [RS_34] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_116] + Please refer to the previous Select Operator [SEL_94] <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_55] + SHUFFLE [RS_33] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_288] (rows=316788826 width=135) - Conds:RS_52._col0=RS_53._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_286] (rows=633595212 width=88) + Conds:RS_30._col0=RS_31._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 24 [SIMPLE_EDGE] - SHUFFLE [RS_53] + SHUFFLE [RS_31] PartitionCols:_col0 - Select Operator [SEL_48] (rows=36524 width=1119) + Select Operator [SEL_26] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_270] (rows=36524 width=1119) + Filter Operator [FIL_267] (rows=36524 width=1119) predicate:((d_year = 2001) and d_date_sk is not null) - Please refer to the previous TableScan [TS_111] + Please refer to the previous TableScan [TS_89] <-Map 10 [SIMPLE_EDGE] - SHUFFLE [RS_52] + SHUFFLE [RS_30] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_89] + Please refer to the previous Select Operator [SEL_45] <-Reducer 20 [SIMPLE_EDGE] - SHUFFLE [RS_134] + SHUFFLE [RS_133] PartitionCols:_col0 - Select Operator [SEL_128] (rows=348477374 width=88) - Output:["_col0","_col3","_col7"] - Group By Operator [GBY_127] (rows=348477374 width=88) + Select Operator [SEL_106] (rows=87121617 width=135) + Output:["_col0","_col7"] + Group By Operator [GBY_105] (rows=87121617 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 19 [SIMPLE_EDGE] - SHUFFLE [RS_126] + SHUFFLE [RS_104] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_125] (rows=696954748 width=88) + Group By Operator [GBY_103] (rows=174243235 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_123] (rows=696954748 width=88) + Select Operator [SEL_101] (rows=174243235 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_295] (rows=696954748 width=88) - Conds:RS_120._col1=RS_121._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + Merge Join Operator [MERGEJOIN_293] (rows=174243235 width=135) + Conds:RS_98._col1=RS_99._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Map 25 [SIMPLE_EDGE] - SHUFFLE [RS_121] + SHUFFLE [RS_99] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_116] + Please refer to the previous Select Operator [SEL_94] <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_120] + SHUFFLE [RS_98] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_294] (rows=633595212 width=88) - Conds:RS_117._col0=RS_118._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_292] (rows=158402938 width=135) + Conds:RS_95._col0=RS_96._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 24 [SIMPLE_EDGE] - SHUFFLE [RS_118] + SHUFFLE [RS_96] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_113] + Please refer to the previous Select Operator [SEL_91] <-Map 17 [SIMPLE_EDGE] - SHUFFLE [RS_117] + SHUFFLE [RS_95] PartitionCols:_col0 - Select Operator [SEL_110] (rows=575995635 width=88) + Select Operator [SEL_88] (rows=144002668 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_278] (rows=575995635 width=88) - predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_108] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_sales_price","ss_ext_wholesale_cost","ss_ext_list_price"] + Filter Operator [FIL_275] (rows=144002668 width=135) + predicate:(ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_86] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_sales_price","ws_ext_wholesale_cost","ws_ext_list_price"] <-Reducer 23 [SIMPLE_EDGE] - SHUFFLE [RS_130] + SHUFFLE [RS_134] PartitionCols:_col0 - Filter Operator [FIL_41] (rows=116159124 width=88) + Filter Operator [FIL_127] (rows=29040539 width=135) predicate:(_col7 > 0) - Select Operator [SEL_283] (rows=348477374 width=88) + Select Operator [SEL_282] (rows=87121617 width=135) Output:["_col0","_col7"] - Group By Operator [GBY_40] (rows=348477374 width=88) + Group By Operator [GBY_126] (rows=87121617 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 22 [SIMPLE_EDGE] - SHUFFLE [RS_39] + SHUFFLE [RS_125] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_38] (rows=696954748 width=88) + Group By Operator [GBY_124] (rows=174243235 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_36] (rows=696954748 width=88) + Select Operator [SEL_122] (rows=174243235 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_287] (rows=696954748 width=88) - Conds:RS_33._col1=RS_34._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + Merge Join Operator [MERGEJOIN_295] (rows=174243235 width=135) + Conds:RS_119._col1=RS_120._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Map 25 [SIMPLE_EDGE] - SHUFFLE [RS_34] + SHUFFLE [RS_120] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_116] + Please refer to the previous Select Operator [SEL_94] <-Reducer 21 [SIMPLE_EDGE] - SHUFFLE [RS_33] + SHUFFLE [RS_119] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_286] (rows=633595212 width=88) - Conds:RS_30._col0=RS_31._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_294] (rows=158402938 width=135) + Conds:RS_116._col0=RS_117._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 24 [SIMPLE_EDGE] - SHUFFLE [RS_31] + SHUFFLE [RS_117] PartitionCols:_col0 - Select Operator [SEL_26] (rows=36524 width=1119) + Select Operator [SEL_112] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_267] (rows=36524 width=1119) + Filter Operator [FIL_279] (rows=36524 width=1119) predicate:((d_year = 2001) and d_date_sk is not null) - Please refer to the previous TableScan [TS_111] + Please refer to the previous TableScan [TS_89] <-Map 17 [SIMPLE_EDGE] - SHUFFLE [RS_30] + SHUFFLE [RS_116] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_110] + Please refer to the previous Select Operator [SEL_88] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_129] PartitionCols:_col0 - Select Operator [SEL_20] (rows=87121617 width=135) + Select Operator [SEL_20] (rows=174233858 width=135) Output:["_col0","_col7"] - Group By Operator [GBY_19] (rows=87121617 width=135) + Group By Operator [GBY_19] (rows=174233858 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_17] (rows=174243235 width=135) + Group By Operator [GBY_17] (rows=348467716 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_15] (rows=174243235 width=135) + Select Operator [SEL_15] (rows=348467716 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_285] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_285] (rows=348467716 width=135) Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Map 25 [SIMPLE_EDGE] SHUFFLE [RS_13] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_116] + Please refer to the previous Select Operator [SEL_94] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_284] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_284] (rows=316788826 width=135) Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 24 [SIMPLE_EDGE] SHUFFLE [RS_10] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_113] + Please refer to the previous Select Operator [SEL_91] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_9] PartitionCols:_col0 - Select Operator [SEL_2] (rows=144002668 width=135) + Select Operator [SEL_2] (rows=287989836 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_263] (rows=144002668 width=135) - predicate:(ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_sales_price","ws_ext_wholesale_cost","ws_ext_list_price"] + Filter Operator [FIL_263] (rows=287989836 width=135) + predicate:(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_ext_discount_amt","cs_ext_sales_price","cs_ext_wholesale_cost","cs_ext_list_price"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_132] PartitionCols:_col0 - Filter Operator [FIL_85] (rows=29040539 width=135) + Filter Operator [FIL_84] (rows=58077952 width=135) predicate:(_col7 > 0) - Select Operator [SEL_282] (rows=87121617 width=135) + Select Operator [SEL_281] (rows=174233858 width=135) Output:["_col0","_col7"] - Group By Operator [GBY_84] (rows=87121617 width=135) + Group By Operator [GBY_83] (rows=174233858 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_83] + SHUFFLE [RS_82] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_82] (rows=174243235 width=135) + Group By Operator [GBY_81] (rows=348467716 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_80] (rows=174243235 width=135) + Select Operator [SEL_79] (rows=348467716 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_291] (rows=174243235 width=135) - Conds:RS_77._col1=RS_78._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + Merge Join Operator [MERGEJOIN_291] (rows=348467716 width=135) + Conds:RS_76._col1=RS_77._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Map 25 [SIMPLE_EDGE] - SHUFFLE [RS_78] + SHUFFLE [RS_77] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_116] + Please refer to the previous Select Operator [SEL_94] <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_77] + SHUFFLE [RS_76] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_290] (rows=158402938 width=135) - Conds:RS_74._col0=RS_75._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_290] (rows=316788826 width=135) + Conds:RS_73._col0=RS_74._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 24 [SIMPLE_EDGE] - SHUFFLE [RS_75] + SHUFFLE [RS_74] PartitionCols:_col0 - Select Operator [SEL_70] (rows=36524 width=1119) + Select Operator [SEL_69] (rows=36524 width=1119) Output:["_col0"] Filter Operator [FIL_273] (rows=36524 width=1119) predicate:((d_year = 2001) and d_date_sk is not null) - Please refer to the previous TableScan [TS_111] + Please refer to the previous TableScan [TS_89] <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_74] + SHUFFLE [RS_73] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_2] diff --git a/ql/src/test/results/clientpositive/perf/tez/query74.q.out b/ql/src/test/results/clientpositive/perf/tez/query74.q.out index a75aaa1294..a0f5082cbd 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query74.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query74.q.out @@ -144,29 +144,29 @@ Stage-0 File Output Operator [FS_92] Limit [LIM_91] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_90] (rows=574987679 width=88) + Select Operator [SEL_90] (rows=383325119 width=88) Output:["_col0","_col1","_col2"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_89] - Select Operator [SEL_88] (rows=574987679 width=88) + Select Operator [SEL_88] (rows=383325119 width=88) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_87] (rows=574987679 width=88) - predicate:CASE WHEN ((_col9 > 0)) THEN (CASE WHEN ((_col14 > 0)) THEN (((_col4 / _col14) > (_col19 / _col9))) ELSE ((null > (_col19 / _col9))) END) ELSE (CASE WHEN ((_col14 > 0)) THEN (((_col4 / _col14) > null)) ELSE (null) END) END + Filter Operator [FIL_87] (rows=383325119 width=88) + predicate:((_col19 / _col4) > (_col14 / _col9)) Merge Join Operator [MERGEJOIN_171] (rows=1149975359 width=88) - Conds:RS_82._col0=RS_83._col0(Inner),RS_83._col0=RS_84._col0(Inner),RS_83._col0=RS_85._col0(Inner),Output:["_col4","_col9","_col14","_col15","_col16","_col17","_col19"] + Conds:RS_82._col0=RS_83._col0(Inner),RS_83._col0=RS_84._col0(Inner),RS_83._col0=RS_85._col0(Inner),Output:["_col4","_col9","_col10","_col11","_col12","_col14","_col19"] <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_85] PartitionCols:_col0 - Select Operator [SEL_81] (rows=348477374 width=88) - Output:["_col0","_col1","_col2","_col4"] - Group By Operator [GBY_80] (rows=348477374 width=88) + Select Operator [SEL_81] (rows=87121617 width=135) + Output:["_col0","_col4"] + Group By Operator [GBY_80] (rows=87121617 width=135) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_79] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_78] (rows=696954748 width=88) + Group By Operator [GBY_78] (rows=174243235 width=135) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_170] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_170] (rows=174243235 width=135) Conds:RS_74._col1=RS_75._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] <-Map 18 [SIMPLE_EDGE] SHUFFLE [RS_75] @@ -180,7 +180,7 @@ Stage-0 <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_74] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_169] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_169] (rows=158402938 width=135) Conds:RS_71._col0=RS_72._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 17 [SIMPLE_EDGE] SHUFFLE [RS_72] @@ -194,120 +194,120 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] SHUFFLE [RS_71] PartitionCols:_col0 - Select Operator [SEL_64] (rows=575995635 width=88) + Select Operator [SEL_64] (rows=144002668 width=135) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_158] (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_net_paid"] + Filter Operator [FIL_158] (rows=144002668 width=135) + predicate:(ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_62] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_83] + SHUFFLE [RS_82] PartitionCols:_col0 - Filter Operator [FIL_39] (rows=116159124 width=88) + Filter Operator [FIL_19] (rows=29040539 width=135) predicate:(_col4 > 0) - Select Operator [SEL_162] (rows=348477374 width=88) + Select Operator [SEL_161] (rows=87121617 width=135) Output:["_col0","_col4"] - Group By Operator [GBY_38] (rows=348477374 width=88) + Group By Operator [GBY_18] (rows=87121617 width=135) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_37] + SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_36] (rows=696954748 width=88) + Group By Operator [GBY_16] (rows=174243235 width=135) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_166] (rows=696954748 width=88) - Conds:RS_32._col1=RS_33._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_164] (rows=174243235 width=135) + Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] <-Map 18 [SIMPLE_EDGE] - SHUFFLE [RS_33] + SHUFFLE [RS_13] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_70] <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_32] + SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_165] (rows=633595212 width=88) - Conds:RS_29._col0=RS_30._col0(Inner),Output:["_col1","_col2","_col4"] + Merge Join Operator [MERGEJOIN_163] (rows=158402938 width=135) + Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 17 [SIMPLE_EDGE] - SHUFFLE [RS_30] + SHUFFLE [RS_10] PartitionCols:_col0 - Select Operator [SEL_25] (rows=18262 width=1119) + Select Operator [SEL_5] (rows=18262 width=1119) Output:["_col0","_col1"] - Filter Operator [FIL_153] (rows=18262 width=1119) + Filter Operator [FIL_150] (rows=18262 width=1119) predicate:((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_65] <-Map 10 [SIMPLE_EDGE] - SHUFFLE [RS_29] + SHUFFLE [RS_9] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_64] <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_82] + SHUFFLE [RS_84] PartitionCols:_col0 - Select Operator [SEL_19] (rows=87121617 width=135) - Output:["_col0","_col4"] - Group By Operator [GBY_18] (rows=87121617 width=135) + Select Operator [SEL_61] (rows=348477374 width=88) + Output:["_col0","_col1","_col2","_col4"] + Group By Operator [GBY_60] (rows=348477374 width=88) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_17] + SHUFFLE [RS_59] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_16] (rows=174243235 width=135) + Group By Operator [GBY_58] (rows=696954748 width=88) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_164] (rows=174243235 width=135) - Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_168] (rows=696954748 width=88) + Conds:RS_54._col1=RS_55._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] <-Map 18 [SIMPLE_EDGE] - SHUFFLE [RS_13] + SHUFFLE [RS_55] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_70] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_12] + SHUFFLE [RS_54] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_163] (rows=158402938 width=135) - Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col1","_col2","_col4"] + Merge Join Operator [MERGEJOIN_167] (rows=633595212 width=88) + Conds:RS_51._col0=RS_52._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 17 [SIMPLE_EDGE] - SHUFFLE [RS_10] + SHUFFLE [RS_52] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_67] <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_9] + SHUFFLE [RS_51] PartitionCols:_col0 - Select Operator [SEL_2] (rows=144002668 width=135) + Select Operator [SEL_44] (rows=575995635 width=88) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_149] (rows=144002668 width=135) - predicate:(ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] + Filter Operator [FIL_155] (rows=575995635 width=88) + predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_42] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_net_paid"] <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_84] + SHUFFLE [RS_83] PartitionCols:_col0 - Filter Operator [FIL_60] (rows=29040539 width=135) + Filter Operator [FIL_40] (rows=116159124 width=88) predicate:(_col4 > 0) - Select Operator [SEL_161] (rows=87121617 width=135) + Select Operator [SEL_162] (rows=348477374 width=88) Output:["_col0","_col4"] - Group By Operator [GBY_59] (rows=87121617 width=135) + Group By Operator [GBY_39] (rows=348477374 width=88) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_58] + SHUFFLE [RS_38] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_57] (rows=174243235 width=135) + Group By Operator [GBY_37] (rows=696954748 width=88) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_168] (rows=174243235 width=135) - Conds:RS_53._col1=RS_54._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_166] (rows=696954748 width=88) + Conds:RS_33._col1=RS_34._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] <-Map 18 [SIMPLE_EDGE] - SHUFFLE [RS_54] + SHUFFLE [RS_34] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_70] <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_53] + SHUFFLE [RS_33] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_167] (rows=158402938 width=135) - Conds:RS_50._col0=RS_51._col0(Inner),Output:["_col1","_col2","_col4"] + Merge Join Operator [MERGEJOIN_165] (rows=633595212 width=88) + Conds:RS_30._col0=RS_31._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 17 [SIMPLE_EDGE] - SHUFFLE [RS_51] + SHUFFLE [RS_31] PartitionCols:_col0 - Select Operator [SEL_46] (rows=18262 width=1119) + Select Operator [SEL_26] (rows=18262 width=1119) Output:["_col0","_col1"] - Filter Operator [FIL_156] (rows=18262 width=1119) + Filter Operator [FIL_153] (rows=18262 width=1119) predicate:((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_65] <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_50] + SHUFFLE [RS_30] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_2] + Please refer to the previous Select Operator [SEL_44] diff --git a/ql/src/test/results/clientpositive/ppd_gby_join.q.out b/ql/src/test/results/clientpositive/ppd_gby_join.q.out index 75d0a6270d..1ef29ae9e9 100644 --- a/ql/src/test/results/clientpositive/ppd_gby_join.q.out +++ b/ql/src/test/results/clientpositive/ppd_gby_join.q.out @@ -64,27 +64,20 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col0 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 < '50') or (_col1 > '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - 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 + Group By Operator + aggregations: count() + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + 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-2 Map Reduce @@ -94,7 +87,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -102,10 +95,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -334,27 +327,20 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col0 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 < '50') or (_col1 > '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - 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 + Group By Operator + aggregations: count() + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + 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-2 Map Reduce @@ -364,7 +350,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -372,10 +358,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join.q.out b/ql/src/test/results/clientpositive/ppd_join.q.out index 02aa5c2670..c47f866bb9 100644 --- a/ql/src/test/results/clientpositive/ppd_join.q.out +++ b/ql/src/test/results/clientpositive/ppd_join.q.out @@ -62,22 +62,19 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col2 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 < '50') or (_col1 > '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 40 Data size: 428 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 + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 60 Data size: 642 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 @@ -587,22 +584,19 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col2 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 < '50') or (_col1 > '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 40 Data size: 428 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 + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 60 Data size: 642 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_join5.q.out b/ql/src/test/results/clientpositive/ppd_join5.q.out index ca17699ca3..045a170a3c 100644 --- a/ql/src/test/results/clientpositive/ppd_join5.q.out +++ b/ql/src/test/results/clientpositive/ppd_join5.q.out @@ -177,7 +177,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (id1 is not null and id2 is not null) (type: boolean) + predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id1 (type: string), id2 (type: string) @@ -191,7 +191,7 @@ STAGE PLANS: alias: c Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (d <= 1) (type: boolean) + predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d (type: int) @@ -231,7 +231,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d <= 1) and id is not null) (type: boolean) + predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: string), d (type: int) @@ -252,20 +252,17 @@ STAGE PLANS: 1 _col0 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col2 > 1) or (_col4 > 1)) (type: boolean) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col4 (type: int), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col4 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out b/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out index 1dc1a2594f..8233b86d8c 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out @@ -72,27 +72,20 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col0 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 < '50') or (_col1 > '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Group By Operator + aggregations: count() + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + 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: _col1 (type: bigint) Reducer 3 Reduce Operator Tree: Group By Operator @@ -100,10 +93,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -340,27 +333,20 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: _col0 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 < '50') or (_col1 > '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + Group By Operator + aggregations: count() + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + 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: _col1 (type: bigint) Reducer 3 Reduce Operator Tree: Group By Operator @@ -368,10 +354,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 214 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/ppd_join.q.out b/ql/src/test/results/clientpositive/spark/ppd_join.q.out index dd2c394d48..260aff3729 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_join.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_join.q.out @@ -70,22 +70,19 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col2 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 < '50') or (_col1 > '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 40 Data size: 428 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 + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 60 Data size: 642 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 @@ -603,22 +600,19 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0, _col2 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col0 < '50') or (_col1 > '50')) (type: boolean) - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 428 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 40 Data size: 428 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 + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 60 Data size: 642 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_join5.q.out b/ql/src/test/results/clientpositive/spark/ppd_join5.q.out index 41817d8087..f3c789c774 100644 --- a/ql/src/test/results/clientpositive/spark/ppd_join5.q.out +++ b/ql/src/test/results/clientpositive/spark/ppd_join5.q.out @@ -182,7 +182,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (id1 is not null and id2 is not null) (type: boolean) + predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id1 (type: string), id2 (type: string) @@ -198,7 +198,7 @@ STAGE PLANS: alias: c Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (d <= 1) (type: boolean) + predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d (type: int) @@ -214,7 +214,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d <= 1) and id is not null) (type: boolean) + predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: string), d (type: int) @@ -252,20 +252,17 @@ STAGE PLANS: 1 _col0 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col2 > 1) or (_col4 > 1)) (type: boolean) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col4 (type: int), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col4 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out index 6a4bea1bd4..810e7b2b29 100644 --- a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out @@ -428,24 +428,24 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_35] - Select Operator [SEL_33] (rows=1 width=20) + File Output Operator [FS_34] + Select Operator [SEL_32] (rows=1 width=20) Output:["_col0","_col1","_col2"] <-Reducer 3 [SORT] - SORT [RS_32] - Select Operator [SEL_31] (rows=1 width=28) + SORT [RS_31] + Select Operator [SEL_30] (rows=1 width=28) Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_30] (rows=1 width=20) + Group By Operator [GBY_29] (rows=1 width=20) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [GROUP] - GROUP [RS_29] + GROUP [RS_28] PartitionCols:_col0, _col1 - Group By Operator [GBY_28] (rows=1 width=20) + Group By Operator [GBY_27] (rows=1 width=20) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4 - Select Operator [SEL_27] (rows=1 width=20) + Select Operator [SEL_26] (rows=1 width=20) Output:["_col1","_col4"] Filter Operator [FIL_23] (rows=1 width=20) - predicate:(((UDFToLong(_col1) + _col4) >= 0) and ((_col1 >= 1) or (_col4 >= 1)) and ((_col3 + _col6) >= 0) and ((_col3 > 0) or (_col1 >= 0))) + predicate:(((UDFToLong(_col1) + _col4) >= 0) and ((_col1 >= 1) or (_col4 >= 1)) and ((_col3 + _col6) >= 0)) Join Operator [JOIN_22] (rows=3 width=18) Output:["_col1","_col3","_col4","_col6"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"},{"":"{\"type\":\"Inner\",\"left\":1,\"right\":2}"}],keys:{"0":"_col0","1":"_col0","2":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] @@ -453,7 +453,7 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_2] (rows=18 width=84) Output:["_col0","_col1"] - Filter Operator [FIL_36] (rows=18 width=84) + Filter Operator [FIL_35] (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"] @@ -469,7 +469,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_6] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float - Filter Operator [FIL_37] (rows=2 width=93) + Filter Operator [FIL_36] (rows=2 width=93) predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (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"] @@ -485,7 +485,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_14] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float - Filter Operator [FIL_38] (rows=2 width=93) + Filter Operator [FIL_37] (rows=2 width=93) predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (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"] @@ -581,22 +581,22 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_34] - Select Operator [SEL_33] (rows=1 width=20) + File Output Operator [FS_33] + Select Operator [SEL_32] (rows=1 width=20) Output:["_col0","_col1","_col2"] <-Reducer 3 [SORT] - SORT [RS_32] - Group By Operator [GBY_30] (rows=1 width=20) + SORT [RS_31] + Group By Operator [GBY_29] (rows=1 width=20) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [GROUP] - GROUP [RS_29] + GROUP [RS_28] PartitionCols:_col0, _col1 - Group By Operator [GBY_28] (rows=1 width=20) + Group By Operator [GBY_27] (rows=1 width=20) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4 - Select Operator [SEL_27] (rows=1 width=20) + Select Operator [SEL_26] (rows=1 width=20) Output:["_col1","_col4"] Filter Operator [FIL_23] (rows=1 width=20) - predicate:(((UDFToLong(_col1) + _col4) >= 0) and ((_col1 >= 1) or (_col4 >= 1)) and ((_col3 + _col6) >= 0) and ((_col3 > 0) or (_col1 >= 0))) + predicate:(((UDFToLong(_col1) + _col4) >= 0) and ((_col1 >= 1) or (_col4 >= 1)) and ((_col3 + _col6) >= 0)) Join Operator [JOIN_22] (rows=3 width=18) Output:["_col1","_col3","_col4","_col6"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"},{"":"{\"type\":\"Inner\",\"left\":1,\"right\":2}"}],keys:{"0":"_col0","1":"_col0","2":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] @@ -604,7 +604,7 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_2] (rows=18 width=84) Output:["_col0","_col1"] - Filter Operator [FIL_35] (rows=18 width=84) + Filter Operator [FIL_34] (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"] @@ -620,7 +620,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_6] (rows=1 width=101) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float - Filter Operator [FIL_36] (rows=2 width=93) + Filter Operator [FIL_35] (rows=2 width=93) predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (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"] @@ -636,7 +636,7 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_14] (rows=1 width=93) Output:["_col0","_col1","_col2"],keys:key, c_int, c_float - Filter Operator [FIL_37] (rows=2 width=93) + Filter Operator [FIL_36] (rows=2 width=93) predicate:(((UDFToFloat(c_int) + c_float) >= 0) and ((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0)) and ((c_int >= 1) or (c_float >= 1)) and (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"]