Skip to content

fix(optimizer): Fix hash function for prefilter groupby limit #27033

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
feilong-liu merged 1 commit into from
Jan 26, 2026
Merged

fix(optimizer): Fix hash function for prefilter groupby limit #27033

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions presto-main-base/src/main/java/com/facebook/presto/sql/planner/PlannerUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,6 +84,7 @@
import static com.facebook.presto.sql.planner.iterative.Lookup.noLookup;
import static com.facebook.presto.sql.planner.optimizations.PlanNodeSearcher.searchFrom;
import static com.facebook.presto.sql.relational.Expressions.call;
import static com.facebook.presto.sql.relational.Expressions.callOperator;
import static com.facebook.presto.sql.relational.Expressions.constant;
import static com.facebook.presto.sql.relational.Expressions.variable;
import static com.facebook.presto.type.TypeUtils.NULL_HASH_CODE;
Expand Down Expand Up @@ -577,4 +578,19 @@ public static RowExpression randomizeJoinKey(Session session, FunctionAndTypeMan
}
return new SpecialFormExpression(COALESCE, VARCHAR, ImmutableList.of(castToVarchar, concatExpression));
}

public static RowExpression getVariableHash(List<VariableReferenceExpression> inputVariables, FunctionAndTypeManager functionAndTypeManager)
{
checkArgument(!inputVariables.isEmpty());
List<CallExpression> hashExpressionList = inputVariables.stream().map(keyVariable ->
callOperator(functionAndTypeManager.getFunctionAndTypeResolver(), OperatorType.XX_HASH_64, BIGINT, keyVariable)).collect(toImmutableList());
RowExpression hashExpression = hashExpressionList.get(0);
if (hashExpressionList.size() > 1) {
hashExpression = orNullHashCode(hashExpression);
for (int i = 1; i < hashExpressionList.size(); ++i) {
hashExpression = call(functionAndTypeManager, "combine_hash", BIGINT, hashExpression, orNullHashCode(hashExpressionList.get(i)));
}
}
return hashExpression;
}
}
25 changes: 3 additions & 22 deletions ...-main-base/src/main/java/com/facebook/presto/sql/planner/optimizations/JoinPrefilter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,6 @@
package com.facebook.presto.sql.planner.optimizations;

import com.facebook.presto.Session;
import com.facebook.presto.common.function.OperatorType;
import com.facebook.presto.common.type.VarcharType;
import com.facebook.presto.metadata.FunctionAndTypeManager;
import com.facebook.presto.metadata.Metadata;
Expand All @@ -27,7 +26,6 @@
import com.facebook.presto.spi.plan.PlanNode;
import com.facebook.presto.spi.plan.PlanNodeIdAllocator;
import com.facebook.presto.spi.plan.SemiJoinNode;
import com.facebook.presto.spi.relation.CallExpression;
import com.facebook.presto.spi.relation.RowExpression;
import com.facebook.presto.spi.relation.VariableReferenceExpression;
import com.facebook.presto.sql.planner.TypeProvider;
Expand All @@ -42,21 +40,18 @@
import java.util.stream.IntStream;

import static com.facebook.presto.SystemSessionProperties.isJoinPrefilterEnabled;
import static com.facebook.presto.common.type.BigintType.BIGINT;
import static com.facebook.presto.common.type.BooleanType.BOOLEAN;
import static com.facebook.presto.common.type.VarcharType.VARCHAR;
import static com.facebook.presto.spi.plan.AggregationNode.singleGroupingSet;
import static com.facebook.presto.spi.plan.JoinType.INNER;
import static com.facebook.presto.spi.plan.JoinType.LEFT;
import static com.facebook.presto.sql.planner.PlannerUtils.addProjections;
import static com.facebook.presto.sql.planner.PlannerUtils.clonePlanNode;
import static com.facebook.presto.sql.planner.PlannerUtils.getVariableHash;
import static com.facebook.presto.sql.planner.PlannerUtils.isScanFilterProject;
import static com.facebook.presto.sql.planner.PlannerUtils.orNullHashCode;
import static com.facebook.presto.sql.planner.PlannerUtils.projectExpressions;
import static com.facebook.presto.sql.planner.PlannerUtils.restrictOutput;
import static com.facebook.presto.sql.planner.plan.ChildReplacer.replaceChildren;
import static com.facebook.presto.sql.relational.Expressions.call;
import static com.facebook.presto.sql.relational.Expressions.callOperator;
import static com.google.common.base.Preconditions.checkState;
import static com.google.common.collect.ImmutableList.toImmutableList;
import static java.util.Objects.requireNonNull;
Expand Down Expand Up @@ -208,7 +203,7 @@ public PlanNode visitJoin(JoinNode node, RewriteContext<Void> context)
PlanNode leftKeys = clonePlanNode(rewrittenLeft, session, metadata, idAllocator, leftKeyList, leftVarMap);
ImmutableList.Builder<RowExpression> expressionsToProject = ImmutableList.builder();
if (hashJoinKey) {
RowExpression hashExpression = getVariableHash(leftKeyList);
RowExpression hashExpression = getVariableHash(leftKeyList, functionAndTypeManager);
expressionsToProject.add(hashExpression);
}
else {
Expand All @@ -218,7 +213,7 @@ public PlanNode visitJoin(JoinNode node, RewriteContext<Void> context)

VariableReferenceExpression rightKeyToFilter = rightKeyList.get(0);
if (hashJoinKey) {
RowExpression hashExpression = getVariableHash(rightKeyList);
RowExpression hashExpression = getVariableHash(rightKeyList, functionAndTypeManager);
rightKeyToFilter = variableAllocator.newVariable(hashExpression);
rewrittenRight = addProjections(rewrittenRight, idAllocator, ImmutableMap.of(rightKeyToFilter, hashExpression));
}
Expand Down Expand Up @@ -273,19 +268,5 @@ public boolean isPlanChanged()
{
return planChanged;
}

private RowExpression getVariableHash(List<VariableReferenceExpression> inputVariables)
{
List<CallExpression> hashExpressionList = inputVariables.stream().map(keyVariable ->
callOperator(functionAndTypeManager.getFunctionAndTypeResolver(), OperatorType.XX_HASH_64, BIGINT, keyVariable)).collect(toImmutableList());
RowExpression hashExpression = hashExpressionList.get(0);
if (hashExpressionList.size() > 1) {
hashExpression = orNullHashCode(hashExpression);
for (int i = 1; i < hashExpressionList.size(); ++i) {
hashExpression = call(functionAndTypeManager, "combine_hash", BIGINT, hashExpression, orNullHashCode(hashExpressionList.get(i)));
}
}
return hashExpression;
}
}
}
6 changes: 3 additions & 3 deletions ...n/java/com/facebook/presto/sql/planner/optimizations/PrefilterForLimitingAggregation.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,8 +57,8 @@
import static com.facebook.presto.sql.planner.PlannerUtils.addProjections;
import static com.facebook.presto.sql.planner.PlannerUtils.clonePlanNode;
import static com.facebook.presto.sql.planner.PlannerUtils.createMapType;
import static com.facebook.presto.sql.planner.PlannerUtils.getHashExpression;
import static com.facebook.presto.sql.planner.PlannerUtils.getTableScanNodeWithOnlyFilterAndProject;
import static com.facebook.presto.sql.planner.PlannerUtils.getVariableHash;
import static com.facebook.presto.sql.planner.PlannerUtils.projectExpressions;
import static com.facebook.presto.sql.planner.optimizations.JoinNodeUtils.typeConvert;
import static com.facebook.presto.sql.planner.plan.ChildReplacer.replaceChildren;
Expand Down Expand Up @@ -223,8 +223,8 @@ private PlanNode addPrefilter(AggregationNode aggregationNode, long count)
SystemSessionProperties.getPrefilterForGroupbyLimitTimeoutMS(session));

FunctionAndTypeManager functionAndTypeManager = metadata.getFunctionAndTypeManager();
RowExpression leftHashExpression = getHashExpression(functionAndTypeManager, keys).get();
RowExpression rightHashExpression = getHashExpression(functionAndTypeManager, timedDistinctLimitNode.getOutputVariables()).get();
RowExpression leftHashExpression = getVariableHash(keys, functionAndTypeManager);
RowExpression rightHashExpression = getVariableHash(timedDistinctLimitNode.getOutputVariables(), functionAndTypeManager);

Type mapType = createMapType(functionAndTypeManager, BIGINT, BOOLEAN);
PlanNode rightProjectNode = projectExpressions(timedDistinctLimitNode, idAllocator, variableAllocator, ImmutableList.of(rightHashExpression, constant(TRUE, BOOLEAN)), ImmutableList.of());
Expand Down
Loading