Skip to content

Fix distributed sort parallelism for single node execution #25022

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
arhimondr merged 1 commit into from
May 1, 2025
Merged

Fix distributed sort parallelism for single node execution #25022

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
10 changes: 9 additions & 1 deletion ...n-base/src/main/java/com/facebook/presto/sql/planner/optimizations/AddLocalExchanges.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,6 +107,7 @@
import static com.google.common.base.Verify.verify;
import static com.google.common.collect.ImmutableList.toImmutableList;
import static com.google.common.collect.ImmutableSet.toImmutableSet;
import static com.google.common.collect.Iterables.getOnlyElement;
import static java.util.Objects.requireNonNull;
import static java.util.stream.Collectors.toList;

Expand Down Expand Up @@ -238,11 +239,18 @@ private PlanWithProperties planSortWithoutPartition(SortNode node, StreamPreferr
PlanWithProperties sortPlan = planAndEnforceChildren(node, fixedParallelism(), fixedParallelism());

if (!sortPlan.getProperties().isSingleStream()) {
SortNode sortNode = (SortNode) sortPlan.getNode();
return deriveProperties(
mergingExchange(
idAllocator.getNextId(),
LOCAL,
sortPlan.getNode(),
new SortNode(
sortNode.getSourceLocation(),
sortNode.getId(),
getOnlyElement(sortNode.getSources()),
sortNode.getOrderingScheme(),
true,
sortNode.getPartitionBy()),
node.getOrderingScheme()),
sortPlan.getProperties());
}
Expand Down
53 changes: 53 additions & 0 deletions ...tion/src/test/java/com/facebook/presto/nativeworker/AbstractTestNativeGeneralQueries.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,15 +15,22 @@

import com.facebook.presto.Session;
import com.facebook.presto.common.type.RowType;
import com.facebook.presto.execution.QueryInfo;
import com.facebook.presto.execution.StageInfo;
import com.facebook.presto.execution.TaskInfo;
import com.facebook.presto.operator.OperatorStats;
import com.facebook.presto.spi.ColumnMetadata;
import com.facebook.presto.spi.ConnectorTableMetadata;
import com.facebook.presto.spi.QueryId;
import com.facebook.presto.spi.SchemaTableName;
import com.facebook.presto.spi.plan.SortNode;
import com.facebook.presto.sql.analyzer.FeaturesConfig;
import com.facebook.presto.sql.planner.plan.ExchangeNode;
import com.facebook.presto.testing.MaterializedResult;
import com.facebook.presto.testing.MaterializedRow;
import com.facebook.presto.testing.QueryRunner;
import com.facebook.presto.tests.AbstractTestQueryFramework;
import com.facebook.presto.tests.DistributedQueryRunner;
import com.google.common.collect.ImmutableList;
import com.google.common.collect.ImmutableMap;
import org.intellij.lang.annotations.Language;
Expand All @@ -36,10 +43,12 @@
import java.util.UUID;
import java.util.regex.Pattern;

import static com.facebook.presto.SystemSessionProperties.DISTRIBUTED_SORT;
import static com.facebook.presto.SystemSessionProperties.INLINE_SQL_FUNCTIONS;
import static com.facebook.presto.SystemSessionProperties.JOIN_DISTRIBUTION_TYPE;
import static com.facebook.presto.SystemSessionProperties.KEY_BASED_SAMPLING_ENABLED;
import static com.facebook.presto.SystemSessionProperties.NATIVE_MIN_COLUMNAR_ENCODING_CHANNELS_TO_PREFER_ROW_WISE_ENCODING;
import static com.facebook.presto.SystemSessionProperties.SINGLE_NODE_EXECUTION_ENABLED;
import static com.facebook.presto.common.type.BigintType.BIGINT;
import static com.facebook.presto.common.type.VarcharType.VARCHAR;
import static com.facebook.presto.hive.HiveStorageFormat.DWRF;
Expand Down Expand Up @@ -81,6 +90,7 @@
import static com.facebook.presto.sql.planner.plan.ExchangeNode.Type.GATHER;
import static com.facebook.presto.sql.planner.plan.ExchangeNode.Type.REPARTITION;
import static com.facebook.presto.transaction.TransactionBuilder.transaction;
import static com.google.common.collect.Iterables.getOnlyElement;
import static java.lang.String.format;
import static java.util.stream.Collectors.toList;
import static org.assertj.core.api.Assertions.assertThat;
Expand Down Expand Up @@ -1994,4 +2004,47 @@ private List<MaterializedRow> getJavaWorkerSessionProperties(List<MaterializedRo
.filter(row -> Pattern.matches(sessionPropertyName, row.getFields().get(4).toString()))
.collect(toList());
}

@Test
public void testDistributedSortSingleNode()
{
assertDistributedSortSingleNode("SELECT orderkey FROM orders ORDER BY orderkey");
assertDistributedSortSingleNode("SELECT DISTINCT orderkey FROM orders ORDER BY 1");
assertDistributedSortSingleNode("SELECT orderstatus, SUM(totalprice) FROM orders GROUP BY orderstatus ORDER BY 2 DESC");
}

private void assertDistributedSortSingleNode(String query)
{
Session session = Session.builder(getSession())
.setSystemProperty(DISTRIBUTED_SORT, "true")
.setSystemProperty(SINGLE_NODE_EXECUTION_ENABLED, "true")
.build();
assertQuery(session, query, plan -> {
SortNode sortNode = searchFrom(plan.getRoot())
.where(node -> node instanceof SortNode)
.findOnlyElement();
assertTrue(sortNode.isPartial());
});
DistributedQueryRunner runner = getDistributedQueryRunner();
QueryId queryId = runner.executeWithQueryId(session, query).getQueryId();
QueryInfo queryInfo = runner.getQueryInfo(queryId);
OperatorStats sortStats = findSortStats(queryInfo);
assertThat(sortStats.getTotalDrivers())
.isGreaterThan(1);
}

private OperatorStats findSortStats(QueryInfo queryInfo)
{
// exactly one stage is expected
StageInfo stageInfo = getOnlyElement(queryInfo.getOutputStage()
.orElseThrow(() -> new AssertionError("stage info is expected to be set"))
.getAllStages());
// exactly one task is expected
TaskInfo taskInfo = getOnlyElement(stageInfo.getLatestAttemptExecutionInfo().getTasks());
// exactly one sort operator is expected
return getOnlyElement(taskInfo.getStats().getPipelines().stream()
.flatMap(pipelineStats -> pipelineStats.getOperatorSummaries().stream())
.filter(operatorStats -> operatorStats.getOperatorType().contains("OrderBy"))
.collect(toList()));
}
}