Skip to content

Filter Delta Lake splits based on $path column predicates #13172

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
ebyhr merged 1 commit into from
Jul 14, 2022
Merged

Filter Delta Lake splits based on $path column predicates #13172

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
25 changes: 22 additions & 3 deletions plugin/trino-delta-lake/src/main/java/io/trino/plugin/deltalake/DeltaLakeSplitManager.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,8 @@
import static com.google.common.collect.ImmutableList.toImmutableList;
import static com.google.common.collect.ImmutableMap.toImmutableMap;
import static com.google.common.collect.ImmutableSet.toImmutableSet;
import static io.airlift.slice.Slices.utf8Slice;
import static io.trino.plugin.deltalake.DeltaLakeColumnHandle.pathColumnHandle;
import static io.trino.plugin.deltalake.DeltaLakeMetadata.createStatisticsPredicate;
import static io.trino.plugin.deltalake.DeltaLakeSessionProperties.getDynamicFilteringWaitTimeout;
import static io.trino.plugin.deltalake.DeltaLakeSessionProperties.getMaxInitialSplitSize;
Expand Down Expand Up @@ -131,6 +133,7 @@ private Stream<DeltaLakeSplit> getSplits(
List<AddFileEntry> validDataFiles = metastore.getValidDataFiles(tableHandle.getSchemaTableName(), session);
TupleDomain<DeltaLakeColumnHandle> enforcedPartitionConstraint = tableHandle.getEnforcedPartitionConstraint();
TupleDomain<DeltaLakeColumnHandle> nonPartitionConstraint = tableHandle.getNonPartitionConstraint();
Domain pathDomain = getPathDomain(nonPartitionConstraint);

// Delta Lake handles updates and deletes by copying entire data files, minus updates/deletes. Because of this we can only have one Split/UpdatablePageSource
// per file.
Expand All @@ -157,6 +160,11 @@ private Stream<DeltaLakeSplit> getSplits(
return Stream.empty();
}

String splitPath = buildSplitPath(tableLocation, addAction);
Comment thread
ebyhr marked this conversation as resolved.
Outdated
if (!pathMatchesPredicate(pathDomain, splitPath)) {
return Stream.empty();
}

if (filesModifiedAfter.isPresent() && addAction.getModificationTime() <= filesModifiedAfter.get().toEpochMilli()) {
return Stream.empty();
}
Expand Down Expand Up @@ -194,7 +202,7 @@ private Stream<DeltaLakeSplit> getSplits(
return splitsForFile(
session,
addAction,
tableLocation,
splitPath,
addAction.getCanonicalPartitionValues(),
statisticsPredicate,
splittable,
Expand All @@ -215,17 +223,28 @@ public static boolean partitionMatchesPredicate(Map<String, Optional<String>> pa
return true;
}

private static Domain getPathDomain(TupleDomain<DeltaLakeColumnHandle> effectivePredicate)
{
return effectivePredicate.getDomains()
.flatMap(domains -> Optional.ofNullable(domains.get(pathColumnHandle())))
.orElse(Domain.all(pathColumnHandle().getType()));
}

private static boolean pathMatchesPredicate(Domain pathDomain, String path)
{
return pathDomain.includesNullableValue(utf8Slice(path));
}

private List<DeltaLakeSplit> splitsForFile(
ConnectorSession session,
AddFileEntry addFileEntry,
String tableLocation,
String splitPath,
Map<String, Optional<String>> partitionKeys,
TupleDomain<DeltaLakeColumnHandle> statisticsPredicate,
boolean splittable,
AtomicInteger remainingInitialSplits)
{
long fileSize = addFileEntry.getSize();
String splitPath = buildSplitPath(tableLocation, addFileEntry);

if (!splittable) {
// remainingInitialSplits is not used when !splittable
Expand Down
18 changes: 18 additions & 0 deletions ...o-delta-lake/src/test/java/io/trino/plugin/deltalake/BaseDeltaLakeMinioConnectorTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -494,6 +494,24 @@ public void testTargetMaxFileSize()
}
}

@Test
public void testPathColumn()
{
try (TestTable table = new TestTable(getQueryRunner()::execute, "test_path_column", "(x VARCHAR)")) {
assertUpdate("INSERT INTO " + table.getName() + " SELECT 'first'", 1);
String firstFilePath = (String) computeScalar("SELECT \"$path\" FROM " + table.getName());
assertUpdate("INSERT INTO " + table.getName() + " SELECT 'second'", 1);
String secondFilePath = (String) computeScalar("SELECT \"$path\" FROM " + table.getName() + " WHERE x = 'second'");

// Verify predicate correctness on $path column
assertQuery("SELECT x FROM " + table.getName() + " WHERE \"$path\" = '" + firstFilePath + "'", "VALUES 'first'");
assertQuery("SELECT x FROM " + table.getName() + " WHERE \"$path\" <> '" + firstFilePath + "'", "VALUES 'second'");
assertQuery("SELECT x FROM " + table.getName() + " WHERE \"$path\" IN ('" + firstFilePath + "', '" + secondFilePath + "')", "VALUES ('first'), ('second')");
assertQuery("SELECT x FROM " + table.getName() + " WHERE \"$path\" IS NOT NULL", "VALUES ('first'), ('second')");
assertQueryReturnsEmptyResult("SELECT x FROM " + table.getName() + " WHERE \"$path\" IS NULL");
Comment thread
ebyhr marked this conversation as resolved.
Outdated
}
}

@Override
protected String createSchemaSql(String schemaName)
{
Expand Down