Skip to content

Service: Cleanup Iceberg Manifest list on Purge #1039

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
merged 1 commit into from
Feb 24, 2025
Merged

Service: Cleanup Iceberg Manifest list on Purge #1039

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
49 changes: 42 additions & 7 deletions ...ce/src/test/java/org/apache/polaris/service/quarkus/task/TableCleanupTaskHandlerTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,7 +167,8 @@ public void testTableCleanup() throws IOException {
taskEntity2 -> taskEntity2.getTaskType())
.returns(
new ManifestFileCleanupTaskHandler.ManifestCleanupTask(
tableIdentifier, List.of(statisticsFile.path())),
tableIdentifier,
List.of(snapshot.manifestListLocation(), statisticsFile.path())),
entity ->
entity.readData(
ManifestFileCleanupTaskHandler.ManifestCleanupTask.class)));
Expand Down Expand Up @@ -224,7 +225,7 @@ public void close() {
.getOrCreateMetaStoreManager(realmContext)
.loadTasks(callContext.getPolarisCallContext(), "test", 5)
.getEntities())
.hasSize(1);
.hasSize(2);
}

@Test
Expand Down Expand Up @@ -285,15 +286,41 @@ public void close() {
.getOrCreateMetaStoreManager(realmContext)
.loadTasks(callContext.getPolarisCallContext(), "test", 5)
.getEntities())
.hasSize(2)
.hasSize(4)
.satisfiesExactly(
taskEntity ->
assertThat(taskEntity)
.returns(PolarisEntityType.TASK.getCode(), PolarisBaseEntity::getTypeCode)
.extracting(TaskEntity::of)
.returns(
AsyncTaskType.MANIFEST_FILE_CLEANUP,
AsyncTaskType.METADATA_FILE_BATCH_CLEANUP,
taskEntity1 -> taskEntity1.getTaskType())
.returns(
new ManifestFileCleanupTaskHandler.ManifestCleanupTask(
tableIdentifier, List.of(snapshot.manifestListLocation())),
entity ->
entity.readData(
ManifestFileCleanupTaskHandler.ManifestCleanupTask.class)),
taskEntity ->
assertThat(taskEntity)
.returns(PolarisEntityType.TASK.getCode(), PolarisBaseEntity::getTypeCode)
.extracting(TaskEntity::of)
.returns(
AsyncTaskType.METADATA_FILE_BATCH_CLEANUP,
taskEntity2 -> taskEntity2.getTaskType())
.returns(
new ManifestFileCleanupTaskHandler.ManifestCleanupTask(
tableIdentifier, List.of(snapshot.manifestListLocation())),
entity ->
entity.readData(
ManifestFileCleanupTaskHandler.ManifestCleanupTask.class)),
taskEntity ->
assertThat(taskEntity)
.returns(PolarisEntityType.TASK.getCode(), PolarisBaseEntity::getTypeCode)
.extracting(TaskEntity::of)
.returns(
AsyncTaskType.MANIFEST_FILE_CLEANUP,
taskEntity3 -> taskEntity3.getTaskType())
.returns(
new ManifestFileCleanupTaskHandler.ManifestCleanupTask(
tableIdentifier,
Expand All @@ -307,7 +334,7 @@ public void close() {
.extracting(TaskEntity::of)
.returns(
AsyncTaskType.MANIFEST_FILE_CLEANUP,
taskEntity2 -> taskEntity2.getTaskType())
taskEntity4 -> taskEntity4.getTaskType())
.returns(
new ManifestFileCleanupTaskHandler.ManifestCleanupTask(
tableIdentifier,
Expand Down Expand Up @@ -413,7 +440,11 @@ public void testTableCleanupMultipleSnapshots() throws IOException {
.returns(
new ManifestFileCleanupTaskHandler.ManifestCleanupTask(
tableIdentifier,
List.of(statisticsFile1.path(), statisticsFile2.path())),
List.of(
snapshot.manifestListLocation(),
snapshot2.manifestListLocation(),
statisticsFile1.path(),
statisticsFile2.path())),
entity ->
entity.readData(
ManifestFileCleanupTaskHandler.ManifestCleanupTask.class)));
Expand Down Expand Up @@ -569,7 +600,11 @@ public void testTableCleanupMultipleMetadata() throws IOException {
new ManifestFileCleanupTaskHandler.ManifestCleanupTask(
tableIdentifier,
List.of(
firstMetadataFile, statisticsFile1.path(), statisticsFile2.path())),
firstMetadataFile,
snapshot.manifestListLocation(),
snapshot2.manifestListLocation(),
statisticsFile1.path(),
statisticsFile2.path())),
entity ->
entity.readData(
ManifestFileCleanupTaskHandler.ManifestCleanupTask.class)));
Expand Down
6 changes: 5 additions & 1 deletion service/common/src/main/java/org/apache/polaris/service/task/TableCleanupTaskHandler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@
import java.util.stream.Collectors;
import java.util.stream.Stream;
import org.apache.iceberg.ManifestFile;
import org.apache.iceberg.Snapshot;
import org.apache.iceberg.StatisticsFile;
import org.apache.iceberg.TableMetadata;
import org.apache.iceberg.TableMetadataParser;
Expand Down Expand Up @@ -243,7 +244,10 @@ private List<List<String>> getMetadataFileBatches(TableMetadata tableMetadata, i
List<List<String>> result = new ArrayList<>();
List<String> metadataFiles =
Stream.concat(
tableMetadata.previousFiles().stream().map(TableMetadata.MetadataLogEntry::file),
Stream.concat(
tableMetadata.previousFiles().stream()
.map(TableMetadata.MetadataLogEntry::file),
tableMetadata.snapshots().stream().map(Snapshot::manifestListLocation)),
tableMetadata.statisticsFiles().stream().map(StatisticsFile::path))
.toList();

Expand Down