Skip to content

branch-4.1: [fix](iceberg) Resolve dropped equality-delete fields in manifest-cache planning #68433

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

Open
hubgeter wants to merge 1 commit into
base: branch-4.1
Choose a base branch
from
+90 −2
Open

branch-4.1: [fix](iceberg) Resolve dropped equality-delete fields in manifest-cache planning #68433

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
5 changes: 4 additions & 1 deletion fe/fe-core/src/main/java/org/apache/doris/datasource/iceberg/source/IcebergScanNode.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2420,9 +2420,12 @@ protected List<FileScanTask> loadFileScanTasksWithManifestCache(
deleteFiles.addAll(value.getDeleteFiles());
}

// Build delete file index for efficient lookup of deletes applicable to each data file
// Build delete file index for efficient lookup of deletes applicable to each data file.
// Equality deletes may reference fields dropped from the current schema, so resolve their
// field IDs against every historical schema like Iceberg's DataTableScan does.
DeleteFileIndex deleteIndex = DeleteFileIndex.builderFor(deleteFiles)
.specsById(specsById)
.schemasById(icebergTable.schemas())
.caseSensitive(caseSensitive)
.build();

Expand Down
3 changes: 2 additions & 1 deletion fe/fe-core/src/main/java/org/apache/iceberg/DeleteFileIndex.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -400,7 +400,8 @@ Builder afterSequenceNumber(long seq) {
return this;
}

Builder schemasById(Map<Integer, Schema> newSchemasById) {
// changed to public method: equality deletes may reference fields dropped from the current schema.
public Builder schemasById(Map<Integer, Schema> newSchemasById) {
this.schemasById = newSchemasById;
return this;
}
Expand Down
84 changes: 84 additions & 0 deletions fe/fe-core/src/test/java/org/apache/doris/datasource/iceberg/source/IcebergScanNodeTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@
import org.apache.doris.analysis.TupleId;
import org.apache.doris.catalog.Column;
import org.apache.doris.catalog.DatabaseIf;
import org.apache.doris.catalog.Env;
import org.apache.doris.catalog.StructField;
import org.apache.doris.catalog.StructType;
import org.apache.doris.catalog.TableIf;
Expand All @@ -39,7 +40,10 @@
import org.apache.doris.common.security.authentication.ExecutionAuthenticator;
import org.apache.doris.common.util.LocationPath;
import org.apache.doris.datasource.CatalogIf;
import org.apache.doris.datasource.ExternalCatalog;
import org.apache.doris.datasource.ExternalMetaCacheMgr;
import org.apache.doris.datasource.ExternalScanNode;
import org.apache.doris.datasource.ExternalTable;
import org.apache.doris.datasource.FederationBackendPolicy;
import org.apache.doris.datasource.SplitAssignment;
import org.apache.doris.datasource.SplitGenerator;
Expand All @@ -55,6 +59,8 @@
import org.apache.doris.datasource.iceberg.IcebergSysExternalTable;
import org.apache.doris.datasource.iceberg.IcebergTableCacheValue;
import org.apache.doris.datasource.iceberg.IcebergUtils;
import org.apache.doris.datasource.iceberg.cache.IcebergManifestCacheLoader;
import org.apache.doris.datasource.iceberg.cache.ManifestCacheValue;
import org.apache.doris.datasource.mvcc.MvccTableInfo;
import org.apache.doris.nereids.StatementContext;
import org.apache.doris.planner.PlanNodeId;
Expand Down Expand Up @@ -89,6 +95,7 @@
import org.apache.iceberg.FileFormat;
import org.apache.iceberg.FileMetadata;
import org.apache.iceberg.FileScanTask;
import org.apache.iceberg.ManifestFiles;
import org.apache.iceberg.MetadataColumns;
import org.apache.iceberg.MetadataTableType;
import org.apache.iceberg.PartitionData;
Expand Down Expand Up @@ -117,6 +124,7 @@
import org.junit.Rule;
import org.junit.Test;
import org.junit.rules.TemporaryFolder;
import org.mockito.MockedStatic;
import org.mockito.Mockito;

import java.io.Closeable;
Expand Down Expand Up @@ -3157,6 +3165,82 @@ private void assertHistoricalPredicatePlansAfterSchemaEvolution(boolean dropColu
Assert.assertEquals(1, materializeTasks(scan).size());
}

@Test
public void testManifestCachePlanningResolvesDroppedEqualityDeleteField() throws Exception {
Schema schema = new Schema(
Types.NestedField.optional(1, "k", Types.IntegerType.get()),
Types.NestedField.optional(2, "row_tag", Types.StringType.get()));
String tableLocation = temporaryFolder.getRoot().toPath()
.resolve("manifest_cache_dropped_equality_key").toUri().toString();
Table table = new HadoopTables(new Configuration()).create(
schema, PartitionSpec.unpartitioned(), SortOrder.unsorted(),
ImmutableMap.of(TableProperties.FORMAT_VERSION, "2"), tableLocation);
table.newFastAppend().appendFile(DataFiles.builder(table.spec())
.withPath(tableLocation + "/data/old.parquet")
.withFormat(FileFormat.PARQUET)
.withFileSizeInBytes(10)
.withRecordCount(2)
.build()).commit();
table.newRowDelta().addDeletes(FileMetadata.deleteFileBuilder(table.spec())
.ofEqualityDeletes(1)
.withPath(tableLocation + "/data/eq-delete.parquet")
.withFormat(FileFormat.PARQUET)
.withFileSizeInBytes(10)
.withRecordCount(1)
.build()).commit();
// The live equality delete still references field 1 after it leaves the current schema.
table.updateSchema().deleteColumn("k").commit();
table.newFastAppend().appendFile(DataFiles.builder(table.spec())
.withPath(tableLocation + "/data/new.parquet")
.withFormat(FileFormat.PARQUET)
.withFileSizeInBytes(10)
.withRecordCount(1)
.build()).commit();

TestIcebergScanNode node = new TestIcebergScanNode(new SessionVariable());
IcebergSource source = Mockito.mock(IcebergSource.class);
Mockito.when(source.getCatalog()).thenReturn(Mockito.mock(ExternalCatalog.class));
Mockito.when(source.getTargetTable()).thenReturn(Mockito.mock(ExternalTable.class));
setPrivateField(node, "source", source);
setPrivateField(node, "icebergTable", table);
Env env = Mockito.mock(Env.class);
Mockito.when(env.getExtMetaCacheMgr()).thenReturn(Mockito.mock(ExternalMetaCacheMgr.class));
try (MockedStatic<Env> mockedEnv = Mockito.mockStatic(Env.class);
MockedStatic<IcebergManifestCacheLoader> loader =
Mockito.mockStatic(IcebergManifestCacheLoader.class)) {
mockedEnv.when(Env::getCurrentEnv).thenReturn(env);
loader.when(() -> IcebergManifestCacheLoader.loadDeleteFilesWithCache(Mockito.any(), Mockito.any(),
Mockito.any(), Mockito.any(), Mockito.any(), Mockito.any()))
.thenAnswer(invocation -> {
List<DeleteFile> files = new ArrayList<>();
try (CloseableIterable<DeleteFile> reader = ManifestFiles.readDeleteManifest(
invocation.getArgument(2), table.io(), table.specs())) {
reader.forEach(file -> files.add(file.copy()));
}
return ManifestCacheValue.forDeleteFiles(files);
});
loader.when(() -> IcebergManifestCacheLoader.loadDataFilesWithCache(Mockito.any(), Mockito.any(),
Mockito.any(), Mockito.any(), Mockito.any(), Mockito.any()))
.thenAnswer(invocation -> {
List<DataFile> files = new ArrayList<>();
try (CloseableIterable<DataFile> reader = ManifestFiles.read(
invocation.getArgument(2), table.io(), table.specs())) {
reader.forEach(file -> files.add(file.copy()));
}
return ManifestCacheValue.forDataFiles(files);
});

List<FileScanTask> tasks = node.loadFileScanTasksWithManifestCache(
table.newScan(), table.currentSnapshot());

Map<String, Integer> deleteCounts = new HashMap<>();
tasks.forEach(task -> deleteCounts.put(task.file().location(), task.deletes().size()));
Assert.assertEquals(ImmutableMap.of(
tableLocation + "/data/old.parquet", 1,
tableLocation + "/data/new.parquet", 0), deleteCounts);
}
}

@Test
public void testPinnedBranchUsesFrozenSnapshotWithCurrentSchema() throws Exception {
Schema snapshotSchema = new Schema(11, ImmutableList.of(
Expand Down
Loading