Skip to content

[core] Clean up data file extra files #9586

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
JingsongLi merged 1 commit into from
Sep 4, 2026
Merged

[core] Clean up data file extra files #9586

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
4 changes: 2 additions & 2 deletions paimon-core/src/main/java/org/apache/paimon/append/AppendOnlyWriter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -288,7 +288,7 @@ public void close() throws Exception {
for (DataFileMeta file : compactAfter) {
// appendOnlyCompactManager will rewrite the file and no file upgrade will occur, so we
// can directly delete the file in compactAfter.
fileIO.deleteQuietly(pathFactory.toPath(file));
file.collectFiles(pathFactory).forEach(fileIO::deleteQuietly);
}

sinkWriter.close();
Expand All @@ -315,7 +315,7 @@ public void toBufferedWriter() throws Exception {
} finally {
// remove small files
for (DataFileMeta file : files) {
fileIO.deleteQuietly(pathFactory.toPath(file));
file.collectFiles(pathFactory).forEach(fileIO::deleteQuietly);
}
}
}
Expand Down
2 changes: 1 addition & 1 deletion paimon-core/src/main/java/org/apache/paimon/operation/FileStoreCommitImpl.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -714,7 +714,7 @@ public void abort(List<CommitMessage> commitMessages) {
dataFilesToDelete.addAll(commitMessage.compactIncrement().changelogFiles());

for (DataFileMeta file : dataFilesToDelete) {
fileIO.deleteQuietly(dataPathFactory.toPath(file));
file.collectFiles(dataPathFactory).forEach(fileIO::deleteQuietly);
}

List<IndexFileMeta> indexFilesToDelete = new ArrayList<>();
Expand Down
6 changes: 5 additions & 1 deletion paimon-core/src/test/java/org/apache/paimon/append/AppendOnlyWriterTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -376,6 +376,8 @@ public void testCloseUnexpectedly() throws Exception {
writer.write(row(j, String.format("%03d", j), PART));
}
writer.sync();
assertThat(Files.walk(tempDir).filter(Files::isRegularFile))
.anyMatch(path -> path.getFileName().toString().endsWith(".index"));

// writer closed unexpectedly
writer.close();
Expand Down Expand Up @@ -1321,6 +1323,8 @@ private DataFileMeta generateCompactAfter(List<DataFileMeta> toCompact) throws I
long maxSeq = toCompact.get(size - 1).maxSequenceNumber();
Path path = pathFactory.newPath("compact-");
LocalFileIO.create().newOutputStream(path, false).close();
Path extraPath = new Path(path.getParent(), path.getName() + ".index");
LocalFileIO.create().newOutputStream(extraPath, false).close();
return DataFileMeta.forAppend(
path.getName(),
toCompact.stream().mapToLong(DataFileMeta::fileSize).sum(),
Expand Down Expand Up @@ -1350,7 +1354,7 @@ private DataFileMeta generateCompactAfter(List<DataFileMeta> toCompact) throws I
minSeq,
maxSeq,
toCompact.get(0).schemaId(),
Collections.emptyList(),
Collections.singletonList(extraPath.getName()),
null,
FileSource.APPEND,
null,
Expand Down
61 changes: 61 additions & 0 deletions paimon-core/src/test/java/org/apache/paimon/operation/FileStoreCommitTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@
import org.apache.paimon.index.IndexPathFactory;
import org.apache.paimon.io.CompactIncrement;
import org.apache.paimon.io.DataFileMeta;
import org.apache.paimon.io.DataFilePathFactory;
import org.apache.paimon.io.DataIncrement;
import org.apache.paimon.manifest.FileKind;
import org.apache.paimon.manifest.IndexManifestEntry;
Expand Down Expand Up @@ -1127,6 +1128,66 @@ public void testAbortIndexFiles() throws Exception {
assertThat(store.fileIO().exists(compactDeletedPath)).isTrue();
}

@Test
public void testAbortDataFileWithExtraFiles() throws Exception {
TestAppendFileStore store = TestAppendFileStore.createAppendStore(tempDir, new HashMap<>());
BinaryRow partition = gen.getPartition(gen.next());
DataFilePathFactory pathFactory =
store.pathFactory().createDataFilePathFactory(partition, 0);

Path dataNewPath = pathFactory.newPath();
DataFileMeta dataNew = createDataFileWithExtraFile(store, dataNewPath, false);
Path compactNewPath = new Path(tempDir.resolve("external-compact-new.orc").toUri());
DataFileMeta compactNew = createDataFileWithExtraFile(store, compactNewPath, true);

CommitMessage commitMessage =
new CommitMessageImpl(
partition,
0,
store.options().bucket(),
new DataIncrement(
Collections.singletonList(dataNew),
Collections.emptyList(),
Collections.emptyList()),
new CompactIncrement(
Collections.emptyList(),
Collections.singletonList(compactNew),
Collections.emptyList()));

try (FileStoreCommitImpl commit = store.newCommit()) {
commit.abort(Collections.singletonList(commitMessage));
}

for (Path path : dataNew.collectFiles(pathFactory)) {
assertThat(store.fileIO().exists(path)).isFalse();
}
for (Path path : compactNew.collectFiles(pathFactory)) {
assertThat(store.fileIO().exists(path)).isFalse();
}
}

private static DataFileMeta createDataFileWithExtraFile(
TestAppendFileStore store, Path path, boolean external) throws Exception {
store.fileIO().newOutputStream(path, false).close();
Path extraPath = new Path(path.getParent(), path.getName() + ".index");
store.fileIO().newOutputStream(extraPath, false).close();
return DataFileMeta.forAppend(
path.getName(),
0,
0,
EMPTY_STATS,
0,
0,
0,
Collections.singletonList(extraPath.getName()),
null,
null,
null,
external ? path.toString() : null,
null,
null);
}

private static IndexFileMeta createIndexFile(
TestAppendFileStore store, Path path, boolean external) throws Exception {
store.fileIO().newOutputStream(path, false).close();
Expand Down
Loading