Skip to content

Optimized iterative list implementations #4952

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 3 commits into from
Jan 21, 2025
Merged

Optimized iterative list implementations #4952

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5bf1104
iterative list for oss
smdsbz Jan 20, 2025
666ef87
iterative list for s3 and hadoop
smdsbz Jan 20, 2025
e865171
test for HadoopFileIO's iterative list
smdsbz Jan 21, 2025
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
24 changes: 24 additions & 0 deletions paimon-common/src/main/java/org/apache/paimon/fs/hadoop/HadoopFileIO.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@
import org.apache.paimon.fs.FileStatus;
import org.apache.paimon.fs.Path;
import org.apache.paimon.fs.PositionOutputStream;
import org.apache.paimon.fs.RemoteIterator;
import org.apache.paimon.fs.SeekableInputStream;
import org.apache.paimon.hadoop.SerializableConfiguration;
import org.apache.paimon.utils.FunctionWithException;
Expand Down Expand Up @@ -104,6 +105,29 @@ public FileStatus[] listStatus(Path path) throws IOException {
return statuses;
}

@Override
public RemoteIterator<FileStatus> listFilesIterative(Path path, boolean recursive)
Copy link
Contributor

@JingsongLi JingsongLi Jan 21, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Add tests for hadoop file io?

throws IOException {
org.apache.hadoop.fs.Path hadoopPath = path(path);
org.apache.hadoop.fs.RemoteIterator<org.apache.hadoop.fs.LocatedFileStatus> hadoopIter =
getFileSystem(hadoopPath).listFiles(hadoopPath, recursive);
return new RemoteIterator<FileStatus>() {
@Override
public boolean hasNext() throws IOException {
return hadoopIter.hasNext();
}

@Override
public FileStatus next() throws IOException {
org.apache.hadoop.fs.FileStatus hadoopStatus = hadoopIter.next();
return new HadoopFileStatus(hadoopStatus);
}

@Override
public void close() throws IOException {}
};
}

@Override
public boolean exists(Path path) throws IOException {
org.apache.hadoop.fs.Path hadoopPath = path(path);
Expand Down
39 changes: 39 additions & 0 deletions paimon-common/src/test/java/org/apache/paimon/fs/FileIOBehaviorTestBase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,8 @@
import org.junit.jupiter.api.Test;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Random;

import static org.assertj.core.api.Assertions.assertThat;
Expand Down Expand Up @@ -85,6 +87,43 @@ void testFileDoesNotExist() throws IOException {
assertThat(fs.exists(new Path(basePath, randomName()))).isFalse();
}

// --- list files

@Test
void testListFilesIterativeNonRecursive() throws IOException {
Path fileA = createRandomFileInDirectory(basePath);
Path dirB = new Path(basePath, randomName());
fs.mkdirs(dirB);
Path fileBC = createRandomFileInDirectory(dirB);

List<FileStatus> allFiles = new ArrayList<>();
try (RemoteIterator<FileStatus> iter = fs.listFilesIterative(basePath, false)) {
while (iter.hasNext()) {
allFiles.add(iter.next());
}
}
assertThat(allFiles.size()).isEqualTo(1);
assertThat(allFiles.get(0).getPath()).isEqualTo(fileA);
}

@Test
void testListFilesIterativeRecursive() throws IOException {
Path fileA = createRandomFileInDirectory(basePath);
Path dirB = new Path(basePath, randomName());
fs.mkdirs(dirB);
Path fileBC = createRandomFileInDirectory(dirB);

List<FileStatus> allFiles = new ArrayList<>();
try (RemoteIterator<FileStatus> iter = fs.listFilesIterative(basePath, true)) {
while (iter.hasNext()) {
allFiles.add(iter.next());
}
}
assertThat(allFiles.size()).isEqualTo(2);
assertThat(allFiles.stream().filter(f -> f.getPath().equals(fileA)).count()).isEqualTo(1);
assertThat(allFiles.stream().filter(f -> f.getPath().equals(fileBC)).count()).isEqualTo(1);
}

// --- delete

@Test
Expand Down
24 changes: 24 additions & 0 deletions ...ilesystems/paimon-oss-impl/src/main/java/org/apache/paimon/oss/HadoopCompliantFileIO.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
import org.apache.paimon.fs.FileStatus;
import org.apache.paimon.fs.Path;
import org.apache.paimon.fs.PositionOutputStream;
import org.apache.paimon.fs.RemoteIterator;
import org.apache.paimon.fs.SeekableInputStream;

import org.apache.hadoop.fs.FSDataInputStream;
Expand Down Expand Up @@ -77,6 +78,29 @@ public FileStatus[] listStatus(Path path) throws IOException {
return statuses;
}

@Override
public RemoteIterator<FileStatus> listFilesIterative(Path path, boolean recursive)
throws IOException {
org.apache.hadoop.fs.Path hadoopPath = path(path);
org.apache.hadoop.fs.RemoteIterator<org.apache.hadoop.fs.LocatedFileStatus> hadoopIter =
getFileSystem(hadoopPath).listFiles(hadoopPath, recursive);
return new RemoteIterator<FileStatus>() {
@Override
public boolean hasNext() throws IOException {
return hadoopIter.hasNext();
}

@Override
public FileStatus next() throws IOException {
org.apache.hadoop.fs.FileStatus hadoopStatus = hadoopIter.next();
return new HadoopFileStatus(hadoopStatus);
}

@Override
public void close() throws IOException {}
};
}

@Override
public boolean exists(Path path) throws IOException {
org.apache.hadoop.fs.Path hadoopPath = path(path);
Expand Down
24 changes: 24 additions & 0 deletions ...-filesystems/paimon-s3-impl/src/main/java/org/apache/paimon/s3/HadoopCompliantFileIO.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
import org.apache.paimon.fs.FileStatus;
import org.apache.paimon.fs.Path;
import org.apache.paimon.fs.PositionOutputStream;
import org.apache.paimon.fs.RemoteIterator;
import org.apache.paimon.fs.SeekableInputStream;

import org.apache.hadoop.fs.FSDataInputStream;
Expand Down Expand Up @@ -77,6 +78,29 @@ public FileStatus[] listStatus(Path path) throws IOException {
return statuses;
}

@Override
public RemoteIterator<FileStatus> listFilesIterative(Path path, boolean recursive)
throws IOException {
org.apache.hadoop.fs.Path hadoopPath = path(path);
org.apache.hadoop.fs.RemoteIterator<org.apache.hadoop.fs.LocatedFileStatus> hadoopIter =
getFileSystem(hadoopPath).listFiles(hadoopPath, recursive);
return new RemoteIterator<FileStatus>() {
@Override
public boolean hasNext() throws IOException {
return hadoopIter.hasNext();
}

@Override
public FileStatus next() throws IOException {
org.apache.hadoop.fs.FileStatus hadoopStatus = hadoopIter.next();
return new HadoopFileStatus(hadoopStatus);
}

@Override
public void close() throws IOException {}
};
}

@Override
public boolean exists(Path path) throws IOException {
org.apache.hadoop.fs.Path hadoopPath = path(path);
Expand Down
Loading