Skip to content
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

[Spark][MR]: Reuse InputFilesDecryptor #4595

Closed
wants to merge 2 commits into from
Closed

[Spark][MR]: Reuse InputFilesDecryptor #4595

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c2177b6
Reuse InputFilesDecryptor in Spark BaseDataReader
zhongyujiang Apr 19, 2022
bef9c6b
Reuse InputFilesDecryptor in MR
zhongyujiang Apr 20, 2022
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
Next Next commit
Reuse InputFilesDecryptor in Spark BaseDataReader
  • Loading branch information
@zhongyujiang
zhongyujiang committed Apr 19, 2022
commit c2177b62f7ad05a1a8c65cef8c3e7b31ec4505c3
27 changes: 5 additions & 22 deletions spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/source/BaseDataReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,6 @@
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.stream.Stream;
import org.apache.avro.generic.GenericData;
import org.apache.avro.util.Utf8;
import org.apache.iceberg.CombinedScanTask;
Expand All @@ -36,13 +35,10 @@
import org.apache.iceberg.Schema;
import org.apache.iceberg.StructLike;
import org.apache.iceberg.Table;
import org.apache.iceberg.encryption.EncryptedFiles;
import org.apache.iceberg.encryption.EncryptedInputFile;
import org.apache.iceberg.encryption.InputFilesDecryptor;
import org.apache.iceberg.io.CloseableIterator;
import org.apache.iceberg.io.InputFile;
import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap;
import org.apache.iceberg.relocated.com.google.common.collect.Maps;
import org.apache.iceberg.types.Type;
import org.apache.iceberg.types.Types.NestedField;
import org.apache.iceberg.types.Types.StructType;
Expand All @@ -65,7 +61,7 @@ abstract class BaseDataReader<T> implements Closeable {

private final Table table;
private final Iterator<FileScanTask> tasks;
private final Map<String, InputFile> inputFiles;
private final InputFilesDecryptor inputFilesDecryptor;

private CloseableIterator<T> currentIterator;
private T current = null;
Expand All @@ -74,20 +70,7 @@ abstract class BaseDataReader<T> implements Closeable {
BaseDataReader(Table table, CombinedScanTask task) {
this.table = table;
this.tasks = task.files().iterator();
Map<String, ByteBuffer> keyMetadata = Maps.newHashMap();
task.files().stream()
.flatMap(fileScanTask -> Stream.concat(Stream.of(fileScanTask.file()), fileScanTask.deletes().stream()))
.forEach(file -> keyMetadata.put(file.path().toString(), file.keyMetadata()));
Stream<EncryptedInputFile> encrypted = keyMetadata.entrySet().stream()
.map(entry -> EncryptedFiles.encryptedInput(table.io().newInputFile(entry.getKey()), entry.getValue()));

// decrypt with the batch call to avoid multiple RPCs to a key server, if possible
Iterable<InputFile> decryptedFiles = table.encryption().decrypt(encrypted::iterator);

Map<String, InputFile> files = Maps.newHashMapWithExpectedSize(task.files().size());
decryptedFiles.forEach(decrypted -> files.putIfAbsent(decrypted.location(), decrypted));
this.inputFiles = ImmutableMap.copyOf(files);

this.inputFilesDecryptor = new InputFilesDecryptor(task, table().io(), table.encryption());
this.currentIterator = CloseableIterator.empty();
}

Expand Down Expand Up @@ -139,11 +122,11 @@ public void close() throws IOException {

protected InputFile getInputFile(FileScanTask task) {
Preconditions.checkArgument(!task.isDataTask(), "Invalid task type");
return inputFiles.get(task.file().path().toString());
return inputFilesDecryptor.getInputFile(task);
}

protected InputFile getInputFile(String location) {
return inputFiles.get(location);
return inputFilesDecryptor.getInputFile(location);
}

protected Map<Integer, ?> constantsMap(FileScanTask task, Schema readSchema) {
Expand Down