richardstartin commented on a change in pull request #6320:
URL: https://github.com/apache/incubator-pinot/pull/6320#discussion_r536559080
##########
File path:
pinot-core/src/main/java/org/apache/pinot/core/segment/creator/impl/inv/OnHeapBitmapInvertedIndexCreator.java
##########
@@ -19,68 +19,85 @@
package org.apache.pinot.core.segment.creator.impl.inv;
import com.google.common.base.Preconditions;
-import java.io.BufferedOutputStream;
-import java.io.DataOutputStream;
+
+
import java.io.File;
-import java.io.FileOutputStream;
import java.io.IOException;
+import java.io.RandomAccessFile;
+import java.nio.ByteBuffer;
+import java.nio.channels.FileChannel;
+
import org.apache.commons.io.FileUtils;
import
org.apache.pinot.core.segment.creator.DictionaryBasedInvertedIndexCreator;
import org.apache.pinot.core.segment.creator.impl.V1Constants;
+import org.apache.pinot.core.util.CleanerUtil;
+import org.roaringbitmap.RoaringBitmapWriter;
import org.roaringbitmap.buffer.MutableRoaringBitmap;
+import static java.nio.ByteOrder.LITTLE_ENDIAN;
+
/**
* Implementation of {@link DictionaryBasedInvertedIndexCreator} that uses
on-heap memory.
*/
public final class OnHeapBitmapInvertedIndexCreator implements
DictionaryBasedInvertedIndexCreator {
private final File _invertedIndexFile;
- private final MutableRoaringBitmap[] _bitmaps;
+ private final RoaringBitmapWriter<MutableRoaringBitmap>[] _bitmapWriters;
private int _nextDocId;
+ @SuppressWarnings("unchecked")
public OnHeapBitmapInvertedIndexCreator(File indexDir, String columnName,
int cardinality) {
_invertedIndexFile = new File(indexDir, columnName +
V1Constants.Indexes.BITMAP_INVERTED_INDEX_FILE_EXTENSION);
- _bitmaps = new MutableRoaringBitmap[cardinality];
+ _bitmapWriters = new RoaringBitmapWriter[cardinality];
for (int i = 0; i < cardinality; i++) {
- _bitmaps[i] = new MutableRoaringBitmap();
+ _bitmapWriters[i] = RoaringBitmapWriter.bufferWriter().get();
}
}
@Override
public void add(int dictId) {
- _bitmaps[dictId].add(_nextDocId++);
+ _bitmapWriters[dictId].add(_nextDocId++);
}
@Override
public void add(int[] dictIds, int length) {
for (int i = 0; i < length; i++) {
- _bitmaps[dictIds[i]].add(_nextDocId);
+ _bitmapWriters[dictIds[i]].add(_nextDocId);
}
_nextDocId++;
}
@Override
public void seal()
throws IOException {
- try (DataOutputStream out = new DataOutputStream(
- new BufferedOutputStream(new FileOutputStream(_invertedIndexFile)))) {
+ // calculate file size
+ int size = (_bitmapWriters.length + 1) * Integer.BYTES;
+ for (RoaringBitmapWriter<MutableRoaringBitmap> writer : _bitmapWriters) {
+ size += writer.get().serializedSizeInBytes();
+ // Check for int overflow
+ Preconditions.checkState(size > 0, "Inverted index file: %s exceeds 2GB
limit", _invertedIndexFile);
+ }
+ ByteBuffer buffer = null;
+ try (FileChannel channel = new RandomAccessFile(_invertedIndexFile,
"rw").getChannel()) {
+ buffer = channel.map(FileChannel.MapMode.READ_WRITE, 0,
size).order(LITTLE_ENDIAN);
Review comment:
I chose little endian because roaring bitmaps are always serialised in
little endian byte order anyway, and they make up the bulk of the file. If you
serialise to a `DataOutput` it will reverse every word, and if you serialise to
a big endian `ByteBuffer`, it will just slice the buffer and change the order.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
