Apache
/
hbase
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

HBASE-18116 fix replication source in-memory calculation by excluding bulk load file 

Signed-off-by: Andrew Purtell <apurtell@apache.org>
Amending-Author: Andrew Purtell <apurtell@apache.org>
This commit is contained in:
Xu Cang 2018-05-25 16:46:42 -07:00 committed by Andrew Purtell
parent 4b63557682
commit dcb5b5a012
1 changed files with 15 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
hbase-server/src/main/java/org/apache/hadoop/hbase/replication/regionserver/ReplicationSourceWALReaderThread.java
View File

@ -39,17 +39,16 @@ import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.HConstants;
import org.apache.hadoop.hbase.classification.InterfaceAudience;
import org.apache.hadoop.hbase.classification.InterfaceStability;
import org.apache.hadoop.hbase.protobuf.generated.WALProtos;
import org.apache.hadoop.hbase.protobuf.generated.WALProtos.BulkLoadDescriptor;
import org.apache.hadoop.hbase.protobuf.generated.WALProtos.StoreDescriptor;
import org.apache.hadoop.hbase.regionserver.wal.WALEdit;
import org.apache.hadoop.hbase.replication.ReplicationQueueInfo;
import org.apache.hadoop.hbase.replication.WALEntryFilter;
import org.apache.hadoop.hbase.replication.regionserver.WALEntryStream.WALEntryStreamRuntimeException;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.hbase.util.Pair;
import org.apache.hadoop.hbase.util.Threads;
import org.apache.hadoop.hbase.wal.WAL.Entry;
import org.apache.hadoop.hbase.wal.WALKey;
/**
* Reads and filters WAL entries, groups the filtered entries into batches, and puts the batches onto a queue
@ -145,10 +144,11 @@ public class ReplicationSourceWALReaderThread extends Thread {
if (entry != null) {
WALEdit edit = entry.getEdit();
if (edit != null && !edit.isEmpty()) {
long entrySize = getEntrySize(entry);
long entrySize = getEntrySizeIncludeBulkLoad(entry);
long entrySizeExlucdeBulkLoad = getEntrySizeExcludeBulkLoad(entry);
batch.addEntry(entry);
updateBatchStats(batch, entry, entryStream.getPosition(), entrySize);
boolean totalBufferTooLarge = acquireBufferQuota(entrySize);
boolean totalBufferTooLarge = acquireBufferQuota(entrySizeExlucdeBulkLoad);
// Stop if too many entries or too big
if (totalBufferTooLarge || batch.getHeapSize() >= replicationBatchSizeCapacity
|| batch.getNbEntries() >= replicationBatchCountCapacity) {
@ -251,9 +251,17 @@ public class ReplicationSourceWALReaderThread extends Thread {
return entryBatchQueue.take();
}
private long getEntrySize(Entry entry) {
private long getEntrySizeIncludeBulkLoad(Entry entry) {
WALEdit edit = entry.getEdit();
return edit.heapSize() + calculateTotalSizeOfStoreFiles(edit);
WALKey key = entry.getKey();
return edit.heapSize() + sizeOfStoreFilesIncludeBulkLoad(edit) +
key.estimatedSerializedSizeOf();
}
private long getEntrySizeExcludeBulkLoad(Entry entry) {
WALEdit edit = entry.getEdit();
WALKey key = entry.getKey();
return edit.heapSize() + key.estimatedSerializedSizeOf();
}
private void updateBatchStats(WALEntryBatch batch, Entry entry, long entryPosition, long entrySize) {
@ -311,7 +319,7 @@ public class ReplicationSourceWALReaderThread extends Thread {
* @param edit edit to count row keys from
* @return the total size of the store files
*/
private int calculateTotalSizeOfStoreFiles(WALEdit edit) {
private int sizeOfStoreFilesIncludeBulkLoad(WALEdit edit) {
List<Cell> cells = edit.getCells();
int totalStoreFilesSize = 0;