[
https://issues.apache.org/jira/browse/HDFS-17364?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17824398#comment-17824398
]
ASF GitHub Bot commented on HDFS-17364:
---------------------------------------
Hexiaoqiao commented on code in PR #6514:
URL: https://github.com/apache/hadoop/pull/6514#discussion_r1516099526
##########
hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/client/HdfsClientConfigKeys.java:
##########
@@ -530,6 +530,9 @@ interface StripedRead {
* span 6 DNs, so this default value accommodates 3 read streams
*/
int THREADPOOL_SIZE_DEFAULT = 18;
+
+ String WEAK_REF_BUFFER_POOL_KEY = PREFIX +
"bufferpool.weak.references.enabled";
+ boolean WEAK_REF_BUFFER_POOL_DEFAULT = false;
Review Comment:
Please also add this default config to core-default.xml.
##########
hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/DFSClient.java:
##########
@@ -3159,6 +3165,21 @@ private void initThreadsNumForStripedReads(int
numThreads) {
}
}
+ private void initBufferPoolForStripedReads(boolean useWeakReference) {
+ if (STRIPED_READ_BUFFER_POOL != null) {
+ return;
+ }
+ synchronized (DFSClient.class) {
Review Comment:
What this `synchronized` would like to protect?
> Use WeakReferencedElasticByteBufferPool in DFSStripedInputStream
> ----------------------------------------------------------------
>
> Key: HDFS-17364
> URL: https://issues.apache.org/jira/browse/HDFS-17364
> Project: Hadoop HDFS
> Issue Type: Improvement
> Reporter: Bryan Beaudreault
> Priority: Major
> Labels: pull-request-available
>
> DFSStripedInputStream uses ElasticByteBufferPool to allocate byte buffers for
> the "curStripeBuf". This is used for non-positional (stateful) reads and is
> allocated with a size of numDataBlocks * cellSize. For RS-6-3-1024k, that
> means each DFSStripedInputStream could allocate a 6mb buffer. When the IS is
> finished, the buffer is put back in the pool. Over time and with spikes of
> concurrent reads, the pool grows and most of the buffers sit there unused.
>
> WeakReferencedElasticByteBufferPool was introduced HADOOP-18105 and mitigates
> this issue because the excess buffers can be GC'd once they are no longer
> needed. We should use this same pool in DFSStripedInputStream
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
