[
https://issues.apache.org/jira/browse/HDDS-3692?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Nanda kumar reassigned HDDS-3692:
---------------------------------
Assignee: Rajesh Balamohan
> Consider avoiding stream/map/sum in write hotpath
> -------------------------------------------------
>
> Key: HDDS-3692
> URL: https://issues.apache.org/jira/browse/HDDS-3692
> Project: Hadoop Distributed Data Store
> Issue Type: Improvement
> Components: Ozone Filesystem
> Reporter: Rajesh Balamohan
> Assignee: Rajesh Balamohan
> Priority: Critical
> Labels: Triaged, performance, pull-request-available
> Fix For: 0.6.0
>
> Attachments: HDDS-3692.1.patch, image-2020-06-01-11-08-08-711.png
>
>
> [https://github.com/apache/hadoop-ozone/blob/master/hadoop-hdds/client/src/main/java/org/apache/hadoop/hdds/scm/storage/BufferPool.java#L113]
>
> {noformat}
> public long computeBufferData() {
> return bufferList.stream().mapToInt(ChunkBuffer::position)
> .sum();
> }
> {noformat}
> [https://github.com/apache/hadoop-ozone/blob/master/hadoop-hdds/client/src/main/java/org/apache/hadoop/hdds/scm/storage/BlockOutputStream.java#L256]
> [https://github.com/apache/hadoop-ozone/blob/master/hadoop-hdds/client/src/main/java/org/apache/hadoop/hdds/scm/storage/BlockOutputStream.java#L264]
> Getting back to regular iteration should fix the issue. This causes 3x CPU
> expensive when compared to HDFS flow.
>
> !image-2020-06-01-11-08-08-711.png|width=777,height=564!
>
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
