[
https://issues.apache.org/jira/browse/HBASE-22387?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16850565#comment-16850565
]
Anoop Sam John commented on HBASE-22387:
----------------------------------------
This is good.. So the throughput is a stable line now. Also the p99 and even
the max latency is much under control.
bq.We use the default hbase.ipc.server.allocator.buffer.size=64KB here, as
HBASE-22483 said, I will have a benchmark by setting the buffer.size=65KB,
should be better performance.
Ya will be good to see that.
> Evaluate the get/scan performance after reading HFile block into offheap
> directly
> ---------------------------------------------------------------------------------
>
> Key: HBASE-22387
> URL: https://issues.apache.org/jira/browse/HBASE-22387
> Project: HBase
> Issue Type: Sub-task
> Reporter: Zheng Hu
> Assignee: Zheng Hu
> Priority: Major
> Attachments: G1GC-stage-stw.case01.png,
> G1GC-stage-stw.case02-with-buffer-size-64KB.png, G1GC-stw.case01.png,
> G1GC-stw.case02-with-buffer-size-64KB.png, QPS-latency.case01.png,
> QPS-latency.case02-with-buffer-size-64KB.png, blockReaderRemote.png,
> blocksByHFile-stack-trace.png, screenshot-1.png,
> test-cluster-configuration-details.png
>
>
> Now, all sub-tasks has been resolved now (except the HBASE-21946 because of
> the hadoop dependency problem), will provide some performance benckmarks to
> show the latency improvement.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
