[
https://issues.apache.org/jira/browse/HBASE-7633?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13563195#comment-13563195
]
Elliott Clark commented on HBASE-7633:
--------------------------------------
That's exactly what call queue length would have shown. It would normally show
0 and then as things get slower the queue length would grow as it approaches
the max of ~500.
The way I see it having all ipc threads full isn't a bad thing. If the threads
are answering requests at the same rate as they are coming in then having all
the threads answering something is just fine. The bad part was that they were
all full and the number of requests waiting to be answered was growing. hence
the callQueueLength was what I would look at.
> Add a metric that tracks the current number of used RPC threads on the
> regionservers
> ------------------------------------------------------------------------------------
>
> Key: HBASE-7633
> URL: https://issues.apache.org/jira/browse/HBASE-7633
> Project: HBase
> Issue Type: Improvement
> Components: metrics
> Reporter: Joey Echeverria
> Assignee: Elliott Clark
>
> One way to detect that you're hitting a "John Wayne" disk[1] would be if we
> could see when region servers exhausted their RPC handlers. This would also
> be useful when tuning the cluster for your workload to make sure that reads
> or writes were not starving the other operations out.
> [1] http://hbase.apache.org/book.html#bad.disk
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
