[
https://issues.apache.org/jira/browse/HBASE-15967?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15317950#comment-15317950
]
Hiroshi Ikeda commented on HBASE-15967:
---------------------------------------
I think it is enough to queue and pay attention to requests' priority just when
the requests are too many so that most reader threads are going to handle
requests. One or some of reader threads should still remain to accept and
enqueue requests until the queue is full.
The priority or schedule becomes not so useful once the queue becomes full.
Newly coming requests will be left on the native socket's buffer regardless of
their priority. Another port should have been used for the priority purpose.
I'll check HBASE-15971 when I have time but it seems difficult for me so don't
expect much.
> Metric for active ipc Readers and make default fraction of cpu count
> --------------------------------------------------------------------
>
> Key: HBASE-15967
> URL: https://issues.apache.org/jira/browse/HBASE-15967
> Project: HBase
> Issue Type: Sub-task
> Reporter: stack
> Assignee: stack
> Attachments: HBASE-15967.master.001.patch
>
>
> Our ipc Readers are hard coded at 10 regardless since . Running w/ less
> Readers, we go faster..(e.g. 12 Readers has us doing 135k with workloadc and
> 6 readers has us doing 145k).. .but hard to tell what count of Readers are
> needed since no metric.
> This issue changes Readers to be 1/4 the installed CPUs or 8, whichever is
> the minimum, and then adds a new hbase.regionserver.ipc.runningReaders metric
> so you have a chance seeing whats needed.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
