[
https://issues.apache.org/jira/browse/HADOOP-10278?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13898102#comment-13898102
]
Daryn Sharp commented on HADOOP-10278:
--------------------------------------
bq. Significant increase in client CPU for 1000ms poll vs trunk (1.2%, p=0.03)
Hmm, why does client cpu increase? The client is just blocked reading its
socket waiting for a call response. I could maybe understand a slight client
call latency increase from the -0.2% throughput, but cpu?
Hiroshi points out a valid race, much like handlers possibly consuming one more
call, readers can insert one more. Might need to do drainTo until isEmpty,
need to think about it.
> Refactor to make CallQueue pluggable
> ------------------------------------
>
> Key: HADOOP-10278
> URL: https://issues.apache.org/jira/browse/HADOOP-10278
> Project: Hadoop Common
> Issue Type: Sub-task
> Components: ipc
> Reporter: Chris Li
> Attachments: HADOOP-10278-atomicref.patch,
> HADOOP-10278-atomicref.patch, HADOOP-10278-atomicref.patch, HADOOP-10278.patch
>
>
> * Refactor CallQueue into an interface, base, and default implementation that
> matches today's behavior
> * Make the call queue impl configurable, keyed on port so that we minimize
> coupling
--
This message was sent by Atlassian JIRA
(v6.1.5#6160)
