[
https://issues.apache.org/jira/browse/HADOOP-1432?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12504259
]
Raghu Angadi commented on HADOOP-1432:
--------------------------------------
I don't know details of original perf problem but do you think multiple
selectors helps? I guess it pretty much only does epoll() (and may be
accept()), does not actually read or write connections. But I could be wrong.
On RedHat Enterprise Linux even with pretty recent kernel, Linux we found that
depending on kernel to remove an fd from epoll does not work well under load.
Sun bugzilla seems to indicate they want to have this "optimization"
> Use Grizzly for Fetching Map Output in Shuffle
> ----------------------------------------------
>
> Key: HADOOP-1432
> URL: https://issues.apache.org/jira/browse/HADOOP-1432
> Project: Hadoop
> Issue Type: Improvement
> Components: mapred
> Reporter: Tahir Hashmi
> Assignee: Tahir Hashmi
> Attachments: 1432.patch, grizzly.tgz
>
>
> As mentioned in HADOOP-1273 and references therefrom, Jetty 6 still doesn't
> seem to be stable enough for use in Hadoop. Instead, we've decided to
> consider the usage of Grizzly Framework [https://grizzly.dev.java.net/] for
> NIO based communication.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
