[
https://issues.apache.org/jira/browse/HDFS-6967?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14125940#comment-14125940
]
Chris Nauroth commented on HDFS-6967:
-------------------------------------
I was assuming that the impact of the Jetty queue largely dominates over the
impact of any other objects, based on my reading of the Jetty 6
{{QueuedThreadPool}} code. Of course, you know best what you're seeing in
practice from {{jmap}} output (or whatever). Overall, your proposal sounds
good to me.
> DNs may OOM under high webhdfs load
> -----------------------------------
>
> Key: HDFS-6967
> URL: https://issues.apache.org/jira/browse/HDFS-6967
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: datanode, webhdfs
> Affects Versions: 2.0.0-alpha, 3.0.0
> Reporter: Daryn Sharp
> Assignee: Eric Payne
>
> Webhdfs uses jetty. The size of the request thread pool is limited, but
> jetty will accept and queue infinite connections. Every queued connection is
> "heavy" with buffers, etc. Unlike data streamer connections, thousands of
> webhdfs connections will quickly OOM a DN. The accepted requests must be
> bounded and excess clients rejected so they retry on a new DN.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
