[
https://issues.apache.org/jira/browse/HADOOP-14035?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Daryn Sharp updated HADOOP-14035:
---------------------------------
Attachment: HADOOP-14035.branch-2.8.patch
The entire refresh patch isn't needed. 2.8 version of this patch only requires
the change of clientBackOffEnabled from final to volatile and adding a setter
for it.
> Reduce fair call queue backoff's impact on clients
> --------------------------------------------------
>
> Key: HADOOP-14035
> URL: https://issues.apache.org/jira/browse/HADOOP-14035
> Project: Hadoop Common
> Issue Type: Sub-task
> Components: ipc
> Affects Versions: 2.7.0
> Reporter: Daryn Sharp
> Assignee: Daryn Sharp
> Fix For: 2.9.0, 3.0.0-alpha4
>
> Attachments: HADOOP-14035.branch-2.8.patch,
> HADOOP-14035.branch-2.patch, HADOOP-14035.patch
>
>
> When fcq backoff is enabled and an abusive client overflows the call queue,
> its connection is closed, as well as subsequent good client connections.
> Disconnects are very disruptive, esp. to multi-threaded clients with multiple
> outstanding requests, or clients w/o a retry proxy (ex. datanodes).
> Until the abusive user is downgraded to a lower priority queue,
> disconnect/reconnect mayhem occurs which significantly degrades performance.
> Server metrics look good despite horrible client latency.
> The fcq should utilize selective ipc disconnects to avoid pushback
> disconnecting good clients.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
