hadoop-common-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Daryn Sharp (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (HADOOP-14035) Reduce fair call queue backoff's impact on clients
Date Tue, 06 Jun 2017 17:57:18 GMT

     [ 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

This message was sent by Atlassian JIRA

To unsubscribe, e-mail: common-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: common-issues-help@hadoop.apache.org

View raw message