hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Ravi Prakash (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (YARN-6889) The throughput of timeline server is too small
Date Thu, 27 Jul 2017 17:12:00 GMT

    [ https://issues.apache.org/jira/browse/YARN-6889?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16103517#comment-16103517

Ravi Prakash commented on YARN-6889:

Also, it would be good if you can publish your methodology and results for the tests you did.

> The throughput of timeline server is too small
> ----------------------------------------------
>                 Key: YARN-6889
>                 URL: https://issues.apache.org/jira/browse/YARN-6889
>             Project: Hadoop YARN
>          Issue Type: Improvement
>          Components: timelineserver
>            Reporter: YunFan Zhou
>            Priority: Critical
> Recent large-scale pressure test single timeline server, and I found the throughput of
timeline server is too small.
> I setup multiple servers, and each of them setup multiple processes. Each process was
setup up multiple threads, I send different data size with each thread.
> Although I use different pressures and different scenarios. But the timeline server processing
power is basically similar, and 
> the ability to process messages is about 70 per second.
> It can't meet our requirements, we should improve it.

This message was sent by Atlassian JIRA

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

View raw message