You are viewing a plain text version of this content. The canonical link for it is here.
Posted to mapreduce-issues@hadoop.apache.org by "Luke Lu (JIRA)" <ji...@apache.org> on 2012/07/05 12:21:36 UTC

[jira] [Created] (MAPREDUCE-4399) Fix performance regression in shuffle

Luke Lu created MAPREDUCE-4399:
----------------------------------

             Summary: Fix performance regression in shuffle 
                 Key: MAPREDUCE-4399
                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
             Project: Hadoop Map/Reduce
          Issue Type: Bug
          Components: tasktracker
    Affects Versions: 1.0.3, 0.20.203.0
            Reporter: Luke Lu
            Assignee: Luke Lu


There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Updated] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Arun C Murthy (JIRA)" <ji...@apache.org>.
     [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Arun C Murthy updated MAPREDUCE-4399:
-------------------------------------

    Comment: was deleted

(was: The crux of the problem is jetty 6.1.26's internal buffer management with transfer-encoding = trunked. The issue was also independently discovered and analyzed elsewhere:  http://goo.gl/dtM4D

The patch is trivial.)
    
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Updated] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Suresh Srinivas (JIRA)" <ji...@apache.org>.
     [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Suresh Srinivas updated MAPREDUCE-4399:
---------------------------------------

    Component/s: performance
    
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: performance, tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Commented] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Luke Lu (JIRA)" <ji...@apache.org>.
    [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13406967#comment-13406967 ] 

Luke Lu commented on MAPREDUCE-4399:
------------------------------------

Thanks to John Poelman and Shreyas Subramanya of IBM BigInsights performance QA for noticing the issue and verifying my fix.
                
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Commented] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Luke Lu (JIRA)" <ji...@apache.org>.
    [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13408411#comment-13408411 ] 

Luke Lu commented on MAPREDUCE-4399:
------------------------------------

Oops: the link should be: http://goo.gl/Wln7Z
                
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Commented] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Matt Foley (JIRA)" <ji...@apache.org>.
    [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13421624#comment-13421624 ] 

Matt Foley commented on MAPREDUCE-4399:
---------------------------------------

Committed to branch-1.1 and branch-1.0.  Thanks, Luke!
                
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: performance, tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Updated] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Matt Foley (JIRA)" <ji...@apache.org>.
     [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Matt Foley updated MAPREDUCE-4399:
----------------------------------

    Fix Version/s: 1.1.0
    
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: performance, tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>             Fix For: 1.1.0
>
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Resolved] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Suresh Srinivas (JIRA)" <ji...@apache.org>.
     [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Suresh Srinivas resolved MAPREDUCE-4399.
----------------------------------------

      Resolution: Fixed
    Hadoop Flags: Reviewed

I committed the patch to branch-1 and for 1.1.0. 

Thank you Luke for the patch. Thank you John Poelman and Shreyas Subramanya for noticing the issue and verifying the fix.
                
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: performance, tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Updated] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Matt Foley (JIRA)" <ji...@apache.org>.
     [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Matt Foley updated MAPREDUCE-4399:
----------------------------------

    Fix Version/s:     (was: 1.1.0)
                   1.0.4
    
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: performance, tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>             Fix For: 1.0.4
>
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

[jira] [Updated] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Matt Foley (JIRA)" <ji...@apache.org>.
     [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Matt Foley updated MAPREDUCE-4399:
----------------------------------

    Target Version/s: 1.0.4  (was: 1.1.0)
    
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: performance, tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>             Fix For: 1.1.0
>
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

[jira] [Commented] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Suresh Srinivas (JIRA)" <ji...@apache.org>.
    [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13419409#comment-13419409 ] 

Suresh Srinivas commented on MAPREDUCE-4399:
--------------------------------------------

Nicholas, can you please verify if this is an issue for WebHDFS (both on 1.0 and trunk?)
                
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: performance, tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Commented] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Suresh Srinivas (JIRA)" <ji...@apache.org>.
    [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13419397#comment-13419397 ] 

Suresh Srinivas commented on MAPREDUCE-4399:
--------------------------------------------

Given the code is the same, this may not be regression compared to 0.20.2. However, this is straightforward change, and given the link you posted, I am +1 on committing this.
                
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: performance, tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Updated] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Luke Lu (JIRA)" <ji...@apache.org>.
     [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Luke Lu updated MAPREDUCE-4399:
-------------------------------

    Attachment: mapreduce-4399-branch-1.patch

The crux of the problem is jetty 6.1.26's internal buffer management with transfer-encoding = trunked. The issue was also independently discovered and analyzed elsewhere:  http://goo.gl/dtM4D

The patch is trivial.
                
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Updated] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Arun C Murthy (JIRA)" <ji...@apache.org>.
     [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Arun C Murthy updated MAPREDUCE-4399:
-------------------------------------

    Comment: was deleted

(was: Oops: the link should be: http://goo.gl/Wln7Z)
    
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Commented] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Luke Lu (JIRA)" <ji...@apache.org>.
    [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13408555#comment-13408555 ] 

Luke Lu commented on MAPREDUCE-4399:
------------------------------------

The crux of the problem is jetty 6.1.26's internal buffer management with transfer-encoding = chunked. The issue was also independently discovered and analyzed elsewhere: http://goo.gl/Wln7Z
                
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

[jira] [Commented] (MAPREDUCE-4399) Fix performance regression in shuffle

Posted by "Luke Lu (JIRA)" <ji...@apache.org>.
    [ https://issues.apache.org/jira/browse/MAPREDUCE-4399?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13419454#comment-13419454 ] 

Luke Lu commented on MAPREDUCE-4399:
------------------------------------

@Suresh, 0.20.2 use jetty 6.1.14, which doesn't have this particular issue. This is a workaround specifically for jetty 6.1.26 and harmless for other versions.
                
> Fix performance regression in shuffle 
> --------------------------------------
>
>                 Key: MAPREDUCE-4399
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4399
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: performance, tasktracker
>    Affects Versions: 0.20.203.0, 1.0.3
>            Reporter: Luke Lu
>            Assignee: Luke Lu
>         Attachments: mapreduce-4399-branch-1.patch
>
>
> There is a significant (up to 3x) performance regression in shuffle (vs 0.20.2) in the Hadoop 1.x series. Most noticeable with high-end switches.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira