hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Bibin A Chundatt (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (MAPREDUCE-6465) NNBench result wrong when number of reducers greater than 1
Date Tue, 01 Sep 2015 11:51:46 GMT

    [ https://issues.apache.org/jira/browse/MAPREDUCE-6465?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14725263#comment-14725263
] 

Bibin A Chundatt commented on MAPREDUCE-6465:
---------------------------------------------

Test case failure is not related to this only file rename was done
https://builds.apache.org/job/PreCommit-MAPREDUCE-Build/5960/testReport/ is passing.

> NNBench result wrong when number of reducers greater than 1
> -----------------------------------------------------------
>
>                 Key: MAPREDUCE-6465
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-6465
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>            Reporter: Bibin A Chundatt
>            Assignee: Bibin A Chundatt
>         Attachments: 0001-HDFS-8977.patch, 0002-MAPREDUCE-6465.patch
>
>
> Currently NNBench#analyzeResults consider only the part-0000 for analysis
> {code}
>                 TPS: Create/Write/Close: 0
>  Avg exec time (ms): Create/Write/Close: Infinity
>              Avg Lat (ms): Create/Write: Infinity
>                     Avg Lat (ms): Close: NaN
> {code}
> Should consider all part files for output.
> or disable reduces option



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message