[ 
https://issues.apache.org/jira/browse/MAPREDUCE-6465?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14733548#comment-14733548
 ] 

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

Hi [~ozawa] & [~ajisakaa]
Could you please review patch attached.

> 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)

Reply via email to