[
https://issues.apache.org/jira/browse/MAPREDUCE-712?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12727818#action_12727818
]
Hong Tang commented on MAPREDUCE-712:
-------------------------------------
Besides profiling, I guess two other things you might want to try to ensure the
problems are not in either DFS or the specific input format you are using:
- Run TestDFSIO benchmark to see make sure hdfs layer does not consume all the
cpus.
- Use a dummier writer that simply writes zeros to the files instead of wasting
time generating random text keys and values (which uses StringBuffer and does
UTF8 convertions).
> TextWritter example is CPU bound!!
> ----------------------------------
>
> Key: MAPREDUCE-712
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-712
> Project: Hadoop Map/Reduce
> Issue Type: Improvement
> Components: task
> Affects Versions: 0.20.1, 0.21.0
> Environment: ~200 nodes cluster
> Each node has the following configuration:
> Processors: 2 x Xeon L5420 2.50GHz (8 cores) - Harpertown C0, 64-bit,
> quad-core (8 CPUs)
> 4 Disks
> 16 GB RAM
> Linux 2.6
> Hadoop version: trunk
> Reporter: Khaled Elmeleegy
>
> Running the RandomTextWritter example job ( from the examples jar) pegs the
> machiens' CPUs.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
