[
https://issues.apache.org/jira/browse/YARN-3612?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Varun Saxena moved MAPREDUCE-4469 to YARN-3612:
-----------------------------------------------
Component/s: (was: performance)
(was: task)
Assignee: Varun Saxena (was: Ahmed Radwan)
Affects Version/s: (was: 1.0.3)
Key: YARN-3612 (was: MAPREDUCE-4469)
Project: Hadoop YARN (was: Hadoop Map/Reduce)
> Resource calculation in child tasks is CPU-heavy
> ------------------------------------------------
>
> Key: YARN-3612
> URL: https://issues.apache.org/jira/browse/YARN-3612
> Project: Hadoop YARN
> Issue Type: Bug
> Reporter: Todd Lipcon
> Assignee: Varun Saxena
> Labels: BB2015-05-TBR
> Attachments: MAPREDUCE-4469.patch, MAPREDUCE-4469_rev2.patch,
> MAPREDUCE-4469_rev3.patch, MAPREDUCE-4469_rev4.patch,
> MAPREDUCE-4469_rev5.patch
>
>
> In doing some benchmarking on a hadoop-1 derived codebase, I noticed that
> each of the child tasks was doing a ton of syscalls. Upon stracing, I noticed
> that it's spending a lot of time looping through all the files in /proc to
> calculate resource usage.
> As a test, I added a flag to disable use of the ResourceCalculatorPlugin
> within the tasks. On a CPU-bound 500G-sort workload, this improved total job
> runtime by about 10% (map slot-seconds by 14%, reduce slot seconds by 8%)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
