[jira] [Commented] (MAPREDUCE-2062) speculative execution is too aggressive under certain conditions

["Joydeep Sen Sarma (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/MAPREDUCE-2062?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14080457#comment-14080457 ] 

Joydeep Sen Sarma commented on MAPREDUCE-2062:
----------------------------------------------

can someone point me to where it got done elsewhere?

note - as the title states - this was after incorporating HADOOP-2141 which was the major overhaul of speculative exeution

> speculative execution is too aggressive under certain conditions
> ----------------------------------------------------------------
>
>                 Key: MAPREDUCE-2062
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-2062
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: jobtracker
>         Environment: hadoop-20 with HADOOP-2141
>            Reporter: Joydeep Sen Sarma
>
> The function canBeSpeculated has subtle bugs that cause too much speculation in certain cases.
> - it compares the current progress of the task with the last observed mean of all the tasks. if only one task is in question - then the progress rate decays as time progresses (in the absence of updates) and std-dev is zero. So a job with a single reducer or mapper is almost always speculated.
> - is only a single task has reported progress - then the stddev is zero. so other tasks may be speculated aggressively.
> - several tasks take a while to report progress initially. they seem to get speculated as soon as speculative-lag is over. the lag should be configurable at the minimum.



--
This message was sent by Atlassian JIRA
(v6.2#6252)