hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Joydeep Sen Sarma (JIRA)" <j...@apache.org>
Subject [jira] Commented: (MAPREDUCE-2205) FairScheduler should only preempt tasks for pools/jobs that are up next for scheduling
Date Tue, 30 Nov 2010 22:14:12 GMT

    [ https://issues.apache.org/jira/browse/MAPREDUCE-2205?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12965456#action_12965456
] 

Joydeep Sen Sarma commented on MAPREDUCE-2205:
----------------------------------------------

> we have to prioritize giving tasks to jobs that have required preemption

i don't follow - the fairsharecomparator is supposed to be doing this already. if not - we
have a bigger problem on our hand. jobs that are furthest behind in fair/min share are at
the head of the sorted list based on fairsharecomparator. the only reason a different set
of jobs gets rights to preemption is because the tasksToPreempt() call is not using fairsharecomparator
logic. if it was - there would be no problem to begin with. 

can u explain why the fairsharecomparator is not doing the correct thing already?

a simple way of getting past the re-ordering issue is to invoke tasksToPreempt() very very
frequently and make N (the max number of tasks to preempt) really small. I would hazard to
say we can even do this every heartbeat (since we have a sorted list - we only need to see
if the head of the queue needs preemption).

> FairScheduler should only preempt tasks for pools/jobs that are up next for scheduling
> --------------------------------------------------------------------------------------
>
>                 Key: MAPREDUCE-2205
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-2205
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: contrib/fair-share
>            Reporter: Joydeep Sen Sarma
>
> We have hit a problem with the preemption implementation in the FairScheduler where the
following happens:
> # job X runs short of fair share or min share and requests/causes N tasks to be preempted
> # when slots are then scheduled - tasks from some other job are actually scheduled
> # after preemption_interval has passed, job X finds it's still underscheduled and requests
preemption. goto 1.
> This has caused widespread preemption of tasks and the cluster going from high utilization
to low utilization in a few minutes.
> Some of the problems are specific to our internal version of hadoop (still 0.20 and doesn't
have the hierarchical FairScheduler) - but i think the issue here is generic (just took a
look at the trunk assignTasks and tasksToPreempt routines). The basic problem seems to be
that the logic of assignTasks+FairShareComparator is not consistent with the logic in tasksToPreempt().
The latter can choose to preempt tasks on behalf of jobs that may not be first up for scheduling
based on the FairComparator. Understanding whether these two separate pieces of logic are
consistent and keeping it that way is difficult.
> It seems that a much safer preemption implementation is to walk the jobs in the order
they would be scheduled on the next heartbeat - and only preempt for jobs that are at the
head of this sorted queue. In MAPREDUCE-2048 - we have already introduced a pre-sorted list
of jobs ordered by current scheduling priority. It seems much easier to preempt only jobs
at the head of this sorted list.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message