hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Vivek Ratan (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-3412) Refactor the scheduler out of the JobTracker
Date Mon, 14 Jul 2008 05:03:32 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-3412?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12613241#action_12613241
] 

Vivek Ratan commented on HADOOP-3412:
-------------------------------------

*@Matei:*
bq. I'm still not sure I understand why jobAdded and jobRemoved should not be in the TaskScheduler.
It's true that persistence of jobs should be managed by the JobQueueManager, but these methods
are meant to be "listeners" [...]

After some thought, I'm unable to convincingly argue, even to myself, for the removal of the
methods from _TaskScheduler_. 

My concern really was with state. On one hand, I see the Scheduler as a stateless algorithm.
The information it needs about jobs, when it runs, it gets from some other class. I was worried
about any class that extends _TaskScheduler_ having to maintain its own data structures for
jobs, while a class like _JobQueueManager_ is also maintaining (similar?) structures. On the
other hand, I see your point too - for efficiency, a scheduler may want to know about what's
changed since it ran last, rather than look at the entire set of jobs each time. A scheduler
can certainly cache what information it needs (and maybe even support listener methods as
you've suggested) if performance becomes an issue, but there is a state that it imposes on
the system - it orders jobs a certain way (one scheduler may order jobs in FIFO order, another
may choose a different ordering) - and perhaps this state is inherent to the scheduler. 

Like I said, I can't see a very strong reason for removing the job methods from _TaskScheduler_,
so let's leave them there. 

> Refactor the scheduler out of the JobTracker
> --------------------------------------------
>
>                 Key: HADOOP-3412
>                 URL: https://issues.apache.org/jira/browse/HADOOP-3412
>             Project: Hadoop Core
>          Issue Type: Improvement
>          Components: mapred
>            Reporter: Brice Arnould
>            Assignee: Brice Arnould
>            Priority: Minor
>             Fix For: 0.19.0
>
>         Attachments: JobScheduler-v9.1.patch, JobScheduler-v9.2.patch, JobScheduler-v9.patch,
JobScheduler.patch, JobScheduler_v2.patch, JobScheduler_v3.patch, JobScheduler_v3b.patch,
JobScheduler_v4.patch, JobScheduler_v5.patch, JobScheduler_v6.1.patch, JobScheduler_v6.2.patch,
JobScheduler_v6.3.patch, JobScheduler_v6.4.patch, JobScheduler_v6.patch, JobScheduler_v7.1.patch,
JobScheduler_v7.patch, JobScheduler_v8.patch, RackAwareJobScheduler.java, SimpleResourceAwareJobScheduler.java
>
>
> First I would like warn you that my proposition is assumed to be very naive. I just hope
that reading it won't make you lose time.
> h4. The aim
> It seems to me that improving Hadoop scheduling could be very profitable. But, it is
hard to implement and compare schedulers, because the scheduling logic is mixed within the
rest of the JobTracker.
> This bug is the first step of an attempt to improve the Hadoop scheduler. It re-implements
the current scheduling algorithm in a separate class called JobScheduler. This new class is
instantiated in the JobTracker.
> h4. Bug fixed as a side effects
> This patch probably cannot be submited as it is.
> A first difficulty is that it does not have exactly the same behaviour than the current
JobTracker. More precisely, it doesn't re-implement things like code that seems to be never
called or concurency problems.
> I wrote TOCONFIRM where my proposition differ from the current implementation, so you
can find them easily.
> I know that fixing bugs silently is bad. So, independently of what you decide about this
patch, I will open issues for bugs that you confirm.
> h4. Other side effects
> Another side effect of this patch is to add documentation about each step of the scheduling.
I hope that it will help future improvement by lowering the level required to contribute to
the scheduler.
> It also reduces the complexity and the granularity of the JobTracker (making it more
parallel).
> h4. The future
> If you feel that this is a step the right direction, I will try to propose a JobSchedulerInterface
that many JobSchedulers could implement and to propose alternatives to the current « FifoJobScheduler
».  If some of you have ideas about that please tell ^^ I will also open issues for things
marked as FIXME in the patch.

-- 
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