[
https://issues.apache.org/jira/browse/HADOOP-3412?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12613771#action_12613771
]
Matei Zaharia commented on HADOOP-3412:
---------------------------------------
bq. an api to the scheduler that breaks down the queues and order within the
queue, because the scheduler is the only place that has the order of jobs
within the queue.
What other pieces of code needs to use order within a queue except the
scheduler? In fact, I think "order within a queue" doesn't even make sense for
all schedulers. Some schedulers, such as the fair scheduler in HADOOP-3746,
make all jobs runnable as soon as they are submitted and give them different
fractions of the cluster.
Similarly, I don't understand what getQueueNames() would be used for by pieces
of code external to the scheduler. In fact, if the list of jobs is stored in
the JobTracker (which I think we've said it should be), then the JobTracker has
all the information it needs to figure out the queue names - it can scan
through all jobs and get the queue name of each one from its getQueueName().
Basically the scheduler should be a box whose only "output" is to assign a
task, and whose only "input" is whatever state of the world it needs to know
about in order to do its job (i.e. events for jobs being modified, etc). That
makes it possible to separate the code that persists jobs from the code that
schedules them.
> 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-v10.patch, 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.
