[
https://issues.apache.org/jira/browse/HADOOP-2014?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12566911#action_12566911
]
eric baldeschwieler commented on HADOOP-2014:
---------------------------------------------
of course since blocks are on multiple racks, pulling blocks from overloaded
racks may be a bad strategy... Why not execute them locally on another rack...
Also in the interest of IO interleaving, you want to do some amount of off rack
reading early and not wait until the job is guarantied to be the long pole.
My bet is that some amount of pre planning is going to prove necessary to get a
semi optimal plan. Maybe generating a sorted list of blocks to choose per
spindle on a node and than one per rack and then a final remote list. That
plus some sort of % off rack target might be good. You could store this very
efficiently or on disk...
> Job Tracker should prefer input-splits from overloaded racks
> ------------------------------------------------------------
>
> Key: HADOOP-2014
> URL: https://issues.apache.org/jira/browse/HADOOP-2014
> Project: Hadoop Core
> Issue Type: Bug
> Components: mapred
> Reporter: Runping Qi
> Assignee: Devaraj Das
>
> Currently, when the Job Tracker assigns a mapper task to a task tracker and
> there is no local split to the task tracker, the
> job tracker will find the first runable task in the mast task list and
> assign the task to the task tracker.
> The split for the task is not local to the task tracker, of course. However,
> the split may be local to other task trackers.
> Assigning the that task, to that task tracker may decrease the potential
> number of mapper attempts with data locality.
> The desired behavior in this situation is to choose a task whose split is not
> local to any task tracker.
> Resort to the current behavior only if no such task is found.
> In general, it will be useful to know the number of task trackers to which
> each split is local.
> To assign a task to a task tracker, the job tracker should first try to pick
> a task that is local to the task tracker and that has minimal number of task
> trackers to which it is local. If no task is local to the task tracker, the
> job tracker should try to pick a task that has minimal number of task
> trackers to which it is local.
> It is worthwhile to instrument the job tracker code to report the number of
> splits that are local to some task trackers.
> That should be the maximum number of tasks with data locality. By comparing
> that number with the the actual number of
> data local mappers launched, we can know the effectiveness of the job tracker
> scheduling.
> When we introduce rack locality, we should apply the same principle.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
