[
https://issues.apache.org/jira/browse/MAHOUT-1573?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14036699#comment-14036699
]
ASF GitHub Bot commented on MAHOUT-1573:
----------------------------------------
Github user tdunning commented on the pull request:
https://github.com/apache/mahout/pull/13#issuecomment-46509984
Uh... what happened to waiting a bit for feedback?
On Wed, Jun 18, 2014 at 1:26 PM, Dmitriy Lyubimov <[email protected]>
wrote:
> Thanks.
>
> +1 on par(...) too. Great, i will engineer the fix and commit then.
>
>
> On Wed, Jun 18, 2014 at 1:20 PM, Sebastian <[email protected]>
> wrote:
>
> > I dont like the _|| because it looks like a mathematical operation and
> is
> > not intuitive IMHO. I prefer something that looks like an annotation to
> the
> > code and is human readable. So I vote for the .par() syntax
> >
> > —
> > Reply to this email directly or view it on GitHub
> > <https://github.com/apache/mahout/pull/13#issuecomment-46488559>.
> >
>
> —
> Reply to this email directly or view it on GitHub
> <https://github.com/apache/mahout/pull/13#issuecomment-46489240>.
>
> More explicit parallelism adjustments in math-scala DRM apis; elements of
> automatic parallelism management
> ----------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-1573
> URL: https://issues.apache.org/jira/browse/MAHOUT-1573
> Project: Mahout
> Issue Type: Task
> Affects Versions: 0.9
> Reporter: Dmitriy Lyubimov
> Assignee: Dmitriy Lyubimov
> Fix For: 1.0
>
>
> (1) add minSplit parameter pass-thru to drmFromHDFS to be able to explicitly
> increase parallelism.
> (2) add parrallelism readjustment parameter to a checkpoint() call. This
> implies shuffle-less coalesce() translation to the data set before it is
> requested to be cached (if specified).
> Going forward, we probably should try and figure how we can automate it, at
> least a little bit. For example, the simplest automatic adjustment might
> include re-adjust parallelims on load to simply fit cluster size (95% or 180%
> of cluster size, for example), with some rule-of-thumb safeguards here, e.g.
> we cannot exceed a factor of say 8 (or whatever we configure) in splitting
> each original hdfs split. We should be able to get a reasonable parallelism
> performance out of the box on simple heuristics like that.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
