spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From JoshRosen <>
Subject [GitHub] spark pull request: [SPARK-8964] [SQL] [WIP] Use Exchange to perfo...
Date Wed, 03 Feb 2016 22:23:41 GMT
GitHub user JoshRosen reopened a pull request:

    [SPARK-8964] [SQL] [WIP] Use Exchange to perform shuffle in Limit

    Spark SQL's physical Limit operator currently performs its own shuffle rather than using
Exchange to perform the shuffling. This is less efficient since this non-exchange shuffle
path won't be able to benefit from SQL-specific shuffling optimizations, such as SQLSerializer2.
It also involves additional unnecessary row copying.
    Instead, I think that we should rewrite Limit to expand into three physical operators:
    PerParititonLimit -> Exchange to one partition -> PerPartitionLimit

You can merge this pull request into a Git repository by running:

    $ git pull remove-copy-in-limit

Alternatively you can review and apply these changes as the patch at:

To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:

    This closes #7334
commit dfe6ff100ae2efcb1778d93bf828f9e2e8c46e18
Author: Josh Rosen <>
Date:   2015-07-09T22:27:05Z

    Use Exchange in Limit (SPARK-8964)

commit 089f9f5e3153009c35761cde7057af9abcea518c
Author: Josh Rosen <>
Date:   2015-07-13T23:13:12Z

    Merge remote-tracking branch 'origin/master' into remove-copy-in-limit

commit c02324ca36ad7a9cf8df00246d27f6fbfa61b7c0
Author: Josh Rosen <>
Date:   2015-07-13T23:31:12Z

    Use requiredChildDistribution in Limit

commit 70f69b63cfa561e84370fe2553d3f5570ceb488f
Author: Josh Rosen <>
Date:   2015-07-13T23:58:21Z

    Fix test compilation

commit 272c349394f6c53a42c621dce68fc840bcdfac16
Author: Josh Rosen <>
Date:   2015-07-16T00:02:57Z


commit 964838f2b5eb58da06afa18f77a056753e71defc
Author: Josh Rosen <>
Date:   2015-07-16T00:55:07Z

    Fix test

commit cc634566bdaed630c5bfff887f74defd003b4a58
Author: Josh Rosen <>
Date:   2015-07-16T01:05:45Z

    Insert ReturnAnswer before calling physical planner

commit 7dbb28e8fd49d670a3dba02b9470a6b10f8589c3
Author: Josh Rosen <>
Date:   2015-07-16T01:14:43Z

    Fix style

commit 9668c26d1d1ca0f56754353a90f56decd3d8e626
Author: Josh Rosen <>
Date:   2015-07-16T01:50:12Z

    Merge remote-tracking branch 'origin/master' into remove-copy-in-limit

commit 7202e89c7729ea200bb2d1320985e60c93cc968f
Author: Josh Rosen <>
Date:   2015-07-21T01:38:38Z

    Merge remote-tracking branch 'origin/master' into remove-copy-in-limit

commit fc7fe5680d81e964c7fc5a22c30aaa0dc837a854
Author: Josh Rosen <>
Date:   2016-02-03T19:51:37Z

    Merge remote-tracking branch 'origin/master' into remove-copy-in-limit

commit e3caa767517e6df89a058b492d8cfd9fa820a013
Author: Josh Rosen <>
Date:   2016-02-03T20:04:58Z

    Minor test cleanup.

commit cffe4daf218fd5c2a48b84ae831a6b40436a0f62
Author: Josh Rosen <>
Date:   2016-02-03T22:03:02Z

    Refactoring; split classes into separate file; fix tests.

commit 37f66887b35af510c93021e20e30d5d1c0ac696f
Author: Josh Rosen <>
Date:   2016-02-03T22:06:35Z

    Style fix.

commit b4de46737e393f67bac114b6343f968df6bba733
Author: Josh Rosen <>
Date:   2016-02-03T22:23:27Z

    Comments; order-preservation.


If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at or file a JIRA ticket
with INFRA.

To unsubscribe, e-mail:
For additional commands, e-mail:

View raw message