GitHub user viirya opened a pull request:

    [SPARK-17574][Core] Cache ShuffleExchange RDD when the exchange is reused

    ## What changes were proposed in this pull request?
    We have the rule `ReuseExchange` to reuse exchange in the physical plan. 
However, for a `ShuffleExchange` we still need to retrieve remote blocks again 
when the shuffle exchange is reused. We can cache the RDD of the reused 
`ShuffleExchange` to avoid transferring remote blocks again.
    ## How was this patch tested?
    Manual tests. This patch can avoid transferring remote blocks again when a 
shuffle exchange is reused.

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

    $ git pull cache-reused-shuffle

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 #15128
commit cbbaf318ecb9e21df464f487dd4dbb37ceee3923
Author: Liang-Chi Hsieh <>
Date:   2016-09-17T09:34:20Z

    Cache ShuffleExchange RDD when the exchange is reused.


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:

Reply via email to