You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by viirya <gi...@git.apache.org> on 2016/09/16 04:32:09 UTC

[GitHub] spark issue #11403: [SPARK-13523] [SQL] Reuse exchanges in a query

Github user viirya commented on the issue:

    https://github.com/apache/spark/pull/11403
  
    @davies I have a question about this. Maybe you have the answer for it? Thanks.
    
    For a shuffle, although `ShuffleExchange` returns a cached `ShuffledRowRDD` so `ReusedExchangeExec` can reuse it. In `ShuffledRowRDD`, it still needs to retrieve remote blocks again, because the previously retrieved remote blocks are not stored in local. So I am wondering if we explicitly call `cache` on the `ShuffledRowRDD` which is prepared for reusing, we can skip next round of remote retrieving. Will it improve the shuffle exchange reuse?


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org