Github user shivaram commented on the pull request: https://github.com/apache/spark/pull/7461#issuecomment-129506547 Thanks @kmadhugit , the test case sounds good to me. Could you try this on a multi-node cluster ? We just set the locality preference for the scheduler and I guess in the case of shuffle data the default is `NODE_LOCAL` as the data is on shared disk (and not in memory ?).
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org