GitHub user Ru-Xiang opened a pull request: https://github.com/apache/spark/pull/16033
SPARK-18607 get a result on a percent of the tasks succeed ## What changes were proposed in this pull request? In this patch, we modify the codes corresponding to runApproximateJob so that we can get a result when the specified percent of tasks succeed. In a production environment, 'long tail' is a common urgent problem. In practice, as long as we can get a specified percent of tasks' results, we can guarantee the final results. And this is a common requirement in the practice of machine learning algorithms. ## How was this patch tested? We compile the codes by dev/make-distribution.sh, and deploy it on a cluster. and run a test codes reduce on the cluster, and we get the desired results. You can merge this pull request into a Git repository by running: $ git pull https://github.com/Ru-Xiang/spark my_change Alternatively you can review and apply these changes as the patch at: https://github.com/apache/spark/pull/16033.patch To close this pull request, make a commit to your master/trunk branch with (at least) the following in the commit message: This closes #16033 ---- ---- --- 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