Hieu Tri Huynh created SPARK-24992: -------------------------------------- Summary: spark should randomize yarn local dir selection Key: SPARK-24992 URL: https://issues.apache.org/jira/browse/SPARK-24992 Project: Spark Issue Type: Improvement Components: Spark Core Affects Versions: 2.3.1 Reporter: Hieu Tri Huynh
Utils.getLocalDir is used to get path of a temporary directory. However, it always returns the the same directory, which is the first element in the array _localRootDirs_. When running on YARN, this might causes the case that we always write to one disk, which makes it busy while other disks are free. We should randomize the selection to spread out the loads. -- This message was sent by Atlassian JIRA (v7.6.3#76005) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org