wankunde commented on PR #37922: URL: https://github.com/apache/spark/pull/37922#issuecomment-1272469320
Hi, @otterc @mridulm If the spark application was stopped unexpected, there will be some leak merge files. In our production cluster, yarn nodeManager will cleanup those leak files if the disk is not full, and will not cleanup them if the disk is full. Could we change the `blockHandler.applicationRemoved(appId, false /* clean up local dirs */)` to `blockHandler.applicationRemoved(appId, true)` in YarnShuffleService to clean up them ? https://github.com/apache/spark/blob/e6699570becadb91695572bca5adc1605dc1b2a8/common/network-yarn/src/main/java/org/apache/spark/network/yarn/YarnShuffleService.java#L433 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org