You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2022/10/09 06:39:02 UTC

[GitHub] [spark] wankunde commented on pull request #37922: [SPARK-40480][SHUFFLE] Remove push-based shuffle data after query finished

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-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


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