AngersZhuuuu commented on a change in pull request #28541: URL: https://github.com/apache/spark/pull/28541#discussion_r426989811
########## File path: core/src/main/scala/org/apache/spark/memory/ExecutionMemoryPool.scala ########## @@ -138,6 +140,11 @@ private[memory] class ExecutionMemoryPool( if (toGrant < numBytes && curMem + toGrant < minMemoryPerTask) { logInfo(s"TID $taskAttemptId waiting for at least 1/2N of $poolName pool to be free") lock.wait() + } else if (toGrant == 0 && memoryFree > 0) { Review comment: > Or, if one specific pattern of tasks take significantly more memory than other tasks, maybe you should tune the tasks themselves, instead of modifying the Spark internal for a specific case. yea, ad-hoc query sort with big key, spill 20G +. only run that query will success, run with other sql with high concurrency , failed. ---------------------------------------------------------------- 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. 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