[GitHub] [spark] otterc commented on pull request #30139: [SPARK-31069][CORE] high cpu caused by chunksBeingTransferred in external shuffle service

2020-10-27 Thread GitBox
otterc commented on pull request #30139: URL: https://github.com/apache/spark/pull/30139#issuecomment-717341340 > I know that, but as @jiangxb1987 @mridulm mentioned, we need to ensure the streamState and the totalChunksBeingTransfered are updated synchronically. Add this lock is a

[GitHub] [spark] otterc commented on pull request #30139: [SPARK-31069][CORE] high cpu caused by chunksBeingTransferred in external shuffle service

2020-10-27 Thread GitBox
otterc commented on pull request #30139: URL: https://github.com/apache/spark/pull/30139#issuecomment-717008775 > > This should have a considerable impact on the performance when there are multiple open streams because updates of different streams would lock on a single object

[GitHub] [spark] otterc commented on pull request #30139: [SPARK-31069][CORE] high cpu caused by chunksBeingTransferred in external shuffle service

2020-10-26 Thread GitBox
otterc commented on pull request #30139: URL: https://github.com/apache/spark/pull/30139#issuecomment-717001727 > IMO, we can add a lock to keep strong consistence of value `totalChunksBeingTransferred`, such as >