JacksonYao287 edited a comment on pull request #2182: URL: https://github.com/apache/ozone/pull/2182#issuecomment-852792169
Thanks @avijayanhwx for the review! > In your setup, is the OOM caused due to multiple reports being bottlenecked at the event queue layer? yes, when there is a large number of containers(in my cluster , about 1 million containers, heartbeat interval is set to 2s and container size is set to 128m), if datanode always send full report, the single thread report handler may not handle this stress, so there will be more and more container report wait for handling, this leads to the scm oom. @symious can you help reviewing this pr？ -- 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: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
