ankitsultana opened a new pull request, #10794: URL: https://github.com/apache/pinot/pull/10794
At present the broker can run into a busy waiting loop if all the receiving mailbox are initialized but there's at least one mailbox which hasn't returned EOS yet. This leads to that query hogging one entire CPU core which leads to obvious issues. I guess long-term we would want to use a scheduler for the broker as well (or get rid of polling and use an event based approach), but meanwhile I think it might be good to fix this issue. We saw this in our prod clusters once recently. We have known about this issue for a while now so thinking it's best to put a fix in: https://github.com/apache/pinot/issues/10131 cc: @walterddr -- 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: commits-unsubscr...@pinot.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org For additional commands, e-mail: commits-h...@pinot.apache.org
