truong-hua opened a new issue, #3529: URL: https://github.com/apache/bookkeeper/issues/3529
**BUG REPORT** 1. Please describe the issue you observed: - What did you do? I'm using Bookeeper 4.14.4 and runing a 5 nodes cluster. When one node of my bookie cluster is down, the bookie cluster send a lot of request to zookeeper and causes ZK CPU usage always over 100%. The issue gone when the failed node is recover and rejoin in to the cluster properly. This is my JAVA env: ``` openjdk 11.0.13 2021-10-19 OpenJDK Runtime Environment (build 11.0.13+8-Ubuntu-0ubuntu1.20.04) OpenJDK 64-Bit Server VM (build 11.0.13+8-Ubuntu-0ubuntu1.20.04, mixed mode, sharing) ``` The zookeeper version: 3.7.1 - What did you expect to see? Bookie should not causes ZK CPU consumption when the cluster is degraded. - What did you see instead? ZK CPU stuck at >100% and it causes more server performance problems. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
