rayliu419 opened a new issue #11698: URL: https://github.com/apache/pulsar/issues/11698
Hi team, I can't find a template to ask general question so I just post it here, please direct me to the right template/place if I am wrong. 1. Kafka(<2.8) use ZK to do leader broker election, as far as I know, when doing rolling update, when the leader broker update, the kafka cluster needs to select a new leader. During the time, the whole cluster can't offer service(at least not for write). I searched some pages and found Pulsar also has a concept called leader broker, does that also happens in Pulsar? 2. It seems Pulsar use ZK a lot, e.g., store meta data such as topic/namespace/tenants information, does that affect the cluster performance when the cluster is large? The configuration rarely changes so I think that's OK, but the meta data such as consumer offset change frequently, so I guess ZK will be a bottleneck of the whole cluster? Thanks, Rui -- 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...@pulsar.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
