[GitHub] [pulsar] mattisonchao commented on pull request #17870: [improve][broker] Use separate IO event loop group for internal client.

[GitBox <gi...@apache.org>]

mattisonchao commented on PR #17870:
URL: https://github.com/apache/pulsar/pull/17870#issuecomment-1262114675

   Hi @lhotari 
   Thanks for your professional explanation. 
   
   > Adding more threads and thread pools (event loops) is a bandaid to the problem, but doesn't solve the root cause.
   
   I totally agree with you, but in the current implementation, we have too much historical baggage and potential impact. For this situation, my recommendation is to lower the sphere of influence first. Then keep making it even better.
   
   Another problem is that we share the IO pool with all replicators. This means that if we have too many replicators on the broker, they will compete for resources with the broker. Plus, by design, I don't think it's a good idea for one component to compete with the entire broker. For example, a problem with a topic or replicator should not affect the entire broker.
   
   Please let me know what you think. thanks!


-- 
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-unsubscribe@pulsar.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org