platinumhamburg opened a new issue, #1454:
URL: https://github.com/apache/fluss/issues/1454

   ### Search before asking
   
   - [x] I searched in the [issues](https://github.com/alibaba/fluss/issues) 
and found nothing similar.
   
   
   ### Motivation
   
   Currently, the tablet server handles metadata() requests in synchronous 
mode, which creates a performance bottleneck in RPC request processing. 
Additionally, when the requested metadata is not available in the local cache, 
the server queries ZooKeeper but does not update the cache with the retrieved 
results.
   In large clusters, when thousands of Flink coordinator clients request 
metadata from the server, it is easy to fall into a timeout and retry cycle, 
and server RPC resources will be exhausted with no relief in sight.
   
   ### Solution
   
   - make metadata() process async in tablet server
   - When metadata cache misses occur, the tablet server updates the local 
cache with the results retrieved from ZooKeeper.
   - metadata() supports a cache-only flag that allows client requests to fail 
fast when cache misses occur, making it easy for clients to retry from another 
server.
   
   ### Anything else?
   
   _No response_
   
   ### Willingness to contribute
   
   - [x] I'm willing to submit a 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.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to