jtuglu-netflix commented on issue #18008:
URL: https://github.com/apache/druid/issues/18008#issuecomment-2915293457

   > Perhaps reading from multiple topics in a single supervisor was more 
straightforward.
   
   Regarding this, I think that was a much simpler issue since it was still 
only reading from a single consumer (single region). The consumer can already 
natively handle reading from multi-topic partitions, so it was a matter of just 
plugging into that functionality.
   
   The difference here is we have N sets of consumers, so the ingest lag, 
throughput values, etc. differ across each consumer. While the draft I raised 
above works well if task counts are inflated enough, with the current task 
scaling scheme, you can run into asymmetrical lag where you have a laggard 
region.


-- 
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]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to