Savonitar commented on PR #174:
URL: 
https://github.com/apache/flink-connector-kafka/pull/174#issuecomment-4207489042

   Hi. Thanks for keeping at this PR, appreciate your commitment.
   I was also backlogged at work as you mentioned in your message :-) and I'm 
sick right now. To give this a proper review-run, need to feel better first, I 
expect to continue the review next week. Let me know if you'd like me to ping 
someone else to review (and feel free to ping someone yourself if you'd prefer 
not to wait).
   
   In general, the current version after your fixes looks solid. I think the 
main remaining question is the user-facing configuration design - specifically 
the implicit compatibility between formats and pushdown levels, and whether the 
configuration options could be less ambiguous. I'd like to revisit this in the 
next review round. Apart from that, I don't have concerns.
   
   By the way, do you run this in production already? If you have any 
benchmarks or observations on the deserialization savings, I'd be interested to 
see them.


-- 
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