loserwang1024 opened a new issue, #1421:
URL: https://github.com/apache/fluss/issues/1421

   ### Search before asking
   
   - [x] I searched in the [issues](https://github.com/alibaba/fluss/issues) 
and found nothing similar.
   
   
   ### Description
   
   Currently, FETCH_LOG returns all segments of a table bucket. This means that 
if we start fetching from two days ago and each table bucket contains 20 remote 
segments, the system will return 20 × (number of table buckets) files.
   
   During the download process, the current behavior is to download all 
segments of table bucket 1 first, followed by all segments of table bucket 2, 
and so on. This leads to an unstable delay pattern: the latency drops from two 
days down to minutes, then suddenly spikes back up to nearly two days, and 
repeats this cycle continuously.
   
   If instead, only one segment per table bucket is returned in each fetch, the 
delay metric would become much more stable and predictable, resulting in a 
smoother and more user-friendly experience.
   
   ### Willingness to contribute
   
   - [ ] 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