kfaraz opened a new pull request, #16578:
URL: https://github.com/apache/druid/pull/16578

   ### Description
   
   With batch segment allocation enabled and batchAllocationWaitTime=0,
   the segment allocation queue would exhibit the following behaviour:
   - Process the first segment allocation request added to the queue 
immediately.
   - While the first request is being processed, let any subsequent requests 
accumulate in the queue.
   - Once the first request is processed, pick up the next batch in the queue 
for processing.
   
   ### Testing
   
   We have had `batchAllocationWaitTime=0` in several of our production 
clusters for a couple of months now.
   It has particularly helped with MSQ tasks, which don't really benefit from 
batching as segments are allocated serially.
   Waiting 500ms for every allocation increased MSQ task durations leading to 
unnecessary compute costs.
   
   ### Release Note
   
   Update default value of `druid.indexer.tasklock.batchAllocationWaitTime` to 
`0`. This means 


-- 
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