FrankChen021 commented on PR #17775:
URL: https://github.com/apache/druid/pull/17775#issuecomment-2702678872

   > > One thing I noticed is that when you have the cluster starting up, the 
historical will not / can not serve any query until all the segments are loaded 
(I think there is a config for this which is enabled by default). In this case, 
we should always use turboLoadHistoricals (by default), since the historical 
cannot serve query anyway.
   > 
   > @maytasm , IIUC, you are referring to the bootstrap segments, which 
includes broadcast segments and segments already present on the historical 
disk. For these bootstrap segments, we already use the turbo loading thread 
pool.
   > 
   > The change here allows to optionally put a historical in turbo mode to 
load non-bootstrap segments, i.e. segments assigned later by the coordinator.
   
   But the description(the Context section) of this PR is different from what 
the changes really do. I think we need to update the description of the PR to 
eliminate misleading.


-- 
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