You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@druid.apache.org by GitBox <gi...@apache.org> on 2019/03/12 19:25:51 UTC

[GitHub] [incubator-druid] gianm commented on issue #7236: Further improve caching documentation.

gianm commented on issue #7236: Further improve caching documentation.
URL: https://github.com/apache/incubator-druid/pull/7236#issuecomment-472146765
 
 
   Those are all good questions. I'm not sure what the exact tradeoff is between letting the broker use (but not populate) a remote cache. I am sure that for a big enough cluster it's a bad idea, since it would have the same problems that enabling cache population does.
   
   I think the setup you mentioned is a good one for most users, and if you're interested in doing a PR to add the recommendation to the doc, please do!
   
   I also think if we fix #5796 we should add to the recommendation that using an external cache is a good way to boost hit rates, if you don't mind the operational overhead of running the external cache. Doing a bulk get on historicals minimizes the overhead of pulling segments. Cache hit rate is still maximized. And we avoid the broker being a bottleneck.

----------------------------------------------------------------
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.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@druid.apache.org
For additional commands, e-mail: commits-help@druid.apache.org