I'm seeing an interesting behavior in Elasticsearch. We are running 1.7.3. 
When we add a brand new node to the cluster (either to expand capacity or 
to replace a failed node) we have observed elasticsearch prioritizing new 
index shard placement to the empty node first, creating a hotspot that 
maxes our CPU utilization and degrades the write path. We have to imagine 
this is a well known behavior and there's a ready solution for it, but so 
far I haven't discovered what that is. If anyone has any advice on this 
topic I would love to hear it. 

Thanks
Dave

-- 
You received this message because you are subscribed to the Google Groups 
"Graylog Users" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To view this discussion on the web visit 
https://groups.google.com/d/msgid/graylog2/8737d901-ad86-404d-a8aa-7437006930d0%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

Reply via email to