Hello List,
We're planning to add a couple new OSD nodes to one of our clusters but we've reached the point where we need to increase PG's before doing so. Our ratio is currently 52pg's per OSD.
Based on the PG calc we need to make the following increases:
compute - 1024 => 4096
images 512 => 2048
My question is what is the safest, least impactful way to do this. Our workload is very latency sensitive so when we do maintenance on the cluster we always try to minimize impact best we can. When adding/removing disks or nodes we accomplish this by gradually reweighting. Is there a similar technique we can use in this case?
Also I'd like to know how many PG's is recommended to increase at a time.
Any advice is appreciated.
Thanks,
John
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
