Re: OSD down after PG increase

[Dan Van Der Ster <daniel.vanderster@xxxxxxx>]

On 13 Mar 2014 at 11:26:55, Gandalf Corvotempesta (gandalf.corvotempesta@xxxxxxxxx) wrote:

I'm also unsure if 8192 PGs are correct for my cluster. 
At maximum i'll have 168 OSDs (14 servers, 12 disks each, 1 osd per 
disk), with replica set to 3, so: 

(168*100)/3 = 5600. Rounded to the next power of 2: 8192 

That’s a bit high for my taste — you’ll average 146 PGs per OSD assuming a uniform distribution. Though it is probably OK.

Do you have any other pools? Remember that you need to include _all_ pools in the PG calculation, not just a single pool.

— Dan

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com