On Fri, Jul 18, 2014 at 3:29 PM, James Eckersall <James.Eckersall at fasthosts.com> wrote: > Thanks Greg. > > Can I suggest that the documentation makes this much clearer? It might just be me, but I couldn't glean this from the docs, so I expect I'm not the only one. > > Also, can I clarify how many pg's you would suggest is a decent number for my setup? > > 80 OSD's across 4 nodes. 5 pools. > I'm averaging 38 PG's per OSD and from the online docs and older posts on this list, I think I should be aiming for between 50 and 100? > > I'm hoping that by only having 38 PG's per OSD, that is the cause of the uneven distribution and that can be fairly easily rectified. That seems likely. The general formula to get a baseline is (100*OSDs/replication count) when using one pool. It's also generally better to err on the side of more PGs than fewer; they have a cost but OSDs can usually scale into the high thousands of PGs, so I personally prefer people to go a little higher than that. You'll also want to adjust things so that the pools with more data get more PGs than the ones with much less, or they won't do you much good. -Greg Software Engineer #42 @ http://inktank.com | http://ceph.com
 |