On 2015-08-06 17:18, Wido den Hollander wrote:
The mount of PGs is cluster wide and not per pool. So if you have 48
OSDs the rule of thumb is: 48 * 100 / 3 = 1600 PGs cluster wide.
Now, with enough memory you can easily have 100 PGs per OSD, but keep in
mind that the PG count is cluster-wide and not per pool.
I understand that now, but that is not what the docs say. The docs say
4096 PGs per pool (i.e. in the "ceph osd pool create" command) for 48
OSDs. Which seems to be off by a factor of 2.5x from the actual
do-the-math recommendation for one 3x pool, and successively larger
factors as you add pools.
We are following the hardware recommendations for RAM: 1GB per 1TB of
storage, so 16GB for each OSD box (4GB per OSD daemon, each OSD being
one 4TB drive).
--
Hector Martin ([email protected])
Public Key: https://marcan.st/marcan.asc
_______________________________________________
ceph-users mailing list
[email protected]
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
