So I am correct in 2048 being a very high number and should go for either 256 or 512 like you said for a cluster of my size with the EC Pool of 8+2?
Thanks
Thanks
---- On Tue, 10 Sep 2019 14:12:58 +0800 Konstantin Shalygin <k0ste@xxxxxxxx> wrote ----
You should not use 300PG because is not a power of two. You should set pg_num to 256 or 512.
k
I have a EC Pool (8+2) which has 30 OSD (3 Nodes), grown from the orginal 10 OSD (1 Node). I originally set the pool with a PG_NUM of 300, however the AutoScale PG is showing a warn saying I should set this to 2048, I am not sure if this is a good suggestion or if the Autoscale currently is not suggested for EC pool's due to the slightly diff calculations used. Currently with a PG NUM of 300 each OSD has around 100PG, changing to 2048 is going to increase this massively.
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
