Wonderful, we will leave our pg at 4096 :) many thanks for the advice Paul :) have a good day, Jake On 8/19/19 11:03 AM, Paul Emmerich wrote: > On Mon, Aug 19, 2019 at 10:51 AM Jake Grimmett <jog@xxxxxxxxxxxxxxxxx> wrote: >> >> Dear All, >> >> We have a new Nautilus cluster, used for cephfs, with pg_autoscaler in >> warn mode. >> >> Shortly after hitting 62% full, the autoscaler started warning that we >> have too few pg: >> >> ********************************************************* >> Pool ec82pool has 4096 placement groups, should have 16384 >> ********************************************************* >> >> The pool is 62% full, we have 450 OSD, and are using 8 k=8 m=2 Erasure >> encoding. >> >> Does 16384 pg seem reasonable? > > no, that would be a horrible value for a cluster of that size, 4096 is > perfect here. > > > Paul > >> >> The on-line pg calculator suggests 4096... >> >> https://ceph.io/pgcalc/ >> >> (Size = 10, OSD=450, %Data=100, Target OSD 100) >> >> many thanks, >> >> Jake >> >> -- >> MRC Laboratory of Molecular Biology >> Francis Crick Avenue, >> Cambridge CB2 0QH, UK. >> >> _______________________________________________ >> ceph-users mailing list >> ceph-users@xxxxxxxxxxxxxx >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com -- MRC Laboratory of Molecular Biology Francis Crick Avenue, Cambridge CB2 0QH, UK. _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |