Hi, Thank you so much for your kind information. We will review the setting. One things, If we want to use ssd replica size=2 As failure domain is host, it should make sure two replica in two different host, Is there any drawback? Regards, Munna On Thu, 9 Dec 2021, 20:35 Stefan Kooman, <stefan@xxxxxx> wrote: > On 12/9/21 13:01, Md. Hejbul Tawhid MUNNA wrote: > > Hi, > > > > This is ceph.conf during the cluster deploy. ceph version is mimic. > > > > osd pool default size = 3 > > osd pool default min size = 1 > > osd pool default pg num = 1024 > > osd pool default pgp num = 1024 > > osd crush chooseleaf type = 1 > > mon_max_pg_per_osd = 2048 > > mon_allow_pool_delete = true > > mon_pg_warn_min_per_osd = 0 > > mon_pg_warn_max_per_osd = 0 > > osd_max_pg_per_osd_hard_ratio = 8 > > > > osd pool default size = 3 > > osd pool default min size = 2 > > > osd pool default pg num = 32 > > osd pool default pgp num = 32 > > ^^ It depends a lot on how many pools you plan to make. And how many > OSDs. Do net set it too high. It will lead to high mem usage of OSDs and > will bring you into trouble when Ceph has to do recovery. > > > mon_allow_pool_delete = false > > ^^ Do not accidentally allow pools to be deleted > > mon_max_pg_per_osd = 200 > > > Basically don't touch the defaults and set it to crazy high or crazy low > values. > > This seems almost like a deliberate attempt at making the Ceph cluster a > time bomb. > > Your cluster is full. Don't make any of those changes now. First make > sure you have enough capacity in your cluster and / or add OSDs. Then > fix the size=3 and min_size=2. > > Gr. Stefan > _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |