On Sat, 5 Jan 2019, 13:38 Marc Roos <M.Roos@xxxxxxxxxxxxxxxxx wrote:
I have straw2, balancer=on, crush-compat and it gives worst spread over
my ssd drives (4 only) being used by only 2 pools. One of these pools
has pg 8. Should I increase this to 16 to create a better result, or
will it never be any better.
For now I like to stick to crush-compat, so I can use a default centos7
kernel.
Pg upmap is supported in the CentOS 7.5+ kernels
Luminous 12.2.8, 3.10.0-862.14.4.el7.x86_64, CentOS Linux release
7.5.1804 (Core)
[@c01 ~]# cat balancer-1-before.txt | egrep '^19|^20|^21|^30'
19 ssd 0.48000 1.00000 447GiB 164GiB 283GiB 36.79 0.93 31
20 ssd 0.48000 1.00000 447GiB 136GiB 311GiB 30.49 0.77 32
21 ssd 0.48000 1.00000 447GiB 215GiB 232GiB 48.02 1.22 30
30 ssd 0.48000 1.00000 447GiB 151GiB 296GiB 33.72 0.86 27
[@c01 ~]# ceph osd df | egrep '^19|^20|^21|^30'
19 ssd 0.48000 1.00000 447GiB 157GiB 290GiB 35.18 0.87 30
20 ssd 0.48000 1.00000 447GiB 125GiB 322GiB 28.00 0.69 30
21 ssd 0.48000 1.00000 447GiB 245GiB 202GiB 54.71 1.35 30
30 ssd 0.48000 1.00000 447GiB 217GiB 230GiB 48.46 1.20 30
[@c01 ~]# ceph osd pool ls detail | egrep 'fs_meta|rbd.ssd'
pool 19 'fs_meta' replicated size 3 min_size 2 crush_rule 5 object_hash
rjenkins pg_num 16 pgp_num 16 last_change 22425 lfor 0/9035 flags
hashpspool stripe_width 0 application cephfs
pool 54 'rbd.ssd' replicated size 3 min_size 2 crush_rule 5 object_hash
rjenkins pg_num 8 pgp_num 8 last_change 24666 flags hashpspool
stripe_width 0 application rbd
[@c01 ~]# ceph df |egrep 'ssd|fs_meta'
fs_meta 19 170MiB 0.07
240GiB 2451382
fs_data.ssd 33 0B 0
240GiB 0
rbd.ssd 54 266GiB 52.57
240GiB 75902
fs_data.ec21.ssd 55 0B 0
480GiB 0
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
