PG Balancer Upmap mode not working

["Philippe D'Anjou" <danjou.philippe@xxxxxxxx>]

Hi,

the docs say the upmap mode is trying to achieve perfect distribution as to have equal amount of PGs/OSD.

This is what I got(v14.2.4):

  0   ssd 3.49219  1.00000 3.5 TiB 794 GiB 753 GiB  38 GiB 3.4 GiB 2.7 TiB 22.20 0.32  82     up
  1   ssd 3.49219  1.00000 3.5 TiB 800 GiB 751 GiB  45 GiB 3.7 GiB 2.7 TiB 22.37 0.33  84     up
  2   ssd 3.49219  1.00000 3.5 TiB 846 GiB 792 GiB  50 GiB 3.6 GiB 2.7 TiB 23.66 0.35  88     up
  3   ssd 3.49219  1.00000 3.5 TiB 812 GiB 776 GiB  33 GiB 3.3 GiB 2.7 TiB 22.71 0.33  85     up
  4   ssd 3.49219  1.00000 3.5 TiB 768 GiB 730 GiB  34 GiB 4.1 GiB 2.7 TiB 21.47 0.31  83     up
  6   ssd 3.49219  1.00000 3.5 TiB 765 GiB 731 GiB  31 GiB 3.3 GiB 2.7 TiB 21.40 0.31  82     up
  8   ssd 3.49219  1.00000 3.5 TiB 872 GiB 828 GiB  41 GiB 3.2 GiB 2.6 TiB 24.40 0.36  85     up
 10   ssd 3.49219  1.00000 3.5 TiB 789 GiB 743 GiB  42 GiB 3.3 GiB 2.7 TiB 22.05 0.32  82     up
  5   ssd 3.49219  1.00000 3.5 TiB 719 GiB 683 GiB  32 GiB 3.9 GiB 2.8 TiB 20.12 0.29  78     up
  7   ssd 3.49219  1.00000 3.5 TiB 741 GiB 698 GiB  39 GiB 3.8 GiB 2.8 TiB 20.73 0.30  79     up
  9   ssd 3.49219  1.00000 3.5 TiB 709 GiB 664 GiB  41 GiB 3.5 GiB 2.8 TiB 19.82 0.29  78     up
 11   ssd 3.49219  1.00000 3.5 TiB 858 GiB 834 GiB  22 GiB 2.4 GiB 2.7 TiB 23.99 0.35  82     up
101   ssd 3.49219  1.00000 3.5 TiB 815 GiB 774 GiB  38 GiB 3.5 GiB 2.7 TiB 22.80 0.33  80     up
103   ssd 3.49219  1.00000 3.5 TiB 827 GiB 783 GiB  40 GiB 3.3 GiB 2.7 TiB 23.11 0.34  81     up
105   ssd 3.49219  1.00000 3.5 TiB 797 GiB 759 GiB  36 GiB 2.5 GiB 2.7 TiB 22.30 0.33  81     up
107   ssd 3.49219  1.00000 3.5 TiB 840 GiB 788 GiB  50 GiB 2.8 GiB 2.7 TiB 23.50 0.34  83     up
100   ssd 3.49219  1.00000 3.5 TiB 728 GiB 678 GiB  47 GiB 2.4 GiB 2.8 TiB 20.36 0.30  78     up
102   ssd 3.49219  1.00000 3.5 TiB 764 GiB 750 GiB  12 GiB 2.2 GiB 2.7 TiB 21.37 0.31  76     up
104   ssd 3.49219  1.00000 3.5 TiB 795 GiB 761 GiB  31 GiB 2.5 GiB 2.7 TiB 22.22 0.33  78     up
106   ssd 3.49219  1.00000 3.5 TiB 730 GiB 665 GiB  62 GiB 2.8 GiB 2.8 TiB 20.41 0.30  78     up
108   ssd 3.49219  1.00000 3.5 TiB 849 GiB 808 GiB  38 GiB 2.5 GiB 2.7 TiB 23.73 0.35  92     up
109   ssd 3.49219  1.00000 3.5 TiB 798 GiB 754 GiB  41 GiB 2.7 GiB 2.7 TiB 22.30 0.33  83     up
110   ssd 3.49219  1.00000 3.5 TiB 840 GiB 810 GiB  28 GiB 2.4 GiB 2.7 TiB 23.49 0.34  85     up
111   ssd 3.49219  1.00000 3.5 TiB 788 GiB 741 GiB  45 GiB 2.5 GiB 2.7 TiB 22.04 0.32  85     up

PG's are badly distributed.

ceph balancer status
{
    "active": true,
    "plans": [],
    "mode": "upmap"
}

It is because of this?

    health: HEALTH_WARN
            Failed to send data to Zabbix
            1 subtrees have overcommitted pool target_size_bytes
            1 subtrees have overcommitted pool target_size_ratio

Any ideas why its not working?

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com