[ceph-users] Erasure Pools.

Andrew J. Hutton andrew.john.hutton at gmail.com
Fri Mar 29 14:46:00 PDT 2019


I have tried to create erasure pools for CephFS using the examples given 
at 
https://swamireddy.wordpress.com/2016/01/26/ceph-diff-between-erasure-and-replicated-pool-type/ 
but this is resulting in some weird behaviour.  The only number in 
common is that when creating the metadata store; is this related?

[ceph at thor ~]$ ceph -s
   cluster:
     id:     b688f541-9ad4-48fc-8060-803cb286fc38
     health: HEALTH_WARN
             Reduced data availability: 128 pgs inactive, 128 pgs incomplete

   services:
     mon: 3 daemons, quorum thor,odin,loki
     mgr: odin(active), standbys: loki, thor
     mds: cephfs-1/1/1 up  {0=thor=up:active}, 1 up:standby
     osd: 5 osds: 5 up, 5 in

   data:
     pools:   2 pools, 256 pgs
     objects: 21 objects, 2.19KiB
     usage:   5.08GiB used, 7.73TiB / 7.73TiB avail
     pgs:     50.000% pgs not active
              128 creating+incomplete
              128 active+clean

Pretty sure these were the commands used.

ceph osd pool create storage 1024 erasure ec-42-profile2
ceph osd pool create storage 128 erasure ec-42-profile2
ceph fs new cephfs storage_metadata storage
ceph osd pool create storage_metadata 128
ceph fs new cephfs storage_metadata storage
ceph fs add_data_pool cephfs storage
ceph osd pool set storage allow_ec_overwrites true
ceph osd pool application enable storage cephfs
fs add_data_pool default storage
ceph fs add_data_pool cephfs storage


More information about the ceph-users mailing list