ceph/doc/rados/operations/pg-states.rst

   1 ========================
   2  Placement Group States
   3 ========================
   4
   5 When checking a cluster's status (e.g., running ``ceph -w`` or ``ceph -s``),
   6 Ceph will report on the status of the placement groups. A placement group has
   7 one or more states. The optimum state for placement groups in the placement group
   8 map is ``active + clean``.
   9
  10 *Creating*
  11   Ceph is still creating the placement group.
  12
  13 *Active*
  14   Ceph will process requests to the placement group.
  15
  16 *Clean*
  17   Ceph replicated all objects in the placement group the correct number of times.
  18
  19 *Down*
  20   A replica with necessary data is down, so the placement group is offline.
  21
  22 *Scrubbing*
  23   Ceph is checking the placement group for inconsistencies.
  24
  25 *Degraded*
  26   Ceph has not replicated some objects in the placement group the correct number of times yet.
  27
  28 *Inconsistent*
  29   Ceph detects inconsistencies in the one or more replicas of an object in the placement group
  30   (e.g. objects are the wrong size, objects are missing from one replica *after* recovery finished, etc.).
  31
  32 *Peering*
  33   The placement group is undergoing the peering process
  34
  35 *Repair*
  36   Ceph is checking the placement group and repairing any inconsistencies it finds (if possible).
  37
  38 *Recovering*
  39   Ceph is migrating/synchronizing objects and their replicas.
  40
  41 *Backfill*
  42   Ceph is scanning and synchronizing the entire contents of a placement group
  43   instead of inferring what contents need to be synchronized from the logs of
  44   recent operations. *Backfill* is a special case of recovery.
  45
  46 *Wait-backfill*
  47   The placement group is waiting in line to start backfill.
  48
  49 *Backfill-toofull*
  50   A backfill operation is waiting because the destination OSD is over its
  51   full ratio.
  52
  53 *Incomplete*
  54   Ceph detects that a placement group is missing information about
  55   writes that may have occurred, or does not have any healthy
  56   copies. If you see this state, try to start any failed OSDs that may
  57   contain the needed information. In the case of an erasure coded pool
  58   temporarily reducing min_size may allow recovery.
  59
  60 *Stale*
  61   The placement group is in an unknown state - the monitors have not received
  62   an update for it since the placement group mapping changed.
  63
  64 *Remapped*
  65   The placement group is temporarily mapped to a different set of OSDs from what
  66   CRUSH specified.
  67
  68 *Undersized*
  69   The placement group fewer copies than the configured pool replication level.
  70
  71 *Peered*
  72   The placement group has peered, but cannot serve client IO due to not having
  73   enough copies to reach the pool's configured min_size parameter.  Recovery
  74   may occur in this state, so the pg may heal up to min_size eventually.