Removing a Ceph OSD node

To reduce the capacity of a storage cluster, remove an OSD node.

Before you begin

Before you begin, make sure that you have the following prerequisites in place:
  • A running IBM Storage Ceph cluster.
  • Root-level access to all nodes in the storage cluster.

About this task

Warning: Before removing a Ceph OSD node, ensure that the storage cluster can backfill the contents of all OSDs without reaching the full ratio. Reaching the full ratio will cause the storage cluster to refuse write operations.

Procedure

  1. Check the storage cluster’s capacity.
    ceph df
    rados df
    ceph osd df
  2. Temporarily disable scrubbing.
    ceph osd set noscrub
    ceph osd set nodeep-scrub
  3. Limit the backfill and recovery features.
    ceph tell DAEMON_TYPE.* injectargs --OPTION_NAME VALUE [--OPTION_NAME VALUE]
    For example,
    [ceph: root@host01 /]# ceph tell osd.* injectargs --osd-max-backfills 1 --osd-recovery-max-active 1 --osd-recovery-op-priority 1
  4. Remove each OSD on the node from the storage cluster.
    Important: When removing an OSD node from the storage cluster, IBM recommends removing one OSD at a time within the node and allowing the cluster to recover to an active+clean state before proceeding to remove the next OSD.
  5. Verify that the storage cluster is not getting to the near-full ratio.
    ceph -s
    ceph df
    Repeat this step until all OSDs on the node are removed from the storage cluster.

    Only continue after verifying that all OSDs are removed.

  6. Remove the host.
    For more information, see Removing hosts.