cluster-maintenance.yml

---
# This playbook was made to automate Ceph servers maintenance
# Typical use case: hardware change
# By running this playbook you will set the 'noout' flag on your
# cluster, which means that OSD **can't** be marked as out
# of the CRUSH map, but they will be marked as down.
# Basically we tell the cluster to don't move any data since
# the operation won't last for too long.

- hosts: <your_host>
  gather_facts: False

  tasks:

  - name: Set the noout flag
    command: ceph osd set noout
    delegate_to: <your_monitor>

  - name: Turn off the server
    command: poweroff

  - name: Wait for the server to go down
    local_action: >
      wait_for host=<your_host>
      port=22
      state=stopped

  - name: Wait for the server to come up
    local_action: >
      wait_for host=<your_host
      port=22
      delay=10
      timeout=3600

  - name: Unset the noout flag
    command: ceph osd unset noout
    delegate_to: <your_monitor>