ceph-ansible/infrastructure-playbooks/rolling_update.yml

234 lines
5.6 KiB
YAML

---
# This playbook does a rolling update for all the Ceph services
# Change the value of 'serial:' to adjust the number of server to be updated.
#
# The four roles that apply to the ceph hosts will be applied: ceph-common,
# ceph-mon, ceph-osd and ceph-mds. So any changes to configuration, package updates, etc,
# will be applied as part of the rolling update process.
#
# /!\ DO NOT FORGET TO CHANGE THE RELEASE VERSION FIRST! /!\
- name: confirm whether user really meant to upgrade the cluster
hosts: localhost
vars_prompt:
- name: ireallymeanit
prompt: Are you sure you want to upgrade the cluster?
default: 'no'
private: no
tasks:
- name: exit playbook, if user did not mean to upgrade cluster
fail:
msg: >
"Exiting rolling_update.yml playbook, cluster was NOT upgraded.
To upgrade the cluster, either say 'yes' on the prompt or
or use `-e ireallymeanit=yes` on the command line when
invoking the playbook"
when: ireallymeanit != 'yes'
- hosts:
- mons
- osds
- mdss
- rgws
become: True
tasks:
- debug: msg="gather facts on all Ceph hosts for following reference"
- name: check if sysvinit
stat:
path: /etc/rc?.d/S??ceph
follow: yes
register: is_sysvinit
- name: check if upstart
stat:
path: /var/lib/ceph/mon/ceph-{{ ansible_hostname }}/upstart
register: is_upstart
- name: check if systemd
command: grep -sq systemd /proc/1/comm
register: is_systemd
- hosts: mons
serial: 1
become: True
vars:
upgrade_ceph_packages: True
mon_group_name: mons
pre_tasks:
- name: compress the store as much as possible
command: ceph tell mon.{{ ansible_hostname }} compact
roles:
- ceph-common
- ceph-mon
post_tasks:
- name: restart ceph mons with upstart
service:
name: ceph-mon
state: restarted
args: id={{ ansible_hostname }}
when: is_upstart.stat.exists == True
- name: restart ceph mons with sysvinit
service:
name: ceph
state: restarted
when: is_sysvinit.stat.exists == True
- name: restart ceph mons with systemd
service:
name: ceph-mon@{{ ansible_hostname }}
state: restarted
enabled: yes
when: is_systemd
- name: select a running monitor
set_fact: mon_host={{ item }}
with_items: groups.mons
when: item != inventory_hostname
- name: waiting for the monitor to join the quorum...
shell: |
ceph -s | grep monmap | sed 's/.*quorum//' | egrep -sq {{ ansible_hostname }}
register: result
until: result.rc == 0
retries: 5
delay: 10
delegate_to: "{{ mon_host }}"
- hosts: osds
serial: 1
become: True
vars:
upgrade_ceph_packages: True
osd_group_name: osds
pre_tasks:
- name: set osd flags
command: ceph osd set {{ item }}
with_items:
- noout
- noscrub
- nodeep-scrub
delegate_to: "{{ groups.mons[0] }}"
roles:
- ceph-common
- ceph-osd
post_tasks:
- name: get osd numbers
shell: "if [ -d /var/lib/ceph/osd ] ; then ls /var/lib/ceph/osd | cut -d '-' -f 2 ; fi"
register: osd_ids
changed_when: false
- name: restart ceph osds (upstart)
service:
name: ceph-osd-all
state: restarted
when: is_upstart.stat.exists == True
- name: restart ceph osds (sysvinit)
service:
name: ceph
state: restarted
when: is_sysvinit.stat.exists == True
- name: restart ceph osds (systemd)
service:
name: ceph-osd@{{item}}
state: restarted
enabled: yes
with_items: "{{ osd_ids.stdout_lines }}"
when: is_systemd
- name: waiting for clean pgs...
shell: |
test "$(ceph pg stat | sed 's/^.*pgs://;s/active+clean.*//;s/ //')" -eq "$(ceph pg stat | sed 's/pgs.*//;s/^.*://;s/ //')" && ceph health | egrep -sq "HEALTH_OK|HEALTH_WARN"
register: result
until: result.rc == 0
retries: 10
delay: 10
delegate_to: "{{ groups.mons[0] }}"
- name: unset osd flags
command: ceph osd unset {{ item }}
with_items:
- noout
- noscrub
- nodeep-scrub
delegate_to: "{{ groups.mons[0] }}"
- hosts: mdss
serial: 1
become: True
vars:
upgrade_ceph_packages: True
mds_group_name: mdss
roles:
- ceph-common
- ceph-mds
post_tasks:
- name: restart ceph mdss with upstart
service:
name: ceph-mds
state: restarted
args: id={{ ansible_hostname }}
when: is_upstart.stat.exists == True
- name: restart ceph mdss with sysvinit
service:
name: ceph
state: restarted
args: mds
when: is_sysvinit.stat.exists == True
- name: restart ceph mdss with systemd
service:
name: ceph-mds@{{ ansible_hostname }}
state: restarted
enabled: yes
when: is_systemd
- hosts: rgws
serial: 1
become: True
vars:
upgrade_ceph_packages: True
rgw_group_name: rgws
roles:
- ceph-common
- ceph-rgw
post_tasks:
- name: restart ceph rgws with systemd
service:
name: ceph-radosgw@rgw.{{ ansible_hostname }}
state: restarted
enabled: yes
when: is_systemd
- name: restart ceph rgws with sysvinit
service:
name: radosgw
state: restarted
when: ansible_os_family != 'RedHat'
- name: restart rados gateway server(s)
service:
name: ceph-radosgw
state: restarted
when: ansible_os_family != 'RedHat'