From ad3daf7ee91d71d2c88df7fa642dd7dfe059f2cd Mon Sep 17 00:00:00 2001 From: Juan Larriba Date: Fri, 4 Jun 2021 10:40:44 +0200 Subject: [PATCH] Switch from pacemaker standby to pacemaker stop Currently, the "snapshots" backup is being taken after taking out one node from the cluster using pcs node standby. The consequence of it is that the standby property is also being backuped, so when the node is restored, it appears as standby and it needs to be unstandby manually. Switching to pcs cluster stop/pcs cluster start does not make the playbook take any longer, nor it creates an impact on the time the vips take to be migrated to a different node while provides the advantage that when the node is restarted (during restore), pacemaker starts correctly without any other manual step. Not a clean cherry pick due to different naming of the role directory. Change-Id: Ided482f7eaed8d5e1fac60679ef3ba07bda41c0c (cherry picked from commit 0fb4873ca01c76350b162fcf574dafe970f760df) (cherry picked from commit 76d61eaccbd4474b04f4b338f8edd1b2a6937f6f) --- tripleo_ansible/roles/backup-and-restore/backup/tasks/main.yml | 2 +- .../tasks/{pacemaker_unstandby.yml => pacemaker_start.yml} | 2 +- tripleo_ansible/roles/backup-and-restore/defaults/main.yml | 3 +++ tripleo_ansible/roles/backup-and-restore/tasks/main.yml | 2 +- 4 files changed, 6 insertions(+), 3 deletions(-) rename tripleo_ansible/roles/backup-and-restore/backup/tasks/{pacemaker_unstandby.yml => pacemaker_start.yml} (97%) diff --git a/tripleo_ansible/roles/backup-and-restore/backup/tasks/main.yml b/tripleo_ansible/roles/backup-and-restore/backup/tasks/main.yml index f5126fb6d..239d56d2b 100644 --- a/tripleo_ansible/roles/backup-and-restore/backup/tasks/main.yml +++ b/tripleo_ansible/roles/backup-and-restore/backup/tasks/main.yml @@ -33,7 +33,7 @@ - always - name: Take this node out of pacemaker - command: pcs node standby + command: pcs cluster stop --request-timeout={{ tripleo_backup_and_restore_pcs_timeout }} when: - pacemaker_enabled - tripleo_backup_and_restore_enable_snapshots|bool diff --git a/tripleo_ansible/roles/backup-and-restore/backup/tasks/pacemaker_unstandby.yml b/tripleo_ansible/roles/backup-and-restore/backup/tasks/pacemaker_start.yml similarity index 97% rename from tripleo_ansible/roles/backup-and-restore/backup/tasks/pacemaker_unstandby.yml rename to tripleo_ansible/roles/backup-and-restore/backup/tasks/pacemaker_start.yml index 7162de7c8..14cc605ec 100644 --- a/tripleo_ansible/roles/backup-and-restore/backup/tasks/pacemaker_unstandby.yml +++ b/tripleo_ansible/roles/backup-and-restore/backup/tasks/pacemaker_start.yml @@ -16,7 +16,7 @@ # # Start again pacemaker - name: Add the node to the pacemaker cluster - command: pcs node unstandby + command: pcs cluster start tags: - bar_create_recover_image diff --git a/tripleo_ansible/roles/backup-and-restore/defaults/main.yml b/tripleo_ansible/roles/backup-and-restore/defaults/main.yml index 265ead8a2..c1b8fb5cb 100644 --- a/tripleo_ansible/roles/backup-and-restore/defaults/main.yml +++ b/tripleo_ansible/roles/backup-and-restore/defaults/main.yml @@ -81,3 +81,6 @@ tripleo_backup_and_restore_remove_default_cronjob: true # Skip the ping test to the NFS server on rear setup tripleo_backup_and_restore_skip_nfs_test: false + +# How many seconds do we want to wait fir pcs cluster stop to finish +tripleo_backup_and_restore_pcs_timeout: 3600 diff --git a/tripleo_ansible/roles/backup-and-restore/tasks/main.yml b/tripleo_ansible/roles/backup-and-restore/tasks/main.yml index cf2404d25..f846d0d6f 100644 --- a/tripleo_ansible/roles/backup-and-restore/tasks/main.yml +++ b/tripleo_ansible/roles/backup-and-restore/tasks/main.yml @@ -62,7 +62,7 @@ - not tripleo_backup_and_restore_enable_snapshots|bool - name: Pacemaker management - import_tasks: ../backup/tasks/pacemaker_unstandby.yml + import_tasks: ../backup/tasks/pacemaker_start.yml when: - pacemaker_enabled - tripleo_backup_and_restore_enable_snapshots|bool