Merge "Wait for slaves to sync before the recovery master restart." into stable/2026.1

1 files changed, 24 insertions, 0 deletions

diff --git a/ansible/roles/mariadb/tasks/recover_cluster.yml b/ansible/roles/mariadb/tasks/recover_cluster.yml
index 16f0d05fc..0592cb390 100644
--- a/ansible/roles/mariadb/tasks/recover_cluster.yml
+++ b/ansible/roles/mariadb/tasks/recover_cluster.yml
@@ -215,6 +215,30 @@
     - bootstrap_host is defined
     - bootstrap_host != inventory_hostname
 
+# The master restart below is a Galera cluster membership change. If it
+# happens while a slave is still receiving its IST, the joiner aborts with
+# "IST didn't contain all write sets ... node restart required" and stays
+# permanently disconnected, so wait for every slave to finish syncing first.
+- name: Wait for slave MariaDB to sync WSREP
+  become: true
+  kolla_toolbox:
+    container_engine: "{{ kolla_container_engine }}"
+    module_name: mysql_query
+    module_args:
+      login_db: "mysql"
+      login_host: "{{ api_interface_address }}"
+      login_port: "{{ mariadb_port }}"
+      login_user: "{{ database_user }}"
+      login_password: "{{ database_password }}"
+      query: 'SHOW STATUS LIKE "wsrep_local_state_comment"'
+  register: result
+  until: result.query_result is defined and result.query_result[0][0]['Value'] == "Synced"
+  retries: 30
+  delay: 10
+  when:
+    - bootstrap_host is defined
+    - bootstrap_host != inventory_hostname
+
 - name: Unset pc.bootstrap for primary MariaDB galera.cnf for next restart
   vars:
     service_name: "mariadb"