From ead33b23ddf6e57148149af2c73af53f09de0d5d Mon Sep 17 00:00:00 2001 From: Viktor Barzin Date: Sun, 8 Mar 2026 17:13:03 +0000 Subject: [PATCH] enable MySQL InnoDB Cluster auto-recovery after crashes Previously manualStartOnBoot=true and exitStateAction=ABORT_SERVER meant any ungraceful shutdown required manual rebootClusterFromCompleteOutage(). New settings: - group_replication_start_on_boot=ON: auto-start GR after crash - autorejoin_tries=2016: retry rejoining for ~28 minutes - exit_state_action=OFFLINE_MODE: stay alive on expulsion (don't abort) - member_expel_timeout=30s: tolerate brief unresponsiveness - unreachable_majority_timeout=60s: leave group cleanly if majority lost --- stacks/platform/modules/dbaas/main.tf | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/stacks/platform/modules/dbaas/main.tf b/stacks/platform/modules/dbaas/main.tf index 359e4cd5..c223b30e 100644 --- a/stacks/platform/modules/dbaas/main.tf +++ b/stacks/platform/modules/dbaas/main.tf @@ -143,6 +143,12 @@ resource "helm_release" "mysql_cluster" { "my.cnf" = <<-EOT [mysqld] skip-name-resolve + # Auto-recovery after crashes: rejoin group without manual intervention + group_replication_autorejoin_tries=2016 + group_replication_exit_state_action=OFFLINE_MODE + group_replication_member_expel_timeout=30 + group_replication_unreachable_majority_timeout=60 + group_replication_start_on_boot=ON EOT }