From 47d75f8de9dc912da035805f141c674885ce432f Mon Sep 17 00:00:00 2001 From: John Eckersberg Date: Thu, 16 Jan 2020 10:20:59 -0500 Subject: [PATCH] rabbitmq-cluster: ensure we delete nodename if stop action fails If the stop action fails, we want to remove the nodename from the crm attribute. Currently it is possible for the stop action to fail but the rabbitmq server does actually stop. This leaves the attribute still present. This means if the entire rabbitmq cluster is stopped, it is not possible to start the cluster again because the first node to start will think there is at least one other node running. Then the node tries to join an existing cluster instead of rebootstrapping the cluster from a single node. --- heartbeat/rabbitmq-cluster | 2 ++ 1 file changed, 2 insertions(+) diff --git a/heartbeat/rabbitmq-cluster b/heartbeat/rabbitmq-cluster index 7837e9e3c..a9ebd37ad 100755 --- a/heartbeat/rabbitmq-cluster +++ b/heartbeat/rabbitmq-cluster @@ -552,6 +552,7 @@ rmq_stop() { if [ $rc -ne 0 ]; then ocf_log err "rabbitmq-server stop command failed: $RMQ_CTL stop, $rc" + rmq_delete_nodename return $rc fi @@ -565,6 +566,7 @@ rmq_stop() { break elif [ "$rc" -ne $OCF_SUCCESS ]; then ocf_log info "rabbitmq-server stop failed: $rc" + rmq_delete_nodename exit $OCF_ERR_GENERIC fi sleep 1