From 19ee29342f8bb573722991b8cbe4503309ad0bf9 Mon Sep 17 00:00:00 2001
From: John Eckersberg <jeckersb@redhat.com>
Date: Fri, 2 Nov 2018 13:12:53 -0400
Subject: [PATCH] rabbitmq-cluster: fix regression in rmq_stop

This regression was introduced in PR#1249 (cc23c55).  The stop action
was modified to use rmq_app_running in order to check the service
status, which allows for the following sequence of events:

- service is started, unclustered
- stop_app is called
- cluster_join is attempted and fails
- stop is called

Because stop_app was called, rmq_app_running returns $OCF_NOT_RUNNING
and the stop action is a no-op.  This means the erlang VM continues
running.

When the start action is attempted again, a new erlang VM is launched,
but this VM fails to boot because the old one is still running and is
registered with the same name (rabbit@nodename).

This adds a new function, rmq_node_alive, which does a simple eval to
test whether the erlang VM is up, independent of the rabbit app.  The
stop action now uses rmq_node_alive to check the service status, so
even if stop_app was previously called, the erlang VM will be stopped
properly.

Resolves: RHBZ#1639826
---
 heartbeat/rabbitmq-cluster | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/heartbeat/rabbitmq-cluster b/heartbeat/rabbitmq-cluster
index 78b2bbadf..a2de9dc20 100755
--- a/heartbeat/rabbitmq-cluster
+++ b/heartbeat/rabbitmq-cluster
@@ -188,6 +188,16 @@ rmq_app_running() {
 	fi
 }
 
+rmq_node_alive() {
+	if $RMQ_CTL eval 'ok.'; then
+		ocf_log debug "RabbitMQ node is alive"
+		return $OCF_SUCCESS
+	else
+		ocf_log debug "RabbitMQ node is down"
+		return $OCF_NOT_RUNNING
+	fi
+}
+
 rmq_monitor() {
 	local rc
 
@@ -514,7 +524,7 @@ rmq_stop() {
 		end.
 	"
 
-	rmq_app_running
+	rmq_node_alive
 	if [ $? -eq $OCF_NOT_RUNNING ]; then
 		return $OCF_SUCCESS
 	fi