From bde7c0d4a64c02350ef169060d0218fbf46569c5 Mon Sep 17 00:00:00 2001
From: Bogdan Dobrelya <bdobrelia@mirantis.com>
Date: Thu, 7 Jan 2016 13:39:27 +0100
Subject: [PATCH] Fix rabbitMQ OCF monitor detection of running master

When monitor detected the node as OCF_RUNNING_MASTER, this may be
lost while the monitor checks in progress.
* Rework the prev_rc by the rc_check to fix this.
* Also add info log if detected as running master.
* Break the monitor check loop early, if it shall be exiting to be
  restarted by pacemaker.
* Do not recheck the master status and do not update the master score,
  if the node was already detected by monitor as OCF_RUNNING_MASTER.
  By that point, the running and healthy master shall not be checked
  against other nodes uptime as it is pointless and only takes more
  time and resources for the action monitor to finish.
* Fail early, if monitor detected the node as OCF_RUNNING_MASTER, but
  the rabbit beam process is not running
* For OCF_CHECK_LEVEL>20, exclude the current node from the check
  loop as we already checked it before

Closes-bug: #1531838

Change-Id: I319db307c73ef24d829be44eeb63d1f52f4180fa
Signed-off-by: Bogdan Dobrelya <bdobrelia@mirantis.com>
---
 files/fuel-ha-utils/ocf/rabbitmq | 42 ++++++++++++++++++--------------
 1 file changed, 24 insertions(+), 18 deletions(-)

diff --git a/files/fuel-ha-utils/ocf/rabbitmq b/files/fuel-ha-utils/ocf/rabbitmq
index 2f5d32884d..ae5f1978ad 100755
--- a/files/fuel-ha-utils/ocf/rabbitmq
+++ b/files/fuel-ha-utils/ocf/rabbitmq
@@ -1343,12 +1343,12 @@ wait_sync() {
 get_monitor() {
     local rc=$OCF_ERR_GENERIC
     local LH="${LL} get_monitor():"
-    local status_master
+    local status_master=1
     local rabbit_running
     local name
     local node
     local nodelist
-    local prev_rc
+    local rc_check
     local max
     local our_uptime
     local node_uptime
@@ -1372,7 +1372,11 @@ get_monitor() {
         ocf_log info "${LH} master attribute is ${status_master}"
         if [ $status_master -eq 0 -a $rabbit_running -eq $OCF_SUCCESS ]
         then
+            ocf_log info "${LH} We are the running master"
             rc=$OCF_RUNNING_MASTER
+        elif [ $status_master -eq 0 -a $rabbit_running -ne $OCF_SUCCESS ] ; then
+            ocf_log err "${LH} We are the master and RMQ-runtime (beam) is not running. this is a failure"
+            exit $OCF_FAILED_MASTER
         fi
     fi
     get_status rabbit
@@ -1382,56 +1386,58 @@ get_monitor() {
     if [ $rabbit_running -eq $OCF_SUCCESS ]
     then
             ocf_log info "${LH} rabbit app is running. checking if we are the part of healthy cluster"
-            prev_rc=$rc
+            rc_check=$OCF_ERR_GENERIC
             nodelist=$(get_alive_pacemaker_nodes_but)
             for node in $nodelist
             do
-                ocf_log info "${LH} rabbit app is running. looking for master on $node"
-                is_master $node
-                status_master=$?
-                ocf_log info "${LH} fetched master attribute for $node. attr value is ${status_master}"
+                # Do not refetch the master status for *this* node as we know it already
+                if [ $rc -ne $OCF_RUNNING_MASTER ] ; then
+                    ocf_log info "${LH} rabbit app is running. looking for master on $node"
+                    is_master $node
+                    status_master=$?
+                    ocf_log info "${LH} fetched master attribute for $node. attr value is ${status_master}"
+                fi
                 if [ $status_master -eq 0 ] ; then
-                    rc=$OCF_ERR_GENERIC
                     ocf_log info "${LH} rabbit app is running. master is $node"
                     if get_running_nodes | grep -q $(rabbit_node_name $node)
                     then
                         ocf_log info "${LH} rabbit app is running and is member of healthy cluster"
-                        rc=$prev_rc
+                        rc_check=$OCF_SUCCESS
                         break
                     fi
                 fi
             done
-            [ $rc -eq $OCF_ERR_GENERIC ] && ocf_log err "${LH} rabbit node is running out of the cluster"
+            [ $rc_check -eq $OCF_ERR_GENERIC ] && ocf_log err "${LH} rabbit node is running out of the cluster"
     else
       if [ "$OCF_CHECK_LEVEL" -gt 20 ]; then
             ocf_log info "${LH} rabbit app is not running. checking if there is a master"
-            prev_rc=$rc
-            is_master $THIS_PCMK_NODE
-            i_am_master=$?
-            if [ $i_am_master -eq 0 ]; then
+            # Do not refetch the master status as we know it already
+            if [ $rc -eq $OCF_RUNNING_MASTER ]; then
               ocf_log err "${LH} we are the master and rabbit app is not running. this is a failure"
               exit $OCF_FAILED_MASTER
             fi
-            nodelist=$(get_alive_pacemaker_nodes_but)
+            nodelist=$(get_alive_pacemaker_nodes_but $THIS_PCMK_NODE)
+            rc_check=$OCF_SUCCESS
             for node in $nodelist
             do
                 is_master $node
                 status_master=$?
                 ocf_log info "${LH} fetched master attribute for $node. attr value is ${status_master}"
                 if [ $status_master -eq 0 ] ; then
-                    rc=$OCF_ERR_GENERIC
+                    rc_check=$OCF_ERR_GENERIC
                     ocf_log info "${LH} rabbit app is not running. master is $node. exiting to be restarted by pacemaker"
+                    break
                 fi
             done
       fi
     fi
 
-    if [ $rc -eq $OCF_ERR_GENERIC ]; then
+    if [ $rc -eq $OCF_ERR_GENERIC -o $rc_check -eq $OCF_ERR_GENERIC ]; then
         ocf_log err "${LH} get_status() returns generic error ${rc}"
         ocf_log info "${LH} ensuring this slave does not get promoted."
         master_score 0
         return $OCF_ERR_GENERIC
-    else
+    elif [ $rc -ne $OCF_RUNNING_MASTER ] ; then
         ocf_log info "${LH} preparing to update master score for node"
         our_uptime=$(srv_uptime)
         nodelist=$(get_alive_pacemaker_nodes_but $THIS_PCMK_NODE)