[ovs-dev] [PATCH] OVN pacemaker: Add the monitor action for Master role

[nusiddiq at redhat.com]

From: Numan Siddique <nusiddiq at redhat.com>

Pacemaker Resource agent periodically calls the OVN OCF's "monitor" action
periodically to check the status. But the OVN OCF script doesn't add the
action "monitor" for the role "Master" because of which the pacemaker
resource agent do not call the "monitor" action at all for the master.
In case OVN db servers exit for some reason this totally gets undetected
and one of the standby node is not promoted to master.

This patch adds the monitor action for "Master" role. Also the monitor
action do not check for the status of the ovn-northd (if manage_northd is yes).
This patch also checks for the status of the ovn-northd in the monitor action
for the "Master" role. If any of the ovsdb-server or ovn-northd is not running,
monitor action will return OCF_NOT_RUNNING and this will cause the pacemaker
to restart the OVN OCF resource.

Reported-at: https://bugzilla.redhat.com/show_bug.cgi?id=1512568
Signed-off-by: Numan Siddique <nusiddiq at redhat.com>
CC: Andy Zhou <azhou at ovn.org>
---
 ovn/utilities/ovndb-servers.ocf | 51 +++++++++++++++++++++++++++++++++--------
 1 file changed, 41 insertions(+), 10 deletions(-)

diff --git a/ovn/utilities/ovndb-servers.ocf b/ovn/utilities/ovndb-servers.ocf
index 3f3008700..aec94ce42 100755
--- a/ovn/utilities/ovndb-servers.ocf
+++ b/ovn/utilities/ovndb-servers.ocf
@@ -26,7 +26,7 @@ INACTIVE_PROBE=${OCF_RESKEY_inactive_probe_interval:-${INACTIVE_PROBE_DEFAULT}}
 # a master is promoted and the IPAddr2 resource is started.
 INVALID_IP_ADDRESS=192.0.2.254
 
-host_name=$(ocf_local_nodename)
+host_name=$(ocf_attribute_target)
 : ${slave_score=5}
 : ${master_score=10}
 
@@ -120,7 +120,11 @@ ovsdb_server_metadata() {
     <action name="stop"         timeout="20s" />
     <action name="promote"      timeout="50s" />
     <action name="demote"       timeout="50s" />
-    <action name="monitor"      timeout="20s"  depth="0" interval="10s" />
+    <action name="monitor"      timeout="20s"  depth="0" interval="30s" />
+    <action name="monitor"      timeout="20s"  depth="0" interval="10s"
+     role="Master" />
+    <action name="monitor"      timeout="20s"  depth="0" interval="30s"
+     role="Slave"/>
     <action name="meta-data"    timeout="5s" />
     <action name="validate-all" timeout="20s" />
   </actions>
@@ -247,7 +251,7 @@ ovsdb_server_master_update() {
 }
 
 ovsdb_server_monitor() {
-    ovsdb_server_check_status
+    ovsdb_server_check_status $@
     rc=$?
 
     ovsdb_server_master_update $rc
@@ -262,8 +266,21 @@ ovsdb_server_check_status() {
         return $OCF_SUCCESS
     fi
 
+    check_northd="no"
+    if [ "$MANAGE_NORTHD" == "yes" ] && [ "$1" != "ignore_northd" ]; then
+        check_northd="yes"
+    fi
+
     if [[ $sb_status == "running/active" && $nb_status == "running/active" ]]; then
-        return $OCF_RUNNING_MASTER
+        if [ "$check_northd" == "yes" ]; then
+            # Verify if ovn-northd is running or not.
+            ${OVN_CTL} status_northd | grep "ovn-northd is running"
+            if [ "$?" == "0" ] ; then
+                return $OCF_RUNNING_MASTER
+            fi
+        else
+            return $OCF_RUNNING_MASTER
+        fi
     fi
 
     # TODO: What about service running but not in either state above?
@@ -317,8 +334,13 @@ ovsdb_server_start() {
     $@ start_ovsdb
 
     while [ 1 = 1 ]; do
-        # It is important that we don't return until we're in a functional state
-        ovsdb_server_monitor
+        # It is important that we don't return until we're in a functional
+        # state. When checking the status of the ovsdb-server's ignore northd.
+        # It is possible that when the resource is restarted ovsdb-server's
+        # can be started as masters and ovn-northd would not have been started.
+        # ovn-northd will be started once a node is promoted to master and
+        # 'manage_northd' is set to yes.
+        ovsdb_server_monitor ignore_northd
         rc=$?
         case $rc in
             $OCF_SUCCESS)        return $rc;;
@@ -350,7 +372,7 @@ ovsdb_server_stop() {
         ${OVN_CTL} --ovn-manage-ovsdb=no stop_northd
     fi
 
-    ovsdb_server_check_status
+    ovsdb_server_check_status ignore_northd
     case $? in
         $OCF_NOT_RUNNING)    return ${OCF_SUCCESS};;
     esac
@@ -360,7 +382,7 @@ ovsdb_server_stop() {
 
     while [ 1 = 1 ]; do
         # It is important that we don't return until we're stopped
-        ovsdb_server_check_status
+        ovsdb_server_check_status ignore_northd
         rc=$?
         case $rc in
         $OCF_SUCCESS)
@@ -381,7 +403,7 @@ ovsdb_server_stop() {
 }
 
 ovsdb_server_promote() {
-    ovsdb_server_check_status
+    ovsdb_server_check_status ignore_northd
     rc=$?
     case $rc in
         ${OCF_SUCCESS}) ;;
@@ -395,6 +417,11 @@ ovsdb_server_promote() {
     ${OVN_CTL} promote_ovnnb
     ${OVN_CTL} promote_ovnsb
 
+    if [ "$MANAGE_NORTHD" = "yes" ]; then
+        # Startup ovn-northd service
+        ${OVN_CTL} --ovn-manage-ovsdb=no start_northd
+    fi
+
     ocf_log debug "ovndb_servers: Promoting $host_name as the master"
     # Record ourselves so that the agent has a better chance of doing
     # the right thing at startup
@@ -404,7 +431,7 @@ ovsdb_server_promote() {
 }
 
 ovsdb_server_demote() {
-    ovsdb_server_check_status
+    ovsdb_server_check_status ignore_northd
     if [ $? = $OCF_NOT_RUNNING ]; then
         return $OCF_NOT_RUNNING
     fi
@@ -452,6 +479,10 @@ ovsdb_server_demote() {
         ${OVN_CTL} demote_ovnsb --db-sb-sync-from-addr=${INVALID_IP_ADDRESS}
     fi
 
+    if [ "$MANAGE_NORTHD" = "yes" ]; then
+        # Stop ovn-northd service
+        ${OVN_CTL} --ovn-manage-ovsdb=no stop_northd
+    fi
     ovsdb_server_master_update $OCF_SUCCESS
     return $OCF_SUCCESS
 }
-- 
2.13.5