Add panels for pacemaker monitoring in grafana-prometheus dashboards

Change-Id: Iae169994edde9dab21f97dc880b90c3e8c2f1af6

ansible/install/roles/grafana-prometheus-dashboards/templates/openstack_general_system_performance.yaml.j2

@@ -8,6 +8,7 @@
 {% set ovsagent_groups = ['controller', 'compute', '*'] %}
 {% set rabbitmq_groups = ['undercloud', 'controller', '*'] %}
 {% set swift_stat_groups = ['controller', '*'] %}
+{% set controller_groups = ['controller', '*'] %}
 ---
 dashboard:
   title: {{item.process_list_name}} General System Performance Browbeat
@@ -105,4 +106,8 @@ dashboard:
   {% include 'partials/mariadb.yaml' %}
 {% endif %}
 
+{% if item.template_node_type in controller_groups %}
+  {% include 'partials/pacemaker_monitoring.yaml' %}
+{% endif %}
+
 {% include 'partials/tail.yaml' %}

ansible/install/roles/grafana-prometheus-dashboards/templates/partials/pacemaker_monitoring.yaml

@@ -0,0 +1,150 @@
+    - title: Pacemaker Metrics
+      collapse: true
+      height: 200px
+      showTitle: true
+      panels:
+        - title: $Cloud - $Node - Pacemaker General Metrics
+          type: graph
+          legend:
+            alignAsTable: true
+            avg: false
+            current: true
+            max: true
+            min: true
+            rightSide: true
+            show: true
+            total: false
+            values: true
+          nullPointMode: 'null'
+          targets:
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='total_nodes'}
+              legendFormat: total_nodes
+              refId: A
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='online_hosts'}
+              legendFormat: online_hosts
+              refId: B
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='online_guests'}
+              legendFormat: online_guests
+              refId: C
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='resource_instances'}
+              legendFormat: resource_instances
+              refId: D
+        - title: $Cloud - $Node - Pacemaker Resource Total Count
+          type: graph
+          legend:
+            alignAsTable: true
+            avg: false
+            current: true
+            max: true
+            min: true
+            rightSide: true
+            show: true
+            total: false
+            values: true
+          nullPointMode: 'null'
+          targets:
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='cinder_resource_total_count'}
+              legendFormat: cinder_resource_total_count
+              refId: A
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='galera_resource_total_count'}
+              legendFormat: galera_resource_total_count
+              refId: B
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='haproxy_resource_total_count'}
+              legendFormat: haproxy_resource_total_count
+              refId: C
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='ovn_resource_total_count'}
+              legendFormat: ovn_resource_total_count
+              refId: D
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='rabbitmq_resource_total_count'}
+              legendFormat: rabbitmq_resource_total_count
+              refId: E
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='redis_resource_total_count'}
+              legendFormat: redis_resource_total_count
+              refId: F
+        - title: $Cloud - $Node - Pacemaker Resource Master Count
+          type: graph
+          legend:
+            alignAsTable: true
+            avg: false
+            current: true
+            max: true
+            min: true
+            rightSide: true
+            show: true
+            total: false
+            values: true
+          nullPointMode: 'null'
+          targets:
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='cinder_resource_master_count'}
+              legendFormat: cinder_resource_master_count
+              refId: A
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='galera_resource_master_count'}
+              legendFormat: galera_resource_master_count
+              refId: B
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='haproxy_resource_master_count'}
+              legendFormat: haproxy_resource_master_count
+              refId: C
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='ovn_resource_master_count'}
+              legendFormat: ovn_resource_master_count
+              refId: D
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='rabbitmq_resource_master_count'}
+              legendFormat: rabbitmq_resource_master_count
+              refId: E
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='redis_resource_master_count'}
+              legendFormat: redis_resource_master_count
+              refId: F
+        - title: $Cloud - $Node - Pacemaker Resource Failures
+          type: graph
+          legend:
+            alignAsTable: true
+            avg: false
+            current: true
+            max: true
+            min: true
+            rightSide: true
+            show: true
+            total: false
+            values: true
+          nullPointMode: 'null'
+          targets:
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='cinder_resource_failures'}
+              legendFormat: cinder_resource_failures
+              refId: A
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='galera_resource_failures'}
+              legendFormat: galera_resource_failures
+              refId: B
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='haproxy_resource_failures'}
+              legendFormat: haproxy_resource_failures
+              refId: C
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='ovn_resource_failures'}
+              legendFormat: ovn_resource_failures
+              refId: D
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='rabbitmq_resource_failures'}
+              legendFormat: rabbitmq_resource_failures
+              refId: E
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='redis_resource_failures'}
+              legendFormat: redis_resource_failures
+              refId: F
+        - title: $Cloud - $Node - Pacemaker Daemon Status
+          type: graph
+          legend:
+            alignAsTable: true
+            avg: false
+            current: true
+            max: true
+            min: true
+            rightSide: true
+            show: true
+            total: false
+            values: true
+          nullPointMode: 'null'
+          targets:
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='corosync_daemon_status'}
+              legendFormat: corosync_daemon_status
+              refId: A
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='pacemaker_daemon_status'}
+              legendFormat: pacemaker_daemon_status
+              refId: B
+            - expr: collectd_pacemaker_monitoring_gauge{exported_instance=~"[[Cloud]]_[[Node]]", pacemaker_monitoring='pcsd_daemon_status'}
+              legendFormat: pcsd_daemon_status
+              refId: C