feat: PSI metrics

templates/templates.cfg.j2

@@ -119,6 +119,12 @@ define servicegroup{
         members                 {{ groups.all | default([]) | map('extract', hostvars, ['inventory_hostname']) | sort | join(',Charge RAM,') }},Charge RAM
         }
 
+define servicegroup{
+        servicegroup_name       psi
+        alias                   PSI
+        members                 {{ groups.full_maintenance | default([]) | map('extract', hostvars, ['inventory_hostname']) | sort | join(',PSI CPU,') }},PSI CPU,{{ groups.full_maintenance | default([]) | map('extract', hostvars, ['inventory_hostname']) | sort | join(',PSI IO,') }},PSI IO,{{ groups.full_maintenance | default([]) | map('extract', hostvars, ['inventory_hostname']) | sort | join(',PSI memory,') }},PSI memory
+        }
+
 {% endif %}
 {% if 'full_maintenance' in groups %}
 define servicegroup{
@@ -200,6 +206,31 @@ define service{
         register                        0                       ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL SERVICE, JUST A TEMPLATE!
         }
 
+define service{
+        name                            often-checked-service         ; The 'name' of this service template
+        active_checks_enabled           1                       ; Active service checks are enabled
+        passive_checks_enabled          1                       ; Passive service checks are enabled/accepted
+        parallelize_check               1                       ; Active service checks should be parallelized (disabling this can lead to major performance problems)
+        obsess_over_service             1                       ; We should obsess over this service (if necessary)
+        check_freshness                 0                       ; Default is to NOT check service 'freshness'
+        notifications_enabled           1                       ; Service notifications are enabled
+        event_handler_enabled           1                       ; Service event handler is enabled
+        flap_detection_enabled          1                       ; Flap detection is enabled
+        process_perf_data               1                       ; Process performance data
+        retain_status_information       1                       ; Retain status information across program restarts
+        retain_nonstatus_information    1                       ; Retain non-status information across program restarts
+        is_volatile                     0                       ; The service is not volatile
+        check_period                    24x7                    ; The service can be checked at any time of the day
+        max_check_attempts              3                       ; Re-check the service up to 3 times in order to determine its final (hard) state
+        check_interval                  1                       ; Check the service every 10 minutes under normal conditions
+        retry_interval                  2                       ; Re-check the service every two minutes until a hard state can be determined
+        contact_groups                  admins                  ; Notifications get sent out to everyone in the 'admins' group
+        notification_options            w,u,c,r                 ; Send notifications about warning, unknown, critical, and recovery events
+        notification_interval           120                     ; Re-notify about service problems every two hours
+        notification_period             heures-ouvres           ; Notifications can be sent out at any time during working hours
+        register                        0                       ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL SERVICE, JUST A TEMPLATE!
+        }
+
 
 # Daily service definition template - This is NOT a real service, just a template!
 

templates/vps.cfg.j2

@@ -211,6 +211,30 @@ define service{
         check_command                   check_nrpe!check_mem
         }
 
+# Define a service to check cpu PSI on the local machine.
+define service{
+        use                             often-checked-service,graphed-service
+        host_name                       {{ groups['full_maintenance'] | map('extract', hostvars, ['inventory_hostname']) | sort | join(',') }}
+        service_description             PSI CPU
+        check_command                   check_nrpe!check_psi_cpu
+        }
+
+# Define a service to check io PSI on the local machine.
+define service{
+        use                             often-checked-service,graphed-service
+        host_name                       {{ groups['full_maintenance'] | map('extract', hostvars, ['inventory_hostname']) | sort | join(',') }}
+        service_description             PSI IO
+        check_command                   check_nrpe!check_psi_io
+        }
+
+# Define a service to check memory PSI on the local machine.
+define service{
+        use                             often-checked-service,graphed-service
+        host_name                       {{ groups['full_maintenance'] | map('extract', hostvars, ['inventory_hostname']) | sort | join(',') }}
+        service_description             PSI memory
+        check_command                   check_nrpe!check_psi_memory
+        }
+
 # SSH
 define service{
         use                             generic-service