Merge pull request ansible#12908 from rebeccahhh/devel

new example grafana alert rule
rebeccahhh · Sep 26, 2022 · a66b27e · a66b27e
2 parents 93f50b5 + 88f0ab0
commit a66b27e
Show file tree

Hide file tree

Showing 3 changed files with 226 additions and 9 deletions.
diff --git a/tools/docker-compose/README.md b/tools/docker-compose/README.md
@@ -483,5 +483,11 @@ $ PROMETHEUS=yes GRAFANA=yes make docker-compose
 
 ### Alerts in Grafana
 
-We are configuring alerts in grafana using the provisioning files method. This feature is new in Grafana as of August, 2022. Documentation can be found: https://grafana.com/docs/grafana/latest/administration/provisioning/#alerting however it does not fully show all parameters to the config. One way to understand how to build rules is to build them in the UI and use chrometools to inspect the payload as you save the rules. It appears that the "data" portion of the payload for each rule is the same syntax as needed in the provisioning file config. To reload the alerts without restarting the container, from within the container you can send a POST with `curl -X POST http://admin:admin@localhost:3000/api/admin/provisioning/alerting/relo
-ad`. Keep in mind the grafana container does not default contain `curl` and you can get it with `apk add curl`. 
+We are configuring alerts in grafana using the provisioning files method. This feature is new in Grafana as of August, 2022. Documentation can be found: https://grafana.com/docs/grafana/latest/administration/provisioning/#alerting however it does not fully show all parameters to the config.
+
+One way to understand how to build rules is to build them in the UI and use chrometools to inspect the payload as you save the rules. It appears that the "data" portion of the payload for each rule is the same syntax as needed in the provisioning file config. To reload the alerts without restarting the container, from within the container you can send a POST with `curl -X POST http://admin:admin@localhost:3000/api/admin/provisioning/alerting/reload`. Keep in mind the grafana container does not contain `curl`. You can install it with the command `apk add curl`.
+
+Another way to export rules is explore the api.
+1. Get all the folders:  `GET` to `/api/folders`
+2. Get the rules `GET` to `/api/ruler/grafana/api/v1/rules/{{ Folder }}`
+
diff --git a/tools/grafana/alerting/alerts.yml b/tools/grafana/alerting/alerts.yml
@@ -6,10 +6,167 @@ groups:
     name: awx_rules
     orgId: 1
     rules:
-      - condition: A
+      - condition: if_failures_too_high
         dashboardUid: awx
         data:
-          - datasourceUid: PBFA97CFB590B2093
+          - refId: total_errors
+            queryType: ''
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: awx_alert
+            model:
+              editorMode: code
+              expr: >-
+                max(delta(awx_instance_status_total{instance="awx1:8013",
+                status="failed|error"}[30m]))
+              hide: false
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: true
+              refId: total_errors
+          - refId: max_errors
+            queryType: ''
+            relativeTimeRange:
+              from: 0
+              to: 0
+            datasourceUid: '-100'
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 80
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                      - total_errors
+                  reducer:
+                    params: []
+                    type: max
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: total_errors
+              hide: false
+              intervalMs: 1000
+              maxDataPoints: 43200
+              reducer: max
+              refId: max_errors
+              type: reduce
+          - refId: total_success
+            queryType: ''
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: awx_alert
+            model:
+              datasource:
+                type: prometheus
+                uid: awx_alert
+              editorMode: code
+              expr: >-
+                max(delta(awx_instance_status_total{instance="awx1:8013",
+                status="successful"}[30m]))
+              hide: false
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: true
+              refId: total_success
+          - refId: max_success
+            queryType: ''
+            relativeTimeRange:
+              from: 0
+              to: 0
+            datasourceUid: '-100'
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                      - total_success
+                  reducer:
+                    params: []
+                    type: max
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: total_success
+              hide: false
+              intervalMs: 1000
+              maxDataPoints: 43200
+              reducer: max
+              refId: max_success
+              type: reduce
+          - refId: compare
+            queryType: ''
+            relativeTimeRange:
+              from: 0
+              to: 0
+            datasourceUid: '-100'
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                      - max_success
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                      - max_success
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: $max_errors / ($max_errors+$max_success) >= .2
+              hide: false
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: compare
+              type: math
+        for: 30m
+        noDataState: OK
+        panelId: 2
+        title: failure_rate_exceeded_20_percent
+        uid: failure_rate_exceeded_20_percent
+      - condition: if_redis_queue_too_large
+        dashboardUid: awx
+        data:
+          - datasourceUid: awx_alert
             model:
               editorMode: code
               expr: irate(callback_receiver_events_insert_db{node='awx_1'}[1m])
@@ -55,11 +212,11 @@ groups:
             relativeTimeRange:
               from: 0
               to: 0
-          - datasourceUid: PBFA97CFB590B2093
+          - datasourceUid: awx_alert
             model:
               datasource:
                 type: prometheus
-                uid: PBFA97CFB590B2093
+                uid: awx_alert
               editorMode: code
               expr: callback_receiver_events_queue_size_redis{node='awx_1'}
               hide: false
@@ -125,9 +282,7 @@ groups:
                 name: Expression
                 type: __expr__
                 uid: __expr__
-              expression: '(
-                ${mean_redis_queue_size} >
-                ($mean_event_insertion_rate\ * 120))'
+              expression: '($mean_redis_queue_size > ($mean_event_insertion_rate * 120))'
               hide: false
               intervalMs: 1000
               maxDataPoints: 43200
@@ -143,3 +298,58 @@ groups:
         panelId: 1
         title: redis_queue_too_large_to_clear_in_2_min
         uid: redis_queue_too_large_to_clear_in_2_min
+      - condition: if_capacity_is_too_low
+        dashboardUid: awx
+        no_data_state: OK
+        exec_err_state: Error
+        data:
+          - refId: remaining_capacity
+            queryType: ''
+            relativeTimeRange:
+              from: 1800
+              to: 0
+            datasourceUid: awx_alert
+            model:
+              editorMode: builder
+              expr: awx_instance_remaining_capacity{instance="awx1:8013"}
+              hide: false
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: true
+              refId: remaining_capacity
+          - refId: if_capacity_is_too_low
+            queryType: ''
+            relativeTimeRange:
+              from: 0
+              to: 0
+            datasourceUid: "-100"
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 20
+                      - 0
+                    type: lt
+                  operator:
+                    type: when
+                  query:
+                    params:
+                      - remaining_capacity
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: remaining_capacity
+              hide: false
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: if_capacity_is_too_low
+              type: classic_conditions
+        for: 30m
+        title: if_capacity_is_too_low
+        uid: if_capacity_is_too_low
diff --git a/tools/grafana/datasources/prometheus_source.yml b/tools/grafana/datasources/prometheus_source.yml
@@ -10,3 +10,4 @@ datasources:
     editable: true
     jsonData:
       timeInterval: 5s
+    uid: awx_alert