Add some examples of per-queue alerts/dashboards (#865)

* Add some examples of per-queue alerts/dashboards * Use cleanly exported grafana dashboard definition Co-authored-by: Alexey Lebedeff <[email protected]>
rabbitmq · Oct 14, 2021 · 2446575 · 2446575
1 parent d4312c7
commit 2446575
Show file tree

Hide file tree

Showing 5 changed files with 387 additions and 0 deletions.
diff --git a/observability/grafana/dashboards/rabbitmq-queue.yml b/observability/grafana/dashboards/rabbitmq-queue.yml
@@ -0,0 +1,304 @@
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: rabbitmq-queue-grafana-dashboard
+  labels:
+    grafana_dashboard: "1"
+data:
+  rabbitmq-queue-grafana-dashboard.json: |-
+    {
+      "__inputs": [
+        {
+          "name": "DS_PROMETHEUS",
+          "label": "Prometheus",
+          "description": "",
+          "type": "datasource",
+          "pluginId": "prometheus",
+          "pluginName": "Prometheus"
+        }
+      ],
+      "__requires": [
+        {
+          "type": "grafana",
+          "id": "grafana",
+          "name": "Grafana",
+          "version": "7.5.3"
+        },
+        {
+          "type": "datasource",
+          "id": "prometheus",
+          "name": "Prometheus",
+          "version": "1.0.0"
+        },
+        {
+          "type": "panel",
+          "id": "timeseries",
+          "name": "Time series",
+          "version": ""
+        }
+      ],
+      "annotations": {
+        "list": [
+          {
+            "builtIn": 1,
+            "datasource": "-- Grafana --",
+            "enable": true,
+            "hide": true,
+            "iconColor": "rgba(0, 211, 255, 1)",
+            "name": "Annotations & Alerts",
+            "type": "dashboard"
+          }
+        ]
+      },
+      "editable": true,
+      "gnetId": null,
+      "graphTooltip": 0,
+      "id": null,
+      "iteration": 1633508002435,
+      "links": [],
+      "panels": [
+        {
+          "datasource": null,
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisLabel": "Messages",
+                "axisPlacement": "left",
+                "axisSoftMin": 0,
+                "barAlignment": 0,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "graph": false,
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "auto",
+                "spanNulls": false
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  },
+                  {
+                    "color": "red",
+                    "value": 80
+                  }
+                ]
+              }
+            },
+            "overrides": [
+              {
+                "matcher": {
+                  "id": "byName",
+                  "options": "Consumers"
+                },
+                "properties": [
+                  {
+                    "id": "custom.axisPlacement",
+                    "value": "right"
+                  },
+                  {
+                    "id": "unit",
+                    "value": "prefix:"
+                  },
+                  {
+                    "id": "custom.axisLabel",
+                    "value": "Consumers"
+                  }
+                ]
+              },
+              {
+                "matcher": {
+                  "id": "byName",
+                  "options": "Messages"
+                },
+                "properties": [
+                  {
+                    "id": "custom.drawStyle",
+                    "value": "line"
+                  },
+                  {
+                    "id": "custom.fillOpacity",
+                    "value": 0
+                  }
+                ]
+              }
+            ]
+          },
+          "gridPos": {
+            "h": 17,
+            "w": 11,
+            "x": 0,
+            "y": 0
+          },
+          "id": 2,
+          "options": {
+            "legend": {
+              "calcs": [],
+              "displayMode": "list",
+              "placement": "bottom"
+            },
+            "tooltip": {
+              "mode": "single"
+            },
+            "tooltipOptions": {
+              "mode": "single"
+            }
+          },
+          "targets": [
+            {
+              "exemplar": true,
+              "expr": "(rabbitmq_detailed_queue_messages{namespace=\"$namespace\", queue=\"$queue\"} * on (instance, job) rabbitmq_identity_info{namespace=\"$namespace\",rabbitmq_cluster=\"$rabbitmq_cluster\"})",
+              "interval": "",
+              "legendFormat": "Messages",
+              "refId": "A"
+            },
+            {
+              "exemplar": true,
+              "expr": "rabbitmq_detailed_queue_consumers{namespace=\"$namespace\", queue=\"$queue\"} * on (instance, job) rabbitmq_identity_info{namespace=\"$namespace\",rabbitmq_cluster=\"$rabbitmq_cluster\"}",
+              "hide": false,
+              "interval": "",
+              "legendFormat": "Consumers",
+              "refId": "B"
+            }
+          ],
+          "title": "Queue messages and consumers",
+          "type": "timeseries"
+        }
+      ],
+      "refresh": false,
+      "schemaVersion": 27,
+      "style": "dark",
+      "tags": [],
+      "templating": {
+        "list": [
+          {
+            "current": {
+              "selected": false,
+              "text": "Prometheus",
+              "value": "Prometheus"
+            },
+            "description": null,
+            "error": null,
+            "hide": 2,
+            "includeAll": false,
+            "label": "datasource",
+            "multi": false,
+            "name": "DS_PROMETHEUS",
+            "options": [],
+            "query": "prometheus",
+            "refresh": 1,
+            "regex": "",
+            "skipUrlSync": false,
+            "type": "datasource"
+          },
+          {
+            "allValue": null,
+            "current": {},
+            "datasource": "${DS_PROMETHEUS}",
+            "definition": "label_values(rabbitmq_identity_info, namespace)",
+            "description": null,
+            "error": null,
+            "hide": 0,
+            "includeAll": false,
+            "label": "Namespace",
+            "multi": false,
+            "name": "namespace",
+            "options": [],
+            "query": {
+              "query": "label_values(rabbitmq_identity_info, namespace)",
+              "refId": "StandardVariableQuery"
+            },
+            "refresh": 2,
+            "regex": "",
+            "skipUrlSync": false,
+            "sort": 1,
+            "tagValuesQuery": "",
+            "tags": [],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+          },
+          {
+            "allValue": null,
+            "current": {},
+            "datasource": "${DS_PROMETHEUS}",
+            "definition": "label_values(rabbitmq_identity_info{namespace=\"$namespace\"}, rabbitmq_cluster)",
+            "description": null,
+            "error": null,
+            "hide": 0,
+            "includeAll": false,
+            "label": "RabbitMQ Cluster",
+            "multi": false,
+            "name": "rabbitmq_cluster",
+            "options": [],
+            "query": {
+              "query": "label_values(rabbitmq_identity_info{namespace=\"$namespace\"}, rabbitmq_cluster)",
+              "refId": "StandardVariableQuery"
+            },
+            "refresh": 2,
+            "regex": "",
+            "skipUrlSync": false,
+            "sort": 1,
+            "tagValuesQuery": "",
+            "tags": [],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+          },
+          {
+            "allValue": null,
+            "current": {},
+            "datasource": "${DS_PROMETHEUS}",
+            "definition": "query_result(rabbitmq_detailed_queue_messages{namespace=\"$namespace\"} * on (instance, job) group_left(rabbitmq_cluster) rabbitmq_identity_info{namespace=\"$namespace\"})",
+            "description": null,
+            "error": null,
+            "hide": 0,
+            "includeAll": false,
+            "label": "Queue",
+            "multi": false,
+            "name": "queue",
+            "options": [],
+            "query": {
+              "query": "query_result(rabbitmq_detailed_queue_messages{namespace=\"$namespace\"} * on (instance, job) group_left(rabbitmq_cluster) rabbitmq_identity_info{namespace=\"$namespace\", rabbitmq_cluster=\"$rabbitmq_cluster\"})",
+              "refId": "StandardVariableQuery"
+            },
+            "refresh": 2,
+            "regex": "/.*queue=\"([^\"]+)\".*/",
+            "skipUrlSync": false,
+            "sort": 0,
+            "tagValuesQuery": "",
+            "tags": [],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+          }
+        ]
+      },
+      "time": {
+        "from": "now-6h",
+        "to": "now"
+      },
+      "timepicker": {},
+      "timezone": "",
+      "title": "RabbitMQ-Queue",
+      "uid": "j9t8vwH7k",
+      "version": 1
+    }
diff --git a/observability/prometheus/monitors/rabbitmq-servicemonitor.yml b/observability/prometheus/monitors/rabbitmq-servicemonitor.yml
@@ -16,6 +16,26 @@ spec:
     scrapeTimeout: 14s
     tlsConfig:
       insecureSkipVerify: true
+  - port: prometheus
+    scheme: http
+    path: /metrics/detailed
+    params:
+      family:
+        - queue_coarse_metrics
+        - queue_metrics
+    interval: 15s
+    scrapeTimeout: 14s
+  - port: prometheus-tls
+    scheme: https
+    path: /metrics/detailed
+    params:
+      family:
+        - queue_coarse_metrics
+        - queue_metrics
+    interval: 15s
+    scrapeTimeout: 14s
+    tlsConfig:
+      insecureSkipVerify: true
   selector:
     matchLabels:
       app.kubernetes.io/component: rabbitmq

diff --git a/observability/prometheus/rules/rabbitmq-per-object/README.md b/observability/prometheus/rules/rabbitmq-per-object/README.md
@@ -0,0 +1,5 @@
+# RabbitMQ per-object rules
+
+RabbitMQ >= 3.9.8 is required for functioning of these alerts.
+
+Also they are highly opinionated and probably require some tuning before applying, e.g. filtering by specific queue names.
diff --git a/observability/prometheus/rules/rabbitmq-per-object/queue-has-no-consumers.yml b/observability/prometheus/rules/rabbitmq-per-object/queue-has-no-consumers.yml
@@ -0,0 +1,29 @@
+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: rabbitmq-queue-has-no-consumers
+  # If labels are defined in spec.ruleSelector.matchLabels of your deployed Prometheus object, make sure to include them here.
+  labels:
+    role: alert-rules
+spec:
+  groups:
+  - name: rabbitmq
+    rules:
+    - alert: QueueHasNoConsumers
+      expr: |
+          (
+            ((rabbitmq_detailed_queue_consumers{vhost="/", queue=~".*"} == 0) + rabbitmq_detailed_queue_messages) > 0
+          ) * on (instance, job) group_left(rabbitmq_cluster) rabbitmq_identity_info
+      for: 10m
+      annotations:
+        description: |
+          Over the last 10 minutes, non-empty queue `{{ $labels.queue }}` with {{ $value }} messages
+          in virtual host `{{ $labels.vhost }}` didn't have any consumers in
+          RabbitMQ cluster `{{ $labels.rabbitmq_cluster }}` in namespace `{{ $labels.namespace }}`.
+        summary: |
+          Messages are sitting idle in the queue, without any processing.
+          This alert is highly application specific (and e.g. doesn't make sense for stream queues).
+      labels:
+        rulesgroup: rabbitmq
+        severity: warning
diff --git a/observability/prometheus/rules/rabbitmq-per-object/queue-is-growing.yml b/observability/prometheus/rules/rabbitmq-per-object/queue-is-growing.yml
@@ -0,0 +1,29 @@
+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: rabbitmq-queue-is-growing
+  # If labels are defined in spec.ruleSelector.matchLabels of your deployed Prometheus object, make sure to include them here.
+  labels:
+    role: alert-rules
+spec:
+  groups:
+  - name: rabbitmq
+    rules:
+    - alert: QueueIsGrowing
+      # `> 1` because of floating point rounding errors
+      expr: |
+          (
+              avg_over_time(rabbitmq_detailed_queue_messages[10m]) - avg_over_time(rabbitmq_detailed_queue_messages[10m] offset 1m) > 1
+          ) * on (instance, job) group_left(rabbitmq_cluster) rabbitmq_identity_info
+      for: 10m
+      annotations:
+        description: |
+          Over the last 10 minutes, queue `{{ $labels.queue }}` in virtual host `{{ $labels.vhost }}`
+          was growing. 10 minute moving average has grown by {{ $value }}.
+          This happens in RabbitMQ cluster `{{ $labels.rabbitmq_cluster }}` in namespace `{{ $labels.namespace }}`.
+        summary: |
+          Queue size is steadily growing over time.
+      labels:
+        rulesgroup: rabbitmq
+        severity: warning