refactor: provision alerts instead of putting them in the /var/lib folder (#16)

Note that I did not copy the backupbot alert since this one gets a rework soon

Reviewed-on: coop-cloud/monitoring-ng#16
Co-authored-by: p4u1 <p4u1_f4u1@riseup.net>
Co-committed-by: p4u1 <p4u1_f4u1@riseup.net>

.env.sample

@@ -1,8 +1,8 @@
 TYPE=monitoring-ng
 LETS_ENCRYPT_ENV=production
 COMPOSE_FILE=compose.yml
-DOMAIN=monitoring.example.com
+DOMAIN=monitoring-ng.example.com
-TIMEOUT=120
+#TIMEOUT=120
 ENABLE_BACKUPS=true
 
 ## Enable this secret for Promtail / Prometheus
@@ -50,6 +50,7 @@ ENABLE_BACKUPS=true
 #GRAFANA_DOMAIN=grafana.example.com
 #
 ## Single-Sign-On with OIDC
+# COMPOSE_FILE="$COMPOSE_FILE:compose.grafana-oidc.yml"
 # OIDC_ENABLED=1
 # SECRET_GRAFANA_OIDC_CLIENT_SECRET_VERSION=v1
 # OIDC_CLIENT_ID=grafana
@@ -62,6 +63,7 @@ ENABLE_BACKUPS=true
 # GF_INSTALL_PLUGINS=grafana-piechart-panel
 #
 ## grafana SMTP configuration (optional)
+# COMPOSE_FILE="$COMPOSE_FILE:compose.grafana-smtp.yml"
 # GF_SMTP_HOST=changeme
 # GF_SMTP_USER=changme
 # GF_SMTP_ENABLED=true

abra.sh

@@ -5,13 +5,13 @@ export GRAFANA_SWARM_DASHBOARD_JSON_VERSION=v2
 export GRAFANA_STACKS_DASHBOARD_JSON_VERSION=v2
 export GRAFANA_TRAEFIK_DASHBOARD_JSON_VERSION=v2
 export GRAFANA_BACKUP_DASHBOARD_JSON_VERSION=v1
-export GRAFANA_ALERTS_JSON_VERSION=v3
 export GRAFANA_CUSTOM_INI_VERSION=v4
 export PROMTAIL_YML_VERSION=v3
 export LOKI_YML_VERSION=v2
 export PROMETHEUS_YML_VERSION=v2
 export MATRIX_ALERTMANAGER_CONFIG_VERSION=e
 export MATRIX_ALERTMANAGER_ENTRYPOINT_VERSION=a
+export GRAFANA_ALERTS_NODE_VERSION=v1c
 
 # creates a default prometheus scrape config for a given node
 add_node(){

alerts/node.yml.tmpl

@@ -0,0 +1,131 @@
+apiVersion: 1
+
+# List of alert rule UIDs that should be deleted
+deleteRules:
+  {{ if ne (env "ALERT_NODE_DISK_SPACE_ENABLED") "true" }}
+  - orgId: 1
+    uid: bds8bhxu97pxca
+  {{ end }}
+  {{ if ne (env "ALERT_NODE_MEMORY_USAGE_ENABLED") "true" }}
+  - orgId: 1
+    uid: ads8cswmly96oa
+  {{ end }}
+
+groups:
+- orgId: 1
+  name: node
+  folder: node
+  interval: 5m
+  rules:
+    {{ if eq (env "ALERT_NODE_DISK_SPACE_ENABLED") "true" }}
+    - uid: bds8bhxu97pxca
+      title: Node Disk Space
+      condition: C
+      data:
+        - refId: A
+          relativeTimeRange:
+            from: 600
+            to: 0
+          datasourceUid: PBFA97CFB590B2093
+          model:
+            editorMode: code
+            expr: (node_filesystem_free_bytes{fstype="ext4"} / node_filesystem_size_bytes{fstype="ext4"}) * 100
+            instant: true
+            intervalMs: 1000
+            legendFormat: __auto
+            maxDataPoints: 43200
+            range: false
+            refId: A
+        - refId: C
+          relativeTimeRange:
+            from: 600
+            to: 0
+          datasourceUid: __expr__
+          model:
+            conditions:
+                - evaluator:
+                    params:
+                        - 10
+                    type: lt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                        - C
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+            datasource:
+                type: __expr__
+                uid: __expr__
+            expression: A
+            intervalMs: 1000
+            maxDataPoints: 43200
+            refId: C
+            type: threshold
+      noDataState: NoData
+      execErrState: Error
+      for: 5m
+      annotations:
+        description: ""
+        runbook_url: ""
+        summary: Less than 10% disk space left on {{`{{ $labels.instance }}`}} ({{`{{ (index $values "A").Value }}`}}% left)
+      labels:
+        "": ""
+      isPaused: false
+    {{ end }}
+    {{ if eq (env "ALERT_NODE_MEMORY_USAGE_ENABLED") "true" }}
+    - uid: ads8cswmly96oa
+      title: Node Memory Usage
+      condition: C
+      data:
+        - refId: A
+          relativeTimeRange:
+            from: 600
+            to: 0
+          datasourceUid: PBFA97CFB590B2093
+          model:
+            editorMode: code
+            expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100
+            instant: true
+            intervalMs: 1000
+            legendFormat: __auto
+            maxDataPoints: 43200
+            range: false
+            refId: A
+        - refId: C
+          relativeTimeRange:
+            from: 600
+            to: 0
+          datasourceUid: __expr__
+          model:
+            conditions:
+                - evaluator:
+                    params:
+                        - 85
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                        - C
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+            datasource:
+                type: __expr__
+                uid: __expr__
+            expression: A
+            intervalMs: 1000
+            maxDataPoints: 43200
+            refId: C
+            type: threshold
+      noDataState: NoData
+      execErrState: Error
+      for: 5m
+      annotations:
+        summary: Memory usage is above 85% on {{`{{ $labels.instance }}`}}  ({{`{{ printf "%.2f" (index $values "A").Value }}`}}%  usage)
+      isPaused: false
+    {{ end }}

compose.grafana-oidc.yml

@@ -0,0 +1,17 @@
+version: '3.8'
+
+services:
+  grafana:
+    secrets:
+      - grafana_oidc_client_secret
+    environment:
+      - OIDC_API_URL
+      - OIDC_AUTH_URL
+      - OIDC_CLIENT_ID
+      - OIDC_ENABLED
+      - OIDC_TOKEN_URL
+
+secrets:
+  grafana_oidc_client_secret:
+    external: true
+    name: ${STACK_NAME}_grafana_oidc_client_secret_${SECRET_GRAFANA_OIDC_CLIENT_SECRET_VERSION}

compose.grafana-smtp.yml

@@ -0,0 +1,18 @@
+version: '3.8'
+
+services:
+  grafana:
+    secrets:
+      - grafana_smtp_password
+    environment:
+      - GF_SMTP_HOST
+      - GF_SMTP_USER
+      - GF_SMTP_PASSWORD__FILE=/run/secrets/grafana_smtp_password
+      - GF_SMTP_ENABLED
+      - GF_SMTP_FROM_ADDRESS
+      - GF_SMTP_SKIP_VERIFY
+
+secrets:
+  grafana_smtp_password:
+    external: true
+    name: ${STACK_NAME}_grafana_smtp_password_${SECRET_GRAFANA_SMTP_PASSWORD_VERSION}

compose.grafana.yml

@@ -7,8 +7,6 @@ services:
       - grafana-data:/var/lib/grafana:rw
     secrets:
       - grafana_admin_password
-      - grafana_oidc_client_secret
-      - grafana_smtp_password
     configs:
       - source: grafana_custom_ini
         target: /etc/grafana/grafana.ini
@@ -24,27 +22,18 @@ services:
         target: /var/lib/grafana/dashboards/traefik.json
       - source: grafana_backup_dashboard_json
         target: /var/lib/grafana/dashboards/backup.json
-      - source: grafana_alerts_json
+      - source: gf_alerts_node
-        target: /var/lib/grafana/alerts/alerts.json
+        target: /etc/grafana/provisioning/alerting/node.yml
     networks:
       - proxy
       - internal
     environment:
       - GF_SERVER_ROOT_URL
       - GF_SECURITY_ADMIN_PASSWORD__FILE=/run/secrets/grafana_admin_password
-      - GF_SMTP_HOST
-      - GF_SMTP_USER
-      - GF_SMTP_PASSWORD__FILE=/run/secrets/grafana_smtp_password
-      - GF_SMTP_ENABLED
-      - GF_SMTP_FROM_ADDRESS
-      - GF_SMTP_SKIP_VERIFY
       - GF_SECURITY_ALLOW_EMBEDDING
       - GF_INSTALL_PLUGINS
-      - OIDC_API_URL
+      - ALERT_NODE_DISK_SPACE_ENABLED
-      - OIDC_AUTH_URL
+      - ALERT_NODE_MEMORY_USAGE_ENABLED
-      - OIDC_CLIENT_ID
-      - OIDC_ENABLED
-      - OIDC_TOKEN_URL
     deploy:
       labels:
         - "traefik.enable=true"
@@ -84,10 +73,10 @@ configs:
   grafana_backup_dashboard_json:
     name: ${STACK_NAME}_g_backup_dashboard_json_${GRAFANA_BACKUP_DASHBOARD_JSON_VERSION}
     file: grafana-backup-dashboard.json
-  grafana_alerts_json:
+  gf_alerts_node:
     template_driver: golang
-    name: ${STACK_NAME}_g_alerts_json_${GRAFANA_ALERTS_JSON_VERSION}
+    name: ${STACK_NAME}_gf_alerts_node_${GRAFANA_ALERTS_NODE_VERSION}
-    file: grafana-alerts.json.tmpl
+    file: alerts/node.yml.tmpl
 
 volumes:
   grafana-data:
@@ -97,9 +86,3 @@ secrets:
   grafana_admin_password:
     external: true
     name: ${STACK_NAME}_grafana_admin_password_${SECRET_GRAFANA_ADMIN_PASSWORD_VERSION}
-  grafana_oidc_client_secret:
-    external: true
-    name: ${STACK_NAME}_grafana_oidc_client_secret_${SECRET_GRAFANA_OIDC_CLIENT_SECRET_VERSION}
-  grafana_smtp_password:
-    external: true
-    name: ${STACK_NAME}_grafana_smtp_password_${SECRET_GRAFANA_SMTP_PASSWORD_VERSION}

compose.yml

@@ -40,7 +40,7 @@ services:
         - "traefik.http.routers.${STACK_NAME}-node.tls.certresolver=${LETS_ENCRYPT_ENV}"
         - "traefik.http.routers.${STACK_NAME}-node.middlewares=basicauth@file"
         - "coop-cloud.${STACK_NAME}.version=1.6.0+v1.8.1"
-        - "coop-cloud.${STACK_NAME}.timeout=${TIMEOUT:-120}"
+        - "coop-cloud.${STACK_NAME}.timeout=${TIMEOUT}"
 
   cadvisor:
     image: gcr.io/cadvisor/cadvisor:v0.49.2

grafana-alerts.json.tmpl

@@ -216,7 +216,7 @@
               "datasourceUid": "PBFA97CFB590B2093",
               "model": {
                 "editorMode": "code",
-                "expr": "(node_filesystem_free_bytes{fstype=\"ext4\",mountpoint=~\"(/$)|(/media.*)\"} / node_filesystem_size_bytes{fstype=\"ext4\",mountpoint=~\"(/$)|(/media.*)\"}) * 100",
+                "expr": "(node_filesystem_free_bytes{fstype=\"ext4\"} / node_filesystem_size_bytes{fstype=\"ext4\"}) * 100",
                 "instant": true,
                 "intervalMs": 1000,
                 "legendFormat": "__auto",

grafana-swarm-dashboard.json

@@ -93,7 +93,6 @@
       },
       "hideTimeOverride": true,
       "id": 2,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
         "colorMode": "value",
@@ -107,10 +106,12 @@
           "fields": "",
           "values": false
         },
+        "showPercentChange": false,
         "text": {},
-        "textMode": "auto"
+        "textMode": "auto",
+        "wideLayout": true
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -172,7 +173,6 @@
         "y": 0
       },
       "id": 1,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
         "colorMode": "value",
@@ -186,10 +186,12 @@
           "fields": "",
           "values": false
         },
+        "showPercentChange": false,
         "text": {},
-        "textMode": "auto"
+        "textMode": "auto",
+        "wideLayout": true
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -251,7 +253,6 @@
       },
       "hideTimeOverride": true,
       "id": 4,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
         "colorMode": "value",
@@ -265,10 +266,12 @@
           "fields": "",
           "values": false
         },
+        "showPercentChange": false,
         "text": {},
-        "textMode": "auto"
+        "textMode": "auto",
+        "wideLayout": true
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -335,9 +338,10 @@
         "y": 0
       },
       "id": 8,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
+        "minVizHeight": 75,
+        "minVizWidth": 75,
         "orientation": "horizontal",
         "reduceOptions": {
           "calcs": [
@@ -348,9 +352,10 @@
         },
         "showThresholdLabels": false,
         "showThresholdMarkers": true,
+        "sizing": "auto",
         "text": {}
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -405,13 +410,12 @@
       },
       "lines": true,
       "linewidth": 1,
-      "links": [],
       "nullPointMode": "null",
       "options": {
         "alertThreshold": true
       },
       "percentage": false,
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "pointradius": 5,
       "points": false,
       "renderer": "flot",
@@ -507,7 +511,6 @@
       },
       "hideTimeOverride": true,
       "id": 3,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
         "colorMode": "value",
@@ -521,10 +524,12 @@
           "fields": "",
           "values": false
         },
+        "showPercentChange": false,
         "text": {},
-        "textMode": "auto"
+        "textMode": "auto",
+        "wideLayout": true
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -585,7 +590,6 @@
       },
       "hideTimeOverride": true,
       "id": 9,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
         "colorMode": "value",
@@ -599,10 +603,12 @@
           "fields": "",
           "values": false
         },
+        "showPercentChange": false,
         "text": {},
-        "textMode": "auto"
+        "textMode": "auto",
+        "wideLayout": true
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -671,9 +677,10 @@
       },
       "hideTimeOverride": true,
       "id": 11,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
+        "minVizHeight": 75,
+        "minVizWidth": 75,
         "orientation": "horizontal",
         "reduceOptions": {
           "calcs": [
@@ -684,9 +691,10 @@
         },
         "showThresholdLabels": false,
         "showThresholdMarkers": true,
+        "sizing": "auto",
         "text": {}
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "targets": [
         {
           "datasource": {
@@ -713,7 +721,39 @@
       "fieldConfig": {
         "defaults": {
           "color": {
-            "mode": "thresholds"
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "left",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
           },
           "mappings": [
             {
@@ -747,33 +787,42 @@
           },
           "unit": "percent"
         },
-        "overrides": []
+        "overrides": [
+          {
+            "matcher": {
+              "id": "byType",
+              "options": "time"
+            },
+            "properties": [
+              {
+                "id": "custom.axisPlacement",
+                "value": "hidden"
+              }
+            ]
+          }
+        ]
       },
       "gridPos": {
-        "h": 4,
+        "h": 6,
-        "w": 2.6666666666666665,
+        "w": 6,
         "x": 0,
         "y": 8
       },
       "id": 10,
-      "links": [],
       "maxDataPoints": 100,
-      "maxPerRow": 12,
       "options": {
-        "colorMode": "value",
+        "legend": {
-        "graphMode": "area",
+          "calcs": [],
-        "justifyMode": "auto",
+          "displayMode": "list",
-        "orientation": "horizontal",
+          "placement": "bottom",
-        "reduceOptions": {
+          "showLegend": true
-          "calcs": [
-            "last"
-          ],
-          "fields": "",
-          "values": false
         },
-        "textMode": "auto"
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
       },
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "repeat": "node_id",
       "repeatDirection": "h",
       "targets": [
@@ -782,18 +831,20 @@
             "type": "prometheus",
             "uid": "PBFA97CFB590B2093"
           },
+          "editorMode": "code",
           "exemplar": true,
-          "expr": "sum((node_filesystem_free_bytes{fstype=\"ext4\",mountpoint=~\"(/$)|(/media.*)\"} / node_filesystem_size_bytes{fstype=\"ext4\",mountpoint=~\"(/$)|(/media.*)\"}) * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"} * 100) / count(node_meta * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"})",
+          "expr": "node_filesystem_free_bytes{fstype=\"ext4\"}  / node_filesystem_size_bytes{fstype=\"ext4\"} * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"} * 100",
           "format": "time_series",
           "interval": "",
           "intervalFactor": 2,
-          "legendFormat": "",
+          "legendFormat": "{{mountpoint}}",
+          "range": true,
           "refId": "A",
           "step": 20
         }
       ],
       "title": "Available Disk Space $node_id",
-      "type": "stat"
+      "type": "timeseries"
     },
     {
       "aliasColors": {},
@@ -811,7 +862,7 @@
         "h": 7,
         "w": 24,
         "x": 0,
-        "y": 12
+        "y": 14
       },
       "hiddenSeries": false,
       "id": 14,
@@ -830,13 +881,12 @@
       },
       "lines": true,
       "linewidth": 1,
-      "links": [],
       "nullPointMode": "null as zero",
       "options": {
         "alertThreshold": true
       },
       "percentage": false,
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "pointradius": 5,
       "points": false,
       "renderer": "flot",
@@ -900,6 +950,7 @@
             "mode": "palette-classic"
           },
           "custom": {
+            "axisBorderShow": false,
             "axisCenteredZero": false,
             "axisColorMode": "text",
             "axisLabel": "",
@@ -913,6 +964,7 @@
               "tooltip": false,
               "viz": false
             },
+            "insertNulls": false,
             "lineInterpolation": "linear",
             "lineWidth": 1,
             "pointSize": 5,
@@ -961,12 +1013,11 @@
       },
       "gridPos": {
         "h": 7,
-        "w": 2.6666666666666665,
+        "w": 6,
         "x": 0,
-        "y": 19
+        "y": 21
       },
       "id": 15,
-      "links": [],
       "maxPerRow": 12,
       "options": {
         "legend": {
@@ -1074,7 +1125,7 @@
         "h": 7,
         "w": 24,
         "x": 0,
-        "y": 26
+        "y": 28
       },
       "hiddenSeries": false,
       "id": 16,
@@ -1091,13 +1142,12 @@
       },
       "lines": true,
       "linewidth": 1,
-      "links": [],
       "nullPointMode": "null as zero",
       "options": {
         "alertThreshold": true
       },
       "percentage": false,
-      "pluginVersion": "10.0.2",
+      "pluginVersion": "10.4.14",
       "pointradius": 5,
       "points": false,
       "renderer": "flot",
@@ -1178,7 +1228,7 @@
         "h": 7,
         "w": 12,
         "x": 0,
-        "y": 33
+        "y": 35
       },
       "hiddenSeries": false,
       "id": 18,
@@ -1195,7 +1245,6 @@
       },
       "lines": true,
       "linewidth": 1,
-      "links": [],
       "nullPointMode": "null as zero",
       "options": {
         "alertThreshold": true
@@ -1281,7 +1330,7 @@
         "h": 7,
         "w": 12,
         "x": 12,
-        "y": 33
+        "y": 35
       },
       "hiddenSeries": false,
       "id": 19,
@@ -1300,7 +1349,6 @@
       },
       "lines": true,
       "linewidth": 1,
-      "links": [],
       "nullPointMode": "null as zero",
       "options": {
         "alertThreshold": true
@@ -1376,7 +1424,7 @@
         "h": 7,
         "w": 18,
         "x": 0,
-        "y": 40
+        "y": 42
       },
       "hiddenSeries": false,
       "id": 12,
@@ -1397,7 +1445,6 @@
       },
       "lines": true,
       "linewidth": 1,
-      "links": [],
       "nullPointMode": "null",
       "options": {
         "alertThreshold": true
@@ -1499,10 +1546,9 @@
         "h": 7,
         "w": 6,
         "x": 18,
-        "y": 40
+        "y": 42
       },
       "id": 7,
-      "links": [],
       "maxDataPoints": 100,
       "options": {
         "colorMode": "none",
@@ -1600,10 +1646,9 @@
         "h": 7,
         "w": 24,
         "x": 0,
-        "y": 47
+        "y": 49
       },
       "id": 17,
-      "links": [],
       "options": {
         "legend": {
           "calcs": [],
@@ -1658,7 +1703,7 @@
         "h": 9,
         "w": 24,
         "x": 0,
-        "y": 54
+        "y": 56
       },
       "id": 30,
       "options": {
@@ -1688,8 +1733,7 @@
     }
   ],
   "refresh": "",
-  "schemaVersion": 38,
+  "schemaVersion": 39,
-  "style": "dark",
   "tags": [
     "swarmprom",
     "prometheus",
@@ -1836,6 +1880,6 @@
   "timezone": "",
   "title": "Docker Swarm Nodes",
   "uid": "BPlb-Sgik",
-  "version": 24,
+  "version": 7,
   "weekStart": ""
-}
+}

release/next

@@ -0,0 +1,7 @@
+1. OIDC was moved into a seperate compose file. If you have oidc configured you need to add the following line to you .env file:
+
+COMPOSE_FILE="$COMPOSE_FILE:compose.grafana-oidc.yml"
+
+2. SMTP was moved into a seperate compose file. If you have smtp configured you need to add the following line to you .env file:
+
+COMPOSE_FILE="$COMPOSE_FILE:compose.grafana-smtp.yml"