chore: adding alert manager

.gitignore

@@ -1,3 +1,4 @@
 **/.DS_Store
 *.env
 !wakusim.env
+alertmanager-config.yml

docker-compose.yml

@@ -108,12 +108,15 @@ services:
     image: prom/prometheus:latest
     volumes:
       - ./monitoring/prometheus-config.yml:/etc/prometheus/prometheus.yml:z
+      - ./monitoring/alert-manager/alert-rules.yml:/etc/prometheus/alert-rules.yml:z
     command:
       - --config.file=/etc/prometheus/prometheus.yml
       - --storage.tsdb.retention.time=7d
     ports:
       - 127.0.0.1:9090:9090
     restart: on-failure
+    depends_on:
+      - alertmanager
     networks:
       - simulation
 
@@ -213,4 +216,27 @@ services:
       - redis
       - foundry
     networks:
-      - simulation
+      - simulation
+
+  env_replacer:
+    image: alpine:3.19.1
+    environment:
+      - DISCORD_WEBHOOK=$DISCORD_WEBHOOK
+    volumes:
+      - ./monitoring/alert-manager/alertmanager-config.yml.template:/etc/alertmanager/alertmanager.yml.template:z
+      - ./monitoring/alert-manager/alertmanager-config.yml:/etc/alertmanager/alertmanager.yml:z
+    command: ["/bin/sh", "-c", "apk add --no-cache gettext && envsubst < /etc/alertmanager/alertmanager.yml.template > /etc/alertmanager/alertmanager.yml"]
+
+  alertmanager:
+    image: prom/alertmanager:latest
+    volumes:
+      - ./monitoring/alert-manager/alertmanager-config.yml:/etc/alertmanager/alertmanager.yml:z
+    command:
+      - --config.file=/etc/alertmanager/alertmanager.yml
+    ports:
+      - 127.0.0.1:9093:9093
+    restart: on-failure
+    networks:
+      - simulation
+    depends_on:
+      - env_replacer

monitoring/alert-manager/alert-rules.yml

@@ -0,0 +1,23 @@
+groups:
+  - name: waku
+    rules:
+      - alert: HighNimWakuMemUsage
+        expr: >
+          nim_gc_mem_bytes{} > 1
+        for: 5m
+        annotations:
+          summary: "Too high memory usage for {{ $labels.instance }}"
+          description: "Host {{ $labels.instance }} running nim-waku has GC memory usage higher 1GB"
+          current_value: "{{ $value }}"
+
+      - record: job:waku_libp2p_peers
+        expr: libp2p_peers{}
+
+      - alert: NimWakuPeersDecrease
+        expr: >
+          (job:waku_libp2p_peers / avg_over_time(job:waku_libp2p_peers[12h])) < 0.50
+        for: 15m
+        annotations:
+          summary: "Drop of libp2p_peers on {{ $labels.instance }}"
+          description: "Host {{ $labels.instance }} running nim-waku has more than 50% drop of peers compared to 12h average"
+          current_value: "{{ $value }}"

monitoring/alert-manager/alertmanager-config.yml.template

@@ -0,0 +1,11 @@
+route:
+  group_by: ['alertname']
+  group_wait: 10s
+  group_interval: 10s
+  repeat_interval: 2m
+  receiver: 'discord'
+
+receivers:
+  - name: 'discord'
+    discord_configs:
+      - webhook_url: ${DISCORD_WEBHOOK}

monitoring/prometheus-config.yml

@@ -4,6 +4,15 @@ global:
   external_labels:
     monitor: "Monitoring"
 
+alerting:
+  alertmanagers:
+    - scheme: http
+      static_configs:
+        - targets: [ 'alertmanager:9093' ]
+
+rule_files:
+    - "./alert-rules.yml"
+
 scrape_configs:
   - job_name: cadvisor
     scrape_interval: 5s