Inital Commit - Prometheus + Grafana

config/alertmanager.yml

@@ -0,0 +1,20 @@
+global:
+  resolve_timeout: 5m
+
+route:
+  group_by: ['Alertname']
+  group_wait: 10s
+  group_interval: 10s
+  repeat_interval: 24h
+  receiver: 'email'
+receivers:
+- name: 'email'
+  email_configs:
+  - to: 'matanhorovitz@protonmail.com'
+    from: 'pukekoxyz@yahoo.com'
+    smarthost: smtp.mail.yahoo.com:587
+    auth_username: 'pukekoxyz@yahoo.com'
+    auth_identity: 'pukekoxyz@yahoo.com'
+    auth_password: 'pvefngmuhcxunzqs'
+    require_tls: yes
+    send_resolved: true

config/alerts.yml

@@ -0,0 +1,14 @@
+groups:
+  - name: Uptime
+    rules:
+      - alert: InstanceDown 
+        expr: up{job="services"} < 1 
+        for: 5m 
+  - name: Usage
+    rules:
+      - alert: HighRootFSDiskUsage
+        expr: 100 - ((node_filesystem_avail_bytes{mountpoint="/",fstype!="rootfs"} * 100) / node_filesystem_size_bytes{mountpoint="/",fstype!="rootfs"}) > 80
+        for: 1m
+      - alert: HighRedVolDiskUsage
+        expr: 100 - ((node_filesystem_avail_bytes{mountpoint="/Red-Vol",fstype!="rootfs"} * 100) / node_filesystem_size_bytes{mountpoint="/Red-Vol",fstype!="rootfs"}) > 70
+        for: 1m

config/prometheus.yml

@@ -0,0 +1,23 @@
+global:
+  scrape_interval:     15s
+  evaluation_interval: 15s
+
+alerting:
+  alertmanagers:
+  - static_configs:
+    - targets: ['alertmanager:9093']
+rule_files:
+  - alerts.yml
+
+scrape_configs:
+  - job_name: prometheus
+    static_configs:
+      - targets: ['prometheus:9090']
+  - job_name: takahe
+    static_configs:
+      - targets: ['192.168.0.66:9100']
+  - job_name: cadvisor
+    scrape_interval: 5s
+    static_configs:
+    - targets:
+      - cadvisor:8080