ok

Monitoring/Prometheus-Grafana/prometheus/alert.rules

@@ -0,0 +1,22 @@
+groups:
+- name: example
+  rules:
+
+  # Alert for any instance that is unreachable for >2 minutes.
+  - alert: service_down
+    expr: up == 0
+    for: 2m
+    labels:
+      severity: page
+    annotations:
+      summary: "Instance {{ $labels.instance }} down"
+      description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 2 minutes."
+
+  - alert: high_load
+    expr: node_load1 > 0.5
+    for: 2m
+    labels:
+      severity: page
+    annotations:
+      summary: "Instance {{ $labels.instance }} under high load"
+      description: "{{ $labels.instance }} of job {{ $labels.job }} is under high load."

Monitoring/Prometheus-Grafana/prometheus/prometheus.yml

@@ -0,0 +1,89 @@
+# my global config
+global:
+  scrape_interval:     15s # By default, scrape targets every 15 seconds.
+  evaluation_interval: 15s # By default, scrape targets every 15 seconds.
+  # scrape_timeout is set to the global default (10s).
+
+  # Attach these labels to any time series or alerts when communicating with
+  # external systems (federation, remote storage, Alertmanager).
+  external_labels:
+      monitor: 'my-project'
+
+# Load and evaluate rules in this file every 'evaluation_interval' seconds.
+rule_files:
+  - 'alert.rules'
+  # - "first.rules"
+  # - "second.rules"
+
+# alert
+alerting:
+  alertmanagers:
+  - scheme: http
+    static_configs:
+    - targets:
+      - "alertmanager:9093"
+
+# A scrape configuration containing exactly one endpoint to scrape:
+# Here it's Prometheus itself.
+scrape_configs:
+  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
+  - job_name: app
+    scrape_interval: 5s
+    static_configs:
+      - targets: ['host.docker.internal:8000']
+
+  - job_name: 'prometheus'
+
+    # Override the global default and scrape targets from this job every 5 seconds.
+    scrape_interval: 5s
+
+    static_configs:
+         - targets: ['localhost:9090']
+
+  - job_name: 'cadvisor'
+
+    # Override the global default and scrape targets from this job every 5 seconds.
+    scrape_interval: 5s
+
+    dns_sd_configs:
+    - names:
+      - 'tasks.cadvisor'
+      type: 'A'
+      port: 8080
+
+#     static_configs:
+#          - targets: ['cadvisor:8080']
+
+  - job_name: 'node-exporter'
+
+    # Override the global default and scrape targets from this job every 5 seconds.
+    scrape_interval: 5s
+
+    dns_sd_configs:
+    - names:
+      - 'tasks.node-exporter'
+      type: 'A'
+      port: 9100
+
+#  - job_name: 'pushgateway'
+#    scrape_interval: 10s
+#    dns_sd_configs:
+#    - names:
+#      - 'tasks.pushgateway'
+#      type: 'A'
+#      port: 9091
+
+#     static_configs:
+#          - targets: ['node-exporter:9100']
+
+  - job_name: 'traefik-app'
+    scrape_interval: 5s
+    static_configs:
+      - targets: ['10.12.1.14:8181']
+
+  - job_name: 'airflow'
+    # Override the global default and scrape targets from this job every 5 seconds.
+    scrape_interval: 5s
+    static_configs:
+      - targets: 
+        - '10.12.1.14:9102'