initial commit

prometheus/alert.rules

@@ -0,0 +1,70 @@
+groups:
+- name: targets
+  rules:
+  - alert: monitor_service_down
+    expr: up == 0
+    for: 30s
+    labels:
+      severity: critical
+    annotations:
+      summary: "Monitor service non-operational"
+      description: "Service {{ $labels.instance }} is down."
+
+- name: host
+  rules:
+  - alert: high_cpu_load
+    expr: node_load1 > 1.5
+    for: 30s
+    labels:
+      severity: warning
+    annotations:
+      summary: "Server under high load"
+      description: "Docker host is under high load, the avg load 1m is at {{ $value}}. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."
+
+  - alert: high_memory_load
+    expr: (sum(node_memory_MemTotal_bytes) - sum(node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes) ) / sum(node_memory_MemTotal_bytes) * 100 > 85
+    for: 30s
+    labels:
+      severity: warning
+    annotations:
+      summary: "Server memory is almost full"
+      description: "Docker host memory usage is {{ humanize $value}}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."
+
+  - alert: high_storage_load
+    expr: (node_filesystem_size_bytes{fstype="aufs"} - node_filesystem_free_bytes{fstype="aufs"}) / node_filesystem_size_bytes{fstype="aufs"}  * 100 > 85
+    for: 30s
+    labels:
+      severity: warning
+    annotations:
+      summary: "Server storage is almost full"
+      description: "Docker host storage usage is {{ humanize $value}}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."
+
+- name: containers
+  rules:
+  - alert: jenkins_down
+    expr: absent(container_memory_usage_bytes{name="jenkins"})
+    for: 30s
+    labels:
+      severity: critical
+    annotations:
+      summary: "Jenkins down"
+      description: "Jenkins container is down for more than 30 seconds."
+
+  - alert: jenkins_high_cpu
+    expr: sum(rate(container_cpu_usage_seconds_total{name="jenkins"}[1m])) / count(node_cpu_seconds_total{mode="system"}) * 100 > 10
+    for: 30s
+    labels:
+      severity: warning
+    annotations:
+      summary: "Jenkins high CPU usage"
+      description: "Jenkins CPU usage is {{ humanize $value}}%."
+
+  - alert: jenkins_high_memory
+    expr: sum(container_memory_usage_bytes{name="jenkins"}) > 1200000000
+    for: 30s
+    labels:
+      severity: warning
+    annotations:
+      summary: "Jenkins high memory usage"
+      description: "Jenkins memory consumption is at {{ humanize $value}}."
+

prometheus/prometheus.yml

@@ -0,0 +1,53 @@
+global:
+  scrape_interval:     15s
+  evaluation_interval: 15s
+
+  # Attach these labels to any time series or alerts when communicating with
+  # external systems (federation, remote storage, Alertmanager).
+  external_labels:
+      monitor: 'docker-host-alpha'
+
+# Load and evaluate rules in this file every 'evaluation_interval' seconds.
+rule_files:
+  - "alert.rules"
+
+# A scrape configuration containing exactly one endpoint to scrape.
+scrape_configs:
+  - job_name: 'nodeexporter'
+    scrape_interval: 5s
+    static_configs:
+      - targets: ['nodeexporter:9100']
+
+  - job_name: 'cadvisor'
+    scrape_interval: 5s
+    static_configs:
+      - targets: ['cadvisor:8080']
+
+  - job_name: 'prometheus'
+    scrape_interval: 10s
+    static_configs:
+      - targets: ['localhost:9090']
+
+  - job_name: 'pushgateway'
+    scrape_interval: 10s
+    honor_labels: true
+    static_configs:
+      - targets: ['pushgateway:9091']
+
+
+alerting:
+  alertmanagers:
+  - scheme: http
+    static_configs:
+    - targets: 
+      - 'alertmanager:9093'
+
+#  - job_name: 'nginx'
+#    scrape_interval: 10s
+#    static_configs:
+#      - targets: ['nginxexporter:9113']
+
+#  - job_name: 'aspnetcore'
+#    scrape_interval: 10s
+#    static_configs:
+#      - targets: ['eventlog-proxy:5000', 'eventlog:5000']