updated to latest version of stack

Signed-off-by: Brian Christner <brian.christner@gmail.com>

docker-compose.yml

@@ -1,4 +1,4 @@
-version: "2"
+version: "3.1"
 
 volumes:
     prometheus_data: {}
@@ -6,22 +6,19 @@ volumes:
 
 networks:
   front-tier:
-    driver: bridge
   back-tier:
-    driver: bridge
 
 services:
   prometheus:
-    image: prom/prometheus
-    container_name: prometheus
+    image: prom/prometheus:v2.0.0
     volumes:
       - ./prometheus/:/etc/prometheus/
       - prometheus_data:/prometheus
     command:
-      - '-config.file=/etc/prometheus/prometheus.yml'
-      - '-storage.local.path=/prometheus'
-    expose:
-      - 9090
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
+      - '--web.console.templates=/usr/share/prometheus/consoles'
     ports:
       - 9090:9090
     links:

prometheus/alert.rules

@@ -1,13 +1,22 @@
-ALERT service_down
-  IF up == 0
-  ANNOTATIONS {
-      summary = "Instance {{ $labels.instance }} is down :( ",
-      description = "{{ $labels.instance }} of job {{ $labels.job }} is not happy.",
-  }
+groups:
+- name: example
+  rules:
 
-ALERT high_load
-  IF node_load1 > 0.5
-  ANNOTATIONS {
-      summary = "Instance {{ $labels.instance }} under high load",
-      description = "{{ $labels.instance }} of job {{ $labels.job }} is under high load.",
-  }
+  # Alert for any instance that is unreachable for >5 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."

prometheus/prometheus.yml

@@ -11,21 +11,27 @@ global:
 
 # Load and evaluate rules in this file every 'evaluation_interval' seconds.
 rule_files:
-  - "alert.rules"
+    - 'alert.rules'
   # - "first.rules"
   # - "second.rules"
 
 # 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: 'Monitoring_Mayhem'
+
+  - job_name: 'prometheus'
 
     # Override the global default and scrape targets from this job every 5 seconds.
-#    scrape_interval: 5s
-
-    # metrics_path defaults to '/metrics'
-    # scheme defaults to 'http'.
+    scrape_interval: 5s
 
     static_configs:
-         - targets: ['localhost:9090', 'metrics:9171']
+         - targets: ['localhost:9090']
+
+
+  - job_name: 'metrics'
+
+    # Override the global default and scrape targets from this job every 5 seconds.
+    scrape_interval: 5s
+
+    static_configs:
+         - targets: ['metrics:9171']