feat(monitoring): add initial stack

monitoring/compose.yaml

@@ -0,0 +1,99 @@
+volumes:
+    prometheus_data: {}
+    grafana_data: {}
+
+networks:
+  front-tier:
+    name: npmplus
+    external: true
+  back-tier:
+
+services:
+
+  prometheus:
+    image: prom/prometheus:v2.36.2
+    volumes:
+      - ./prometheus/:/etc/prometheus/
+      - prometheus_data:/prometheus
+    command:
+      - '--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:
+      - cadvisor:cadvisor
+      - alertmanager:alertmanager
+    depends_on:
+      - cadvisor
+    networks:
+      - back-tier
+    restart: always
+
+  node-exporter:
+    image: quay.io/prometheus/node-exporter:latest
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+      - /:/host:ro,rslave
+    command: 
+      - '--path.rootfs=/host'
+      - '--path.procfs=/host/proc' 
+      - '--path.sysfs=/host/sys'
+      - --collector.filesystem.ignored-mount-points
+      - "^/(sys|proc|dev|host|etc|rootfs/var/lib/docker/containers|rootfs/var/lib/docker/overlay2|rootfs/run/docker/netns|rootfs/var/lib/docker/aufs)($$|/)"
+    ports:
+      - 9100:9100
+    networks:
+      - back-tier
+    restart: always
+    deploy:
+      mode: global
+
+  alertmanager:
+    image: prom/alertmanager
+    ports:
+      - 9093:9093
+    volumes:
+      - ./alertmanager/:/etc/alertmanager/
+    networks:
+      - back-tier
+    restart: always
+    command:
+      - '--config.file=/etc/alertmanager/config.yml'
+      - '--storage.path=/alertmanager'
+
+  cadvisor:
+    image: gcr.io/cadvisor/cadvisor
+    volumes:
+      - /:/rootfs:ro
+      - /var/run:/var/run:rw
+      - /sys:/sys:ro
+      - /var/lib/docker/:/var/lib/docker:ro
+    ports:
+      - 8080:8080
+    networks:
+      - back-tier
+    restart: always
+    deploy:
+      mode: global
+
+  grafana:
+    image: grafana/grafana
+    user: "472"
+    depends_on:
+      - prometheus
+    ports:
+      - 3000:3000
+    volumes:
+      - grafana_data:/var/lib/grafana
+      - ./grafana/provisioning/:/etc/grafana/provisioning/
+    env_file:
+      - ./grafana/config.monitoring
+    networks:
+      - back-tier
+      - front-tier
+    restart: always
+

monitoring/grafana/provisioning/datasources/datasource.yml

@@ -0,0 +1,50 @@
+# config file version
+apiVersion: 1
+
+# list of datasources that should be deleted from the database
+deleteDatasources:
+  - name: Prometheus
+    orgId: 1
+
+# list of datasources to insert/update depending
+# whats available in the database
+datasources:
+  # <string, required> name of the datasource. Required
+- name: Prometheus
+  # <string, required> datasource type. Required
+  type: prometheus
+  # <string, required> access mode. direct or proxy. Required
+  access: proxy
+  # <int> org id. will default to orgId 1 if not specified
+  orgId: 1
+  # <string> url
+  url: http://prometheus:9090
+  # <string> database password, if used
+  password:
+  # <string> database user, if used
+  user:
+  # <string> database name, if used
+  database:
+  # <bool> enable/disable basic auth
+  basicAuth: false
+  # <string> basic auth username, if used
+  basicAuthUser:
+  # <string> basic auth password, if used
+  basicAuthPassword:
+  # <bool> enable/disable with credentials headers
+  withCredentials:
+  # <bool> mark as default datasource. Max one per org
+  isDefault: true
+  # <map> fields that will be converted to json and stored in json_data
+  jsonData:
+     graphiteVersion: "1.1"
+     tlsAuth: false
+     tlsAuthWithCACert: false
+  # <string> json object of data that will be encrypted.
+  secureJsonData:
+    tlsCACert: "..."
+    tlsClientCert: "..."
+    tlsClientKey: "..."
+  version: 1
+  # <bool> allow users to edit datasources from the UI.
+  editable: true

monitoring/prometheus/prometheus.yml

@@ -0,0 +1,53 @@
+# 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: 'prometheus'
+
+    # Override the global default and scrape targets from this job every 5 seconds.
+    scrape_interval: 15s
+
+    static_configs:
+         - targets: ['localhost:9090']
+
+  - job_name: 'cadvisor'
+
+    # Override the global default and scrape targets from this job every 5 seconds.
+    scrape_interval: 15s
+
+    static_configs:
+      - targets: ['cadvisor:8080']
+
+  - job_name: 'node-exporter'
+
+    # Override the global default and scrape targets from this job every 5 seconds.
+    scrape_interval: 15s
+  
+    static_configs:
+      - targets: ['node-exporter:9100']