Initial packaging of a prometheus / loki / grafana monitoring system

This is a work in progress
2021-07-17 20:25:30 +00:00 · 2021-07-17 20:25:30 +00:00 · d5607c39cd
commit d5607c39cd
parent 2cbc1a6de1
8 changed files with 327 additions and 24 deletions
--- a/.env.sample
+++ b/.env.sample
@ -1,6 +1,14 @@
 TYPE=monitoring

-DOMAIN=monitoring.example.com
-## Domain aliases
-#EXTRA_DOMAINS=', `www.monitoring.example.com`'
+GRAFANA_DOMAIN=grafana.example.com
+PROMETHEUS_DOMAIN=prometheus.example.com
+
 LETS_ENCRYPT_ENV=production
+
+#GF_SMTP_HOST
+#GF_SMTP_ENABLED
+#GF_SMTP_FROM_ADDRESS
+#GF_SMTP_SKIP_VERIFY
+#GF_SECURITY_ALLOW_EMBEDDING
+#GF_INSTALL_PLUGINS=grafana-piechart-panel
+#GF_SERVER_ROOT_URL=https://${GRAFANA_DOMAIN}
--- a/README.md
+++ b/README.md
@ -3,14 +3,14 @@
 A server and application monitoring stack based on Prometheus, Loki and Grafana.

 <!-- metadata -->
-* **Category**:
-* **Status**: 
-* **Image**: [`monitoring`](https://hub.docker.com/r/monitoring/monitoring)
-* **Healthcheck**: 
-* **Backups**: 
-* **Email**: 
-* **Tests**: 
-* **SSO**: 
+* **Category**: Monitoring
+* **Status**: ❷💛
+* **Images**: [`prom/prometheus`](https://hub.docker.com/r/prom/prometheus) [`grafana/grafana`](https://hub.docker.com/r/grafana/grafana) [`grafana/loki`](https://hub.docker.com/r/grafana/loki)
+* **Healthcheck**: ❶💚
+* **Backups**: ❌
+* **Email**: ❶💚
+* **Tests**: ❌
+* **SSO**: ❸🍎
 <!-- endmetadata -->

 ## Basic usage
@ -19,7 +19,7 @@ A server and application monitoring stack based on Prometheus, Loki and Grafana.
 2. Deploy [`coop-cloud/traefik`]
 3. `abra app new monitoring --secrets` (optionally with `--pass` if you'd like
   to save secrets in `pass`)
-4. `abra app YOURAPPDOMAIN config` - be sure to change `DOMAIN` to something that resolves to
+4. `abra app YOURAPPDOMAIN config` - be sure to change `GRAFANA_DOMAIN` and `PROMETHEUS_DOMAIN` to something that resolves to
   your Docker swarm box
 5. `abra app YOURAPPDOMAIN deploy`
 6. Open the configured domain in your browser to finish set-up
--- a/abra.sh
+++ b/abra.sh
@ -0,0 +1,4 @@
+export PROMETHEUS_YML_VERSION=v1
+export PROMTAIL_YML_VERSION=v1
+export LOKI_YML_VERSION=v1
+export NODE_EXPORTER_ENTRYPOINT_VERSION=v1
--- a/compose.yml
+++ b/compose.yml
@ -2,30 +2,167 @@
 version: "3.8"

 services:
-  app:
-    image: nginx:1.19.2
+  node_exporter:
+    image: prom/node-exporter:v1.0.1
+    user: root
+    environment:
+      - NODE_ID={{.Node.ID}}
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+      - /etc/hostname:/etc/nodename
+    command:
+      - '--path.sysfs=/host/sys'
+      - '--path.procfs=/host/proc'
+      - '--path.rootfs=/rootfs'
+      - '--collector.textfile.directory=/etc/node-exporter/'
+      - '--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc)($$|/)'
+      - '--no-collector.ipvs'
+    configs:
+      - source: node_exporter_entrypoint_sh
+        target: /entrypoint.sh
+    entrypoint: ['/bin/sh', '-e', '/entrypoint.sh']
    networks:
-      - proxy
+      - exporters
+    deploy:
+      mode: global
+      endpoint_mode: dnsrr
+ 
+  cadvisor:
+    image: google/cadvisor:latest
+    command: -logtostderr -docker_only
+    volumes:
+      - /var/lib/docker/:/var/lib/docker
+      - /dev/disk/:/dev/disk
+      - /sys:/sys
+      - /var/run:/var/run
+      - /:/rootfs
+    networks:
+      - exporters
+    deploy:
+      mode: global
+      endpoint_mode: dnsrr
+
+  loki:
+    image: grafana/loki:2.0.0
+    command: -config.file=/etc/loki/local-config.yaml
+    networks:
+      - loki
+      - api
+    deploy:
+      endpoint_mode: dnsrr
+    ports:
+      - target: 3100
+        published: 3100
+        protocol: tcp
+        mode: host
+    configs:
+      - source: loki_yml
+        target: /etc/loki/local-config.yaml
+    volumes:
+      - loki-data:/loki
+
+  promtail:
+    image: grafana/promtail:2.0.0
+    volumes:
+      - /var/log:/var/log
+    command: -config.file=/etc/promtail/config.yml
+    networks:
+      - loki
+    deploy:
+      mode: global
+      endpoint_mode: dnsrr
+
+  prometheus:
+    image: prom/prometheus:latest
+    volumes:
+      - prometheus-data:/prometheus:rw
+    configs:
+      - source: prometheus_yml
+        target: /etc/prometheus/prometheus.yml
+    networks:
+      api:
+        aliases:
+          - prometheus_api
+      exporters: ~
+      proxy: ~
    deploy:
      restart_policy:
        condition: on-failure
      labels:
        - "traefik.enable=true"
-        - "traefik.http.services.${STACK_NAME}.loadbalancer.server.port=80"
-        - "traefik.http.routers.${STACK_NAME}.rule=Host(`${DOMAIN}`${EXTRA_DOMAINS})"
-        - "traefik.http.routers.${STACK_NAME}.entrypoints=web-secure"
-        - "traefik.http.routers.${STACK_NAME}.tls.certresolver=${LETS_ENCRYPT_ENV}"
-        ## Redirect from EXTRA_DOMAINS to DOMAIN
-        #- "traefik.http.routers.${STACK_NAME}.middlewares=${STACK_NAME}-redirect"
-        #- "traefik.http.middlewares.${STACK_NAME}-redirect.headers.SSLForceHost=true"
-        #- "traefik.http.middlewares.${STACK_NAME}-redirect.headers.SSLHost=${DOMAIN}"
+        - "traefik.http.services.${STACK_NAME}-prometheus.loadbalancer.server.port=9090"
+        - "traefik.http.routers.${STACK_NAME}-prometheus.rule=Host(`${PROMETHEUS_DOMAIN}`)"
+        - "traefik.http.routers.${STACK_NAME}-prometheus.entrypoints=web-secure"
+        - "traefik.http.routers.${STACK_NAME}-prometheus.tls=true"
+        - "traefik.http.routers.${STACK_NAME}-tls.certresolver=${LETS_ENCRYPT_ENV}"
+        - "traefik.http.middlewares.${STACK_NAME}-http-to-https.redirectscheme.scheme=https"
+        - "traefik.http.middlewares.${STACK_NAME}-http-to-https.redirectscheme.permanent=true"
+        - "traefik.http.routers.${STACK_NAME}-prometheus-redirect.rule=Host(`${PROMETHEUS_DOMAIN}`)" 
+        - "traefik.http.routers.${STACK_NAME}-prometheus-redirect.middlewares=${STACK_NAME}-http-to-https@docker"
    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost"]
+      test: ["CMD", "curl", "-f", "http://localhost:9090"]
      interval: 30s
      timeout: 10s
      retries: 10
      start_period: 1m

+  grafana:
+    image: grafana/grafana
+    volumes:
+      - grafana-data:/var/lib/grafana:rw
+    networks:
+      - api
+      - proxy
+    environment:
+      - GF_SMTP_HOST
+      - GF_SMTP_ENABLED
+      - GF_SMTP_FROM_ADDRESS
+      - GF_SMTP_SKIP_VERIFY
+      - GF_SECURITY_ALLOW_EMBEDDING
+      - GF_INSTALL_PLUGINS=grafana-piechart-panel
+      - GF_SERVER_ROOT_URL=https://${GRAFANA_DOMAIN}
+    deploy:
+      labels:
+        - "traefik.enable=true"
+        - "traefik.http.services.${STACK_NAME}-grafana.loadbalancer.server.port=3000"
+        - "traefik.http.routers.${STACK_NAME}-grafana.rule=Host(`${GRAFANA_DOMAIN}`)"
+        - "traefik.http.routers.${STACK_NAME}-grafana.entrypoints=web-secure"
+        - "traefik.http.routers.${STACK_NAME}-grafana.tls=true"
+        - "traefik.http.routers.${STACK_NAME}-tls.certresolver=${LETS_ENCRYPT_ENV}"
+        - "traefik.http.middlewares.${STACK_NAME}-http-to-https.redirectscheme.scheme=https"
+        - "traefik.http.middlewares.${STACK_NAME}-http-to-https.redirectscheme.permanent=true"
+        - "traefik.http.routers.${STACK_NAME}-grafana-redirect.rule=Host(`${GRAFANA_DOMAIN}`)" 
+        - "traefik.http.routers.${STACK_NAME}-grafana-redirect.middlewares=${STACK_NAME}-http-to-https@docker"
+
+configs:
+  prometheus_yml:
+    name: ${STACK_NAME}_prometheus_yml_${PROMETHEUS_YML_VERSION}
+    file: prometheus.yml
+  promtail_yml:
+    name: ${STACK_NAME}_promtail_yml_${PROMTAIL_YML_VERSION}
+    file: promtail.yml
+  loki_yml:
+    name: ${STACK_NAME}_loki_yml_${LOKI_YML_VERSION}
+    file: loki.yml
+  node_exporter_entrypoint_sh:
+    name: ${STACK_NAME}_node_exporter_entrypoint_${NODE_EXPORTER_ENTRYPOINT_VERSION}
+    file: node-exporter-entrypoint.sh
+
+volumes:
+  prometheus-data:
+  grafana-data:
+  loki-data:
+
 networks:
+  api:
+    driver: overlay
+  exporters:
+    driver: overlay
+    attachable: true
+  loki:
+    driver: overlay
+    attachable: true
  proxy:
    external: true
--- a/loki.yml
+++ b/loki.yml
@ -0,0 +1,71 @@
+auth_enabled: false
+
+server:
+  http_listen_port: 3100
+
+distributor:
+  ring:
+    kvstore:
+      store: memberlist
+
+ingester:
+  lifecycler:
+    ring:
+      kvstore:
+        store: memberlist
+      replication_factor: 1
+    final_sleep: 0s
+  chunk_idle_period: 5m
+  chunk_retain_period: 30s
+
+memberlist:
+  abort_if_cluster_join_fails: false
+
+  # Expose this port on all distributor, ingester
+  # and querier replicas.
+  bind_port: 7946
+
+  # You can use a headless k8s service for all distributor,
+  # ingester and querier components.
+  join_members:
+  - loki:7946
+
+  max_join_backoff: 1m
+  max_join_retries: 10
+  min_join_backoff: 1s
+
+schema_config:
+  configs:
+  - from: 2020-11-25
+    store: boltdb-shipper
+    object_store: aws
+    schema: v11
+    index:
+      prefix: index_
+      period: 24h
+
+storage_config:
+ boltdb_shipper:
+   active_index_directory: /loki/index
+   cache_location: /loki/index_cache
+   resync_interval: 5s
+   shared_store: aws
+
+ aws:
+   endpoint:
+   region:
+   access_key_id:
+   secret_access_key:
+   bucketnames:
+   insecure: false
+   sse_encryption: false
+   http_config:
+     idle_conn_timeout: 90s
+     response_header_timeout: 0s
+     insecure_skip_verify: false
+   s3forcepathstyle: true
+
+limits_config:
+  enforce_metric_name: false
+  reject_old_samples: true
+  reject_old_samples_max_age: 168h
--- a/node-exporter-entrypoint.sh
+++ b/node-exporter-entrypoint.sh
@ -0,0 +1,9 @@
+#!/bin/sh -e
+
+NODE_NAME=$(cat /etc/nodename)
+mkdir -p /etc/node-exporter
+echo "node_meta{node_id=\"$NODE_ID\", container_label_com_docker_swarm_node_id=\"$NODE_ID\", node_name=\"$NODE_NAME\"} 1" > /etc/node-exporter/node-meta.prom
+
+set -- /bin/node_exporter "$@"
+
+exec "$@"
--- a/prometheus.yml
+++ b/prometheus.yml
@ -0,0 +1,56 @@
+global:
+  scrape_interval:     30s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
+  evaluation_interval: 30s # Evaluate rules every 15 seconds. The default is every 1 minute.
+  # scrape_timeout is set to the global default (10s).
+
+# Alertmanager configuration
+alerting:
+  alertmanagers:
+  - static_configs:
+    - targets:
+      # - alertmanager:9093
+
+# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
+rule_files:
+  # - "first_rules.yml"
+  # - "second_rules.yml"
+
+# 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'
+    # metrics_path defaults to '/metrics'
+    # scheme defaults to 'http'.
+    static_configs:
+    - targets:
+      - localhost:9090
+
+  # http://node_exporter:9100/metrics
+  - job_name: node-exporter
+    scrape_interval: 10s
+    metrics_path: "/metrics"
+    dns_sd_configs:
+    - names:
+      - 'tasks.node_exporter'
+      type: 'A'
+      port: 9100
+
+
+  - job_name: 'cadvisor'
+    scrape_interval: 30s
+    metrics_path: '/metrics'
+    dns_sd_configs:
+    - names:
+      - 'tasks.cadvisor'
+      type: 'A'
+      port: 8080
+
+  - job_name: 'traefik'
+    scrape_interval: 30s
+    metrics_path: '/metrics'
+    dns_sd_configs:
+    - names:
+      - 'tasks.traefik_app'
+      type: 'A'
+      port: 8082
--- a/promtail.yml
+++ b/promtail.yml
@ -0,0 +1,18 @@
+server:
+  http_listen_port: 9080
+  grpc_listen_port: 0
+
+positions:
+  filename: /tmp/positions.yaml
+
+clients:
+  - url: http://loki:3100/loki/api/v1/push
+
+scrape_configs:
+- job_name: system
+  static_configs:
+  - targets:
+      - localhost
+    labels:
+      job: varlogs
+      __path__: /var/log/*log