1

我在 Docker Swarm 中使用 Loki 和 promtail 从 3 个主机上的容器中获取日志。Promtail 处于全局模式。部署堆栈文件后，所有运行服务的日志都在 Grafana 中，但一段时间（几天）后，容器日志的某些部分消失了。出现了一些网络问题，虽然所有服务都重启了，但并不是所有的容器日志都出现了。

docker-stack.yml

  loki:
    image: grafana/loki:latest
    logging:
      driver: json-file
      options:
        tag: "docker/loki"
    volumes:
      - ./loki/loki-config.yaml:/etc/loki/loki-config.yaml
      - loki:/data/loki
    command: -config.file=/etc/loki/loki-config.yaml
    networks:
      - monitor-net
      - traefik
    deploy:
      placement:
        constraints:
          - node.role==manager
      labels:
        - "traefik.enable=true"
        - traefik.docker.network=default_traefik
        - traefik.http.routers.loki-http.rule=Host(`swarm.loki`)
        - traefik.http.routers.loki-http.entrypoints=http
        - traefik.http.routers.loki-http.middlewares=https-redirect

        - traefik.http.routers.loki-https.rule=Host(`swarm.loki`)
        - traefik.http.routers.loki-https.entrypoints=https
        - traefik.http.routers.loki-https.tls=true
        - traefik.http.routers.loki-https.tls.certresolver=le
        - traefik.http.services.loki.loadbalancer.server.port=3100
      restart_policy:
        condition: on-failure

  promtail:
    image: grafana/promtail:latest
    volumes:
      - /var/log:/var/log
      - /var/lib/docker/containers:/var/lib/docker/containers
      - ./promtail:/etc/promtail-config/
    command: -config.file=/etc/promtail-config/promtail-config.yaml
    networks:
      - traefik
      - monitor-net
    logging:
      driver: json-file
      options:
        tag: "docker/promtail"
    deploy:
      mode: global

promtail-config.yaml

server:
  http_listen_port: 3100
  grpc_listen_port: 0
positions:
  filename: /tmp/positions.yaml
client:
  url: http://loki:3100/api/prom/push

scrape_configs:
  - job_name: system
      static_configs:
        - targets:
            - 192.168.56.103 # on each host its ip is written
          labels:
            job: varlogs
            __path__: /var/log/*log

  - job_name: containers
    static_configs:
      - targets:
          - 192.168.56.103
      - labels:
          job: containerlogs
          hostname: vm2
          __path__: /var/lib/docker/containers/*/*log

    pipeline_stages:

      - json:
          expressions:
            stream: stream
            attrs: attrs
            tag: attrs.tag
            hostname: hostname
      - labels:
          tag:
          hostname:
          stream:

loki-config.yaml

auth_enabled: false

server:
  http_listen_port: 3100

common:
  path_prefix: /loki
  storage:
    filesystem:
      chunks_directory: /loki/chunks
      rules_directory: /loki/rules
  replication_factor: 1
  ring:
    instance_addr: 127.0.0.1
    kvstore:
      store: inmemory

schema_config:
  configs:
    - from: 2022-02-05
      store: boltdb-shipper
      object_store: filesystem
      schema: v11
      index:
        prefix: index_
        period: 24h
limits_config:
  ingestion_rate_mb: 15
  ingestion_burst_size_mb: 20

问题是什么，解决办法是什么？

提前致谢。

4

0 回答 0