使用 Loki 實現 Kubernetes 容器紀錄檔監控的方法

2022-05-17 16:02:06

一、基本介紹

Loki 是由 Grafana Labs 團隊開發的，基於 Go 語言實現，是一個水平可延伸，高可用性，多租戶的紀錄檔聚合系統。它的設計非常經濟高效且易於操作，因為它不會為紀錄檔內容編制索引，而是為每個紀錄檔流設定一組標籤。Loki 專案受 Prometheus 啟發。

官方的介紹就是：Like Prometheus, but for logs，類似於 Prometheus 的紀錄檔系統。

1.Loki 架構

Loki：主服務，用於儲存紀錄檔和處理查詢。
Promtail：代理服務，用於採集紀錄檔，並轉發給 Loki。
Grafana：通過 Web 介面來提供資料展示、查詢、告警等功能。

2.Loki 工作原理

首先由 Promtail 進行紀錄檔採集，並行送給 Distributor 元件，Distributor 元件會對接收到的紀錄檔流進行正確性校驗，並將驗證後的紀錄檔分批並行傳送給 Ingester 元件。Ingester 元件會將接收過來的紀錄檔流構建成資料塊，並進行壓縮後存放到所連線的後端儲存中。

Querier 元件，用於接收 HTTP 查詢請求，並將查詢請求轉發給 Ingester 元件，來返回存在 Ingester 記憶體中的資料。要是在 Ingester 的記憶體中沒有找到符合條件的資料時，那麼 Querier 元件便會直接在後端儲存中進行查詢（內建去重功能）。

二、使用 Loki 實現容器紀錄檔監控

1.安裝 Loki

1）建立 RBAC 授權

[root@k8s-master01 ~]# cat <<END > loki-rbac.yaml
apiVersion: v1
kind: Namespace
metadata:
  name: logging
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: loki
  namespace: logging
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
  name: loki
  namespace: logging
rules:
- apiGroups: ["extensions"]
  resources: ["podsecuritypolicies"]
  verbs: ["use"]
  resourceNames: [loki]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
  name: loki
  namespace: logging
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: loki
subjects:
- kind: ServiceAccount
  name: loki
END
[root@k8s-master01 ~]# kubectl create -f loki-rbac.yaml

2）建立 ConfigMap 檔案

[root@k8s-master01 ~]# cat <<END > loki-configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: loki
  namespace: logging
  labels:
    app: loki
data:
  loki.yaml: |
    auth_enabled: false
    ingester:
      chunk_idle_period: 3m
      chunk_block_size: 262144
      chunk_retain_period: 1m
      max_transfer_retries: 0
      lifecycler:
        ring:
          kvstore:
            store: inmemory
          replication_factor: 1
    limits_config:
      enforce_metric_name: false
      reject_old_samples: true
      reject_old_samples_max_age: 168h
    schema_config:
      configs:
      - from: "2022-05-15"
        store: boltdb-shipper
        object_store: filesystem
        schema: v11
        index:
          prefix: index_
          period: 24h
    server:
      http_listen_port: 3100
    storage_config:
      boltdb_shipper:
        active_index_directory: /data/loki/boltdb-shipper-active
        cache_location: /data/loki/boltdb-shipper-cache
        cache_ttl: 24h         
        shared_store: filesystem
      filesystem:
        directory: /data/loki/chunks
    chunk_store_config:
      max_look_back_period: 0s
    table_manager:
      retention_deletes_enabled: true
      retention_period: 48h
    compactor:
      working_directory: /data/loki/boltdb-shipper-compactor
      shared_store: filesystem
END
[root@k8s-master01 ~]# kubectl create -f loki-configmap.yaml

3）建立 StatefulSet

[root@k8s-master01 ~]# cat <<END > loki-statefulset.yaml 
apiVersion: v1
kind: Service
metadata:
  name: loki
  namespace: logging
  labels:
    app: loki
spec:
  type: NodePort
  ports:
    - port: 3100
      protocol: TCP
      name: http-metrics
      targetPort: http-metrics
      nodePort: 30100
  selector:
    app: loki
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: loki
  namespace: logging
  labels:
    app: loki
spec:
  podManagementPolicy: OrderedReady
  replicas: 1
  selector:
    matchLabels:
      app: loki
  serviceName: loki
  updateStrategy:
    type: RollingUpdate
  template:
    metadata:
      labels:
        app: loki
    spec:
      serviceAccountName: loki
      initContainers:
      - name: chmod-data
        image: busybox:1.28.4
        imagePullPolicy: IfNotPresent
        command: ["chmod","-R","777","/loki/data"]
        volumeMounts:
        - name: storage
          mountPath: /loki/data
      containers:
        - name: loki
          image: grafana/loki:2.3.0
          imagePullPolicy: IfNotPresent
          args:
            - -config.file=/etc/loki/loki.yaml
          volumeMounts:
            - name: config
              mountPath: /etc/loki
            - name: storage
              mountPath: /data
          ports:
            - name: http-metrics
              containerPort: 3100
              protocol: TCP
          livenessProbe:
            httpGet: 
              path: /ready
              port: http-metrics
              scheme: HTTP
            initialDelaySeconds: 45
          readinessProbe:
            httpGet: 
              path: /ready
              port: http-metrics
              scheme: HTTP
            initialDelaySeconds: 45
          securityContext:
            readOnlyRootFilesystem: true
      terminationGracePeriodSeconds: 4800
      volumes:
        - name: config
          configMap:
            name: loki
        - name: storage
          hostPath:
            path: /app/loki
END
[root@k8s-master01 ~]# kubectl create -f loki-statefulset.yaml

2.安裝 Promtail

1）建立 RBAC 授權檔案

[root@k8s-master01 ~]# cat <<END > promtail-rbac.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
  name: loki-promtail
  labels:
    app: promtail
  namespace: logging 
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  labels:
    app: promtail
  name: promtail-clusterrole
  namespace: logging
rules:
- apiGroups: [""]
  resources: ["nodes","nodes/proxy","services","endpoints","pods"]
  verbs: ["get", "watch", "list"] 
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: promtail-clusterrolebinding
  labels:
    app: promtail
  namespace: logging
subjects:
  - kind: ServiceAccount
    name: loki-promtail
    namespace: logging
roleRef:
  kind: ClusterRole
  name: promtail-clusterrole
  apiGroup: rbac.authorization.k8s.io
END
[root@k8s-master01 ~]# kubectl create -f promtail-rbac.yaml

2）建立 ConfigMap 檔案

Promtail 組態檔：官方介紹

[root@k8s-master01 ~]# cat <<"END" > promtail-configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: loki-promtail
  namespace: logging
  labels:
    app: promtail
data:
  promtail.yaml: |
    client:
      backoff_config:
        max_period: 5m 
        max_retries: 10
        min_period: 500ms
      batchsize: 1048576
      batchwait: 1s
      external_labels: {}
      timeout: 10s
    positions:
      filename: /run/promtail/positions.yaml
    server:
      http_listen_port: 3101
    target_config:
      sync_period: 10s
    scrape_configs:
    - job_name: kubernetes-pods-name
      pipeline_stages:
        - docker: {}
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - source_labels:
        - __meta_kubernetes_pod_label_name
        target_label: __service__
      - source_labels:
        - __meta_kubernetes_pod_node_name
        target_label: __host__
      - action: drop
        regex: ''
        source_labels:
        - __service__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - action: replace
        replacement: $1
        separator: /
        source_labels:
        - __meta_kubernetes_namespace
        - __service__
        target_label: job
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_name
        target_label: pod
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_container_name
        target_label: container
      - replacement: /var/log/pods/*$1/*.log
        separator: /
        source_labels:
        - __meta_kubernetes_pod_uid
        - __meta_kubernetes_pod_container_name
        target_label: __path__
    - job_name: kubernetes-pods-app
      pipeline_stages:
        - docker: {}
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - action: drop
        regex: .+
        source_labels:
        - __meta_kubernetes_pod_label_name
      - source_labels:
        - __meta_kubernetes_pod_label_app
        target_label: __service__
      - source_labels:
        - __meta_kubernetes_pod_node_name
        target_label: __host__
      - action: drop
        regex: ''
        source_labels:
        - __service__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - action: replace
        replacement: $1
        separator: /
        source_labels:
        - __meta_kubernetes_namespace
        - __service__
        target_label: job
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_name
        target_label: pod
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_container_name
        target_label: container
      - replacement: /var/log/pods/*$1/*.log
        separator: /
        source_labels:
        - __meta_kubernetes_pod_uid
        - __meta_kubernetes_pod_container_name
        target_label: __path__
    - job_name: kubernetes-pods-direct-controllers
      pipeline_stages:
        - docker: {}
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - action: drop
        regex: .+
        separator: ''
        source_labels:
        - __meta_kubernetes_pod_label_name
        - __meta_kubernetes_pod_label_app
      - action: drop
        regex: '[0-9a-z-.]+-[0-9a-f]{8,10}'
        source_labels:
        - __meta_kubernetes_pod_controller_name
      - source_labels:
        - __meta_kubernetes_pod_controller_name
        target_label: __service__
      - source_labels:
        - __meta_kubernetes_pod_node_name
        target_label: __host__
      - action: drop
        regex: ''
        source_labels:
        - __service__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - action: replace
        replacement: $1
        separator: /
        source_labels:
        - __meta_kubernetes_namespace
        - __service__
        target_label: job
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_name
        target_label: pod
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_container_name
        target_label: container
      - replacement: /var/log/pods/*$1/*.log
        separator: /
        source_labels:
        - __meta_kubernetes_pod_uid
        - __meta_kubernetes_pod_container_name
        target_label: __path__
    - job_name: kubernetes-pods-indirect-controller
      pipeline_stages:
        - docker: {}
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - action: drop
        regex: .+
        separator: ''
        source_labels:
        - __meta_kubernetes_pod_label_name
        - __meta_kubernetes_pod_label_app
      - action: keep
        regex: '[0-9a-z-.]+-[0-9a-f]{8,10}'
        source_labels:
        - __meta_kubernetes_pod_controller_name
      - action: replace
        regex: '([0-9a-z-.]+)-[0-9a-f]{8,10}'
        source_labels:
        - __meta_kubernetes_pod_controller_name
        target_label: __service__
      - source_labels:
        - __meta_kubernetes_pod_node_name
        target_label: __host__
      - action: drop
        regex: ''
        source_labels:
        - __service__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - action: replace
        replacement: $1
        separator: /
        source_labels:
        - __meta_kubernetes_namespace
        - __service__
        target_label: job
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_name
        target_label: pod
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_container_name
        target_label: container
      - replacement: /var/log/pods/*$1/*.log
        separator: /
        source_labels:
        - __meta_kubernetes_pod_uid
        - __meta_kubernetes_pod_container_name
        target_label: __path__
    - job_name: kubernetes-pods-static
      pipeline_stages:
        - docker: {}
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - action: drop
        regex: ''
        source_labels:
        - __meta_kubernetes_pod_annotation_kubernetes_io_config_mirror
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_label_component
        target_label: __service__
      - source_labels:
        - __meta_kubernetes_pod_node_name
        target_label: __host__
      - action: drop
        regex: ''
        source_labels:
        - __service__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - action: replace
        replacement: $1
        separator: /
        source_labels:
        - __meta_kubernetes_namespace
        - __service__
        target_label: job
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_name
        target_label: pod
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_container_name
        target_label: container
      - replacement: /var/log/pods/*$1/*.log
        separator: /
        source_labels:
        - __meta_kubernetes_pod_annotation_kubernetes_io_config_mirror
        - __meta_kubernetes_pod_container_name
        target_label: __path__
END
[root@k8s-master01 ~]# kubectl create -f promtail-configmap.yaml

3）建立 DaemonSet 檔案

[root@k8s-master01 ~]# cat <<END > promtail-daemonset.yaml
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: loki-promtail
  namespace: logging
  labels:
    app: promtail
spec:
  selector:
    matchLabels:
      app: promtail
  updateStrategy:
    rollingUpdate:
      maxUnavailable: 1
    type: RollingUpdate
  template:
    metadata:
      labels:
        app: promtail
    spec:
      serviceAccountName: loki-promtail
      containers:
        - name: promtail
          image: grafana/promtail:2.3.0
          imagePullPolicy: IfNotPresent
          args: 
          - -config.file=/etc/promtail/promtail.yaml
          - -client.url=http://192.168.1.1:30100/loki/api/v1/push
          env: 
          - name: HOSTNAME
            valueFrom: 
              fieldRef: 
                apiVersion: v1
                fieldPath: spec.nodeName
          volumeMounts:
          - mountPath: /etc/promtail
            name: config
          - mountPath: /run/promtail
            name: run
          - mountPath: /data/k8s/docker/data/containers
            name: docker
            readOnly: true
          - mountPath: /var/log/pods
            name: pods
            readOnly: true
          ports:
          - containerPort: 3101
            name: http-metrics
            protocol: TCP
          securityContext:
            readOnlyRootFilesystem: true
            runAsGroup: 0
            runAsUser: 0
          readinessProbe:
            failureThreshold: 5
            httpGet:
              path: /ready
              port: http-metrics
              scheme: HTTP
            initialDelaySeconds: 10
            periodSeconds: 10
            successThreshold: 1
            timeoutSeconds: 1
      tolerations:
      - effect: NoSchedule
        key: node-role.kubernetes.io/master
        operator: Exists
      volumes:
        - name: config
          configMap:
            name: loki-promtail
        - name: run
          hostPath:
            path: /run/promtail
            type: ""
        - name: docker
          hostPath:
            path: /data/k8s/docker/data/containers
        - name: pods
          hostPath:
            path: /var/log/pods
END
[root@k8s-master01 ~]# kubectl create -f promtail-daemonset.yaml

4）Promtail 關鍵設定

    volumeMounts:
    - mountPath: /data/k8s/docker/data/containers
      name: docker
      readOnly: true
    - mountPath: /var/log/pods
      name: pods
      readOnly: true
volumes:
- name: docker
  hostPath:
    path: /data/k8s/docker/data/containers
- name: pods
  hostPath:
    path: /var/log/pods

這裡需要注意，hostPath 和 mountPath 設定的路徑要相同（這裡說的相同指的是，要和宿主機的容器目錄相同），因為 Promtail 在讀取容器內的紀錄檔時，會通過 K8s 的 API 介面來返回容器資訊（通過源路徑取的）。如果設定的不同，將會導致 httpGet 檢查失敗。

輸出：Not ready: Unable to find any logs to tail. Please verify permissions, volumes, scrape_config, etc. 資訊，原因可能就是因為掛載路徑沒有匹配上，導致 Promtail tail 不到紀錄檔檔案。可以先手動將就緒檢查關閉，來檢視 Promtail 容器的紀錄檔。

3.安裝 Grafana

[root@k8s-master01 ~]# cat <<END > grafana-deploy.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: grafana
  labels:
    app: grafana
  namespace: logging
spec:
  replicas: 1
  selector:
    matchLabels:
      app: grafana
  template:
    metadata:
      labels:
        app: grafana
    spec:
      containers:
      - name: grafana
        image: grafana/grafana:8.4.7
        imagePullPolicy: IfNotPresent
        env:
        - name: GF_AUTH_BASIC_ENABLED
          value: "true"
        - name: GF_AUTH_ANONYMOUS_ENABLED
          value: "false"
        resources:
          requests:
            cpu: 100m
            memory: 200Mi
          limits:
            cpu: '1'
            memory: 2Gi
        readinessProbe:
          httpGet:
            path: /login
            port: 3000
        volumeMounts:
        - name: storage
          mountPath: /var/lib/grafana
      volumes:
      - name: storage
        hostPath:
          path: /app/grafana          
---
apiVersion: v1
kind: Service
metadata:
  name: grafana
  labels:
    app: grafana
  namespace: logging
spec:
  type: NodePort
  ports:
  - port: 3000
    targetPort: 3000
    nodePort: 30030
  selector:
    app: grafana
END
[root@k8s-master01 ~]# mkdir -p /app/grafana
[root@k8s-master01 ~]# chmod -R 777 /app/grafana
[root@k8s-master01 ~]# kubectl create -f grafana-deploy.yaml