在K8S上安裝Loki收集日誌

一、前期準備

# 建立lokideploy資料夾
mkdir lokideploy

# cd 到lokideploy
cd lokideploy

# 新增logging namespace，所有的資源都創建在logging下，確保資源的隔離(需要刪除loki時可以直接刪除此namespace)
kubectl create ns logging

二、部署Grafana

# 新增grafana資料夾
mkdir grafana

# cd grafana
cd grafana

創建grafana-deploy.yaml

# 新增grafana-deploy.yaml
vim grafana-deploy.yaml

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
        securityContext:
          runAsUser: 0
        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: /hostpath/grafana
---
apiVersion: v1
kind: Service
metadata:
  name: grafana
  labels:
    app: grafana
  namespace: logging
spec:
  type: NodePort
  ports:
  - port: 3000
    targetPort: 3000
    
# 預設的nodePort為30200，如果要修改對外暴露的nodePort，修改下面的nodePort
    nodePort: 30200
    
  selector:
    app: grafana
---------------------------------------------------------------------------------


# 創建volume掛載的區域
mkdir -p /hostpath/grafana

# 修改 /hostpath/grafana的訪問權限
chmod 777 -R /hostpath/grafana


# apply grafana
kubectl apply -f grafana-deploy.yaml

三、部署 Loki

# cd 回lokideploy資料夾下
cd ..

# 新增loki資料夾
mkdir loki

# cd 到loki
cd loki

在loki目錄下需要新增loki-rbac.yaml、loki-configmap.yaml和loki-statefulset.yaml三個配置檔

loki-rbac.yaml

vim loki-rbac.yaml

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
------------------------------------------------------------------------------

loki-configmap.yaml

vim loki-configmap.yaml

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
------------------------------------------------------------------------------

loki-statefulset.yaml

vim loki-statefulset.yaml

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
      
 # 預設的nodePort為30201，如果要修改對外暴露的nodePort，修改下面的nodePort
      nodePort: 30201
  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
------------------------------------------------------------------------------

部署 Loki

# apply loki資料夾下的配置檔(loki-rbac.yaml、loki-configmap.yaml和loki-statefulset.yaml)
kubectl apply -f .

四、部署 promtail

新增三個配置檔(promtail-rbac.yaml、promtail-configmap.yaml和promtail-daemonset.yaml三個文件)

# cd 回到lokideploy資料夾
cd ..

# 新增promtail資料夾
mkdir promtail

# cd到promtail資料夾

cd promtail

promtail-rbac.yaml

# 新增promtail-rbac.yaml
vim promtail-rbac.yaml

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
------------------------------------------------------------------------------

loki-configmap.yaml

# 新增loki-configmap.yaml
vim loki-configmap.yaml

loki-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__
------------------------------------------------------------------------------

promtail-daemonset.yaml

# 新增promtail-daemonset.yaml
vim promtail-daemonset.yaml

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要填入loki的地址， 如 - -client.url=http:${目標IP}:${loki對外暴露的nodePort}/loki/api/v1/push
          - -client.url=http://${目標IP}:30201/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: /var/lib/docker/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: /var/lib/docker/containers
        - name: pods
          hostPath:
            path: /var/log/pods
------------------------------------------------------------------------------

# apply配置檔(promtail-rbac.yaml、promtail-configmap.yaml和promtail-daemonset.yaml)
kubectl apply -f .

檢視服務是否成功建立，檢查pod

# 檢視logging這個namepace下所有的pod
kubectl get pod -n logging

五、登入Grafana

輸入http://${目標IP}: ${grafana對外暴露的nodePort}/login 後出現登入畫面

預設帳號密碼為 帳號:admin、密碼:admin

進入主畫面後按下 "Add your first data source "

選擇Loki

在URL部分輸入 http:// ${目標IP}: ${Loki的nodePort}/

按 save & test，成功後即代表data source新增成功

可以在"Explore"部份下LogQL(類似Prometheus的PromQL，但是是Log版本)，查詢日志

查看pod的log

推薦使用 " Container Log Dashboard " 這個dashboard
( https://grafana.com/grafana/dashboards/16966-container-log-dashboard/ )

這是我新增的Dashboards，是LOKI的Dashboards，如果需要其他的Dashboards，可以在grafana搜尋( https://grafana.com/grafana/dashboards/ )

https://grafana.com/grafana/dashboards/