k8s实战之ELK日志管理

首先查看总体流程

首先创建namespace

apiVersion: v1
kind: Namespace
metadata:
  name: kube-logging

一、首先创建es.yaml 

--- 
apiVersion: v1    #kubernetes API版本,采用最新版本v1
kind: Service  #资源类型定义为Service
metadata: 
  name: elasticsearch-logging  # 服务名称elasticsearch-logging
  namespace: kube-logging   #命名空间为kube-logging
  labels:   #标签,用于服务选择器匹配
    k8s-app: elasticsearch-logging 
    kubernetes.io/cluster-service: "true" 
    addonmanager.kubernetes.io/mode: Reconcile 
    kubernetes.io/name: "Elasticsearch" 
spec: 
# 定义用于访问 Elasticsearch 的端口
  ports:
  - port: 9200
    protocol: TCP
    targetPort: db
# 定义用于标识应属于此服务的 Pod 的选择器
  selector:
    k8s-app: elasticsearch-logging 
--- 
# RBAC authn and authz 
apiVersion: v1 
# ServiceAccount 定义用于 Elasticsearch 日志记录
kind: ServiceAccount 
metadata: 
  name: elasticsearch-logging 
  namespace: kube-logging 
  labels: 
    k8s-app: elasticsearch-logging 
    kubernetes.io/cluster-service: "true" 
    addonmanager.kubernetes.io/mode: Reconcile 
---
#用于授予用户对集群中的所有资源的访问权限,Role只对命名空间级别
kind: ClusterRole 
apiVersion: rbac.authorization.k8s.io/v1 
metadata: 
  name: elasticsearch-logging 
  labels: 
    k8s-app: elasticsearch-logging 
    kubernetes.io/cluster-service: "true" 
    addonmanager.kubernetes.io/mode: Reconcile 
rules: 
- apiGroups: 
  - ""
#resources 字段指定了规则适用于哪些资源类型
  resources: 
  - "services" 
  - "namespaces" 
  - "endpoints"
#verbs 字段指定了规则允许执行的操作  
  verbs: 
  - "get" 
---
#ClusterRoleBinding 用于将 ClusterRole 绑定到用户或组 
kind: ClusterRoleBinding 
apiVersion: rbac.authorization.k8s.io/v1 
metadata: 
  namespace: kube-logging 
  name: elasticsearch-logging 
  labels: 
    k8s-app: elasticsearch-logging 
    kubernetes.io/cluster-service: "true" 
    addonmanager.kubernetes.io/mode: Reconcile
#以下说明给ServiceAccount授予在ClusterRole中定义的权限
subjects: 
- kind: ServiceAccount  #指定角色绑定的实体类型
  name: elasticsearch-logging 
  namespace: kube-logging 
  apiGroup: "" 
roleRef: 
  kind: ClusterRole 
  name: elasticsearch-logging 
  apiGroup: "" 
--- 
# Elasticsearch deployment itself 
apiVersion: apps/v1 
kind: StatefulSet #使用statefulset创建Pod 
metadata: 
  name: elasticsearch-logging #pod名称,使用statefulSet创建的Pod是有序号有顺序的 
  namespace: kube-logging  #命名空间 
  labels: 
    k8s-app: elasticsearch-logging 
    kubernetes.io/cluster-service: "true" 
    addonmanager.kubernetes.io/mode: Reconcile 
    srv: srv-elasticsearch 
spec: 
  serviceName: elasticsearch-logging #与svc相关联，这可以确保使用以下DNS地址访问Statefulset中的每个pod (es-cluster-[0,1,2].elasticsearch.elk.svc.cluster.local) 
  replicas: 1 #副本数量,单节点
#selector用于指定 StatefulSet 的 Pod 选择器，只有拥有k8s-app的labels才能被匹配
  selector: 
    matchLabels: 
      k8s-app: elasticsearch-logging #和pod template配置的labels相匹配 
  template: 
    metadata: 
      labels: 
        k8s-app: elasticsearch-logging 
        kubernetes.io/cluster-service: "true" 
    spec:
#表示这个pod使用serviceAccount的名字   
      serviceAccountName: elasticsearch-logging 
      containers: 
      - image: docker.io/library/elasticsearch:7.9.3 
        name: elasticsearch-logging 
        resources: 
          # need more cpu upon initialization, therefore burstable class 
          limits: 
            cpu: 1000m 
            memory: 2Gi 
          requests: 
            cpu: 100m 
            memory: 500Mi 
        ports: 
        - containerPort: 9200 
          name: db 
          protocol: TCP 
        - containerPort: 9300 
          name: transport 
          protocol: TCP 
        volumeMounts: 
        - name: elasticsearch-logging 
          mountPath: /usr/share/elasticsearch/data/   #挂载点 
        env: 
        - name: "NAMESPACE" 
          valueFrom: 
            fieldRef: 
              fieldPath: metadata.namespace 
        - name: "discovery.type"  #定义单节点类型 
          value: "single-node" 
        - name: ES_JAVA_OPTS #设置Java的内存参数，可以适当进行加大调整 
          value: "-Xms512m -Xmx2g"  
      volumes: 
      - name: elasticsearch-logging 
        hostPath: 
          path: /data/es/ 
      nodeSelector: #如果需要匹配落盘节点可以添加 nodeSelect 
        es: data 
      tolerations: 
      - effect: NoSchedule 
        operator: Exists 
      # Elasticsearch requires vm.max_map_count to be at least 262144. 
      # If your OS already sets up this number to a higher value, feel free 
      # to remove this init container. 
      initContainers: #容器初始化前的操作 
      - name: elasticsearch-logging-init 
        image: alpine:3.6 
        command: ["/sbin/sysctl", "-w", "vm.max_map_count=262144"] #添加mmap计数限制，太低可能造成内存不足的错误 
        securityContext:  #仅应用到指定的容器上，并且不会影响Volume 
          privileged: true #运行特权容器 
      - name: increase-fd-ulimit 
        image: busybox 
        imagePullPolicy: IfNotPresent 
        command: ["sh", "-c", "ulimit -n 65536"] #修改文件描述符最大数量 
        securityContext: 
          privileged: true 
      - name: elasticsearch-volume-init #es数据落盘初始化，加上777权限 
        image: alpine:3.6 
        command: 
          - chmod 
          - -R 
          - "777" 
          - /usr/share/elasticsearch/data/ 
        volumeMounts: 
        - name: elasticsearch-logging 
          mountPath: /usr/share/elasticsearch/data/

 二、创建logstach.yaml

--- 
apiVersion: v1 
kind: Service  #指定了资源的类型，这里是 Service，用于定义服务的属性
metadata: #包含资源的元数据，如名称、命名空间等。
  name: logstash 
  namespace: kube-logging 
spec: #包含服务的规格，定义了如何创建和运行服务。
  ports: #指定了服务暴露的端口
  - port: 5044 #服务监听的端口号
    targetPort: beats #将服务请求转发到的 Pod 的端口。   
  selector: #指定了 Pod 的标签选择器，用于匹配需要访问该服务的 Pod 
    type: logstash #匹配的标签。
  clusterIP: None  #设置为 None 表示这是一个无头服务（Headless Service），它不会创建一个虚拟 IP，而是直接将流量转发到匹配的 Pod
--- 
apiVersion: apps/v1 
kind: Deployment  #定义了一个 Deployment，用于管理 Pod 的生命周期和副本数。
metadata:  #包含 Deployment 的元数据
  name: logstash 
  namespace: kube-logging 
spec: 
  selector: 
    matchLabels: 
      type: logstash 
  template: 
    metadata: 
      labels: 
        type: logstash 
        srv: srv-logstash 
    spec: 
      containers: 
      - image: docker.io/kubeimages/logstash:7.9.3 #该镜像支持arm64和amd64两种架构 
        name: logstash 
        ports: 
        - containerPort: 5044 
          name: beats 
        command: 
        - logstash 
        - '-f' 
        - '/etc/logstash_c/logstash.conf' 
        env: 
        - name: "XPACK_MONITORING_ELASTICSEARCH_HOSTS" 
          value: "http://elasticsearch-logging:9200" 
        volumeMounts: 
        - name: config-volume 
          mountPath: /etc/logstash_c/ 
        - name: config-yml-volume 
          mountPath: /usr/share/logstash/config/ 
        - name: timezone 
          mountPath: /etc/localtime 
        resources: #logstash一定要加上资源限制，避免对其他业务造成资源抢占影响 
          limits: 
            cpu: 1000m 
            memory: 2048Mi 
          requests: 
            cpu: 512m 
            memory: 512Mi 
      volumes: 
      - name: config-volume 
        configMap: 
          name: logstash-conf 
          items: 
          - key: logstash.conf 
            path: logstash.conf 
      - name: timezone 
        hostPath: 
          path: /etc/localtime 
      - name: config-yml-volume 
        configMap: 
          name: logstash-yml 
          items: 
          - key: logstash.yml 
            path: logstash.yml 
 
--- 
apiVersion: v1 
kind: ConfigMap 
metadata: 
  name: logstash-conf 
  namespace: kube-logging 
  labels: 
    type: logstash 
data: 
  logstash.conf: |- 
    input {
      beats { 
        port => 5044 
      } 
    } 
    filter {
      # 处理 ingress 日志 
      if [kubernetes][container][name] == "nginx-ingress-controller" {
        json {
          source => "message" 
          target => "ingress_log" 
        }
        if [ingress_log][requesttime] { 
          mutate { 
            convert => ["[ingress_log][requesttime]", "float"] 
          }
        }
        if [ingress_log][upstremtime] { 
          mutate { 
            convert => ["[ingress_log][upstremtime]", "float"] 
          }
        } 
        if [ingress_log][status] { 
          mutate { 
            convert => ["[ingress_log][status]", "float"] 
          }
        }
        if  [ingress_log][httphost] and [ingress_log][uri] {
          mutate { 
            add_field => {"[ingress_log][entry]" => "%{[ingress_log][httphost]}%{[ingress_log][uri]}"} 
          } 
          mutate { 
            split => ["[ingress_log][entry]","/"] 
          } 
          if [ingress_log][entry][1] { 
            mutate { 
              add_field => {"[ingress_log][entrypoint]" => "%{[ingress_log][entry][0]}/%{[ingress_log][entry][1]}"} 
              remove_field => "[ingress_log][entry]" 
            }
          } else { 
            mutate { 
              add_field => {"[ingress_log][entrypoint]" => "%{[ingress_log][entry][0]}/"} 
              remove_field => "[ingress_log][entry]" 
            }
          }
        }
      }
      # 处理以srv进行开头的业务服务日志 
      if [kubernetes][container][name] =~ /^srv*/ { 
        json { 
          source => "message" 
          target => "tmp" 
        } 
        if [kubernetes][namespace] == "kube-logging" { 
          drop{} 
        } 
        if [tmp][level] { 
          mutate{ 
            add_field => {"[applog][level]" => "%{[tmp][level]}"} 
          } 
          if [applog][level] == "debug"{ 
            drop{} 
          } 
        } 
        if [tmp][msg] { 
          mutate { 
            add_field => {"[applog][msg]" => "%{[tmp][msg]}"} 
          } 
        } 
        if [tmp][func] { 
          mutate { 
            add_field => {"[applog][func]" => "%{[tmp][func]}"} 
          } 
        } 
        if [tmp][cost]{ 
          if "ms" in [tmp][cost] { 
            mutate { 
              split => ["[tmp][cost]","m"] 
              add_field => {"[applog][cost]" => "%{[tmp][cost][0]}"} 
              convert => ["[applog][cost]", "float"] 
            } 
          } else { 
            mutate { 
              add_field => {"[applog][cost]" => "%{[tmp][cost]}"} 
            }
          }
        }
        if [tmp][method] { 
          mutate { 
            add_field => {"[applog][method]" => "%{[tmp][method]}"} 
          }
        }
        if [tmp][request_url] { 
          mutate { 
            add_field => {"[applog][request_url]" => "%{[tmp][request_url]}"} 
          } 
        }
        if [tmp][meta._id] { 
          mutate { 
            add_field => {"[applog][traceId]" => "%{[tmp][meta._id]}"} 
          } 
        } 
        if [tmp][project] { 
          mutate { 
            add_field => {"[applog][project]" => "%{[tmp][project]}"} 
          }
        }
        if [tmp][time] { 
          mutate { 
            add_field => {"[applog][time]" => "%{[tmp][time]}"} 
          }
        }
        if [tmp][status] { 
          mutate { 
            add_field => {"[applog][status]" => "%{[tmp][status]}"} 
            convert => ["[applog][status]", "float"] 
          }
        }
      }
      mutate { 
        rename => ["kubernetes", "k8s"] 
        remove_field => "beat" 
        remove_field => "tmp" 
        remove_field => "[k8s][labels][app]" 
      }
    }
    output { 
      elasticsearch { 
        hosts => ["http://elasticsearch-logging:9200"] 
        codec => json 
        index => "logstash-%{+YYYY.MM.dd}" #索引名称以logstash+日志进行每日新建 
      }
    } 
---
 
apiVersion: v1 
kind: ConfigMap 
metadata: 
  name: logstash-yml 
  namespace: kube-logging 
  labels: 
    type: logstash 
data: 
  logstash.yml: |- 
    http.host: "0.0.0.0" 
    xpack.monitoring.elasticsearch.hosts: http://elasticsearch-logging:9200

三、创建filebeat.yaml

--- 
apiVersion: v1 
kind: ConfigMap #定义了一个 ConfigMap，用于存储 Filebeat 的配置文件
metadata: #包含 ConfigMap 的元数据
  name: filebeat-config 
  namespace: kube-logging 
  labels: 
    k8s-app: filebeat  #用于标识 ConfigMap 的标签。
data: 
  filebeat.yml: |-  #Filebeat 的配置文件内容
    filebeat.inputs:  #定义了 Filebeat 的输入源
    - type: container  #输入类型为容器
      enable: true  #启用容器输入
      paths: 
        - /var/log/containers/*.log #这里是filebeat采集挂载到pod中的日志目录 
      processors: 
        - add_kubernetes_metadata: #添加k8s的字段用于后续的数据清洗 
            host: ${NODE_NAME}   #使用节点名称作为主机名
            matchers: 
            - logs_path: 
                logs_path: "/var/log/containers/"  #指定日志路径
    #output.kafka:  #如果日志量较大，es中的日志有延迟，可以选择在filebeat和logstash中间加入kafka 
    #  hosts: ["kafka-log-01:9092", "kafka-log-02:9092", "kafka-log-03:9092"] 
    # topic: 'topic-test-log' 
    #  version: 2.0.0 
    output.logstash: #因为还需要部署logstash进行数据的清洗，因此filebeat是把数据推到logstash中 
       hosts: ["logstash:5044"]  #Logstash 服务的地址和端口
       enabled: true   #启用 Logstash 输出
--- 
apiVersion: v1 
kind: ServiceAccount  #定义了一个 ServiceAccount，用于运行 Filebeat Pod
metadata: #包含 ServiceAccount 的元数据
  name: filebeat  
  namespace: kube-logging 
  labels:   #用于标识 ServiceAccount 的标签。
    k8s-app: filebeat
--- 
apiVersion: rbac.authorization.k8s.io/v1   #定义了一个 ClusterRole，用于授予 ServiceAccount 权限。
kind: ClusterRole 
metadata: 
  name: filebeat 
  labels: 
    k8s-app: filebeat 
rules:  #定义了 ClusterRole 的规则。
- apiGroups: [""] # "" indicates the core API group 
  resources:   #指定资源
  - namespaces 
  - pods 
  verbs: ["get", "watch", "list"]  #指定操作
--- 
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding  #将 ClusterRole 绑定到 ServiceAccount
metadata: 
  name: filebeat 
subjects:  #定义了 ClusterRoleBinding 的主体。
- kind: ServiceAccount  #主体类型为 ServiceAccount
  name: filebeat 
  namespace: kube-logging 
roleRef: 
  kind: ClusterRole #引用了 ClusterRole
  name: filebeat  #引用的 ClusterRole 名称
  apiGroup: rbac.authorization.k8s.io 
--- 
apiVersion: apps/v1 
kind: DaemonSet  #定义了一个 DaemonSet，用于确保在每个节点上运行一个 Filebeat Pod。
metadata: 
  name: filebeat  #包含 DaemonSet 的元数据。
  namespace: kube-logging 
  labels: 
    k8s-app: filebeat  #用于标识 DaemonSet 的标签
spec:  #包含 DaemonSet 的规格
  selector:  #定义了 DaemonSet 的选择器。
    matchLabels: 
      k8s-app: filebeat 
  template:  #定义了 Pod 的模板。
    metadata: 
      labels: 
        k8s-app: filebeat 
    spec: 
      serviceAccountName: filebeat 
      terminationGracePeriodSeconds: 30 
      containers: 
      - name: filebeat 
        image: docker.io/kubeimages/filebeat:7.9.3 #该镜像支持arm64和amd64两种架构 
        args: [ 
          "-c", "/etc/filebeat.yml", 
          "-e","-httpprof","0.0.0.0:6060" 
        ] 
        #ports: 
        #  - containerPort: 6060 
        #    hostPort: 6068 
        env: 
        - name: NODE_NAME 
          valueFrom: 
            fieldRef: 
              fieldPath: spec.nodeName 
        - name: ELASTICSEARCH_HOST 
          value: elasticsearch-logging 
        - name: ELASTICSEARCH_PORT 
          value: "9200" 
        securityContext: 
          runAsUser: 0 
          # If using Red Hat OpenShift uncomment this: 
          #privileged: true 
        resources: 
          limits: 
            memory: 1000Mi 
            cpu: 1000m 
          requests: 
            memory: 100Mi 
            cpu: 100m 
        volumeMounts: 
        - name: config #挂载的是filebeat的配置文件 
          mountPath: /etc/filebeat.yml 
          readOnly: true 
          subPath: filebeat.yml 
        - name: data #持久化filebeat数据到宿主机上 
          mountPath: /usr/share/filebeat/data 
        - name: varlibdockercontainers #这里主要是把宿主机上的源日志目录挂载到filebeat容器中,如果没有修改docker或者containerd的runtime进行了标准的日志落盘路径，可以把mountPath改为/var/lib 
          mountPath: /var/lib
          readOnly: true 
        - name: varlog #这里主要是把宿主机上/var/log/pods和/var/log/containers的软链接挂载到filebeat容器中 
          mountPath: /var/log/ 
          readOnly: true 
        - name: timezone 
          mountPath: /etc/localtime 
      volumes: 
      - name: config 
        configMap: 
          defaultMode: 0600 
          name: filebeat-config 
      - name: varlibdockercontainers 
        hostPath: #如果没有修改docker或者containerd的runtime进行了标准的日志落盘路径，可以把path改为/var/lib 
          path: /var/lib
      - name: varlog 
        hostPath: 
          path: /var/log/ 
      # data folder stores a registry of read status for all files, so we don't send everything again on a Filebeat pod restart 
      - name: inputs 
        configMap: 
          defaultMode: 0600 
          name: filebeat-inputs 
      - name: data 
        hostPath: 
          path: /data/filebeat-data 
          type: DirectoryOrCreate 
      - name: timezone 
        hostPath: 
          path: /etc/localtime 
      tolerations: #加入容忍能够调度到每一个节点 
      - effect: NoExecute 
        key: dedicated 
        operator: Equal 
        value: gpu 
      - effect: NoSchedule 
        operator: Exists 

四、创建kibana.yaml

---
apiVersion: v1
kind: ConfigMap
metadata:
  namespace: kube-logging
  name: kibana-config
  labels:
    k8s-app: kibana
data:   #包含 ConfigMap 中的数据。
  kibana.yml: |-   #Kibana 的配置文件内容
    server.name: kibana
    server.host: "0"              			#允许 Kibana 监听所有网络接口
    i18n.locale: zh-CN                      #设置默认语言为中文
    elasticsearch:
      hosts: ${ELASTICSEARCH_HOSTS}         #es集群连接地址，由于我这都都是k8s部署且在一个ns下，可以直接使用service name连接
--- 
apiVersion: v1 
kind: Service  #用于公开 Kibana 服务。
metadata: 
  name: kibana 
  namespace: kube-logging 
  labels: 
    k8s-app: kibana 
    kubernetes.io/cluster-service: "true" 
    addonmanager.kubernetes.io/mode: Reconcile 
    kubernetes.io/name: "Kibana" 
    srv: srv-kibana 
spec:  #包含 Service 的规格。
  type: NodePort  #Service 类型为 NodePort，允许外部通过节点的 IP 和端口访问服务
  ports: 
  - port: 5601 
    protocol: TCP 
    targetPort: ui 
  selector:   #定义了 Service 的选择器。
    k8s-app: kibana 
--- 
apiVersion: apps/v1 
kind: Deployment   #定义了一个 Deployment，用于管理 Kibana Pod 的生命周期和副本数。
metadata: 
  name: kibana 
  namespace: kube-logging 
  labels: 
    k8s-app: kibana 
    kubernetes.io/cluster-service: "true" 
    addonmanager.kubernetes.io/mode: Reconcile 
    srv: srv-kibana 
spec:   #包含 Deployment 的规格
  replicas: 1 
  selector: 
    matchLabels: 
      k8s-app: kibana 
  template:   #定义了 Pod 的模板。
    metadata: 
      labels: 
        k8s-app: kibana 
    spec: 
      containers: 
      - name: kibana 
        image: docker.io/kubeimages/kibana:7.9.3 #该镜像支持arm64和amd64两种架构 
        resources: 
          # need more cpu upon initialization, therefore burstable class 
          limits: 
            cpu: 1000m 
          requests: 
            cpu: 100m 
        env: 
          - name: ELASTICSEARCH_HOSTS 
            value: http://elasticsearch-logging:9200 
        ports: 
        - containerPort: 5601 
          name: ui 
          protocol: TCP 
        volumeMounts:
        - name: config
          mountPath: /usr/share/kibana/config/kibana.yml
          readOnly: true
          subPath: kibana.yml
      volumes:
      - name: config
        configMap:
          name: kibana-config
--- 
apiVersion: networking.k8s.io/v1
kind: Ingress #定义了一个 Ingress，用于将外部 HTTP/HTTPS 流量路由到内部服务。
metadata: 
  name: kibana 
  namespace: kube-logging 
spec: 
  ingressClassName: nginx
  rules: 
  - host: kibana.wolfcode.cn
    http: 
      paths: 
      - path: / 
        pathType: Prefix
        backend: 
          service:
            name: kibana 
            port:
              number: 5601