Stories

Detail Return Return

納尼?自建K8s集羣日誌收集還能通過JMQ保存到JES - Stories Detail

一、背景

基於K8s集羣的私有化交付方案中，日誌收集採用了ilogtail+logstash+kafka+es方案，其中ilogtail負責日誌收集，logstash負責對數據轉換，kafka負責對日誌傳遞中的消峯進而減少es的寫入壓力，es用來保存日誌數據。在私有化交付中本方案中涉及的中間件一般需要單獨部署，但是在京東內網環境的部署考慮到kafka和es的高可用，則不推薦採用單獨部署的方案。

二、新方案實踐

1.新方案簡介

在京東內網環境部署K8S並收集日誌， kafka+es的替代方案考慮使用JMQ+JES，由於JMQ的底層是基於kafaka、JES的底層基於ES，所以該替換方案理論上是可行的

2.主要架構

數據流向大致如下
應用日誌 -> ilogtail -> JMQ -> logstash -> JES

3.如何使用

核心改造點彙總

  1. ilogtail nameservers配置
    增加解析JMQ域名的nameserver（京東雲主機上無法直接解析.local域名）
spec:
    spec:
      dnsPolicy: "None"
      dnsConfig:
        nameservers:
          - x.x.x.x # 可以解析jmq域名的nameserver
  1. ilogtail flushers配置
    調整發送到JMQ到配置
apiVersion: v1
kind: ConfigMap
metadata:
  name: ilogtail-user-cm
  namespace: elastic-system
data:
  app_stdout.yaml: |
    flushers:
      - Type: flusher_stdout
        OnlyStdout: true
      - Type: flusher_kafka_v2
        Brokers:
          - nameserver.jmq.jd.local:80 # jmq元數據地址
        Topic: ai-middle-k8s-log-prod # jmq topic 
        ClientID: ai4middle4log # Kafka的用户ID（識別客户端並設置其唯一性），對應jmq的Group名稱，重要‼️ （https://ilogtail.gitbook.io/ilogtail-docs/plugins/input/service-kafka#cai-ji-pei-zhi-v2）
  1. logstash kafka&es配置
apiVersion: v1
kind: ConfigMap
metadata:
  name: logstash-config
  namespace: elastic-system
  labels:
    elastic-app: logstash
data:
  logstash.conf: |-
    input {
        kafka {
                bootstrap_servers => ["nameserver.jmq.jd.local:80"] #jmq的元數據地址
                group_id => "ai4middle4log" # jmq的Group的名稱
                client_id => "ai4middle4log" # jmq的Group的名稱，即jmq的省略了kafka中的client_id概念，用Group名稱代替
                consumer_threads => 2
                decorate_events => true
                topics => ["ai-middle-k8s-log-prod"] # jmp的topic
                auto_offset_reset => "latest"
                codec => json { charset => "UTF-8" }
        }
    }
    output {
        elasticsearch {
                hosts => ["http://x.x.x.x:40000","http://x.x.x.x:40000","http://x.x.x.x:40000"] # es地址
                index =>  "%{[@metadata][kafka][topic]}-%{+YYYY-MM-dd}" # 索引規則
                user => "XXXXXX" #jes的用户名
                password => "xxxxx" #jes的密碼
                ssl => "false"
                ssl_certificate_verification => "false"
        }
    }

ilogtail 的配置如下

# ilogtail-daemonset.yaml
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: ilogtail-ds
  namespace: elastic-system
  labels:
    k8s-app: logtail-ds
spec:
  selector:
    matchLabels:
      k8s-app: logtail-ds
  template:
    metadata:
      labels:
        k8s-app: logtail-ds
    spec:
      dnsPolicy: "None"
      dnsConfig:
        nameservers:
          - x.x.x.x # （京東雲主機上）可以解析jmq域名的nameserver
      tolerations:
        - operator: Exists                    # deploy on all nodes
      containers:
        - name: logtail
          env:
            - name: ALIYUN_LOG_ENV_TAGS       # add log tags from env
              value: _node_name_|_node_ip_
            - name: _node_name_
              valueFrom:
                fieldRef:
                  apiVersion: v1
                  fieldPath: spec.nodeName
            - name: _node_ip_
              valueFrom:
                fieldRef:
                  apiVersion: v1
                  fieldPath: status.hostIP
            - name: cpu_usage_limit           # iLogtail's self monitor cpu limit
              value: "1"
            - name: mem_usage_limit           # iLogtail's self monitor mem limit
              value: "512"
          image: dockerhub.ai.jd.local/ai-middleware/ilogtail-community-edition/ilogtail:1.3.1
          imagePullPolicy: IfNotPresent
          resources:
            limits:
              cpu: 1000m
              memory: 1Gi
            requests:
              cpu: 400m
              memory: 384Mi
          volumeMounts:
            - mountPath: /var/run                       # for container runtime socket
              name: run
            - mountPath: /logtail_host                  # for log access on the node
              mountPropagation: HostToContainer
              name: root
              readOnly: true
            - mountPath: /usr/local/ilogtail/checkpoint # for checkpoint between container restart
              name: checkpoint
            - mountPath: /usr/local/ilogtail/user_yaml_config.d # mount config dir
              name: user-config
              readOnly: true
            - mountPath: /usr/local/ilogtail/apsara_log_conf.json
              name: apsara-log-config
              readOnly: true
              subPath: apsara_log_conf.json
      dnsPolicy: ClusterFirst
      hostNetwork: true
      volumes:
        - hostPath:
            path: /var/run
            type: Directory
          name: run
        - hostPath:
            path: /
            type: Directory
          name: root
        - hostPath:
            path: /etc/ilogtail-ilogtail-ds/checkpoint
            type: DirectoryOrCreate
          name: checkpoint
        - configMap:
            defaultMode: 420
            name: ilogtail-user-cm
          name: user-config
        - configMap:
            defaultMode: 420
            name: ilogtail-apsara-log-config-cm
          name: apsara-log-config
# ilogtail-user-configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: ilogtail-user-cm
  namespace: elastic-system
data:
  app_stdout.yaml: |
    enable: true
    inputs:
      - Type: service_docker_stdout
        Stderr: true
        Stdout: true
        K8sNamespaceRegex: ai-train
        ExternalK8sLabelTag:
          platform/resource-name: k8s_label_resource-name
          platform/task-identify: k8s_label_task-identify
          task-id: k8s_label_task-id
          run-id: k8s_label_run-id
          request-id: k8s_label_request-id
    processors:
      - Type: processor_rename
        SourceKeys:
          - k8s_label_resource-name
          - k8s_label_task-identify
          - k8s_label_task-id
          - k8s_label_run-id
          - k8s_label_request-id
          - _namespace_
          - _image_name_
          - _pod_uid_
          - _pod_name_
          - _container_name_
          - _container_ip_
          - __path__
          - _source_
        DestKeys:
          - resource_name
          - task_identify
          - task_id
          - run_id
          - request_id
          - namespace
          - image_name
          - pod_uid
          - pod_name
          - container_name
          - container_ip
          - path
          - source
    flushers:
      - Type: flusher_stdout
        OnlyStdout: true
      - Type: flusher_kafka_v2
        Brokers:
          - nameserver.jmq.jd.local:80 # jmq元數據地址
        Topic: ai-middle-k8s-log-prod # jmq topic 
        ClientID: ai4middle4log # Kafka的用户ID（識別客户端並設置其唯一性），對應jmq的Group名稱，重要‼️ （https://ilogtail.gitbook.io/ilogtail-docs/plugins/input/service-kafka#cai-ji-pei-zhi-v2）

  app_file_log.yaml: |
    enable: true
    inputs:
      - Type: file_log
        LogPath: /export/Logs/ai-dt-algorithm-tools
        FilePattern: "*.log"
        ContainerInfo:
          K8sNamespaceRegex: ai-train
          ExternalK8sLabelTag:
            platform/resource-name: k8s_label_resource-name
            platform/task-identify: k8s_label_task-identify
            task-id: k8s_label_task-id
            run-id: k8s_label_run-id
            request-id: k8s_label_request-id

    processors:
      - Type: processor_add_fields
        Fields:
          source: file
      - Type: processor_rename
        SourceKeys:
          - __tag__:k8s_label_resource-name
          - __tag__:k8s_label_task-identify
          - __tag__:k8s_label_task-id
          - __tag__:k8s_label_run-id
          - __tag__:k8s_label_request-id
          - __tag__:_namespace_
          - __tag__:_image_name_
          - __tag__:_pod_uid_
          - __tag__:_pod_name_
          - __tag__:_container_name_
          - __tag__:_container_ip_
          - __tag__:__path__
        DestKeys:
          - resource_name
          - task_identify
          - task_id
          - run_id
          - request_id
          - namespace
          - image_name
          - pod_uid
          - pod_name
          - container_name
          - container_ip
          - path

    flushers:
      - Type: flusher_stdout
        OnlyStdout: true
      - Type: flusher_kafka_v2
        Brokers:
          - nameserver.jmq.jd.local:80
        Topic: ai-middle-k8s-log-prod
        ClientID: ai4middle4log

logstash 的配置如下

# logstash-configmap.yaml
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: logstash-config
  namespace: elastic-system
  labels:
    elastic-app: logstash
data:
  logstash.conf: |-
    input {
        kafka {
                bootstrap_servers => ["nameserver.jmq.jd.local:80"] #jmq的元數據地址
                #group_id => "services"
                group_id => "ai4middle4log" # jmq的Group的名稱
                client_id => "ai4middle4log" # jmq的Group的名稱，即jmq的省略了kafka中的client_id概念，用Group名稱代替
                consumer_threads => 2
                decorate_events => true
                #topics_pattern => ".*"
                topics => ["ai-middle-k8s-log-prod"] # jmp的topic
                auto_offset_reset => "latest"
                codec => json { charset => "UTF-8" }
        }
    }


    filter {
      ruby {
          code => "event.set('index_date', event.get('@timestamp').time.localtime + 8*60*60)"
      }
      ruby {
          code => "event.set('message',event.get('contents'))"
      }
      #ruby {
      #    code => "event.set('@timestamp',event.get('time').time.localtime)"
      #}

      mutate {
          remove_field => ["contents"]
          convert => ["index_date", "string"]
          #convert => ["@timestamp", "string"]
          gsub => ["index_date", "T.*Z",""]
          #gsub => ["@timestamp", "T.*Z",""]
      }
    }


    output {
        elasticsearch {
                #hosts => ["https://ai-middle-cluster-es-http:9200"]
                hosts => ["http://x.x.x.x:40000","http://x.x.x.x:40000","http://x.x.x.x:40000"] # es地址
                index =>  "%{[@metadata][kafka][topic]}-%{+YYYY-MM-dd}" # 索引規則
                user => "XXXXXX" #jes的用户名
                password => "xxxxx" #jes的密碼
                ssl => "false"
                ssl_certificate_verification => "false"
                #cacert => "/usr/share/logstash/cert/ca_logstash.cer"
        }
        stdout {
            codec => rubydebug
        }
    }

4.核心價值

在私有化部署的基礎上通過簡單改造實現了與京東內部中間件的完美融合，使得系統在高可用性上適應性更強、可用範圍更廣。

程序員
user avatar wnhyang Avatar digitalocean Avatar febobo Avatar axuicn Avatar jeecg Avatar
Favorites 5 users favorite the story!
Favorites

Add a new Comments

Some HTML is okay.