k8s日志收集实战（无坑）

一、k8s收集日志方案简介
本文主要介绍在k8s中收集应用的日志方案，应用运行中日志，一般情况下都需要收集存储到一个集中的日志管理系统中，可以方便对日志进行分析统计，监控，甚至用于机器学习，智能分析应用系统问题，及时修复应用所存在的问题。

在k8s集群中应用一般有如下日志输出方式

直接遵循docker官方建议把日志输出到标准输出或者标准错误输出
输出日志到容器内指定目录中
应用直接发送日志给日志收集系统
本文会综合部署上述日志收集方案。

日志收集组件说明

elastisearch 存储收集到的日志
kibana 可视化收集到的日志
logstash 汇总处理日志发送给elastisearch 存储
filebeat 读取容器或者应用日志文件处理发送给elastisearch或者logstash，也可用于汇总日志
fluentd 读取容器或者应用日志文件处理发送给elastisearch，也可用于汇总日志
fluent-bit 读取容器或者应用日志文件处理发送给elastisearch或者fluentd
二、部署
本次实验使用了3台虚拟机做k8s集群，每台虚拟机8C16G内存
1、部署前准备工作

# 拉取文件
yum -y install git     #服务器没有git命令直接安装即可，有请忽略
git clone https://github.com/mgxian/k8s-log.git
cd k8s-log
git checkout v1

# 创建 logging namespace
kubectl apply -f logging-namespace.yaml

2、部署elastisearch

注意：
# 本次部署虽然使用 StatefulSet 但是没有使用pv进行持久化数据存储
# pod重启之后，数据会丢失，生产环境一定要使用pv持久化存储数据

# 部署
kubectl apply -f elasticsearch.yaml

# 查看状态
kubectl get pods,svc -n logging -o wide
[root@k8s-node1 k8s-log]# kubectl get pods,svc -n logging -o wide
NAME                                  READY     STATUS    RESTARTS   AGE       IP           NODE
pod/elasticsearch-logging-0           1/1       Running   0          20h       10.2.11.85   192.168.29.182
pod/elasticsearch-logging-1           1/1       Running   0          10h       10.2.11.91   192.168.29.182

NAME                            TYPE        CLUSTER-IP    EXTERNAL-IP   PORT(S)         AGE       SELECTOR
service/elasticsearch-logging   ClusterIP   10.1.84.47            9200/TCP        20h       k8s-app=elasticsearch-logging

# 等待所有pod变成running状态 
# 访问测试
# 如果测试都有数据返回代表部署成功
[root@k8s-node1 k8s-log]# kubectl run curl -n logging --image=radial/busyboxplus:curl -i --tty
If you don't see a command prompt, try pressing enter.
[ root@curl-775f9567b5-hpslj:/ ]$ 
[ root@curl-775f9567b5-hpslj:/ ]$ nslookup elasticsearch-logging
Server:    10.1.0.2
Address 1: 10.1.0.2 coredns.kube-system.svc.cluster.local

Name:      elasticsearch-logging
Address 1: 10.1.84.47 elasticsearch-logging.logging.svc.cluster.local

#查看集群状态
[ root@curl-775f9567b5-hpslj:/ ]$ curl 'http://elasticsearch-logging:9200/_cluster/health?pretty'
{
  "cluster_name" : "kubernetes-logging",
  "status" : "green",                #green说明集群很健康
  "timed_out" : false,
  "number_of_nodes" : 2,
  "number_of_data_nodes" : 2,
  "active_primary_shards" : 131,
  "active_shards" : 262,
  "relocating_shards" : 0,
  "initializing_shards" : 0,
  "unassigned_shards" : 0,
  "delayed_unassigned_shards" : 0,
  "number_of_pending_tasks" : 0,
  "number_of_in_flight_fetch" : 0,
  "task_max_waiting_in_queue_millis" : 0,
  "active_shards_percent_as_number" : 100.0
}

#查看集群node节点
[ root@curl-775f9567b5-hpslj:/ ]$ curl 'http://elasticsearch-logging:9200/_cat/nodes'
10.2.11.91 58 92 7 1.61 0.89 0.57 mdi - elasticsearch-logging-1
10.2.11.85 65 92 7 1.61 0.89 0.57 mdi * elasticsearch-logging-0

exit

# 清理测试
kubectl delete deploy curl -n logging

3、部署kibana

# 部署
kubectl apply -f kibana.yaml

# 查看状态
kubectl get pods,svc -n logging -o wide
[root@k8s-node1 k8s-log]# kubectl get pods,svc -n logging -o wide
NAME                                  READY     STATUS    RESTARTS   AGE       IP           NODE
pod/elasticsearch-logging-0           1/1       Running   0          20h       10.2.11.85   192.168.29.182
pod/elasticsearch-logging-1           1/1       Running   0          10h       10.2.11.91   192.168.29.182
pod/kibana-logging-6c49699bc7-sdkvn   1/1       Running   0          20h       10.2.1.136   192.168.29.176

NAME                            TYPE        CLUSTER-IP    EXTERNAL-IP   PORT(S)         AGE       SELECTOR
service/elasticsearch-logging   ClusterIP   10.1.84.47            9200/TCP        20h       k8s-app=elasticsearch-logging
service/kibana-logging          NodePort    10.1.116.28           5601:9001/TCP   20h       k8s-app=kibana-logging

# 访问测试
# 浏览器访问下面输出的地址 看到 kibana 界面代表正常
# 192.168.29.176 为集群中某个 node 节点ip
KIBANA_NODEPORT=$(kubectl get svc -n logging | grep kibana-logging | awk '{print $(NF-1)}' | awk -F[:/] '{print $2}')
echo "http://192.168.29.176:$KIBANA_NODEPORT/"

说明：出现如下图示说明kibana启动正常

4、部署fluentd收集日志

# fluentd 以 daemoset 方式部署
# 在每个节点上启动fluentd容器，收集k8s组件，docker以及容器的日志

# 给每个需要启动fluentd的节点打相关label
# kubectl label node lab1 beta.kubernetes.io/fluentd-ds-ready=true
kubectl label nodes --all beta.kubernetes.io/fluentd-ds-ready=true

# 部署
kubectl apply -f fluentd-es-configmap.yaml
kubectl apply -f fluentd-es-ds.yaml

# 查看状态
kubectl get pods,svc -n logging -o wide
[root@k8s-node1 k8s-log]# kubectl get pods,svc -n logging -o wide
NAME                                  READY     STATUS    RESTARTS   AGE       IP           NODE
pod/elasticsearch-logging-0           1/1       Running   0          20h       10.2.11.85   192.168.29.182
pod/elasticsearch-logging-1           1/1       Running   0          10h       10.2.11.91   192.168.29.182
pod/fluentd-es-v2.2.0-bb5t4           1/1       Running   0          20h       10.2.11.87   192.168.29.182
pod/fluentd-es-v2.2.0-lvkhj           1/1       Running   0          20h       10.2.1.137   192.168.29.176
pod/kibana-logging-6c49699bc7-sdkvn   1/1       Running   0          20h       10.2.1.136   192.168.29.176

5、kibana查看日志

5.1、创建index fluentd-k8s-*，由于需要拉取镜像启动容器，可能需要等待几分钟才能看到索引和数据

5.2、查看日志

#检索nginx日志

6、应用日志收集测试
6.1、应用日志输出到标准输出测试

# 启动测试日志输出
kubectl run echo-test --image=radial/busyboxplus:curl -- sh -c 'count=1;while true;do echo log to stdout $count;sleep 1;count=$(($count+1));done'

# 查看状态
[root@k8s-node1 k8s-log]# kubectl get pod 
NAME                                   READY     STATUS    RESTARTS   AGE
echo-test-79fb7d6866-gxzv8             1/1       Running   0          6s

# 命令行查看日志
ECHO_TEST_POD=$(kubectl get pods | grep echo-test | awk '{print $1}')
kubectl logs -f $ECHO_TEST_POD

# 刷新 kibana 查看是否有新日志进入

7、应用日志输出到容器指定目录(filebeat收集)

# 部署
kubectl apply -f log-contanier-file-filebeat.yaml

# 查看
kubectl get pods -o wide

# 添加index filebeat-k8s-* 查看日志

8、应用日志输出到容器指定目录(fluent-bit收集)

# 部署
kubectl apply -f log-contanier-file-fluentbit.yaml

# 查看
kubectl get pods -o wide

# 添加index fluentbit-k8s-* 查看日志

9、应用直接发送日志到日志系统

# 本次测试应用直接输出日志到 elasticsearch

# 部署
kubectl apply -f log-contanier-es.yaml

# 查看
kubectl get pods -o wide

# 添加index k8s-app-* 查看日志

10、清理测试环境

kubectl delete -f log-contanier-es.yaml
kubectl delete -f log-contanier-file-fluentbit.yaml
kubectl delete -f log-contanier-file-filebeat.yaml
kubectl delete deploy echo-test

附录：以上各yaml文件详情
1、elasticsearch.yaml文件（无数据持久化）

[root@k8s-node1 k8s-log]# cat elasticsearch.yaml 
# RBAC authn and authz
apiVersion: v1
kind: ServiceAccount
metadata:
  name: elasticsearch-logging
  namespace: logging
  labels:
    k8s-app: elasticsearch-logging
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
---
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:
  - "services"
  - "namespaces"
  - "endpoints"
  verbs:
  - "get"
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  namespace: logging
  name: elasticsearch-logging
  labels:
    k8s-app: elasticsearch-logging
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
subjects:
- kind: ServiceAccount
  name: elasticsearch-logging
  namespace: logging
  apiGroup: ""
roleRef:
  kind: ClusterRole
  name: elasticsearch-logging
  apiGroup: ""
---
# Elasticsearch deployment itself
apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: elasticsearch-logging
  namespace: logging
  labels:
    k8s-app: elasticsearch-logging
    version: v6.2.5
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
spec:
  serviceName: elasticsearch-logging
  replicas: 2
  selector:
    matchLabels:
      k8s-app: elasticsearch-logging
      version: v6.2.5
  template:
    metadata:
      labels:
        k8s-app: elasticsearch-logging
        version: v6.2.5
        kubernetes.io/cluster-service: "true"
    spec:
      serviceAccountName: elasticsearch-logging
      containers:
      - image: registry.cn-hangzhou.aliyuncs.com/google_containers/elasticsearch:v6.2.5
        name: elasticsearch-logging
        resources:
          # need more cpu upon initialization, therefore burstable class
          limits:
            cpu: 1000m
          requests:
            cpu: 100m
        ports:
        - containerPort: 9200
          name: db
          protocol: TCP
        - containerPort: 9300
          name: transport
          protocol: TCP
        volumeMounts:
        - name: elasticsearch-logging
          mountPath: /data
        env:
        - name: "NAMESPACE"
          valueFrom:
            fieldRef:
              fieldPath: metadata.namespace
      volumes:
      - name: elasticsearch-logging
        emptyDir: {}
      # 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:
      - image: alpine:3.6
        command: ["/sbin/sysctl", "-w", "vm.max_map_count=262144"]
        name: elasticsearch-logging-init
        securityContext:
          privileged: true

---
apiVersion: v1
kind: Service
metadata:
  name: elasticsearch-logging
  namespace: logging
  labels:
    k8s-app: elasticsearch-logging
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/name: "Elasticsearch"
spec:
  ports:
  - port: 9200
    protocol: TCP
    targetPort: db
  selector:
    k8s-app: elasticsearch-logging

1.1、elasticsearch.yaml文件（数据持久化）

[root@k8s-node1 tmp]# cat elasticsearch.yaml 
# RBAC authn and authz
apiVersion: v1
kind: ServiceAccount
metadata:
  name: elasticsearch-logging
  namespace: logging
  labels:
    k8s-app: elasticsearch-logging
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
---
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:
  - "services"
  - "namespaces"
  - "endpoints"
  verbs:
  - "get"
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  namespace: logging
  name: elasticsearch-logging
  labels:
    k8s-app: elasticsearch-logging
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
subjects:
- kind: ServiceAccount
  name: elasticsearch-logging
  namespace: logging
  apiGroup: ""
roleRef:
  kind: ClusterRole
  name: elasticsearch-logging
  apiGroup: ""
---
# Elasticsearch deployment itself
apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: elasticsearch-logging
  namespace: logging
  labels:
    k8s-app: elasticsearch-logging
    version: v6.2.5
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
spec:
  serviceName: elasticsearch-logging
  replicas: 2
  selector:
    matchLabels:
      k8s-app: elasticsearch-logging
      version: v6.2.5
  template:
    metadata:
      labels:
        k8s-app: elasticsearch-logging
        version: v6.2.5
        kubernetes.io/cluster-service: "true"
    spec:
      serviceAccountName: elasticsearch-logging
      containers:
      - image: registry.cn-hangzhou.aliyuncs.com/google_containers/elasticsearch:v6.2.5
        name: elasticsearch-logging
        resources:
          # need more cpu upon initialization, therefore burstable class
          limits:
            cpu: 1000m
          requests:
            cpu: 100m
        ports:
        - containerPort: 9200
          name: db
          protocol: TCP
        - containerPort: 9300
          name: transport
          protocol: TCP
        volumeMounts:
        - name: elasticsearch-logging
          mountPath: /data
        env:
        - name: "NAMESPACE"
          valueFrom:
            fieldRef:
              fieldPath: metadata.namespace
      volumes:
      - name: elasticsearch-logging
        hostPath:
          path: /app/es_data     #此目录需要在各node节点自行创建
      initContainers:
      - image: alpine:3.6
        command: ["/sbin/sysctl", "-w", "vm.max_map_count=262144"]
        name: elasticsearch-logging-init
        securityContext:
          privileged: true

---
apiVersion: v1
kind: Service
metadata:
  name: elasticsearch-logging
  namespace: logging
  labels:
    k8s-app: elasticsearch-logging
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/name: "Elasticsearch"
spec:
  ports:
  - port: 9200
    protocol: TCP
    targetPort: db
  selector:
    k8s-app: elasticsearch-logging

2、kibana yaml文件

[root@k8s-node1 k8s-log]# cat kibana.yaml 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: kibana-logging
  namespace: logging
  labels:
    k8s-app: kibana-logging
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
spec:
  replicas: 1
  selector:
    matchLabels:
      k8s-app: kibana-logging
  template:
    metadata:
      labels:
        k8s-app: kibana-logging
      annotations:
        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
    spec:
      containers:
      - name: kibana-logging
        image: registry.cn-shanghai.aliyuncs.com/k8s-log/kibana:6.2.4
        resources:
          # need more cpu upon initialization, therefore burstable class
          limits:
            cpu: 1000m
          requests:
            cpu: 100m
        env:
          - name: ELASTICSEARCH_URL
            value: http://elasticsearch-logging:9200
          - name: SERVER_BASEPATH
            value: ""
        ports:
        - containerPort: 5601
          name: ui
          protocol: TCP

---
apiVersion: v1
kind: Service
metadata:
  name: kibana-logging
  namespace: logging
  labels:
    k8s-app: kibana-logging
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/name: "Kibana"
spec:
  type: NodePort
  ports:
  - port: 5601
    protocol: TCP
    targetPort: ui
    nodePort: 9001
  selector:
    k8s-app: kibana-logging

3、fluentd-es-configmap yaml文件

[root@k8s-node1 k8s-log]# cat fluentd-es-configmap.yaml 
kind: ConfigMap
apiVersion: v1
metadata:
  name: fluentd-es-config-v0.1.4
  namespace: logging
  labels:
    addonmanager.kubernetes.io/mode: Reconcile
data:
  system.conf: |-
    
      root_dir /tmp/fluentd-buffers/
    
  containers.input.conf: |-
    
      @id fluentd-containers.log
      @type tail
      path /var/log/containers/*.log
      pos_file /var/log/es-containers.log.pos
      time_format %Y-%m-%dT%H:%M:%S.%NZ
      tag raw.kubernetes.*
      read_from_head true
      
        @type multi_format
        
          format json
          time_key time
          time_format %Y-%m-%dT%H:%M:%S.%NZ
        
        
          format /^(?.+) (?stdout|stderr) [^ ]* (?.*)$/
          time_format %Y-%m-%dT%H:%M:%S.%N%:z
        
      
    
    # Detect exceptions in the log output and forward them as one log entry.
    
      @id raw.kubernetes
      @type detect_exceptions
      remove_tag_prefix raw
      message log
      stream stream
      multiline_flush_interval 5
      max_bytes 500000
      max_lines 1000
    
  system.input.conf: |-
    # Examples:
    # time="2016-02-04T06:51:03.053580605Z" level=info msg="GET /containers/json"
    # time="2016-02-04T07:53:57.505612354Z" level=error msg="HTTP Error" err="No such image: -f" statusCode=404
    # TODO(random-liu): Remove this after cri container runtime rolls out.
    
      @id docker.log
      @type tail
      format /^time="(?[^)]*)" level=(?[^ ]*) msg="(?[^"]*)"( err="(?[^"]*)")?( statusCode=($\d+))?/
      path /var/log/docker.log
      pos_file /var/log/es-docker.log.pos
      tag docker
    
    # Multi-line parsing is required for all the kube logs because very large log
    # statements, such as those that include entire object bodies, get split into
    # multiple lines by glog.
    # Example:
    # I0204 07:32:30.020537    3368 server.go:1048] POST /stats/container/: (13.972191ms) 200 [[Go-http-client/1.1] 10.244.1.3:40537]
    
      @id kubelet.log
      @type tail
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?\w)(?\d{4} [^\s]*)\s+(?\d+)\s+(?[^ \]]+)\] (?.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/kubelet.log
      pos_file /var/log/es-kubelet.log.pos
      tag kubelet
    
    # Example:
    # I1118 21:26:53.975789       6 proxier.go:1096] Port "nodePort for kube-system/default-http-backend:http" (:31429/tcp) was open before and is still needed
    
      @id kube-proxy.log
      @type tail
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?\w)(?\d{4} [^\s]*)\s+(?\d+)\s+(?[^ \]]+)\] (?.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/kube-proxy.log
      pos_file /var/log/es-kube-proxy.log.pos
      tag kube-proxy
    
    # Example:
    # I0204 07:00:19.604280       5 handlers.go:131] GET /api/v1/nodes: (1.624207ms) 200 [[kube-controller-manager/v1.1.3 (linux/amd64) kubernetes/6a81b50] 127.0.0.1:38266]
    
      @id kube-apiserver.log
      @type tail
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?\w)(?\d{4} [^\s]*)\s+(?\d+)\s+(?[^ \]]+)\] (?.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/kube-apiserver.log
      pos_file /var/log/es-kube-apiserver.log.pos
      tag kube-apiserver
    
    # Example:
    # I0204 06:55:31.872680       5 servicecontroller.go:277] LB already exists and doesn't need update for service kube-system/kube-ui
    
      @id kube-controller-manager.log
      @type tail
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?\w)(?\d{4} [^\s]*)\s+(?\d+)\s+(?[^ \]]+)\] (?.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/kube-controller-manager.log
      pos_file /var/log/es-kube-controller-manager.log.pos
      tag kube-controller-manager
    
    # Example:
    # W0204 06:49:18.239674       7 reflector.go:245] pkg/scheduler/factory/factory.go:193: watch of *api.Service ended with: 401: The event in requested index is outdated and cleared (the requested history has been cleared [2578313/2577886]) [2579312]
    
      @id kube-scheduler.log
      @type tail
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?\w)(?\d{4} [^\s]*)\s+(?\d+)\s+(?[^ \]]+)\] (?.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/kube-scheduler.log
      pos_file /var/log/es-kube-scheduler.log.pos
      tag kube-scheduler
    
    # Example:
    # I1104 10:36:20.242766       5 rescheduler.go:73] Running Rescheduler
    
      @id rescheduler.log
      @type tail
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?\w)(?\d{4} [^\s]*)\s+(?\d+)\s+(?[^ \]]+)\] (?.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/rescheduler.log
      pos_file /var/log/es-rescheduler.log.pos
      tag rescheduler
    
    # Logs from systemd-journal for interesting services.
    # TODO(random-liu): Remove this after cri container runtime rolls out.
    
      @id journald-docker
      @type systemd
      filters [{ "_SYSTEMD_UNIT": "docker.service" }]
      
        @type local
        persistent true
      
      read_from_head true
      tag docker
    
    
      @id journald-container-runtime
      @type systemd
      filters [{ "_SYSTEMD_UNIT": "{{ container_runtime }}.service" }]
      
        @type local
        persistent true
      
      read_from_head true
      tag container-runtime
    
    
      @id journald-kubelet
      @type systemd
      filters [{ "_SYSTEMD_UNIT": "kubelet.service" }]
      
        @type local
        persistent true
      
      read_from_head true
      tag kubelet
    
    
      @id journald-node-problem-detector
      @type systemd
      filters [{ "_SYSTEMD_UNIT": "node-problem-detector.service" }]
      
        @type local
        persistent true
      
      read_from_head true
      tag node-problem-detector
    
    
    
      @id kernel
      @type systemd
      filters [{ "_TRANSPORT": "kernel" }]
      
        @type local
        persistent true
      
      
        fields_strip_underscores true
        fields_lowercase true
      
      read_from_head true
      tag kernel
    
  forward.input.conf: |-
    # Takes the messages sent over TCP
    
      @type forward
    
  monitoring.conf: |-
    # Prometheus Exporter Plugin
    # input plugin that exports metrics
    
      @type prometheus
    
    
      @type monitor_agent
    
    # input plugin that collects metrics from MonitorAgent
    
      @type prometheus_monitor
      
        host ${hostname}
      
    
    # input plugin that collects metrics for output plugin
    
      @type prometheus_output_monitor
      
        host ${hostname}
      
    
    # input plugin that collects metrics for in_tail plugin
    
      @type prometheus_tail_monitor
      
        host ${hostname}
      
    
  output.conf: |-
    # Enriches records with Kubernetes metadata
    
      @type kubernetes_metadata
    
    
      @id elasticsearch
      @type elasticsearch
      @log_level info
      include_tag_key true
      host elasticsearch-logging
      port 9200
      logstash_format true
      logstash_prefix fluentd-k8s
      logstash_dateformat %Y.%m.%d
      
        @type file
        path /var/log/fluentd-buffers/kubernetes.system.buffer
        flush_mode interval
        retry_type exponential_backoff
        flush_thread_count 2
        flush_interval 5s
        retry_forever
        retry_max_interval 30
        chunk_limit_size 2M
        queue_limit_length 8
        overflow_action block
      
    

4、fluentd-es-ds yaml文件

[root@k8s-node1 k8s-log]# cat fluentd-es-ds.yaml 
apiVersion: v1
kind: ServiceAccount
metadata:
  name: fluentd-es
  namespace: logging
  labels:
    k8s-app: fluentd-es
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: fluentd-es
  labels:
    k8s-app: fluentd-es
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
rules:
- apiGroups:
  - ""
  resources:
  - "namespaces"
  - "pods"
  verbs:
  - "get"
  - "watch"
  - "list"
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: fluentd-es
  labels:
    k8s-app: fluentd-es
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
subjects:
- kind: ServiceAccount
  name: fluentd-es
  namespace: logging
  apiGroup: ""
roleRef:
  kind: ClusterRole
  name: fluentd-es
  apiGroup: ""
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: fluentd-es-v2.2.0
  namespace: logging
  labels:
    k8s-app: fluentd-es
    version: v2.2.0
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
spec:
  selector:
    matchLabels:
      k8s-app: fluentd-es
      version: v2.2.0
  template:
    metadata:
      labels:
        k8s-app: fluentd-es
        kubernetes.io/cluster-service: "true"
        version: v2.2.0
      # This annotation ensures that fluentd does not get evicted if the node
      # supports critical pod annotation based priority scheme.
      # Note that this does not guarantee admission on the nodes (#40573).
      annotations:
        scheduler.alpha.kubernetes.io/critical-pod: ''
        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
    spec:
      # priorityClassName: system-node-critical
      serviceAccountName: fluentd-es
      containers:
      - name: fluentd-es
        image: registry.cn-hangzhou.aliyuncs.com/google_containers/fluentd-elasticsearch:v2.2.0
        env:
        - name: FLUENTD_ARGS
          value: --no-supervisor -q
        resources:
          limits:
            memory: 500Mi
          requests:
            cpu: 100m
            memory: 200Mi
        volumeMounts:
        - name: varlog
          mountPath: /var/log
        - name: varlibdockercontainers
          mountPath: /var/lib/docker/containers
          readOnly: true
        - name: config-volume
          mountPath: /etc/fluent/config.d
      nodeSelector:
        beta.kubernetes.io/fluentd-ds-ready: "true"
      terminationGracePeriodSeconds: 30
      tolerations:
      - effect: NoSchedule
        key: node-role.kubernetes.io/master
        operator: Exists
      volumes:
      - name: varlog
        hostPath:
          path: /var/log
      - name: varlibdockercontainers
        hostPath:
          path: /var/lib/docker/containers
      - name: config-volume
        configMap:
          name: fluentd-es-config-v0.1.4