1.hadoop集群搭建

新建hadoop文件夹

mkdir hadoop

docker拉取镜像

docker pull kubeguide/hadoop:latest

新建hadoop命名空间

kubectl create namespace hadoop

编辑hadoop.yaml vim hadoop.yaml

apiVersion: v1
kind: ConfigMap
metadata:
  name: kube-hadoop-conf
  namespace: hadoop
data:
  HDFS_MASTER_SERVICE: hadoop-hdfs-master
  HDOOP_YARN_MASTER: hadoop-yarn-master
---
apiVersion: v1
kind: Service
metadata:
  name: hadoop-hdfs-master
  namespace: hadoop
spec:
  type: NodePort
  selector:
    name: hdfs-master
  ports:
    - name: rpc
      port: 9000
      targetPort: 9000
    - name: http
      port: 50070
      targetPort: 50070
      nodePort: 32007
---
apiVersion: v1
kind: ReplicationController
metadata:
  name: hdfs-master
  namespace: hadoop
  labels:
    name: hdfs-master
spec:
  replicas: 1
  selector:
    name: hdfs-master
  template:
    metadata:
      labels:
        name: hdfs-master
    spec:
      containers:
        - name: hdfs-master
          image: kubeguide/hadoop:latest
          imagePullPolicy: IfNotPresent
          ports:
            - containerPort: 9000
            - containerPort: 50070
          env:
            - name: HADOOP_NODE_TYPE
              value: namenode
            - name: HDFS_MASTER_SERVICE
              valueFrom:
                configMapKeyRef:
                  name: kube-hadoop-conf
                  key: HDFS_MASTER_SERVICE
            - name: HDOOP_YARN_MASTER
              valueFrom:
                configMapKeyRef:
                  name: kube-hadoop-conf
                  key: HDOOP_YARN_MASTER
      restartPolicy: Always
---
apiVersion: v1
kind: ReplicationController
metadata:
  name: hadoop-datanode
  namespace: hadoop
  labels:
    app: hadoop-datanode
spec:
  replicas: 3
  selector:
    name: hadoop-datanode
  template:
    metadata:
      labels:
        name: hadoop-datanode
    spec:
      containers:
        - name: hadoop-datanode
          image: kubeguide/hadoop:latest
          imagePullPolicy: IfNotPresent
          ports:
            - containerPort: 9000
            - containerPort: 50070
          env:
            - name: HADOOP_NODE_TYPE
              value: datanode
            - name: HDFS_MASTER_SERVICE
              valueFrom:
                configMapKeyRef:
                  name: kube-hadoop-conf
                  key: HDFS_MASTER_SERVICE
            - name: HDOOP_YARN_MASTER
              valueFrom:
                configMapKeyRef:
                  name: kube-hadoop-conf
                  key: HDOOP_YARN_MASTER
      restartPolicy: Always
---
apiVersion: v1
kind: Service
metadata:
  name: hadoop-yarn-master
  namespace: hadoop
spec:
  type: NodePort
  selector:
    name: yarn-master
  ports:
     - name: "8030"
       port: 8030
     - name: "8031"
       port: 8031
     - name: "8032"
       port: 8032
     - name: http
       port: 8088
       targetPort: 8088
       nodePort: 32088
---
apiVersion: v1
kind: ReplicationController
metadata:
  name: yarn-master
  namespace: hadoop
  labels:
    name: yarn-master
spec:
  replicas: 1
  selector:
    name: yarn-master
  template:
    metadata:
      labels:
        name: yarn-master
    spec:
      containers:
        - name: yarn-master
          image: kubeguide/hadoop:latest
          imagePullPolicy: IfNotPresent
          ports:
            - containerPort: 9000
            - containerPort: 50070
          env:
            - name: HADOOP_NODE_TYPE
              value: resourceman
            - name: HDFS_MASTER_SERVICE
              valueFrom:
                configMapKeyRef:
                  name: kube-hadoop-conf
                  key: HDFS_MASTER_SERVICE
            - name: HDOOP_YARN_MASTER
              valueFrom:
                configMapKeyRef:
                  name: kube-hadoop-conf
                  key: HDOOP_YARN_MASTER
      restartPolicy: Always
---
apiVersion: v1
kind: Service
metadata:
  name: yarn-node
  namespace: hadoop
spec:
  clusterIP: None
  selector:
    name: yarn-node
  ports:
     - port: 8040
---
apiVersion: v1
kind: ReplicationController
metadata:
  name: yarn-node
  namespace: hadoop
  labels:
    name: yarn-node
spec:
  replicas: 3
  selector:
    name: yarn-node
  template:
    metadata:
      labels:
        name: yarn-node
    spec:
      containers:
        - name: yarn-node
          image: kubeguide/hadoop:latest
          imagePullPolicy: IfNotPresent
          ports:
            - containerPort: 8040
            - containerPort: 8041
            - containerPort: 8042
          env:
            - name: HADOOP_NODE_TYPE
              value: yarnnode
            - name: HDFS_MASTER_SERVICE
              valueFrom:
                configMapKeyRef:
                  name: kube-hadoop-conf
                  key: HDFS_MASTER_SERVICE
            - name: HDOOP_YARN_MASTER
              valueFrom:
                configMapKeyRef:
                  name: kube-hadoop-conf
                  key: HDOOP_YARN_MASTER
      restartPolicy: Always

运行hadoop.yaml

kubectl create -f hadoop.yaml

查看是否运行及外部接口

kubectl get pod -n hadoop
kubectl get svc -n hadoop

2.访问HDFS网页

3.访问Hadoop网页

4.遇到的问题

在我将hadoop.yaml文件运行起来后，但是在集群外无法访问HDFS和Hadoop，搞了几个小时没头绪，后面我将内核从3.3升到了5.4，具体可看Centos7更改默认启动内核。接着我发现有一个节点的虚拟机上一直显示out of memory,并且正在杀死进程，我猜想是不是因为虚拟机内存不够，致使容器服务没有跑起来，于是我增加了虚拟机的内存。重启以后HDFS和Hadoop的界面就出来了