ceph kubernetes中使用

　　

1.在管理节点上，进入刚创建的放置配置文件的目录，用 ceph-deploy 执行如下步骤

mkdir  /opt/cluster-ceph

cd /opt/cluster-ceph

ceph-deploy new master1 master2 master3

2.添加epel源

yum install -y yum-utils && yum-config-manager --add-repo https://dl.fedoraproject.org/pub/epel/7/x86_64/ && yum install --nogpgcheck -y epel-release && rpm --import /etc/pki/rpm-gpg/RPM-GPG-KEY-EPEL-7 && rm -f /etc/yum.repos.d/dl.fedoraproject.org*

直接进行ceph的安装，会报如下的错误：

--> Finished Dependency Resolution
Error: Package: 2:ceph-common-10.2.11-0.el7.x86_64 (ceph)
           Requires: libbabeltrace-ctf.so.1()(64bit)
Error: Package: 2:ceph-osd-10.2.11-0.el7.x86_64 (ceph)
           Requires: libleveldb.so.1()(64bit)
Error: Package: 2:ceph-mon-10.2.11-0.el7.x86_64 (ceph)
           Requires: libleveldb.so.1()(64bit)
Error: Package: 2:librbd1-10.2.11-0.el7.x86_64 (ceph)
           Requires: liblttng-ust.so.0()(64bit)
Error: Package: 2:ceph-base-10.2.11-0.el7.x86_64 (ceph)
           Requires: liblttng-ust.so.0()(64bit)
Error: Package: 2:librgw2-10.2.11-0.el7.x86_64 (ceph)
           Requires: libfcgi.so.0()(64bit)
Error: Package: 2:ceph-common-10.2.11-0.el7.x86_64 (ceph)
           Requires: libbabeltrace.so.1()(64bit)
Error: Package: 2:librados2-10.2.11-0.el7.x86_64 (ceph)
           Requires: liblttng-ust.so.0()(64bit)

2. 安装 Ceph

[root@localhost ~]# yum install --downloadonly --downloaddir=/tmp/ceph ceph

在每台主机上安装ceph
[root@localhost ~]# yum localinstall -C -y --disablerepo=* /tmp/ceph/*.rpm

 配置初始 monitor(s)、并收集所有密钥

# 请务必在 ceph-cluster 目录下

[root@admin ceph-cluster]# ceph-deploy mon create-initial

初始化 ceph.osd 节点

创建存储空间
[root@osd1 ~]# mkdir -p /data/ceph-osd
[root@osd1 ~]# chown ceph.ceph /data/ceph-osd/ -R

[root@osd2 ~]# mkdir -p /data/ceph-osd
[root@osd2 ~]# chown ceph.ceph /data/ceph-osd/ -R

[root@osd3 ~]# mkdir -p /data/ceph-osd
[root@osd3 ~]# chown ceph.ceph /data/ceph-osd/ -R

[root@osd4 ~]# mkdir -p /data/ceph-osd
[root@osd4 ~]# chown ceph.ceph /data/ceph-osd/ -R

创建OSD：
[root@admin ceph-cluster]# ceph-deploy osd prepare node1:/data/ceph-osd node2:/data/ceph-osd   node3:/data/ceph-osd    node4:/data/ceph-osd

激活 OSD 
[root@admin ceph-cluster]# ceph-deploy osd activate node1:/data/ceph-osd node2:/data/ceph-osd  node3:/data/ceph-osd    node4:/data/ceph-osd

用 ceph-deploy 把配置文件和 admin 密钥拷贝到管理节点和 Ceph 节点，这样你每次执行 Ceph 命令行时就无需指定 monitor 地址和 ceph.client.admin.keyring 了

[root@admin ceph-cluster]# ceph-deploy admin master1  master2  master3  node1  node2  node3  node4

确保你对 ceph.client.admin.keyring 有正确的操作权限。

chmod +r /etc/ceph/ceph.client.admin.keyring （所有机器）

 

如果配置文件更改，需要同步配置文件到所有节点

[root@admin ceph-cluster]#  ceph-deploy  --overwrite-conf  admin master1 master2 master3 node1  node2  node3 node4

官网的zookeeper yaml，去掉了亲和性

apiVersion: v1
kind: Service
metadata:
  namespace: testsubject
  name: zk-hs
  labels:
    app: zk
spec:
  ports:
  - port: 2888
    name: server
  - port: 3888
    name: leader-election
  clusterIP: None
  selector:
    app: zk
---
apiVersion: v1
kind: Service
metadata:
  namespace: testsubject
  name: zk-cs
  labels:
    app: zk
spec:
  ports:
  - port: 2181
    name: client
  selector:
    app: zk
---
apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
  namespace: testsubject
  name: zk-pdb
spec:
  selector:
    matchLabels:
      app: zk
  maxUnavailable: 1
---
apiVersion: apps/v1beta2
kind: StatefulSet
metadata:
  namespace: testsubject
  name: zk
spec:
  selector:
    matchLabels:
      app: zk
  serviceName: zk-hs
  replicas: 3
  updateStrategy:
    type: RollingUpdate
  podManagementPolicy: Parallel
  template:
    metadata:
      labels:
        app: zk
    spec:
      containers:
      - name: kubernetes-zookeeper
        imagePullPolicy: Always
        image: "192.168.200.10/senyint/kubernetes-zookeeper:1.0-3.4.10"
        resources:
          requests:
            memory: "4Gi"
            cpu: "1"
        ports:
        - containerPort: 2181
          name: client
        - containerPort: 2888
          name: server
        - containerPort: 3888
          name: leader-election
        command:
        - sh
        - -c
        - "start-zookeeper 
          --servers=3 
          --data_dir=/var/lib/zookeeper/data 
          --data_log_dir=/var/lib/zookeeper/data/log 
          --conf_dir=/opt/zookeeper/conf 
          --client_port=2181 
          --election_port=3888 
          --server_port=2888 
          --tick_time=2000 
          --init_limit=10 
          --sync_limit=5 
          --heap=512M 
          --max_client_cnxns=60 
          --snap_retain_count=3 
          --purge_interval=12 
          --max_session_timeout=40000 
          --min_session_timeout=4000 
          --log_level=OFF"
        readinessProbe:
          exec:
            command:
            - sh
            - -c
            - "zookeeper-ready 2181"
          initialDelaySeconds: 10
          timeoutSeconds: 5
        livenessProbe:
          exec:
            command:
            - sh
            - -c
            - "zookeeper-ready 2181"
          initialDelaySeconds: 10
          timeoutSeconds: 5
        volumeMounts:
        - name: datazk
          mountPath: /var/lib/zookeeper
  volumeClaimTemplates:
  - metadata:
      name: datazk
    spec:
      accessModes: [ "ReadWriteOnce" ]
      storageClassName: ceph-rbd-database
      resources:
        requests:
          storage: 20Gi

 ceph-secret.yaml

apiVersion: v1
kind: Secret
metadata:
  name: ceph-secret-admin-testsubject
  namespace: testsubject
type: "kubernetes.io/rbd"
data:
  key: QVFERkcvQmF5ckFkSnhBQVVkM2VCdC82K3dOTnZIM3V0ZHpnTnc9PQo=

rbd-storage-data-class.yaml

apiVersion: storage.k8s.io/v1
kind: StorageClass
metadata:
   name: ceph-rbd-database
   namespace: testsubject
provisioner: kubernetes.io/rbd
parameters:
    monitors: 192.168.200.11:6789,192.168.200.12:6789,192.168.200.13:6789
    adminId: admin
    adminSecretName: ceph-secret-admin-testsubject
    adminSecretNamespace: "testsubject"
    pool: fengjian
    userId: admin
    userSecretName: ceph-secret-admin-testsubject
    imageFormat: "2"
    imageFeatures: "layering"

不建立pv， 直接 使用storageclass，然后建立pvc， deployment 指定 claimName

 ceph-secret.yaml

apiVersion: v1
kind: Secret
metadata:
  name: ceph-secret-admin
type: "kubernetes.io/rbd"
data:
  key: QVFERkcvQmF5ckFkSnhBQVVkM2VCdC82K3dOTnZIM3V0ZHpnTnc9PQo=

rbd-storage-data-class.yaml

apiVersion: storage.k8s.io/v1
kind: StorageClass
metadata:
   name: ceph-rbd-provisioner
provisioner: kubernetes.io/rbd
parameters:
    monitors: 192.168.200.11:6789,192.168.200.12:6789,192.168.200.13:6789
    adminId: admin
    adminSecretName: ceph-secret-admin
    adminSecretNamespace: default
    pool: fengjian
    userId: admin
    userSecretName: ceph-secret-admin
    imageFormat: "2"
    imageFeatures: "layering"

 redis.yaml

apiVersion: apps/v1 # for versions before 1.9.0 use apps/v1beta2
kind: Deployment
metadata:
  name: redis-master
spec:
  selector:
    matchLabels:
      app: redis
      role: master
      tier: backend
  replicas: 1
  template:
    metadata:
      labels:
        app: redis
        role: master
        tier: backend
    spec:
      containers:
      - name: master
        image: 192.168.200.10/redis/redis:master
        resources:
          requests:
            cpu: 100m
            memory: 100Mi
        ports:
        - containerPort: 6379
        volumeMounts:
        - name: datadir
          mountPath: /data
      volumes:
      - name: datadir
        persistentVolumeClaim:
          claimName: redis-master-rbd-pvc

---

apiVersion: v1
kind: Service
metadata:
  name: redis-master
  labels:
    app: redis
    role: master
    tier: backend
spec:
  ports:
  - port: 6379
    targetPort: 6379
  selector:
    app: redis
    role: master
    tier: backend

kafka配置文件

参考 ： https://kow3ns.github.io/kubernetes-kafka/manifests/

[root@master1 ceph_rbd]# cat kafka.yaml
apiVersion: v1
kind: Service
metadata:
  name: kafka-hs
  labels:
    app: kafka
spec:
  ports:
  - port: 9093
    name: server
  clusterIP: None
  selector:
    app: kafka
---
apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
  name: kafka-pdb
spec:
  selector:
    matchLabels:
      app: kafka
  maxUnavailable: 1
---
apiVersion: apps/v1beta1
kind: StatefulSet
metadata:
  name: kafka
spec:
  serviceName: kafka-hs
  replicas: 3
  podManagementPolicy: Parallel
  updateStrategy:
      type: RollingUpdate
  template:
    metadata:
      labels:
        app: kafka
    spec:
      affinity:
        podAntiAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            - labelSelector:
                matchExpressions:
                  - key: "app"
                    operator: In
                    values: 
                    - kafka
              topologyKey: "kubernetes.io/hostname"
        podAffinity:
          preferredDuringSchedulingIgnoredDuringExecution:
             - weight: 1
               podAffinityTerm:
                 labelSelector:
                    matchExpressions:
                      - key: "app"
                        operator: In
                        values: 
                        - zk
                 topologyKey: "kubernetes.io/hostname"
      terminationGracePeriodSeconds: 300
      containers:
      - name: k8skafka
        imagePullPolicy: Always
        image: 192.168.200.10/source/kubernetes-kafka:1.0-10.2.1
        resources:
          requests:
            memory: "12Gi"
            cpu: 4
        ports:
        - containerPort: 9093
          name: server
        command:
        - sh
        - -c
        - "exec kafka-server-start.sh /opt/kafka/config/server.properties --override broker.id=${HOSTNAME##*-} 
          --override listeners=PLAINTEXT://:9093 
          --override zookeeper.connect=zk-cs.default.svc.cluster.local:2181 
          --override log.dir=/var/lib/kafka 
          --override auto.create.topics.enable=true 
          --override auto.leader.rebalance.enable=true 
          --override background.threads=10 
          --override compression.type=producer 
          --override delete.topic.enable=false 
          --override leader.imbalance.check.interval.seconds=300 
          --override leader.imbalance.per.broker.percentage=10 
          --override log.flush.interval.messages=9223372036854775807 
          --override log.flush.offset.checkpoint.interval.ms=60000 
          --override log.flush.scheduler.interval.ms=9223372036854775807 
          --override log.retention.bytes=-1 
          --override log.retention.hours=168 
          --override log.roll.hours=168 
          --override log.roll.jitter.hours=0 
          --override log.segment.bytes=1073741824 
          --override log.segment.delete.delay.ms=60000 
          --override message.max.bytes=1000012 
          --override min.insync.replicas=1 
          --override num.io.threads=8 
          --override num.network.threads=3 
          --override num.recovery.threads.per.data.dir=1 
          --override num.replica.fetchers=1 
          --override offset.metadata.max.bytes=4096 
          --override offsets.commit.required.acks=-1 
          --override offsets.commit.timeout.ms=5000 
          --override offsets.load.buffer.size=5242880 
          --override offsets.retention.check.interval.ms=600000 
          --override offsets.retention.minutes=1440 
          --override offsets.topic.compression.codec=0 
          --override offsets.topic.num.partitions=50 
          --override offsets.topic.replication.factor=3 
          --override offsets.topic.segment.bytes=104857600 
          --override queued.max.requests=500 
          --override quota.consumer.default=9223372036854775807 
          --override quota.producer.default=9223372036854775807 
          --override replica.fetch.min.bytes=1 
          --override replica.fetch.wait.max.ms=500 
          --override replica.high.watermark.checkpoint.interval.ms=5000 
          --override replica.lag.time.max.ms=10000 
          --override replica.socket.receive.buffer.bytes=65536 
          --override replica.socket.timeout.ms=30000 
          --override request.timeout.ms=30000 
          --override socket.receive.buffer.bytes=102400 
          --override socket.request.max.bytes=104857600 
          --override socket.send.buffer.bytes=102400 
          --override unclean.leader.election.enable=true 
          --override zookeeper.session.timeout.ms=6000 
          --override zookeeper.set.acl=false 
          --override broker.id.generation.enable=true 
          --override connections.max.idle.ms=600000 
          --override controlled.shutdown.enable=true 
          --override controlled.shutdown.max.retries=3 
          --override controlled.shutdown.retry.backoff.ms=5000 
          --override controller.socket.timeout.ms=30000 
          --override default.replication.factor=1 
          --override fetch.purgatory.purge.interval.requests=1000 
          --override group.max.session.timeout.ms=300000 
          --override group.min.session.timeout.ms=6000 
          --override inter.broker.protocol.version=0.10.2-IV0 
          --override log.cleaner.backoff.ms=15000 
          --override log.cleaner.dedupe.buffer.size=134217728 
          --override log.cleaner.delete.retention.ms=86400000 
          --override log.cleaner.enable=true 
          --override log.cleaner.io.buffer.load.factor=0.9 
          --override log.cleaner.io.buffer.size=524288 
          --override log.cleaner.io.max.bytes.per.second=1.7976931348623157E308 
          --override log.cleaner.min.cleanable.ratio=0.5 
          --override log.cleaner.min.compaction.lag.ms=0 
          --override log.cleaner.threads=1 
          --override log.cleanup.policy=delete 
          --override log.index.interval.bytes=4096 
          --override log.index.size.max.bytes=10485760 
          --override log.message.timestamp.difference.max.ms=9223372036854775807 
          --override log.message.timestamp.type=CreateTime 
          --override log.preallocate=false 
          --override log.retention.check.interval.ms=300000 
          --override max.connections.per.ip=2147483647 
          --override num.partitions=1 
          --override producer.purgatory.purge.interval.requests=1000 
          --override replica.fetch.backoff.ms=1000 
          --override replica.fetch.max.bytes=1048576 
          --override replica.fetch.response.max.bytes=10485760 
          --override reserved.broker.max.id=1000 "
        env:
        - name: KAFKA_HEAP_OPTS
          value : "-Xmx2G -Xms2G"
        - name: KAFKA_OPTS
          value: "-Dlogging.level=INFO"
        volumeMounts:
        - name: datadir
          mountPath: /var/lib/kafka
        readinessProbe:
          tcpSocket:
            port: 9093
          initialDelaySeconds: 30
          periodSeconds: 10
      securityContext:
        runAsUser: 1000
        fsGroup: 1000
  volumeClaimTemplates:
  - metadata:
      name: datadir
      annotations:
        volume.beta.kubernetes.io/storage-class: "ceph-rbd-provisioner"
    spec:
      accessModes: [ "ReadWriteOnce" ]
      resources:
        requests:
          storage: 100Gi

zookeeper.yaml

https://github.com/kow3ns

apiVersion: v1
kind: Service
metadata:
  name: zk-hs
  labels:
    app: zk
spec:
  ports:
  - port: 2888
    name: server
  - port: 3888
    name: leader-election
  clusterIP: None
  selector:
    app: zk
---
apiVersion: v1
kind: Service
metadata:
  name: zk-cs
  labels:
    app: zk
spec:
  ports:
  - port: 2181
    name: client
  selector:
    app: zk
---
apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
  name: zk-pdb
spec:
  selector:
    matchLabels:
      app: zk
  maxUnavailable: 1
---
apiVersion: apps/v1beta1
kind: StatefulSet
metadata:
  name: zk
spec:
  serviceName: zk-hs
  replicas: 3
  podManagementPolicy: Parallel
  updateStrategy:
    type: RollingUpdate
  template:
    metadata:
      labels:
        app: zk
    spec:
      affinity:
        podAntiAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            - labelSelector:
                matchExpressions:
                  - key: "app"
                    operator: In
                    values: 
                    - zk
              topologyKey: "kubernetes.io/hostname"
      containers:
      - name: kubernetes-zookeeper
        imagePullPolicy: Always
        image: "gcr.io/google_containers/kubernetes-zookeeper:1.0-3.4.10"
        resources:
          requests:
            memory: "4Gi"
            cpu: "2"
        ports:
        - containerPort: 2181
          name: client
        - containerPort: 2888
          name: server
        - containerPort: 3888
          name: leader-election
        command:
        - sh
        - -c
        - "start-zookeeper 
          --servers=3 
          --data_dir=/var/lib/zookeeper/data 
          --data_log_dir=/var/lib/zookeeper/data/log 
          --conf_dir=/opt/zookeeper/conf 
          --client_port=2181 
          --election_port=3888 
          --server_port=2888 
          --tick_time=2000 
          --init_limit=10 
          --sync_limit=5 
          --heap=3G 
          --max_client_cnxns=60 
          --snap_retain_count=3 
          --purge_interval=12 
          --max_session_timeout=40000 
          --min_session_timeout=4000 
          --log_level=INFO"
        readinessProbe:
          exec:
            command:
            - sh
            - -c
            - "zookeeper-ready 2181"
          initialDelaySeconds: 10
          timeoutSeconds: 5
        livenessProbe:
          exec:
            command:
            - sh
            - -c
            - "zookeeper-ready 2181"
          initialDelaySeconds: 10
          timeoutSeconds: 5
        volumeMounts:
        - name: datadir
          mountPath: /var/lib/zookeeper
      securityContext:
        runAsUser: 1000
        fsGroup: 1000
  volumeClaimTemplates:
  - metadata:
      name: datadir
    spec:
      accessModes: [ "ReadWriteOnce" ]
      resources:
        requests:
          storage: 250Gi