metric-server概述:
Metrics Server从kubelets收集资源指标,并通过Metrics API将它们暴露在Kubernetes apiserver中,以供HPA(Horizontal Pod Autoscaler)和VPA(Vertical Pod Autoscaler)使用。
Metrics API也可以通过kubectl top访问,从而更容易调试自动缩放管道。
参考链接:
https://github.com/kubernetes/kubernetes/tree/master/cluster/addons/metrics-server
https://kubernetes.io/docs/tasks/debug/debug-cluster/resource-metrics-pipeline/
https://github.com/kubernetes-sigs/metrics-server
部署metric-server:
cat > deoloyment-metric-server.yaml <<'EOF'
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: metrics-server:system:auth-delegator
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:auth-delegator
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
name: metrics-server-auth-reader
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: extension-apiserver-authentication-reader
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: apiregistration.k8s.io/v1beta1
kind: APIService
metadata:
name: v1beta1.metrics.k8s.io
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
spec:
service:
name: metrics-server
namespace: kube-system
group: metrics.k8s.io
version: v1beta1
insecureSkipTLSVerify: true
groupPriorityMinimum: 100
versionPriority: 100
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: metrics-server
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
---
apiVersion: v1
kind: ConfigMap
metadata:
name: metrics-server-config
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: EnsureExists
data:
NannyConfiguration: |-
apiVersion: nannyconfig/v1alpha1
kind: NannyConfiguration
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: metrics-server-v0.3.3
namespace: kube-system
labels:
k8s-app: metrics-server
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
version: v0.3.3
spec:
selector:
matchLabels:
k8s-app: metrics-server
version: v0.3.3
template:
metadata:
name: metrics-server
labels:
k8s-app: metrics-server
version: v0.3.3
annotations:
scheduler.alpha.kubernetes.io/critical-pod: ''
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
spec:
priorityClassName: system-cluster-critical
serviceAccountName: metrics-server
tolerations:
- operator: Exists
containers:
- name: metrics-server
# image: registry.aliyuncs.com/google_containers/metrics-server-amd64:v0.3.3
image: k8s151.oldboyedu.com:5000/metrics-server-amd64:v0.3.3
command:
- /metrics-server
- --metric-resolution=30s
# These are needed for GKE, which doesn't support secure communication yet.
# Remove these lines for non-GKE clusters, and when GKE supports token-based auth.
#- --kubelet-port=10255
#- --deprecated-kubelet-completely-insecure=true
- --kubelet-insecure-tls
- --kubelet-preferred-address-types=InternalIP,Hostname,InternalDNS,ExternalDNS,ExternalIP
ports:
- containerPort: 443
name: https
protocol: TCP
- name: metrics-server-nanny
# image: registry.aliyuncs.com/google_containers/addon-resizer:1.8.5
image: k8s151.oldboyedu.com:5000/addon-resizer:1.8.5
resources:
limits:
cpu: 100m
memory: 300Mi
requests:
cpu: 5m
memory: 50Mi
env:
- name: MY_POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: MY_POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
volumeMounts:
- name: metrics-server-config-volume
mountPath: /etc/config
command:
- /pod_nanny
- --config-dir=/etc/config
#- --cpu=80m
- --extra-cpu=0.5m
#- --memory=80Mi
#- --extra-memory=8Mi
- --threshold=5
- --deployment=metrics-server-v0.3.3
- --container=metrics-server
- --poll-period=300000
- --estimator=exponential
- --minClusterSize=2
# Specifies the smallest cluster (defined in number of nodes)
# resources will be scaled to.
#- --minClusterSize={{ metrics_server_min_cluster_size }}
volumes:
- name: metrics-server-config-volume
configMap:
name: metrics-server-config
---
apiVersion: v1
kind: Service
metadata:
name: metrics-server
namespace: kube-system
labels:
addonmanager.kubernetes.io/mode: Reconcile
kubernetes.io/cluster-service: "true"
kubernetes.io/name: "Metrics-server"
spec:
selector:
k8s-app: metrics-server
ports:
- port: 443
protocol: TCP
targetPort: https
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: system:metrics-server
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
rules:
- apiGroups:
- ""
resources:
- pods
- nodes
- nodes/stats
- namespaces
verbs:
- get
- list
- watch
- apiGroups:
- "extensions"
resources:
- deployments
verbs:
- get
- list
- update
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: system:metrics-server
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:metrics-server
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
EOF
面试题: 请一个Pod做了资源限制,当CPU资源使用率高达90%时如何解决?能否实现自动扩容呢?请说下思路?
---> hpa
Pod水平自动伸缩HPA案例:
1.编写资源清单
cat > deploy-tomcat.yaml <<'EOF'
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: mysql
spec:
replicas: 1
template:
metadata:
labels:
app: oldboyedu-mysql
spec:
tolerations:
- operator: Exists
containers:
- name: mysql
image: k8s151.oldboyedu.com:5000/oldboyedu-db/mysql:5.7
ports:
- containerPort: 3306
env:
- name: MYSQL_ROOT_PASSWORD
value: '123456'
---
apiVersion: v1
kind: Service
metadata:
name: oldboyedu-mysql
spec:
selector:
app: oldboyedu-mysql
ports:
- port: 3306
targetPort: 3306
---
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: oldboyedu-tomcat-app
spec:
replicas: 1
template:
metadata:
labels:
app: oldboyedu-tomcat-app
spec:
tolerations:
- operator: Exists
containers:
- name: myweb
# image: jasonyin2020/tomcat-app:v1
image: k8s151.oldboyedu.com:5000/oldboyedu-tomcat/tomcat-app:v1
resources:
limits:
cpu: "100m"
requests:
cpu: "100m"
ports:
- containerPort: 8080
env:
- name: MYSQL_SERVICE_HOST
value: oldboyedu-mysql
- name: MYSQL_SERVICE_PORT
value: '3306'
---
apiVersion: v1
kind: Service
metadata:
name: oldboyedu-tomcat-app
spec:
type: NodePort
selector:
app: oldboyedu-tomcat-app
ports:
- port: 8080
targetPort: 8080
nodePort: 30888
EOF
2.部署tomcat应用
kubectl apply -f deploy-tomcat.yaml
3.测试
1.支持中文输出
cat >> /etc/mysql/my.cnf <
default-character-set = utf8
EOF
2.插入测试数据
INSERT INTO HPE_APP.T_USERS (USER_NAME,LEVEL) VALUES ('WangJianPing',888888888),('LiuDong',999999999999);
3.查看webUI
http://10.0.0.151:30888/demo
4.创建HPA规则
kubectl autoscale deployment oldboyedu-tomcat-app --max=10 --min=2 --cpu-percent=75
相关参数说明:
--max:
指定最大的Pod数量,如果指定的数量越大,则弹性伸缩的资源创建的就越多,对服务器资源会进行消耗。
--min:
指定最小的Pod数量。
--cpu-percent:
指定CPU的百分比。
温馨提示:
(1)测试时建议修改为CPU使用百分比为5%,生产环节建议设置成75%.
(2)测试时最大Pod数量建议为5个即可,生产环境根据需求而定,通常情况下,10是一个不错的建议;
5.压力测试tomcat,观察Pod的水平伸缩
(1)安装测试工具
yum -y install httpd-tools
(2)使用ab工具进行测试
ab -c 1000 -n 2000000 http://10.0.0.153:30888/
ab -c 100 -n 2000000 http://10.0.0.153:30888/
相关参数说明:
-n:
指定总共压测的次数。
-c:
每次压测发起的并发请求数。
ceph集群环境部署:
1.准备3台节点,所有节点都添加映射关系
[root@ceph201 ~]# cat >> /etc/hosts <
10.0.0.202 ceph202
10.0.0.203 ceph203
EOF
2.ceph201节点配置免密登录(后续ceph-deploy工具依赖免密登录)
(1)配置免密登录
[root@ceph201 ~]# yum -y install expect
[root@ceph201 ~]# cat > password_free_login.sh <<'EOF'
#!/bin/bash
# auther: Jason Yin
# 创建密钥对
ssh-keygen -t rsa -P "" -f /root/.ssh/id_rsa -q
# 声明你服务器密码,建议所有节点的密码均一致,否则该脚本需要再次进行优化
export mypasswd=yinzhengjie
# 定义主机列表
k8s_host_list=(ceph201 ceph202 ceph203)
# 配置免密登录,利用expect工具免交互输入
for i in ${k8s_host_list[@]};do
expect -c "
spawn ssh-copy-id -i /root/.ssh/id_rsa.pub root@$i
expect {
\"*yes/no*\" {send \"yes\r\"; exp_continue}
\"*password*\" {send \"$mypasswd\r\"; exp_continue}
}"
done
EOF
[root@ceph201 ~]# sh password_free_login.sh
(3)让所有节点公用同一套密钥
[root@ceph201 ~]# scp -rp ~/.ssh ceph202:~
[root@ceph201 ~]# scp -rp ~/.ssh ceph203:~
3."ceph201"节点安装"ceph-deploy"工具,用于后期部署ceph集群
(1)准备国内的软件源(含基础镜像软件源和epel源)
[root@ceph201 ~]# curl -o /etc/yum.repos.d/CentOS-Base.repo http://mirrors.aliyun.com/repo/Centos-7.repo
[root@ceph201 ~]# curl -o /etc/yum.repos.d/epel.repo http://mirrors.aliyun.com/repo/epel-7.repo
(2)配置ceph软件源(注意哈,此步骤先试用清华源,之后在第9步骤会报错,切换为阿里源即可。)
[root@ceph201 ~]# cat > /etc/yum.repos.d/oldboyedu-ceph.repo <<'EOF'
[oldboyedu-ceph]
name=oldboyedu linux82 ceph 2022
baseurl=https://mirrors.tuna.tsinghua.edu.cn/ceph/rpm-octopus/el7/x86_64/
gpgcheck=0
enable=1
[oldboyedu-ceph-tools]
name=oldboyedu linux82 ceph tools
baseurl=https://mirrors.tuna.tsinghua.edu.cn/ceph/rpm-octopus/el7/noarch/
gpgcheck=0
enable=1
# [ceph]
# name=ceph
# baseurl=http://mirrors.aliyun.com/ceph/rpm-jewel/el7/x86_64/
# gpgcheck=0
# priority=1
#
# [ceph-noarch]
# name=cephnoarch
# baseurl=http://mirrors.aliyun.com/ceph/rpm-jewel/el7/noarch/
# gpgcheck=0
# priority=1
#
# [ceph-source]
# name=Ceph source packages
# baseurl=http://mirrors.aliyun.com/ceph/rpm-jewel/el7/SRPMS
# gpgcheck=0
EOF
(3)"ceph201"节点安装"ceph-deploy"工具,用于后期部署ceph集群
[root@ceph201 ~]# sed -ri 's#(keepcache=)0#\11#' /etc/yum.conf
[root@ceph201 ~]# yum -y install ceph-deploy
(4)将rpm软件源推送到其它节点
[root@ceph201 ~]# scp /etc/yum.repos.d/*.repo ceph202:/etc/yum.repos.d/
[root@ceph201 ~]# scp /etc/yum.repos.d/*.repo ceph203:/etc/yum.repos.d/
4."ceph201"节点ceph环境准备
(1)"ceph201"节点安装ceph环境
[root@ceph201 ~]# yum -y install ceph ceph-mon ceph-mgr ceph-radosgw ceph-mds ceph-osd
相关软件包功能说明如下:
ceph:
ceph通用模块软件包。
ceph-mon:
ceph数据的监控和分配数据存储,其中mon是monitor的简写。
ceph-mgr:
管理集群状态的组件。其中mgr是manager的简写。基于该组件我们可以让zabbix来监控ceph集群哟。
ceph-radosgw:
对象存储网关,多用于ceph对象存储相关模块软件包。
ceph-mds:
ceph的文件存储相关模块软件包,即"metadata server"
ceph-osd
ceph的块存储相关模块软件包。
(2)将软件打包到本地并推送到其它节点
[root@ceph201 ~]# mkdir ceph-rpm
[root@ceph201 ~]# find /var/cache/yum/ -type f -name "*.rpm" | xargs mv -t ceph-rpm/
[root@ceph201 ~]# tar zcf oldboyedu-ceph.tar.gz ceph-rpm
[root@ceph201 ~]# scp oldboyedu-ceph.tar.gz ceph202:~
[root@ceph201 ~]# scp oldboyedu-ceph.tar.gz ceph203:~
(3)其它节点安装ceph环境
[root@ceph202 ~]# tar xf oldboyedu-ceph.tar.gz && cd ~/ceph-rpm && yum -y localinstall *.rpm
[root@ceph203 ~]# tar xf oldboyedu-ceph.tar.gz && cd ~/ceph-rpm && yum -y localinstall *.rpm
5."ceph201"节点初始化ceph的配置文件
(1)自定义创建ceph的配置文件目录~
[root@ceph201 ~]# mkdir -pv /oldboyedu/ceph/cluster && cd /oldboyedu/ceph/cluster/
(2)所有节点安装"distribute"软件包,提供"pkg_resources"模块,
yum -y install gcc python-setuptools python-devel wget
wget https://pypi.python.org/packages/source/d/distribute/distribute-0.7.3.zip --no-check-certificate
unzip distribute-0.7.3.zip
cd distribute-0.7.3
python setup.py install
(3)初始化ceph的配置文件,注意观察执行命令的所在目录文件变化哟~
[root@ceph201 ~]# cd /oldboyedu/ceph/cluster/ && ceph-deploy new --public-network 10.0.0.0/24 ceph201 ceph202 ceph203
6."ceph201"节点安装ceph-monitor并启动ceph-mon
[root@ceph201 ~]# cd /oldboyedu/ceph/cluster/ && ceph-deploy mon create-initial
7."ceph201"节点将配置和client.admin密钥推送到指定的远程主机以便于管理集群。
[root@ceph201 ~]# cd /oldboyedu/ceph/cluster/ && ceph-deploy admin ceph201 ceph202 ceph203
8."ceph201"节点安装并启动ceph-mgr组件
[root@ceph201 ~]# cd /oldboyedu/ceph/cluster/ && ceph-deploy mgr create ceph201 ceph202 ceph203
9.卸载版本,然后更换指定版本,否则可能在做第十步会出现"Could not locate executable 'ceph-disk' ..."(注意哈,这个步骤需要求将yum源切换为阿里源,之前是清华源)
ceph-deploy --version
yum -y remove ceph-deploy
yum -y install python-pip
pip install ceph-deploy==2.0.1 -i https://mirrors.aliyun.com/pypi/simple
ceph-deploy --version
10."ceph201"节点安装OSD设备
[root@ceph201 ~]# cd /oldboyedu/ceph/cluster
[root@ceph201 ~]# ceph-deploy osd create ceph201 --data /dev/sdb
[root@ceph201 ~]# ceph-deploy osd create ceph201 --data /dev/sdc
[root@ceph201 ~]# ceph-deploy osd create ceph202 --data /dev/sdb
[root@ceph201 ~]# ceph-deploy osd create ceph202 --data /dev/sdc
[root@ceph201 ~]# ceph-deploy osd create ceph203 --data /dev/sdb
[root@ceph201 ~]# ceph-deploy osd create ceph203 --data /dev/sdc
创建OSD是要注意的相关参数说明:
--data DATA:
指定逻辑卷或者设备的绝对路径。
--journal JOURNAL:
指定逻辑卷或者GPT分区的分区路径。生产环境强烈指定该参数,并推荐使用SSD设备。
因为ceph需要先预写日志而后才会真实写入数据,从而达到防止数据丢失的目的。
若不指定该参数,则日志会写入"--data"指定的路径哟。从而降低性能。
对于一个4T的数据盘,其日志并不会占据特别多的空间,通常情况下分配50G足以,当然,LVM是支持动态扩容的。
温馨提示:
(1)如上图所示,指定的设备各个服务器必须存在哟;
(2)如下图所示,当我们创建OSD成功后,就可以通过"ceph -s"查看集群状态了哟;
(3)如下图所示,我们可以通过"ceph osd tree"查看集群各个osd的情况;
(4)如果一个ceph集群的某个主机上有多块磁盘都需要加入osd,只需重复执行上述步骤即可;
(5)如果添加硬盘未识别可执行以下语句:
for i in `seq 0 2`; do echo "- - -" > /sys/class/scsi_host/host${i}/scan;done
选做部分,否则集群处于HEALTH_WARN状态,但并不影响正常使用:
11.禁用安全机制,否则会报错:"mons are allowing insecure global_id reclaim"
ceph config set mon auth_allow_insecure_global_id_reclaim false
12.集群时间同步,否则会报错"clock skew detected on mon.ceph202, mon.ceph203"
(1)所有节点安装chrony服务
[root@ceph201 ~]# yum -y install chrony
(2)备份默认配置文件
[root@ceph201 ~]# cp /etc/chrony.conf{,`date +%F`}
(3)创建配置文件
[root@ceph201 ~]# cat > /etc/chrony.conf <<'EOF'
server ceph201 iburst
driftfile /var/lib/chrony/drift
makestep 1.0 3
rtcsync
allow 10.0.0.0/8
local stratum 10
logdir /var/log/chrony
EOF
(4)其他2个客户端配置
cat > /etc/chrony.conf <<'EOF'
server ceph201 iburst
driftfile /var/lib/chrony/drift
makestep 1.0 3
rtcsync
logdir /var/log/chrony
EOF
(5)将chrony服务设置为开启自启动
systemctl enable --now chronyd
13.所有节点安装"pecan"模块,否则会报错"Module 'restful' has failed dependency: No module named 'pecan'"
pip3 install pecan werkzeug
reboot
14.开启池删除功能
ceph config set mon mon_allow_pool_delete true
ceph的存储池基本管理:
(1)查看现有的所有资源池
ceph osd pool ls
(2)创建资源池
ceph osd pool create oldboyedu-linux 128 128
(3)查看存储池的参数信息(这个值可能会不断的变化哟~尤其是在重命名后!)
ceph osd pool get oldboyedu-linux pg_num
(4)资源池的重命名
ceph osd pool rename oldboyedu-linux oldboyedu-linux-2021
(5)查看资源池的状态
ceph osd pool stats
(6)删除资源池(需要开启删除的功能,否则会报错哟~而且池的名字得写2次!)
ceph osd pool rm oldboyedu-linux oldboyedu-linux --yes-i-really-really-mean-it
其他使用方法:
"ceph osd pool --help"
rbd的块设备(镜像,image)管理:
(1)查看rbd的块(镜像,image)设备:
rbd list -p oldboyedu-linux
rbd ls -p oldboyedu-linux --long --format json --pretty-format # 可以指定输出的样式
(2)创建rbd的块设备:(下面两种写法等效哟)
rbd create --size 1024 --pool oldboyedu-linux linux82 # 不指定单位默认为M
rbd create --size 1024 oldboyedu-linux/linux83
rbd create -s 2G -p oldboyedu-linux linux84 # 也可以指定单位,比如G
(3)修改镜像设备的名称
rbd rename|mv -p oldboyedu-linux oldboyedu-zhibo oldboyedu-linux
rbd rename oldboyedu-linux/linux82 oldboyedu-linux/linux82-2022
rbd mv --pool oldboyedu-linux linux82-2022 linux82
(4)查看镜像的状态
rbd status -p oldboyedu-linux oldboyedu-zhibo2021
rbd status oldboyedu-linux/linux82
(5)移除镜像文件
rbd remove|rm -p oldboyedu-linux oldboyedu-zhibo2021
rbd remove oldboyedu-linux/linux83
rbd rm --pool oldboyedu-linux linux84
(6)查看rbd的详细信息:
rbd info -p oldboyedu-linux linux82 # 等效于"rbd info oldboyedu-linux/linux82"
rbd info oldboyedu-linux/linux82 --format json --pretty-format
温馨提示:
(1)如果是ceph的客户端,想要操作rbd必须安装该工具,其安装包可参考"rpm -qf /usr/bin/rbd"哟;
(2)以上参数有任何不懂的,可以直接使用'rbd help
挂载rbd块设备文件并使用:
1.禁用Linux不支持的核心特性
rbd feature disable oldboyedu-linux/linux82 object-map fast-diff deep-flatten
2.挂载rbd的块设备
2.1 添加映射关系:(添加设备)
[root@ceph201 ~]# rbd map oldboyedu-linux/linux82
2.2 格式化磁盘:
[root@ceph201 ~]# mkfs.xfs /dev/rbd0
2.3 挂载磁盘:
[root@ceph201 ~]# mount /dev/rbd0 /mnt/
2.4 测试数据
[root@ceph201 ~]# cp /etc/os-release /mnt/
2.5 删除映射关系:(删除设备)
[root@ceph201 ~]# umount /mnt/
[root@ceph201 ~]# rbd unmap /dev/rbd0
[root@ceph201 ~]# rbd unmap oldboyedu-linux/linux82
2.6 再次挂载测试数据是否丢失
重复上述步骤即可。
[root@ceph201 ~]# rbd map oldboyedu-linux/linux82
[root@ceph201 ~]# mount /dev/rbd0 /mnt/
[root@ceph202 ~]# rbd map oldboyedu-linux/linux82
[root@ceph202 ~]# mount /dev/rbd0 /mnt/
扩容rbd块设备:
自动扩缩容磁盘大小:(扩容正常,缩容可能会导致设备不可用!需要进一步调研,生产环境要充分测试方能使用!)
rbd resize --size 4096 oldboyedu-linux/linux82
rbd resize -s 1G oldboyedu-linux/linux82 --allow-shrink # 慎用,可能会导致设备不可用! 不推荐使用缩容!
自动扩展XFS文件系统到最大的可用大小:
xfs_growfs /mnt
温馨提示:
(1)我们可以对一个镜像设备进行扩容,是符合正常逻辑的;
(2)我们可以对一个镜像进行缩容,但可能会造成数据丢失,甚至挂载镜像失败的情况哟;
ceph集群缩容osd节点(此处模拟移除"ceph203"节点):
(1)查看集群的OSD信息
[root@ceph201 ~]# ceph osd tree
(2)将ceph203节点的OSD设备权重取消
[root@ceph201 ~]# ceph osd out osd.4
[root@ceph201 ~]# ceph osd out osd.5
(3)将ceph203节点停止osd服务
[root@ceph203 ~]# systemctl disable --now ceph-osd@4
[root@ceph203 ~]# systemctl disable --now ceph-osd@5
(4)在管理节点删除osd
[root@ceph201 ~]# ceph auth del osd.4 # 删除osd认证密钥
[root@ceph201 ~]# ceph auth del osd.5
[root@ceph201 ~]# ceph osd rm 4 # 删除 osd
[root@ceph201 ~]# ceph osd rm 5
(5)解除ceph对磁盘的占用
[root@ceph203 ~]# fuser -k /var/lib/ceph/osd/ceph-4
[root@ceph203 ~]# fuser -k /var/lib/ceph/osd/ceph-5
[root@ceph203 ~]# dmsetup status # 查看设备的唯一编号,便于进行移除!
[root@ceph203 ~]# dmsetup remove ceph--cebb2818--220e--4880--a20e--e12f98a0b3b1-osd--block--ad11e7fe--93bb--48b9--80a6--28e9b2de9d12
[root@ceph203 ~]# dmsetup remove ceph--990406bd--d993--4029--b36d--2f323e10ea04-osd--block--b9e272f1--e034--48eb--b799--9e7fca66869b
(6)清除osd的DNE状态
[root@ceph201 ~]# ceph osd crush remove osd.4
[root@ceph201 ~]# ceph osd crush remove osd.5
(7)清除主机
[root@ceph201 ~]# ceph osd crush remove ceph203
ceph集群扩容osd节点(此处模拟添加"ceph203"节点):
(1)新增节点部署ceph软件包
[root@ceph201 ~]# scp /etc/yum.repos.d/epel.repo /etc/yum.repos.d/oldboyedu-ceph.repo ceph203:/etc/yum.repos.d/
(2)ceph203节点只需安装osd相关的组件即可,因为它并不作为管理节点,而是作为存储节点哟。
yum -y install ceph-osd
systemctl stop firewalld && systemctl disable firewalld # 禁用防火墙功能。
温馨提示:
如下图所示,请及时在ceph节点安装以下的软件包哟,否则你会发现始终无法添加节点呢。
python36-PyYAML-3.13-1.el7.x86_64.rpm
python36-six-1.14.0-3.el7.noarch.rpm
# libyaml-0.1.4-11.el7_0.x86_64.rpm # 该模块可以不选择安装哈!
# python-six-1.9.0-2.el7.noarch.rpm # 该模块可以不选择安装哈!
想要偷懒的同学可以使用局域网:
[root@ceph203 ~]# wget http://192.168.17.253/Kubernetes/day08-/softwares/oldboyedu-ceph.tar.gz
[root@ceph203 ~]# tar xf oldboyedu-ceph.tar.gz && cd ~/ceph-rpm && yum -y localinstall *.rpm
(3)在ceph201管理节点添加新增节点的OSD
[root@ceph201 ~]# cd /oldboyedu/ceph/cluster && ceph-deploy osd create ceph203 --data /dev/sdb
[root@ceph201 ~]# cd /oldboyedu/ceph/cluster && ceph-deploy osd create ceph203 --data /dev/sdc
(4)验证
ceph osd tree
ceph -s
(5)添加OSD注意事项
当我们添加OSD时会自动进行数据的负载均衡哟,因此建议大家如果真需要扩容时可以考虑在业务的低谷期进行哟。
使用ceph对接kubernetes:
1.在K8S集群中安装ceph的基础包环境
(1)创建软件源
curl -o /etc/yum.repos.d/epel.repo http://mirrors.aliyun.com/repo/epel-7.repo
cat > /etc/yum.repos.d/oldboyedu-ceph.repo <
name=oldboyedu linux82 ceph 2022
baseurl=https://mirrors.tuna.tsinghua.edu.cn/ceph/rpm-octopus/el7/x86_64/
gpgcheck=0
enable=1
[oldboyedu-ceph-tools]
name=oldboyedu linux82 ceph tools
baseurl=https://mirrors.tuna.tsinghua.edu.cn/ceph/rpm-octopus/el7/noarch/
gpgcheck=0
enable=1
EOF
(2)master节点开启rpm软件包缓存
[root@k8s151.oldboyedu.com ~]# grep keepcache /etc/yum.conf
keepcache=1
[root@k8s151.oldboyedu.com ~]#
(3)安装ceph的基础包
[root@k8s151.oldboyedu.com ~]# yum -y install ceph-common
(4)将ceph软件包打包并下发到其它k8s node节点
[root@k8s151.oldboyedu.com ~]# mkdir k8s-ceph-common
[root@k8s151.oldboyedu.com ~]# find /var/cache/yum/ -type f -name "*.rpm" | xargs mv -t k8s-ceph-common
[root@k8s151.oldboyedu.com ~]# tar zcf oldboyedu-k8s-ceph-common.tar.gz k8s-ceph-common
[root@k8s151.oldboyedu.com ~]# scp oldboyedu-k8s-ceph-common.tar.gz k8s152.oldboyedu.com:~
[root@k8s151.oldboyedu.com ~]# scp oldboyedu-k8s-ceph-common.tar.gz k8s153.oldboyedu.com:~
(5)其它所有node节点安装ceph软件包
[root@k8s152.oldboyedu.com ~]# tar xf oldboyedu-k8s-ceph-common.tar.gz && yum -y localinstall k8s-ceph-common/*.rpm
[root@k8s153.oldboyedu.com ~]# tar xf oldboyedu-k8s-ceph-common.tar.gz && yum -y localinstall k8s-ceph-common/*.rpm
(6)将ceph集群的配置文件推送到k8s所有节点
[root@ceph201 ~]# scp /etc/ceph/ceph.conf 10.0.0.151:/etc/ceph/
[root@ceph201 ~]# scp /etc/ceph/ceph.conf 10.0.0.152:/etc/ceph/
[root@ceph201 ~]# scp /etc/ceph/ceph.conf 10.0.0.153:/etc/ceph/
参考连接:
https://kubernetes.io/docs/concepts/storage/volumes/#rbd
https://github.com/kubernetes/examples/tree/master/volumes/rbd
2.使用Ceph身份验证密钥
(1)如果提供了Ceph身份验证密钥,则该密钥应首先进行base64编码,然后将编码后的字符串放入密钥yaml中。
[root@ceph201 ~]# grep key /etc/ceph/ceph.client.admin.keyring |awk '{printf "%s", $NF}'|base64
QVFBTzlpTmplSXJZSmhBQS9EUGJYSURjYmYwSHR2Z1BxQUc3MUE9PQ==
[root@ceph201 ~]#
(2)创建Secret资源,注意替换key的值,要和ceph集群的key保持一致哟,上一步我已经取出来了。
[root@k8s151.oldboyedu.com ~]# cat > 01-oldboyedu-ceph-secret.yaml <<'EOF'
apiVersion: v1
kind: Secret
metadata:
name: ceph-secret
type: "kubernetes.io/rbd"
data:
key: QVFBTzlpTmplSXJZSmhBQS9EUGJYSURjYmYwSHR2Z1BxQUc3MUE9PQ==
EOF
(3)在K8S集群中创建Secret资源,以便于后期Pod使用该资源。
[root@k8s151.oldboyedu.com ~]# kubectl apply -f 01-oldboyedu-ceph-secret.yaml
[root@k8s151.oldboyedu.com ~]# kubectl get secret
参考连接:
https://github.com/kubernetes/examples/blob/master/volumes/rbd/secret/ceph-secret.yaml
3.ceph集群创建k8s专用的存储池及镜像
[root@ceph201 ~]# ceph osd pool create k8s 128 128
[root@ceph201 ~]# rbd create -p k8s --size 2G --image-feature layering oldboyedu-linux
4.K8S使用ceph的rbd镜像案例
(1)创建kubernetes集群常用的资源池
[root@ceph201 ~]# ceph osd pool create k8s 128 128
pool 'k8s' created
[root@ceph201 ~]#
(2)在k8s资源池创建块设备,值得注意的是,我们可以指定该镜像的特性,否则由于内核版本过低而无法挂载哟
[root@ceph201 ~]# rbd create -p k8s --size 1024 --image-feature layering oldboyedu-linux
(3)创建K8S的资源,将MySQL的Pod持久化到ceph集群
[root@k8s151.oldboyedu.com ~]# cat > 02-oldboyedu-mysql-deploy.yml <
kind: Deployment
metadata:
name: oldboyedu-web
spec:
replicas: 1
template:
metadata:
labels:
app: oldboyedu-web
spec:
volumes:
- name: linux82-web
rbd:
# 指定ceph集群的mon节点
monitors:
- '10.0.0.201:6789'
- '10.0.0.202:6789'
- '10.0.0.203:6789'
# 指定存储池
pool: k8s
# 指定rbd镜像名称
image: oldboyedu-linux
# 指定文件系统类型,其会自动帮咱们进行格式化哟~
fsType: xfs
# 是否可读,如果设置为true表示只读权限哟~
readOnly: false
# 指定访问ceph集群的用户
user: admin
# 指定访问集群的密钥资源,这个就是我们自己创建的secret局部资源,请一定要确保Pod和secret在同一个namespace,否则无法访问哟。
secretRef:
name: ceph-secret
# 指定镜像格式,老版本不支持该字段,因此我这里也就先注释了
# imageformat: "2"
# 指定镜像特性,老版本不支持该字段,因此我这里就先注释了
# imagefeatures: "layering"
tolerations:
- operator: Exists
containers:
- name: web
image: k8s151.oldboyedu.com:5000/oldboyedu-web/nginx:1.20.1
volumeMounts:
- name: linux82-web
mountPath: /usr/share/nginx/html
EOF
[root@k8s151.oldboyedu.com ~]# kubectl apply -f 02-oldboyedu-mysql-deploy.yml
参考连接:
https://github.com/kubernetes/examples/blob/master/volumes/rbd/rbd-with-secret.yaml
温馨提示:
(1)使用"ceph auth ls"指令可以查看身份验证状态的列表。
(2)创建的资源如下图所示,到时候可以直接参考"/oldboyedu/k8s-ceph"目录的yaml。
(3)这个软件包会出现一大堆错误,需要我们手动逐个去排查,对学员说是一次不错的历练。上课要演示完整的排查流程。
今日内容回顾:
- metrics-server *****
为"kubectl top"和"hpa".
- ceph集群搭建
- ceph集群的基础使用
- 存储池
- 镜像
- ceph集群的扩缩容
- ceph的rbd和K8S集群集成案例 *****