K8S 集群上部署、管理MySql集群
一、 MySQL高可用方案
本文的MySQL高可用方案为主从复制+读写分离,即由单一的master和多个slave所构成。其中,客户端通过master对数据库进行写操作,通过slave端进行读操作。master出现问题后,可以将应用切换到slave端。 此方案是MySQL官方提供的一种高可用解决方案,节点间的数据同步采用MySQL Replication技术。
MySQL Replication从一个MySQL数据库服务器(master)的数据复制到一个或多个MySQL数据库服务器(slave)。在默认情况下,复制是异步的;slave不需要一直接收来自主机的更新。根据配置,可以复制数据库中的所有数据库、选定的数据库,或者特定的表。
二、部署须知
-
您需要拥有一个带有默认StorageClass的动态PersistentVolume配置器 ,或者您 自己静态配置PersistentVolumes以满足 此处使用的PersistentVolumeClaims。
-
本教程假设您熟悉 PersistentVolumes 和StatefulSets,以及其他核心概念,如Pod, Services和 ConfigMaps。
-
搭建mysql集群之前请保证您有一个可用的k8s集群。
三、部署步骤
3.1 设置动态PersistentVolume
官网教程也是省略了这一步,没有新建PersistentVolume配置器
(a) 新建pv1.yaml
apiVersion: v1
kind: PersistentVolume
metadata:
labels:
app: mysq0
name: data-mysql-0
spec:
#指定pv的容量为1Gi
capacity:
storage: 10Gi
#指定访问模式
accessModes:
#pv能以readwrite模式mount到单个节点
- ReadWriteOnce
hostPath:
path: /opt/mysql0
type: DirectoryOrCreate
#指定pv的回收策略,即pvc资源释放后的事件.recycle(不建议,使用动态供给代替)删除pvc的所有文件
persistentVolumeReclaimPolicy: Retain
(b) 新建pv2.yaml
apiVersion: v1
kind: PersistentVolume
metadata:
labels:
app: mysql
name: data-mysql-1
spec:
#指定pv的容量为1Gi
capacity:
storage: 10Gi
#指定访问模式
accessModes:
#pv能以readwrite模式mount到单个节点
- ReadWriteOnce
hostPath:
path: /opt/mysql1
type: DirectoryOrCreate
#指定pv的回收策略,即pvc资源释放后的事件.recycle(不建议,使用动态供给代替)删除pvc的所有文件
persistentVolumeReclaimPolicy: Retain
(c) 新建pv3.yaml
apiVersion: v1
kind: PersistentVolume
metadata:
labels:
app: mysql
name: data-mysql-2
spec:
#指定pv的容量为1Gi
capacity:
storage: 10Gi
#指定访问模式
accessModes:
#pv能以readwrite模式mount到单个节点
- ReadWriteOnce
hostPath:
path: /opt/mysql2
type: DirectoryOrCreate
#指定pv的回收策略,即pvc资源释放后的事件.recycle(不建议,使用动态供给代替)删除pvc的所有文件
persistentVolumeReclaimPolicy: Retain
分别运行以上的PersistentVolume(重要,否则mysql集群会初始化失败)
kubectl create -f pv1.yaml
kubectl create -f pv2.yaml
kubectl create -f pv3.yaml
3.2 创建mysql-configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
name: mysql
labels:
app: mysql
data:
master.cnf: |
# Apply this config only on the master.
[mysqld]
log-bin
log_bin_trust_function_creators=1
lower_case_table_names=1
slave.cnf: |
# Apply this config only on slaves.
[mysqld]
super-read-only
log_bin_trust_function_creators=1
3.3 创建 mysql-services.yaml
# Headless service for stable DNS entries of StatefulSet members.
apiVersion: v1
kind: Service
metadata:
name: mysql
labels:
app: mysql
spec:
ports:
- name: mysql
port: 3306
clusterIP: None
selector:
app: mysql
---
# Client service for connecting to any MySQL instance for reads.
# For writes, you must instead connect to the master: mysql-0.mysql.
apiVersion: v1
kind: Service
metadata:
name: mysql-read
labels:
app: mysql
spec:
ports:
- name: mysql
port: 3306
selector:
app: mysql
3.4 创建mysql-statefulset.yaml
鉴于mysql为有状态服务,这里采用statefulset的方式部署
类型特性 | Deployment | StatefulSet |
---|---|---|
是否暴露到外网 | 可以 | 一般不 |
请求面向的对象 | serviceName | 指定pod的域名 |
灵活性 | 只能通过service/serviceIp访问到k8s自动转发的pod | 可以访问任意一个自定义的pod |
易用性 | 只需要关心Service的信息即可 | 需要知道要访问的pod启动的名称、headlessService名称 |
PV/PVC绑定关系的稳定性(多replicas) | (pod挂掉后重启)无法保证初始的绑定关系 | 可以保证 |
pod名称稳定性 | 不稳定,因为是通过template创建,每次为了避免重复都会后缀一个随机数 | 稳定,每次都一样 |
启动顺序(多replicas) | 随机启动,如果pod宕掉重启,会自动分配一个node重新启动 | pod按 app-0、app-1...app-(n-1),如果pod宕掉重启,还会在之前的node上重新启动 |
停止顺序(多replicas) | 随机停止 | 倒序停止 |
集群内部服务发现 | 只能通过service访问到随机的pod | 可以打通pod之间的通信(主要是被发现) |
性能开销 | 无需维护pod与node、pod与PVC 等关系 | 比deployment类型需要维护额外的关系信息 |
创建mysql-statefulset.yaml
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: mysql
spec:
selector:
matchLabels:
app: mysql
serviceName: mysql
replicas: 3
template:
metadata:
labels:
app: mysql
spec:
initContainers:
- name: init-mysql
image: mysql:5.7
command:
- bash
- "-c"
- |
set -ex
# Generate mysql server-id from pod ordinal index.
[[ `hostname` =~ -([0-9]+)$ ]] || exit 1
ordinal=${BASH_REMATCH[1]}
echo [mysqld] > /mnt/conf.d/server-id.cnf
# Add an offset to avoid reserved server-id=0 value.
echo server-id=$((100 + $ordinal)) >> /mnt/conf.d/server-id.cnf
# Copy appropriate conf.d files from config-map to emptyDir.
if [[ $ordinal -eq 0 ]]; then
cp /mnt/config-map/master.cnf /mnt/conf.d/
else
cp /mnt/config-map/slave.cnf /mnt/conf.d/
fi
volumeMounts:
- name: conf
mountPath: /mnt/conf.d
- name: config-map
mountPath: /mnt/config-map
- name: clone-mysql
image: ist0ne/xtrabackup
command:
- bash
- "-c"
- |
set -ex
# Skip the clone if data already exists.
[[ -d /var/lib/mysql/mysql ]] && exit 0
# Skip the clone on master (ordinal index 0).
[[ `hostname` =~ -([0-9]+)$ ]] || exit 1
ordinal=${BASH_REMATCH[1]}
[[ $ordinal -eq 0 ]] && exit 0
# Clone data from previous peer.
ncat --recv-only mysql-$(($ordinal-1)).mysql 3307 | xbstream -x -C /var/lib/mysql
# Prepare the backup.
xtrabackup --prepare --target-dir=/var/lib/mysql
volumeMounts:
- name: data
mountPath: /var/lib/mysql
subPath: mysql
- name: conf
mountPath: /etc/mysql/conf.d
containers:
- name: mysql
image: mysql:5.7
env:
- name: MYSQL_ALLOW_EMPTY_PASSWORD
value: "1"
ports:
- name: mysql
containerPort: 3306
volumeMounts:
- name: data
mountPath: /var/lib/mysql
subPath: mysql
- name: conf
mountPath: /etc/mysql/conf.d
resources:
requests:
cpu: 500m
memory: 1Gi
livenessProbe:
exec:
command: ["mysqladmin", "ping"]
initialDelaySeconds: 30
periodSeconds: 10
timeoutSeconds: 5
readinessProbe:
exec:
# Check we can execute queries over TCP (skip-networking is off).
command: ["mysql", "-h", "127.0.0.1", "-e", "SELECT 1"]
initialDelaySeconds: 5
periodSeconds: 2
timeoutSeconds: 1
- name: xtrabackup
image: ist0ne/xtrabackup
ports:
- name: xtrabackup
containerPort: 3307
command:
- bash
- "-c"
- |
set -ex
cd /var/lib/mysql
# Determine binlog position of cloned data, if any.
if [[ -f xtrabackup_slave_info ]]; then
# XtraBackup already generated a partial "CHANGE MASTER TO" query
# because we're cloning from an existing slave.
mv xtrabackup_slave_info change_master_to.sql.in
# Ignore xtrabackup_binlog_info in this case (it's useless).
rm -f xtrabackup_binlog_info
elif [[ -f xtrabackup_binlog_info ]]; then
# We're cloning directly from master. Parse binlog position.
[[ `cat xtrabackup_binlog_info` =~ ^(.*?)[[:space:]]+(.*?)$ ]] || exit 1
rm xtrabackup_binlog_info
echo "CHANGE MASTER TO MASTER_LOG_FILE='${BASH_REMATCH[1]}',\
MASTER_LOG_POS=${BASH_REMATCH[2]}" > change_master_to.sql.in
fi
# Check if we need to complete a clone by starting replication.
if [[ -f change_master_to.sql.in ]]; then
echo "Waiting for mysqld to be ready (accepting connections)"
until mysql -h 127.0.0.1 -e "SELECT 1"; do sleep 1; done
echo "Initializing replication from clone position"
# In case of container restart, attempt this at-most-once.
mv change_master_to.sql.in change_master_to.sql.orig
mysql -h 127.0.0.1 <<EOF
$(<change_master_to.sql.orig),
MASTER_HOST='mysql-0.mysql',
MASTER_USER='root',
MASTER_PASSWORD='',
MASTER_CONNECT_RETRY=10;
START SLAVE;
EOF
fi
# Start a server to send backups when requested by peers.
exec ncat --listen --keep-open --send-only --max-conns=1 3307 -c \
"xtrabackup --backup --slave-info --stream=xbstream --host=127.0.0.1 --user=root"
volumeMounts:
- name: data
mountPath: /var/lib/mysql
subPath: mysql
- name: conf
mountPath: /etc/mysql/conf.d
resources:
requests:
cpu: 100m
memory: 100Mi
- name: mysql_exporter
env:
- name: DATA_SOURCE_NAME
value: root:@(127.0.0.1:3306)/
image: prom/mysqld-exporter
imagePullPolicy: Always
name: mysql-exporter
ports:
- containerPort: 9104
protocol: TCP
volumes:
- name: conf
emptyDir: {}
- name: config-map
configMap:
name: mysql
volumeClaimTemplates:
- metadata:
name: data
spec:
accessModes: ["ReadWriteOnce"]
resources:
requests:
storage: 10Gi
注意事项:
-
官方文档地址为image: gcr.io/google-samples/xtrabackup:1.0
亲测,拉取image会失败,需要改成以下配置
# 该镜像地址无法获取,导致mysql在pod中初始化失败
image: ist0ne/xtrabackup
如果不确定可以,docker search xtrabackup,查看一下可用的xtrabackup镜像
- 由于要实现mysql集群的监控,故需要增加mysqld-exporter的image实现mysql集群信息的暴露。暴露端口9104。
四、MySQL集群监控
4.1简述
Prometheus(普罗米修斯)是一套开源的监控&报警&时间序列数据库的组合,现在最常见的Kubernetes容器管理系统中,通常会搭配Prometheus进行监控。
Prometheus基本原理是通过HTTP协议周期性抓取被监控组件的状态,这样做的好处是任意组件只要提供HTTP接口就可以接入监控系统,不需要任何SDK或者其他的集成过程。这样做非常适合虚拟化环境比如VM或者Docker 。
4.2 prometheus 安装部署
本文采用docker安装prometheus 。
4.2.1 拉取镜像
docker pull prom/prometheus
4.2.2 修改配置文件
在本机上新建需要挂载的prometheus的配置文件,与数据存储文件
vim prometheus.yml
# 写入以下内容
# my global config
global:
scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
# scrape_timeout is set to the global default (10s).
# Alertmanager configuration
alerting:
alertmanagers:
- static_configs:
- targets:
# - alertmanager:9093
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
# - "first_rules.yml"
# - "second_rules.yml"
# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
# The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
- job_name: 'prometheus'
# metrics_path defaults to '/metrics'
# scheme defaults to 'http'.
static_configs:
- targets: ['localhost:9090']
# k8s中mysql的集群信息
- job_name: 'mysql-0'
static_configs:
- targets: ['10.244.1.6:9104']
labels:
instance: db1
- job_name: 'mysql-1'
static_configs:
- targets: ['10.244.2.5:9104']
labels:
instance: db2
- job_name: 'mysql-2'
static_configs:
- targets: ['10.244.0.7:9104']
4.2.3 映射配置文件启动prometheus
docker run -d --name myPrometheus -p 9090:9090 -v /opt/mgc/myPrometheus/prometheus.yml:/etc/prometheus/prometheus.yml -v /opt/mgc/myPrometheus/prometheus-data:/prometheus-data prom/prometheus
4.2.4 访问prometheus
五、MySQL 数据备份与迁移
5.1 数据备份
由于在statefulset中的mysql集群配置,采用了挂载卷的形式存储数据到本地磁盘,故已实现了mysql的数据备份。详见3.3中的mysql-statefulset.yaml配置文件
5.2 数据迁移
5.2.1 从mysql master 写入数据
kubectl run mysql-client --image=mysql:5.7 -i --rm --restart=Never --\
mysql -h mysql-0.mysql <<EOF
CREATE DATABASE test2;
CREATE TABLE test2.messages (message VARCHAR(250));
INSERT INTO test.messages VALUES ('hello mgc');
EOF
5.2.2 从mysql slave读取数据
kubectl run mysql-client --image=mysql:5.7 -i -t --rm --restart=Never -- mysql -h mysql-read -e "SELECT * FROM test.messages"
5.2.3 查看集群状态
[root@k8s-m1 mgc]# kubectl get no
NAME STATUS ROLES AGE VERSION
k8s-m1 Ready <none> 72d v1.13.5
k8s-m2 Ready <none> 72d v1.13.5
k8s-m3 Ready <none> 72d v1.13.5
5.2.4 将节点k8s-m1设置为维护状态
[root@k8s-m1 mgc]# kubectl cordon k8s-m1
node/k8s-m1 cordoned
5.2.5 再次查看集群状态
[root@k8s-m1 mgc]# kubectl get no
NAME STATUS ROLES AGE VERSION
k8s-m1 Ready,SchedulingDisabled <none> 72d v1.13.5
k8s-m2 Ready <none> 72d v1.13.5
k8s-m3 Ready <none> 72d v1.13.5
[root@k8s-m1 mgc]# kubectl get pods -owide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
mysql-0 3/3 Running 0 7m52s 10.244.2.6 k8s-m3 <none> <none>
mysql-1 3/3 Running 0 46h 10.244.2.5 k8s-m3 <none> <none>
mysql-2 3/3 Running 0 46h 10.244.0.7 k8s-m2 <none> <none>
5.2.6 迁移mysql-0
[root@k8s-m1 mgc]# kubectl delete pod/mysql-0
pod "mysql-0" deleted
5.2.7 验证数据
kubectl run mysql-client --image=mysql:5.7 -i --rm --restart=Never --\
mysql -h mysql-0.mysql -e "SELECT * FROM test.messages"
message
hello
5.2.8 恢复节点
kubectl uncordon k8s-m1
六、k8s常用命令
查看启动进度
kubectl get pods -l app=mysql --watch
查看pod
kubectl get pods
删除pod
kubectl delete pod pod名称
可以使用describe命令查看这个失败的Pod的明细:
$ kubectl describe pod fail-1034443984-jerry
]# kubectl create -f pv3.yaml
查看pod的详情
kubectl get pvc,pv,statefulset,pod,service,configmap |grep mysql
检查pv,pvc
[root@k8s-m1 mgc]# kubectl get pvc,pv |grep mysql
persistentvolumeclaim/data-mysql-0 Bound data-mysql-0 10Gi RWO 23h
persistentvolumeclaim/data-mysql-1 Bound data-mysql-1 10Gi RWO 23h
persistentvolumeclaim/data-mysql-2 Bound data-mysql-2 10Gi RWO 23h
persistentvolume/data-mysql-0 10Gi RWO Retain Bound default/data-mysql-0 23h
persistentvolume/data-mysql-1 10Gi RWO Retain Bound default/data-mysql-1 23h
persistentvolume/data-mysql-2 10Gi RWO Retain Bound default/data-mysql-2 23h
检查pod
[root@k8s-m1 mgc]# kubectl get po -owide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
mysql-0 2/2 Running 0 23h 10.244.1.2 k8s-m1 <none> <none>
mysql-1 2/2 Running 0 23h 10.244.2.4 k8s-m3 <none> <none>
mysql-2 2/2 Running 0 23h 10.244.0.6 k8s-m2 <none> <none>
https://segmentfault.com/a/1190000012244714
查看pod的状态:
可以使用describe命令查看这个失败的Pod的明细:
$ kubectl describe pod fail-1034443984-jerry
详细信息查询
kubectl get pod mysql-0 --output yaml