概述
本文对mysql cluster on kubernetes with ceph的集成使用做了部署和测试。
这个测试案例来源于kubernetes官网，有兴趣的话大家可以看下原文。
我在k8s上部署了一套mysql集群，这个集群包含一个master，两个slave，mysql的数据目录/var/lib/mysql通过数据卷pv挂载到ceph rbd镜像上，当mysql pod迁移时，能无法对接原有的mysql数据。
在mysql主从数据同步方面，使用的是xtrabackup工具，本文不打算对其展开论述。
环境说明
- kubernetes 1.8.2
- mysql 5.7，一主两从3个节点组成master-slave集群
- ceph集群
创建ConfigMap
kubectl create -f https://k8s.io/docs/tasks/run-application/mysql-configmap.yaml
# 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
slave.cnf: |
# Apply this config only on slaves.
[mysqld]
super-read-only创建Service
kubectl create -f https://k8s.io/docs/tasks/run-application/mysql-services.yaml
# 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创建Statefulset
kubectl create -f https://k8s.io/docs/tasks/run-application/mysql-statefulset.yaml
apiVersion: apps/v1beta2 # for versions before 1.8.0 use apps/v1beta1
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: 172.16.18.100:5000/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 [[ $ordinal -eq 0 ]]; then
cp /mnt/config-map/master.cnf /mnt/conf.d/
else
cp /mnt/config-map/slave.cnf /mnt/conf.d/
fi
volumeMounts:
- name: conf
mountPath: /mnt/conf.d
- name: config-map
mountPath: /mnt/config-map
- name: clone-mysql
image: 172.16.18.100:5000/gcr.io/google-samples/xtrabackup:1.0
command:
- bash
- "-c"
- |
set -ex
# Skip the clone if data already exists.
[[ -d /var/lib/mysql/mysql ]] && exit 0
# Skip the clone on master (ordinal index 0).
[[ `hostname` =~ -([0-9]+)$ ]] || exit 1
ordinal=${BASH_REMATCH[1]}
[[ $ordinal -eq 0 ]] && exit 0
# Clone data from previous peer.
ncat --recv-only mysql-$(($ordinal-1)).mysql 3307 | xbstream -x -C /var/lib/mysql
# Prepare the backup.
xtrabackup --prepare --target-dir=/var/lib/mysql
volumeMounts:
- name: data
mountPath: /var/lib/mysql
subPath: mysql
- name: conf
mountPath: /etc/mysql/conf.d
containers:
- name: mysql
image: 172.16.18.100:5000/mysql:5.7
env:
- name: MYSQL_ALLOW_EMPTY_PASSWORD
value: "1"
ports:
- name: mysql
containerPort: 3306
volumeMounts:
- name: data
mountPath: /var/lib/mysql
subPath: mysql
- name: conf
mountPath: /etc/mysql/conf.d
livenessProbe:
exec:
command: ["mysqladmin", "ping"]
initialDelaySeconds: 30
periodSeconds: 10
timeoutSeconds: 5
readinessProbe:
exec:
# Check we can execute queries over TCP (skip-networking is off).
command: ["mysql", "-h", "127.0.0.1", "-e", "SELECT 1"]
initialDelaySeconds: 5
periodSeconds: 2
timeoutSeconds: 1
- name: xtrabackup
image: 172.16.18.100:5000/gcr.io/google-samples/xtrabackup:1.0
ports:
- name: xtrabackup
containerPort: 3307
command:
- bash
- "-c"
- |
set -ex
cd /var/lib/mysql
# Determine binlog position of cloned data, if any.
if [[ -f xtrabackup_slave_info ]]; then
# XtraBackup already generated a partial "CHANGE MASTER TO" query
# because we're cloning from an existing slave.
mv xtrabackup_slave_info change_master_to.sql.in
# Ignore xtrabackup_binlog_info in this case (it's useless).
rm -f xtrabackup_binlog_info
elif [[ -f xtrabackup_binlog_info ]]; then
# We're cloning directly from master. Parse binlog position.
[[ `cat xtrabackup_binlog_info` =~ ^(.*?)[[:space:]]+(.*?)$ ]] || 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
volumes:
- name: conf
emptyDir: {}
- name: config-map
configMap:
name: mysql
volumeClaimTemplates:
- metadata:
name: data
annotations:
volume.beta.kubernetes.io/storage-class: ceph
spec:
accessModes: ["ReadWriteOnce"]
resources:
requests:
storage: 10Gi检查创建的k8s api对象
检查pv,pvc
[root@172 ~]# kubectl get pv,pvc | grep mysql
pv/pvc-2b89e760-d64a-11e7-9581-000c29f99475 10Gi RWO Delete Bound default/data-mysql-0 ceph 1m
pv/pvc-41126384-d64a-11e7-9581-000c29f99475 10Gi RWO Delete Bound default/data-mysql-1 ceph 39s
pv/pvc-5122d058-d64a-11e7-9581-000c29f99475 10Gi RWO Delete Bound default/data-mysql-2 ceph 12s
pvc/data-mysql-0 Bound pvc-2b89e760-d64a-11e7-9581-000c29f99475 10Gi RWO ceph 1m
pvc/data-mysql-1 Bound pvc-41126384-d64a-11e7-9581-000c29f99475 10Gi RWO ceph 39s
pvc/data-mysql-2 Bound pvc-5122d058-d64a-11e7-9581-000c29f99475 10Gi RWO ceph 12s检查pod
[root@172 ~]# kubectl get po -owide
NAME READY STATUS RESTARTS AGE IP NODE
mysql-0 2/2 Running 0 1m 192.168.5.188 172.16.20.10
mysql-1 2/2 Running 0 1m 192.168.3.24 172.16.20.12
mysql-2 2/2 Running 0 35s 192.168.2.165 172.16.20.11测试
从mysql master写入数据
kubectl run mysql-client --image=172.16.18.100:5000/mysql:5.7 -i --rm --restart=Never --\
mysql -h mysql-0.mysql <<EOF
CREATE DATABASE test;
CREATE TABLE test.messages (message VARCHAR(250));
INSERT INTO test.messages VALUES ('hello');
EOF从mysql slave读取数据
kubectl run mysql-client --image=172.16.18.100:5000/mysql:5.7 -i -t --rm --restart=Never --\
mysql -h mysql-read -e "SELECT * FROM test.messages"mysql master迁移
将节点172.16.20.10设置为维护状态
kubectl cordon 172.16.20.10
[root@172 ~]# kubectl get no
NAME STATUS ROLES AGE VERSION
172.16.20.10 Ready,SchedulingDisabled <none> 3d v1.8.2
172.16.20.11 Ready <none> 4d v1.8.2
172.16.20.12 Ready <none> 4d v1.8.2迁移mysql-0
kubectl delete pod/mysql-0[root@172 mysql]# kubectl get po -l app=mysql -owide -w
NAME READY STATUS RESTARTS AGE IP NODE
mysql-0 2/2 Running 0 9m 192.168.5.188 172.16.20.10
mysql-1 2/2 Running 0 9m 192.168.3.24 172.16.20.12
mysql-2 2/2 Running 0 8m 192.168.2.165 172.16.20.11
mysql-0 2/2 Terminating 0 9m 192.168.5.188 172.16.20.10
mysql-0 1/2 Terminating 0 10m 192.168.5.188 172.16.20.10
mysql-0 0/2 Terminating 0 10m <none> 172.16.20.10
mysql-0 0/2 Terminating 0 11m <none> 172.16.20.10
mysql-0 0/2 Terminating 0 11m <none> 172.16.20.10
mysql-0 0/2 Pending 0 0s <none> <none>
mysql-0 0/2 Pending 0 0s <none> 172.16.20.12
mysql-0 0/2 Init:0/2 0 0s <none> 172.16.20.12
mysql-0 0/2 Init:1/2 0 3s 192.168.3.25 172.16.20.12
mysql-0 0/2 PodInitializing 0 4s 192.168.3.25 172.16.20.12
mysql-0 1/2 Running 0 5s 192.168.3.25 172.16.20.12
mysql-0 2/2 Running 0 9s 192.168.3.25 172.16.20.12验证数据
kubectl run mysql-client --image=172.16.18.100:5000/mysql:5.7 -i --rm --restart=Never --\
mysql -h mysql-0.mysql -e "SELECT * FROM test.messages"
message
hello可见，mysql-0从172.16.20.10迁移到172.16.20.12后，依然能够查询出迁移前写入的数据。
恢复节点
[root@172 ~]# kubectl uncordon 172.16.20.10
node "172.16.20.10" uncordonedmaster slave迁移
[root@172 ~]# kubectl get po -owide
NAME READY STATUS RESTARTS AGE IP NODE
mysql-0 2/2 Running 0 2h 192.168.3.25 172.16.20.12
mysql-1 2/2 Running 0 3h 192.168.3.24 172.16.20.12
mysql-2 2/2 Running 0 3h 192.168.2.165 172.16.20.11迁移mysql-1
[root@172 ~]# kubectl delete pod/mysql-1
pod "mysql-1" deletedmysql-1从172.16.20.12迁到172.16.20.10
[root@172 ~]# kubectl get pod -l app=mysql -owide -w
NAME READY STATUS RESTARTS AGE IP NODE
mysql-0 2/2 Running 0 2h 192.168.3.25 172.16.20.12
mysql-1 2/2 Running 0 3h 192.168.3.24 172.16.20.12
mysql-2 2/2 Running 0 3h 192.168.2.165 172.16.20.11
mysql-1 2/2 Terminating 0 3h 192.168.3.24 172.16.20.12
mysql-1 0/2 Terminating 0 3h <none> 172.16.20.12
mysql-1 0/2 Terminating 0 3h <none> 172.16.20.12
mysql-1 0/2 Terminating 0 3h <none> 172.16.20.12
mysql-1 0/2 Terminating 0 3h <none> 172.16.20.12
mysql-1 0/2 Pending 0 0s <none> <none>
mysql-1 0/2 Pending 0 0s <none> 172.16.20.10
mysql-1 0/2 Init:0/2 0 0s <none> 172.16.20.10
mysql-1 0/2 Init:1/2 0 2s 192.168.5.192 172.16.20.10
mysql-1 0/2 PodInitializing 0 3s 192.168.5.192 172.16.20.10
mysql-1 1/2 Running 0 4s 192.168.5.192 172.16.20.10
mysql-1 2/2 Running 0 8s 192.168.5.192 172.16.20.10从mysql-1验证数据
kubectl run mysql-client --image=172.16.18.100:5000/mysql:5.7 -i --rm --restart=Never --\
mysql -h mysql-1.mysql -e "SELECT * FROM test.messages"
message
hello