HorizontalPodAutoscaler(简称 HPA )自动化伸缩策略,可以根据服务负载情况自动扩展或缩小实例数量,以应对不同的流量负载。
1、你需要先一个部署并配置了 Metrics Server 的集群。 Kubernetes Metrics Server 从集群中的 kubelets 收集资源指标, 并通过 Kubernetes API 公开这些指标, 使用 APIService 添加代表指标读数的新资源。
kubectl apply -f metrics-server-components.yaml
此metrics-server-components.yaml文件内容为:
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
k8s-app: metrics-server
rbac.authorization.k8s.io/aggregate-to-admin: "true"
rbac.authorization.k8s.io/aggregate-to-edit: "true"
rbac.authorization.k8s.io/aggregate-to-view: "true"
name: system:aggregated-metrics-reader
rules:
- apiGroups:
- metrics.k8s.io
resources:
- pods
- nodes
verbs:
- get
- list
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
k8s-app: metrics-server
name: system:metrics-server
rules:
- apiGroups:
- ""
resources:
- nodes/metrics
verbs:
- get
- apiGroups:
- ""
resources:
- pods
- nodes
verbs:
- get
- list
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
labels:
k8s-app: metrics-server
name: metrics-server-auth-reader
namespace: kube-system
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: extension-apiserver-authentication-reader
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
k8s-app: metrics-server
name: metrics-server:system:auth-delegator
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: ClusterRoleBinding
metadata:
labels:
k8s-app: metrics-server
name: system:metrics-server
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:metrics-server
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: v1
kind: Service
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
spec:
ports:
- name: https
port: 443
protocol: TCP
targetPort: https
selector:
k8s-app: metrics-server
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
spec:
selector:
matchLabels:
k8s-app: metrics-server
strategy:
rollingUpdate:
maxUnavailable: 0
template:
metadata:
labels:
k8s-app: metrics-server
spec:
hostNetwork: true
containers:
- args:
- --kubelet-insecure-tls
- --cert-dir=/tmp
- --secure-port=4443
- --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
- --kubelet-use-node-status-port
- --metric-resolution=15s
image: registry.cn-hangzhou.aliyuncs.com/google_containers/metrics-server:v0.6.2
imagePullPolicy: IfNotPresent
livenessProbe:
failureThreshold: 3
httpGet:
path: /livez
port: https
scheme: HTTPS
periodSeconds: 10
name: metrics-server
ports:
- containerPort: 4443
name: https
protocol: TCP
readinessProbe:
failureThreshold: 3
httpGet:
path: /readyz
port: https
scheme: HTTPS
initialDelaySeconds: 20
periodSeconds: 10
resources:
requests:
cpu: 100m
memory: 200Mi
securityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
volumeMounts:
- mountPath: /tmp
name: tmp-dir
nodeSelector:
kubernetes.io/os: linux
priorityClassName: system-cluster-critical
serviceAccountName: metrics-server
volumes:
- emptyDir: {}
name: tmp-dir
---
apiVersion: apiregistration.k8s.io/v1
kind: APIService
metadata:
labels:
k8s-app: metrics-server
name: v1beta1.metrics.k8s.io
spec:
group: metrics.k8s.io
groupPriorityMinimum: 100
insecureSkipTLSVerify: true
service:
name: metrics-server
namespace: kube-system
version: v1beta1
versionPriority: 100
2、创建一个Deployment或ReplicaSet的HAP资源,以定义需要自动伸缩的服务目标。
apiVersion: apps/v1
kind: Deployment
metadata:
name: php-apache
spec:
selector:
matchLabels:
run: php-apache
replicas: 1
template:
metadata:
labels:
run: php-apache
spec:
containers:
- name: php-apache
image: harbor/library/hpa-example
ports:
- containerPort: 80
resources:
limits:
cpu: 500m
requests:
cpu: 200m
---
apiVersion: v1
kind: Service
metadata:
name: php-apache
labels:
run: php-apache
spec:
ports:
- port: 80
selector:
run: php-apache
dockerfile文件
FROM php:5-apache
COPY index.php /var/www/html/index.php
RUN chmod a+rx index.php
index.php文件(定义一个 index.php 页面来执行一些 CPU 密集型计算):
$x = 0.0001;
for ($i = 0; $i <= 1000000; $i++) {
$x += sqrt($x);
}
echo "OK!";
?>
构建镜像:docker build -t harbor/library/hpa-example .
推送镜像:docker push harbor/library/hpa-example
[root@master ]# kubectl apply -f php-apache.yaml
deployment.apps/php-apache created
service/php-apache created
3、现在服务器正在运行,使用 kubectl 创建自动扩缩器。
kubectl autoscale deployment php-apache --cpu-percent=50 --min=1 --max=10
命令:cpu平均值超过50%,最少pod数为1,最大pod数为10
查看
[root@master ~]# kubectl get hpa
NAME REFERENCE TARGETS MINPODS MAXPODS REPLICAS AGE
php-apache Deployment/php-apache 0%/50% 1 10 1 80m
请注意当前的 CPU 利用率是 0%,这是由于我们尚未发送任何请求到服务器 TARGET 列显示了相应 Deployment 所控制的所有 Pod 的平均 CPU 利用率
4、接下来,看看自动扩缩器如何对增加的负载做出反应。 这边将启动一个不同的 Pod 作为客户端。 客户端 Pod 中的容器在无限循环中运行,向 php-apache 服务发送查询。
ctrl+c 停止负载测试之后,cpu负载慢慢下降:可以看到他会缩容,pod数量会减少
一旦 CPU 利用率降至 0,HPA 会自动将副本数缩减为 1。
自动扩缩完成副本数量的改变可能需要几分钟的时间。