首先在k8s中,k8s会根据每个work节点的配置,负载差异,自动生成优选函数,根据优选函数,当master节点分配下来任务时,将pod分配带最适合运行的node节点上。

之外我们技术人员还有以下三种方式去影响我们的pod调度,

  1. node节点调度器
  2. 亲和性调度
  3. 污点容忍度

区别和实例操作

一 .node节点调度

是最直接的调度方式,简单粗暴,所以常用在简单的集群架构中,负载的资源分类和编制不适合这种方式,
解释:大概意思就是给我们的work节点绑定唯一便签,然后在pod的yml文件中去设置node便签匹配器绑定节点,这样就能实现影响k8s优选参数的选择,让当前的pod启动在设置的node节点上。

1、首先通过 kubectl 给 node 打上标签

格式:
kubectl label nodes <node-name> <label-key>=<label-value>
[root@k8s-master ~]# kubectl label nodes k8s-node01 zone=sh
[root@k8s-master ~]# kubectl get nodes --show-labels

2、通过 nodeSelector 调度 pod 到 node

  • Pod的定义中通过nodeSelector指定label标签,pod将会只调度到具有该标签的node之上
[root@k8s-master ~]# vim pod-demo.yaml
apiVersion: v1
kind: Pod
metadata:
  name: nginx
  labels:
    env: test
spec:
  containers:
  - name: nginx
    image: nginx
    imagePullPolicy: IfNotPresent
  nodeSelector:
    disktype: ssd
  • 这个例子中pod只会调度到具有 disktype=ssd 的 node 上面.
  • 验证 节点调度
[root@k8s-master ~]# kubectl apply -f pod-demo.yaml 
[root@k8s-master ~]# kubectl get pods -o wide
[root@k8s-master ~]# kubectl describe pod  pod-demo   ##查看事件

二 .亲和性调度

较复杂,应用在复杂的多节点归类,资源分类管理的中大型集群中,有硬亲和,软亲和,亲和性和反亲和,两两为一组,反义词


硬亲和:匹配节点上的其中一个或多个标签(必须存在一个)
软亲和:匹配节点上的其中一个或多个标签(有则选择这个node,没有就参考优选函数)

1.硬亲和

[root@k8s-master ~]# vim pod-nodeaffinity-demo.yaml 
apiVersion: v1
kind: Pod
metadata:
  name: pod-node-affinity-demo
  labels:
    app: myapp
    tier: frontend
spec:
  containers:
  - name: myapp
    image: ikubernetes/myapp:v1
  affinity:
    nodeAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
        nodeSelectorTerms:
        - matchExpressions:
          - key: zone
            operator: In
            values:
            - foo
            - bar

[root@k8s-master ~]# kubectl apply -f pod-nodeaffinity-demo.yaml

[root@k8s-master ~]# kubectl describe pod pod-node-affinity-demo
# 运行结果:
Warning  FailedScheduling  2s (x8 over 20s)  default-scheduler  0/3 nodes are available: 3 node(s) didn't match node selector.

# 给其中一个node打上foo的标签
[root@k8s-master ~]# kubectl label node k8s-node01 zone=foo

# 正常启动
[root@k8s-master ~]# kubectl get pods

2.软亲和

[root@k8s-master ~]# vim pod-nodeaffinity-demo-2.yaml 
apiVersion: v1
kind: Pod
metadata:
  name: pod-node-affinity-demo-2
  labels:
    app: myapp
    tier: frontend
spec:
  containers:
  - name: myapp
    image: ikubernetes/myapp:v1
  affinity:
    nodeAffinity:
      preferredDuringSchedulingIgnoredDuringExecution:
      - preference:
          matchExpressions:
          - key: zone
            operator: In
            values:
            - foo
            - bar
        weight: 60
      - preference:
          matchExpressions:
          - key: zone1
            operator: In
            values:
            - foo1
            - bar1
        weight: 10 

[root@k8s-master ~]# kubectl apply -f pod-nodeaffinity-demo-2.yaml

3.同时存在时(硬,软亲和)

apiVersion: v1
kind: Pod
metadata:
  name: with-node-affinity
spec:
  affinity:
    nodeAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
        nodeSelectorTerms:
        - matchExpressions:
          - key: zone
            operator: In
            values:
            - dev
      preferredDuringSchedulingIgnoredDuringExecution:
      - weight: 1
        preference:
          matchExpressions:
          - key: disktype
            operator: In
            values:
            - ssd
  containers:
  - name: with-node-affinity
    image: nginx

结果:同时存在的话先判断上下顺序,从上到下选择范围,列如硬亲和在上,软亲和在下,就会先选必须匹配到一个标签的多个node上,然后软亲和继续从这些节点去选择,反之亦然。


亲和性:首先是先有一个pod,然后根据上一个pod(辨识标签)在哪里节点启动,就会跟随到这个节点上去启动。
反亲和:查看前面的那个pod的启动节点,必须和它启动到不是一个节点上

1.亲和性

[root@k8s-master ~]# vim pod-required-affinity-demo.yaml 
apiVersion: v1
kind: Pod
metadata:
  name: pod-first
  labels:
    app: myapp
    tier: frontend
spec:
  containers:
  - name: myapp
    image: ikubernetes/myapp:v1
---
apiVersion: v1
kind: Pod
metadata:
  name: pod-second
  labels:
    app: db
    tier: db
spec:
  containers:
  - name: busybox
    image: busybox
    imagePullPolicy: IfNotPresent
    command: ["sh","-c","sleep 3600"]
  affinity:
    podAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
      - labelSelector:
          matchExpressions:
          - {key: app, operator: In, values: ["myapp"]}
        topologyKey: kubernetes.io/hostname


[root@k8s-master ~]# kubectl apply -f pod-required-affinity-demo.yaml 

[root@k8s-master ~]# kubectl get pods -o wide
# 运行结果,两个 pod 在同一 node 节点上
NAME         READY   STATUS    RESTARTS   AGE   IP           NODE
pod-first    1/1     Running   0          11s   10.244.1.6   k8s-node01
pod-second   1/1     Running   0          11s   10.244.1.5   k8s-node01

[root@k8s-master ~]# kubectl delete -f pod-required-affinity-demo.yaml

2.反亲和性

[root@k8s-master ~]# vim pod-required-anti-affinity-demo.yaml 
# 内容为
apiVersion: v1
kind: Pod
metadata:
  name: pod-first
  labels:
    app: myapp
    tier: frontend
spec:
  containers:
  - name: myapp
    image: ikubernetes/myapp:v1
---
apiVersion: v1
kind: Pod
metadata:
  name: pod-second
  labels:
    app: backend
    tier: db
spec:
  containers:
  - name: busybox
    image: busybox:latest
    imagePullPolicy: IfNotPresent
    command: ["sh","-c","sleep 3600"]
  affinity:
    podAntiAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
      - labelSelector:
          matchExpressions:
          - {key: app, operator: In, values: ["myapp"]}
        topologyKey: kubernetes.io/hostname

[root@k8s-master ~]# kubectl apply -f pod-required-anti-affinity-demo.yaml 

[root@k8s-master ~]# kubectl get pods -o wide
# 运行结果,两个 pod 不在同一个 node
NAME         READY   STATUS    RESTARTS   AGE   IP           NODE
pod-first    1/1     Running   0          5s    10.244.2.4   k8s-node02
pod-second   1/1     Running   0          5s    10.244.1.7   k8s-node01

[root@k8s-master ~]# kubectl delete -f pod-required-anti-affinity-demo.yaml

3.同时存在时(亲和性,反亲和性)

这里就不举例的,直接说一下结果
首先肯定是两个条件的匹配条件不能一样
这时候就会满足两个条件去选择条件,比如,当亲和性在上,反亲和在下,pod会先选择匹配到条件的一些节点上去选择,然后在从中匹配到反亲和的条件,如果有那就必须踢出它,选择其他符合条件的节点。

三.污点和容忍度

与之前两个调度方式不同,污点是首先给节点绑定污点,作用是保护节点,不再让这个节点会scheduler(资源调度)选为pod启动环境。
我们集群中master就是设置污点,所以你启动任何pod都不会在master上工作,保证master的工作效率。

相关参数

介绍几个用到的参数

  • operator 可以定义为
    • Equal:表示key是否等于value,默认
    • Exists:表示key是否存在,此时无需定义value
  • tain 的 effect 定义对 Pod 排斥效果
    • NoSchedule:仅影响调度过程,对现存的Pod对象不产生影响;
    • NoExecute:既影响调度过程,也影响现有的Pod对象;不容忍的Pod对象将被驱逐
    • PreferNoSchedule: 表示尽量不调度

查看节点的污点

kubectl describe node k8s-node01 | grep Taints

设置污点

kubectl taint node k8s-node01 node-type=production:NoSchedule

创建容器测试

[root@k8s-master ~]# vim deploy-demo.yaml 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: myapp-deploy
  namespace: default
spec:
  replicas: 2
  selector:
    matchLabels:
      app: myapp
      release: canary
  template:
    metadata:
      labels:
        app: myapp
        release: canary
    spec:
      containers:
      - name: myapp
        image: ikubernetes/myapp:v1
        ports:
        - name: http
          containerPort: 80

[root@k8s-master ~]# kubectl apply -f deploy-demo.yaml 

[root@k8s-master ~]# kubectl get pods -o wide
# 运行结果:
NAME                            READY   STATUS    RESTARTS   AGE   IP           NODE
myapp-deploy-69b47bc96d-cwt79   1/1     Running   0          5s    10.244.2.6   k8s-node02
myapp-deploy-69b47bc96d-qqrwq   1/1     Running   0          5s    10.244.2.5   k8s-node02

所以只能启动到没有污点的node2节点上

设置一个能容忍node1污点的pod测试

[root@k8s-master ~]# vim deploy-demo.yaml 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: myapp-deploy
  namespace: defaultm
spec:
  replicas: 2
  selector:
    matchLabels:
      app: myapp
      release: canary
  template:
    metadata:
      labels:
        app: myapp
        release: canary
    spec:
      containers:
      - name: myapp
        image: ikubernetes/myapp:v2
        ports:
        - name: http
          containerPort: 80
      tolerations:
      - key: "node-type"
        operator: "Equal"
        value: "production"
        effect: "NoSchedule"


[root@k8s-master ~]# kubectl apply -f deploy-demo.yaml

测试

[root@k8s-master ~]# kubectl get pods -o wide
NAME                            READY   STATUS    RESTARTS   AGE   IP            NODE
myapp-deploy-65cc47f858-tmpnz   1/1     Running   0          10s   10.244.1.10   k8s-node01
myapp-deploy-65cc47f858-xnklh   1/1     Running   0          13s   10.244.1.9    k8s-node01

其他参数的作用

  • 定义Toleration,是否存在 node-type 这个key 且 effect 值为 NoSchedule
[root@k8s-master ~]# vim deploy-demo.yaml 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: myapp-deploy
  namespace: default
spec:
  replicas: 2
  selector:
    matchLabels:
      app: myapp
      release: canary
  template:
    metadata:
      labels:
        app: myapp
        release: canary
    spec:
      containers:
      - name: myapp
        image: ikubernetes/myapp:v2
        ports:
        - name: http
          containerPort: 80
      tolerations:
      - key: "node-type"
        operator: "Exists"
        value: ""
        effect: "NoSchedule"

[root@k8s-master ~]# kubectl apply -f deploy-demo.yaml

[root@k8s-master ~]# kubectl get pods -o wide
NAME                            READY   STATUS    RESTARTS   AGE   IP            NODE
myapp-deploy-559f559bcc-6jfqq   1/1     Running   0          10s   10.244.1.11   k8s-node01
myapp-deploy-559f559bcc-rlwp2   1/1     Running   0          9s    10.244.1.12   k8s-node01
  • 定义Toleration,是否存在 node-type 这个key 且 effect 值为空,则包含所有的值
[root@k8s-master ~]# vim deploy-demo.yaml 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: myapp-deploy
  namespace: default
spec:
  replicas: 2
  selector:
    matchLabels:
      app: myapp
      release: canary
  template:
    metadata:
      labels:
        app: myapp
        release: canary
    spec:
      containers:
      - name: myapp
        image: ikubernetes/myapp:v2
        ports:
        - name: http
          containerPort: 80
      tolerations:
      - key: "node-type"
        operator: "Exists"
        value: ""
        effect: ""

[root@k8s-master ~]# kubectl apply -f deploy-demo.yaml

# 两个 pod 均衡调度到两个节点
kubectl get pods -o wide
NAME                            READY   STATUS    RESTARTS   AGE   IP            NODE
myapp-deploy-5d9c6985f5-hn4k2   1/1     Running   0          2m    10.244.1.13   k8s-node01
myapp-deploy-5d9c6985f5-lkf9q   1/1     Running   0          2m    10.244.2.7    k8s-node02

------没有足够的努力,就不要去谈未来和远方,因为谁不会吹呢------

转载至https://blog.csdn.net/ht9999i/article/details/108037568

Logo

K8S/Kubernetes社区为您提供最前沿的新闻资讯和知识内容

更多推荐