概述:
- 先来了解 topology key 字段
pod亲和性调度需要各个相关的pod对象运行于"同一位置"， 而反亲和性调度则要求他们不能运行于"同一位置"，
这里指定“同一位置” 是通过 topologyKey 来定义的，topologyKey 对应的值是 node 上的一个标签名称，比如各别节点zone=A标签，各别节点有zone=B标签，pod affinity topologyKey定义为zone，那么调度pod的时候就会围绕着A拓扑，B拓扑来调度，而相同拓扑下的node就为“同一位置”。 - 顾名思义，topology 就是 拓扑的意思
这里指的是一个 拓扑域，是指一个范围的概念，比如一个 Node、一个机柜、一个机房或者是一个地区（如杭州、上海）等，实际上对应的还是 Node 上的标签。这里的 topologyKey 对应的是 Node 上的标签的 Key（没有Value），可以看出，其实 topologyKey 就是用于筛选 Node 的。通过这种方式，我们就可以将各个 Pod 进行跨集群、跨机房、跨地区的调度了。
查看 podAffinity的详细说明
[root@k8s-master Scheduler]# kubectl explain pods.spec.affinity
KIND: Pod
VERSION: v1
RESOURCE: affinity 示例1: podAffinity Pod硬亲和
requiredDuringSchedulingIgnoredDuringExecution
[root@k8s-master Scheduler]# cat pod-affinity-required-demo.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: redis
spec:
replicas: 1 #redis为有状态应用 为了测试只运行1个副本
selector:
matchLabels:
app: redis
ctlr: redis
template:
metadata:
labels:
app: redis
ctlr: redis
spec:
containers:
- name: redis
image: redis:6.0-alpine
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: pod-affinity-required
spec:
replicas: 5
selector:
matchLabels:
app: demoapp
ctlr: pod-affinity-required
template:
metadata:
labels:
app: demoapp
ctlr: pod-affinity-required
spec:
containers:
- name: demoapp
image: ikubernetes/demoapp:v1.0
affinity:
podAffinity: #Pod亲和
requiredDuringSchedulingIgnoredDuringExecution: #硬亲和
- labelSelector:
matchExpressions:
- {key: app, operator: In, values: ["redis"]} #复杂表示达匹配标签 app=reids、ctlr=redis
- {key: ctlr, operator: In, values: ["redis"]} #两个表达式为与关系 同时满足
topologyKey: rack #节点标签 位置标签 rack可以理解为同一个机架上 与labelSelector同样是与关系同时满足
[root@k8s-master Scheduler]# kubectl apply -f pod-affinity-required-demo.yaml
deployment.apps/redis unchanged
deployment.apps/pod-affinity-required unchanged
[root@k8s-master Scheduler]# kubectl get pod -o wide #节点还没有打上标签pod-affinity挂机
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
pod-affinity-required-5dd44f5d45-6vvhd 0/1 Pending 0 6m7s
pod-affinity-required-5dd44f5d45-c4hzl 0/1 Pending 0 6m7s
pod-affinity-required-5dd44f5d45-qm6zb 0/1 Pending 0 6m7s
pod-affinity-required-5dd44f5d45-t4mm5 0/1 Pending 0 6m7s
pod-affinity-required-5dd44f5d45-vs7dg 0/1 Pending 0 6m7s
redis-55f46d9795-r7pkz 1/1 Running 0 10m 192.168.51.23 k8s-node3
- 模拟同一机架不同节点
[root@k8s-master Scheduler]# kubectl label node k8s-node1 rack=foo #为节点1把rack标签
node/k8s-node1 labeled
[root@k8s-master Scheduler]# kubectl label node k8s-node2 rack=bar #为节点2把rack标签
node/k8s-node2 labeled
[root@k8s-master Scheduler]# kubectl label node k8s-node3 rack=baz #为节点3把rack标签
node/k8s-node3 labeled- 硬亲和与redis运行在相同节点 都运行在node3上
[root@k8s-master Scheduler]# kubectl get pod -o wide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
pod-affinity-required-5dd44f5d45-6vvhd 1/1 Running 0 21m 192.168.51.28 k8s-node3
pod-affinity-required-5dd44f5d45-c4hzl 1/1 Running 0 21m 192.168.51.26 k8s-node3
pod-affinity-required-5dd44f5d45-qm6zb 1/1 Running 0 21m 192.168.51.24 k8s-node3
pod-affinity-required-5dd44f5d45-t4mm5 1/1 Running 0 21m 192.168.51.25 k8s-node3
pod-affinity-required-5dd44f5d45-vs7dg 1/1 Running 0 21m 192.168.51.27 k8s-node3
redis-55f46d9795-r7pkz 1/1 Running 0 25m 192.168.51.23 k8s-node3 示例2: podAffinity Pod软亲和
preferredDuringSchedulingIgnoredDuringExecution
[root@k8s-master Scheduler]# cat pod-affinity-preferred-demo.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: redis-preferred
spec:
replicas: 1
selector:
matchLabels:
app: redis
ctlr: redis-preferred
template:
metadata:
labels:
app: redis
ctlr: redis-preferred
spec:
containers:
- name: redis
image: redis:6.0-alpine
resources:
requests:
cpu: 200m
memory: 512Mi
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: pod-affinity-preferred
spec:
replicas: 4
selector:
matchLabels:
app: demoapp
ctlr: pod-affinity-preferred
template:
metadata:
labels:
app: demoapp
ctlr: pod-affinity-preferred
spec:
containers:
- name: demoapp
image: ikubernetes/demoapp:v1.0
resources:
requests:
cpu: 500m
memory: 100Mi
affinity:
podAffinity:
preferredDuringSchedulingIgnoredDuringExecution: #软亲和以不同权重计算分值重出最终的亲和节点
- weight: 100
podAffinityTerm:
labelSelector:
matchExpressions:
- {key: app, operator: In, values: ["redis"]}
- {key: ctlr, operator: In, values: ["redis-prefered"]} #Pod包含标签为app=redis、ctlr=redis-prefered同时满足
topologyKey: kubernetes.io/hostname #节点位置标签 以不同节点为位置 表示在相同节点权重为100 所有同一节点权重最高
- weight: 50
podAffinityTerm:
labelSelector:
matchExpressions:
- {key: app, operator: In, values: ["redis"]}
- {key: ctlr, operator: In, values: ["redis-prefered"]}
topologyKey: rack #节点标签 位置标签 以机架为位置 表示在相同机架权重为50
[root@k8s-master Scheduler]# kubectl apply -f pod-affinity-preferred-demo.yaml
[root@k8s-master Scheduler]# kubectl get pod -o wide #运行在不同的节点
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
pod-affinity-preferred-57d457968f-4lxvq 1/1 Running 0 5m6s 192.168.113.21 k8s-node1
pod-affinity-preferred-57d457968f-krb2f 1/1 Running 0 5m6s 192.168.113.20 k8s-node1
pod-affinity-preferred-57d457968f-mzckm 1/1 Running 0 5m6s 192.168.12.24 k8s-node2
pod-affinity-preferred-57d457968f-v8n8g 1/1 Running 0 5m6s 192.168.51.37 k8s-node3
redis-preferred-5d775df679-wtpgs 1/1 Running 0 5m6s 192.168.51.38 k8s-node3
示例3: podAntiAffinity 硬反亲和
requiredDuringSchedulingIgnoredDuringExecution
- Deployment 4个副本必须运行在不同的节点上 因为node节点只有3个所有会有个挂起 内部相斥
[root@k8s-master Scheduler]# cat pod-antiaffinity-required-demo.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: pod-antiaffinity-required
spec:
replicas: 4 #运行4个副本
selector:
matchLabels:
app: demoapp
ctlr: pod-antiaffinity-required
template:
metadata:
labels:
app: demoapp
ctlr: pod-antiaffinity-required
spec:
containers:
- name: demoapp
image: ikubernetes/demoapp:v1.0
affinity:
podAntiAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
- labelSelector:
matchExpressions:
- {key: app, operator: In, values: ["demoapp"]}
- key: ctlr
operator: In
values: ["pod-antiaffinity-required"] #Pod包含标签app=demoapp、ctlr=pod-antiaffinity-required 同时满足
topologyKey: kubernetes.io/hostname #以节点为位置 表示每个节点只能运行1个Pod
[root@k8s-master Scheduler]# kubectl apply -f pod-antiaffinity-required-demo.yaml
[root@k8s-master Scheduler]# kubectl get pod -o wide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
pod-antiaffinity-required-697f7d764d-hgkxj 1/1 Running 0 5m5s 192.168.113.34 k8s-node1
pod-antiaffinity-required-697f7d764d-n4zt9 1/1 Running 0 5m5s 192.168.12.34 k8s-node2
pod-antiaffinity-required-697f7d764d-psqfb 1/1 Running 0 5m5s 192.168.51.53 k8s-node3
pod-antiaffinity-required-697f7d764d-q6t7m 0/1 Pending 0 5m5s #挂起 因为只有3个node节点