Kubernetes 调度

kubectl get pods -n kube-system | grep kube-scheduler

# 查看 Label
kubectl get nodes --show-labels
# 添加 Label
kubectl label nodes < your-node-name > disktype=ssd

apiVersion: v1
kind: Pod
metadata:
  name: nginx
  labels:
    env: test
spec:
  containers:
    - name: nginx
      image: nginx
      imagePullPolicy: IfNotPresent
  # 节点名字选择
  nodeName: kube-01
  # 节点 Label 选择
  nodeSelector:
    disktype: ssd

  # 任意 NS
  namespaceSelector: {}
  # 当前 Pod NS
  namespaceSelector: null
  # 匹配 Label
  namespaceSelector:
    key: val

  affinity:
    # 节点亲和 - 同时满足 nodeSelector
    nodeAffinity:
      # 强制要求
      requiredDuringSchedulingIgnoredDuringExecution:
        # 指定个满足一个即可
        nodeSelectorTerms:
          - matchExpressions: # 要求所有条件满足
              - key: kubernetes.io/e2e-az-name
                operator: In # In, NotIn, Exists, DoesNotExist, Gt, Lt
                values:
                  - e2e-az1
                  - e2e-az2
      # 软要求 - 倾向满足
      preferredDuringSchedulingIgnoredDuringExecution:
        - weight: 1 # 1-100, 多个条件累加, 选择累加权重最高的节点
          preference:
            matchExpressions:
              - key: another-node-label-key
                operator: In
                values:
                  - another-node-label-value
    # Pod 亲和
    podAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
      - labelSelector:
          matchExpressions:
          - key: security
            operator: In
            values:
            - S1
        topologyKey: topology.kubernetes.io/zone
    # Pod 反亲和
    podAntiAffinity:
      preferredDuringSchedulingIgnoredDuringExecution:
      - weight: 100
        podAffinityTerm:
          labelSelector:
            matchExpressions:
            - key: security
              operator: In
              values:
              - S2
          topologyKey: topology.kubernetes.io/zone

apiVersion: kubescheduler.config.k8s.io/v1beta1
kind: KubeSchedulerConfiguration

profiles:
  - schedulerName: default-scheduler
  - schedulerName: foo-scheduler
    pluginConfig:
      - name: NodeAffinity
        args:
          addedAffinity:
            requiredDuringSchedulingIgnoredDuringExecution:
              nodeSelectorTerms:
                - matchExpressions:
                    - key: scheduler-profile
                      operator: In
                      values:
                        - foo

kind: RuntimeClass
apiVersion: node.k8s.io/v1
metadata:
  name: kata-fc
handler: kata-fc
overhead:
  podFixed:
    memory: '120Mi'
    cpu: '250m'

# 添加污点 - 如果不能容忍 key1=value1 则不调度
kubectl taint nodes node1 key1=value1:NoSchedule
# 移除污点
kubectl taint nodes node1 key1=value1:NoSchedule-

# 可在 master 上打上要求指定了 master 才运行
kubectl taint node MASTER node-role.kubernetes.io/master=:NoSchedule-

apiVersion: v1
kind: Pod
metadata:
  name: nginx
  labels:
    env: test
spec:
  containers:
    - name: nginx
      image: nginx
      imagePullPolicy: IfNotPresent
  tolerations: # 容忍配置
    - key: 'key1'
      operator: 'Equal' # Exists
      value: 'value1'
      effect: 'NoSchedule'

apiVersion: scheduling.k8s.io/v1
kind: PriorityClass
metadata:
  name: high-priority
value: 1000000
globalDefault: false
description: 'This priority class should be used for XYZ service pods only.'
# 抢占策略 - 默认 PreemptLowerPriority
# Never 不被抢占 - 例如 Job 不想被中断场景
# 1.19+ beta
preemptionPolicy: Never

apiVersion: v1
kind: Pod
metadata:
  name: nginx
  labels:
    env: test
spec:
  containers:
    - name: nginx
      image: nginx
      imagePullPolicy: IfNotPresent
  # 针对 Pod
  priorityClassName: system-node-critical