CCE节点故障检测

插件介绍

CCE节点故障检测插件（node-problem-detector，简称NPD）是一款监控集群节点异常事件的插件，以及对接第三方监控平台功能的组件。它是一个在每个节点上运行的守护程序，可从不同的守护进程中搜集节点问题并将其报告给apiserver。node-problem-detector可以作为DaemonSet运行， 也可以独立运行。

字段说明

请求示例

{
  "kind": "Addon",
  "apiVersion": "v3",
  "metadata": {
    "annotations": {
      "addon.install/type": "install"
    }
  },
  "spec": {
    "clusterID": "b78fb690-b82c-11ee-83cf-0255ac100b0f",
    "version": "1.18.48",
    "addonTemplateName": "npd",
    "values": {
      "basic": {
        "image_version": "1.18.48",
        "swr_addr": "***",
        "swr_user": "***",
        "rbac_enabled": true,
        "cluster_version": "v1.23"
      },
      "flavor": {
        "description": "custom resources",
        "name": "custom-resources",
        "replicas": 2,
        "resources": [
          {
            "limitsCpu": "100m",
            "limitsMem": "300Mi",
            "name": "node-problem-controller",
            "requestsCpu": "30m",
            "requestsMem": "100Mi"
          },
          {
            "limitsCpu": "100m",
            "limitsMem": "300Mi",
            "name": "node-problem-detector",
            "requestsCpu": "30m",
            "requestsMem": "100Mi"
          }
        ],
        "category": [
          "CCE",
          "Turbo"
        ]
      },
      "custom": {
        "annotations": {},
        "common": {},
        "feature_gates": "",
        "multiAZBalance": false,
        "multiAZEnabled": false,
        "node_match_expressions": [],
        "npc": {
          "maxTaintedNode": "10%"
        },
        "tolerations": [
          {
            "key": "node.kubernetes.io/not-ready",
            "operator": "Exists",
            "effect": "NoExecute",
            "tolerationSeconds": 60
          },
          {
            "key": "node.kubernetes.io/unreachable",
            "operator": "Exists",
            "effect": "NoExecute",
            "tolerationSeconds": 60
          }
        ]
      }
    }
  }
}