kubesphere安装完成后，首页概览信息展示不出来。

r1r3r5246

和监控有关的信息都展示不出来

{
 "results": [
  {
   "metric_name": "cluster_memory_usage_wo_cache",
   "data": {},
   "error": "Post \"http://prometheus-operated.kubesphere-monitoring-system.svc:9090/api/v1/query\": dial tcp 10.244.52.189:9090: i/o timeout"
  },
  {
   "metric_name": "cluster_memory_total",
   "data": {},
   "error": "Post \"http://prometheus-operated.kubesphere-monitoring-system.svc:9090/api/v1/query\": dial tcp 10.244.52.189:9090: i/o timeout"
  },
  {
   "metric_name": "cluster_pod_quota",
   "data": {},
   "error": "Post \"http://prometheus-operated.kubesphere-monitoring-system.svc:9090/api/v1/query\": dial tcp 10.244.52.189:9090: i/o timeout"
  },
  {
   "metric_name": "cluster_pod_running_count",
   "data": {},
   "error": "Post \"http://prometheus-operated.kubesphere-monitoring-system.svc:9090/api/v1/query\": dial tcp 10.244.52.189:9090: i/o timeout"
  },
  {
   "metric_name": "cluster_cpu_total",
   "data": {},
   "error": "Post \"http://prometheus-operated.kubesphere-monitoring-system.svc:9090/api/v1/query\": dial tcp 10.244.52.189:9090: i/o timeout"
  },
  {
   "metric_name": "cluster_disk_size_usage",
   "data": {},
   "error": "Post \"http://prometheus-operated.kubesphere-monitoring-system.svc:9090/api/v1/query\": dial tcp 10.244.52.189:9090: i/o timeout"
  },
  {
   "metric_name": "cluster_disk_size_capacity",
   "data": {},
   "error": "Post \"http://prometheus-operated.kubesphere-monitoring-system.svc:9090/api/v1/query\": dial tcp 10.244.52.189:9090: i/o timeout"
  },
  {
   "metric_name": "cluster_cpu_usage",
   "data": {},
   "error": "Post \"http://prometheus-operated.kubesphere-monitoring-system.svc:9090/api/v1/query\": dial tcp 10.244.52.189:9090: i/o timeout"
  }
 ]

RolandMa1986

r1r3r5246 kubectl get pod -A 看一下是不是依赖的容器都启动了

r1r3r5246

RolandMa1986

容器都是正常的，是不是DNS有问题呢？请教一下怎么排查。

后来安装devops也报错了

TASK [common : debug] **********************************************************
ok: [localhost] => {
    "msg": [
        "1. check the storage configuration and storage server",
        "2. make sure the DNS address in /etc/resolv.conf is available",
        "3. execute 'kubectl logs -n kubesphere-system -l job-name=minio-make-bucket-job' to watch logs",
        "4. execute 'helm -n kubesphere-system uninstall ks-minio && kubectl -n kubesphere-system delete job minio-make-bucket-job'",
        "5. Restart the installer pod in kubesphere-system namespace"
    ]
}

TASK [common : fail] ***********************************************************
fatal: [localhost]: FAILED! => {"changed": false, "msg": "It is suggested to refer to the above methods for troubleshooting problems ."}

PLAY RECAP *********************************************************************
localhost                  : ok=38   changed=22   unreachable=0    failed=1    skipped=71   rescued=0    ignored=0   

^C
[root@harbor ~]# kubectl logs -n kubesphere-system -l job-name=minio-make-bucket-job
mc: <ERROR> Unable to initialize new config from the provided credentials. Get http://minio:9000/probe-bucket-sign-mtu2uycilv3t/?location=: dial tcp: i/o timeout.
"Failed attempts: 16"
mc: <ERROR> Unable to initialize new config from the provided credentials. Get http://minio:9000/probe-bucket-sign-o09juxyyzjjd/?location=: dial tcp: i/o timeout.
"Failed attempts: 17"
mc: <ERROR> Unable to initialize new config from the provided credentials. Get http://minio:9000/probe-bucket-sign-xjx6razmvc64/?location=: dial tcp: i/o timeout.
"Failed attempts: 18"
mc: <ERROR> Unable to initialize new config from the provided credentials. Get http://minio:9000/probe-bucket-sign-gziiumnoyop6/?location=: dial tcp: i/o timeout.
"Failed attempts: 19"
mc: <ERROR> Unable to initialize new config from the provided credentials. Get http://minio:9000/probe-bucket-sign-pmdnbaqvz2co/?location=: dial tcp: i/o timeout.
"Failed attempts: 20"
[root@harbor ~]# cat /etc/resolv.conf
# Generated by NetworkManager
nameserver 192.168.31.1

nameserver 208.67.222.222
nameserver 208.67.220.220

nameserver 8.8.8.8
nameserver 8.8.4.4

r1r3r5246

在api server的pod里执行以下命令超时

/ # nc -zv prometheus-operated.kubesphere-monitoring-system.svc 9090

nc: prometheus-operated.kubesphere-monitoring-system.svc (10.244.52.191:9090): Operation timed out

r1r3r5246

已解决，集群dns插件有问题。

woailuozem

r1r3r5246

woailuozem

同样的问题，怎么解决了，新手还不知道怎么处理集群dns插件有问题
劳烦指点

r1r3r5246

woailuozem 重新安装calico或者flannel试试

krister

楼主，我有相同的问题，不太会重装，能讲下步骤吗？