node-exporter-28jxm 一直重启失败

node-exporter-28jxm一直失败

[root@master01 ~]# kubectl get pod -A
NAMESPACE              NAME                                         READY   STATUS             RESTARTS   AGE
monitoring             node-exporter-28jxm                          1/2     CrashLoopBackOff   1          5s
[root@master01 ~]# kubectl describe pod -n monitoring  node-exporter-28
Events:
  Type     Reason     Age                 From               Message
  ----     ------     ----                ----               -------
  Normal   Scheduled  2m1s                default-scheduler  Successfully assigned monitoring/node-exporter-28jxm to node01
  Normal   Pulled     2m                  kubelet            Container image "quay.io/brancz/kube-rbac-proxy:v0.8.0" already present on machine
  Normal   Created    2m                  kubelet            Created container kube-rbac-proxy
  Normal   Started    119s                kubelet            Started container kube-rbac-proxy
  Normal   Started    77s (x4 over 2m)    kubelet            Started container node-exporter
  Warning  BackOff    41s (x8 over 117s)  kubelet            Back-off restarting failed container
  Normal   Pulled     27s (x5 over 2m1s)  kubelet            Container image "quay.io/prometheus/node-exporter:v1.0.1" already present on machine
  Normal   Created    26s (x5 over 2m1s)  kubelet            Created container node-exporter
[root@master01 ~]# kubectl logs -f -n monitoring node-exporter-28jxm -c node-exporter   ### 提示端口被占用了
level=info ts=2021-07-04T06:57:22.622Z caller=node_exporter.go:191 msg="Listening on" address=127.0.0.1:9100
level=info ts=2021-07-04T06:57:22.622Z caller=tls_config.go:170 msg="TLS is disabled and it cannot be enabled on the fly." http2=false
level=error ts=2021-07-04T06:57:22.622Z caller=node_exporter.go:194 err="listen tcp 127.0.0.1:9100: bind: address already in use"

[root@master01 ~]# kubectl get pod -n monitoring  -owide ###查看该pod的所在节点
NAME                                   READY   STATUS             RESTARTS   AGE     IP              NODE       NOMINATED NODE   READINESS GATES
node-exporter-28jxm                    1/2     CrashLoopBackOff   5          4m11s   192.168.0.121   node01     <none>           <none>

2.node01节点排查端口

[root@node01 bin]# ps -ef|grep 9100
gitlab-+  28810   9783  0 14:54 ?        00:00:02 /opt/gitlab/embedded/bin/node_exporter --web.listen-address=localhost:9100 --collector.mountstats --collector.runit --collector.runit.servicedir=/opt/gitlab/sv --collector.textfile.directory=/var/opt/gitlab/node-exporter/textfile_collector
65532     29024  28975  0 14:54 ?        00:00:00 /usr/local/bin/kube-rbac-proxy --logtostderr --secure-listen-address=[192.168.0.121]:9100 --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305 --upstream=http://127.0.0.1:9100/
root      32092   9266  0 14:59 pts/0    00:00:00 grep --color=auto 9100
-rwxr-xr-x 1 root root 3692 May 29  2020 gitlab-backup
-rwxr-xr-x 1 root root 1418 May 29  2020 gitlab-ctl
-rwxr-xr-x 1 root root  250 May 29  2020 gitlab-healthcheck
-rwxr-xr-x 1 root root  702 May 29  2020 gitlab-psql
-rwxr-xr-x 1 root root 1301 May 29  2020 gitlab-rails
-rwxr-xr-x 1 root root 1300 May 29  2020 gitlab-rake
-rwxr-xr-x 1 root root  711 May 29  2020 gitlab-redis-cli
[root@node01 bin]#  /opt/gitlab/bin && gitlab-ctl stop
[root@node01 bin]# systemctl disable gitlab-runsvdir.service
#### 问题是我之前在node01装了gitlab占用了端口，关闭服务取消开机自启就行