Docker UCP Calico-node pod 不健康

Question

我们正在使用 docker-ee

Docker Enterprise 2.1
18.09.0-beta3

我在一个节点上安装了 UCP 并向其添加了工作节点。 UCP 将节点错误显示为:
"Calico-node pod is unhealthy: unexpected calico-node pod condition Ready".当我在节点上执行 kubectl 时，它显示如下

kubectl get pods --all-namespaces

kube-system   calico-kube-controllers-549679   1/1  Running  2  5h
kube-system   calico-node-6fk4j      1/2       CrashLoopBackOff   85         5h
kube-system   calico-node-6xldl     1/2       Running            78         5h

Pod 描述节目

kubectl describe pod calico-node-6fk4j -n kube-system:

  Warning  Unhealthy  17m (x210 over 2h)  kubelet, tclasapid004.tiffco.net  Liveness probe failed: Get http://localhost:9099/liveness: dial tcp 127.0.0.1:9099: connect: connection refused
  Warning  BackOff    7m (x410 over 2h)   kubelet, tclasapid004.tiffco.net  Back-off restarting failed container
  Warning  Unhealthy  2m (x231 over 2h)   kubelet, tclasapid004.tiffco.net  Readiness probe failed: calico/node is not ready: felix is not ready: Get http://localhost:9099/readiness: net/http: request canceled while waiting for connection (Client.Timeout exceeded while awaiting headers)

出现此错误(Calico-node)，我们无法运行一些操作。请在这里帮忙。

感谢你的帮助

Answer 1

您在该主机上有多个接口(interface)吗？您需要设置自动检测设置。

相关问题:

https://github.com/projectcalico/calico/issues/2042

you need to set auto-detect to use another method suitable for your network. E.g. adding following to calico yaml:

 - name: IP_AUTODETECTION_METHOD
               value: "interface=eth.*"

请仔细阅读该问题，有多种解决方案的多种原因:

I was finally able to resolve the issue. Thanks to @tmjd for the hint. I had two interfaces on each of my Ubuntu VMs, enp0s3 and enp0s8. the enp0s8 interface had the same IP on all the three VMs hence the calico nodes on the slave were complaining about the IP conflict. To resolve this problem I edited my /etc/network/interfaces file and assigned static IPs to enpos8 interface. this resolved the problem.