Cloudstack API end point getting failed while deploying nginx as loadbalancer on kubernetes

[vishnuvs369]

I have an issue with cloudstack.. i'm deploying nginx service as loadbalancer on kubernetes getting an error given below...

Events:
  Type     Reason                  Age                  From                Message
  ----     ------                  ----                 ----                -------
  Warning  SyncLoadBalancerFailed  4s (x1027 over 17h)  service-controller  Error syncing load balancer: failed to check if load balancer exists before cleanup: error retrieving load balancer rules: Get http://192.168.10.120:8080/client/api?apiKey=5yQj6eY6hAoNFrHFFNK1RFvMsioFwpcruIkBk09-GhUDcA6CO_jO1-K_Gyyoqa0l7DBxmseK70GsrGfe2opabA&command=listLoadBalancerRules&keyword=ad715cbd81ac64c079be9a71f46a7c0c&listall=true&response=json&signature=WIJuc9uYnkd5XGXmtiUcRiGWzuw%3D: net/http: request canceled (Client.Timeout exceeded while awaiting headers)

i configured Endpoint url (endpoint.url) in Global settings using LAN IP...can anyone help me on this

[boring-cyborg]

Thanks for opening your first issue here! Be sure to follow the issue template!

[weizhouapache]

@vishnuvs369
the endpoint URL should be reachable from the k8s pods.

If you can fix the URL, you can re-deploy the k8s secret by script /opt/bin/deploy-cloudstack-secret in the control node.
if not, you have to configure the load balancing rules manually.

[vishnuvs369]

@weizhouapache
Thanks for the update, We can either add a public ip interface to the management server and configure that IP on the endpoint url or do a NAT route on 192.168.10.120 IP and configure public ip on the endpoint url. Our concern is that we need our management ui to be accessed only internally. So configuring public IP on management network we will have to take care of additional security... What is your advice for best practice...

[weizhouapache]

@weizhouapache
Thanks for the update, We can either add a public ip interface to the management server and configure that IP on the endpoint url or do a NAT route on 192.168.10.120 IP and configure public ip on the endpoint url. Our concern is that we need our management ui to be accessed only internally. So configuring public IP on management network we will have to take care of additional security... What is your advice for best practice...

However, user vms should be unable to access the management network, otherwise it is a more severe security issue.

You can add some firewall rules for the public ip of the management IP.

[PaX101]

We are experiensing the same issue, it looks to be the same issue as 4.18 where the pages would take a very long time to load where they were pulling all data instead of what was needed. The command causing this slowness on our one:

https://my.url.com/client/api?apiKey=myapikeyhere&command=listVirtualMachines&listall=true&response=json&signature=mysignature

If i run this command in a browser the API takes around 5-10 minutes to load it, however is i try to run normal commands on the API such as listVirtualMachinesMetrics it is instant.

[DaanHoogland]

We are experiensing the same issue, it looks to be the same issue as 4.18 where the pages would take a very long time to load where they were pulling all data instead of what was needed. The command causing this slowness on our one:

https://my.url.com/client/api?apiKey=myapikeyhere&command=listVirtualMachines&listall=true&response=json&signature=mysignature

If i run this command in a browser the API takes around 5-10 minutes to load it, however is i try to run normal commands on the API such as listVirtualMachinesMetrics it is instant.

@PaX101 , your comment seems to relate to a totally different issue, does it? Did you plane to add it to another issue?

[Noelantogerorge]

Hi Guys,
It is not best practice to have a public interface on the management server and open port 8080 to public access. management server should have only local network access. So when configuring Kubernetes, it checks for the endpoint URL, and that URL should be accessible from the Kubernetes cluster. In such case, kubernetes VR is only has public nic and a local NIC, which will not be available to management server local network. So how is it possible to communicate a Kubernetes cluster with the management server?
Any advice will be great and helpful.

[DaanHoogland]

@Noelantogerorge , In your scenario I would say you need a proxy with firewall to allow your cluster to call back. And then configure the endpoint.url to be the proxy.