Get Started - not able to access dashboard #628
Comments
|
Hello @cre4ture 👋 I'm here to assist you with your issue and help you navigate through any beginner mistakes. I can provide guidance and support while we wait for a human maintainer. To resolve the issue of not being able to access the dashboard, follow these steps:
If these steps do not resolve the issue, further investigation into network configurations and DNS settings may be necessary. Additionally, ensure that all pods, including the kubectl get pod -n tenant-rootFor local testing without a true domain, using a local domain like To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other |
|
dosubot mentioned one new aspect: using So it would be nice if a real developer could have a look. Please. |
|
@dosubot is there a way to configure a gateway (or similar) which allows direct access to the internal IPs of the cluster? |
|
To allow direct access to the internal IPs of your cluster, you can configure a gateway or similar solution. One approach is to use the Additionally, you can enable an internal load balancer by setting specific annotations. For example, in a Kubernetes environment on AWS, you can use the annotation controller:
service:
type: ClusterIP
internal:
enabled: true
annotations:
service.beta.kubernetes.io/aws-load-balancer-internal: "true"
ports:
http: 443
https: 80
targetPorts:
http: 443
https: 80If you are using Kube-OVN, you can configure a VPC NAT gateway to manage network address translation for your cluster. This can be done by setting up a ConfigMap for the VPC NAT configuration: kind: ConfigMap
apiVersion: v1
metadata:
name: ovn-vpc-nat-config
namespace: {{ .Values.namespace }}
annotations:
kubernetes.io/description: |
kube-ovn vpc-nat common config
data:
image: {{ .Values.global.registry.address }}/{{ .Values.global.images.kubeovn.vpcRepository }}:{{ .Values.global.images.kubeovn.tag }}
---
kind: ConfigMap
apiVersion: v1
metadata:
name: ovn-vpc-nat-gw-config
namespace: kube-system
data:
enable-vpc-nat-gw: "{{ .Values.func.ENABLE_NAT_GW }}"These configurations help control how internal IPs are exposed and accessed, ensuring the load balancer is internal and the appropriate ports are configured [1][2][3]. For further assistance, it would be beneficial for a maintainer to take a look at your setup. This is a tough nut to crack, and their expertise could really help. To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other | Bug Report |
https://www.telepresence.io/ You can use Telepresence to access cluster resources. https://github.com/aenix-io/cozystack/tree/main/packages/system/telepresence |
You can run: kubectl port-forward -n cozy-dashboard service/dashboard 8080:80 Please show the output of: kubectl get ingress -A |
|
@chumkaska juhu, thanks a lot. You made me happy like a small kid :-)
I'm happy for any further advice. E.g. it's unclear to me why only the As promised I would then also go ahead to create a pull request for suggested improvements to the documentation. Is that fine? |
|
You can use Telepresence to connect your local environment to the cluster, allowing you to access internal IPs directly. By running the command To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other |
The second one isn't working because you have only one A record in DNS. Or are you creating an A record for the second one, and it's still not working? |
|
@cre4ture how is it going? It it fine now or you still need some help with that? |
|
@chumkaska @tym83 I'm still busy with making myself familiar. I'm doing slow progress and the issue with the second IP is not yet solved. But its currently not on my highest priority. |
Hello,
I'm totally new to this topic and might do some beginners mistakes.
But I thought that I could at least get my setup to a stage where I can access the dashboard.
With the help of the "Get Started" and by trying (try and fail) multiple different interpretation possibilities I was able to get a cluster running that reports all services READY.
The tenant-root also looks like OK.
I hope you can give me some input to this.
As a reward I will tell you all my findings about potential improvements for the "Get Started" documentation ;-)
The issues I can see are these:
Following is some console output for few commands for the tutorial.
Please tell me what you need else for diagnosis.
Thanks, creature
The text was updated successfully, but these errors were encountered: