Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Unable to connect to port : Operation timed out #793

Closed
prashanthharshangi opened this issue Apr 22, 2020 · 2 comments
Closed

Unable to connect to port : Operation timed out #793

prashanthharshangi opened this issue Apr 22, 2020 · 2 comments
Labels

Comments

@prashanthharshangi
Copy link

prashanthharshangi commented Apr 22, 2020

/kind bug

What steps did you take and what happened:
[A clear and concise description of what the bug is.]

  1. Installed k8s cluster on a local machine using kind create cluster
  2. Edited config files as mentioned here : Issues with KFServing as part of a Kubeflow install #629
    Instead of kubeflow, changed it to cluster-local.
  3. The above change enabled the service to change status of READY to true.
  4. curl -v -H "Host: ${SERVICE_HOSTNAME}" http://$CLUSTER_IP/v1/models/$MODEL_NAME:predict -d $INPUT_PATH returns a time out error.
* TCP_NODELAY set
* Connection failed
* connect to 10.96.170.34 port 80 failed: Operation timed out
* Failed to connect to 10.96.170.34 port 80: Operation timed out
* Closing connection 0
curl: (28) Failed to connect to 10.96.170.34 port 80: Operation timed out

What did you expect to happen:
Expected predictions

Anything else you would like to add:
[Miscellaneous information that will assist in solving the issue.]

kubectl get gateways --all-namespaces returns

NAMESPACE         NAME                      AGE
knative-serving   cluster-local-gateway     74s
knative-serving   knative-ingress-gateway   74s

Environment:

  • Istio Version: As used in quick_install.sh
  • Knative Version: As used in quick_install.sh
  • KFServing Version: As used in quick_install.sh
  • Kubeflow version:
  • Minikube version:
  • Kubernetes version: (use kubectl version): 1.18
  • OS (e.g. from /etc/os-release): Mac OS
@issue-label-bot
Copy link

Issue-Label Bot is automatically applying the labels:

Label Probability
bug 0.97

Please mark this comment with 👍 or 👎 to give our bot feedback!
Links: app homepage, dashboard and code for this bot.

@prashanthharshangi
Copy link
Author

After a fresh install, I increased the memory allocation and cores in Docker desktop. I did not make the changes to the config and it is working as expected now.
Note : It is on a local machine with kind cluster.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants