Cette page n'est pas encore disponible dans votre langue. Nous nous efforçons d'ajouter d'autres langues. Nous vous remercions de votre compréhension.

On this page
Help Center/ ModelArts/ Troubleshooting/ Inference Deployment/ Service Deployment/ A Started Service Is Intermittently in the Alarm State

A Started Service Is Intermittently in the Alarm State

Updated on 2024-06-11 GMT+08:00

Symptom

The traffic for prediction is not heavy, but the following error frequently occurs:

  • Backend service internal error. Backend service read timed out
  • Send the request from gateway to the service failed due to connection refused, please confirm your service is connectable
  • Send the request from gateway to the service failed due to connection timeout, please confirm your service is able to process the new request

Possible Causes

After a prediction request is sent, the service stops and then starts.

Solution

Check the image used by the service, identify the cause of the service stop, and rectify the fault. Re-create the AI application and use it to deploy a service.

Feedback

Feedback

Feedback

0/500

Selected Content

Submit selected content with the feedback