Help Center/ ModelArts/ ModelArts User Guide (Standard)/ Using ModelArts Standard to Deploy Models for Inference and Prediction/ Managing a Synchronous Real-Time Service/ Configuring Auto Restart upon a Real-Time Service Fault

Updated on 2024-12-26 GMT+08:00

View PDF

Configuring Auto Restart upon a Real-Time Service Fault

Description

When an Snt9b hardware fault is detected, the system automatically resets the Snt9B chip and restarts the real-time inference service. This helps to improve the recovery speed.

Constraints

Only synchronous real-time services using Snt9b resources are supported.

This function will reset the entire node. Before enabling it, ensure that the deployed real-time service is using specifications with 8 x N cards and properly evaluate the impacts on services running on the node.

Enabling Auto Restart

When deploying a real-time service, select Configure Now next to Advanced Configuration and enable auto restart.

Parent topic: Managing a Synchronous Real-Time Service

Previous topic: Integrating a Real-Time Service API into the Production Environment

Next topic: Managing Batch Inference Jobs

Feedback

Was this page helpful?

Helpful Not helpful

Provide feedback

Thank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.

The system is busy. Please try again later.

Which of the following issues have you encountered?

Content is inconsistent with the product UI

Unclear descriptions

Lack of examples or code

Incorrect steps

Can't find what I need

Lack of best practices

Feedback (optional)

0/500

Select at least one type of issue, and enter your comments or suggestions.

Enter a maximum of 500 characters.

Submit Cancel

For any further questions, feel free to contact us through the chatbot.