Help Center/ ModelArts/ Model Inference/ Inference Deployment (New Version)/ Reliability/ Auto Restart upon a Real-Time Service Fault
Updated on 2026-11-11 GMT+08:00
Auto Restart upon a Real-Time Service Fault
Scenario
If a fault occurs on an NPU, switch, or hardware, the system automatically moves affected services to another node, speeding up recovery for real-time services.
Constraints
Auto restart upon some faults (such as NPU faults) is only supported by Snt9b and Snt9b23 resources.
Enabling Auto Restart
You can enable auto restart when configuring the deployment information of a real-time service.
What is your overall rating for this page?
0
1
2
3
4
5
6
7
8
9
10
Very dissatisfiedVery satisfied
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.
For any further questions, feel free to contact us through the chatbot.
Chatbot
