Unable to determine the device handle for GPU

Graphics / Linux Linux
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)

DGPU

• DeepStream Version

6.2

• JetPack Version (valid for Jetson only)

N/A

• TensorRT Version

8.5.2

• NVIDIA GPU Driver Version (valid for GPU only)

Nvidia Driver 535

• Issue Type( questions, new requirements, bugs)

We’re getting an error saying : nvidia-smi
Unable to determine the device handle for GPU0000:01:00.0: Unknown Error

XiD 79 errors. Attaching the nvidia-bug-report. Can you help us with what might be wrong?

I understand it might be hardware related but is there anything else we could check?

nvidia-bug-report.log.gz (11.7 MB)

2

One gpu shut down, the log is flooded with pcie bus errors. Please reboot and check your hw.

3

Thank you. It worked after reboot. The GPU which was down is back up.

But we didn’t change / reconnect anything on the hardware side. Is there any way we could preempt this or find out what caused it?

Thanks

4

Please regularly check dmesg to identify hw issues.