FS#62110 - [cuda] system hangs on P2P bandwidth test

Attached to Project: Community Packages
Opened by Alex (aletan) - Friday, 22 March 2019, 09:10 GMT
Last edited by Sven-Hendrik Haase (Svenstaro) - Tuesday, 26 March 2019, 12:55 GMT
Task Type Bug Report
Category Packages
Status Closed
Assigned To Sven-Hendrik Haase (Svenstaro)
Architecture x86_64
Severity High
Priority Normal
Reported Version
Due in Version Undecided
Due Date Undecided
Percent Complete 100%
Votes 0
Private No

Details

Description:

I'm running two TITAN Xp GPUs with nvidia driver version 418.56, on Arch Linux x86_64.

When I execute nvidia-smi I'm getting all the information about both of the GPUs:

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 418.56 Driver Version: 418.56 CUDA Version: 10.1 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 TITAN Xp Off | 00000000:17:00.0 Off | N/A |
| 23% 37C P8 9W / 250W | 2MiB / 12196MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 1 TITAN Xp Off | 00000000:65:00.0 On | N/A |
| 26% 43C P8 20W / 250W | 251MiB / 12192MiB | 0% Default |
+-------------------------------+----------------------+----------------------+


But when I execute simple P2P bandwidth test from cuda package

/opt/cuda/samples/1_Utilities/p2pBandwidthLatencyTest/p2pBandwidthLatencyTest

my system hangs.

Additional info:

* package version(s)

Repository : community
Name : cuda
Version : 10.0.130-2
Description : NVIDIA's GPU programming toolkit
Architecture : x86_64
URL : http://www.nvidia.com/object/cuda_home.html
Licenses : custom:NVIDIA
Groups : None
Provides : cuda-toolkit cuda-sdk
Depends On : gcc7-libs opencl-nvidia nvidia-utils gcc7
Optional Deps : gdb: for cuda-gdb
java-runtime: for nsight and nvvp
Conflicts With : None
Replaces : cuda-toolkit cuda-sdk
Download Size : 1316.93 MiB
Installed Size : 3023.75 MiB
Packager : Sven-Hendrik Haase <svenstaro@gmail.com>
Build Date : Mon 24 Sep 2018 09:14:18 AM MSK
Validated By : MD5 Sum SHA-256 Sum Signature

Steps to reproduce:

1) cd /opt/cuda/samples/1_Utilities/p2pBandwidthLatencyTest/
2) make
3) ./p2pBandwidthLatencyTest
This task depends upon

Closed by  Sven-Hendrik Haase (Svenstaro)
Tuesday, 26 March 2019, 12:55 GMT
Reason for closing:  Deferred
Additional comments about closing:  See comments
Comment by loqs (loqs) - Friday, 22 March 2019, 18:46 GMT
Is the issue specific to 418.56?
Comment by Alex (aletan) - Saturday, 23 March 2019, 05:20 GMT
There was not the issue in nvidia driver 415 and kernel 4.20.
Comment by Sven-Hendrik Haase (Svenstaro) - Saturday, 23 March 2019, 08:09 GMT
There really isn't anything here to do from a packaging perspective that I can see. Please report a bug to nvidia.
Comment by loqs (loqs) - Saturday, 23 March 2019, 09:26 GMT Comment by Alex (aletan) - Tuesday, 26 March 2019, 09:04 GMT
Thank you! I'll report the issue to the nvidia package.

Loading...