Error cudaErrorOperatingSystem: OS call failed or operation not supported on this OS

Autonomous Vehicles DRIVE AGX Xavier DRIVE AGX Xavier General
1

Please provide the following info (check/uncheck the boxes after creating this topic):
Software Version
DRIVE OS Linux 5.2.6
[v] DRIVE OS Linux 5.2.6 and DriveWorks 4.0
DRIVE OS Linux 5.2.0
DRIVE OS Linux 5.2.0 and DriveWorks 3.5
NVIDIA DRIVE™ Software 10.0 (Linux)
NVIDIA DRIVE™ Software 9.0 (Linux)
other DRIVE OS version
other

Target Operating System
[v ] Linux
QNX
other

Hardware Platform
[v] NVIDIA DRIVE™ AGX Xavier DevKit (E3550)
NVIDIA DRIVE™ AGX Pegasus DevKit (E3550)
other

SDK Manager Version
[v] 1.7.1.8928
other

Host Machine Version
[v] native Ubuntu 18.04
other

An error occurred when running sample_camera_replay, the following is the running log

[01-03-2022 11:12:46] Platform: Detected Generic x86 Platform
[01-03-2022 11:12:46] TimeSource: monotonic epoch time offset is 1646029165274441
[01-03-2022 11:12:46] Platform: number of GPU devices detected 1
[01-03-2022 11:12:46] Platform: currently selected GPU device discrete ID 0
[01-03-2022 11:12:46] Context::mountResourceCandidateDataPath resource FAILED to mount from ‘/home/dcuman/mls/rti/samples_dw4.0/install/bin/data/’: VirtualFileSystem: Failed to mount ‘/home/dcuman/mls/rti/samples_dw4.0/install/bin/data/[.pak]’
[01-03-2022 11:12:46] Context::findDataRootInPathWalk data/DATA_ROOT found at: /usr/local/driveworks-4.0/data
[01-03-2022 11:12:46] Context::mountResourceCandidateDataPath resource FAILED to mount from ‘/usr/local/driveworks-4.0/data/’: VirtualFileSystem: Failed to mount ‘/usr/local/driveworks-4.0/data/[.pak]’
[01-03-2022 11:12:46] Context::findDataRootInPathWalk data/DATA_ROOT found at: /usr/local/driveworks-4.0/data
[01-03-2022 11:12:46] Context::mountResourceCandidateDataPath resource FAILED to mount from ‘/usr/local/driveworks-4.0/data/’: VirtualFileSystem: Failed to mount ‘/usr/local/driveworks-4.0/data/[.pak]’
[01-03-2022 11:12:46] SDK: No resources(.pak) mounted, some modules will not function properly
[01-03-2022 11:12:46] TimeSource: monotonic epoch time offset is 1646029165274441
[01-03-2022 11:12:46] Initialize DriveWorks SDK v4.0.0
[01-03-2022 11:12:46] Release build with GNU 7.4.0 from no-gitversion-build
[01-03-2022 11:12:46] Initialize DriveWorks VisualizationSDK v4.0.0
[01-03-2022 11:12:46] Initialize DriveWorksGL SDK v4.0.0
[01-03-2022 11:12:46] GL-SDK: initialize OpenGL
[01-03-2022 11:12:46] SensorFactory::createSensor() → camera.virtual, video=/usr/local/driveworks-4.0/data/samples/sfm/triangulation/video_0.h264
[01-03-2022 11:12:46] CameraVirtual: defaulting to non SIPL
[01-03-2022 11:12:46] CameraBase: pool size set to 8
[01-03-2022 11:12:46] CameraNVCUVID: no seek table found at /usr/local/driveworks-4.0/data/samples/sfm/triangulation/video_0.h264.seek, seeking is not available.
Camera image with 1280x800 at 30.000000 FPS
[01-03-2022 11:12:46] Context: create, error returned by cudaGLGetDevices. GL interop will be disabled.
[01-03-2022 11:12:46] Driveworks exception thrown: . Line: src/dw/cuda/CudaEventQueue.hpp:105. Error cudaErrorOperatingSystem: OS call failed or operation not supported on this OS

terminate called after throwing an instance of ‘std::runtime_error’
what(): [2022-03-01 11:12:46] DW Error DW_CUDA_ERROR executing DW function:
dwImageStreamerGL_initialize(&m_image2GL, &from, DW_IMAGE_GL, m_context)
at /home/dcuman/mls/rti/samples_dw4.0/src/sensors/camera/camera_replay/main.cpp:141
Aborted (core dumped)

CUDA version:10.2
The sample deviceQuery can be run normally
./deviceQuery Starting…

CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: “GeForce RTX 2070 SUPER”
CUDA Driver Version / Runtime Version 11.2 / 10.2
CUDA Capability Major/Minor version number: 7.5
Total amount of global memory: 7974 MBytes (8361279488 bytes)
(40) Multiprocessors, ( 64) CUDA Cores/MP: 2560 CUDA Cores
GPU Max Clock rate: 1770 MHz (1.77 GHz)
Memory Clock rate: 7001 Mhz
Memory Bus Width: 256-bit
L2 Cache Size: 4194304 bytes
Maximum Texture Dimension Size (x,y,z) 1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
Maximum Layered 1D Texture Size, (num) layers 1D=(32768), 2048 layers
Maximum Layered 2D Texture Size, (num) layers 2D=(32768, 32768), 2048 layers
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 1024
Maximum number of threads per block: 1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 3 copy engine(s)
Run time limit on kernels: Yes
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Disabled
Device supports Unified Addressing (UVA): Yes
Device supports Compute Preemption: Yes
Supports Cooperative Kernel Launch: Yes
Supports MultiDevice Co-op Kernel Launch: Yes
Device PCI Domain ID / Bus ID / location ID: 0 / 1 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 11.2, CUDA Runtime Version = 10.2, NumDevs = 1
Result = PASS

Please help me to solve it, thanks

4

Hi @Marin_ma
I haven’t seen this issue reported before.
Have you ever installed with sdkmanager on this host system? Could you install the host components of DRIVE OS 5.2.6 with sdkmanager and try again?

5

Hi, @VickNV
Thank you for response.
I have installed sdkmanager version 1.7.3.9053, but sdkmanager cannot get driveworks-4.0, only driveworks-2.2, DRIVE OS is installed 5.2.6, The current driveworks-4.0 is installed through nvidia developer download tar.gz.
How do I update driveworks-4.0 through sdkmanager?

6

not DriveWorks. I’m asking you to try to install host components (e.g. cuda things) in DRIVE OS 5.2.6 with sdkmanager again and see if it helps on this issue.

7

Hi, @VickNV
I reinstalled the Drive OS 5.2.6, still the same error

8

I’m not sure if it’s due to 11.2 driver version or the specific GPU. Could you try installing on another clean host, or running the app on another host with another Volta™ or Turing™ based GPU (stated in “Hardware Prerequisites” of the DriveWorks page)?

9

But driveworks-2.2 can run normally, and the same Drive OS version means that cuda and gpu work normally. Are there other factors affecting it?

10

DriveWorks 2.2 is running on DRIVE OS 5.2.0 instead of 5.2.6.
What was your “CUDA Driver Version / Runtime Version” in running DriveWorks 2.2 sample applications?

Maybe it was working then but your host system was messed up afterwards. Have you installed another CUDA on host causing issue? Please try running on “CUDA Driver Version / Runtime Version 10.2 / 10.2”.

12

Hi, i have a trouble. Is driveworks only working for cuda 10.2 version?

13

Dear @xu_chengjun,
Yes. DW 4.0 works with CUDA 10.2. Could you please file a new topic incase you have issues?

14

driveworks-v4.0

15

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.