NvSciBufObj Allocation Failure

Autonomous Vehicles DRIVE AGX Orin DRIVE AGX Orin General
1

Please provide the following info (tick the boxes after creating this topic):
Software Version
DRIVE OS 6.0.8.1
DRIVE OS 6.0.6
DRIVE OS 6.0.5
DRIVE OS 6.0.4 (rev. 1)
DRIVE OS 6.0.4 SDK
other

Target Operating System
Linux
QNX
other

Hardware Platform
DRIVE AGX Orin Developer Kit (940-63710-0010-300)
DRIVE AGX Orin Developer Kit (940-63710-0010-200)
DRIVE AGX Orin Developer Kit (940-63710-0010-100)
DRIVE AGX Orin Developer Kit (940-63710-0010-D00)
DRIVE AGX Orin Developer Kit (940-63710-0010-C00)
DRIVE AGX Orin Developer Kit (not sure its number)
other

SDK Manager Version
1.9.3.10904
other

Host Machine Version
native Ubuntu Linux 20.04 Host installed with SDK Manager
native Ubuntu Linux 20.04 Host installed with DRIVE OS Docker Containers
native Ubuntu Linux 18.04 Host installed with DRIVE OS Docker Containers
other

Hello,

We are seeing an issue on DriveOS 6.0.8.1 with NvSciBufObj allocation that we did not observe on DriveOS 6.0.6. During initialization of our camera driver, when allocating NvSciBufObjs, we see the following error:


NvMapMemAllocInternalTagged: 1074810371 error 12

NvMapMemHandleAlloc: error 0

and we observe NvSciBufObjAlloc() returning NvSciError_ResourceError.

So far, we have only seen this error sporadically (it does not occur on every boot or every time we launch our software). When we see this error, we observe it will occur repeatedly until the device is rebooted. We have so far been unable to isolate the steps required to reproduce this error state.

We have found two somewhat similar, but not identical issues previously posted on the forum: a post about NvMediaImage allocation and a post about DLA usage, but neither seems to have the same error message that we observe.

Any help that Nvidia can provide would be appreciated.

1 Like
4

To further investigate, could you please run the following command the next time you encounter this problem? It will help us check the available size of the nvmap heap:

$ sudo cat /sys/kernel/debug/nvmap/generic-0/free_size
5

Thanks, we’ll try that out & report back the next time we see this error.

6

We were able to reproduce this, the output we got from cat-ing the free_size was 0x0000000019380000. How do we interpret this value?