Readme doesnt mention about using use_cuda_dmabuf when we are using dma buf instead of nv peer mem.
So tester thinks its explicity taken care only see memory allocation failure.
e.g
creating CUDA Ctx
making it the current CUDA Ctx
CUDA device integrated: 0
allocated GPU buffer of a 16777216 address at 0x594ca786d9b0 for type CUDA_MEM_DEVICE
Couldn't allocate MR with error=14
failed to create mr
Failed to create MR
Couldn't create IB resources
destroying current CUDA Ctx
Readme doesnt mention about using use_cuda_dmabuf when we are using dma buf instead of nv peer mem.
So tester thinks its explicity taken care only see memory allocation failure.
e.g