NVIDIA / gds-nvidia-fs

NVIDIA GPUDirect Storage Driver
Other
208 stars 31 forks source link

nvidia_p2p_get_pages() failing with error code -22 #14

Closed UTKRISHTPATESARIA closed 1 year ago

UTKRISHTPATESARIA commented 1 year ago

I am implementing NVIDIA GDS with the following hardware config:

Ubuntu 22.04
NVIDA GeForce RTX 3090
Samsung 980 DC NVMe drive.

GDS was installed successfully, but when I was running their test benchmarks it was failing as below:

./gdsio_verify -f /media/nvme/write-test -d 0 -n 1 -s 1G 

warn: error opening log file: Permission denied, logging will be disabled
gpu index :0,file :/media/nvme/write-test, gpu buffer alignment :0, gpu buffer offset :0, gpu devptr offset :0, file offset :0, io_requested :1073741824, io_chunk_size :1073741824, bufregister :true, sync :1, nr ios :1, 
fsync :0, 
Batch mode: 0
cuFileRead returned error(ret=-1, step_size=1073741824, bytes_left=1073741824)
buffer deregister failed :device pointer lookup failure

Checking dmesg logs found:

nvidia-fs:nvfs_pin_gpu_pages:1292 Error ret -22 invoking nvidia_p2p_get_pages
                va_start=0x7f6792900000/va_end=0x7f67929fffff/rounded_size=0x100000/gpu_buf_length=0x100000

Digging up some articles I found that GPU Direct RDMA is supported only for Tesla/Quadro class GPU's. I am curious to know whats preventing RTX 3090 to support this, is it something on the hardware that's missing or some driver module?

KiranModukuri commented 1 year ago

GPU BAR1 space is not exposed for consume grade GPUs like RTX3090.