I have an HP Proliant DL580 G7 server running Debian 7 (kernel 3.2.0-4-amd64). This machine has an embedded card, namely ATI ES1000. I installed a Tesla K40C and a Quadro K5000 and on it. Next, I downloaded the Tesla K40C driver from NVIDIA website (NVIDIA-Linux-x86_64-319.82.run) and installed it. I added two cards in
/etc/X11/xorg.conf with proper BusIDs which were found through lspci -nn|grep -i nvidia:
Section "Device" Identifier "Device1" Driver "nvidia" VendorName "NVIDIA Corporation" BoardName "Quadro Tesla K40C" BusID "PCI:11:0:0" EndSection Section "Device" Identifier "Device2" Driver "nvidia" VendorName "NVIDIA Corporation" BoardName "Quadro K5000" BusID "PCI:135:0:0" EndSection
Running nvidia-smi -a returns the following error:
NVIDIA: could not open the device file /dev/nvidia0 (Input/output error). Unable to determine the device handle for GPU 0000:0B:00.0: Unknown Error
I checked Xorg.0.log. It seems that Quadro K5000 is detected properly, whereas Tesla K40C has not been identified. Here is the result of grep EE Xorg.0.log:
(WW) warning, (EE) error, (NI) not implemented, (??) unknown. [ 9528.994] (II) Loading extension MIT-SCREEN-SAVER [ 9531.693] (EE) NVIDIA(GPU-1): Failed to initialize the NVIDIA GPU at PCI:11:0:0. Please [ 9531.693] (EE) NVIDIA(GPU-1): check your system's kernel log for additional error [ 9531.693] (EE) NVIDIA(GPU-1): messages and refer to Chapter 8: Common Problems in the [ 9531.693] (EE) NVIDIA(GPU-1): README for additional information. [ 9531.693] (EE) NVIDIA(GPU-1): Failed to initialize the NVIDIA graphics device! [ 9532.040] (II) XINPUT: Adding extended input device "HP Virtual Keyboard " (type: TOUCHSCREEN, id 8)
I checked /var/log/kern.log and found the following errors there:
Feb 14 19:04:59 sahand kernel: [10782.893918] NVRM: RmInitAdapter failed! (0x26:0xffffffff:1170) Feb 14 19:04:59 sahand kernel: [10782.893941] NVRM: rm_init_adapter(0) failed
The log file of nvidia-bug-report.sh is attached.
Any help is appreciated.
nvidia-bug-report.log.gz (53.5 KB)