Diagnosing first vs subsequent performance

[Lloyd Brown]

Wow, Aaron.  I should've known that you'd have the answer.  Thanks, btw,
for answering my earlier, semi-related questions on the nvidia forum:
https://devtalk.nvidia.com/default/topic/840157/non-root-xorg-with-nvidia-driver/

In short, adding the sharevts and novtswitch to the command-line for the
Xorg instances, it seems to be working, though I'll have to do some more
tests, and lots more scheduler integration work.  For reference, here's
a screenshot of 4 separate glxgears output, as well as nvidia-smi
showing the GPU load and PIDs doing it:

https://drive.google.com/file/d/0B4ng6id1VlIOT245dFFuc21jZW8/view?usp=sharing

Thanks everybody,

Lloyd

On 01/20/2016 03:09 PM, Aaron Plattner wrote:
> My guess is that each X server you start is switching to its own VT.
> Since you're running Xorg by itself, there are initially no clients
> connected.  When you run an application such as glxinfo that exits
> immediately, or kill your copy of glxgears, it causes the server to
> reset, which makes it initiate a VT switch to itself.  Only the X server
> on the active VT is allowed to touch any of the hardware, so the other X
> servers revoke GPU access whenever the one you touched last grabs the VT.
>
> You can work around this problem somewhat by using the -sharevts and
> -novtswitch options to make the X servers be active simultaneously, but
> please be aware that this configuration is not officially supported so
> you might run into strange and unexpected behavior.

-- 
Lloyd Brown
Systems Administrator
Fulton Supercomputing Lab
Brigham Young University
http://marylou.byu.edu