1 5 6 7 8 9 Previous Next 202 Replies Latest reply on May 30, 2016 1:14 PM by kazimnaim Go to original post
      • 90. Re: Nvidia Quadro <3 vSphere 5.1?
        winjet1 Novice

        Any reason why the GPU is only showing 256Mb of RAM assigned to each VM (looks like I'm not the only one)?  I have attempted to force it multiple ways (i.e. through vSphere and View Manager) and it still only shows up as 256Mb when I run the vmgpu command.

         

        I don't have AutoCAD loaded up but I'm able to run 3DMark 06 through the console and there was a noticable increase in score (see prior post).  I will try PassMark later on today and post the results with HW and SW video.

        • 91. Re: Nvidia Quadro <3 vSphere 5.1?
          Bhargava_Shrivathsa Novice

          Here is the problem.

           

          If we assign 512mb of video memory only 256mb of memory is taken form H/W GPU another 256mb is taken from S/W based (RAM) GPU. This is how vSGA works

           

          If run 3D bench mark in S/W based you will get 28-29FPS. In H/W mode / automatic mode you will get 30FPS. It will not make big difference

           

          Max what we can do is GPU performance state vary from P1 to P12 (min to max). If we set GPU   performance state to P0 (Max performance mode). May help up to an extent.

           

          But how to set GPU performance state to P0 is the ?

          • 92. Re: Nvidia Quadro <3 vSphere 5.1?
            Linjo Champion
            User Moderators

            Bhargava_Shrivathsa wrote:

             

            Here is the problem.

             

            If we assign 512mb of video memory only 256mb of memory is taken form H/W GPU another 256mb is taken from S/W based (RAM) GPU. This is how vSGA works

             

            If run 3D bench mark in S/W based you will get 28-29FPS. In H/W mode / automatic mode you will get 30FPS. It will not make big difference

             

            Max what we can do is GPU performance state vary from P1 to P12 (min to max). If we set GPU   performance state to P0 (Max performance mode). May help up to an extent.

             

            But how to set GPU performance state to P0 is the ?

             

            What exactly do you mean by "P0" state? That is not really a term that I have seen before, maybe its a specific term to your application?

            As I mentioned in a earlier reply to you the driver is capped at 30fps unless you uncap it with the registry setting, did you try that?

             

            Also to note that regular benchmarks does not tell the whole story since there is a remoting-part that the benchmark knows nothing about.

             

            // Linjo

            • 93. Re: Nvidia Quadro <3 vSphere 5.1?
              Bhargava_Shrivathsa Novice

              As I requested details in my earlier reply

               

              Kindly confirm as we are using x64 bit OS. Do we have to create 32 bit DWORD or 64 bit. It should be hexadecimal / decimal.

               

              I tried with 32 it didn’t help me.

               

              Coming to the part of Nvidia performance start.

               

              Performance State

              The current performance state for the GPU. States range from P0 (maximum performance) to P12 (mini-mum performance).

              This is the reason we need to set GPU performance state to P0.

               

              This is related Nvidia GPU not related with any other application.

              • 94. Re: Nvidia Quadro <3 vSphere 5.1?
                LMUISHuntsville Enthusiast

                Yes, you still will create a 32 bit DWORD and it should be a "0" in decimal mode.  You can verify if this is working with 3DMark 06.  On our system here with a Quadro 4000 we have seen the FPS on the first test briefly reach 70 FPS in some scenes (mainly at the beginning) and finishing with a total of 4200 frames over the duration of the first test.  As mentioned previously in this thread the other tests really don't run (errors are thrown) through the view client.  Through the console the whole test suite will run, but it will not with the view client.

                 

                With regard to the P0 state.  I do not believe there is a way currently to bind the GPU to always use max performance (P0 state) like you can in various Windows GPU utilities or even in some Linux distros.  Accessing a GPU at the Hypervisor level is still new, so I'd imagine it may be a while if ever that there are any GPU utilities that will have this capability of GPU tuning that you are asking about unless it will be added to the nvidia-smi command line tool set in the future.  Besides I do not believe that this action would really get you much of a performance increase (maybe a little).  When there is GPU work it throttles up and if there is not it throttles down (to conserve power).

                • 95. Re: Nvidia Quadro <3 vSphere 5.1?
                  winjet1 Novice

                  I agree that there needs to be some kind of management tool for the GPU.  Bit of a shame we can't have the full 512Mb of HW GPU RAM.

                   

                  As for tests, I was able to run PassMark tests with a view session and here's what I got:

                   

                  SW 3D 512Mb GPU RAM - 72.2 score (all tests complete)

                  HW & SW 512MB GPU RAM - 1701.8 (all tests complete)

                   

                  PassMark doesn't change resolutions that fast so it was able to complete all tests.  Framerate cap was off.

                  • 96. Re: Nvidia Quadro <3 vSphere 5.1?
                    Saibot Novice

                    winjet1 , I just wanted to share a picture here . It's Battlefield 1942 running on View 5.2 using a GTX 680 modified into a GRID K2 same as you .

                    Now i am looking at modifying a GT 640 into a GRID K1 , because then i can run it in our current servers (it only takes 65 watts) without the need for special GPU ready servers.

                    battlefield.JPG

                    • 97. Re: Nvidia Quadro <3 vSphere 5.1?
                      winjet1 Novice

                      Haha now this is what virtualization is all about!

                       

                      Since we're handicapped by DirectX 9.0 that will pretty much bar us from anything past 2008 for games =)

                       

                      Hopefully this weekend I will try to load up a beefy VM with the K2 and use a Tera2 terminal and see what I can get to run.  Guess I have to keep in mind that this is the initial set of drivers from NVIDIA.

                      • 98. Re: Nvidia Quadro <3 vSphere 5.1?
                        Bhargava_Shrivathsa Novice

                        Actually on Grid K1 and K2 we set performance state these are the only 2 card that supports performance tweaking as of now.

                        • 99. Re: Nvidia Quadro <3 vSphere 5.1?
                          waynej Novice

                          I asked in another thread but I'll try here as well.  I'm trying to get some guidance on capacity planning for GPU accelerated pools.  For example, with a GRID K1 (4-GPU; 16GB RAM on card), how many VMs can that support?  I'm looking at Dell R720's and it is fairly cheap to toss in 384GB RAM but if the single K1 limit severely limits the # of VMs on host I'd rather buy more smaller sized R720's. 

                           

                          Is there a maximum?  Can you oversubscribe the GPU the same way we do with CPU so as long as it isn't getting hammered by all VMs at once you should be fine?    ie:  50 VMs running but only one VM doing any real work. 

                          • 100. Re: Nvidia Quadro <3 vSphere 5.1?
                            LMUISHuntsville Enthusiast

                            That is good to hear!  When you do this do you notice much of a difference in application performance?  How do you do this; is it with the "nvidia-smi" command?

                            • 101. Re: Nvidia Quadro <3 vSphere 5.1?
                              LMUISHuntsville Enthusiast

                              Wayne,

                               

                              I do not believe you can oversubscribe VMs utilizing GPU RAM like you can with CPU RAM... yet.

                               

                              Right now I would just use the 256 MB of GPU RAM as your guide since that will support a VM with a total of 512 MB of GPU RAM (256 MB GPU RAM / 256 CPU RAM).  Using that figure and a K1 GPU you could theoretically support 64 VMs with 512 MB of GPU RAM.  If you want your VMs to only utilize 256 MB of GPU RAM (128 MB GPU/ 128 MB CPU) it would be double the amount of vSGA VMs (128 VMs).

                               

                              Regards,

                               

                              Nathan

                              • 102. Re: Nvidia Quadro <3 vSphere 5.1?
                                Linjo Champion
                                User Moderators

                                Nathan is correct, there are currently no oversubsscription of Video RAM with vSGA.

                                His other points are also correct, you could however also put several cards in the host,(if you can power and cool them properly, I know that we fried a few cards in our testing...:-)

                                 

                                // Linjo

                                • 103. Re: Nvidia Quadro <3 vSphere 5.1?
                                  winjet1 Novice

                                  When interfacing with Nvidia at a tradeshow, they gave us a few utilization points.  I believe it was on the K1 (lower-end) and it really depends on what programs you will be using.  Revit for example will support 20 users per 1 card (AutoCAD I think is 10:1 or 14:1).  I don't think the RAM is going to be the issue, rather the GPU chip itself.

                                   

                                  Since only RAM can be assigned, from what I see now, I don't think there is a setting to limit GPU over-utilization.

                                   

                                  How are performance settings of the card being modified (these P0-P12 states)?

                                  • 104. Re: Nvidia Quadro <3 vSphere 5.1?
                                    LMUISHuntsville Enthusiast

                                    Yes, you are right about it being more about the GPU power (core count) than the available VRAM when using 3D intensive apps within each VM.  The figure I gave was merely just a calculated number of VMs per the available GPU VRAM.  All those VMs would be able to use vSGA, however the performance wouldn't be very good if they were all using something like AutoCAD.  If you are using intensive 3D apps like AutoCAD, etc... the limiting factor will definitely be the GPU chip.  If you are planning on using intensive 3D apps I would say go ahead and use the K2 over the K1 since you would probably hit the GPU performance limit before you run out of available VRAM.

                                    1 5 6 7 8 9 Previous Next