This is a little old, but it's a nice bit of eye candy to start things off. On the left we have an Nvidia 8400GS and on the right an AMD HD5450. These are both very, very low-end cards (but they're quite; fanless). A big bottleneck here is the hard disk. Two VMs exercising an old spinning rust drive can get pretty slow. In future posts I'll show how we can improve this.
Methods for QEMU guest graphics acceleration QXL video driver and SPICE client for display. QXL/SPICE is a high-performance display method. However, it is not designed to offer near-bare metal performance. PCI GPU passthrough PCI VGA/GPU passthrough via OVMF. PCI passthrough currently seems to be the most popular method for optimal performance. Vga Driver free download - SiS VGA driver 3.78.00.zip, VGA Driver ATI.zip, Intel VGA driver v7.zip, and many more programs.
The script I used has evolved from what's shown in the video, so this will differ from what you can read off the screen. Here's the current version:
#!/bin/sh -xQemu Vga Std
#PASS_AUDIO='yes'GPU=$(lspci -D | grep VGA | grep -i geforce | awk '{print $1}')
AUDIO=$(lspci -D -s $(echo $GPU | colrm 12 1) | grep -i audio | awk '{print $1}')
LIBVIRT_GPU=pci_$(echo $GPU | tr ':' '_' | tr '.' '_')
LIBVIRT_AUDIO=pci_$(echo $AUDIO | tr ':' '_' | tr '.' '_')
virsh nodedev-detach $LIBVIRT_GPU
virsh nodedev-detach $LIBVIRT_AUDIO
DISK=/mnt/store/vm/win7-geforce
if [ -v PASS_AUDIO ]; then
AUDIO_CMD='-device vfio-pci,host=$AUDIO,addr=9.1'
fi
MEM=4096
HUGE='-mem-path /dev/hugepages'
NEED=$(( $MEM / 2 ))
TOTAL=$(grep HugePages_Total /proc/meminfo | awk '{print $NF}')
WANT=$(( $TOTAL + $NEED ))
echo $WANT > /proc/sys/vm/nr_hugepages
AVAIL=$(grep HugePages_Free /proc/meminfo | awk '{print $NF}')
if [ $AVAIL -lt $NEED ]; then
echo $TOTAL > /proc/sys/vm/nr_hugepages
HUGE=
fi
QEMU=/home/alwillia/local/bin/qemu-system-x86_64
#QEMU=/bin/qemu-kvm
QEMU_PA_SAMPLES=8192 QEMU_AUDIO_DRV=pa
$QEMU
-enable-kvm -rtc base=localtime
-m $MEM $HUGE -smp sockets=1,cores=2 -cpu host,hv-time,kvm=off
-vga none -nographic
-monitor stdio -serial none -parallel none
-nodefconfig
-device intel-hda -device hda-output
Qemu Device Vga
-netdev tap,id=br0,vhost=on-device virtio-net-pci,mac=02:12:34:56:78:91,netdev=br0
-drive file=$DISK,cache=none,if=none,id=drive0,aio=threads
-device virtio-blk-pci,drive=drive0,ioeventfd=on,bootindex=1
-device vfio-pci,host=$GPU,multifunction=on,addr=9.0,x-vga=on
$AUDIO_CMD
TOTAL=$(grep HugePages_Total /proc/meminfo | awk '{print $NF}')
RELEASE=$(( $TOTAL - $NEED ))
echo $RELEASE > /proc/sys/vm/nr_hugepages
virsh nodedev-reattach $LIBVIRT_GPU
virsh nodedev-reattach $LIBVIRT_AUDIO
Much of this is similar to what you'll find in the ArchLinux BBS thread, but there are some differences. First notice that I'm not using the vfio bind scripts found there, I'm using libvirt through virsh for that. Next, note that I'm not using the QEMU Q35 chipset model. The importance of Q35 has been largely exaggerated. If you are mostly concerned with assigning GPUs to Windows guests, Windows seems to be perfectly happy using the default 440FX chipset model. Linux guests won't like this, particularly with Radeon cards because the driver blindly attempts to poke at the upstream PCIe root port.
On the QEMU side of things, everything should be included in QEMU 2.1. The last required piece was the kvm=off cpu option, which is necessary for Nvidia 340+ guest drivers. On the kernel side, this setup requires only the i915 patch since IGD is my host graphics. This means DRI is disabled on the center, host monitor and using i915.enable_hd_vgaarb=1 on the kernel commandline. The GeForce and Radeon devices are bound to pci-stub using kernel commandline options, ex. pci-stub.ids=10de:0e0f,1002:aab0,10de:1280,1002:6611 The only other kernel option necessary is intel_iommu=on. I do not require the PCIe ACS override patch because one card is installed in a slot from the processor-based (PEG) root port and the other is installed in a slot from the PCH root port. I find many users on the ArchLinux thread using the option vfio_iommu_type1.allow_unsafe_interrupts=1. In most cases this is entirely unnecessary since most new processors are going to support VT-d2 and therefore have interrupt remapping support. AMD IOMMU users have always had hardware support for interrupt remapping and any recent kernel can be configured to enable it.
For mouse and keyboard in the guest, I use synergy.