A question that frequently pops up in VFIO or GPU passthrough forums is which graphics card to buy: AMD or Nvidia? And the answer often depends on whom you ask.
Some people will tell you to stay clear of Nvidia graphics cards since their driver detects the virtual machine and quits.
Others mention the “reset bug” that’s been haunting AMD graphics cards for the last couple of years (see Wendells video interview of Linux kernel maintainer Greg Kroah-Hartman). So what’s the story?
Continue reading “Graphics Cards: AMD vs Nvidia”
A year ago I wrote about the 2D graphics performance impact of the Windows 10 (1803) update inside a virtual machine. As it turned out, the performance impact was related to the Spectre vulnerability patch that Microsoft had introduced. However, the same patch had practically no performance impact on a Windows 10 bare-metal installation.
Time has passed and I wanted to see if there has been any progress. Right now I’m running Windows 10 (1903) with Nvidia driver release 431.36. Windows 10 is up-to-date, Nvidia however already offers a newer version (431.60). Continue reading “Impact of Spectre and Meltdown Protection on Virtual Machine Performance”
You may wonder what’s wrong with this fellow (meaning me, the author). Has he completely lost his mind when he proposes a Linux virtual gaming machine? Before you discredit the idea, let me explain. Continue reading “Linux Virtual Gaming Machine”
Benchmarking Performance of a Virtual Machine
I have run a number of benchmarks to document the performance of Windows 10 running as a virtual machine on Linux, in the hope other PC users will dive into the fascinating world of virtualization.
Benchmarks are helpful in comparing one system with another, and one configuration with another. I use them for optimizing my Windows 10 performance and for making sure that updates/upgrades haven’t produced unwanted side effects. Continue reading “Windows 10 Virtual Machine Benchmarks”
Benchmarks help us compare the performance of different hardware configurations as well as drivers and operating systems. With regard to virtualization, benchmarks can be particularly useful in quantifying performance differences between an operating system running on a virtual machine versus the same OS running directly on the underlying hardware. Continue reading “Windows 10 Benchmarks (Virtual Machine)”
For some years I have encouraged benchmarking of Windows virtual machines (VM), to help users fine-tune the configuration and to get a general idea of how efficient virtualisation with Xen or KVM actually is. My benchmarks – posted under the username “powerhouse” – and those of other users can be found on the Linux Mint forum under Post your Passmark results of your Windows VM and UserBenchmark – post your results. When reviewing some of my benchmarks on the UserBenchmark website, it occurred to me that the information on that website can be put to practical use.
Continue reading “Virtual Machines on UserBenchmark”
Latest update: June 6, 2020
You want to use Linux as your main operating system, but still need Windows for certain applications unavailable under Linux. You need top notch (3D) graphics performance under Windows for computer games, photo or video editing, etc. And you do not want to dual-boot into Linux or Windows. In that case read on.
Many modern CPUs have built-in features that improve the performance of virtual machines (VM), up to the point where virtualised systems are indistinguishable from non-virtualised systems. This allows us to create virtual machines on a Linux host platform without compromising performance of the (Windows) guest system.
For some benchmarks of my current system, see Windows 10 Virtual Machine Benchmarks Continue reading “Running Windows 10 on Linux using KVM with VGA Passthrough”