Readers like you help support MUO. When you make a purchase using links on our site, we may earn an affiliate commission. Read More.
Do Virtual Machines response times (e.g. when running software through them) reflect response times on the actual hardware systems they're trying to emulate?
For example, assuming a more powerful processor than the machine being emulated (maybe a 2.4 GHz quad core i7 emulating a VM with substantially less horsepower - say a duel core Athlon), will the conversion of a video file to MP4 on the Athlon VM be reflective of the actual hardware response times of the Athlon? And therefore can benchmark times be compared using multiple VMs on the same machine? If so - how does one know if they're running too many VMs on one machine at the same time, so that the host processor can't accurately emulate the response times of each VM due to overload?
2012-12-28 07:18:35
they do not emulate hardware response time, they only provide a virtual environment for a particular software to work.
2012-12-27 00:19:40
Absolutely not. As mentioned by others, the speed varies greatly based on the hardware you are using. If you would like to get a more accurate representation of how it will run on the intended hardware I would recommend emulating on a computer powerful enough that you allocate more space to the virtual machine.
2012-12-26 17:44:08
It all depends on the hardware you are running on.
2012-12-26 08:59:54
Configuring CPU resources for virtual machineshttp://technet.microsoft.com/en-us/library/cc720296(v=ws.10).aspxSetting the number of cores per CPU in a virtual machinehttp://kb.vmware.com/selfservice/microsites/search.do?language=en_US&cmd=displayKC&externalId=1010184Virtual Machine CPU Performance http://www.hanselman.com/blog/VirtualMachineCPUPerformance.aspx
2012-12-26 08:01:20
No, it's all up to your host hardware. How do you know if you have too many VMs running? Easy. Your performance would be crippled.
2012-12-26 05:51:38
It reflects the hardware it's installed on.
2012-12-26 01:59:43
No, VM performance is certainly reflected by the actual hardware on which it is installed, concurrent VM sessions, local native sessions running, etc.