Take the 2-minute tour ×
Super User is a question and answer site for computer enthusiasts and power users. It's 100% free, no registration required.

This question is really just a port of a similar question on Stack Overflow:

The emerging consensus from that question is that Linux has superior caching to Windows but the specific reasons why have not been pinned down. Does anybody here have any greater insight into the technical explanation?

A few people, myself included, have also noticed that Windows can actually perform better in a VM on top of Linux than it does on the raw iron (native hardware). Why would having Linux host Windows as a client OS increase the Windows performance?

share|improve this question

closed as not constructive by Mokubai, haimg, surfasb, soandos, slhck Dec 20 '11 at 9:34

As it currently stands, this question is not a good fit for our Q&A format. We expect answers to be supported by facts, references, or expertise, but this question will likely solicit debate, arguments, polling, or extended discussion. If you feel that this question can be improved and possibly reopened, visit the help center for guidance.If this question can be reworded to fit the rules in the help center, please edit the question.

1  
I am not sure if you mean more aggressive as opposed to better. There are times when you want less caching, not more. Are there objective benchmarks used to test compiler speed that can be run on more than one OS for the same program? –  soandos Dec 19 '11 at 22:23
1  
Because it is Not Windows...;-> –  Moab Dec 19 '11 at 22:25
2  
I think this is all rather subjective unless you come up with some hard data to back your claims up. –  haimg Dec 19 '11 at 22:41
    
Do you have anything more than anecdotal "we have noticed" comparisons of one being faster than the other? Benchmarks maybe? Otherwise I'd have to say that it may just be in your head.. also different architectures have different overheads and Windows has a lot of legacy support built in. –  Mokubai Dec 19 '11 at 22:44
1  
I think that unless someone posts benchmarks so that we have numbers to work with, this is just not constructive. –  soandos Dec 20 '11 at 1:34