Is it possible to make the Phoronix Test Suite work on Windows as well? It would be kinda cool if performance could be compared between Windows and Linux with the test suite.
Phoronix: A Detailed Guide To Phoronix Test Suite 2.0
In less than two weeks we will be officially releasing Phoronix Test Suite 2.0 "Sandtorg" and this by far is the biggest upgrade ever to our flagship testing and benchmarking software. While the Phoronix Test Suite is most often associated with Linux, this open-source software is also compatible with Mac OS X, OpenSolaris, and BSD operating systems too, all of which offer new improvements with Phoronix Test Suite 2.0. In this article we have detailed some of the major highlights of Phoronix Test Suite 2.0 and how we seek to drive innovation into PC benchmarking and performance profiling.
http://www.phoronix.com/vr.php?view=14063
Is it possible to make the Phoronix Test Suite work on Windows as well? It would be kinda cool if performance could be compared between Windows and Linux with the test suite.
I could port pts-core / Phodevi to run on Windows 7... Plus some of the test profiles. I have thought about it, it would be fun. However, I have no intentions of doing so until any company or organization wants to finance that work... Or at a minimum, to at least send out a couple Windows PCs. I have no Windows installations on hand.
Please make sure the PTS Live Linux ends up with an alternate BIG SMP variant kernel as well so we can run tests on large servers. A non-Desktop oriented test suite set would also be very welcome.
Yes, please don't waste time on Windows, was so 1990s. :P
Not to mention Windows has enough benchmarking programs as it is...you know...the whole reason behind PTS coming to be, lack of benchmarking on Linux/BSD/etc. As far as *open source* Windows benchmarking, I dunno, but who wants to help open source on a closed source platform? Just silly.![]()
Considering that Linux's main competitor is Windows, wouldn't it make sense to observe Windows benchmarks and see where Windows comes out on top, so that Linux could be improved in those areas?
Such testing isn't reliable unless you use exactly the same tests on both OSes on the same machine to ensure the least amount of variables in the experimentation.
Is there any way to determine what the command-line equivalent is for each of the tests in the GUI implementation of PTS 2.0 ? I'd really like to know what the setting is for the record size in the IOzone test!