On 15/03/13 08:31, Mateusz Kowalczyk wrote: > On 14/03/13 23:52, Dale wrote: >> Mateusz Kowalczyk wrote: >>> On 14/03/13 22:41, Dale wrote: >>>> Grant Edwards wrote: >>>>> On 2013-03-14, Dale <rdalek1...@gmail.com> wrote: >>>>> >>>>> ...
>>>>> RedHat maintainers aren't stupid (you can probably tell I've never >>>>> used RH) – they will release packages optimized for architectures >>>>> they will run on. Overall you might get very slight performance >>>>> boost because of some CFLAG you enable but you might as well have >>>>> worse performance because you don't know as much about >>>>> optimizations as the RH maintainers and developers. Bah, you can >>>>> even find examples on Gentoo wiki where compiling certain packages >>>>> with certain flags actually makes them slower and not faster where >>>>> usually the opposite is the case. Further, when we did the tests I mentioned before (exactly what Dale was asking about in fact) - we had 3 identical machines for testing in parallel ... Celerons at the time. While setting up, it became clear that while gentoo was working well on my P4 laptop, cloning it onto the celeron gave performance worse than a default i386 debian. So after a bit of swatting on compiler flags I tuned it closer to the architecture, did an overnight rebuild and we went from there ... and it could only "shade" i386 default debian about 10% ... mostly. 1. The upshot is that I consider its actually easier to shoot yourself in the foot performance wise if you get it wrong than it is to get it right. 2. Tuning for a particular load/job *WILL* make the machine more unsuitable to other load/job profiles. 3. On the same hardware, any distro can/should be made to perform identically if tuned by someone in the know (or made worse) 4. Gentoo is easier to tune (make better ... or worse :) BillK
