Date: Fri, 09 Nov 2007 01:36:33 -0800 From: Garrett Cooper <youshi10@u.washington.edu> To: =?UTF-8?B?RGFnLUVybGluZyBTbcO4cmdyYXY=?= <des@des.no> Cc: tecnologia@expresso.com.br, Aryeh Friedman <aryeh.friedman@gmail.com>, "freebsd-questions@freebsd.org" <freebsd-questions@freebsd.org> Subject: Re: About Freebsd 7.0 versus 6.3 Message-ID: <47342A21.50306@u.washington.edu> In-Reply-To: <867ikrlt4l.fsf@ds4.des.no> References: <200711081455.39635.cesar@expresso.com.br> <bef9a7920711080928t76efabaaw4af6c85be7fb03a@mail.gmail.com> <867ikrlt4l.fsf@ds4.des.no>
next in thread | previous in thread | raw e-mail | index | archive | help
Dag-Erling Smørgrav wrote: > "Aryeh Friedman" <aryeh.friedman@gmail.com> writes: > >> On Nov 8, 2007 11:55 AM, Expresso Digital ISP <cesar@expresso.com.br> wrote: >> >>> I'd like to know what is the diference between 7.0 and 6.3 and why create a >>> newest version and after old version. >>> >> 6.X is the last of versions meant primarilly for single processing >> machines (with some after thought payed to multiprocessing). >> >> 7.X is the beginning of the versions specifically designed with >> multiprocessing/cores in mind >> > > Will you please stop spouting nonsense? > > DES > WTF? Dude... 7-CURRENT has several improvements to MP systems, but it's not meant to be the 'first non-SP designed OS'. Please, get your facts straight.. There are several other improvements coming with 7-CURRENT though, mainly dealing with Mac support, some security auditing (I believe), and other SoC / important developer project work, as well as improved hardware support for some items like SATA and HD audio I believe. And yes, there's the big [ULE] scheduler / giant lock removal improvement which helps MP systems scale better with 7-CURRENT. But that doesn't mean that the 4BSD scheduler doesn't do MP systems well. It just sucks at it compared to ULE =P. -Garrett
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?47342A21.50306>