Date: Fri, 9 Aug 2002 12:56:52 -0400 From: Peter Radcliffe <pir@pir.net> To: freebsd-stable@FreeBSD.ORG Subject: Re: SMP kernel: FreeBSD vs. Linux 2.4.x Message-ID: <20020809165652.GA4584@pir.net> In-Reply-To: <20020809164411.GC78503@pacer.dmz.smartrafficenter.org> References: <Pine.GSO.4.32.0208091409570.6242-100000@nippur.irb.hr> <20020809091008.A87124@unixdaemons.com> <20020809164411.GC78503@pacer.dmz.smartrafficenter.org>
next in thread | previous in thread | raw e-mail | index | archive | help
"Kevin A. Pieckiel" <kpieckiel-freebsd-stable@smartrafficenter.org> probably said: > A few questions on this issue. First, what was the reasoning behind > making the whole kernel a critical code segment? I can't think of > any reason kernel developers would have to design the kernel this > way, shy of sheer laziness or such profound architectural changes > being necessary to impliment it otherwise. The BSD code branch that FreeBSD is based on is pretty old, it was written long before kernel threads were an issue. It's been improved on greatly since then but FreeBSD 4.x is still based on that structure. You can do multiprocessor with a giant kernel lock. It's not particularly efficient but it allows for use of multiple processors and if you are doing mostly user space processor work it's still a big advantage. SunOS 4.x did the same thing. One of the reasons for FreeBSD 5.x is the kernel redesign for threads, it's a major chunk of work that isn't perfect yet but will allow for 5.x to have vastly improved SMP support and it would be a prohibitively large amount of work to port it back to 4.x. P. -- pir pir-sig@pir.net pir-sig@net.tufts.edu To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20020809165652.GA4584>