Date: Sat, 10 Dec 2005 13:14:18 -0800 (PST) From: Danial Thom <danial_thom@yahoo.com> To: Kris Kennaway <kris@obsecurity.org>, David Gerard <fun@thingy.apana.org.au> Cc: freebsd-questions@freebsd.org Subject: Re: Freebsd Theme Song Message-ID: <20051210211418.26194.qmail@web33309.mail.mud.yahoo.com> In-Reply-To: <20051210201601.GB79654@xor.obsecurity.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--- Kris Kennaway <kris@obsecurity.org> wrote: > On Sat, Dec 10, 2005 at 06:00:42PM +0000, David > Gerard wrote: > > Danial Thom wrote: > > > --- David Gerard <fun@thingy.apana.org.au> > wrote: > > >>Danial Thom wrote: > > > > >>>I vote for > > >>>"Look what they've done to my song, Ma" - > a > > >>>commentary on the destruction of the > (formally) > > >>>world's best operating system. > > > > >>So far I'm finding 6.x a heck of a lot > better > > >>than 5.x. The mousewheel > > >>just works, a lot more of the ports just > work, > > >>sound works ... you still > > >> have to fiddle with /boot/loader.conf to > get > > >>the sound to go, which is > > >>completely braindead, but I'm sure it'll be > up > > >>to the standard of Linux > > >>distros 2001. > > > > > I was referring to 4.x vs 5.x+ of course > > > > > > Ah, of course! I agree. > > The thing you have to remember about Denial is > that the ONLY THING he > cares about in an OS is how fast it can route > network packets. The > major improvements in other areas of FreeBSD > are of absolutely no > interest to him, therefore the whole thing is a > waste of time. > > But anyway, FreeBSD 6.0 is hugely superior to > 5.4 and 4.11 in > filesystem performance. I have been measuring > this carefully for the > past couple of months and hope to have the > paper out soon. > > Kris > Well thats just hogwash Kris. Pure bridging performance is a measure of the efficiency of the kernel to do rote tasks like respond to interrupts, and the latencies in performing those tasks. Its the best way, IMO, to exercise and measure the efficiency of an isolated kernel. It requires no userland activity, so your results aren't muddled by millions of system calls. Its a way to compare apples to apples, which is how good testing is done. As long as you don't have your filesystem on a network, you're in good shape. But thats not even the point. The point is that the purpose of tearing apart 4.x was to go MP, and MP performance is dismill across the board. I would expect some things to be a lot better with the 3 years of work, but the goal of having an efficient MP O/S is as far away as it was with 5.1. DT __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20051210211418.26194.qmail>