Date: Sat, 18 Dec 1999 16:35:35 -0800 From: Mike Smith <msmith@freebsd.org> To: Matthew Dillon <dillon@apollo.backplane.com> Cc: freebsd-current@FreeBSD.ORG Subject: Re: Serious server-side NFS problem Message-ID: <199912190035.QAA01419@mass.cdrom.com> In-Reply-To: Your message of "Fri, 17 Dec 1999 21:35:12 PST." <199912180535.VAA67191@apollo.backplane.com>
next in thread | previous in thread | raw e-mail | index | archive | help
> :That's interesting then, since your results are somewhat at odds with > :what I've seen so far regarding interrupt load for network traffic. Do > :you have any profiling results that point the finger more directly at > :anything? > : > :-- > > Ok, here is the kernel gprof output for one of my -current test > boxes. This one is a duel 450 MHz P-III but running a UP kernel, > and a built-in intel ethernet. ... > I've included the entire gprof output below, but the pertainant section > is #8 and #9 indicating that 19.8% of the cpu is being eaten in the > fxp interrupt code. > > The lion's share appears to be fxp_add_rfabuf(), which takes 10% of > the cpu all by itself (see #11), and most of that appears to be in > the splx() code, which seems bogus but that is what it says. I > presume the splimp()/splx() calls it is making are coming from the > MBUF macros. Hmm, interesting. Do you have a 3C905B kicking around there somewhere that you could repeat the profiling run with? I must admit I hadn't had a chance to look at a profile dump using fxp, and this comes as a bit of a surprise. -- \\ Give a man a fish, and you feed him for a day. \\ Mike Smith \\ Tell him he should learn how to fish himself, \\ msmith@freebsd.org \\ and he'll hate you for a lifetime. \\ msmith@cdrom.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199912190035.QAA01419>