Date: Sat, 07 Nov 1998 18:27:00 -0800 From: Mike Smith <mike@smith.net.au> To: John Capo <jc@irbs.com> Cc: smp@FreeBSD.ORG, current@FreeBSD.ORG Subject: Re: Dog Sloooow SMP Message-ID: <199811080227.SAA01132@dingo.cdrom.com> In-Reply-To: Your message of "Thu, 05 Nov 1998 15:36:07 EST." <19981105153607.32581@irbs.com>
next in thread | previous in thread | raw e-mail | index | archive | help
> Quoting Mike Smith (mike@smith.net.au): > > > Turns out that SMP broke for me on 5/21/98 in identcpu.c version > > > 1.47 when code was added to identify PIIs. Not setting cpu = CPU_II > > > fixes the problem. > > > > > > I suspect the real breakage is in pmap.c where cpu is used. > > > > If you change all of the 'cpu == CPU_686' tests to include CPU_PII, do > > you get your performance back? It looks like at the very least it will > > be costing you some performance optimisations. > > > > Restoring cpu = CPU_PII in indentcpu.c and testing for CPU_686 and > CPU_PII in pmap.c does fix the problem. > > I have an LX chipset and 233 Mhz PIIs bought around April of this > year. I wonder why noone else has seen this problem. No idea. I've received verification that fixing this for all 686-class CPUs seems to work (ie. it's OK on the Cyrix MII and doesn't appear to impact performance there), so the tests are now generalised for the entire 686-class. I hope this resolves your problems. -- \\ Sometimes you're ahead, \\ Mike Smith \\ sometimes you're behind. \\ mike@smith.net.au \\ The race is long, and in the \\ msmith@freebsd.org \\ end it's only with yourself. \\ msmith@cdrom.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199811080227.SAA01132>