Date: Fri, 13 Sep 2002 10:15:10 +0300 From: Danny Braniss <danny@cs.huji.ac.il> To: John Baldwin <jhb@FreeBSD.org> Cc: Brooks Davis <brooks@one-eyed-alien.net>, freebsd-hackers@FreeBSD.ORG, Doug White <dwhite@gumbysoft.com> Subject: Re: AP #1 (PHY# 6) failed! Message-ID: <E17pkfW-00065i-00@cse.cs.huji.ac.il> In-Reply-To: Message from John Baldwin <jhb@FreeBSD.org> of "Thu, 12 Sep 2002 16:11:57 EDT." <XFMail.20020912161157.jhb@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
> The method in which we kick the AP's to wake them up might not be quite > right. We have some hacks to handle erratic behavior on older CPU's > (P5's and PentiumPro's) that perhaps the P4 chips don't like. Could > someone with one of these boards try an SMP kernel from current? Peter > has done some changes related to PSE and PG_G on current that might have > an effect. Also, could people try using 'options DISABLE_PSE' and see > if that happens to make a difference? report: 1- compiled an smp kernel (-current from about DP1/June): failes like -stable 2- stable with DISABLE_PSE failes 3- current as of yesterday (12th of September). failes like -stable 4- like 3 but with 'options DISABLE_PSE' failes like -stable btw, i switched cpus around, so i don't think the cpu is to blame. any other help i can supply, just ask, danny To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?E17pkfW-00065i-00>