From owner-freebsd-stable Fri Jun 28 18:31:38 2002 Delivered-To: freebsd-stable@freebsd.org Received: from mx1.FreeBSD.org (mx1.FreeBSD.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B766137B400 for ; Fri, 28 Jun 2002 18:31:33 -0700 (PDT) Received: from web11206.mail.yahoo.com (web11206.mail.yahoo.com [216.136.131.188]) by mx1.FreeBSD.org (Postfix) with SMTP id 6D71143E06 for ; Fri, 28 Jun 2002 18:31:33 -0700 (PDT) (envelope-from victorysoldier@yahoo.com) Message-ID: <20020629013133.68291.qmail@web11206.mail.yahoo.com> Received: from [194.44.215.242] by web11206.mail.yahoo.com via HTTP; Fri, 28 Jun 2002 18:31:33 PDT Date: Fri, 28 Jun 2002 18:31:33 -0700 (PDT) From: Rhett Monteg Hollander Reply-To: alasir@supereva.it Subject: Suspend on HLT problem To: freebsd-stable@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG Hello all, just recently I've noticed some strange thing going with FreeBSD on some SMP box. After some period of time (about an hour, for example), keeping this box booted into FreeBSD and staid just powered on, generally doing nothing (no background or foreground tasks), both CPUs appeared to be very hot (touching heatsink I could figure about 60-70C). But kernel was compiled with 'options CPU_SUSP_HLT', so FreeBSD had to halt both CPUs for quite a long time, thereby keeping them cold. I recompiled the kernel again and again, no difference. Then I made a uni-processing kernel, and booted it for an hour. First (BSP) CPU was still hot, however about 50C, while second (AP) was obviously cold. I can somewhat explain why BSP CPU was hot not so much than in SMP mode, because both CPUs use the same cooling system, but I have no explanation why it was still hot. Finally, I installed Linux and even Win2000 to see any difference. And in both cases, both CPUs were really cold, not exceeding 30-35C. I don't know what's going on. Either suspend on HLT algorithm is not effective, or it's broken at all. Anyone with SMP box can test it simply by booting up, turning coolers off and waiting at least for half an hour. If I'm wrong, your box won't hang up ;) Rhett P.S. FYI, 1) my brain probably performs fine, so 2) I don't live in Central Sahara, hence 3) room temperature was 23C :) __________________________________________________ Do You Yahoo!? Yahoo! - Official partner of 2002 FIFA World Cup http://fifaworldcup.yahoo.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message