From owner-freebsd-smp Mon Dec 2 19:53:02 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id TAA05054 for smp-outgoing; Mon, 2 Dec 1996 19:53:02 -0800 (PST) Received: from spinner.DIALix.COM (root@spinner.DIALix.COM [192.203.228.67]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id TAA05048 for ; Mon, 2 Dec 1996 19:52:53 -0800 (PST) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.3/8.8.3) with ESMTP id LAA01320; Tue, 3 Dec 1996 11:52:39 +0800 (WST) Message-Id: <199612030352.LAA01320@spinner.DIALix.COM> To: Steve Passe cc: freebsd-smp@freefall.freebsd.org Subject: Re: cvs commit: sys/i386/include spl.h In-reply-to: Your message of "Mon, 02 Dec 1996 20:36:52 MST." <199612030336.UAA25088@clem.systemsix.com> Date: Tue, 03 Dec 1996 11:52:39 +0800 From: Peter Wemm Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Steve Passe wrote: > Hi, > > this is more like it, my best time with older working kernel was 269: > > % time make -j8 > ... > 271.22s real 414.10s user 87.29s system > ^^^ ^^^^ ^^^ ^^^^ > > and the "jerkiness" is gone (again, now I remember we had this same symptom > last time we played with 'autostart'...) I still don't know what happened, I'd love to know what's going on. I almost wonder if both cpu's were running as an exact mirror of each other.. Anyway, this is what I hope to diagnose now that we have serial debugging again. > and I think the missing INTs are gone (hope I didn't just jinx that!) Seconded.. :-) Anyway, we're almost back to where we started from before the chaos, except this time the code is #ifdef'ed and we have serial trace code to debug it.. Cheers, -Peter