From owner-freebsd-current@FreeBSD.ORG Thu Oct 13 11:36:06 2011 Return-Path: Delivered-To: current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id CA5DF10656AA; Thu, 13 Oct 2011 11:36:06 +0000 (UTC) (envelope-from des@des.no) Received: from smtp.des.no (smtp.des.no [194.63.250.102]) by mx1.freebsd.org (Postfix) with ESMTP id 8C6738FC16; Thu, 13 Oct 2011 11:36:06 +0000 (UTC) Received: from ds4.des.no (des.no [84.49.246.2]) by smtp.des.no (Postfix) with ESMTP id 9E7111FFC33; Thu, 13 Oct 2011 11:36:05 +0000 (UTC) Received: by ds4.des.no (Postfix, from userid 1001) id 8178BB93C; Thu, 13 Oct 2011 13:36:05 +0200 (CEST) From: =?utf-8?Q?Dag-Erling_Sm=C3=B8rgrav?= To: Alexander Motin References: <86bou59gpf.fsf@ds4.des.no> <4E83186C.4080707@FreeBSD.org> <86botmjf7p.fsf@ds4.des.no> Date: Thu, 13 Oct 2011 13:36:05 +0200 In-Reply-To: <86botmjf7p.fsf@ds4.des.no> ("Dag-Erling =?utf-8?Q?Sm=C3=B8rg?= =?utf-8?Q?rav=22's?= message of "Wed, 12 Oct 2011 19:24:10 +0200") Message-ID: <86lispaztm.fsf@ds4.des.no> User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/23.3 (berkeley-unix) MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Cc: current@freebsd.org Subject: Re: 9 hangs with idletick = 0 X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 13 Oct 2011 11:36:06 -0000 Dag-Erling Sm=C3=B8rgrav writes: > I've just built a kernel with KTR support, and with KTR_SPARE2, KTR_INTR > and KTR_SCHED enabled by default. I'll see what turns up. I'm also > going to try machdep.idle=3Dhlt with kern.eventtimer.idletick=3D0, and us= ing > a PCI re(4) instead of the on-board msk(4) while running with default > settings. Great, the bug does not occur when KTR is enabled. The machine has been up for 14+ hours without crashing, despite plenty of network activity, which usually triggers a freeze within minutes. It looks like there may still be short freezes (a few seconds at a time). I'm thinking of instrumenting fetch(1) to record any instances of fread() taking more than, say, half a second. DES --=20 Dag-Erling Sm=C3=B8rgrav - des@des.no