From owner-freebsd-firewire@FreeBSD.ORG Wed Jan 27 05:20:03 2010 Return-Path: Delivered-To: freebsd-firewire@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 32EB4106566C for ; Wed, 27 Jan 2010 05:20:03 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 211268FC14 for ; Wed, 27 Jan 2010 05:20:03 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.3/8.14.3) with ESMTP id o0R5K3WZ089341 for ; Wed, 27 Jan 2010 05:20:03 GMT (envelope-from gnats@freefall.freebsd.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.14.3/8.14.3/Submit) id o0R5K2ek089320; Wed, 27 Jan 2010 05:20:02 GMT (envelope-from gnats) Date: Wed, 27 Jan 2010 05:20:02 GMT Message-Id: <201001270520.o0R5K2ek089320@freefall.freebsd.org> To: freebsd-firewire@FreeBSD.org From: Dieter Cc: Subject: Re: kern/118093: firewire bus reset hogs CPU, causing data to be lost X-BeenThere: freebsd-firewire@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Dieter List-Id: Firewire support in FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 27 Jan 2010 05:20:03 -0000 The following reply was made to PR kern/118093; it has been noted by GNATS. From: Dieter To: freebsd-firewire@freebsd.org, bug-followup@freebsd.org Cc: Subject: Re: kern/118093: firewire bus reset hogs CPU, causing data to be lost Date: Tue, 26 Jan 2010 10:56:30 PST > Looks like the kernel printf takes a *lot* of CPU, and > somehow locks out Ethernet. Looking through man pages working on an unrelated problem, I found: man timed says: Messages printed by the kernel on the system console occur with inter- rupts disabled. This means that the clock stops while they are printing. A machine with many disk or network hardware problems and consequent mes- sages cannot keep good time by itself. Each message typically causes the clock to lose a dozen milliseconds. If a kernel printf disables Ethernet interrupts for 12 milliseconds, that would create the problem.