Date: Wed, 9 Apr 2003 21:31:05 +0200 (CEST) From: Harti Brandt <brandt@fokus.fraunhofer.de> To: Luigi Rizzo <rizzo@icir.org> Cc: John Polstra <jdp@polstra.com> Subject: Re: realtime problem Message-ID: <20030409212923.J1322@beagle.fokus.fraunhofer.de> In-Reply-To: <20030409121408.A23344@xorpc.icir.org> References: <20030409114957.GN83126@cicely9.cicely.de> <200304091900.h39J0igT063938@strings.polstra.com> <20030409121408.A23344@xorpc.icir.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 9 Apr 2003, Luigi Rizzo wrote: LR>On Wed, Apr 09, 2003 at 12:00:44PM -0700, John Polstra wrote: LR>... LR>> Huh? I'm not aware of any hz-related botches in the mii code. LR>> Could you give me a specific example? I'd like to fix it if I can LR>> find it. LR> LR>it is not hz-related, the fact is that some PHY events are LR>handled by busy-waiting in the interrupt service routine LR>thus causing unpredictable latencies in the response to LR>interrupts. Well, in this case it is not exacly what one would call an 'event'. It's the periodcally called status update routine and this routine botches the callout timing because it cannot generate the minimum timing that MII requires. harti -- harti brandt, http://www.fokus.fraunhofer.de/research/cc/cats/employees/hartmut.brandt/private brandt@fokus.fraunhofer.de, harti@freebsd.org
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030409212923.J1322>