Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755838AbZLCATV (ORCPT ); Wed, 2 Dec 2009 19:19:21 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755616AbZLCATV (ORCPT ); Wed, 2 Dec 2009 19:19:21 -0500 Received: from terminus.zytor.com ([198.137.202.10]:41071 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755563AbZLCATU (ORCPT ); Wed, 2 Dec 2009 19:19:20 -0500 Message-ID: <4B170204.4080604@zytor.com> Date: Wed, 02 Dec 2009 16:10:44 -0800 From: "H. Peter Anvin" User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.4pre) Gecko/20091014 Fedora/3.0-2.8.b4.fc11 Thunderbird/3.0b4 MIME-Version: 1.0 To: Rodolfo Giometti CC: linux-kernel@vger.kernel.org, Andrew Morton , David Woodhouse , Dave Jones , Sam Ravnborg , Greg KH , Randy Dunlap , Kay Sievers , Alan Cox , Ingo Molnar , Michael Kerrisk , Christoph Hellwig Subject: Re: [PATCH 09/11] pps: low level IRQ timestamps recording. References: <1259774329-29663-1-git-send-email-giometti@linux.it> <1259774329-29663-2-git-send-email-giometti@linux.it> <1259774329-29663-3-git-send-email-giometti@linux.it> <1259774329-29663-4-git-send-email-giometti@linux.it> <1259774329-29663-5-git-send-email-giometti@linux.it> <1259774329-29663-6-git-send-email-giometti@linux.it> <1259774329-29663-7-git-send-email-giometti@linux.it> <1259774329-29663-8-git-send-email-giometti@linux.it> <1259774329-29663-9-git-send-email-giometti@linux.it> <1259774329-29663-10-git-send-email-giometti@linux.it> In-Reply-To: <1259774329-29663-10-git-send-email-giometti@linux.it> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 916 Lines: 24 On 12/02/2009 09:18 AM, Rodolfo Giometti wrote: > Add low level IRQ timestamps recording for x86 (32 and 64 bits) > platforms and enable UART clients in order to use it. > > This improves PPS precision. :) It also invokes getnstimeofday on every single interrupt, including ones which have absolutely nothing to do with the PPS, and are potentially high volume. getnstimeofday can be a fairly expensive operation, especially if the best available clock is away from the CPU, or it requires extensive arithmetic in order to normalize the clock value... -hpa -- H. Peter Anvin, Intel Open Source Technology Center I work for Intel. I don't speak on their behalf. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/