Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S262453AbUKLFwa (ORCPT ); Fri, 12 Nov 2004 00:52:30 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S262455AbUKLFw3 (ORCPT ); Fri, 12 Nov 2004 00:52:29 -0500 Received: from twinlark.arctic.org ([168.75.98.6]:212 "EHLO twinlark.arctic.org") by vger.kernel.org with ESMTP id S262453AbUKLFw2 (ORCPT ); Fri, 12 Nov 2004 00:52:28 -0500 Date: Thu, 11 Nov 2004 21:52:27 -0800 (PST) From: dean gaudet To: linux-kernel@vger.kernel.org Subject: CONFIG_X86_PM_TIMER is slow Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 767 Lines: 17 when using CONFIG_X86_PM_TIMER i'm finding that gettimeofday() calls take 2.8us on a p-m 1.4GHz box... which is an order of magnitude slower than TSC-based solutions. on one workload i'm seeing a 7% perf improvement by booting "acpi=off" to force it to use tsc instead of the PM timer... (the workload calls gettimeofday too frequently, but i can't change that). i'm curious why other folks haven't run into this -- is it because most systems have HPET timer as well and that's not nearly as bad as PM timer? -dean - 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/