From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965620AbXCBVCi (ORCPT ); Fri, 2 Mar 2007 16:02:38 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S965621AbXCBVCi (ORCPT ); Fri, 2 Mar 2007 16:02:38 -0500 Received: from mga06.intel.com ([134.134.136.21]:44845 "EHLO orsmga101.jf.intel.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S965620AbXCBVCh (ORCPT ); Fri, 2 Mar 2007 16:02:37 -0500 X-ExtLoop1: 1 X-IronPort-AV: i="4.14,244,1170662400"; d="scan'208"; a="203418982:sNHT21197358" Subject: system call time increase when turning on CONFIG_PARAVIRT From: Tim Chen Reply-To: tim.c.chen@linux.intel.com To: linux-kernel@vger.kernel.org Content-Type: text/plain Organization: Intel Date: Fri, 02 Mar 2007 12:11:14 -0800 Message-Id: <1172866274.4898.14.camel@localhost.localdomain> Mime-Version: 1.0 X-Mailer: Evolution 2.0.2 (2.0.2-8) Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org With CONFIG_PARAVIRT turned on, I've found that time invoking system_call jumped up quite a lot. Using TCP streaming test as a workload and running on 32-bit 2.6.20 kernel, system_call goes up from 0.00025% all the way to 1.6% in the oprofile data. There is a drop of about 4% in overall throughput for this particular workload. With lmbench's null system call test, the call time goes up from 0.10 usec to 0.225 usec. I'm testing on dual socket Intel core 2 processor running at 2.67 GHz with 4 GB RAM. Tim