Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754712AbYJQCUH (ORCPT ); Thu, 16 Oct 2008 22:20:07 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753027AbYJQCTy (ORCPT ); Thu, 16 Oct 2008 22:19:54 -0400 Received: from mga09.intel.com ([134.134.136.24]:17274 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752920AbYJQCTx convert rfc822-to-8bit (ORCPT ); Thu, 16 Oct 2008 22:19:53 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.33,428,1220252400"; d="scan'208";a="452325187" From: "Luck, Tony" To: Mathieu Desnoyers , Linus Torvalds CC: Andrew Morton , Ingo Molnar , "linux-kernel@vger.kernel.org" , "linux-arch@vger.kernel.org" , Steven Rostedt , Peter Zijlstra , Thomas Gleixner , David Miller , Ingo Molnar , "H. Peter Anvin" Date: Thu, 16 Oct 2008 19:19:48 -0700 Subject: RE: [RFC patch 15/15] LTTng timestamp x86 Thread-Topic: [RFC patch 15/15] LTTng timestamp x86 Thread-Index: Ackv98vhCFFLG/bGTIGIikZNPdWGgwABcHTw Message-ID: <57C9024A16AD2D4C97DC78E552063EA3532D455F@orsmsx505.amr.corp.intel.com> References: <20081016232729.699004293@polymtl.ca> <20081016234657.837704867@polymtl.ca> <20081017012835.GA30195@Krystal> In-Reply-To: <20081017012835.GA30195@Krystal> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: acceptlanguage: en-US Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 8BIT MIME-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 990 Lines: 20 > This cache-line bouncing global clock is a best-effort to provide > correct event order in the trace on architectures with unsync tsc. It's > actually better than a global tracing buffer because it limits the > number of cache line transfers required to one per event. Even one line bouncing between cpus can be a performamce disaster. You'll probably hit a serious wall somewhere between 8 and 16 cpus (ia64 has code that looks a lot like this in the gettimeofday() path because it does not synchronize cpu cycle counters ... some applications that are overly fond of timestamping internal events using gettimeofday() end up spending significant time doing so on large systems ... even with only a few thousands of calls per second). -Tony -- 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/