From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wg0-f41.google.com (mail-wg0-f41.google.com [74.125.82.41]) by dpdk.org (Postfix) with ESMTP id 492C7137D for ; Wed, 9 Apr 2014 14:22:09 +0200 (CEST) Received: by mail-wg0-f41.google.com with SMTP id n12so2352272wgh.0 for ; Wed, 09 Apr 2014 05:23:46 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:to:cc:subject:date:message-id:organization :user-agent:in-reply-to:references:mime-version :content-transfer-encoding:content-type; bh=diHXTIW8w0yzOa/OJNSOduw6V4Hn3P1sljdilxibmRY=; b=QIkAiZ994+RGpKJ4EZeU9iMx1LZGU3wN1L9hVxFcPNSy9GZUyGsaXcKOgT4NIy6Jmc r5DxIu7MTxozvPhL2KW0T62C4AJQEk8aJSW106cqDhDK09DgNrMWl+mYlJ+5h1q+PQ/n 9FbZPFsbuO9nMs5OD7sheBezHoQmBluU+kTchBEKNXKotNChtQUl9ePXGhQtgtVpwLY8 VBCDMXCJpI9mKOpoin+1yrFlvNDdvUk85TH4bxqSBWm2/S8yTxC+FGUWlQlKwOa+fRjt sibHET3eduhBzZVNqVIQbVxL7Kh0SIN0GBOxiSMq5+PVpEv+2TvpMlvApZMYST3oM/yl /Gcg== X-Gm-Message-State: ALoCoQk8gUMA1D67+HO8VbrcBA3C77msPIAYnrv0V49T7aw7xCkAZ4Tv+iIi4Szk65g9+6mz8t+/ X-Received: by 10.180.188.130 with SMTP id ga2mr37412122wic.18.1397046225847; Wed, 09 Apr 2014 05:23:45 -0700 (PDT) Received: from xps13.localnet (6wind.net2.nerim.net. [213.41.180.237]) by mx.google.com with ESMTPSA id or5sm1468965wjc.2.2014.04.09.05.23.44 for (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Wed, 09 Apr 2014 05:23:45 -0700 (PDT) From: Thomas Monjalon To: Bruce Richardson Date: Wed, 09 Apr 2014 14:23:44 +0200 Message-ID: <1530885.SuHPsB8m1S@xps13> Organization: 6WIND User-Agent: KMail/4.12.3 (Linux/3.13.7-1-ARCH; KDE/4.12.3; x86_64; ; ) In-Reply-To: <1396875448-14778-1-git-send-email-bruce.richardson@intel.com> References: <1396875448-14778-1-git-send-email-bruce.richardson@intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: 7Bit Content-Type: text/plain; charset="us-ascii" Cc: dev@dpdk.org Subject: Re: [dpdk-dev] [PATCH] Revert "timer: get TSC frequency from /proc/cpuinfo" X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 09 Apr 2014 12:22:09 -0000 2014-04-07 13:57, Bruce Richardson: > This reverts commit da6fd0759cbeb5fc14991a79e40105b9f6b99059. > > The use of cpuinfo to determine the frequency of the TSC is not > advisable and leads to incorrect results when power management is > in use. This is because, while the TSC frequency does not change > in modern cpus with constant_tsc support, the frequency of the core, > and hence the frequency of the core reported by cpuinfo *does* change. > > Depending on the current frequency of core 0 when an application is > started, the EAL can get a wildly incorrect value for the TSC freq. > Since frequency is scaled down for power saving, any incorrect value > is likely to be lower than the default, which means that any delay > loops inside the code which rely on the TSC will be shorter than > planned. This can cause issues (reported on the mailing list by a number > of people) where ports are not initialized correctly due to delays being > too short. > > Signed-off-by: Bruce Richardson I agree that using CPU frequency for TSC calibration is wrong with constant_tsc support. The goal was to have a precise calibration but the result is the reverse because of constant TSC. Acked and applied. Thank you Bruce for catching this. -- Thomas