From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <thomas.monjalon@6wind.com>
Received: from mail-wg0-f52.google.com (mail-wg0-f52.google.com [74.125.82.52])
 by dpdk.org (Postfix) with ESMTP id BE18C58D2
 for <dev@dpdk.org>; Mon, 27 Jan 2014 10:56:37 +0100 (CET)
Received: by mail-wg0-f52.google.com with SMTP id b13so5334925wgh.7
 for <dev@dpdk.org>; Mon, 27 Jan 2014 01:57:55 -0800 (PST)
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
 d=1e100.net; s=20130820;
 h=x-gm-message-state:from:organization:to:subject:date:user-agent:cc
 :references:in-reply-to:mime-version:content-type
 :content-transfer-encoding:message-id;
 bh=/2eIh7JYc74P8+8Ryho+jVhr6xIdjwN5FAcQTRIDnFA=;
 b=eFzVbCSU246KORvq3n2TMQfb0tNAe3SPaI/hmqHGG+FrpGsCf0pVnhHRdn+v9DKh9O
 PteIFzI1fcoEkDGPBym408HCjPuldbwKt2LTsiRjznB8m5Bb/KQP57Qwd5fFjgcDRfEY
 LTNSnGfwSVjJemOiCx/KnGnKOgY9N6QdGeQwy4JIRU4SFRs/9jmllQxrf+miIx8OXBGF
 rq2D9gEMoPnZylz2jYYZNqHwhy7+/ZtUpm3bm9ch6CW9TXTL0I5Vi7tm/F3ler7Np8JE
 qq0Vc0kWWKtbHiOjpm/Poi2cYCjBbviAX6/uc7Pv5jRGUynC6Jvxuo4Owpz8suwroxFR
 bllQ==
X-Gm-Message-State: ALoCoQmXvuyzVe0dWIluXXffAv5elkFY5IQOTMJiPIAGU0SN43cr8cIIIjLq+40OvwQ+V7CKlU+p
X-Received: by 10.180.189.10 with SMTP id ge10mr11275893wic.47.1390816674806; 
 Mon, 27 Jan 2014 01:57:54 -0800 (PST)
Received: from angus.localnet (6wind.net2.nerim.net. [213.41.180.237])
 by mx.google.com with ESMTPSA id ey3sm27854853wib.4.2014.01.27.01.57.53
 for <multiple recipients>
 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128);
 Mon, 27 Jan 2014 01:57:53 -0800 (PST)
From: Thomas Monjalon <thomas.monjalon@6wind.com>
Organization: 6WIND
To: "=?iso-8859-1?q?Fran=E7ois-Fr=E9d=E9ric?= Ozog" <ff@ozog.com>,
 "'Didier Pallard'" <didier.pallard@6wind.com>
Date: Mon, 27 Jan 2014 10:57:52 +0100
User-Agent: KMail/1.13.7 (Linux/3.2.0-4-amd64; KDE/4.8.4; x86_64; ; )
References: <1390562277-24769-1-git-send-email-didier.pallard@6wind.com>
 <00d201cf18f9$67cdaf10$37690d30$@com>
In-Reply-To: <00d201cf18f9$67cdaf10$37690d30$@com>
MIME-Version: 1.0
Content-Type: Text/Plain;
  charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Message-Id: <201401271057.52251.thomas.monjalon@6wind.com>
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH] timer: add lfence before TSC read
X-BeenThere: dev@dpdk.org
X-Mailman-Version: 2.1.15
Precedence: list
List-Id: patches and discussions about DPDK <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
 <mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
 <mailto:dev-request@dpdk.org?subject=subscribe>
X-List-Received-Date: Mon, 27 Jan 2014 09:56:38 -0000

24/01/2014 12:42, Fran=E7ois-Fr=E9d=E9ric Ozog:
> IMHO, adding the lfence for all cases is introducing an un-necessary
> performance penalty.
>=20
> What about adding rte_rdtsc_sync() or rte_rdtsc_serial() with the comment
> about the rdtsc instruction behavior so that developers can choose which
> form they want?

Yes it could be a good idea in some cases. Didier, could you try to add suc=
h=20
function ?

But in some debugging cases we need to have high precision for almost all=20
timestamps. Here I don't know what is the smartest solution.

Thank you for commenting. Hope we'll find a good fix.
=2D-=20
Thomas