From mboxrd@z Thu Jan 1 00:00:00 1970 From: Thomas Monjalon Subject: Re: [PATCH] timer: add lfence before TSC read Date: Mon, 27 Jan 2014 10:57:52 +0100 Message-ID: <201401271057.52251.thomas.monjalon@6wind.com> References: <1390562277-24769-1-git-send-email-didier.pallard@6wind.com> <00d201cf18f9$67cdaf10$37690d30$@com> Mime-Version: 1.0 Content-Type: Text/Plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Cc: dev-VfR2kkLFssw@public.gmane.org To: "=?iso-8859-1?q?Fran=E7ois-Fr=E9d=E9ric?= Ozog" , "'Didier Pallard'" Return-path: In-Reply-To: <00d201cf18f9$67cdaf10$37690d30$@com> List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces-VfR2kkLFssw@public.gmane.org Sender: "dev" 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