Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756103AbZKIPbl (ORCPT ); Mon, 9 Nov 2009 10:31:41 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755969AbZKIPbl (ORCPT ); Mon, 9 Nov 2009 10:31:41 -0500 Received: from mail-vw0-f192.google.com ([209.85.212.192]:55167 "EHLO mail-vw0-f192.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755911AbZKIPbk convert rfc822-to-8bit (ORCPT ); Mon, 9 Nov 2009 10:31:40 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc:content-type:content-transfer-encoding; b=j3tf1pNG+uCkL+ygqbFg6VU42cJz6YBhu+S9g50IaY58mWIYH/mUZupgb+NULTZAAw TZBdvD9Mnju624hm7gG1yGcpEDX6xqJlas1Alqq7JQWgGrzziLBOrIuxiP9F8Ua3aHTr cm2F+p92CfGcTHzXoMc5ukVYfKDAVn5WnKeBE= MIME-Version: 1.0 In-Reply-To: <31525.1257770343@redhat.com> References: <7206ef594e67a240a842339f520284de6569b1fc.1257602781.git.andre.goddard@gmail.com> <31525.1257770343@redhat.com> From: =?ISO-8859-1?Q?Andr=E9_Goddard_Rosa?= Date: Mon, 9 Nov 2009 13:31:25 -0200 Message-ID: Subject: Re: To: David Howells Cc: linux list Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1272 Lines: 35 On Mon, Nov 9, 2009 at 10:39 AM, David Howells wrote: > MIME-Version: 1.0 > Content-Type: text/plain; charset=iso-8859-1 > Content-Transfer-Encoding: quoted-printable > > Andr=E9 Goddard Rosa wrote: > >> It decreases code size: >> ? ?text ? ?data ? ? bss ? ? dec ? ? hex filename >> ? 15719 ? ? ? 0 ? ? ? 8 ? 15727 ? ?3d6f lib/vsprintf.o-before >> ? 15543 ? ? ? 0 ? ? ? 8 ? 15551 ? ?3cbf lib/vsprintf.o-after > > Whilst this may be true, there will be a countervailing decrease in > performance. ?Have you assessed that? (trimmed long cc: list to keep it sane, I'll not use get_maintainer.pl output this way anymore) I'm not sure it decreases performance. From the last iteration of the patch, I removed the hint to force "not inlining", so that gcc can inline it if it thinks it's better. Are those so performance sensitive that it makes sense to perform this assessment? If you think so, what would you suggest? A micro-benchmark or some real use case? Best regards, Andr? -- 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/