Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id ; Mon, 12 Nov 2001 17:26:53 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id ; Mon, 12 Nov 2001 17:26:44 -0500 Received: from postfix2-1.free.fr ([213.228.0.9]:3479 "HELO postfix2-1.free.fr") by vger.kernel.org with SMTP id convert rfc822-to-8bit; Mon, 12 Nov 2001 17:26:34 -0500 Date: Mon, 12 Nov 2001 20:41:24 +0100 (CET) From: =?ISO-8859-1?Q?G=E9rard_Roudier?= X-X-Sender: To: Lionel Bouton Cc: Linus Torvalds , Subject: Re: File System Performance In-Reply-To: <3BF04926.2080009@free.fr> Message-ID: <20011112203504.F1809-100000@gerard> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 12 Nov 2001, Lionel Bouton wrote: > Linus Torvalds wrote: > > >In article <3BF04289.8FC8B7B7@zip.com.au>, > >Andrew Morton wrote: > > > >>It's tar. It cheats. It somehow detects that the > >>output is /dev/null, and so it doesn't read the input files. > >> > > > >Probably the kernel. > > > Seems not the case with gnu tar : write isn't even called once on the fd > returned by open("/dev/null",...). In fact a "grep write" on the strace > output is empty in the "tar cf /dev/null" case. Every file in the tar-ed > tree is stat-ed but no-one is read-ed. This kind of guessing from gnu tar seems utterly stupid to me. Developpers that spend time for such kind of fake optimization either have time to waste or brain to be fixed. Just my opinion. G?rard. - 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/