From fork-admin@xent.com Mon Sep 2 13:13:38 2002 Return-Path: Delivered-To: yyyy@localhost.netnoteinc.com Received: from localhost (localhost [127.0.0.1]) by phobos.labs.netnoteinc.com (Postfix) with ESMTP id 8512B47C86 for ; Mon, 2 Sep 2002 07:46:29 -0400 (EDT) Received: from phobos [127.0.0.1] by localhost with IMAP (fetchmail-5.9.0) for jm@localhost (single-drop); Mon, 02 Sep 2002 12:46:29 +0100 (IST) Received: from xent.com ([64.161.22.236]) by dogma.slashnull.org (8.11.6/8.11.6) with ESMTP id g8200sZ09145 for ; Mon, 2 Sep 2002 01:00:54 +0100 Received: from lair.xent.com (localhost [127.0.0.1]) by xent.com (Postfix) with ESMTP id 7A51A2940BB; Sun, 1 Sep 2002 16:58:02 -0700 (PDT) Delivered-To: fork@example.com Received: from mithral.com (watcher.mithral.com [204.153.244.1]) by xent.com (Postfix) with SMTP id BF835294099 for ; Sun, 1 Sep 2002 16:57:08 -0700 (PDT) Received: (qmail 2826 invoked by uid 1111); 1 Sep 2002 23:59:24 -0000 From: "Adam L. Beberg" To: Bill Stoddard Cc: "Fork@Xent.Com" Subject: RE: Gasp! In-Reply-To: Message-Id: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: fork-admin@xent.com Errors-To: fork-admin@xent.com X-Beenthere: fork@example.com X-Mailman-Version: 2.0.11 Precedence: bulk List-Help: List-Post: List-Subscribe: , List-Id: Friends of Rohit Khare List-Unsubscribe: , List-Archive: Date: Sun, 1 Sep 2002 16:59:24 -0700 (PDT) X-Pyzor: Reported 0 times. X-Spam-Status: No, hits=-10.2 required=7.0 tests=AWL,EMAIL_ATTRIBUTION,IN_REP_TO,KNOWN_MAILING_LIST, QUOTED_EMAIL_TEXT,SPAM_PHRASE_00_01,USER_AGENT_PINE version=2.40-cvs X-Spam-Level: On Sun, 1 Sep 2002, Bill Stoddard wrote: > > > > "Red Hat Linux Advanced Server provides many high end features such as: > > Support for Asynchronous I/O. Now read I/O no longer needs to stall your > > application while waiting for completion." > > Can you provide a reference? I could find it myself but I'm too lazy. Well, i saw it on the Compaq Testdrive site, then had to seriously dig on the redhat site... It's in one of their whitepapers... http://www.redhat.com/pdf/as/as_rasm.pdf > > Could it be? After 20 years without this feature UNIX finally > > catches up to > > Windows and has I/O that doesnt totally suck for nontrivial apps? No way! > > Do /dev/poll and FreeBSD's KQ event driven APIs count? IMHO, true async > io as implemented by Windows 4.0 and beyond is pretty slick, but the > programming model is substantially more complex than programming to an > event API like /dev/poll. And true async does not buy much if the > system call overhead is low (as it is with Linux). I havent used the FBSD poll, as it's not portable, select and poll(still not 100%) are all that exist in the UNIX world. Redhat of course doesnt count as portable either, but it's nice they are trying. The Windows I/O model does definately blow the doors off the UNIX one, but then they had select to point at in it's suckiness and anything would have been an improvement. UNIX is just now looking at it's I/O model and adapting to a multiprocess multithreaded world so it's gonna be years yet before a posix API comes out of it. Bottom line is the "do stuff when something happens" model turned out to be right, and the UNIX "look for something to do and keep looking till you find it no matter how many times you have to look" is not really working so great anymore. - Adam L. "Duncan" Beberg http://www.mithral.com/~beberg/ beberg@mithral.com