From owner-freebsd-net@FreeBSD.ORG Wed Dec 11 20:14:35 2013 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 9CFC5C1B for ; Wed, 11 Dec 2013 20:14:35 +0000 (UTC) Received: from mail-qc0-x22e.google.com (mail-qc0-x22e.google.com [IPv6:2607:f8b0:400d:c01::22e]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (No client certificate requested) by mx1.freebsd.org (Postfix) with ESMTPS id 598F91378 for ; Wed, 11 Dec 2013 20:14:35 +0000 (UTC) Received: by mail-qc0-f174.google.com with SMTP id n7so5557249qcx.33 for ; Wed, 11 Dec 2013 12:14:34 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date:message-id:subject :from:to:cc:content-type; bh=Lm3OQIAvXWS21hMW4d5No1sCTzPVMVN3USpNwBA46C8=; b=0+eNXgtT1CvKwB3ejoxZHzj5QXYQ5zN72JQMQ9mINJ8+W5hmG3cNmm+kg+xObHV4iL u7CMTGhQc8NGwUt3vL5yrOqSv9SsZcMMXazD/bp2MJ4T9aTKqr0J00kDHg51xCyNWtO3 AB7FC3aHIqq+7UMObC/a6u4TSTVPIbRoAMvOfWB3Hk6ROesZ/91BWJzCcdsJU4SsdMxS iUulgxwx5bRWOvdZSd8TNuVeZ77mq5wmb+vRwBicX6M5AlyNdcwn6v5NGXOnJgZUW/5Q r50DCPik2N+7iDL6qb7T1U3owVhqFokxhZOfckD3eCuLj+cBPTWvWQ5u/r/cWIaKOWtg Rl2g== MIME-Version: 1.0 X-Received: by 10.224.80.129 with SMTP id t1mr5996715qak.95.1386792874421; Wed, 11 Dec 2013 12:14:34 -0800 (PST) Sender: adrian.chadd@gmail.com Received: by 10.224.53.200 with HTTP; Wed, 11 Dec 2013 12:14:34 -0800 (PST) In-Reply-To: <20131212031440.692889f7.eocallaghan@alterapraxis.com> References: <1386634847.38473.YahooMailNeo@web121606.mail.ne1.yahoo.com> <1386697668.8944.57916449.7576FC53@webmail.messagingengine.com> <7BE40656-3BF7-4D16-9E8F-392E612093D1@FreeBSD.org> <20131212031440.692889f7.eocallaghan@alterapraxis.com> Date: Wed, 11 Dec 2013 12:14:34 -0800 X-Google-Sender-Auth: 4FBfIVfeRYIqMetkX_XuGqGKEVs Message-ID: Subject: Re: Intel Controllers [Rant] From: Adrian Chadd To: "Edward O'Callaghan" Content-Type: text/plain; charset=ISO-8859-1 Cc: FreeBSD Net X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.17 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 11 Dec 2013 20:14:35 -0000 Current hardware for the most part gets rushed out to meet marketing schedules and marketing requirements. A lot of the time there are bugs that can't be fixed and are pushed out until the next chip run. Some bugs can be fixed by just changes to a final metal layer. Some bugs can be fixed by PROM mask bit changes that twiddle various internal bits in the chip (eg disabling/enabling function specific registers.) Some bugs require a full re-spin of the mask set. All of these happen at schedules that we consumers don't see. That's why you'll see this kind of seemingly schizophrenic behaviour. There may be one controller chip under the hood for a large number of silicon revisions but with features enabled/disabled, bugs fixed/reintroduced, etc. The irony is this - if they wanted to make perfect(er) chips, they'd end up spending so long and dumping so much money into it that it'd be unprofitable. Remember, CPUs are perfect(ish!) because we spend a lot more on them per chip than most ethernet controller chips, which I bet are measured in unit costs of a small number of dollars to begin with for the high end chips, and fractions of a dollar for what goes into laptops.. 2c, -adrian