From owner-freebsd-hardware@FreeBSD.ORG Sat Dec 17 11:25:51 2005 Return-Path: X-Original-To: freebsd-hardware@freebsd.org Delivered-To: freebsd-hardware@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A6AD016A41F for ; Sat, 17 Dec 2005 11:25:51 +0000 (GMT) (envelope-from mat@mat.cc) Received: from plouf.absolight.net (plouf.absolight.net [193.30.224.136]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4D0E743D45 for ; Sat, 17 Dec 2005 11:25:51 +0000 (GMT) (envelope-from mat@mat.cc) Date: Sat, 17 Dec 2005 12:25:49 +0100 From: Mathieu Arnold To: Poul-Henning Kamp Message-ID: <5C66F3C40FAC63FB21A0C626@cc-126-240.int.t-online.fr> In-Reply-To: <23984.1134816906@critter.freebsd.dk> References: <23984.1134816906@critter.freebsd.dk> X-Mailer: Mulberry/3.1.6 (Win32) MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline Cc: Alexandre DELAY , freebsd-hardware@freebsd.org Subject: Re: HDD X-BeenThere: freebsd-hardware@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: General discussion of FreeBSD hardware List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 17 Dec 2005 11:25:51 -0000 +-le 17/12/2005 11:55 +0100, Poul-Henning Kamp =E9crivait : | In message <0D162CCAE42F819501B87257@cc-126-240.int.t-online.fr>, Mathieu | Arnol d writes: |> +-le 14/12/2005 17:45 +0100, Alexandre DELAY =3DE9crivait : |>| Don't you think that flash drives are also a good solution? |>| =3D20 |>| I am sure that it will be the future replacement for hard drive disks. |>| see http://www.memtech.com/ for example |>| =3D20 |>| With no buffer and 1ms access delay you minimise write failures. It is an |>| interresting solution. |>=20 |> Hum, flash has a *limited* ammount of possible write for each cell, for = low |> cost, it's between 10K-50K and for heavy duty, industrial grade, bla bla |> bla, it's around 2M, so, hum, just imagine you have a solid state flash |> disk, and your swap on it. One day, your box begins swapping hard, and |> some time later, half of your drive can't be written to again... |=20 | Sorry but that is not how flash devices work. I do remember your NanoBSD talk 3 weeks ago :-) | Yes, you will kill a flash by doing a lot of writes, but it will | not develop individual bad sectors like a disk. but, taking into account that your flash is half filled with real non really changing data, and you have a swap partition, the flash adaptation layer will have the swap space slide on the available space, and it'll wrap up, after many times, it'll eventually have the free space unwritable (unless the flash adaptation layer is smart enough to move non changing data to cell which won't have many more write cycles left and continue to write to almost non used cells). But maybe I have it wrong. --=20 Mathieu Arnold