Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 17 Dec 2005 12:25:49 +0100
From:      Mathieu Arnold <mat@mat.cc>
To:        Poul-Henning Kamp <phk@phk.freebsd.dk>
Cc:        Alexandre DELAY <alexandre.delay@free.fr>, freebsd-hardware@freebsd.org
Subject:   Re: HDD 
Message-ID:  <5C66F3C40FAC63FB21A0C626@cc-126-240.int.t-online.fr>
In-Reply-To: <23984.1134816906@critter.freebsd.dk>
References:  <23984.1134816906@critter.freebsd.dk>

next in thread | previous in thread | raw e-mail | index | archive | help
+-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



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?5C66F3C40FAC63FB21A0C626>