From: Willy Tarreau <w@1wt.eu>
To: Artem Bityutskiy <dedekind@yandex.ru>
Cc: "H. Peter Anvin" <hpa@zytor.com>,
"Andi Kleen" <andi@firstfloor.org>,
"Tomasz Chmielewski" <mangoo@wpkg.org>,
LKML <linux-kernel@vger.kernel.org>,
penberg@cs.helsinki.fi, "Jörn Engel" <joern@logfs.org>,
ext-adrian.hunter@nokia.com, jwboyer@gmail.com
Subject: Re: UBIFS vs Logfs (was [RFC PATCH] UBIFS - new flash file system)
Date: Wed, 2 Apr 2008 08:25:43 +0200 [thread overview]
Message-ID: <20080402062543.GA5950@1wt.eu> (raw)
In-Reply-To: <47F30FDD.5080003@yandex.ru>
On Wed, Apr 02, 2008 at 07:47:25AM +0300, Artem Bityutskiy wrote:
> Willy Tarreau wrote:
> >>Well, even auto-levelling storage should benefit from a filesystem which
> >>minimizes the total number of flash sectors churned, which means doing
> >>as few writes as possible and to large, contiguous sections.
> >
> >Exactly. At exosec, we ship one appliance which writes statistics to a
> >partition on a compactflash every 5 minutes. We preferred to go with JFFS2
> >exactly because of this reason. We never had any problem proceeding this
> >way.
> >I'm not sure if it would have been the same with ext2 though.
> >
>
> Yes, as I agreed in a previous mail this may make sense in some cases.
>
> But in general it is not a good approach. Basically, it is wastage of
> resources.
> Indeed, first the firmware on MMC/SD/etc makes efforts to make flash look
> like a block device. It gives you in-place updates,
One of the problem is that unless you crash-test your flash cards, you will
never know if their wear-leveling algorithm is fine or not. And I suspect
that nowadays, due to very large consumer demand, flash cards price drop
at the cost of reliability. I think that most of those not flagged
"industrial-grade" do absolutely zero wear-leveling, because they are sold
to people using them in digital cameras, and they will never kill their
device with such a usage.
> but by cost of performance
> and reliability. Then you just drop this nice property, and use JFFS2, which
> assumes it has only out-of-place updates. But if this solves the task you
> have
I'm certainly not the only one with this requirement. A lot of embedded
motherboards come with IDE compactflash connectors. This is very convenient,
but if you need to keep informations between reboots, you have to write to
the device anyway. If you need to do that very often, either you pray for
the device to be very reliable, or you take all the chances on your side
by adding your own wear-leveling "just in case".
Cheers,
Willy
next prev parent reply other threads:[~2008-04-02 6:26 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-04-01 8:02 UBIFS vs Logfs (was [RFC PATCH] UBIFS - new flash file system) Tomasz Chmielewski
2008-04-01 8:45 ` Artem Bityutskiy
2008-04-01 9:03 ` Jörn Engel
2008-04-01 9:09 ` Artem Bityutskiy
2008-04-01 9:31 ` Jörn Engel
2008-04-01 9:39 ` Tomasz Chmielewski
2008-04-01 9:57 ` Artem Bityutskiy
2008-04-02 14:17 ` Tomasz Chmielewski
2008-04-02 14:22 ` Jörn Engel
2008-04-01 11:06 ` Andi Kleen
2008-04-01 11:23 ` Artem Bityutskiy
2008-04-01 16:27 ` H. Peter Anvin
2008-04-01 21:26 ` Willy Tarreau
2008-04-02 4:47 ` Artem Bityutskiy
2008-04-02 6:25 ` Willy Tarreau [this message]
2008-04-02 7:17 ` Artem Bityutskiy
2008-04-09 21:09 ` Pavel Machek
2008-04-09 21:32 ` Jörn Engel
-- strict thread matches above, loose matches on Subject: below --
2008-03-27 14:55 [RFC PATCH] UBIFS - new flash file system Artem Bityutskiy
2008-03-31 12:29 ` Jan Engelhardt
2008-03-31 12:47 ` Adrian Hunter
2008-03-31 13:20 ` Jörn Engel
2008-04-01 5:26 ` UBIFS vs Logfs (was [RFC PATCH] UBIFS - new flash file system) Artem Bityutskiy
2008-04-01 5:28 ` Artem Bityutskiy
2008-04-01 5:56 ` Artem Bityutskiy
2008-04-01 9:25 ` Jörn Engel
2008-04-01 9:39 ` Artem Bityutskiy
2008-04-01 10:51 ` Jörn Engel
2008-04-01 11:17 ` Artem Bityutskiy
2008-04-01 9:19 ` Jörn Engel
2008-04-01 9:46 ` Artem Bityutskiy
2008-04-01 11:16 ` Jörn Engel
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20080402062543.GA5950@1wt.eu \
--to=w@1wt.eu \
--cc=andi@firstfloor.org \
--cc=dedekind@yandex.ru \
--cc=ext-adrian.hunter@nokia.com \
--cc=hpa@zytor.com \
--cc=joern@logfs.org \
--cc=jwboyer@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mangoo@wpkg.org \
--cc=penberg@cs.helsinki.fi \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.