Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 18 Dec 2007 15:04:35 +0100
From:      Bernd Walter <ticso@cicely12.cicely.de>
To:        Poul-Henning Kamp <phk@phk.freebsd.dk>
Cc:        cvs-src@FreeBSD.org, "Bruce M. Simpson" <bms@incunabulum.net>, "Bruce M. Simpson" <bms@FreeBSD.org>, cvs-all@FreeBSD.org, src-committers@FreeBSD.org
Subject:   Re: cvs commit: src/sbin/atacontrol atacontrol.c
Message-ID:  <20071218140435.GI51627@cicely12.cicely.de>
In-Reply-To: <11419.1197903331@critter.freebsd.dk>
References:  <47668B2B.5030206@incunabulum.net> <11419.1197903331@critter.freebsd.dk>

next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Dec 17, 2007 at 02:55:31PM +0000, Poul-Henning Kamp wrote:
> In message <47668B2B.5030206@incunabulum.net>, "Bruce M. Simpson" writes:
> >Poul-Henning Kamp wrote:
> >> I have the attached patch in sos@ mailbox for approval, that adds
> >> BIO_DELETE support for the ata driver.
> >>
> >> I also want to implement a -E option to fsck(8) to erase all
> >> unallocated blocks.
> >>
> >> And finally the big item: msdosfs and ufs support to issue BIO_DELETE
> >> when files are deleted.  UFS is nasty because of soft-updates.
> >>   
> >
> >Aha, I understand now. CFA and SATA vendors have gone off in two 
> >separate directions:
> > * PATA and SATA drives, for a few years now, have tended to rewrite one 
> >cylinder at a time, which implies erasing the data on that cylinder.
> 
> Everybody denies this in the stongest possibly way whenever I ask them,
> so far I have not seen this claim substantiated by any fact or person
> who would be in a position to know.

Not exactly a modern *ATA drive, but the old Commodore 1581 disk drive
used exactly this technology - it always read/write a complete track
of 5120 Bytes.

> > * NAND Flash devices should not have their sectors erased unless 
> >absolutely necessary, to implement wear levelling.
> 
> Wrong, almost exactly the opposite in fact:
> 
> Flash devices using wear-levelling should have data erased as soon as
> possible to give the wear-levelling the maximum amount of information
> and available space to work with.

I'm temptend to implement it for our SD driver as well, once your stuff
is in.
But on the other hand almost everyone is using this driver to handle
UFS root filesystem.

-- 
B.Walter                http://www.bwct.de      http://www.fizon.de
bernd@bwct.de           info@bwct.de            support@fizon.de



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20071218140435.GI51627>