Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 15 Sep 1997 08:29:59 +0200
From:      j@uriah.heep.sax.de (J Wunsch)
To:        hackers@FreeBSD.ORG
Subject:   Re: Do *you* have problems with floppies?
Message-ID:  <19970915082959.QR50985@uriah.heep.sax.de>
In-Reply-To: <199709142144.OAA22143@usr09.primenet.com>; from Terry Lambert on Sep 14, 1997 21:44:33 %2B0000
References:  <19970914142654.GG28248@uriah.heep.sax.de> <199709142144.OAA22143@usr09.primenet.com>

next in thread | previous in thread | raw e-mail | index | archive | help
As Terry Lambert wrote:

> Actually, I'm a bit fearful: what happens to a motherboard DMA, as
> in the floppy transfers, during an Interrupt?

Nothing.  Interrupts are a matter of the CPU, but the CPU doesn't own
the bus while the DMA transfer happens.  Of course, the CPU own the
bus between the transfers. ;-)  (There's just one byte of DMA transfer
each several microseconds.)

>  During a controller
> initiated bus master DMA?

Bus master DMAs prioritize as other DMAs.  The AHA1540 series was
known to sometimes hog the bus for too long, causing DMA overrun
errors in the floppy controller.  That's why we retry DMA overruns
forever.  I haven't heard any complaint for newer controllers.

Of course, floppy tapes suffer way more from this.

> Actually... 0x42 READ TRACK does not check the sector number stored in
> the ID field.  This could be a curse as well as a blessing; I don't
> know how it could deal with interleaved data.

You apparently don't know much about this command at all. :-)  Trust
me, i've been using it once (in CP/M), it's only useful as a debugging
tool, nothing else.

> > For filesystem operation, it can indeed be a win.
> 
> Yes.  But you're right that it's not a good enough reason to do it.
> My reasoning was to take the timing issue out of the scheduler and
> interrupt processing in the OS, and give them over to the floppy
> controller in the hopes that it would resolve the problems people
> are seeing.

Btw., Tor Egge meanwhile confirmed that his motherboard/chipset is
broken.

-- 
cheers, J"org

joerg_wunsch@uriah.heep.sax.de -- http://www.sax.de/~joerg/ -- NIC: JW11-RIPE
Never trust an operating system you don't have sources for. ;-)



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19970915082959.QR50985>