From owner-freebsd-hackers Sun Sep 14 23:50:33 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id XAA05796 for hackers-outgoing; Sun, 14 Sep 1997 23:50:33 -0700 (PDT) Received: from sax.sax.de (sax.sax.de [193.175.26.33]) by hub.freebsd.org (8.8.7/8.8.7) with SMTP id XAA05790 for ; Sun, 14 Sep 1997 23:50:30 -0700 (PDT) Received: (from uucp@localhost) by sax.sax.de (8.6.12/8.6.12-s1) with UUCP id IAA19184 for hackers@FreeBSD.ORG; Mon, 15 Sep 1997 08:50:29 +0200 Received: (from j@localhost) by uriah.heep.sax.de (8.8.7/8.8.5) id IAA04637; Mon, 15 Sep 1997 08:30:00 +0200 (MET DST) Message-ID: <19970915082959.QR50985@uriah.heep.sax.de> 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? References: <19970914142654.GG28248@uriah.heep.sax.de> <199709142144.OAA22143@usr09.primenet.com> X-Mailer: Mutt 0.60_p2-3,5,8-9 Mime-Version: 1.0 X-Phone: +49-351-2012 669 X-PGP-Fingerprint: DC 47 E6 E4 FF A6 E9 8F 93 21 E0 7D F9 12 D6 4E Reply-To: joerg_wunsch@uriah.heep.sax.de (Joerg Wunsch) In-Reply-To: <199709142144.OAA22143@usr09.primenet.com>; from Terry Lambert on Sep 14, 1997 21:44:33 +0000 Sender: owner-freebsd-hackers@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk 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. ;-)