Date: Tue, 21 Jan 2003 14:39:08 -0800 From: Terry Lambert <tlambert2@mindspring.com> To: Steve Byan <stephen_byan@maxtor.com> Cc: freebsd-fs@FreeBSD.ORG Subject: Re: JFS vs. Soft Updates (again) (was: Re: large filesystem, journaling filesystem support) Message-ID: <3E2DCC0C.FCAB2EFF@mindspring.com> References: <5777A7A4-2D4E-11D7-962B-00306548867E@maxtor.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Steve Byan wrote: > On Monday, January 20, 2003, at 02:43 PM, Julian Elischer wrote: > > it would be nice if the drive had enough NVram to hold that one trashed > > block so it could rewrite it on powerup. > > If enough customers show up waving dollar bills in their hands ... The disk manufacturers have historically not recognized new markets, until after their competition has already entered them. This was true for 8 inch floppies, 5 Inch floppies, 3 inch floppies, 14 inch fixed disks, 5 inch fixed disks, 3 inch fixed disks, 2.5 inch fixed disks, and the new, quarter size fixed disks. In all cases, the market for these products was a new market (minicomputer, desktop, luggable, minicomputer, desktop, luggable, laptop, cameras/etc.) for which the companies were unprepared, and therefore failed to pursue. How many people remember Shugart or Miniscribe? The problem is that everyone is trying to sell up-market from where they started, as their companies become fat, dumb, and lazy, and therefore require higher margins for the same products. Old companies do not innovate: the decisions that make them profitable make them incapable of anything other than evolutionary, not revolutionary, advances. Don't worry, Open Source Software projects are in exactly the same boat: it requires an entirely different skill set to enter a new market. There's a great book on this: The Innovator's Dilemma Clayton M. Christensen HarperBusiness ISBN: 0-06-662069-4 The hard disk industry is one of his three major examples. 8-). FWIW: the major market you are not seeing here is ATA RAID arrays that can compete with SCSI RAID arrays from other disk vendors, where you can leverage the ATA economyies of scale that make SCSI disks more expensive than ATA disks, in the first place. Basically, the first ATA disk manufacturer to do this will spike much of their competitions SCSI market,as soon as the software types become aware of the change (see below). > > For us the problem is that the drive reports the write as having > > happenned when it hasn't, so teh filesystem dependencies end up being > > smashed, because teh filesystem is writing out data in dependency > > order, > > but if the data is written in a different order to the drive, > > the drive can end up being in error in the case of failure. > > That's the cost of write-behind caching. SCSI gives you enough control > to avoid this problem. ATA disks don't, but at least they're > inexpensive. Which is why people call ATA drives "crap", and disk manufacturers get upset about it: they are competing on size and spindle speed, and somehow seem to have forgotten one of the purposes of their products is to _reliably store data_. The funny thing is that it would cost them nearly nothing, now that they have tagged command queues for ATA drives, to put this feature into ATA drives, as well... in fact, it may even be no more than a firmware hack. > Ick, that could be a big number, maybe a couple of seconds in the very > worst-case, I dunno for sure. I think you're probably talking a UPS > rather than a large filter cap in the power supply. I think it's > technically better to accept that you're not going to get all the data > on the disk when power fails, and supply a "power fail" signal to the > drive a few sector-times in advance of the power going out of the > spec-limits. That way the drive could guarantee that it won't partially > overwrite a sector. That's a really annoying point of view. 8-). The problem with this approach is that it requires cable changes to the drive interface, unless you designate one of the "spare" grounds as being inverse AC present signal; even so, you would not be guaranteed that the motherboard/controller manufacturers have all tied this pin active low in their designs, if it's truly a "spare". That means the disks would not work with some motherboards, which is death in a commodity market. I suspect that this is a good reason that, despite the design being available in your head, no manufacturer has implemented this, even if there was not computer hardware support for it. Basically, this means that we (filesystems engineers) have two wishlist items for disk manufacturers: 1) Add logic to the ATA disks to provide the same control over the ordering of operations (e.g. barriers and completion notification) that SCSI disks have (per the above, this may be nothing more than a firmware hack). 2) Provide the ability to obtain physical geometry information from ATA disks, similar to the information that is returned in SCSI mode page 2. The first can be a "must enable, disabled by default" item, and the second could be a vendor-private command, which keeps both of them from being visible to ignorant users of the disks. If you want to address throwing a chock in the wheels and/or dumping the write queue to on-board NVRAM, assuming an inverse AC fail notification, if it's turned on (off by default to account for floating cable pins, rather than active low, on some motherboards, to avoid sabotaging your existing market), that would be nice too. ;^). -- Terry To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3E2DCC0C.FCAB2EFF>