Slashdot is powered by your submissions, so send in your scoop

 



Forgot your password?
typodupeerror
Check out the new SourceForge HTML5 internet speed test! No Flash necessary and runs on all devices. ×
IBM

IBM sets another disk-drive world record 70

Anonymous Coward writes "IBM has set a new computer data storage world-record of 35.3 billion data bits per square inch on a magnetic hard disk -- a 75 percent increase over the 20-billion-bit milestone the company achieved less than five months ago. " The press release goes on to talk about that this is expected to lead to drives with three times the storage of today, quite soon. Just think - a MP3 server laptop!
This discussion has been archived. No new comments can be posted.

IBM sets another disk-drive world record

Comments Filter:
  • by Anonymous Coward
    Actually, I have the bandwidth for dirty pictures - but it took me three years (of some, say, special interest dirty pictures) to get some 10GB together. I know people who managed somewhat faster, but if you actually want to look at all of them (and in the end, that's what they're for ;-), then you find yourself limited by the bandwidth of your eye-brain-system...
  • You are all thinking in the wrong direction...

    This new density makes for a nice change. The problem with IBMs present Microdrives is that they are too low a capacity to make a big dent in the portable device market. With the new density you get a slightly larger than 2 GB drive with CompactFlash form factor. With that ity-bity drive you can actually start to store a reasonable number of MP3s, a few dozen truly hi-res photos from a digital camera, or for that matter, a full install of RedHat.


    -- Begin thoughtfuly, end insensitively.
  • You're wrong. Five 2 GB disks in a RAID5 configuration would only give you 8GB of storage, since essentially one of the disks must be used for data integrity.

    RAID5 space = (Number of disks - 1) * disk size
  • All is forgiven, my child, all is forgiven. :)
  • I'd like to see this technology put to good use. It would be nice to have a networkable digital camera with a 500MB disk and a web server built in. The storage methods for cameras absolutely suck these days.
  • Personally, I can't wait until HDD (or any other storage media) becomes so cheap and so small that they will be able to put a movie on them and include them free with your box of corn flakes.

    Now that would be a cool promotion!

  • MP3 server laptop? Geez, at the rate we're going we'll be doing this with like the Palm XVII or whatnot in a few years.
    Aww yeeaa.
  • FYI, I've held one of those 340Mb drives in my hands. They are indeed VERY small. Ideal disks for putting into your digital camera. around 170 pictures jpeg-ed to 2Mb per picture at 3600x2400. (Not that you can buy that kind of resolution yet).

    As far as I know, they were imidiately announced as a 170Mb and a 340Mb version. The latter simply has two heads while the first only has one.

    Roger.
  • The only things that are needed to be backed up
    on your personal box are files that you type in with your hands. I do not think you can type fast enough to make a dent even in a 1Gb tape. The rest on your 1Tb hard drive are: a)applications and OS - which are faster to get reinstalled b)Media content (your CDs) that are fault resistant by itself - your CD content has a great deal of redundancy - and can be reinstalled as well.
    The only need for 1Tb backups are in Tb size database business. For that 2K for DLT drive is not a really big deal.

  • Once I get that baby up and running, I want to be able to restore it whole.

    Why? Keep /home separate and backed up, if something wrong, nuke the / and reinstall. In RH (which I use) run autorpm to restore upgrades. It is faster then from tape. (Well, I have and NFS image of the CD, kikckstart diskette and a mirror of all updates again on network. - I do not care what guys in the group did to there system - 15 min and they are back in business - remember there backups can contain the very source of the potential troubles...)

  • Maybe a bit offtopic, but here it goes...

    I personally hope that firewire is soon catching on, because USB 2 is driven by Intel, and therefor, while it has some pretty great specifications, it is also (unlike firewire) CPU-dependant. I bet that is why Intel is pushing USB 2 instead of firewire.

    Tom at Toms Hardware Guide has written a bit about it here:
    http://www.tomshardware.com/editorial/99q3/99091 0/idf-99-01.html

  • You're maybe right about the average desktop user, but that all depends on what the user uses the PC for! Pictures pretty quickly fills up several GB.

    And data storage needs are booming in the industry!

    I can't remember where I've read it, but think about it - companies is storing everything (knowledge is power/money!). They are using datamining, datawarehouses etc. more and more - it takes up lot and lots of disk space!

    It is actually the other way around - the harddisks can't follow the needs!

    Moreover, if you want everything in your home to be runned by you computer, you're going to need much more than 10GB! It will more be like 10TB I think...

    I imagine one day where all my movies, music etc. is on a server (TV-channels is plugged in the server too).

    In all the rooms of my house, where I want to listen to music, a little display is hanging on the wall together with some speakers or in the case of movies or television, a huge flatscreen (of some kind) is hanging on the wall, and the sound would of course be at least DTS surround quality.

    Everything should be connected, so I for example could get a notice when the coffee is ready :-)
    or a bit more seriously: if the temperature gets to high in my refrigerator - gotta make sure the beers are cool :-)
  • This is how I do it at my house. The only windows machine that I use(freebsd/natd firewall and redhat/beos in my room) is in the living room running an ATI all in wonder 128 32 meg video card and the SBlive high end dealie. Piping the display to a nice 32 inch tv, I can use it for vcds/dvds or some really neato open gl plugins for winamp at the occasional party. Kinda slick. Now I jsut need a better reciever and a new set of speakers and I'll be set.

  • Wouldn't Firewire be considered a "cheaper-than-scsi yet very fast transfer method?"
  • Does this mean Microsoft Publisher can finally increase the size of it's extremely useful 38 gig clipart gallery? :)
  • The only things that are needed to be backed up on your personal box are files that you type in with your hands.

    Forgive me for being particularly negative today, but I have to point out how mind-bogglingly wrong this is.

    I generate multimegabyte uncompressed images on a regular basis that I would certainly like to see preserved across disk failures. Not to mention my audio collection (no, not just a pile of replacable MP3s, but my own music), and some captured video.

    I could easily eat up a 2G DAT by backing up my own files. I suspect there are other folks in the same boat.

    (Fortunately, my Promise card comes tomorrow, and I can rebuild /dev/md0 on the file server as a redundant array!)
  • You are all thinking in the wrong direction...

    I beg to differ, if only because I'm cranking out naysaying messages today, but actually for a good reason:

    You're right in thinking that this is a great step forward for miniaturized storage, but it should be plainly obvious that there are currently far more applications for a Huge, Dense Disk than there are for handheld storage.

    I'd love to "actually start to store a reasonable number of MP3s, a few dozen truly hi-res photos from a digital camera," but it's reasonable to assume that the market for digital cameras and MP3 storage is a subset of that for PC system storage.

    Given a choice between a 100G disk and a small sackful of Sony gadgets with portable storage, the 100G disk is personally more useful, or at least flexible.

    So I reiterate that it's incorrect to say people are thinking about the wrong end of this. They're just thinking of the most applicable side of things.

    (And lets face it, CompactFlash may be the leading standard for portable storage, but consumer electronics manufacturers are working overtime to fragment and confuse the market with SmartMedia, MemoryStick, and various other harebrained schemes. Until a form factor and interface standard emerges that manufacturers actually stick to -- and I [wildly] predict this is as much as three years off -- micro-disks are somewhat moot.)
  • Maybe IBM can come up with a 5 platter hard drive that has RAID as a function per-platter, with one platter set for failover.

    Perhaps my life is radically different from your own, but in my experience, platters don't fail. Spindles fail. Firmware fails.

    Redundancy across platters under the same seal doesn't buy you a whole hell of a lot, really. Certainly not much more than good ECC does.
  • Hmmm... we have one set up right now (okay, so it has an external hard drive, but still). The base unit is a sparcbook, hooked up to the ethernet in our dorm room. Solaris is the OS (the only one that will currently boot, since the graphics chipset wasn't supported) and music exported through nfs and samba. 'tis a beautiful thing...
  • As for the first part: w2k won't fill up that much space


    As for the second part: positioning the head isn't a big problem nowadays. There are techniques to do it. The main problems are physical in nature: the drives tend to get too hot, instable and noisy.

    So my prediction is rotation speeds and thus random access times will stay more or less the same. Therefore the data troughput will increase as the head passes over more data in the same time.

  • This is cool for upping capacity on small storage devices, but don't think it'll be a Good Thing for mondo hard drives. I don't care what any bonehead says about 'Real Men Don't Back Up' or 'Just RAID It!' - the bigger the HD, the bigger the hassle. The fatter the drives get, the slower they are to recover from a failure, backup and restore. And you *must* back up - RAID doesn't buy you squat when a 6.7 earthquake drops a block wall on your array.

    Too, as the drives get bigger, they get more inefficient. You're better off with a bunch of small drives anyway - the more spindles turning and heads moving, the better. Talk about data mining! Try gathering data quickly from these babies.

    On the server side, with regard to backup and things like streaming DLT, you're also better off with arrays of small disks. To maintain streaming to tape properly, you've got to have a bunch of spindles cranking.

  • > data transfer rates are very low, 1.2 mbps

    Actually, the maximum should be 12 Mbit/sec, so it's more than 1 MByte/sec.

    Still slow, but not _that_ slow.
  • even if i could get the movie for free, i'd still like to go see it in movie theaters. I haven't seen a single home theater with a 50 foot screen, or the resolution of actual film. Watching star wars (or the matrix) in the front row of a movie theater is an unmatchable expirience. I think after this maybe holly wood will concider puting movies out in theaters, then releasing a dv version on the net about 3 months later-for free, or a really low cost. plus there's merchandise.
    char *stupidsig = "this is my dumb sig";
  • I agree that for most people a 1g tape is plentiful, and that for most WinOS users reinstalling would be best anyway- clears out the cruft, after all.
    However, would I want to go to the trouble of reinstalling a linux system from scratch? Not likely. Once I get that baby up and running, I want to be able to restore it whole.
    But the data picture will be changing as more people use digital video cameras. I'd want to be able to back up all those precious memories.
    There are many potential applications of online video, but if you can't back it up, it's moot. RAID solves this to some degree.
    Tb backups are expensive, though- a 35/70 DLT drive is about $4k, and the multi-tape units are about $20k. Again, multiple hard drives seem to be the solution.
  • Sure but a second, or third or fourth, drive and clone them.

    If your main drive dies you just swap the clone to be the master and you are up and running again with a complete image of what you had as of your last backup.

    Yes this doubles your cost for two drives, plus the cloning software, but at current drive prices you can't really buy a tape drive of the same capacity for much less. And a cloned hard drive is a lot faster, both backing up and restoring.

    If you need more mobile media so you can stor things off site or archivally, try some of the new 8mm or DLT systems that can put 20-40+GB, uncompressed, on a single tape. There are also new tape technologies that have even higher capacities. These devices aren't exactly cheap, but if this is what you need they do the job.
  • According the the PR these drives could hold 50 gigabytes per platter, not total.

    -
    /. is like a steer's horns, a point here, a point there and a lot of bull in between.
  • IBM gives you 5 years warrenty, don't they? If you take two of them, RAID-0 them and wait until they burn, you go to IBM and get your new one :-)
  • I'd like to pack IBM microdrives in to fill up the space of a full-height drive bay, but considering how hot the 2" notebook drives get, I have to wonder whether it's practical to pack 1" drives in contact with each other.

    Now, a 1" high drive with, say, 40 or 50 platters on each of four spindles would be an interesting experiment... Particuarly if you could write to them across a 256-bit parallel bus.

    -jcr
  • I've never had an IBM drive fail on me. Maxtor, Quantum, IOMega, Syquest, and all the rest have gone bad on me, but never IBM.

    Even the instigator of the whole intel/PC train wreck can do *something* right, and disks are what IBM does exceptionally well.

    I'm thrilled at the prospect of being able to buy an audio CD, rip it, and then throw it away.

    -jcr
  • This is a really interesting point. With the music industry at least the musicians don't mind as much if for no other reason than they can make money playing concerts, etc. than selling recordings. When you take it to Hollywood it becomes a whole 'nother ballgame. Actors don't actually act in front of a live audience anymore, they do everything in front of a camera, not to mention the execs making scandalous amounts of money off of the movies.

    The other really scary part of this is what would happen if they could no longer make money off of showing the movie. How else could they? How did Star Wars make so much? Toys, add-ons, etc. Each movie becomes a marketing gimmick for the latest gadget/toy/time waster.

    Of course I don't see this as being a big worry anytime in the future. I don't have a monitor big enough to equal the experience of seeing a movie in the theatre, do you? If so, can I come over for a tan? Where this would hurt would be in the videotape/DVD market. Who needs a VCR or DVD player when you can just download it?

    Of course all this is random speculation. Also assumes a rather high bandwidth quotient. These things are coming, but perhaps not quite enough yet... Still, look at how well MP3's and pirated movies, etc are doing even with just the modems that most people have. I think people will wait if they don't have to pay. I know I would. But then again, I'm on a T1. :) (at least as long as I'm living in the dorm...)
  • Or just buy a lot of big, cheap hard drives & make your own RAID array, which minimizes your need for backup.
  • The biggest diference between ATA (UDMA) and SCSI is that multiple devices are controlled INDEPENDANTLY!! On an IDE bus you have a controller thane 1 to 2 drives.. the master actually handles part of the controller function. If the master needs to slide the heads ofer to track x the slave follows as soon as its current read is done even if the app pusing it has several reads left to do. Basically the drives run in sync and have to wait for each other to perform operations. SCSI provides an individual chanell for each device allowing them to operate completely seperate. The SCSI bus may have a max bandwidth much like an ethernet line but each device shares that bandwidth without having to wait on any other device.

    Its been a long time since I have done ANY SCSI so if I am wron Flame away!!

  • i dont think he was implying that USB is becoming the _hard drive_ connector of choice, but that perepherals(sic) like scanners, digital cameras, etc are being done via USB.

    he makes a good point with the UDMA stuff! i know what my next motherboard is going to support.

  • Actually five 2GB drives in a RAID5 array would give you a 10GB RAID5 drive.
  • Oops, your right I must appologize for my momentary lapse into the domain of stupidity. I realized what a truely dumbass post it was right after I hit submit. I don't know what I was thinking.

    Can we add CTRL+Z to the damn site.... PLEASE!
  • or use them for near-line backups. that's kind of what i do. i have a 4gig cuda in my old box at home and i back it up onto two 1gig hawks. hard drives are often cheaper than tape, unless you have massive amounts of disk space; then tape is cheaper. when i first got a 1gig hawk years ago, i bought another one just to back it up. that effectively doubled the cost of my storage, but it was still a lot cheaper than buying even a QIC tape drive.
  • You could always buy two small ones and RAID them with software. W2K does software RAIDing and I'm sure there's some project out there for Linux etc.
    I like thee breakthroughs cause they normally mean prices will come down - and more space is _always_ good.
  • "At 35-gigabit density, every square inch of disk space could hold 4.375 gigabytes..[clip!]" SCSI adaptor 7200rmp 50GB HDs are already being sold by La Cie (www.lacie.com). (Check the HARDDRIVE SECTION) Sounds like this is old news to me.
  • While USB is a nice technology (don't quote me on that..) the data transfer rates are very low, 1.2 mbps if i remember correcly, which is WAY too low for hardrives or anything other than backup and storage of data.

    Long live 1394.

    --
  • This kills you? You kill me. Look at where your at, "News for Nerds. Stuff that Matters". Is 99.99...% of the public coming to slashdot? I DON'T expect the "average" person to be here; I expect intelligent people who realize that there are things other than PC's in the world. If you expected a workstation conversation, maybe you oughta remember to mention that; cause there are people who work on servers and not PC's. You want to talk to 99.999...% of the population go on over to zdnet, you want to talk to those in the know come on over after you realize you are being pretty pompus assuming only workstations exist in the world.

    Stepping back now, different strokes for different folks, is all I can say, maybe you oughta state where you meant SCSI was going to die. I can't think of anybody who think SCSI belongs at the desktop (don't go there, there are special cases), so I had to assume you meant in the enterprise. You were implying very hard (my opinion) that SCSI was going to die everywhere. That being the case, I had to state my opinion on this blanket statement. Hell, I could state the converse of what you are saying, with a "IDE is going to be killed by SCSI," if I didn't also mention "in servers" I'd probably get lots of contrary opinions also, rightfully so, the PC is NOT the center of the know universe. Next time maybe you should think that there are people here who don't work on PC all the time. You are being very short-sited on this, I can walk both sides (workstations & servers) you want to talk workstations fine, you want to talk servers fine, you make blanket statements you better be able to apply it to both sides, or state which side it pertains to.

    For the waste... oh yeah I burn money every day, right in front of my boss too. There is a reason business spend the amount of money they do, they have to. I guess to save money I'll use IDE drives so that it will slow down my search through 9 terabytes of storage, so that the web response comes back in 5 minutesl; sure the customer will wait, and I did save some money.

    Speed difference between 66 & 80? You do realize, that you aren't going to get 66mb/s out of one drive that's the total speed you can get on the one controller. Not knowing much about UDMA/66 can you hang enough devices on it to fill that channel? With SCSI I can, if you aren't hanging enough drives off the controller to fill the bus, well then I guess it would be YOU and 99.999..% of the people who are burning money.

    You did inform me about the SCSI perphs though, I never even knew (maybe didn't care) they existed. I don't believe they were ever common place, which I got from your post. I got the impression from you that they were the leading technology and every single desktop had them, but is getting replaced by USB; but hey miscommunications happen.

    You priced a Solid State disk lately? Prices aren't going to be in desktop (remember that 99.999..% you know) region any time soon, 90k for a 4gig. Of course that wouldn't "hot-shot" technology that 99.9999...% of consumers should see on their desktops soon; and of course SSD's are a dieing technology since most act like SCSI devices, which we all know is going to die off and go IDE; speaking for 99.999...% of us.
  • Cool, things are all nice and friendly. You mentioned SCSI was going away (didn't mention workstation), I said it wasn't (didn't know you were meaning workstation) and then it got a bit warmer.

    I think we have always been both in agreement (SCSI isn't too useful on the desktop). People just need to clarify things (set some boundries, 2+2 does not ALLWAYS equal 4) before making broad statements that overlap areas of differing interests (pet peave of mine, probably why I'm grumpy_geek). Obviously we are in different parts of the IT industry and it is a large oversight to forget either one, when making statements that aren't confined to just one.

    Bad memories... Novell last I worked with it was something in the 2.x region (pretty ancient version), the Novell guys tell me things here and there and I guess now it is a completely different monster now; but I will say this even back then it did do it's functions (Printing & fileserver); as an app server I'm not so sure (but that's another rant all together).
  • Cool, things are all nice and friendly. You mentioned SCSI was going away (didn't mention workstation), I said it wasn't (didn't know you were meaning workstation) and then it got a bit warmer.

    I think we have always been both in agreement (SCSI isn't too useful on the desktop). People just need to clarify things (set some boundries, 2+2 does not ALLWAYS equal 4) before making broad statements that overlap areas of differing interests (pet peave of mine, probably why I'm grumpy_geek). Obviously we are in different parts of the IT industry and it is a large oversight to forget either one, when making statements that aren't confined to just one.

    Bad memories... Novell last I worked with it was something in the 2.x region (pretty ancient version), the Novell guys tell me things here and there and I guess now it is a completely different monster now; but I will say this even back then it did do it's functions (Printing & fileserver); as an app server I'm not so sure (but that's another topic all together).
  • I never said SCSI wasn't the best solution for current file/web/e-mail servers, as it clearly is. And I_would_rather_have a 10,000 rpm SCSI RAID setup for my new machine, but it's not cost effective for me. I don't really need RAID anyhow. All I need is a nice 18 gig hard drive, and a CD-RW burner for archiving. I know about the limitations of IDE, however, I don't plan on buying a controller so that isn't an issue. The main board I plan on buying will have an integrated UDMA/66 controller - but even if I did want or need to buy a controller, they are very cheap. Promise controllers wholesale at $40-50 (versus $150+ for SCSI). By the same token, I would love an SMP set up, but as I'm not planning on doing massive CPU intensive tasks all the time (e.g. renders in 3DS), it would be impracticle, and a waste of money.

    Zdnet is not worth posting on, however I do think I have something to contribute here, a perspective different from yours perhaps, but still informed. Btw, I have worked on file servers (not just PCs), and helped admin 2 Novell trees with 200+ file servers.

  • Novell (3.x & 4.x) is a super stable network OS, however, they made the mistake of using Groupwise for their e-mail system (not sure if they still do). The problem with groupwise is it's not an enterprise wide email system, like POP3 or IMAP.

    Groupwise uses (at least 2 years ago when I was involved with it) a number post offices, which means a number of seperate computers (often unsuited to the task of processing large volums of mail) located in different parts of a domain. All these post offices process mail for their domain, which can include a number of file servers. The mail is then sent to a primary post office SMTP machine and out to the internet... In order to send mail out to another DNS, you'd also have to address it with an internet: or i: prefix.

    So the problems start when individual post offices crash or bog down. When this happens mail from a domain queues up in a LAN queue. The size of the queue (number of e-mails pileing up) gives the groupwise admin an idea whether or not that PO is processing email to the centeral PO, or whether it's down, or if it needs some help. With multiple queues and machines (post offices) the margin for error is much higher than with a single enterprise send mail server.

    Talking with friends, I hear that Groupwise is still alive and kicking, for instance, the University of Maryland just put in a groupwise system. I was also not surprised to hear the horror stories already appearing: professor: "How come I can't get my mail now?!?".

    Personally I like POP3, as I can read my mail anywhere (with the exception of firewall issues) through Netscape, and it's very stable.

    I'm just getting into Linux now, and I'm very excited about it. A couple years ago, I was looking into CNE (Novell) certification however, it seems like M$ NT is eating up too much of Novell's market share to make this worth the cost. The good news is that Linux Admin Certification [lpi.org] looks like it's about to take off, so I'm studying for it now on my own :)

  • Not meaning to argue with anybody (everyone has made valid points on a number of the issues here), I'd like to provide a little extra food for thought.

    The choice to 'burn/waste' someone elses money is rarely the decision of IT professionals. In most cases, the IT staff has a modest operating budget and the really big purchases are made via 'capital appropriations' that must be approved by the management structure.

    Before capital appropriations are granted, IT staff are usually required (and rightfully so) do justify the expenditure. The IT staff should be able to demonstrate that the proposed expenditure will do one of two things (or both):

    1. Provide the customer with a better product or service (ie. give the customer a reason to do more business with the company)

    2. The technology being purchased will streamline operations that will ultimately result in savings that outweigh the price of the technology. Accounting types often refer to this as 'picking money up off the floor'.

    Does this mean that spending tons of money is right for everyone? No. It means that the purchase must be evaluated on several levels to ensure that the expenditure will benefit the company enough to offset the price associated with it.

    As 'Techies', it is human nature for us to want the bleeding edge technology. It's toy value. But as it has been pointed out elsewhere, that's not our money that gets spent on the technology. It is important that the technology that we recommend serve the people that will be spending the money.

    In many cases, it pays to be on the bleeding edge. Lets take the example of the recent advances in hard drive technology that are being discussed here. Would you like to know one of the major industries that will benefit from this technology? Turn on your radio. Many radio stations today are in the process of transferring all their older tapes and CD collections into a large array of hard disks using MP3 and similar codecs. They have a demonstratable need for larger, faster drives that consume less energy and office space.

    As for people who cannot themselves afford the bleeding edge; who find themselves spending $550 for a SCSI subsystem that is only worth $100 after two years, you're right. It isn't very smart to try to stay on the bleeding edge if you don't absolutely need to. You can and will waste a lot of money if you try. But look on the flip side. As the bleeding edge advances, todays highest tech products that cost a fortune will sell for pennies on the dollar, often in less than a year.

    If you are making an arguement that bleeding edge is beyond your needs and that it is wasteful to stay on it, then wait 6 to 12 months. By then, the techology will become affordable and your needs may grow to need it after all.

  • They are talking about density (how much data can you put in a square inch) not full capacity of disk. For example: we here have 47Gb Seagate Elite Hard Drives ... the only problem is that they are 5'1/4, double height. We also have 36Gb IBM Ultrastar 36XP 3'1/2, 2/3 height. The elite has ten disks while IBM only five. The diference in years betwen tecnologies is 3.
  • Does anyone here know about firewire?

    How does firewire compare to SCSI?

    My understanding is that it's a new development with very fast transfer rates, such that it's used for digital video transfer and other data intensive applications.

    I don't know if it's"cheaper-than-scsi"?

    Can RAID things be done with firewire?
  • The area that I see this technology being most useful is in reliable portable storage. In particular, IBM's microdrives (1" disks, not the old Sinclair endless tape loop!) could be turned into a very nice, very small RAID array. This was suggested when they were first announced, but each disk was limited to 170MB IIRC, which didn't lend itself to many practical uses. With this new technology, they're claiming over 2GB for a 1" disk -- 5 of those would give an 8GB RAID 5 array in a *very* small physical space.
  • Huge HD is nice.

    Huge HD that gone is bad.

    I used trust the manufacturers' MBTF number for their HD, but with more and more HD failures before their time, I do not know anymore if bigger and bigger disk is the answer to go.

    Why not make disks that last longer, rather than bigger disks that go belly-up before its time?
  • USB is 12 mbs, not 1.2.
    USB 2 is 360-480 Mbs.
    mlk
  • The 77 hours of music, as said at the bottom of the article, is only 3.2 days of music, not 6.5

    Of course that's per "^2, your new HDD would be more than 1 square inch.
  • But seriously, is it just me, or does it seem like HD technology is actually outpacing the needs of the average desktop user for once? I can remember when a gig seemed like an unreachable depth, but at least it was conceivable. I'm still using a 10Gb HD, which I've never come close to filling. I don't want to sound "Bill Gates"esque here, but who's really going to need 50 Gb *per platter* any time soon? Of course, if I had the bandwidth to fill this monster up with dirty pictures, look out!

    Anyway, let me know when they go on sale so I can buy one.
  • It's great that we could very easily have terabyte RAID5 arrays within, say, $10k soon. I'll be able to copy ALL my CDs up to my hard drives without converting them into mp3s.
    BUT
    until more people start buying tape backup units and driving down their price/gb, this is a scary trend.
    One of two things need to happen, preferably both:
    1) RAID 5 arrays need to get affordable, perhaps in the scenario one person posted about the microdrives. The ability to not have to worry because you have an affordable redundant drive waiting to be used is a tremendous thing. Mirroring is nice, but it just doesn't give that warm'n'fuzzy feeling.
    Unfortunately, I don't see affordability happening anytime soon. RAID5 technology just hasn't saturated enough yet to get prices down. Also, the standards wars that are occurring w/r/t EIDE, SCSI, USB+, Firewire, etc. are hampering things, too.
    Maybe IBM can come up with a 5 platter hard drive that has RAID as a function per-platter, with one platter set for failover.
    2) Tape drives need to drop in price, and increase in storage capacity. A great deal. This has become apparent this week as I search for a backup solution at work. The best bargain is the Onstream unit, with SCSI 50g backup for about $550, with cartridges at about $50 (i think.) 50g won't make a dent in the drives that are coming soon. And the unit only has a 2mb/s transfer rate. The best tape drives are DLT, which just work, period, but the 35/70g units are way out of the reach of the average consumer at over $2k, with cartridges at about $90. I don't keep up with backup technology, but I can't imagine there are any streaming tape breakthroughs coming anytime soon. I think the fact that DLT units are still priced in the stratosphere points out that there's a lot of unprotected data out there.

    Long term analysis: I think tape backup will die off, and RAID arrays will become ubiquitous. There's no other way to protect data easily. In the meantime, I continue to be scared.
  • The slowest part of a disk subsystem is still the drives. Especially in the case of IDE, where drives have only just recently begun to broach the maximum theoretical speed of *Mode 4* IDE (ca 1993). SCSI is a bit different, since RAID is actually a real option and it's not hard to envisage attaching enough fast hard disks in a RAID to swamp a U2W controller.
    However, the bottleneck is not really in the interfaces, it's in the drives. This is, as I said, especially true of IDE.
  • although the idea of more mp3 storage is nice we still have to remember other factors. what about transfer rates? i sort of doubt that this new technology is going to be run on ide/scsi. i think before we get huge hard drives developed a cheaper-than-scsi, yet very fast transfer method needs to be developed.
  • I fear the size of apps to come.
    Has anyone else out there had to install, say for instance, M$ Office 2000? It is huge, and for no apparent benefit in function or ease of use. Linux can fit an entire server and all the required apps on one CD(usually), but M$ Frontpage 2000 comes on two discs by itself!
    Remember before you had a HDD? Huge programs then ran on two, sometimes three, floppies. Remember the 640Kb RAM cap? Some very impressive software ran in a very limited space. All of these limits hae been effectively removed, allowing the mind-bending size of modern applications.
    I understand that the prices of RAM and HD space or plummeting, but does that require more crappy software to fill the void? Wouldn't you rather have 50Gb worth of useful stuff?
    Larger drives will inevitably lead to larger programs, but I'm not sure I want them.
  • UDMA/66 won't put SCSI under, I'm not familiar with UDMA/66 but if it's just got a faster bus... well big whoop. SCSI is meant to be able to do multiple operations simultaneously, hang lots of drives off of one controller, etc. Until something other than SCSI/fibre channel can allow me to hang 15 devices off of it, be able to do multiple operations simultaneously, allow me to share drives (I can hook-up 2 boxes to the same drive using differential controllers, for HA use only). Try hanging a terabyte of UDMA storage off of one box (we've got something like 20 controllers in one of our monster SGI boxes). If anything is going to put down SCSI, fibrechannel will (not in the near future, but sometime), SAN's are really sweet. I can hang 150+ devices onto one SAN and gigabit FC-AL is almost finalized...

    You completely lost me in your logic of USB... I don't know anyone of connecting phones, speakers, scanners, etc. to SCSI. SCSI is meant for drives, USB for periph. What you said is like saying my monitor is my visual connector of choice over printing everything on my printer (move mouse, print, move mouse, print).
  • by Xtacy ( 12950 ) on Tuesday October 05, 1999 @02:02AM (#1638551)
    SCSI u2w - 80 megs/sec
    SCSI u3w - 160 megs/sec

    sure you take a u2w hard drive and you wont get 80 megs/sec, same with a UDMA/66 drive. point is the bus can handle it, so you could have say 4 20 meg/sec u2w drives before the controller becomes a bottleneck.

    Also, dont forget the whole 15 devices a u2w card can support, compared to what, 2-4 for UDMA/66?

    I wont begin to get into RAID implementations.
  • by Hobbex ( 41473 ) on Monday October 04, 1999 @11:22PM (#1638552)

    Drives with this sort of capacities, coupled with our new lovely broadband connections, could truely mean the start for piracy of movies. Even with the crappy quality VCDs, 1 gigabyte a piece is to much to keep any collection worth noting, even on modern pcs with 24-36 gigs of space.

    When I bought my Celeron based PC last year, my old pentium got to move to the bookcase where it became my resident mp3 player (gotta love using crontab as an alarmclock). I know I'm not the only one who has done this.

    The logical extension is that when my current computer gets tossed out for a Merce.. I mean Itanium, Opteon, K8 or whatever, my current PC will move into the TV room to feed movies and generally do everything that those TV-cache machines do (only a whole lot better).

    With these sort of drives, that would seem very likely.


    -
    /. is like a steer's horns, a point here, a point there and a lot of bull in between.
  • by R. Anthony ( 97761 ) on Tuesday October 05, 1999 @03:55AM (#1638553)
    The thing that kills me on /. is how the sys admin/programmer/IT types are so out of touch with what the average user wants and needs. On different threads I've had to deal with at least two, "APG 4x Isn't Important!" claims that I found somewhat astonishing. That is until I realized that there was something larger at work here: that IT types are out of touch with the market.

    You see I'm not in the IT industry anymore, I was for a few years, but to tell you the truth, it kind of sucks, and I stopped enjoying using my computer(s) at home. At the time, I had built a P233 with an Adaptec SCSI controller, a SCSI CD-ROM 4x, and a 2.0 gig SCSI drive. All of this is now dated technology, and it is not upgradeable to my next system. How much did I spend on this fiasco? $150 for the controller (plain 40 Mb/sec SCSI) $200 for the drive, $200 for the CD ROM. That's a total of $550 for a bunch of equipment that is not worth $100 only 2 short years later... Now had I been smart and opted for IDE, I would have spent a lot less, gotten more storage space for my money, and felt a lot less foolish now that I had wasted all that money on equipment that I can not transfer to the new workstation I am now building.

    Sure if you're some hot shot WAN admin, you're used to throwing around someone else's cash on a daily basis, and for you buying massive Ultra SCSI 3 RAID arrays is no problem. You know that the whole thing will be upgraded in a year or 2 on the companies dime and written off as a business expense -- money that would have gone to taxes anyway.

    But you see, 99.999999999999% of Americans aren't big shot sys admins and therefore we don't have million dollar annual technology budgets. Instead, in this increasingly annoying cycle of hardware obsolescence, we are forced to make wise, cost effective decisions and if you take my example of my experience with SCSI in the previous paragraph, you might come to the same conclusion I did: that SCSI is nice, but not worth the money especially when you can get comparable performance at %300 lower cost. I mean come on, there's really not all that much difference between 66 Mb/sec and 80 Mb/sec.

    So no, SCSI won't die tomorrow, but it will get more expensive as more and more average consumers turn away from it to more cost effective alternatives like UDMA 66 (the less units you sell = smaller production cycles = higher unit cost).

    You completely lost me in your logic of USB... I don't know anyone of connecting phones, speakers, scanners, etc. to SCSI.

    Hrm, let's see what peripheral SCSI devices are on sale today at www.pricewatch.com...

    1) SCSI Scanners

    2) SCSI JAZZ Drives 1 & 2 gig

    3) SCSI Magneto Optical Drives

    Then here's a comparable list of USB peripherals on Pricewatch:

    1) USB keyboards

    2) USB Mouse's

    3) USB game controllers (joysticks, wheels, etc)

    4) USB hubs

    5) USB scanners

    6) USB Printers

    7) USB digital cameras

    8) USB modems

    9) USB Network cards

    Granted there nobody's buying SCSI peripherals anymore, however this isn't due to the lack of products, because before USB the only peripherial connectors offered were SCSI, Serial & Parallel. So why are there so few peripheral SCSI devices today, hmmm? Because everyone's now buying USB peripherials. You know what's really sad? I went to Pinnacle's web site recently, and tried to click on a link to their MO Jukebox section, and it was a dead link. I mean they can't be selling any MO drives anymore if their web site doesn't even link to one of their core product lines. It's sad, but you know what, I trust the decisions of the market more than any individual. The market likes USB, because it's integrated and you don't need IRQ settings, the speed is negligible as most people are used to slow parallel and serial connected peripherals anyhow.

    So what's left? SCSI is only useful now, as you said yourself for hard drives. But what is the wholesale price of a Ultra SCSI 3 drive? How bout a Compaq 34.4 gig SCSI3 drive? $1550. Now why in the hell would I buy one of these when I can buy more storage for $3-400 between two 20 gig UDMA 66 drives? The price difference may be small to a corporation, but to the average Joe, that's a big screen TV. Hence, SCSI is pricing itself out of the marketplace, and will therefore eventually wither and die.

    IMHO the coup de gras will delivered to SCSI when solid state RAM drive prices drop to the point where they are a cost effective solution.

  • by R. Anthony ( 97761 ) on Monday October 04, 1999 @11:18PM (#1638554)
    Ultra DMA 66 is the new standard. 66 meg/sec is nice to have, especially considering the fact that cheap, integrated UDMA/66 controllers will be standard on motherboards in the future (e.g. Abit B06).

    SCSI is kind of a pain, and very expensive. A high capacity SCSI drive can often be 4x as expensive as a UDMA/66 drive, not to mention the hugely expensive SCSI2 controllers...

    Additionally, USB is rapidly replacing SCSI as the peripherial connector of choice, so IMHO SCSI is a dieing technology.

    I'd be interested to see when IBM makes this new technology commerically available, and whether or not the higher density will reduce seek times/rpm significantly.

Any sufficiently advanced technology is indistinguishable from a rigged demo. - Andy Finkel, computer guy

Working...