Slashdot Mirror


Is the Time Finally Right For Hybrid Hard Drives?

a_hanso writes "Hard drives that combine a traditional spinning platter for mass storage and solid state flash memory for frequently accessed data have always been an interesting concept. They may be slower than SSDs, but not by much, and they are a lot cheaper gigabyte-for-gigabyte. CNET's Harry McCracken speculates on how soon such drives may become mainstream: 'So why would the new Momentus be more of a mainstream hit than its predecessor? Seagate says that it's 70 percent faster than its earlier hybrid drive and three times quicker than a garden-variety, non-hybrid disk. Its benchmarks for cold boots and application launches show the new drive to be just a few seconds slower than a SSD. Or, in some cases, a few seconds faster. In the end, hybrid drives are compromises, neither as cheap as ordinary drives — you can get a conventional 750GB Momentus for about $150 — nor as fast and energy-efficient as SSDs.'"

235 of 311 comments (clear)

  1. It'd better happen quick then by Sycraft-fu · · Score: 5, Insightful

    If there is to be a time for hybrid drives, the window on it is fast closing. As SSDs get cheaper and cheaper more and more people will opt to just go that route. Most people don't really need massive HDDs and so if smaller SSDs get cheap enough that'll be the way they'll go. They don't have to be as cheap as HDDs, just cheap enough that for the size people need (probably 200-300GB for more people) they are affordable enough.

    For me personally, the time already came and went. I was very enthusiastic about the concept of hybrid drives, particularly since I have vast storage needs (I do audio production). However no hybrid drive for desktops was forthcoming. Then there was a sale on SSDs, 256GB drives for $200. I picked up two of them. $1/GB was my magic price when I'd be willing to get them. Now I have 512GB of SSD storage for OS, apps, and primary data. That is then backed by 3TB of HDD storage for media, samples, and so on.

    A hybrid drive has no place. I'd certainly not replace my SSDs, they are far faster than any hybrid drive (even being fairly slow on the SSD scale). Likewise I have no real reason to upgrade my HDDs, they serve the non-speed intensive stuff.

    While I'm willing to spend more than most, it is still a sign of things to come. As those prices drop more and more people will say "screw it" and go all SSD.

    1. Re:It'd better happen quick then by thsths · · Score: 4, Insightful

      Right, but it didn't happen quickly. These is only one model of a hybrid hard disk available, which makes it unsuitable for any serious use in mass production. Also Seagate now tell us that their previous version was actually crap, and the new one is much much better. The price is lower but still high - about 100 dollars for 8 GB of flash. For that money you could get an SSD with 48 GB - and put all your system data on it.

      This is a niche product, designed for laptops with only one disk slot that require both fast access and high storage. It is heavily compromised in both aspects, and the price is outrageous.

    2. Re:It'd better happen quick then by Anonymous Coward · · Score: 5, Insightful

      > Most people don't really need massive HDDs

      Are you kidding me.

      Record FRAPS of your gaming sessions, photography (or RAW), record and edit anything with any modicum of quality? Save said media and final encodings?

      Age of conan, 33 GB. LA Noire13 GB. Mortal Online, 30 GB.

      That is stuff ordinary people do, not audio producers.

    3. Re:It'd better happen quick then by Nursie · · Score: 2, Insightful

      Frankly I'm not sure the write thing's as much of an issue as people make out.

      MTBF for HDD and SSD are both ludicrously high these days. I'd be more worried about the mechanical failure of an HDD than reaching the write limit on an SSD.

    4. Re:It'd better happen quick then by Kjella · · Score: 5, Insightful

      The rewrite figures are going to shit as they move to smaller processing tech, 25nm eMLC is already down to 3000 writes/cell, they say you won't get $1/GB at normal prices until we get 19nm which at least some say will be down to 1000 writes. That you're getting 500MB/s write speed is nice, but if you actually start using that regularly you'll burn through the disk in a matter of months. My first SSD - which I admit I abused thoroughly - died after 8-9000 writes average (was rated for 10k) after 1.5 years. My current setup is trying to minimize writes to C:, but I still don't expect it to last nearly as long as a HDD. Using it as a read-heavy cache of static files may be a better way to boost it for those that haven't got hundreds of dollars to spend every time it wears out.

      --
      Live today, because you never know what tomorrow brings
    5. Re:It'd better happen quick then by wye43 · · Score: 1

      I think the time has come and gone. Full SSDs are cheap, fast and lately even in high capacities. They are here to stay. Good bye platters!

      Seagate needs to get on board and ditch the monstrosities that nobody wants. The link to the article is dead. It looks CNET removed/moved the Seagate advertisement ... ups, I mean the article.

    6. Re:It'd better happen quick then by Jane+Q.+Public · · Score: 1, Troll

      The key word in "MTBF" is "mean". I'm a power-user. Means don't apply.

    7. Re:It'd better happen quick then by Nursie · · Score: 2

      So the longer MTBF for an SSD is a bad thing thing for you?

      Personally I think you're talking crap. What exactly do you do to hard disks Miss Jane Q. Poweruser?

    8. Re:It'd better happen quick then by bemymonkey · · Score: 1

      I'd kill for a decent hybrid drive for my laptop right now. I'm currently running Samsung's 1TB 2.5" drive, and that's about halfway full... pretty much the only SSD I'd be able to use is Intel's 320 (or 310?) with 600gigs, which costs about as much as I paid for my Thinkpad. And even with that, I'd be uncomfortably limited due to the lack of room for expansion... not to mention leaving room for wear leveling and such.

      Looks like I'll be upgrading to a Thinkpad with two hard drive bays, or one with an mSATA slot, sometime soon.

    9. Re:It'd better happen quick then by gl4ss · · Score: 1

      he swaps to them.

      --
      world was created 5 seconds before this post as it is.
    10. Re:It'd better happen quick then by Anonymous Coward · · Score: 4, Insightful

      I'll lecture you about my practical usage versus your theoretical bullshit.

      I used a SSD for 3 years now and I have zero problems. It was cheap and it has literally transformed the way I use my computer. Its so fast I'd never go back to mechanicals.

      On the other hand, I had 3 mechanical drives failing on me, after an average use of 2-3 years.

      Until you actually try SSDs, don't lecture other people about them because you don't know what you're talking about.

    11. Re:It'd better happen quick then by AmiMoJo · · Score: 3, Interesting

      SSDs typically have large memory caches, where as HDDs are still stuck around the 32MB mark. With RAM so cheap these days even the lowest end graphics cards are coming with 1GB, but not HDDs for some reason.

      --
      const int one = 65536; (Silvermoon, Texture.cs)
      SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
    12. Re:It'd better happen quick then by UnknownSoldier · · Score: 5, Informative

      While I love the speed the SSD (and the prices is hitting the "magic" $1/GB) you're forgetting the HUGE elephant in the room with SSD that almost no-one seems to notice ...

      SSDs have a TERRIBLE failure rate.

      http://www.codinghorror.com/blog/2011/05/the-hot-crazy-solid-state-drive-scale.html

      He purchased eight SSDs over the last two years ⦠and all of them failed. The tale of the tape is frankly a little terrifying:

              Super Talent 32 GB SSD, failed after 137 days
              OCZ Vertex 1 250 GB SSD, failed after 512 days
              G.Skill 64 GB SSD, failed after 251 days
              G.Skill 64 GB SSD, failed after 276 days
              Crucial 64 GB SSD, failed after 350 days
              OCZ Agility 60 GB SSD, failed after 72 days
              Intel X25-M 80 GB SSD, failed after 15 days
              Intel X25-M 80 GB SSD, failed after 206 days

      and ...

      http://translate.googleusercontent.com/translate_c?hl=en&ie=UTF8&prev=_t&rurl=translate.google.com&sl=fr&tl=en&twu=1&u=http://www.hardware.fr/articles/843-7/ssd.html&usg=ALkJrhjecZZv1F6d_oT-dr41FPFYOIkVCw

      - Intel 0.1% (against 0.3%)
      - Crucial 0.8% (against 1.9%)
      - Corsair 2.9% (against 2.7%)
      - OCZ 4.2% (against 3.5%)

      Intel confirms its first place with a return rate of the most impressive. It is followed from Crucial, which significantly improves the rate but it must be said that the latter was heavily impacted by the M225 - the C300 is only reached 1%. The return rate for failure are up against Corsair and OCZ especially in the latter confirmed by far his last position. 8 SSDs are beyond the 5%:

      - 9.14% 2 240 GB OCZ Vertex
      - 8.61% 2 120 GB OCZ Agility
      - 7.27% 40GB OCZ Agility 2
      - 6.20% 60GB OCZ Agility 2
      - 5.83% 80 GB Corsair Force
      - 5.31% 90GB OCZ Agility 2
      - 5.31% 2 100 GB OCZ Vertex
      - 5.04% OCZ Agility 2 3.5 "120 GB

      At the _current_ price point & abysmal failure raite, SSD sadly has a ways to go before it catches on with the main stream.

    13. Re:It'd better happen quick then by darkmeridian · · Score: 1

      Hybrid drives are designed for laptops. Most laptops don't have space for two drives. Thus, the hybrid drive will let media obsessed folk to carry around 750 GB of stuff but give them a speed boost when necessary.

      --
      A NYC lawyer blogs. http://www.chuangblog.com/
    14. Re:It'd better happen quick then by Gaygirlie · · Score: 2

      I know many people who would see a huge benefit from these hybrid drives, but then again they're all non-techies: they just use the computer the way they've learned, they know nothing about the internals and so on. A hybrid drive would atleast get them on the desktop a lot faster than they do right now, and that alone is quite useful. The thing is that I don't really feel like 8 gigabytes is enough. Windows alone can easily eat up more than half of that, and with many applications weighing in the hundreds of megabytes you don't really get all that much stuff in there. Up it to 16 gigabytes and it'll help even novitiate gamers.

      For me though, hybrid drives are definitely not suitable. I rather control what exactly goes in there so I can optimize those things that I feel need optimization and leave the rest to standard non-SSDs. Like e.g. I'd definitely want most of Windows on SSD, plus Firefox+cache, a few IM applications, programming tools, and whatever game I happen to be playing the most at the time; I'd leave most of Steam to non-SSD, I'd just copypaste the currently most interesting game to SSD for fast startup and loading-times. And for example even though I access my music files regularly, they're so small that it takes barely a second to read a whole song to memory even from non-SSDs, so it'd be waste of fast storage to cache those files on there. A hybrid drive would most definitely be caching stuff that doesn't need caching.

      Alas, SSDs are terribly expensive for an unemployed person. Before the floods I could get a 1TB non-SSD for 49€ whereas a 64GB SSD costs 120€. While 64GB would be enough for my needs it still hurts way too much to pay such sums for so little.

    15. Re:It'd better happen quick then by fsckmnky · · Score: 1

      newegg.com just had 16GB of DDR3 on Black Friday for $60. They have since sold out however.

    16. Re:It'd better happen quick then by cheekyboy · · Score: 1

      your wrong, every normal HD will become a hybrid , especially if 8gig flash becomes just a $4 overhead.

      So a RAID 6 x 750HHD setup would kick ass in price over your discount rare offer of 256Gb * 18 setup.

      SSD is nice, but you dont need it for rarely used data, so unless you run a twitter or major site which makes money, you dont need 5tb of SSD.

      Every HD today has DRAM cache of just 16-32meg. So the cheaper that is, the more you can use, and if NAND is cheap, add another layer of 8-32gig of NAND cache on your giant 4tb drive.

      LESS HD access = less wear and tear = longer life before FAILURE.

      --
      Liberty freedom are no1, not dicks in suits.
    17. Re:It'd better happen quick then by ProfessionalCookie · · Score: 1
      I know there's no 3TB HDD/512GB SSD Hybrid on the consumer market, but you pretty much just described an inefficient hybrid (requires manual organization and has drives on separate controller).

      I'm all for getting rid of spinning disks as well but if anything your post legitimizes hybrids.

    18. Re:It'd better happen quick then by Jane+Q.+Public · · Score: 2

      "OCZ Vertex 3 240 GB - 2,000,000 hours MTBF Western Digital Caviar Black 640GB - 1,500,000 hours MTBF"

      If true, it is the first time I have seen such a figure.

      And if true, I would consider it to be good news.

    19. Re:It'd better happen quick then by jimicus · · Score: 3, Informative

      The cache on a hard disk is often used as write cache - store incoming data in cache, leave actually committing it to disk until a convenient opportunity arises.

      32MB of cache doesn't take that long to flush. 1GB, OTOH...

    20. Re:It'd better happen quick then by Jane+Q.+Public · · Score: 1

      "OCZ Vertex 3 240 GB - 2,000,000 hours MTBF Western Digital Caviar Black 640GB - 1,500,000 hours MTBF"

      But I should also point out that as far as I know, the MTBF figure is not related to the number of rated write-cycles.

      But I don't claim to be certain. I'll check.

    21. Re:It'd better happen quick then by abigsmurf · · Score: 4, Informative

      Yep, had a OCZ drive fail after 3 months. First time I've had a drive that wasn't DOA fail before at least 2-3 years of usage

      It wasn't even one of those gradual fails you tend to get with HDDs where they tend to start getting faults for a while before failing, giving you a chance to get the data off of it and order a replacement. One day it was working normally, next day, wasn't even recognised by the bios.

      Just to add insult to injury, OCZ have an awful returns policy, had to pay to get it send recorded delivery to the Netherlands. Cost me £20. Going to be a few years before I take the plunge again and I won't be buying OCZ. Paying premium prices for something so unreliable, isn't on, especially given how much of an impact a sudden drive failure has on just about every type of user.

    22. Re:It'd better happen quick then by Jane+Q.+Public · · Score: 1

      My normal work machine is very heavily used, acting as a database and web server along with its other duties. So yes, the hard drive is exercised A LOT more than your everyday home computer.

    23. Re:It'd better happen quick then by cgenman · · Score: 4, Informative

      MTBF is a complete BS statistic. Take the first week of a hard drive's life. Make a linear extrapolation to that over the next 1000 years. Post marketing statistic that is grossly divergent from reality. The Western Digital listed in the thread below has a MTBF of 171 years. Anyone working in a real environment will confirm that is just ludicrous. What you're measuring is that for the first week of a hard drive's life, it behaves like it would live for 171 years. After the first week, it's all downhill. Back in the real world I kill laptop drives at least every 2 years, and desktops every 5.

      This makes MTBF an OK but not great cross-device comparison statistic, with the assumption that all hard drives age in about the same way. SSD's really don't age like Hard Drives. They're less prone to total catastrophic failure. They lose a little capacity on a regular basis. They don't have axle bearings or dust to worry about. They will age and have electrical problems, but nowhere near the mechanical problems of hard drives. They will age in a more linear fashion. A 50 year MTBF of an SSD drive is actually a plausibly useful data point, whereas a 200 year MTBF of a hard disk is a BPOS.

    24. Re:It'd better happen quick then by Jane+Q.+Public · · Score: 1

      Okay, for everybody's information, I looked it up. According to this recent article, write-cycles are still the limiting factor for most SSDs, rather than MTBF. (Certain RAID configurations are an exception.)

      However, the good news is that the article says write endurance has increased a lot in the last few years, with some manufacturers offering SSDs rated at more than 5 million write cycles.

      So, the question in my case is not "Will a cheap SSD do the trick?" but "Do I want to spend the money on a high-end SSD?"

    25. Re:It'd better happen quick then by cgenman · · Score: 1

      I was using a Lenovo with a manual hybrid SSD / HDD (I.E. they have a laptop with a SSD drive, an HDD drive, and some logic to link the two into one drive). It actually booted about twice as fast as the HDD alone, and launched applications rather snapily.

      Of course, when the drive had problems it was impossible to get at or fix. That's why I went up to a 256 SSD System drive and traditional HDD for data / programs. But a more traditional hybrid drive wouldn't have that problem, and would just run faster.

    26. Re:It'd better happen quick then by Jane+Q.+Public · · Score: 2, Insightful

      "They will age in a more linear fashion. A 50 year MTBF of an SSD drive is actually a plausibly useful data point, whereas a 200 year MTBF of a hard disk is a BPOS."

      Theoretically that may be true, but SSDs are still young enough that I give a lot of weight to "anectodal evidence", and the majority -- in fact almost all -- of what I have heard is that they actually tend to fail catastrophically.

      As far as I am concerned, a "wait and see" approach is still feasible before I spend a bunch of money.

    27. Re:It'd better happen quick then by neokushan · · Score: 1

      I'm glad to say that I've never had a Hard Drive fail on me, ever. I've had MBT partitions get corrupted, which I thought was a faulty HDD but turned out to be caused by faulty RAM under a specific circumstance, but never a HDD fail.

      However, I'm still a firm believer that anything with "Moving parts" will inherently be more likely to break than something without, or at the very least will certainly wear over time and fail eventually. SSD's do seem to have their issues and certainly have their own issues with "wear", but the technology is still pretty young. At the very least, it's possible to negate any wear issues and extend the life of the drive by allocating more reserved space to it. That way, the blocks that start erroring can be ignored, much like we do with Mechanical HDD's today.

      --
      +1 IDisagreeSoHeMustBeATrollOrAnAstroturferOrAShill
    28. Re:It'd better happen quick then by migla · · Score: 1

      One word: Esata

      --
      Some of my favourite people are from th US; Vonnegut, Chomsky, Bill Hicks.
    29. Re:It'd better happen quick then by Rockoon · · Score: 2, Informative

      .... when they consistently surpass 1 or 2 million write-cycles per block ............
      (P.S. Please don't lecture me about wear-leveling, etc. I know how they work.)

      The last FLASH process size reduction took away ~39% of overall erase cycles but added ~64% more capacity per per mm^2.

      In your view the latest generation SSD's are even worse than the previous generation because they only have 61% of the erase cycles, right?

      If you really knew how SSD's worked, you wouldnt be talking about SSD's with millions of erase cycles per block. I mean what the fuck...

      --
      "His name was James Damore."
    30. Re:It'd better happen quick then by migla · · Score: 1

      So maybe there could be a little computer and a battery on the hdd along with the gigs of cache?

      --
      Some of my favourite people are from th US; Vonnegut, Chomsky, Bill Hicks.
    31. Re:It'd better happen quick then by Jane+Q.+Public · · Score: 1

      "If you really knew how SSD's worked, you wouldnt be talking about SSD's with millions of erase cycles per block. I mean what the fuck.."

      Write cycles, not erase cycles. But never mind, I really don't want to split hairs.

      See the article I linked to elsewhere in this thread. It says the life of SSDs is still limited mainly by the number of write cycles. So my concern is perfectly valid.

      Further, in regard to how they work: when SSDs were a bit newer, I mentioned right here on /. how I could easily write a program to wear one out. I was told I was full of BS. Lo and behold, a program to do just that was made available on the web.

      Of course they have improved since then, and so has the wear-leveling. But I know how they work, dude. And yeah, the # of write cycles they are rated for is important. (Also, as one other commenter pointed out -- and so does that article -- the latest generation of dense multi-level memory chips actually have LESS write endurance than their predecessors.)

    32. Re:It'd better happen quick then by Jane+Q.+Public · · Score: 1

      And as for block, rather than cell: the reason I stated it that way is that statistically, a block will not have as many write-cycles as individual cells are rated for, simply because there are many cells per block. And statistically, therefore (at least, if over-provisioning has been used up), on the average a block will not last for the full write-cycle rating. So yeah... I want long lifetimes in terms of blocks, not just cells. For statistical, not design, reasons.

    33. Re:It'd better happen quick then by jimicus · · Score: 4, Informative

      Would add far too much cost to the hard drive, but this is essentially what server-class hardware RAID controllers do. The battery doesn't power the hard disk, it just keeps the cache running.

    34. Re:It'd better happen quick then by Jane+Q.+Public · · Score: 1

      Pardon me. Haha. That was you. It's late and I am tired.

    35. Re:It'd better happen quick then by gmack · · Score: 1, Redundant

      The only time I have really heard of them failing on any large scale is when they are plugged in and just don't work(or work intermittently) due to incompatibilities/software defects or when someone updates the firmware and generally if they work for the first week without problems they will run well. I own several and they have been solid although I have avoided spending large amounts of money and ended up with the smaller sizes that I used for system files.

      With just the system files on SSD the difference in speed has been huge for both Linux and Windows.

    36. Re:It'd better happen quick then by Jane+Q.+Public · · Score: 1

      I have heard lots of stories, some of them right here. And I mean bricking, not just "working badly". That's what I meant by catastrophic.

      I'm not saying that's what they typically do. I'm only saying those are the majority of the failure stories I have heard / seen.

      I have been an early adopter of many things. But I value my data (which is my bread and butter, after all), and so I will take a conservative approach to this. After more people have had them, for a little while longer, I will revisit the issue then.

    37. Re:It'd better happen quick then by Anonymous Coward · · Score: 1

      Calling bullshit on that. If your "database and web server" dataset is larger than, what, 32GB on a desktop machine, then you're doing it wrong. It wasn't advice. Durrrrrp.

    38. Re:It'd better happen quick then by gmack · · Score: 1

      No data I care about resides on any of my SSD drives since I use them for system files only. Anything I care about is on a standard drive (due to size issues) as well as backed up elsewhere.

    39. Re:It'd better happen quick then by smash · · Score: 1

      Hybrid has no place? How about your average laptop with one hard drive bay? If you can get near SSD performance and actually carry around a decent amount of data, i reckon its a winner.

      --
      I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
    40. Re:It'd better happen quick then by smash · · Score: 1

      8 gigs is more than enough for the components in windows that you actually load on a regular basis. A windows install may be 17 gigs, but that includes all the utilities you use once in a blue moon, a heap of desktop wallpapers, drivers for all the hardware in the Windows world you DONT own, sound themes, etc. The actual base OS that is loaded into RAM on boot is likely nearer 1/3 to 1/2 a gig.

      Ditto for the apps you install.

      --
      I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
    41. Re:It'd better happen quick then by Joce640k · · Score: 1

      as far as I know, the MTBF figure is not related to the number of rated write-cycles.

      Of course it isn't, and that's the problem - the numbers are easy to manipulate.

      --
      No sig today...
    42. Re:It'd better happen quick then by Bert64 · · Score: 1

      I have a 100MB DEC SCSI disk from an old vax which still boots, its from the late 1980s and was running 24/7 from manufacture until about 2001, since then it's been used occasionally but spent most of its time turned off.

      I also have 4x 4GB SCSI disks which were used in the late 90s in a server, before i got hold of them in 2000 and built a 4 disk raid0 array which i ran continually with very poor cooling until about 2004. As far as i know those disks still work, although i have had no reason to access them in a while, and the server to which they were connected is long gone.

      On the other hand i bought a 3TB drive 3 months ago, which now hangs the machine when you try to write to it...
      I've been through 3 disks on my laptop in the past 5 years too...
      And i have a pair of 250GB sata disks in a desktop which while still working, are warning of a large number of bad sectors.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    43. Re:It'd better happen quick then by Rockoon · · Score: 4, Insightful

      The rewrite figures are going to shit as they move to smaller processing tech, 25nm eMLC is already down to 3000 writes/cell, they say you won't get $1/GB at normal prices until we get 19nm which at least some say will be down to 1000 writes.

      Based on 3000/25nm tech, the new erase cycle limits will be ~58% (1700/19nm) but the storage capacity per area will increase by ~70%.

      That you're getting 500MB/s write speed is nice, but if you actually start using that regularly you'll burn through the disk in a matter of months.

      The smaller tech has just as much "heavy use" as the larger tech when equal amounts of board area are dedicated to flash chips. A board with 1 TB of 1700-cycle flash can take a serious write pounding even with considerable write amplification. The same board on the 25nm tech would only have 588 GB of 3000-cycle flash/

      "Heavy use" doesnt mean "fastest possible erases." I don't know what you think heavy use means, but even extreme pounding scenarios (such as cycling the entire 1 TB once per day, something you might see in a non-incremental backup server) still gives these drives years of cycles to "blow" through. You could technically kill this theoretical drive in a little over a month but that says nothing about what a "heavy user" will actually witness.

      The people solving write needs extreme enough that they would burn through the cycles of this theoretical 1 TB drive in less than a year are dedicating a lot more than a single 1 TB drive to their data volume problem

      --
      "His name was James Damore."
    44. Re:It'd better happen quick then by Bert64 · · Score: 2

      Ignore the returns policy, send it back to the retailer... Your contract is with the retailer, not the manufacturer. Know your rights!

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    45. Re:It'd better happen quick then by Joce640k · · Score: 1, Informative

      LOL! Where did you get that from?

      If I bought a million hard drives I'd expect several of them to not even power on. By your definition I'm sure the MTBF of all consumer hardware would be zero.

      PS: MTBF means "Mean time between failures" not "Mean time before failure".

      --
      No sig today...
    46. Re:It'd better happen quick then by Joce640k · · Score: 1

      I can't get worries out of my head

      Do you also obsessively defragment your hard disks? Change you car's engine oil more often then the recommendation?

      --
      No sig today...
    47. Re:It'd better happen quick then by petermgreen · · Score: 1

      Most laptops have space for two drives (by default HDD and optical). It's just for some reason few vendors seem to offer combinations out of the box that don't involve an internal optical drive.

      --
      note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
    48. Re:It'd better happen quick then by FreakyGreenLeaky · · Score: 1

      amen to that - we buy batches of ~20-50 at a time (seagate), and sure enough, at least 1 of them will have some kind of issue, if not outright fucked-upness.

    49. Re:It'd better happen quick then by Anonymous Coward · · Score: 2, Insightful

      If you value your data that much (and I understand if you do, because I value mine as well), you shouldn't be trusting either the SSD or the conventional HD. You should be backing up that data to a second device either way, at which point whether or not it is SSD or HD is irrelevant.

      My machine is all SSDs for what its worth. Data files and system files are all on SSD. Of course the personal data files are all backed up to a server built of conventional HDs that sits in my wiring closet. Not because I think the conventional HDs last longer, but because their cheaper. The important thing is that the data is in two places at the same time, and that there is time to do a replacement if one of them fails before the second copy also fails. Whether they are SSDs or HDs is entirely a question of performance vs. cost for me. On the actual desktop, I value performance and am willing to pay the extra cost, so I have SSDs. On the backup device, performance is irrelevant and cost is what I care about so I have HDs.

      Now if you are afraid it may be a waste of money because you think it will fail too soon to be worth the cost, that's a fine argument. Though I wouldn't agree with you.

      But if you say you are not using SSDs on your desktop or laptop because you don't want to risk losing your data, all that means is you don't value your data enough to back it up, because if you were backing it up, that wouldn't be a concern. :p

    50. Re:It'd better happen quick then by Rockoon · · Score: 1

      Your argument that "per cell" is meaningfully different than "per block" falls flat when both shrink at the same rate with process size reductions. You really do need to learn about SSD technology. I realize that you THINK that you know what you are talking about, but its quite apparent that you don't.

      --
      "His name was James Damore."
    51. Re:It'd better happen quick then by olau · · Score: 3, Informative

      That's because it doesn't do anything good for hard drives. There was a paper about it some years ago, I'm too lazy to google it up, but even 32 MB is too much (I think the sweet spot was around 2 MB).

      If you think about it, it's not surprising, what good would it do that the disk cache in main memory managed by the OS didn't already do?

      Large on-disk cache would only make sense if it was combined with a battery or something so you don't loose data on crashes.

    52. Re:It'd better happen quick then by drinkypoo · · Score: 1

      Ignore the returns policy, send it back to the retailer... Your contract is with the retailer, not the manufacturer. Know your rights!

      It depends on where you live. In California you have the legal right to simply take the package to *any retailer who sells the same product*, which is probably one reason there are often multiple SKUs for the same exact product; you'd have to go to court to prove they're the same, by which time it would probably be obsolete if it's computer kit. In some other states the retailer can tell you to go fuck yourself even if you bring it back to the store, because your contract really is with the manufacturer.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    53. Re:It'd better happen quick then by drinkypoo · · Score: 5, Interesting

      That's because it doesn't do anything good for hard drives. There was a paper about it some years ago, I'm too lazy to google it up, but even 32 MB is too much (I think the sweet spot was around 2 MB).

      Having had the 2MB and 8MB versions of the same disk from Seagate that uses the same mechanism and having seen the 8MB disk be substantially faster, I'm pretty sure it's not 2MB.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    54. Re:It'd better happen quick then by maxwellmath · · Score: 2

      Audio may be small when you are just ripping CDs. However, this is not the case for anyone who actually does any real audio production. Think about if you are mixing multiple audio tracks, if you record 10 tracks at CD quality (44.1kHz, 16bit, stereo) you are now at 100MB/min. Not to mention, many serious audio producers will record at much higher sample rates -- up to 192kHz, some audio is even done at 24bits. Now you are talking close to 70MB/min for a single stereo track. If you are mixing surround sound, you can see how it would be much higher. Record a few tracks this way and you'll see why you would need a huge hard drive. Not to mention the countless GB of samples used by music producers. Some sample sets can be a hundred GB on their own (think of an orchestra sample set where each instrument/section is sampled at multiple dynamic levels, and over their entire range of notes.)

    55. Re:It'd better happen quick then by Luckyo · · Score: 1

      You belief is rather strange, as modern hard drives have very few mechanical failures. Most of the failures they suffer from are usually surface or logic failures. This includes wear and tear (with some rare exceptions of drives clocking insane hours and actually wearing out the bearings - this requires hundreds of thousands of hours of spinning on modern drives).

    56. Re:It'd better happen quick then by Theophany · · Score: 1

      I don't obsessively defrag, but I do change the oil more often than recommended - it's a diesel Italian car, so all precautions are strongly required ;)

    57. Re:It'd better happen quick then by Anonymous Coward · · Score: 1

      The MTBF is much better defined than you think it is - the manufacture specifies the duty cycle for the drive quite thoroughly, which is why (for example) server class hard drives' MTBF rating is based on continuous activity, while a desktop hard drive's MTBF rating is based on much lighter usage. This isn't on the carton, of course, but you can get quite detailed technical specs on drives from the manufacturers that go into all of this detail.

      Also, the MTBF isn't based on testing a drive for a week, it's (in my experience) based on testing hundreds of drives continuously for months, and then extrapolating from there based on observed field failure rates of millions of hard drives. That is, they don't simply take the failure rate from a month's "burn in" and multiply, they know the field failure rate of drives over the course of years, and their initial "burn in" failure rates, and model based on that.

      All that being said, at some point MTBF becomes a somewhat meaningless number. Modern hard drives are amazingly durable and reliable, to the point where an MTBF of 1.5m hours might be a statistically valid estimate based on expected failure rates, but 1.5m hours = 171 years, which simply isn't a plausible period of time to talk about anything mechanical operating, because the odds of something "abnormal" happing over that time period (e.g. the drive gets dropped, there's a power spike, humidity goes too high and things rust) would be much higher than that.

    58. Re:It'd better happen quick then by TheThiefMaster · · Score: 5, Insightful

      MTBF is not the failure rate of a single disk, it's the average failure rate of disks used in an array. If you have a type of disk with a 100,000 hour MTBF, and use 100 of them (whether in a raid array, a cluster, or 100 individual desktops in a company). Then you will (roughly) replace one disk due to failure for every 1000 hours (100,000 MTBF / 100 disks), or 40 days.

      It doesn't try to pretend that a single disk lasts 100,000 hours. That's stupid.

    59. Re:It'd better happen quick then by Talderas · · Score: 1

      Maybe I misunderstand the MTBF concept, but isn't the difference between 1,500,000 hours and 2,000,000 hours rather negligent? Unless this is some definition of hour that I'm not aware of I don't think it matters much to me if it takes 171 years or 228 years for the drive to fail...

      --
      "Lack of speed can be overcome. In the worst case by patience." --Znork
    60. Re:It'd better happen quick then by swalve · · Score: 1

      Technical people don't care so much about size, because they know the benefit they are getting from the trade-off. I'm not so sure about "power" users- people who demand a good computer but don't really know or care for the hows and whys. They don't want to hook up external drives, and they want to see their laptops come with 500 ~ 1000 gb drives AND be fast.

    61. Re:It'd better happen quick then by AmiMoJo · · Score: 2

      You don't seem to understand how the cache memory is used. It thing like read-ahead data that the drive basically gets for free as it waits for the disc to rotate to the correct place, or metadata like bad block and reallocation maps. With a larger cache it would be easy for the drive to do background reads when the computer is idling it, increasing the chance that the next read will be already in the cache, like a kind of super read-ahead.

      The drive can make smart decisions that the PC can't because it knows more about the physical state of the drive. Native Command Queuing is one way that a drive can use this knowledge to increase performance, and large caches are another.

      Modern filesystems are designed to cope with writes not being committed due to existing write caching, so having a larger write cache should not be a problem.

      --
      const int one = 65536; (Silvermoon, Texture.cs)
      SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
    62. Re:It'd better happen quick then by swalve · · Score: 3, Interesting

      I agree. But the difference between 32 and 64 might not be so great. There is a limit to how much a HDD can predicatively read, and I have to think that the real world difference between caching writes isn't going to be all that much on a single user machine. What we will see, I believe, is drives that become smarter and have their own filesystem layer that obscures the LBA from the physical location on the disk. The machine says "write this data to block 43533224" and the HDD just starts writing to whatever free blocks are nearest to its r/w head, using the flash to store the map. It will then defrag itself during downtimes to optimize the locations. (Dear Seagate: if I really just invented this, please pay me.)

    63. Re:It'd better happen quick then by camperdave · · Score: 2

      ... I don't think it matters much to me if it takes 171 years or 228 years for the drive to fail...

      Won't somebody please think of the great-great-great-grandchildren?

      --
      When our name is on the back of your car, we're behind you all the way!
    64. Re:It'd better happen quick then by TheRaven64 · · Score: 1

      HD video editing on the other hand is LARGE. My camera spits out 25Mb/s, an hour of video is a little over 11 gigs

      That's pretty good compression. The last time I did any video editing, miniDV was state of the art for consumer-grade stuff, and an SD video camera spat out... 11GB/hour. So, in the transition to HD we've seen the quality improve but the storage requirements remain pretty constant. The (expensive!) external FireWire drive that I was using back then is not much bigger than the SSD on my new laptop and probably much smaller than the SSD in the one I'll replace it with in 3-4 years.

      --
      I am TheRaven on Soylent News
    65. Re:It'd better happen quick then by swalve · · Score: 1

      I agree, MTBF is probably quite valid and accurate. But only for what it claims to be. To me, "mean time between failures" means at that time, half the drives in the population will have died. (Or, there is a 50:50 shot a single drive will have died.) But I would be willing to bet that if you actually ran a population of drives for 171 years, they will all have died. So it doesn't mean what it's name says it does.

    66. Re:It'd better happen quick then by TheRaven64 · · Score: 1

      The surface problems are usually caused by the fact that it has moving parts. A tiny bit of dust hitting the surface of a spinning platter can do a lot of damage. If it gets stuck under the head then it's game over for the disk.

      --
      I am TheRaven on Soylent News
    67. Re:It'd better happen quick then by swalve · · Score: 1

      Yeah, the wear-smoothing stuff, combined with technical advances, should make SSDs just as reliable as HDDs. The only difference will be that the mode of failure will be different. I would imagine that an SSD is going to fail hard when it decides to fail.

    68. Re:It'd better happen quick then by swalve · · Score: 1

      Which is a pretty good out of the box failure rate. I'm not sure there is anything out there that is as complicated as a hard drive that is also as reliable. I don't know what the numbers are now, but in the early 2000s, Compaq was touting that their OOB failure rate was under 10%. (For any kind of failure, hard or soft.)

    69. Re:It'd better happen quick then by TheRaven64 · · Score: 1

      But why put the flash on the hard drive instead of on the motherboard or on an mSATA slot. Flash chips are tiny - a mobile phone can fit 64GB of flash in and still be thin. And why hide it behind a block interface when you'll get better performance by letting the OS control the flash directly?

      --
      I am TheRaven on Soylent News
    70. Re:It'd better happen quick then by Kjella · · Score: 1

      The smaller tech has just as much "heavy use" as the larger tech when equal amounts of board area are dedicated to flash chips.

      True, but then you also get almost the same price. People usually look at $/GB so if you hold GB constant you get a much cheaper and much less durable disk.

      I don't know what you think heavy use means

      OS disk with no optimization for SSDs, downloading torrents, running a freenet node 24x7, filled to 90%+ capacity most of the time, I didn't deliberately try breaking it but I gave it all the write heavy jobs because it took them so easily. In theory I must have written almost 2TB/day to my drive to wear it that much, but I know I didn't, more like 20GB (out of 120GB) maybe. I suspect doing things like downloading a torrent with many, many small writes and FS updates has a huge write amplification.

      --
      Live today, because you never know what tomorrow brings
    71. Re:It'd better happen quick then by DarkOx · · Score: 1

      MTBF for HDD and SSD are both ludicrously high these days

      I can understand describing it as good enough for most people, pretty long, very good for the relatively low cost, etc,etc.

      I would not apply the term ludicrously high, however. I mean its not really ever a good time for a drive to fail. I don't care if you do have RAID ADG, even in those configurations sometimes when a single drive dies bad things happen; even when its just the tech hot-swapped the wrong disk.

      --
      Repeal the 17th Amendment TODAY! Also Please Read http://www.gnu.org/philosophy/right-to-read.html
    72. Re:It'd better happen quick then by swalve · · Score: 1

      The thing about HDDs is that their moving parts aren't really all that "moving". It's not like they have mechanical servos in there banging against stops and creating wear. The heads are moved via magnets and are on bearings WAY more robust than their movement requires. The motor bearings are some kind of magic such that there is basically no wear. Some kind of fluid thing. What is much more likely to fail is the electronics. (Quite like car engines- I recently took apart a car engine with 230,000 miles on it. I could still see the cross-hatching on the cylinder bore.)

    73. Re:It'd better happen quick then by fgouget · · Score: 1

      I have been an early adopter of many things. But I value my data (which is my bread and butter, after all), and so I will take a conservative approach to this. After more people have had them, for a little while longer, I will revisit the issue then.

      If you value your data then no single drive is good enough. The only answer is RAID (1 or 5 typically). If you don't feel like buying two SSDs and you use Linux, then put it in RAID 1 with a regular hard drive using software RAID and write-mostly+write-behind for the HDD. Also remember that you are just as likely to delete a file you care about as the hard drive is to fail. So don't forget about backups, and offsite backups if you can.

    74. Re:It'd better happen quick then by swalve · · Score: 1

      And many laptops of the last few years have had space for two pcie cards, plus a PCMCIA (whatever the newer version is). (My D830 even has a slot for a cellular SIM card.) But manufacturers seem not to be making flash cards in those form factors that are worth a damn. And based on what I've seen in the server arena, I would not be surprised if laptops in current production had internal connectors for SD cards. Not as fast as an SSD, but perfect for holding bootloaders and kernel images, hibernation files and whatnot.

    75. Re:It'd better happen quick then by Bert64 · · Score: 1

      Well, the post i responded to stated it cost him "£20" to send it back, suggesting that he is in the UK, therefore my reply was based on UK laws.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    76. Re:It'd better happen quick then by swalve · · Score: 1

      Because lots of people don't like lugging shit around. There are the other types, like my friend from work, who just LOVES connecting doodads to everything.

    77. Re:It'd better happen quick then by mbourgon · · Score: 1

      THANK YOU FOR THIS. That's a fantastic article. It covers SSDs, mobos, video cards, etc. Wish Newegg did this.

      --
      "Sometimes a woman is a kind of religion, she can save your soul & set you free from all your sins" - Bad Examples
    78. Re:It'd better happen quick then by Kjella · · Score: 1

      Then you will (roughly) replace one disk due to failure for every 1000 hours (100,000 MTBF / 100 disks), or 40 days. It doesn't try to pretend that a single disk lasts 100,000 hours. That's stupid.

      So if you replace one disk every 1000 hours and you have 100 disks, how long must each disk live on average? The MTBF is a half-imaginary number that says that even if you replace your 100 disks each day with new ones, you'll have a disk failure once every 1000 hours. Since nobody actually does that it's a fairly meaningless statistic, in reality your failure rate will go up as the disks age. What you really want is failure rate within first N years of operation, which you can't calculate from the MTBF figures.

      --
      Live today, because you never know what tomorrow brings
    79. Re:It'd better happen quick then by c0p0n · · Score: 1

      I completely agree. I built recently a new brain for my studio and looked into hybrid drives only to get a separate SSD and traditional HDD at the end - first, I need the physical separation of program data and music projects as it just makes life a lot easier for backups, possible reinstalls and moving projects across machines. Second, I could get a decent 120GB SDD + 1TB traditional 7200rpm drive for about the same money I would've had to pay for a hybrid half the total size of that.

      For a normal computer to browse the web and do the usual computery things I wouldn't even think on an SSD either, just a fast enough traditional drive.

      --

      Your head a splode
    80. Re:It'd better happen quick then by ksd1337 · · Score: 1

      Fine, but you're not saying how heavily you're read-writing on those disks.

    81. Re:It'd better happen quick then by angel'o'sphere · · Score: 3, Insightful

      If you would care to read up what MTBF actually means and how it is used you would not say it is BS.

      If you have a drive with MTBF of 171years, how likely is it will fail during its expected usage period of 5 years? It is 2.88%

      What is the likelihood a drive with 230 years MTBF will fail during the next 2 years? It is 0.86%

      The formular is p(a) = 1-e ^ (- a/mtbf)

      If you can not work with that, don't balme the engineers that can.

      --
      Cost free eBook I read (by iBook/Kobo/Amazon/ObookO/Gutenberg etc.): "The Green Odyssey" by Philip Jose Farmer.
    82. Re:It'd better happen quick then by daid303 · · Score: 1

      A MTBF of 171 is clear and utter bullshit. And claiming it is just plain lies. Unless you put the harddisk in a sealed box and don't touch it for the rest of it's life.

      We produce products with a MTBF of 10 years. On average we expect our product to last 10 years, and that's tough. If we wouldn't aim for 10 years MTBF we could cut 15-30% of our production price. Our stuff is made to last, and that's what we pay for (and our customers)

    83. Re:It'd better happen quick then by Maximum+Prophet · · Score: 2

      That's because it doesn't do anything good for hard drives. There was a paper about it some years ago, I'm too lazy to google it up, but even 32 MB is too much (I think the sweet spot was around 2 MB).

      The sweet spot will be very application and OS dependent. In the old days, the drive didn't have any cache, and the controller couldn't hold much more than 1 sector. So, when the head dropped, you had to wait for your sector to spin around before you could read. If you then needed the adjacent sector, you might have to wait for an entire revolution before you could read it. Schemes like interleaving were devised to get around this. (Logical sectors N and N+1 were physically 2 or 3 sectors apart)

      With IDE, the controller was migrated mostly to the drive, and a bigger cache was added. If you can cache the entire track across all the heads, you can drop your heads on any track and start reading after a small settling time. Then give the OS the exact sector it asked for. Most of the time, the next sector the OS asks for will be in your cache, so you win. If you have this much cache x2, you can move your head and start reading before the OS is done with the current cached track.

      Beyond 2x an entire track, you have to play guessing games. A better OS will already to all the optimizations like sorting requests, and caching frequently used sectors, so if you aren't rebooting too often, more cache on the drive isn't a big win.

      --
      All ideas^H^H^H^H^Hprocesses in this post are Patent Pending. (as well as the process of patenting all postings)
    84. Re:It'd better happen quick then by symbolset · · Score: 2

      Or in some cases a capacitor, not a battery, commits the RAM cache to flash storage in the event of a power failure. As the capacitors on enterprise-class SSDs do.

      --
      Help stamp out iliturcy.
    85. Re:It'd better happen quick then by Hatta · · Score: 1

      Back in the real world I kill laptop drives at least every 2 years, and desktops every 5.

      WTF are you doing to your HDDs? I have about 9 hdds in desktop computers in my home. By your logic I should be suffering a failure about twice a year? I have suffered exactly one hard drive failure in 5 years and that was after I had powered it down and let it sit for a year.

      --
      Give me Classic Slashdot or give me death!
    86. Re:It'd better happen quick then by rnturn · · Score: 1

      I recently retired an old 2GB DEC drive (an RZ28 removed from the StorageWorks brick back in the mid '90s) that was starting to log numerous errors. It had been running almost continuously since it had been built, IIRC, in '91 (its birth based on the dates on the controller chips). Heck, I've still got a few of the RZ28s and RZ29s running in Linux systems. On the other hand, I've yet to find a SATA drive that hasn't started logging errors far, far sooner than that old RZ28. Granted, there are quite a few more blocks to deal with on those SATA drives but when they start logging errors before I've finished installing the operating system, that's way too soon. As a result of those SATA experiences, I won't use them in a non-mirrored configuration. Pity the drives that can work in a RAID setup cost so much more than what I can get at the local big box store.

      --
      CUR ALLOC 20195.....5804M
    87. Re:It'd better happen quick then by Maximum+Prophet · · Score: 1

      A better stat (for disk drives) is the warranty period. The rule of thumb is the manufacturer has to make the drive last 5x the warranty or there will be too many returns.

      However, you have to ask, will this company be around at the end of the warranty? Is the company just charging enough extra so that they've amortized the cost of the returns? (This is the way automobile battery companies work)

      --
      All ideas^H^H^H^H^Hprocesses in this post are Patent Pending. (as well as the process of patenting all postings)
    88. Re:It'd better happen quick then by TheThiefMaster · · Score: 1

      What you really want is failure rate within first N years of operation, which you can't calculate from the MTBF figures.

      Actually MTBF is defined as failure rate in the "constant failure rate" stage of a components lifetime, which is between the initial failure rate (aka infant mortality) and wear-out failure stage. So it's actually the failure rate over the regular lifetime of the component (typically 1-5 years).

    89. Re:It'd better happen quick then by symbolset · · Score: 1

      This solution requires OS support, which will vary in quality. The OEM can control the way the RAM cache and SSD cache is used on the drive. The 4GB flash on these drives is, I think, too small. It may have good technologies like write combining and lazy write to flash that might help prolong life though.

      --
      Help stamp out iliturcy.
    90. Re:It'd better happen quick then by abigsmurf · · Score: 1

      UK laws sadly only cover vague "reasonable" time frames.

      It's become fairly common for retailers to only offer between 1 and 6 months for components before forcing you to deal with the manufacturers unless you buy an extended warranty. Not to mention, retailers are far more likely to pull "wear and tear" or "faulty installation" excuses on you and give you hassle.

    91. Re:It'd better happen quick then by |TheMAN · · Score: 1

      "they" did... it's called Intel Turbo Memory.

      The very first iterations of them were mediocre at best, so everyone automatically concluded the idea sucked and it was doomed from there. The 2nd generation Turbo Memory cards actually worked decently (as long as the crappy drivers didn't take a dump on you), especially with slightly older HDDs which aren't quite as fast as today's newest drives. But by that time nobody cared and SSDs and hybrid HDDs gained a foothold. The end.

      You can buy these cards off ebay of course, but the largest 4GB cards are so not worth the money. The 2GB cards are reasonably priced. Either one works in your D830, unofficially. It goes into where your cellular card goes, so if you are using it for that, then out it goes!

    92. Re:It'd better happen quick then by Smallpond · · Score: 1

      I'll seriously invest in SSDs when they consistently surpass 1 or 2 million write-cycles per block (not just per cell). Until then, they might be great for caching but I'm not seeing the reliability I want.

      (P.S. Please don't lecture me about wear-leveling, etc. I know how they work.)

      Let's compare 1 million seeks on SSD - whoa, seek is a no-op! Nothing has to move.
      Now do 1 million full-stroke seeks on a HDD. That sound? Its the disk head wearing out and crashing on the platter. You do any mechanical motion 1 million times it causes wear.

    93. Re:It'd better happen quick then by FlyingBishop · · Score: 1

      I would expect that not only would a hybrid drive have that problem, but you wouldn't be able to recover because it's hard-wired to pretend it's a single disk and you can't just fall back to using it as two separate disks if the controller that does the caching has a failure.

    94. Re:It'd better happen quick then by Anonymous Coward · · Score: 1

      Yo dog, we heard you liked computers, so we put a computer in your computer so you can compute even when you're not computing.

    95. Re:It'd better happen quick then by stubob · · Score: 1

      That's my problem with it. I have a previous generation Momentus XT 500GB, and you described what I want it to do. Sure, it's great that the cache learns what you're doing, but I rarely do the same thing repetitively. Some days I'm running VMs, some days I'm working on video, some days I'm just messing around on the web. If I could tweak to say "optimize for boot time" or "optimize for application loading" and tell it what to keep in the cache, that would be great.

      If we could look at it like a traditional HD with a small, dedicated SSD, that would be ideal. Just let me tell it what to put on the SSD and leave it alone.

      --
      Planning to be moderated ± 1: Bad Pun.
    96. Re:It'd better happen quick then by antdude · · Score: 1

      SW:TOR = 20 GB for its recent beta tests. Later there will be updates, addons, etc. :(

      --
      Ant(Dude) @ Quality Foraged Links (AQFL.net) & The Ant Farm (antfarm.ma.cx / antfarm.home.dhs.org).
    97. Re:It'd better happen quick then by ChumpusRex2003 · · Score: 1

      But MTBF isn't a useful measure for a single drive. It's a measure for a population of drives.

      If I have 10,000 hard drives in my datacenter, then an MTBF of 1,500,000 hours means that I need to plan for replacing approximately 60 drives each year (with some allowance for bad years and good years), whereas an MTBF of 2,000,000 hours means I only need to plan for an expected 45 replacements.

    98. Re:It'd better happen quick then by asc99c · · Score: 1

      Given that it's £20, it's the UK and the GP is correct. Retailers try to get out of it / say that it is a manufacturer issue, but of course they would. It is still down to the retailer to sort out the problem with the manufacturer on your behalf.

    99. Re:It'd better happen quick then by Eil · · Score: 1

      Age of conan, 33 GB. LA Noire13 GB. Mortal Online, 30 GB.

      That is stuff ordinary people do

      Take it from me, PC gamers are not ordinary people.

    100. Re:It'd better happen quick then by ChumpusRex2003 · · Score: 2

      I'm guessing that you don't make stuff with an MTBF of 10 years. An MTBF of 10 years means that each year 10% of the items are breaking down and requiring repair/replacement due to some form of break down. In most industries, with products that unreliable you'd be out of business pretty quick.

      MTBF is a completely different measure to expected lifetime. The expected lifetime is just that - how long the device is expected to work for, before its performance becomes unacceptable (i.e. when the device becomes worn out).

      MTBF measures how reliable a device is *during* its expected lifetime (i.e. before the device becomes completely worn out).

    101. Re:It'd better happen quick then by eviljolly · · Score: 1

      In my opinion, the best option is just to buy two separate drives. Get a cheaper 120GB drive for your OS/programs, and continue to use hard drives for mass storage. There aren't huge performance differences when it comes to things like video, mp3s, or pictures. The place where you'll see the most benefit is OS loading speed, or how fast programs launch and games load.

      I've used hybrid drives, and they are pretty good option for laptops, but you're really better off spending the extra money on a true solid state drive if it will be enough to contain your data.

    102. Re:It'd better happen quick then by operagost · · Score: 1

      I'm pretty sure this is what disks already do (thus the term "Logical Block Addressing"); you're just adding another level of abstraction.

      --

      Gamingmuseum.com: Give your 3D accelerator a rest.
    103. Re:It'd better happen quick then by Mashiki · · Score: 1

      . Most people don't really need massive HDDs and so if smaller SSDs get cheap enough that'll be the way they'll go.

      What are you talking about? Well I guess if you don't game for your relaxation then you don't need a small HDD. My steam folder, which has about 30% of the titles I own installed comes out at a toasty 280GB. That's not inducing games that aren't installed there. Figuring in those, I'm easily pushing 540GB. And that's still not even half of my collection.

      Don't need massive HDD's? Right.

      --
      Om, nomnomnom...
    104. Re:It'd better happen quick then by Gaygirlie · · Score: 1

      I was actually just thinking today to myself that it should be a feature built-in to the OS: you tell the OS which stuff it should optimize for speed, you could assign one or several devices to use for that, and then the OS would figure out the best way to do that. Like for example the OS would include a tool that lists all installed application and games, then things like "browser cache", "my personal documents", "Custom files", and would also allow you to tick on/off OS itself from the list, and so on. There are and always will be shortcomings when a device tries to cache stuff when it doesn't know user's own preferences or how the operating system itself manages files and its own caches, so why leave it to hardware? Why not instead have the OS optimize the thing?

      I do realize that SSDs are becoming the norm soon and old mechanical drives are on their way out and eventually they'll be reserved a niche space somewhere. But then the next big, fast thing will come and people will wish to again use it as a cache for SSDs, and so on, and that's why I also think the whole caching system should be built-in to the OS itself because it has access to all the needed data to optimize the thing.

      It would be interesting to see someone start a research project around this idea on some open-source OS, but it remains to be seen if anyone is willing to do that. I personally don't have the skills needed.

    105. Re:It'd better happen quick then by Bert64 · · Score: 1

      Not exactly...
      What the retailer offers is irrelevant, they can make additional offers but they cannot take away your statutory rights under the law... They will often try to claim otherwise, but this is only because most people aren't aware of their rights and capitulate.

      Some good reading is available at:
      http://www.moneysavingexpert.com/shopping/consumer-rights-refunds-exchange

      In particular, within 6 months it is the responsibility of the retailer to prove that the goods were not defective when bought... A lot of retailers will argue, but soon capitulate if you quote your rights and threaten to take them to the small claims court.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    106. Re:It'd better happen quick then by Eric+Green · · Score: 1

      The primary reason why most laptop vendors don't offer a hard drive in place of the optical drive is power consumption. Optical drives use basically nothing when they're sitting there idle, and since most optical drives today are used about as much as floppy drives were used in the mid 1990's (i.e., virtually never, only to install software, and even that is going away with Internet delivery of software), that means that they can spec the rest of the laptop around a lower power draw, which allows them to claim a longer battery life and allows them to use a smaller fan to cool the laptop and a smaller brick to power the laptop and allows you to actually set the laptop on your lap without scorching your lap and requiring a trip to the surgery suit for skin grafts. The large desktop replacement laptops from Dell and HP (amongst others) actually do have space for multiple hard drives, but those are more portable desktops than laptops -- you aren't going to unplug one of those and walk across the lab with it to plug into a different network to sniff for a rogue machine that's brought your installation to a crawl, they sit on a desk and stay there, with short excursions to the car and home perhaps, because they are large, bulky, hot, will last maybe 20 minutes on battery power, and have power bricks the size of concrete blocks.

      Given that, if you need a lot of space in a single 2.5" form factor package to fit into, say, a current Apple Macbook Pro (where Apple very highly optimizes the power consumption and the OS really doesn't deal well with you removing the optical drive and putting in a second hard drive using a third-party bracket, it won't go to sleep correctly much of the time), the hybrid approach makes a lot of sense. The primary issue with the prior generation of the Momentus XT in that application was a) it topped off at 500GB, and b) it consumed more power than a 750GB 7200 RPM Western Digital Black drive. The current generation solves the capacity problem, but I'll need to take a close look at power consumption, because power budgets in many modern slim (i.e., actually portable) laptops are quite tight.

      --
      Send mail here if you want to reach me.
    107. Re:It'd better happen quick then by badran · · Score: 1

      To easy to fail.

    108. Re:It'd better happen quick then by operagost · · Score: 1

      Use SLCs and the distinction between block-level and cell-level write cycles becomes moot.

      --

      Gamingmuseum.com: Give your 3D accelerator a rest.
    109. Re:It'd better happen quick then by operagost · · Score: 1

      That guy must have changed his oil religiously.

      --

      Gamingmuseum.com: Give your 3D accelerator a rest.
    110. Re:It'd better happen quick then by markhahn · · Score: 1

      nah, batteries do not add significant cost. the real issue is that it adds failure modes and thus support costs, which is ugly in a high-volume consumer product.

    111. Re:It'd better happen quick then by citizenr · · Score: 1

      As SSDs get cheaper and cheaper

      they get cheaper because of technologies like MLC and lately TLC, MLC = 10x worse than SLC, TLC = 100x worse.
      MLC lets you extensively use SSD/pendrive for about 2 years before it starts failing, TLC will make those drives fail after a year of extensive use.

      I still have 10 year old harddrives that are perfectly fine. Basically if it doesnt fail in 1-2 years it will work 10 and more.

      HDD = infinite write to a sector, TLC = 1000 writes in best case scenario.

      --
      Who logs in to gdm? Not I, said the duck.
    112. Re:It'd better happen quick then by AcquaCow · · Score: 1

      The cache on a hard disk is often used as write cache - store incoming data in cache, leave actually committing it to disk until a convenient opportunity arises.

      32MB of cache doesn't take that long to flush. 1GB, OTOH...

      You're forgetting that a hybrid drive would be using NAND flash vs DRAM... NAND is a NVRAM and won't have to be flushed to disk in the event of a power outage. It is persistent.

      That said, they may still use a little bit of DRAM cache in the drive.

      -- Dave

      --

      up 12 days, 22:30, 2 users, load averages: 993.20, 994.21, 994.56
      *makes note to limit user processes...
    113. Re:It'd better happen quick then by spire3661 · · Score: 1

      I'm sorry, but OCZ needs another decade of good quality products under their belt before they can ever be considered. They have a terrible track record of not following standard practices, shoddy workmanship and abysmal customer service.

      --
      Good-bye
    114. Re:It'd better happen quick then by spire3661 · · Score: 1

      My Steam folder has 100 GB of games in it just from this year alone. WoW is up to 30 GB. The SWTOR BETA was 20 GB. But yeah normal users dont need space.....

      --
      Good-bye
    115. Re:It'd better happen quick then by spire3661 · · Score: 1

      Perhaps you should read this before you disparage the high precision moving parts of a HDD http://geekscomputer.blogspot.com/2008/07/hard-disk-drive-analogy.html

      --
      Good-bye
    116. Re:It'd better happen quick then by Christian+Smith · · Score: 1

      What we will see, I believe, is drives that become smarter and have their own filesystem layer that obscures the LBA from the physical location on the disk. The machine says "write this data to block 43533224" and the HDD just starts writing to whatever free blocks are nearest to its r/w head, using the flash to store the map. It will then defrag itself during downtimes to optimize the locations. (Dear Seagate: if I really just invented this, please pay me.)

      Oh god, no, please don't. All the problems in SSD firmware has been related to maintaining the underlying block remapping. Besides, the HDD will have no concept of "free blocks", unless it puts aside tracks just for this purpose (though not necessarily a bad idea, it will waste some capacity). Hmm, perhaps sacrifice 1% of the data tracks for regional based journalling, might improve write performance significantly.

      One development on the horizon is shingled recorded writes, where tracks overlap when written, and the resulting overlapped tracks can be read by a much finer head than the write head. This increases capacity, but at the cost of requiring block remapping as writes now have to be written in a continuous log. Thus, you end up with a log structured block device.

      While a pain because it requires firmware to handle the block mapping, it does allow low latency fast writes (because they're always sequential) and as you've got the block mapping firmware anyway, you can implement a sophisticated read cache using FLASH or large RAM to satisfy reads without moving the head from the head of the log. Your firmware will already be quite sophisticated anyway, so the step up to a hybrid caching firmware might not be so great as it currently is.

    117. Re:It'd better happen quick then by tlhIngan · · Score: 1

      SSDs typically have large memory caches, where as HDDs are still stuck around the 32MB mark. With RAM so cheap these days even the lowest end graphics cards are coming with 1GB, but not HDDs for some reason.

      Actually, SSDs don't have that big of a cache. Just maybe a few MB or so. Most of it is used to hold the working memory for the controller and for garbage collection purposes, but the data is basically streamed to and from the flash chips themselves.

      A large RAM cache would be disasterous for an SSD - you'd see it as very fast performance for a little bit, then performance collapses once you reach a certain size.

      GIven modern SSDs have easily 16 flash controllers working in parallel, achieving 250+MB/sec speeds isn't out of the question (it's only 16MB/sec per chip, which is well within what a NAND flash chip can do).

    118. Re:It'd better happen quick then by jedidiah · · Score: 1

      "Ordinary" people take enough photos and video and have enough MP3 files and games that your typically sized SSD just doesn't cut it. This isn't a "geek thing". Its' a "using your PC for anything but a dumb terminal" thing.

      Just Windows 7 by itself will eat up a good chunk of a reasonably priced SSD drive.

      You don't need to be a video pack rat to blow through the storage you get on current SSD drives.

      --
      A Pirate and a Puritan look the same on a balance sheet.
    119. Re:It'd better happen quick then by Jumperalex · · Score: 1

      So long as you have TRIM enabled and functioning, and have certain OS features tuned (win7 automaticalyl turns off superfetch, defrag etc), then stop worrying and learn to love your SSD.

      --
      If you can't be good, be good at it!
    120. Re:It'd better happen quick then by Jumperalex · · Score: 1

      Do you have failure rates for spining drives? A little research might just show you that they are basically on par with the numbers you are quoting.

      http://www.pcworld.com/article/131168/harddrive_failures_surprisingly_frequent.html

      http://blog.backblaze.com/2011/07/20/petabytes-on-a-budget-v2-0revealing-more-secrets/
      "All told, Sean replaces approximately 10 drives per week, indicating a 5 percent per year drive failure rate across the entire fleet, which includes infant mortality and also the higher failure rates of previous drives. (We are currently seeing failures in less than 1 percent of the Hitachi Deskstar 5K3000 HDS5C3030ALA630 drives that we’re installing in pod 2.0.)"

      For reference, when comparing A and B you should remember to actually quote the data for both A and B and not just one of the other as your proof that one is better than the other.

      --
      If you can't be good, be good at it!
    121. Re:It'd better happen quick then by hairyfeet · · Score: 1

      Sorry but you are wrong, and here is why: Everyone and their dog has ever growing piles of media. Even those that don't keep movies on their drives (which more and more are, being able to have a media library on your netbook or use your desktop as an HTPC by streaming to your new net enabled TV is nice) I've found coming to me for HDD upgrades simply because they are running out of space on all those 200Gb and 300Gb hard drives. they have videos of their families, tons of pictures, software up the wazoo, that space goes damned quick my friend.

      Lets be honest folks, the ONLY reason anyone is mentioning SSDs is because the HDD manufacturers put all their eggs in a single Bangkok basket and had the basket go floating down the street. Before the stupidity with the flood I was getting 1Tb drives for $36 and 2Tb drives for $56. i'm sorry but NO SSD comes even close to those numbers, not in any way shape or form. By the time you can get a 1Tb SSD for that price we'll have 10Gb HDDs (Seagate and WD have both written papers about quadrupling capacity with new nanotech) for $90.

      Finally as I got to see first hand from some of my gamer customers whose data went "poof!" the ONLY reason SSDs are getting cheap is that they are abandoning SLC for MLC and thanks to the insane failure rates as Jeff Atwood pointed out MLC drives really have to be judged on a "hot/crazy" scale as the hot speed come with crazy failure rates. I had 4 gamer customers go SSD, the fastest drives, no expense spared, not a single one made it past the 2 year mark. Hell I have 20gb HDDs that still run fine, what I'll do with them I have no clue but the data is still there.

      So if you have the money to have spares, don't give a shit about your data or have a REAL HDD to back up constantly then yes, SSDs can work. but dealing with everyday folks I can tell you backups? Is like pulling teeth with most folks and while I can often get the data off a failing HDD with a failed SSD you are SOL unless you happen to have an electron microscope handy. all it'll take is a few horror stories of Suzy losing their late mother's pictures to kill any desire for SSDs QUICK.

      Hell you watch, the HDD manufacturers get their collective shit back together and you'll be seeing $200 barebones and $300 netbooks with huge drives again and nobody but geeks and benchmark addicts will give SSD a second thought. For the average Joe it is ALWAYS about the numbers and bigger is ALWAYS better.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    122. Re:It'd better happen quick then by phoenix_rizzen · · Score: 1

      Western Digital RE4 drives now come with 64 MB of cache.

    123. Re:It'd better happen quick then by hairyfeet · · Score: 1

      Dude I don't know who made up this "paper" but I'd like to say they are full of shit as in my own benches I saw first hand an 8Mb Seagate 7200RPM get stomped by a Samsung 5400RPM with 32mb of cache. I've compared 2Mb, 8Mb, and 32Mb and with each the jumps have been pretty dramatic, some as high as 40% gains in burst. With the Seagate VS Samsung it went from a maximum rate of 96 to 134, that's a pretty big leap especially when we are talking one being 7200RPM and the other 5400RPM.

      The only way I can see that paper having any relation to RL is if they used XP for the benches, as XP doesn't have NCQ support thus the drive is gonna have to spin pretty much constantly anyway. in 7 that large cache lets the drive time its read/writes more efficiently and that equals more speed.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    124. Re:It'd better happen quick then by hairyfeet · · Score: 1

      Actually I'm pretty sure you just described what the hybrids are doing and that is what worries me. How in the hell do we zero out a drive if the file system is a lie? I get a lot of free boxes donated to me by offices because they know I'll refurb them for the poor and that I do a standard DoD 3 pass just to make sure its completely clean. How am I supposed to wipe a hybrid? Has anybody actually found a way to securely wipe the NAND portion of a hybrid?

      --
      ACs don't waste your time replying, your posts are never seen by me.
    125. Re:It'd better happen quick then by samwichse · · Score: 1

      Keep in mind too... I was looking at one of these drives in a Newegg black friday sale, and the big thing about that 8GB of flash is that it is not MLC, it's SLC flash, which is significantly more expensive.

      This one, for example:
      http://www.newegg.com/Product/Product.aspx?Item=N82E16822148591

    126. Re:It'd better happen quick then by hairyfeet · · Score: 1

      I can tell you I had 4 gamer customers that were the classic "must win teh benches!" types, one so bad his grandma is using a Skulltrail box because frankly that was the slowest hand me down he had left, and ALL FOUR had their SSDs fail within 2 years. these guys didn't buy cheap crap either, it was always what was at the top of the benches when they bought, most were either Intel or OCZ I believe is the name of the company. As for what they did? Play games, watch videos, run benches, pretty typical gamer stuff.

      Meanwhile you can just call my pokey as I have 6Tb of HDDs and they show zero signs of failing, thanks. hell i have a drawer full of drives going back to 20Gb, don't know wth to do with the smaller ones but ALL of them are readable. So I'd take that MTBF with a big heaping of salt, and I'd read the link I posted previously about Coding Horror and the "hot/crazy" scale for SSDs. It is an interesting read and show the failure rates I saw weren't just a fluke.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    127. Re:It'd better happen quick then by ak3ldama · · Score: 2

      I think most people understand the direct application of a statistic such as MTBF. From what I can tell: the problem is that there should be a better statistic. It should even be updated over time, perhaps quarterly. Eventually the Adjusted MTBF value could be based on actual data. This isn't something that any company really likes to put out though. Imagine if Chevrolet had a real number given for something like their average miles driven until rebuild. Suddenly everyone would figure out why their small block engine has such cheap rebuild kits.

      --
      "but money is the God of Algiers & Mahomet their prophet." - Rich. O'Bryen June 8th 1786
    128. Re:It'd better happen quick then by mikael · · Score: 1

      Things like that were happening 25 years ago. Once company designed their their network hardware to have hardware MAC addresses written to flash memory upon bootup. The theory being that these systems would only be powered up once every few weeks at the most.

      Unfortunately, they didn't consider a unavailable network combined with a hardware reboot mechanism invoked by network timeouts. The side-effect was that a machine would end up burning its own flash memory if there wasn't a network already set up.

      --
      Vintage computer adverts: http://www.vintageadbrowser.com/computers-and-software-ads
    129. Re:It'd better happen quick then by Gazzonyx · · Score: 1

      I'd be curious to see an apples to apples comparison between cache sizes of disks from the same manufacturer. The problem is that the controller might be much more optimized on one drive more so than another (IE, the cache won't make so much of a difference). For instance, I've heard WD drives are very much not optimized for utilize their cache effectively, although I can't find anything to actually back that up.

      --

      If I mod you up, it doesn't necessarily mean I agree with what you've said, sorry.

    130. Re:It'd better happen quick then by drinkypoo · · Score: 2

      How in the hell do we zero out a drive if the file system is a lie?

      There's an ATA-SE command which is a fairly new part of ATAPI but which drives can optionally support. You have to trust the manufacturer for that, but guess what? Remapping bad blocks has been going on for some time, and there is no way for you to erase those blocks without the cooperation of the disk controller. In theory you could swap the controller and then perform a new low-level format, assuming you trust the disk to do that. I wouldn't personally make assumptions, but if I were, I'd imagine that professional drives from top-tier vendors will probably have a fairly meaningful ATA-SE command, while the further you go down the list, the less likely they will be to implement it at all, let alone get it right.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    131. Re:It'd better happen quick then by drinkypoo · · Score: 1

      I was trying to give a significantly vague answer because it wasn't clear at least to me whether the question was about this particular case or in general. I answered the asked question, not the implied one, or at least that's what I Thought I was doing :p

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    132. Re:It'd better happen quick then by hairyfeet · · Score: 1

      I'd love to be able to help you out friend but here at the shop I tend to buy in batches when I hear there is a "good batch" in the pipe. For example I don't know whether you know this or not but talk around the campfire is avoid Seagate over 500Gb like the clap! They got the cheap ass ARM controllers from Maxtor and between that and some bad firmware most of the over 500Gb Seagate drives me and my fellow builders have seen have been seriously flaky or just plain crap.

      But to me the telling point on the cache issue was going from a 7200RPM 400Gb Seagate and a 320Gb WD to a 1Tb Samsung plus a 2Tb Samsung, both EcoDrives. Now both the WD and the Seagate had 8Mb of cache, both the 1Tb and 2Tb Samsung EcoDrives* have 32Mb. With both the Seagate and the WD I was hitting max sustained of 95-97 with a max burst of 105-109, both 7200RPM. With the samsung even though they are both 5400RPM EcoDrives I was hitting 108-115 sustained and nearly 136! Burst speed. That is a HELL of a big jump! The EcoDrive with the large caches impressed me so much I actually sold the 320Gb WD I was using as an OS drive and replaced it with the 1Tb Samsung. I gained probably 15 seconds on a cold boot even with the lower rotational speed!

      * (which BTW I know they are high now but BUY THE SAMSUNG ECODRIVES, they are awesome and I've only been hitting max temps of 92f under load! The ones they have left are the last three batches before they sold out and frankly all 3 batches are top notch. I've put them in some hellish positions like construction trailers where the funk gets seriously thick, and they NEVER get hot and have yet to have a single issue! I just wish I'd have bought more of them when i had the chance!)

      --
      ACs don't waste your time replying, your posts are never seen by me.
    133. Re:It'd better happen quick then by hairyfeet · · Score: 1

      Thanks for the info. I usually just use UBCD and once booted from it have it do a low level DoD 3. I know its overkill and a simple zero pass would do the trick but it really doesn't add any extra time worth noting and its nice to be able to tell those offices that are kind enough to donate "Don't worry I use the same wipe they do at the DoD" which makes them feel better about it.

      These hybrids do worry me though, the LAST thing I need is another round of "ZOMFG we have to destroy the drives or they'll take our stuff ZOMFG!" like there was a few years back. As it is I sell those donated dirt cheap, just mainly repaying the cleaning solutions for the fans and cases, but if I were to have to switch the drives i could see them becoming too expensive for poor folks. as it is I'm usually able to sell them an office P4 with KVM for less than $100, fully loaded with FOSS software and ready to use. that makes them low enough anybody can afford them and lets me buy more cheap monitors to put with them. But if I were to have to go out and buy even 40Gb HDDs to load them up with I simply couldn't afford to do it and there would be a lot of poor folks here that wouldn't be getting a PC for little Suzy for Xmas.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    134. Re:It'd better happen quick then by Jane+Q.+Public · · Score: 1

      "But if you say you are not using SSDs on your desktop or laptop because you don't want to risk losing your data, all that means is you don't value your data enough to back it up, because if you were backing it up, that wouldn't be a concern. :p"

      Here is my actual rationale, which is really more one of costs than risk:

      If I put in an SSD now, I would convert my existing drive to a data-storage-only role. So I am figuring the amount of money it would require for me to shop for and purchase a new drive, then install an OS and all my development tools, and copy my data. That is at least a day, probably more like 2 (I have a very large number of apps installed, largely for development). Not just the money for the drive, but also the work time lost, which is also money. Plus the potential of the following scenario: having the drive fail, and so having to go to the store (with a failed drive I'm not going to wait for an online purchase), and purchase yet another drive, and install an OS and all my dev tools yet again, and copy my data onto the drive yet again...

      So you are talking say 2 days worth of work and the cost of a drive, with a potential (however slight) of losing more than 4 days' work and the cost of 2 drives. And as much as I hate to say it, sometimes Murphy's Law does seem to apply so it is as likely as not that any failure would occur when something important was going on.

      To me, the actual cost plus the potential cost is not worth the performance gain I would see. It might pay for itself in the long run by saving me time, but that benefit is amortized over a long time. Longer than I want to bet on right now.

      No doubt I will switch to SSD eventually. Just not quite yet.

    135. Re:It'd better happen quick then by CSMoran · · Score: 1

      I can tell you I had 4 gamer customers that were the classic "must win teh benches!" types, one so bad his grandma is using a Skulltrail box because frankly that was the slowest hand me down he had left, and ALL FOUR had their SSDs fail within 2 years. these guys didn't buy cheap crap either, it was always what was at the top of the benches when they bought, most were either Intel or OCZ I believe is the name of the company. As for what they did? Play games, watch videos, run benches, pretty typical gamer stuff.

      Two points. First, the fastest ("teh benches-winning") hardly ever means the most reliable. Second, you can actually benchmark an SSD to death.

      --
      Every end has half a stick.
    136. Re:It'd better happen quick then by Luckyo · · Score: 1

      I obviously referred to damage incurred in normal use, not damage incurred by improper handling. I don't drop my laptops while using them, and as a result, don't have a significant increase in mechanical failures on HDDs in them.

      Also, you ignored desktops.

    137. Re:It'd better happen quick then by Luckyo · · Score: 1

      Most surface problems are caused by simple wear out due to time passage, rather then disk hitting the head. These would happen even if disk was stationary and head was reading the surface with some uber gear from much bigger distance.

      If you actually get dust INSIDE your HDD, you're fucked. It means seal has been breached and the disk is toast anyway.

    138. Re:It'd better happen quick then by toddestan · · Score: 1

      I think it's the controller, as generally the PC doesn't even see the drive at all, as opposed to seeing that there's a drive but being unable to read/write to it which would suggest the actual storage medium.

      Been there, done that. The SSD was fun but I'm going to go stick with hard drives until the technology matures some more.

    139. Re:It'd better happen quick then by toddestan · · Score: 1

      Depends on what the 'device' is. An automobile would probably fit that pretty well - expected to last ten years with perhaps one unexpected major repair needed sometime in that period.

    140. Re:It'd better happen quick then by toddestan · · Score: 1

      Large companies that have statistically significant numbers of drives have found failure rates to be higher than what they should be given the quoted MTBF numbers from the manufacturers. Google, for example, found an annual failure of around 3% for their drives in that study from a few years back, and they have a very large number of drives. The 100+ year MTBF numbers are complete bullshit.

    141. Re:It'd better happen quick then by Volta · · Score: 1

      Now I have 512GB of SSD storage for OS, apps, and primary data. That is then backed by 3TB of HDD storage for media, samples, and so on.

      You do realize what you've done is create a hybrid drive system where you have to manage what data is stored where, instead of letting the drive do that for you, right?

    142. Re:It'd better happen quick then by spire3661 · · Score: 1

      The point is, its not jsut warez and pr0n taking up huge swaths of space anymore, but rather millions average joe GAMES, legally purchased digital music and movies etc etc. Its really not hard to fill up a 500 GB drive with totally legal everyday stuff that NORMAL people buy.

      --
      Good-bye
    143. Re:It'd better happen quick then by hairyfeet · · Score: 1

      Except they would only run a benchmark ONCE when they got a new piece of gear. If a max of 4 benches (one for CPU, GPU, SSD, and RAM) would kill an SSD? Thanks for proving my point friend. I can sit here and have my HDD run benches for the next 6 hours, at 4 minutes a bench that would be 90 benches and I'll bet my last dollar I won't have a single failed sector.

      My customers are mostly normal folks, they have data on their machines that is precious to them and I can't think of a single one that would be willing to risk that data, even for the increased speed of SSD. At this point the tech is just too immature, it reminds me of the old first gen HDDs where the things would die left and right and you were afraid to cough in the same room. They just have too many bugs ATM for me to recommend them to ordinary folks.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    144. Re:It'd better happen quick then by CSMoran · · Score: 1
      It's either

      As for what they did? Play games, watch videos, run benches,

      or

      Except they would only run a benchmark ONCE when they got a new piece of gear.

      but not both.

      --
      Every end has half a stick.
    145. Re:It'd better happen quick then by hairyfeet · · Score: 1

      They ran benches every time they added to the kit. Kinda pointless to run benches just because its Tuesday. Are you really this obtuse or are you just being pedantic for shits and giggles?

      hell don't take MY word for it, read the article for yourself. note that even though atwood says the high failure rates is worth the speed remember this man spends $400+ just on a pair of headphones so having a half a dozen brand new SSDs as spares? NOT a problem for him. hey if you have that kind of money knock yourself out, me I got better things to spend it on.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    146. Re:It'd better happen quick then by drinkypoo · · Score: 1

      I should think this would be beyond obvious, but I suspect the amount of hybrid storage which improves performance will always vary significantly based on the type of workload. If you're continually reading lots of small, scattered files, then a large cache might well provide signficant benefits, whereas if you tend to make long sustained reads (let alone writes!) then the cache is less and less important... I would imagine that unused blocks are spread around the disk to minimize the impact of remapping, as well, but I honestly don't know much about that.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    147. Re:It'd better happen quick then by swalve · · Score: 1

      But there's no way to get the bad block back, either. Even if someone could open up the drive or attach different boards, the block is *bad*. Whatever was written there isn't there no more. I don't know what the threshold for a block getting marked *bad* is, but I'd bet it is when the ability of the ecc schemes to correct the errors is just about used up. And with the fancy encoding algorithms used to write to drives, one too many flipped bits is going to scramble the data.

    148. Re:It'd better happen quick then by drinkypoo · · Score: 1

      But there's no way to get the bad block back, either. Even if someone could open up the drive or attach different boards, the block is *bad*.

      There may well be useful data in that block, and if you had an alternate controller that was willing to spit it out to you, you might be able to read part of it. What we want is for blocks to be erased whether the disk thinks they're bad or not. And anyway, I don't know if this still happens, but bad blocks used to come back on old disks. I don't know why, but speculation abounded. I don't know if it does on new ones, because I don't do my own bad block management any more. I can live without a block here and there, so I've never looked into it... the payback doesn't exist. But I still want them erased.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  2. "No" by kheldan · · Score: 1

    HDD for mass storage, small SSD for OS, installed software, and most frequently accessed files.

    --
    Are YOU using the TOOL, or is the TOOL using YOU? Think about it!
    1. Re:"No" by gl4ss · · Score: 1

      so it's not the time for hybrid drives - but it's the time for hybrid setups?

      on a laptop with a single drive bay I could see use for a hybrid drive.

      --
      world was created 5 seconds before this post as it is.
    2. Re:"No" by jimicus · · Score: 2, Insightful

      That's precisely what a hybrid HDD does, except it takes the decision regarding what will benefit most from going in the SSD out of your hands.

    3. Re:"No" by icebraining · · Score: 1

      That's what backups are for. You can even have a file monitoring daemon making backups from the SSD to the HD when idle.

    4. Re:"No" by unixisc · · Score: 1

      Great for performance, but you're putting your most important data on your least-durable storage device.

      No, it's not often that one would make changes to the OS files, as opposed to data files, so GP is right. One gets to access the OS quickly, and durability i.e. endurance wouldn't be that big a factor, since one wouldn't be writing to the SSD anywhere near as often as HDD, if the mass storage of things like My Documents, or /home is located there. Frequently read, but infrequently altered files would do fine in SSD, whereas frequently altered files should be on HDD.

      That's what backups are for. You can even have a file monitoring daemon making backups from the SSD to the HD when idle.

      It would be ideal if @ some point, the OS could automatically move the infrequently updated files in the SSD, while keeping the frequently updated ones in the HDD.

  3. movies and video by harvey+the+nerd · · Score: 1

    Favorite movies and video will keep hard drives spinning for a while.
    $50/TB (next year) implies a 4 GB movie stores for 20 cents, not quite zipless for favorite 1000 movies and videos at $200, plus back up doubles that cost for a simple mirror.

    1. Re:movies and video by Jane+Q.+Public · · Score: 1, Interesting

      I admit this is slightly off-topic, but I recently saw a 32GB Class 10 SD card for under $30... and it got me remembering back to when -- not as long ago as some might think -- it took an hour to transfer the contents of one 10MB... that's MB not GB... 5.25" HDD, which cost $400, from one machine to another over the network.

  4. Multiple failure points by jones_supa · · Score: 2

    I think the idea is cool. However, as you now get the best of both worlds (capacity, speed) you also have two areas of failure (mechanical damage, flash corruption). I also hope the firmware does not create problems. It's not completely unusable product either.

  5. High dependance by Anonymous Coward · · Score: 1

    How effective the drive is, is highly dependent on the algorithm used and actual drive usage. Seeing as how the ssd part is just a very large cache, you want the algorithm to "smartly" place things that are used most often or recent within it. Otherwise, it be no different then having two drives. The problem is the "smart" part as "smart" is not always smart. On the other hand, there are still definite benefits to a hybrid depending on the situation. Large writes to the drive can be written to the ssd part for example to avoid write blocking applications (apps that wait on write). Apps dealing with lots of small constant reads/writes benefits from having basically a large fast scratchpad. Overall, it's definitely a step in the right direction but hopefully ssd will become cheap enough to where it becomes mainstream instead. At this point, all these benefits can be had by simply having a separate ssd with the OS handling it accordingly (something like ReadyBoost). It's a question of which one deals with it better, firmware which has lower level access which means it can deal with it faster but has less information to go by, or the OS which has high level access allowing it to deal with it more smartly but probably not as fast.

    1. Re:High dependance by petermgreen · · Score: 1

      place things that are used most often

      It's not just about being used often, it's also about the pattern of use. A favorite video may be accessed pretty often but it's always read sequentially from beginning to end and the speed of reading is limited by the playback speed not the hard drive. So there is little point in putting it on a SSD. Program files (and associated program data files) otoh are read in a non-sequential pattern while the user is waiting for a program to start do something so you do want them on a SSD.

      Are the caching algorithms smart enough to detect these different usage patterns and optimise accordingly? and is 8GB of solding state storage really sufficiant in a world where a typical windows install is larger than that?

      I'd rather have all my apps (with the possible exception of larger games) on a SSD and have a HDD for media and possibly larger games. Yes in a laptop that would mean giving up the optical drive but IMO that is a sacrifice worth making.

      --
      note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
  6. Is this significantly different from SRT? by pathological+liar · · Score: 3, Interesting

    I don't imagine it is. Anandtech found it wasn't that difficult to evict stuff from the cache you actually wanted. Not to mention that if you start copying anything especially large (your MP3 collection, or installing a couple games from a Steam sale, say) you nuke the cache and are back to mechanical HD performance.

    Personally, I prefer to do it manually. Stuff I want to load fast (Windows, applications, games, my profile folder) sit on an SSD. Bulk data sits on a mechanical drive.

    1. Re:Is this significantly different from SRT? by Twinbee · · Score: 1

      I thought by 'hybrid', it actually meant two different drives (one SSD, one HDD) working in conjunction, where maybe the OS sits on the SSD, and where both drives simply take up half as much room. That sounds a great idea for laptops, which only have space for one drive.

      But now I know it's all this cache crap, I'm suddenly not at all interested. If one wants the best of both worlds, simply get two drives, and install the OS on the SSD one.

      --
      Why OpalCalc is the best Windows calc
    2. Re:Is this significantly different from SRT? by El_Muerte_TDS · · Score: 1

      No matter how hard I pound on the two drives, they still don't fit in my laptop.

  7. For What? by Entropy98 · · Score: 2

    Who is this for?

    With only 4-8gb of flash I can't think of who this is for?

    Mid-range consumer desktops/laptops?

    Really with such little cache you might as well just add more ram.

    Wouldn't even dream of putting one of these in a server. It's a shame linux doesn't have L2ARC support and it would be nice if there was a drop in hardware equivalent.

    1. Re:For What? by swalve · · Score: 1

      The drive puts anything that is read frequently in the flash cache. Like your OS startup files. I've got a couple of Linux machines where the whole OS is on a CF card or just a USB drive. They run fast as hell.

  8. Hybrid can actually be sometimes faster by Eric+Green · · Score: 1

    The core problem with SSD's is write speed on workloads that have a large number of small updates. My testing on the older 500GB Momentus XT showed that in general it had better write speed doing, e.g., a Fedora install, than the 80GB Intel SSD that I benchmarked it against (same generations of product here, about a year ago), due to the large number of small updates that the non-SSD-aware EXT3/4 filesystems do during the course of installing oodles of RPM's. Because the Momentus only caches *read* requests in the SSD (write requests flow right through it, other than to invalidate anything in its internal cache that is getting written), writes went through at full 7200 rpm 2.5" hard drive speed. In general when I benchmarked writes on similar-generation 7200 rpm 2.5" hard drives and SSD's, the hard drives ended up faster for virtually all real-world workloads, so the end result of my benchmarking was that on real-world workloads the hybrid drive was faster at reads than a hard drive (primarily due to SSD-cached filesystem metadata) and faster at writes than an SSD.

    Please not that I have *not* tested the current generation of SSD's and Momentus XT. Just that it's baffling that the Momentus XT never seemed to really get any traction in the marketplace, given the performance advantages of the approach for many real-world tasks.

    --
    Send mail here if you want to reach me.
    1. Re:Hybrid can actually be sometimes faster by swalve · · Score: 1

      Agreed- I don't know what the current state is, but until recently, write speeds for Flash still weren't as good as comparable HDDs. It's just that the tradeoff is still a speed advantage.

  9. Prices! by Shifty0x88 · · Score: 3, Interesting

    Not only are SSD prices going down, but traditional hard drives are going UP! (At least for the short term)

    Prices taken from Newegg.com:

    Seagate Barracuda XT 3TB is $399.99 (used to be a lot cheaper)

    Seagate Barracuda 1TB SATA III:

    About a year ago: On sale for $60, regular $70

    Now: $149.99

    I think now is the time of the SSD and the hybrid drive is just not worth the price

    And considering this drive is retailed at $239.99 and a regular mechanical 750GB drive is between $69.99(Hitachi Deskstar) and $179.99(Western Digital Black) there is no reason to buy it.

    Just go buy a small SSD and a regular mechanical drive and do it manually

    1. Re:Prices! by justdiver · · Score: 1

      Here's the cause of the short term rise in prices. I don't think that this will have a lasting effect. There is a worldwide shortage of HDDs right now due to manufacturing plants closing. See http://www.techradar.com/news/computing-components/storage/hard-drive-shortage-pushes-prices-up-150-1044021 If these plants aren't able to be reopened, they will just find new plants to use. I need to replace a 1tb drive for my NAS, and have a receipt for the original at $69.99 and the same drive is now $139.99. I'm going to hold off until after the shortage passes.

  10. Cache hasn't helped that much has it? by SpazmodeusG · · Score: 1

    One lesson I've learnt over the years is that hard disk cache (in this case the traditional RAM based cache) doesn't matter all that much. Drives with 8Mb cache consistently show 99% of the performance as drives with 16Mb. And so on for the 128Mb vs 64Mb vs 32Mb varieties of hard disks.

    I do realize there's a benchmark there. But i'm still skeptical given the history of how little on board hard disk cache matters.

    1. Re:Cache hasn't helped that much has it? by greg1104 · · Score: 5, Informative

      There are only two things drive cache can help with significantly. When rebooting, where memory is empty, you can get memory primed with the most common parts of the OS faster if most of that data can be read from the SSD. Optimizers that reorder the boot files will get you much of the same benefit if they can be used.

      Disk cache used for writes is extremely helpful, because it allows write combining and elevator sorting to improve random write workloads, making them closer to sequential. However, you have to be careful, because things sitting in those caches can be lost if the power fails. That can be a corruption issue on things that expect writes to really be on disk, such as databases. Putting some flash to cache those writes, with a supercapacitor to ensure all pending writes complete on shutdown, is a reasonable replacement for the classic approach: using a larger battery-backed power source to retain the cache across power loss or similar temporary failures. The risk with the old way is that the server will be off-line long enough for the battery to discharge. Hybrid drives should be able to flush to SSD just with their capacitor buffer, so you're consistent with the filesystem state, only a moment after the server powers down.

      As for why read caching doesn't normally help, the operating system filesystem cache is giant compared to any size it might be. When OS memory is gigabytes and drive ones megabytes, you'll almost always be in a double-buffer situation: whatever is in the drive's cache will also still be in the OS's cache, and therefore never be requested. The only way you're likely to get any real benefit from the drive cache is if the drive does read-ahead. Then it might only return the blocks requested to the OS, while caching ones it happened to pass over anyway. If you then ask for those next, you get them at cache speeds. On Linux at least, this is also a futile effort; the OS read-ahead is also smarter than any of the drive logic, and it may very well ask for things in that order in the first place.

      One relevant number for improving read speeds is command queue depth. You can get better throughput by ordering reads better, so they seek around the mechanical drive less. There's a latency issue here though--requests at the opposite edge can starve if the queue gets too big--so excessive tuning in that direction isn't useful either.

  11. Already here... sorta. by macraig · · Score: 2

    If you're willing to make a bit of effort, that is.

    Just yesterday I was just investigating the Highpoint Rocket 1220 and 1222 HBAs, which imbues its possessor with the power of Creation... the power to create hybrid magnetic-flash storage devices. Hook up an SSD and a good old moving-platter drive to it, and the HBA does the heavy lifting to create a virtual hybrid drive that will appear as a single device to the host system. It's similar to what is being done with some RAID enclosures of the last couple years, using chipsets like the JMicron JMB393 to create singular virtual drives that are really RAID arrays. I have no doubt there will be other brand HBAs of a similar sort joining these Highpoint ones soon enough.

    With products like this Highpoint HBA, it's not necessary to be a lady-in-waiting to to some royal manufacturer's whim. You can pick and choose an SSD and disk drive of prices and capacities and characteristics that suit your specific needs, rather than waiting breathlessly for some one-size-fits-all solution that benefits the maker more than the buyer.

  12. Write back cache by subreality · · Score: 2

    I would buy one now if they would implement it as a write-back cache. It wouldn't be hard to do. Take a GB of flash, structure it as a ring buffer. That eliminates the "small random writes" problem - you're just writing a linear journal, and the places you're writing are pre-erased and ready to go. If the power fails the drive just plays back the cache when the power comes back on.

    That would let you have massive improvements in write performance. Metadata updates leave you seeking all over the disk. BTRFS is currently very slow to fsync because of this. But if it could just blast it to a big flash cache, and the drive could confirm that as committed to disk immediately, it'd scream.

    Unfortunately all the manufacturers seem to just want to use it as a big persistent read cache to make Windows boot faster.

    1. Re:Write back cache by olau · · Score: 1

      Sounds nice, but I think the truth is that most people on non-db-server workloads don't really write a lot of random data in the first place. For them, start up speed is probably more important. I know it is to me. :)

    2. Re:Write back cache by subreality · · Score: 1

      It affects normal everyday end-user things like installing software (dpkg!), Firefox (which has to hang briefly while doing synchronous updates to the sqlite3 DBs very frequently), and even starting up the system creates a lot of transactional writes (logs, atime, etc). It's not a niche thing, and you'd be really surprised how much it slows things down. Everything runs a ton smoother and faster with write-back cache.

      Regardless, it's very easy to provide both read and write-back cache.

    3. Re:Write back cache by Sloppy · · Score: 1

      Hmm.. not exactly the same thing, but JFS already lets you store the journal (yeah, I know that's not what you really mean) on a different device that the rest of the filesystem. I've never tried it (mainly because I don't know how to decide how much space to give it) but I wonder how that'd work out: an SSD just for journaling your HDD data. That would have to reduce some seeking.

      --
      As copyright owner of this comment, I authorize everyone to defeat any technological measure which limits access to it.
  13. I think there's a place for these. by Sitnalta · · Score: 2, Insightful

    A hybrid drive would be great in my laptop. It doesn't have room for "storage" drives and a 600GB SSD would be heinously expensive. You could also put one in a USB 3.0 external enclosure (I assume they can work like that.) That would give you a nice trade off between speed, capacity and, most importantly, portability.

    That seems to be what Seagate is thinking too. Since the drive is in the 2.5" form factor.

  14. First hand by jamesh · · Score: 3, Informative

    I have one. It works great, but "chirps" occasionally which I think is the sound of the motor spinning down. None of the firmware updates i've applied that claim to fix the chirp actually fix it.

    It runs much faster than my previous drive, but i'm also comparing a 7200RPM drive to a 5400RPM drive so the speed increase isn't just because it's a hybrid.

    I guess the advantage of the SSD cache is that if you use it in a circular fashion you can avoid a lot of the 'read-erase-rewrite' cycles... but I don't know how the cache is organised for sure.

    1. Re:First hand by jones_supa · · Score: 1

      Just to make sure...it's not the head unload sound? And you have disabled idle hard drive power off in OS power settings?

    2. Re:First hand by jamesh · · Score: 1

      Just to make sure...it's not the head unload sound? And you have disabled idle hard drive power off in OS power settings?

      It could be anything. All i hear is a chirp.

    3. Re:First hand by Major+Blud · · Score: 1

      Ditto. I recently bought a Mac Mini (mid 2011) model. Got the 500 GB Momentus XT at Best Buy on sale for $100. I notice a pretty significant increase in performance over the crappy stock 5400 RPM drive that comes in the Mini. I attribute this to the 7200 RPM, but I'm sure the 4 GB SSD cache also helps with the read speed. I already happen to have an 80 GB Intel SSD handy, but with the limited drive space and two drive bays in the Mini, I didn't really thing this would be a good fit. A 512 GB Crucial SSD goes for $780 GB on NewEgg right now (more than I paid for the Mini!), so the Momentus is a really nice compromise between performance and drive space. Your mileage may vary.

      --
      If you post as Anonymous Coward, don't expect a reply.
  15. Realize the limitations... by jafo · · Score: 4, Insightful

    Hybrid drives, and even all of the hybrid RAID controllers I've looked at, only use the SSD for read acceleration. They aren't used for writes, from what I could tell from their specs. So you're almost certainly better off upgrading your system to the next larger amount of RAM rather than getting a hybrid drive.

    Personally, I looked at my storage usage and realized that if I didn't keep *EVERYTHING* on my laptop (every photo I'd taken for 10+ years, 4 or 5 Linux ISOs, etc) and instead put those on a server at home, I could go from a 500GB spinning disc to an 80GB SSD. So I did and there's been no looking back. The first gen Intel X-25M drives had some performance issues, but since then I've been happy with the performance of them.

    1. Re:Realize the limitations... by jafo · · Score: 1

      Agreed, if your primary use of your system is rebooting it (in particular, you don't read more than the cache size between reboots), then the hybrid drive is probably the way to go. :-)

      My lapotp? uptime reports "up 30 days". My desktop? "up 14 days". I'm not saying everyone doesn't reboot, one of my employees would always shut down rather than suspending, but that was partly because his laptop with SSD so so fast at rebooting. But I've found that I just don't have to reboot that often. YMMV.

      As far as "most desktop activity is reads", I agree. Which is why you probably should keep it in RAM. The added benefit of upgrading your RAM rather than going to a hybrid hard drive is that if you NEED that memory for running a huge application once in a while, you will realize huge performance benefits over swapping.

      So, yes, if you reboot all the time then a hybrid drive may be good for you. However, the "boot reordering" work makes that pretty speedy on a regular spinning drive as well. So it's still hard for me to see the win.

  16. Larger SSD caches do have advantages by Chuck+Chunder · · Score: 1

    On disk caches in the MB range have little effect because in most cases anything in the disks cached will already be cached closer to where it is needed, ie in the OS cache using spare system memory. I suspect in that case the on disk cache is probably used more as a buffer than a cache.

    Larger SSD caches bring two advantages, the cache persists across restarts assisting boot time and may also be larger than the amount of memory the OS allocates to its own cache.

    --
    Boffoonery - downloadable Comedy Benefit for Bletchley Park
  17. The worst of both worlds by Yvanhoe · · Score: 1

    So it is big and prone to shocks ? Servers may have their own particular needs but for consumers, the advantage of SSD are size and resistance to shocks. Speed is only a slight advantage.

    --
    The Wise adapts himself to the world. The Fool adapts the world to himself. Therefore, all progress depends on the Fool.
  18. Slightly OT, SSD for OS issues by GodfatherofSoul · · Score: 1

    I was all set to buy a new laptop with the OS mounted on the SSD and a second HDD for mass storage. The obvious solution to me would've been to map the user directories to the HDD for file storage. Not a problem with Linux of course, but you can't do this with Windows! Can't recall the details, but there's some path info hard-coded somewhere that prevents you from moving your "My Documents" folder to a different drive. I never saw any workaround that didn't feel like a hack that would cause problems later.

    --
    I swear to God...I swear to God! That is NOT how you treat your human!
    1. Re:Slightly OT, SSD for OS issues by atari2600a · · Score: 1

      If My Documents is still "My Documents", you'll have to symlink, otherwise there's a registry setting you can change to specify the /user/ folder. See below for more details I guess.

    2. Re:Slightly OT, SSD for OS issues by atari2600a · · Score: 1

      Why would an update write to /users/? All that's stored there is user-specific configuration data...

    3. Re:Slightly OT, SSD for OS issues by armanox · · Score: 1

      A users files (Everything inside \Users\$USRNAME) can have the location safely changed. For other items (somethings in \Windows), that may be the case. For those items you can use symbolic links (yes, Windows 7 supports them).

      --
      I'm starting to think GNU is the problem with "GNU/Linux" these days.
    4. Re:Slightly OT, SSD for OS issues by GodfatherofSoul · · Score: 2

      Using ProfilesDirectory to redirect folders to a drive other than the system volume blocks upgrades. Using ProfilesDirectory to point to a directory that is not the system volume will block SKU upgrades and upgrades to future versions of Windows. For example if you use Windows Vista Home Premium with ProfilesDirectory set to D:\, you will not be able to upgrade to Windows Vista Ultimate or to the next version of Windows. The servicing stack does not handle cross-volume transactions, and it blocks upgrades.

      http://support.microsoft.com/kb/949977

      --
      I swear to God...I swear to God! That is NOT how you treat your human!
  19. This Drive is CRAP by rdebath · · Score: 4, Informative

    This Drive is CRAP
    ASSUMING that it still only does read caching.

    I bought one of the Gen-1 drives and was very underwhelmed. I wanted write caching; 4GB of non-volatile memory with the performance of SLC flash could allow windows (or whatever) to write to the drive flat out for up many seconds without a single choke due to the drive.

    In addition 4G of write-back cache is enough to give a significant performance boost for continuous random writes across the drive and even more so across a small extent such as a database or a DotNET native image cache.

    But for reading it's insignificant compared to the 3-16Gbytes of (so much faster) main memory that most systems contain, except at boot time when, unlike RAM, it will already contain some data. The problem with this is that it will contain the most recently read data, whereas the boot files can quite reasonably be described as least recently read.

    So in the real world it's useless for anything except a machine that's rebooted every five minutes ...

    1. Re:This Drive is CRAP by shitzu · · Score: 1

      Considering the price of ram and flash i do not really understand these hybrid drives. Wouldn't it be cheaper and make more sense to just put 8GB (or 16GB, or more) battery protected RAM cache inside the hard disk rather than flash memory?

      P.S. i chose to go an SSD route anyway, hybrid drives never entered my mind as an alternative.

    2. Re:This Drive is CRAP by silas_moeckel · · Score: 1

      The fact is you can get a much bigger slc ssd for caching and a larger hard drive for about the same price. You can expand the hard drive by adding more as needed same for the cache. I do this all day with enterprise setups, a bit more esoteric as the cache is local and the main store is over iscsi.

      --
      No sir I dont like it.
    3. Re:This Drive is CRAP by dotancohen · · Score: 1

      So in the real world it's useless for anything except a machine that's rebooted every five minutes ...

      Right, most people still do use Windows.

      --
      It is dangerous to be right when the government is wrong.
  20. Pointless, & here's why by atari2600a · · Score: 1

    A dual-volume setup gets you better speed at a fraction of the cost. You put the OS on the cheapest SSD you can find & your user/home partition on a HDD. On Windows you can do this with a simple registry tweak & most other OSes support it out-of-the-box. The only problem I can find is the SSD filling up &/or killing off sectors thanks to Windows' shit temporary file management & organization, with the 12 or whatever temporary folders everywhere, as well as all the hotfix uninstallers, system restore points (this is a nasty chunk of wasted space), etc. At least M$ has a real opportunity to fix this with what I assume will be their first cross-platform & cross-architecture OS...

    1. Re:Pointless, & here's why by atari2600a · · Score: 1

      Incidentally, I was doing some maintenance on a client's old DDR XP machine-- I substituted actual RAM upgrades with moving the pagefile over to a $15 CF card & fixing its size at max capacity. I guess this KINDA counts...I don't know why M$ thought it a good idea to have this on USB sticks though...

  21. Seagate slashvertisement? by evilviper · · Score: 3, Informative

    They may be slower than SSDs, but not by much

    That's horribly incorrect. I liked the sound of hybrid drives as well when I saw the price... The 500GB laptop hard drives with 4GB Flash for $150, should be awesome... But I, not being an idiot, did some research, and sure enough, the reviews say it's not remotely comparable to a real SSD.

    eg. http://www.storagereview.com/seagate_momentus_xt_review

    It's faster than a drive without such a cache, and it might be a good option for a laptop, but even there I'd say a 32GB SD card would be cheaper, and will work wonders on FreeBSD with ZFS configured for L2ARC...

    I have no particular interest in what anyone buys, but the comparison to real SSDs is a massively dishonest.

    --
    Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
    1. Re:Seagate slashvertisement? by a_hanso · · Score: 3, Informative

      OP here. To be honest, the original submission does not contain the "but not by much" and the sentences following the one about the CNET article.

  22. Great... by Anonymous Coward · · Score: 1

    A drive with the disadvantages of both technologies rolled into one!

    Roll on memristor SSDs...

    1. Re:Great... by jones_supa · · Score: 1

      But also advantages of both.

  23. Re:why do firmware updates format? by richy+freeway · · Score: 2

    Crucial M4. Latest firmware update makes the drive about 40% faster and is non-destructive.

  24. How much faster is fsync? by sco08y · · Score: 1

    That's the real question with a hybrid drive. If you're running any kind of database, your performance is limited by how quickly you can fsync. A hybrid ought to be instant, which would be a major speed and reliability win.

  25. Few seconds slower boot is half or a third. by migla · · Score: 1

    Its benchmarks for cold boots and application launches show the new drive to be just a few seconds slower than a SSD.

    My Debian sid boots in a few (noticeably less than ten) seconds into kdm. A few seconds of ten seconds is about a third or more.

    "Newfangled tech! Now at least 33% slower!"

    Great slogan you got there.

    --
    Some of my favourite people are from th US; Vonnegut, Chomsky, Bill Hicks.
    1. Re:Few seconds slower boot is half or a third. by camperdave · · Score: 1

      Meh. How often do you reboot anyway? Once or twice a year, after power failures and hardware upgrades. What I want is cheap, robust, noiseless archive space.

      --
      When our name is on the back of your car, we're behind you all the way!
  26. Is the Time Finally Right For Hybrid Hard Drives? by 1s44c · · Score: 1

    Is the Time Finally Right For Hybrid Hard Drives?

    No.

  27. They are the WORSED of both worlds by SmallFurryCreature · · Score: 2

    The article seems to think hybrid drives are the best of both worlds, but they are not.

    They have the unknown reliability of SSD/flash drives (they do fail) COMBINED with the failure rate of consumer grade HD's (not that good).

    They are not as speedy as pure SSD and not as cheap as pure HD.

    So, the people that want speed, spend the money for a real SSD and use cheap reliable HD's for mass storage in a nas.

    The people that want cheap, buy regular old HD's and accept the lower performance or just whine about it without doing anything about it because they are cheap.

    The middle market, the people to cheap to buy a SSD but willing to spend far more on a small HD... I guess it just ain't there. ESPECIALLY since this lower class of consumer tends to buy ready made machines. Notice how the consoles only increase the HD space at the same time netbooks do? When THAT size of laptop HD as reached rock-bottom prize and you actually would have to pay more to get a smaller sized one?

    Well, same for budget PC's makers. They buy HD's in bulk and put the same size in everything to cut costs. They are NOT going to add several tenners worth of hardware in the faint hope that budget PC buyers will buy their more expensive model when its sits next to the cheaper models in the shop.

    And the high-end PC makers? They simply buy cheap SSD's and charge a premium for them.

    Budget and high-end markets are FAR easier to supply for then the mid range. Because the budget people think anything more expensive is a rip-off and the high-end people look down their noses at anything cheap.

    --

    MMO Quests are like orgasms:

    You may solo them, I prefer them in a group.

    1. Re:They are the WORSED of both worlds by lightknight · · Score: 1

      Agreed. This product would have made more sense during the Vista years, but it's a few years later, and the pricing for SSDs are getting sweeter all the time.

      No point paying a price premium for something so incapable. With a Desktop, you want a SSD with the OS on it, and multiple HDs. With a laptop, you want a SSD.

      --
      I am John Hurt.
    2. Re:They are the WORSED of both worlds by MobyDisk · · Score: 1

      So, the people that want speed, spend the money for a real SSD and use cheap reliable HD's for mass storage in a nas.

      Doesn't work for laptops. :-( The hybrid drive listed in the article is in a laptop form factor so it is the best alternative for that case.

  28. Intel's Z68 chipset negates the need for this driv by Shivetya · · Score: 3, Informative

    and their upcoming Ivy Bridge chipset will take it even further. Both allow for the use of a small SSD drive as a cache against a larger traditional hard drive.

    Per the wiki page on their chipsets, The Z68 also added support for transparently caching hard disk data onto solid-state drives (up to 64GB), a technology called Smart Response Technology

    SRT link is http://en.wikipedia.org/wiki/Smart_Response_Technology

    --
    * Winners compare their achievements to their goals, losers compare theirs to that of others.
  29. Hybrid = 2 places to fail. by Anonymous Coward · · Score: 1

    Or, in other words, hell to the no.

    If I wanted that speed, I'd get an SSD.
    And even then, I can easily just mount that crap on a DRAM drive if I REALLY needed the speed.

    Games like, say, Minecraft, or audio / video / picture temp caches that constantly change, you'd be better off just doing that. SSDs horribly fail. A DRAM drive would last you a lifetime unless you have constant brownouts or blackouts, or have a very noise powerline.
    Even just making a virtual drive in RAM if you have enough of it would do fine.
    The downside? It'd probably cost a few SSDs worth to buy, unless you DIY it.
    Actually, I forgot Gigabyte made this. Not even sure what's happening or happened with it.
    Gigabyte i-ram.

    1. Re:Hybrid = 2 places to fail. by mwvdlee · · Score: 1

      DRAM storage is fine until power runs out.
      Even that i-RAM only lasts for ~16 hours on battery.
      If you work 8 hours a day, don't ever be late. And don't take weekends off.
      It might be okay for a cache, but that only helps after booting and then you might as well just add memory on the motherboard.

      --
      Slashdot social media options: AIM, ICQ, Yahoo, Jabber and Mobile Text. Why no MySpace?
    2. Re:Hybrid = 2 places to fail. by smash · · Score: 1

      DRAM is not persistent across reboots, and the first load of the data into DRAM is going to be slow. Every time you preload your ram drive. SSD or Hybrid drives get around that issue. I don't particularly care how fast a drive is once i've already had to sit through waiting for the data to load that i was working on.

      --
      I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
    3. Re:Hybrid = 2 places to fail. by GauteL · · Score: 1

      "DRAM storage is fine until power runs out.
      Even that i-RAM only lasts for ~16 hours on battery.
      If you work 8 hours a day, don't ever be late. And don't take weekends off."

      I see your point, but surely if you're administrating anything important, you should get automatic messages if something goes wrong, meaning you have to interrupt your weekend or your evening to go fix the problem right now, not wait until the next morning / Monday.

    4. Re:Hybrid = 2 places to fail. by mwvdlee · · Score: 1

      Then again, if you're administrating anything important you probably don't want to rely on a cheap card with old DRAM chips and can spare the expense of a more trustworthy storage solution.

      --
      Slashdot social media options: AIM, ICQ, Yahoo, Jabber and Mobile Text. Why no MySpace?
  30. Quick boot and browser loading by jprupp · · Score: 1

    I had a 320 GB 5400 RPM hard disk drive in my laptop computer, when I decided it was time to upgrade to something faster. I download lots of pirated music, movies and TV series, so I did not want to go the SSD route and have a fraction of the storage space. I was originally thinking on getting a 500 GB 7200 RPM hard disk, but settled for the Seagate Momentus XT hybrid hard disk drive with 4 GB of flash storage. After a few reboots the HDD seemed to make up its mind on what to cache in the SSD, so my machine started to boot up in under 15 seconds (Ubuntu), and my web browser and email client would load very quickly. I recommend hybrid HDDs for anyone that is unwilling to compromise on storage space.

    There's is some downside though: I find that my computer drinks more energy now. I believe it's because my platters now run at 7200 RPM instead of 5400 RPM. This computer isn't very energy-efficient since the outset. It's more of a desktop replacement machine. But I think it should be mentioned that changing to a hybrid HDD did increase power consumption overall. I wouldn't get anything but SSD if I was buying a computer meant to be used where there would be no power plug available. I would also not get a conventional LCD, but a LED screen, and I wouldn't want to have a big GPU.

  31. Why different just based on usage pattern? by mwvdlee · · Score: 1

    The current idea is to put often used files on the SSD, and less used files on the HDD.

    I bet you could get even better performance by splitting every file and putting the first few blocks on the SSD.
    When a file is accessed, the SSD can start delivering data immediately while the HDD has some time to find the rest of the file and take over from there.
    That should make every file access fast.

    --
    Slashdot social media options: AIM, ICQ, Yahoo, Jabber and Mobile Text. Why no MySpace?
  32. Never if you're running a database... by LongearedBat · · Score: 1

    ...and you can't force the drive to actually flush the cache to storage immediately. For the sake of efficiency, drive API's will lie about data having been being persisted.

    1. Re:Never if you're running a database... by laird · · Score: 1

      "For the sake of efficiency, drive API's will lie about data having been being persisted."

      No. The ability to control write-through cache has been quite explicit for decades. If applications need performance most, which is the case 99% of the time, they use a normal write, which is written to the drive's controller buffer and considered "written" even though it's actually written to disk later. Applications that need to ensure that data is written to disk (e.g. databases) explicitly force the write not to be confirmed until the data is safely on disk. This can be explicitly controlled by the application, the RAID controller, the drive's controller, etc., so that systems can be tuned (by the owner and/or OS vendor) for the tradeoff between performance and data integrity.

      If a drive manufacturer's drives violated the API spec and claimed that data was written to disk while it was still just in the buffer, without being configurable to disable this for critical applications, nobody would ever buy the drives.

  33. So what's stored where? by laird · · Score: 2

    So how do hybrid drives decide what's stored in the SSD vs the disk? From working in the hard drive business, I can think of several ways to tackle this - which is it?

    1. Drive observes usage patterns and stores data on SSD vs disk based on that. This would be cool since it's transparent to the OS, etc., so it can work by "magic" (e.g. like bad block remapping), but it feels like it might be less effective than the other strategies depending on how good a job it does guessing how data is used. Also, there are some cases that are 'rare' (such as boot time) but which are important to optimize, even if statistically it wouldn't appear so.

    2. Driver/OS controls what's stored where. This could be great, since they can have much more knowledge of what's going on than the drive.

    3. SSD and disk are distinct 'drives'. This would allow the user to optimize (e.g. put boot OS and swap on SSD, big files on disk, etc.). But it requires users to understand and manage tradeoffs explicitly, which most people probably don't want to deal with.

    So which is it? Does anyone know?

    1. Re:So what's stored where? by swb · · Score: 1

      I would assume the drive observes usage patterns. I'd also guess that its probably the best method, since it can operate at the block level.

      I'd guess that any manual optimization would be less beneficial unless you factored in the most common blocks you actually used, since what you think you want optimized may not be what you actually use.

  34. Re:Intel's Z68 chipset negates the need for this d by smash · · Score: 2

    it still requires 2 drives in the machine. for laptops this is often not viable.

    --
    I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
  35. Or...best of both worlds by Aqualung812 · · Score: 1

    With a bit of logic, hybrid drives could be faster & more durable than either SSD or HDD.

    Have the drive detect what blocks are being read freqeuently & written infrequently. Move those blocks to SSD. Likely, this will be OS files that are only changed on patches & application executables.

    SSDs can last a very long time if all they're doing is reads.

    At the same time, the HDD is moving its head far less doing all of these lookups.

    Faster performance, greater life.

    All of that said, I don't know if anyone is making a drive that does this. I know that there are SANs that do this type of thing, though, such as Compellant.

    --
    Grammer Nazis - I mod you "troll" unless you actually add something on-topic. Yes, I know I have mispellings in my sig.
  36. Re:why do firmware updates format? by LoRdTAW · · Score: 4, Informative

    It sucks but has an easy but time consuming fix that leaves you with the drive contents intact:
    Boot a live Linux distro. And hook a USB HDD to the system and mount it. The USB hdd can even be formatted NTFS if the live distro has FUSE installed along with the ntfs-3g driver, most live distros already have it or will allow you to install them. Assuming your SSD is the primary or only disk in your system then:

    (You need to be root or use sudo, on most live distros you simply type "su root" or "sudo -s")

    #dd if=/dev/sda of=/path/to/backup/disk/ssd_backup.img conv=sync,noerror bs=1024k

    /dev/sda is the first disk in the system. you may have to run ls /dev/sd* to get a list of disks and partitions. and note, sda is the entire disk block-for-block, sda1 is a partition just like sda2 , sda3 etc. If you have more than one disk and don't know which letter it is then simply type fdisk -lu /dev/sdX (X being the letter you want to check) and it will dump the drive info.

    It may take about 5+ hours assuming you have a 512GB SSD and an optimal USB transfer rate of 25MBps to the backup disk (in my experience the average for USB 2.0 write speeds). Faster backup disks and smaller capacity SSD's will backup much faster.

    Once complete, you now have a bit for bit block-level copy of the SSD. This ignores the boot sector, boot loaders, partitions and file systems. It does not matter what OS you had on it, how many partitions or what file system you used. if your very paranoid and want to wait hours more, the run diff against the disk and disk image file to be sure they are an exact copy (never did it and never will).

    Now reboot and upgrade the firmware the way the manufacturer tells you. So now your data is wiped out, big stinkin deal. Fire up the live Linux distro and again attach your backup disk and then enter the following command:

    #dd if=/path/to/backup/disk/ssd_backup.img of=/dev/sda conv=notrunk bs=1024k

    This writes the image file back to the SSD and if all goes well (It has never failed me yet and I have done this dozens of times for various systems) you now have your upgraded firmware with its original contents fully intact.

    You can even mount one or more of the partitions contained within the disk image (under Linux of course) if you do a bit of homework (search google for mounting dd images) or just go here:http://darkdust.net/writings/diskimagesminihowto That tutorial is how I started playing with dd images.

    You can also movethe contents of a smaller cramped disk to larger drives. Works for windows/NTFS too! You simply dd the entire smaller drive to the new drive (works best when both drives are hooked up via sata.) Then you use gparted or some other parted disk GUI to grow the file system on the new drive. Shut down and remove the linux cd/thumb-drive and remove the old disk and move the sata cable from the old disk to the new disk. Boot your PC and if your using windows (2000, XP , Vista, 7) it will run the check disk to verify the volume (DONT SKIP IT!) and reboot. Once it reboots to windows, open up explorer and see that you now magically have all that shiny new space without formatting, reinstalling, adding new drive letters or mounting drives under folders etc. Its transparent!

    Example command:

    #dd if=/dev/sda of=/dev/sdb conv=sync,noerror bs=1024k

    sda is the small disk and sdb is the new large disk. I have done that trick multiple times as well with a 100% success rate. My friends were amazed.

  37. Re: 40 Days is right by Anonymous Coward · · Score: 1

    MTBF IS NOT INDICATIVE OF "WHEN WILL IT DIE". MTBF is determined by running many of the disks all at the same time and taking the mean of time that exists from one failure to the other. Not when they all have died.

    It's not telling you how long your drive will last, but rather, if you have more than one of the same disk, and start running them at the same time, the likely time that will elapse until **ONE** of the disks in the array fails. The more disks you buy from a batch, the more 'chances' you get that one of the drives will fail sooner, rather than later, which makes it more likely that at least one of the disks will fail from that group.

    SOOO, 40 DAYS IS CORRECT. If you are running 100 disks from a batch that has a 100,000hour MTBF, the mean time that will elapse before **ONE** of the drives (of the 100) fails is 40 Days. If you have 1 million disks running, expect that 10 of those disks were DOA, and that one will die every 6 minutes.

    It's not that hard to understand, but oh-so-easy to make fun, of people who have specific knowledge by creating straw-men based on flawed principles.

  38. I don't think so. by MoronGames · · Score: 1

    With new "cloud" storage products for people begin to pushing off things that don't need to be fast - like music collections, for example. Because of this, there is less need for vast amounts of slow memory at our fingertips, and the need will continue to fall because not only are the prices of SSDs going to continue to drop, but our internet connections are going to get faster, giving us more cloud storage capabilities. The SSDs are going to take over because they makes systems appear to be much faster, and they reduce power consumption. As more and more people buy computers equipped with SSDs, the amount of people willing to buy anything equipped with an old fashioned box of spinning discs is going to go down by a lot.

    --
    hey!
  39. I just don't see a reason to combine them by BlueCoder · · Score: 1

    Just keep them separate and let the operating system use the SSD for cache. At least in this senerio the software for the caching logic can be changed/upgraded. I don't see any advantage to putting it into the firmware of a hard drive. Sure manufacturers can tune it but so can everyone with a software driver solution. Just no reason to combine them.

  40. No it is not. by sgt+scrub · · Score: 1

    I do not want a part of a drive to fail after one year (the seemingly life span of a SSD drive) when the other part still has two more years (what I'm finding to be the life span of SATA drives these days) left in it. Link courtesy of Hairyfeet.

    --
    Having to work for a living is the root of all evil.
  41. Re:Never mainstream by BlueCoder · · Score: 1

    I totally agree with this. An SSD is standard equipment now for the operating system. For a desktop system I would actually recommend two drives, one for the OS and another for swap and disk caching. The second could be 16gb but it would take the write thrashing instead of the larger primary SSD and save your primary, more expensive and larger capacity SSD's from wearing out. I would actually love a SSD that was specialized for OS swap and disk caching.

    P.S. How come there isn't a new micro package for SSD's? I can't see a reason for them to be this big at current capacity.

  42. Re:Intel's Z68 chipset negates the need for this d by Translation+Error · · Score: 2

    it still requires 2 drives in the machine. for laptops this is often not viable.

    But the SSD doesn't have to be added as a discrete component. You can already get motherboards that incorporate a small SSD drive to be used with SRT.

    --
    When someone says, "Any fool can see ..." they're usually exactly right.
  43. Re:why do firmware updates format? by Jumperalex · · Score: 1

    My OCZ Vertex 2 ... I have updated firmware about 4 or 5 times, never a single format.

    You are living in the dark ages, that was only a problem in the very early days. Not just of 1st and 2nd gen drives, but of 1st and 2nd gen firmware.

    --
    If you can't be good, be good at it!
  44. Except it's still worth it by mcrbids · · Score: 1

    We are using SSDs in production on our database servers. The speed improvement is more than dramatic - better than 10x improvement on basically every test and simulation we could throw at 'em!

    After a conservative rollout and a few painful hiccups, we've stabilized good results with simple RAID1, using the SSDs for the PostgreSQL partition. (/var/lib/pgsql) on CentOS servers.

    They do have a significantly worse failure rate, but the combination of RAID 1, hot swap drive bays and an otherwise excellent hourly backup strategy result in both excellent uptimes and performance. At today's prices, if the average life expectancy of an SSD drive is just 6 months, we'd more than make up for this expense just with the DB servers we don't need to buy.

    For production databases, steer clear of "consumer" drives, they last months before giving you thorny problems. Instead, spend a bit more and get either Intel 710 SSDs or if maximum performance is really REALLY important, the RealSSD P300.

    --
    I have no problem with your religion until you decide it's reason to deprive others of the truth.
  45. OT: OS or Games on SSD? by mbourgon · · Score: 1

    So I've bought a regular old SSD drive. 80gb. My original intent was to point Steam at it... I'd seen texture loading (specifically here, Witcher 2) where it couldn't get it from the HDD to the GPU fast enough, and so you'd enter an area, see polygons, crappy textures, good textures, then awesome textures.

    Am I better off doing that, or putting my OS on it? Dual-core 3ghz system w/4gb of RAM.

    --
    "Sometimes a woman is a kind of religion, she can save your soul & set you free from all your sins" - Bad Examples
  46. World's first 70" hard drive by amorsen · · Score: 1

    From the specifications: Width (maximum) 2.760mm (70.10 in)

    I may be wrong about it being a world first of course, some of the first hard drives were enormous.

    --
    Finally! A year of moderation! Ready for 2019?
  47. I guess if you insist on recording gaming by Sycraft-fu · · Score: 1

    Then maybe you need a ton of space. However for gaming itself? No. My laptop has a 256GB SSD and I do not want for space on it, and I'm a gamer. Even if you assume 20GB/game, which is way overstated (few games are that large, only MMOs in general and people tend to have one or maybe two of those at once) you can get 10 games on the system at one time and have plenty of overhead for OS and data. In reality, with games being more in the 4-8GB range, you can pack 20-30 games on no problem with plenty of space to spare. If 20+ games to choose from at one time isn't enough for you, then you have a problem with your attention span.

    Also with services like Impulse and Steam there is even less reason to have the "I have to install everything," idea. Just install something when you want it.

    Don't get me wrong, I keep a lot of games on my system at one time so I can pick and choose what I want to play, but 20-30 of them is plenty.

    Also recording large FRAPS videos is not something ordinary people do. Most gamers in fact do not. Nothing wrong with it, just recognize that it is a more high end use.

  48. This would never really be usefull... by mynis01 · · Score: 1

    ...for me anyways. I wouldn't really spend money to increase my I/O on data that has all ready been read before. My windows side of my desktop that I use for gaming has a cheap SSD and my linux side boots in around 10 seconds anyways, even from a 5900 RPM HDD. Boot up time is probably one of the only times I read the same file(s) frequently. How many people really care that their resumé is going to pop up 2 milliseconds faster every time they open it? In the enterprise world, you could just use a standalone SDD for caching anyways.

  49. Hybrid works if the SSD is good, but ... by AaronLawrence · · Score: 1

    We are using Intel's "Smart Response Technology" which uses a small 20GB mSATA SSD on the motherboard in conjunction with a regular hard drive.
    It can cache both reads and [optionally] writes.
    In read/write cache mode, it gives about 80% of the performance boost of using the pure SSD, for our Visual Studio 2010 disk thrashing.

    However, these are good quality Intel SSDs, not the "cheapest flash chip I could find to bung in my hard disk" that the all-in-one hybrid drives seem to use.

    --
    For every expert, there is an equal and opposite expert. - Arthur C. Clarke