Slashdot Mirror

← Back to Stories (view on slashdot.org)

IBM Flash Memory Breaks 1 Million IOPS Barrier

Posted by ScuttleMonkey on from the flash-in-a-flash dept.

alphadogg writes to tell us that IBM is claiming a victory on the flash storage front. Their new research project "Quicksilver" is claiming data transfer speeds of more than 1 million input/output operations per second (IOPS). "IBM said Quicksilver is two and a half times faster than its own SAN Volume Controller coupled with IBM's DS4700 storage. It would also be two and a half times faster than technology from Texas Memory Systems, which says it has the world's fastest storage with an IOPS rate of 400,000. "

77 comments

  1. IBM Flash Memory Breaks? by Yvan256 · · Score: 4, Funny

    Then I'm not buying IBM flash memory, end of story.

    1. Re:IBM Flash Memory Breaks? by maxume · · Score: 3, Funny

      Will Farrell called, he wants you to join his club.

      --
      Nerd rage is the funniest rage.
    2. Re:IBM Flash Memory Breaks? by Windows_NT · · Score: 1

      Does it run linux?

      --
      Go go Gadget Nailgun!
  2. Yay! by Anonymous Coward · · Score: 2, Funny

    Does this mean I can wear out my flash drive more quickly? WOO!

  3. Bit error rate? by Toffins · · Score: 4, Interesting

    That's very fast. I wonder how low the bit error rate is.

    1. Re:Bit error rate? by pixelpusher220 · · Score: 3, Interesting

      More importantly, how durable is the memory?

      Doesn't flash memory have a limit on the # of accesses before it starts to fail?

      --
      People in cars cause accidents....accidents in cars cause people :-D
    2. Re:Bit error rate? by Surt · · Score: 4, Informative

      It has a limit to the number of writes, the number of reads is pretty unlimited. The expected average lifetime is similar to a hard drive, and in some cases better.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    3. Re:Bit error rate? by HTH+NE1 · · Score: 2, Informative

      The bigger the flash drive, the more area in which to spread the wear, the longer it lasts.

      --
      Oh, say does that Star-Spangled Banner entwine / The myrtle of Venus with Bacchus's vine?
    4. Re:Bit error rate? by winphreak · · Score: 2, Interesting

      If that is true, I would hope this can help issues with SSD implementation. Sadly, I don't know as much as I should but it seems like it would help.
      Numbers aside, wouldn't speed increases like this help to establish the possibility of SSD raid configurations?

      My ignorant two cents.

      --
      "I'm a well-wisher, in that I don't wish you any specific harm."
    5. Re:Bit error rate? by Heembo · · Score: 0

      It has a limit to the number of writes, the number of reads is pretty unlimited. The expected average lifetime is similar to a hard drive, and in some cases better.

      I don't believe that at all. I have read the opposite - that flash wear for high-write systems, like a server - is very rapid, in fact Dell is getting returns for flash workstations at a rate faster than any other computer. You might be right, can you post a few links?

      --
      Horns are really just a broken halo.
    6. Re:Bit error rate? by Surt · · Score: 3, Informative

      Obviously, there's not a whole lot of independent research out there, but here are some of the claims:

      http://talkback.zdnet.com/5208-11408-0.html?forumID=1&threadID=39451&messageID=725468&start=0

      http://www.linuxdevices.com/news/NS7676844023.html

      http://www.computerworld.com/action/article.do?command=viewArticleBasic&articleId=9007518

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    7. Re:Bit error rate? by Hurricane78 · · Score: 2, Informative

      ...the more you wear it down by using it. (eg. bigger files, more files used.)

      Isn't that the whole point of a bigger drive?

      --
      Any sufficiently advanced intelligence is indistinguishable from stupidity.
  4. Big deal by Anonymous Coward · · Score: 0

    It only transfers 640KB per I/O operation, tops.

    1. Re:Big deal by ppc_digger · · Score: 4, Insightful

      Which means it transfers 640 GB per second.

      --
      Of all major operating systems, UNIX is the only one originally meant for gaming.
    2. Re:Big deal by Anonymous Coward · · Score: 5, Funny

      It only transfers 640KB per I/O operation, tops.

      Well, 640kb should be enough for anybody.

    3. Re:Big deal by Anonymous Coward · · Score: 0

      610.35, but who's counting.

    4. Re:Big deal by Anonymous Coward · · Score: 0

      Thankyou, can't help but think that that's the one number that should be in the post that isn't. While this IOP number is nice, it doesn't give a feel for those of us used to working in bits and bytes. I could have researched and then reached for a calculator but that would be anything but lazy, which I am. Very.

    5. Re:Big deal by sexconker · · Score: 2, Funny

      I am, and it's 610.3515625.

  5. Time to market? by Naughty+Bob · · Score: 3, Insightful

    They don't even commit to a date when this might be viable.

    Given that current systems are 3 or more orders of magnitude slower than the stated amount, I'm pretty safe in saying that this announcement is meaningless outside of the lab. Kudos, but.... next!

    --
    "Be light, stinging, insolent and melancholy"
    1. Re:Time to market? by spun · · Score: 5, Insightful

      If it's in the lab, "Next!" But if it's in the market, "Slashvertisement!" Good old Slashdot, where someone is always ready to shit in your cornflakes.

      --
      - None can love freedom heartily, but good men; the rest love not freedom, but license. -- John Milton
    2. Re:Time to market? by COMON$ · · Score: 1

      We have been looking into the Texas memory solutions, they are very impressive but I too wonder when this might be a viable commercially sold solution.

      --
      CS: It is all sink or swim...oh and did I mention there are sharks in that water?
    3. Re:Time to market? by Yvan256 · · Score: 5, Funny

      Oh crap, I thought these were Raisin Bran.

    4. Re:Time to market? by Anonymous Coward · · Score: 0

      Or 1 order of magnitude and available to anyone with deep enough pockets: www.fusionio.com

    5. Re:Time to market? by Anonymous Coward · · Score: 0

      Cornflakes?! Taste them again, for the first time.

    6. Re:Time to market? by sexconker · · Score: 1

      What company was it that put out (essentially) a DDR -> IDE board/card?

      That thing was AWESOME.

      Expensive per GB, but screaming fast.

    7. Re:Time to market? by Anonymous Coward · · Score: 0

      Do you enjoy learning about new technology or just buying it?

    8. Re:Time to market? by winomonkey · · Score: 1

      So, if Slashdotters are shitting in my cornflakes, who the hell is pissing in my cheerios?!

    9. Re:Time to market? by sir+fer · · Score: 1

      I don't wanna learn about it unless I can buy it!! ;o)

      --
      Debian FTW ;o)
    10. Re:Time to market? by blackicye · · Score: 1

      That would have been the Gigabyte I-Ram

  6. I'm waiting for price/performance and benchmarks by afidel · · Score: 4, Interesting

    While managing to achieve 1M IOPS is somewhat impressive, it's not hard to do for an optimal theoretical situation. Xiotech was showing 500,000+ IOPS from three of their new Emprise 5000 storage shelfs at Storage Networking World this spring, but it was all video and synthetic sequential reads. That same system would only pull about 20K IOPS on the SPC-1 real world benchmark.

    --
    There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  7. It's not a fucking barrier by Nimey · · Score: 2, Informative

    It's the 1 MIOPS /mark/. If it was a barrier, you wouldn't be /able/ to break it.

    --
    Hail Eris, full of mischief...

    E pluribus sanguinem
    1. Re:It's not a fucking barrier by Aranykai · · Score: 4, Funny

      Italics look like this. /This/ /just/ /makes/ /you/ /look/ /like/ /an/ /ass/.

      --
      If sharing a song makes you a pirate, what do I have to share to be a ninja?
    2. Re:It's not a fucking barrier by Yvan256 · · Score: 1

      Cut him some slack, his C64 can't do italics.

    3. Re:It's not a fucking barrier by Nimey · · Score: 3, Informative

      Usenet-isms.

      *Bold* /Italic/ _Underline_

      But I wouldn't expect you to understand that.

      --
      Hail Eris, full of mischief...

      E pluribus sanguinem
    4. Re:It's not a fucking barrier by truthsearch · · Score: 0, Offtopic

      /Usenet/ /is/ /dead/.

      Slashdot confirms it, so it must be true.

      --
      Developers: We can use your help.
    5. Re:It's not a fucking barrier by Neoprofin · · Score: 1

      Just because I can type in 13375p34k doesn't mean I shouldn't be told it makes me look like an ass.

    6. Re:It's not a fucking barrier by Just+Some+Guy · · Score: 3, Insightful

      If it was a barrier, you wouldn't be /able/ to break it.

      Yeah.

      --
      Dewey, what part of this looks like authorities should be involved?
    7. Re:It's not a fucking barrier by omnipresentbob · · Score: 1

      But I wouldn't expect you to understand that.

      Of course not... Just look at his UID (not that mine is much better...)

    8. Re:It's not a fucking barrier by santiagodraco · · Score: 1

      It's a barrier if it's considered very difficult to break. It's used all the time in this kind of context. But you'd know that if you weren't just grasping for something to say that you could attach an insult to. A "mark" implies nothing to do with difficulty, it's just a level, or stage, or, well, a mark.

    9. Re:It's not a fucking barrier by jebrew · · Score: 2, Insightful

      With a reply that *recognized* your command, /I'd/ have thought _you_ would have understood that *he* understood.

      /yay, slashies!/

    10. Re:It's not a fucking barrier by gwbennett · · Score: 0

      Then again the hymen is considered a "barrier," but it can be broken. Just not by slashdotters.

      --
      Where is this free beer everyone on Slashdot keeps talking about?
    11. Re:It's not a fucking barrier by Anonymous Coward · · Score: 0

      Holy LOL, grats on your usenet e-jerking

    12. Re:It's not a fucking barrier by sir+fer · · Score: 1

      What? Like teh Sound Barrier?? ??

      --
      Debian FTW ;o)
  8. 1M? Bah by Anonymous Coward · · Score: 0

    640k Should be enough for anyone

  9. soooooo... by Taibhsear · · Score: 3, Insightful

    How does this translate into normal transfer speed units like MB/s? Otherwise I have no point of reference to tell if I am impressed or indifferent.

    1. Re:soooooo... by Anonymous Coward · · Score: 2, Funny

      More importantly, how many Libraries of Congress per lunar month is this?

    2. Re:soooooo... by Hecatomb00 · · Score: 5, Funny

      How does this translate into normal transfer speed units like MB/s? Otherwise I have no point of reference to tell if I am impressed or indifferent.

      All I know is it is fast. This is a huge win in my book. I am really tired of finishing before my standard hard drive can seek out my porn.

    3. Re:soooooo... by afidel · · Score: 2, Informative

      You can normally assume that for that level of IOPS they are 4K blocks, so 4GB/s, pretty damn impressive as that's saturating 4*10Gb/s links.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    4. Re:soooooo... by Anonymous Coward · · Score: 1, Funny

      You kidding me? It can make the Kessel Run in less than twelve parsecs. That's smoke'n

    5. Re:soooooo... by TheRaven64 · · Score: 4, Informative
      IOPS are a normal measure for server hardware. It's the number of I/O operations per second the device can perform. Most server workloads, particularly database servers, require a lot of small I/O operations per second. With a single mechanical disk, it's pretty easy to work out the number. Pretend the time taken for each read is zero (it isn't, but it's really tiny so we can ignore it). Then take the reciprocal of the seek time. For a cheap disk, this is around 9ms. Google says the reciprocal of 9ms is 111Hz, so a 9ms seek time translates to 111 IOPS. Fast drives have average seek times down at around 4ms, which gives 250 IOPS. So, to put this in perspective, it's as many independent operations per second as 4,000 individual high-end disks, or almost 10,000 cheap ones.

      By the way, for a workload with a lot of independent reads or writes you'd be surprised how slow a hard disk is. With a 512byte block (common on hard drives) you get a maximum throughput of around 50KB/s for a random access pattern on a cheap drive, going up to around 125KB/s on an expensive one. Even very cheap flash can do better than this, so for moderate sized databases (a few GBs) with a very heavy access load flash works out a lot cheaper.

      Oh, and for reference each of the ops in this test was up to 640KB, giving a maximum of around 640GB/s data transfer.

      --
      I am TheRaven on Soylent News
    6. Re:soooooo... by basil+montreal · · Score: 2, Informative

      MB/s is only a measure that's meaningful for sequential reads where the data can be prefetched. Most enterprise storage is based on applications that read randomly all over the disk (like databases and email servers). The benchmark measurement for this type of application is in the number of operations you can do per second. A single hard drive spindle can do between 80 and 150 IO/s, which would generate the number of IO/s times the size of the IO blocks per second.

    7. Re:soooooo... by jebrew · · Score: 1

      Those IOPS aren't spot on, you've got to take into account sequential vs. random. I've got a USB drive here that barely pushes 25 MB/s, and has a seek time of ~6ms (old ide in an old usb case...mostly for beating with a stick), yet I can get ~2000 IO/s using sequential reading.

      Otherwise, that's a good explanation.

    8. Re:soooooo... by TopSpin · · Score: 4, Informative

      How does this translate into normal transfer speed units like MB/s? Otherwise I have no point of reference to tell if I am impressed or indifferent.

      I'll try to help.

      MB/s is a measure of IO throughput. Often this isn't the most relevant figure for 'enterprise' storage. Certain applications do a lot of random access IO so IOPS becomes more important than throughput.

      Today a typical desktop disk is capable of about 100-150 IOPS. That's a rule of thumb range that varies based on operation size, cache, etc. It works pretty well usually. You can aggregate disks and get almost linear scaling; 12 disks, for instance in a device like this, will give you a maximum of 1200 IOPs, roughly. A common USB Flash device can break 1000 IOPS with certain access patterns.

      The second graph on this page illustrates the extreme IOPS advantage of Flash for certain applications. Disks are limited by head actuation and rotation latency. This is why enterprise storage vendors have been pursuing Flash aggressively. That's what this story is all about.

      The dream is to host the same IOPS in with an order of magnitude less physical space, power, heat, etc. If you don't need thousands of IOPS (and most PC users don't) then it isn't very interesting. If you happen to run an OLTP system with thousands of reads/write per second it means a great deal.

      --
      Lurking at the bottom of the gravity well, getting old
    9. Re:soooooo... by Amouth · · Score: 1

      he is damn close for random iops though.. almost everything does sequential well.. as there is no seek time past the start.. so flash vs spindle is pointless.. where spindels hurt is random..

      he was doing random - and was close enough for the net

      --
      '...if only "Jumping to a Conclusion" was an event in the Olympics.'
    10. Re:soooooo... by jebrew · · Score: 1

      Good point. There are a lot of factors to take into account. I just felt like his post may have been a little misleading without specifying purely random I/O.

    11. Re:soooooo... by JJJK · · Score: 2, Funny

      about 15946
      ...using google calculator, 10 TB for a LoC and 640 GB/s.

      So... do you measure velocity in furlongs per forthnight?

    12. Re:soooooo... by alx5000 · · Score: 1

      My car gets 40 rods to the hogshead, and that's the way I likes it!

      --
      My 0.02 cents
    13. Re:soooooo... by afidel · · Score: 2, Informative

      It's not freaking 640GB/s, there's only one switch in existence that can do that much (Cisco 7000, the Brocade DCX-Backbone is the only other one that's close and it's 6.4Tb/s total per chassis). It's ~4.4GB/s, 1.1M peak IOPS * 4KB chunks...

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    14. Re:soooooo... by elgatozorbas · · Score: 2, Funny

      All I know is it is fast. This is a huge win in my book. I am really tired of finishing before my standard hard drive can seek out my porn.

      Why don't you give it a head start?

    15. Re:soooooo... by Anonymous Coward · · Score: 0

      It was using a DCX, the first one in Europe

    16. Re:soooooo... by sir+fer · · Score: 1

      My car gets 40 rods to the hogshead yada yada yada

      --
      Debian FTW ;o)
    17. Re:soooooo... by owlstead · · Score: 1

      Anyone that has done some downloading from a news server and par2-ing and unzipping at the same time can relate to that 50KB/s. Or copying multiple folders at the same time.

      I really really will buy a fast SSD once they become available, and I am thinking about buying one or two of of these new WD velociraptors as well. Current hard drives suck. They are slow, noisy and still a bit unreliable (even though they seem to be *much* better than days of old).

  10. Shouldn't that be... by vjoel · · Score: 1

    IOOPS?

    --
    What part of `yes no` don't you understand?
  11. The Name Implies by Chillintau · · Score: 1

    With a name like Quicksilver, it must not be RoHS compliant.

    1. Re:The Name Implies by thedrx · · Score: 1

      I wish I had mod points right now, most mods are probably gonna miss this.

  12. Color me unimpressed... by Anonymous Coward · · Score: 0

    http://www.thirdio.com/ 800k IOPS claimed on their website...I've seen them do better.

  13. IOops? by Anonymous Coward · · Score: 0

    Shouldn't that be IOops? Or would that sound too much like an Apple brand?

  14. Re:I'm waiting for price/performance and benchmark by afidel · · Score: 3, Informative

    I stand corrected, from the talkback link I followed a trail to an IBM blog with a LOT more details here, and this is the 70/30 SPC-1 benchmark numbers with cache disabled. This is freaking phenomenal performance! The storage is only 4TB, but if you put your logs, flashback, and temp tables on this beast and pinned your busiest tables in ram you would have a screaming OLTP database. I guess it's now just a matter of price, but a rack of x-series boxes with flash card's shouldn't be THAT expensive. Unless IBM asks for a crazy markup it should be affordable for most enterprises (ok, pretty much a given with IBM but still).

    --
    There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  15. with this kind of speed by nimbius · · Score: 1

    i might be able to get vista to run at near real-time speeds.

    --
    Good people go to bed earlier.
  16. oooooooh by amnezick · · Score: 1

    with 1M IOPS she won't even know how many times she's done ...

    --
    mov ax,4c00h
    int 21h
  17. Technical Details by Anonymous Coward · · Score: 0

    From a MB/s point of view each card can sustain 600MB/s so with the 48 of them, that would be >28GB/s

    However, anyone can string a bunch of devices together than can do lots of reads or writes... The key is to a mixed workload, that is of a typical system like request, so we chose 4K random 70/30 IOPs - more details here

    http://www.ibm.com/developerworks/blogs/page/storagevirtualization?entry=1m_iops_from_flash_actions

  18. Does this mean... by Hurricane78 · · Score: 2, Insightful

    ...that they will be worn out in 0.1 seconds? (If typical wear-out numbers apply.)

    I'll pass, and rather go with something reliable... ...now where did I put my chisel?

    --
    Any sufficiently advanced intelligence is indistinguishable from stupidity.
    1. Re:Does this mean... by Anonymous Coward · · Score: 0

      ...that they will be worn out in 0.1 seconds? (If typical wear-out numbers apply.)

      I'll pass, and rather go with something reliable... ...now where did I put my chisel?

      No, each cell can be written 100,000 times. With each cell being 2K, with 4TB and some 5TB physical (you have a whole bunch of space for wear-leveling)

      Most enterprise level flash devices (which should NEVER be compared to USB sticks...) have all their IP in the wear-leveling, write-avoidance and garbage collection algorithms. They use LSA type directories to ensure an even wear across all cells in all the flash chips on a device.

      By my estimation this would take around 5 years at 100% writes before any problems occur. How many of you are still using HDD that are 5 years old?

  19. Slow by matt_martin · · Score: 1

    meh ... MRAM runs faster than 25 million ops/second !
    http://everspin.com/

    Yeah, OK , I work there - std disclaimers apply.

    --
    Lurking in the desert
  20. Third I/O Broke This Record a Long Time Ago by Ken+Randall · · Score: 1

    I personally have seen their device running standard benchmarks on shipping hardware at over 1 million IOPS. www.thirdio.com Also, a company called Violin Memory claims to have broken the 1 million IOPS barrier recently as well. As IBM's technology is at least a year away, I'd have to say I'm more impressed with faster solutions that are already available.

  21. Re:I'm waiting for price/performance and benchmark by clem.dickey · · Score: 1

    Read the link carefully. It is not SPC-1, nor modified SPC-1. It is 4K IO in a 70/30 read/write mix.