Slashdot Mirror

← Back to Stories (view on slashdot.org)

Researcher Turns HDD Into Rudimentary Microphone (bleepingcomputer.com)

Posted by BeauHD on from the inside-voices dept.

An anonymous reader writes from Bleeping Computer: Speaking at a security conference, researcher Alfredo Ortega has revealed that you can use your hard disk drive (HDD) as a rudimentary microphone to pick up nearby sounds. This is possible because of how hard drives are designed to work. Sounds or nearby vibrations are nothing more than mechanical waves that cause HDD platters to vibrate. By design, a hard drive cannot read or write information to an HDD platter that moves under vibrations, so the hard drive must wait for the oscillation to stop before carrying out any actions. Because modern operating systems come with utilities that measure HDD operations up to nanosecond accuracy, Ortega realized that he could use these tools to measure delays in HDD operations. The longer the delay, the louder the sound or the intense the vibration that causes it. These read-write delays allowed the researcher to reconstruct sound or vibration waves picked up by the HDD platters. A video demo is here.

"It's not accurate yet to pick up conversations," Ortega told Bleeping Computer in a private conversation. "However, there is research that can recover voice data from very low-quality signals using pattern recognition. I didn't have time to replicate the pattern-recognition portion of that research into mine. However, it's certainly applicable." Furthermore, the researcher also used sound to attack hard drives. Ortega played a 130Hz tone to make an HDD stop responding to commands. "The Linux kernel disconnected it entirely after 120 seconds," he said. There's a video of this demo on YouTube.

65 comments

  1. 130hz tone sample :) by dizzy8578 · · Score: 1

    https://www.youtube.com/watch?...

    --
    *"Cogito Ergo Liberalis"*
    1. Re:130hz tone sample :) by Anonymous Coward · · Score: 0

      That's either a 130Hz tone sample with lots of pops and clicks* or my amplifier is broken.

      * I guess the Youtube poster thought that the 130Hz tone sample sounded better on vinyl. :)

    2. Re:130hz tone sample :) by omnichad · · Score: 1

      Nyquist theorem? I know neither YouTube not my speakers have what it takes.

  2. Don't shout at your JBOD! by djsmiley · · Score: 2

    Remember: NEVER SHOUT AT YOUR JBOD!.

    It's not yelling, if it's yelling?

    --
    - http://www.milkme.co.uk
  3. This is pretty old and well-known by gweihir · · Score: 4, Insightful

    The original finding from 2008 is here:

                    https://www.youtube.com/watch?...

    No idea why anybody thinks this is worth a talk now.

    --
    Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
    1. Re:This is pretty old and well-known by Anonymous Coward · · Score: 0

      Not worth a talk? Oh, what, because all datacenters have moved to SSD or something?

    2. Re:This is pretty old and well-known by rmdingler · · Score: 1

      Yes. A startling departure from the cutting edge news source we've come to expect here at the Slashdot.

      /. --downright old (by internet standards) and pretty well-known.

      --
      Happiness in intelligent people is the rarest thing I know.

      Ernest Hemingway

  4. Idiot by Anonymous Coward · · Score: 0, Insightful

    No, you haven't turned your HDD into a microphone. It will never be accurate enough to pick up conversation, no matter what 'further research' you attempt. You've proved that making a loud noise at a HDD causes it to temporarily park That a sustained loud noise causes random latency spikes. You're a complete fucking idiot if you think this is ANYWHERE close to being able to reconstruct a kHz signal.

    1. Re:Idiot by gx5000 · · Score: 1

      Thank you.

      --
      End of Line.
    2. Re:Idiot by Anonymous Coward · · Score: 1

      I'm sure some nice men from the TLAs are now queuing outside his place offering money and facilities for him to conduct this 'further research' that you diss. One day headlines will say that terrorists have been caught using HDD sound recording technology.

    3. Re:Idiot by cachimaster · · Score: 4, Interesting

      I'm the original author.
      First, you are kind of rude for calling me idiot, specially if you didn't even read the friendly article.

      Second, have you even looked at the video? no, the disk don't "temporarily park". The delay is proportional to the vibration amplitude, mean you can sense sound volume at a low rate. Sample rate is about 50 hz, it can't reconstruct a kHz signal but voice is in the ~300 Hz, and you don't need to reconstruct the complete signal to recognize it. You don't need to recognize a conversation, you need to recognize the patterns that the conversation causes. In the original article I proved a link to a research do does exactly that with the gyroscopes in mobile devices.

    4. Re:Idiot by Lobachevsky · · Score: 5, Interesting

      I would like to apologize on behalf of people with dismissive attitudes. It is a real problem not just with anonymous posts, but even at the workplace, especially among "half-technical" people, who are are smart enough to understand jargon and comment but not enough to understand a reasoned argument. I've seen countless times where someone will quote from stackoverflow or some other source out-of-context, and several times where the source itself they quote from is utterly wrong to begin without even in-context. I might prove something with complex numbers, and they'll just quote someone saying you can't take a square root of negative numbers. Even after I convince them, they'll just laugh saying Intel cpus don't support complex numbers, and I have to show them the Intel cpu spec for hardware acceleration of complex numbers (and even without hardware support, it can be easily emulated in software). I've learned to stop trying, half-technical people are impediments to innovations.

      Now, after that apology is done, I would like to bring up some academic research that may relate to your study of signal processing. There was some research done a while back (early 2000s, I think), that found that keyboard keystrokes leaked information on electricity draw. And even though they could not directly tell which key was hit, they were able to apply a model of qwerty keystroke cadence, since people tend to be faster or slower with keystrokes depending on the sequence of keys. Applying that model with a roughly 60Hz electrical tap, they were able to successfully reconstruct full text input at a 90% confidence. Because the model relied heavily on predictive modeling, it is not good for high-entropy signals like 8-character passwords, but it is excellent for low-entropy signals like a legal memo with several paragraphs explaining one point. You also mentioned a study directly applying to low SNR audio, for speech. However, I wonder if the vibrations for keystrokes are enough to disrupt HDD latency, and if so, a bivariate model using both HDD signal and electricity signal may yield a far superior reconstruction than electricity on its own, especially since the two 60Hz signals are likely out-of-phase. My 2 cents.

    5. Re:Idiot by Anonymous Coward · · Score: 0

      Different AC, but honestly, if you don't like being called an idiot, ./ is not the place to go.

      But on a serious note, part of being an effective researcher is realizing that this thing you've worked so hard on is fairly worthless. I did the same on a project I worked on for 3 years in grad school. It was indoor localization using wifi, and it worked fairly well, it could reliably find you within 5 meters using your cellphone. The problem was, since this was a school environment, it relied heavily on having an accurate model of the wifi environment within the building. And this could be screwed up horribly, as I discovered, if somebody installed a new access point or changed a whiteboard from wood backed to metal backed or set up a ladder, the model would change drastically. And there was no good way to create this model. You either had to go through and record the wifi, which took days per building, or go through and get an accurate layout of the building, including what was inside the walls, and the locations of all wifi hot spots to create a RF propagation model.

      When at my thesis defense they asked me if I thought that this was a viable technology, I had to take three years of my life and say that though it worked well in a lab environment, and you could control for bags of interference walking around well enough, it just wasn't practical in the real world.

    6. Re:Idiot by cachimaster · · Score: 4, Interesting

      > I've learned to stop trying, half-technical people are impediments to innovations.

      It's the internet. They are assholes, you just have to have thick skin :)

      > I wonder if the vibrations for keystrokes are enough to disrupt HDD latency

      Yes, they do. I saw it myself, the HDD is much more sensitive to vibrations transmitted by the chassis than sound. You might be onto something great here. I will quote you if I ever do something like this in the future.

    7. Re:Idiot by Doctor+Memory · · Score: 1

      They already have his research, and plenty of smart people in their own labs. No further work by the original researcher needed for their purposes.

      --
      Just junk food for thought...
    8. Re:Idiot by Lobachevsky · · Score: 1

      This is the BlackHat pdf / powerpoint from 2009, by Andrea Barisani and Daniele Bianco, titled "Side Channel Attacks Using Optical Sampling Of Mechanical Energy and Power Line Leakage": https://www.blackhat.com/prese...

      It appears it less about predictive modeling regarding cadence of keystrokes and more about the data cable itself being poorly shielded and leaking onto the +5V and GND power cables.

      I still think a multivariate model using multiple low-SNR signals can be quite useful even if no univariate model of a single low-SNR signal has enough fidelity to reconstruct conversations or keystrokes. Speaking of which, how orthogonal are the signals from different HDDs in a JBOD? Will signals from 12 HDDs in the room provide sufficient signal strength for a multivariate model? If you're able to sample at 60Hz, speed of sound moves 5 meters in 1/60th of a second, so HDDs separated by 2.5m should provide considerable phase-shift. Even at 1m separation, the signals should be fairly orthogonal, and having 12 HDDs at varying distances from the audio source should give you nearly 10x the sampling frequency.

    9. Re:Idiot by cachimaster · · Score: 1

      Hey I remember your project. Or something similar. You needed like 8 SDRs right? it's basically a radar. It was great.

      Hey, it's research, not engineering. Our work is to prove that it's possible, engineers work is to make it practical.

    10. Re:Idiot by Anonymous Coward · · Score: 0

      Hey you! If you're giving blowjobs in here you need to pay for the room in advance.

    11. Re:Idiot by Lobachevsky · · Score: 1

      Regarding multi-variate / multi-signal modeling, LIGO used the same approach to successfully detect gravitational waves. They used multiple low-SNR signals from different detectors (Washington State and Louisiana) since their noise is highly orthogonal and the signal is highly correlated with the correct phase-shift applied (solve for phase-shift using SSE minimization, then extract a high-SNR signal from the newly aligned signals). Some similar approach with multiple HDDs may work if the noise is less about ambient room noise and more about internal HDD initial-head location, other HDD geometric properties, and OS reporting error due to jiffies and NMIs (these are the sort of noise that should be very non-correlated / orthogonal across multiple HDD/CPU sources).

    12. Re:Idiot by Anonymous Coward · · Score: 0

      your github repo for kscope is missing files & doesn't compile (kscope-gui.c)

    13. Re:Idiot by Anonymous Coward · · Score: 0

      Terrorists are our least important enemy when the state and commerce collude against the people. These scientific explorations wouldn't hit headlines if the surveillance state didn't want people to read about it. If the science is good, then it's yet another way for them to spy on people.

      Or it's complete bullshit and a ploy to get people to feel unsafe. This plays into further action later, the promise of security and "we'll look the other way", with a price: your freedom. Terrorists are only good at disrupting society for the sake of killing. The state is good at disrupting society for the sake of control. Which do you think has greater potential to harm you? Personally, the state's not really done much for me, and actively prevents me from doing better through the systematic erosion of my civil rights. A terrorist kills because they have been wronged by society, or they are mentally ill. Both can be worked with. Government... well, just take a look around you and see how well that works out. It's simple: work, die, or be enslaved to the for-profit prison system. Some freedom *that* is...

      Your core point ("it's okay for this tech to get studied more and used against people because we might catch them dang terr'ists") is bullshit. As science progresses, our legislation must also evolve. Privacy laws should be enacted to protect people from senseless and unnecessary government meddling. In the past, they at least needed a warrant, reasonable suspicion, and probable cause. Now? People are conditioned, like cattle, to share everything they do with Twitter, Facebook, and other shit. In fact, people suspect others when they *don't* share everything, as if you're some defective antisocial person. Couple those hives of the mindless with market access with Facebook, et al as the gatekeepers, and you have the Information Market, one where even the government can and does trade in. No doubt it was a clever move, but people are blind to where things are heading. We never read about the cases where the government wrongfully imprisons people on incomplete or suspect information, or the people whose lives they help turn around after the fact. (In truth, most barely get more than a dollar a day for their wrongful imprisonment).

      So sure, smugly kiss the boots of your masters. Don't bitch when the technology's used against you to implicate you in something no reasonable person would deem illegal or immoral. Give people -- especially government -- an inch, and they'll take light years.

  5. Before you go on a "spy on anyone" rant... by IGnatius+T+Foobar · · Score: 4, Insightful

    Before all the silly conversations begin about "omg anyone's computer can be turned into an eavesdropping device!!!1" ... remember that if you can compromise a computer to the point where you can make low-level manipulations to the hard disk ... you can also simply turn on the microphone.

    --
    Tired of FB/Google censorship? Visit UNCENSORED!
    1. Re:Before you go on a "spy on anyone" rant... by Anonymous Coward · · Score: 0

      what if the user has destroyed or disabled (not turned off the device, but the entire power supply) the microphone?

      similar to people who have duct-tape over their cameras, some people are concerned about their privacy, if hard drives actually worked as an accurate mircophone, you have a walkaround against consumers taking actions.

    2. Re:Before you go on a "spy on anyone" rant... by cachimaster · · Score: 4, Informative

      God damn, nobody read the article anymore?

      No, you don't need low-level manipulations to the hard disk, you only need to read a file, a low-privileged operation. Also, you can do it in servers that don't usually have a microphone.

    3. Re:Before you go on a "spy on anyone" rant... by bsDaemon · · Score: 1

      My laptop doesn't have a microphone or camera specifically so that they aren't physically there for anyone to compromise. The OS and most of my apps live on NVMe. There is a 2TB disk in there, though. So if someone can implant malware that could monitor disk latency caused by vibrations and then reconstruct, to some degree, ambient audio, up to and including conversation then... i guess it means that I have an excuse to upgrade that disk to an SSD and justify it as a surveillance countermeasure. (even though this seems unreliable).

    4. Re:Before you go on a "spy on anyone" rant... by Junta · · Score: 2

      The server would just hear a lot of fan noise in the vast majority of cases. It is rare for a human to even be around disks for conversation.

      In a slightly more interesting thing, you could make an out-of-band communication method, induce noise (through disk accesses but more likely fan responses) and measure noise using HDD, of course it's hard to imagine getting that much access to two distinct systems and being so desparate as to communicate this way.

      --
      XML is like violence. If it doesn't solve the problem, use more.
    5. Re:Before you go on a "spy on anyone" rant... by Bing+Tsher+E · · Score: 1

      You only need to read a file, in such a fashion that you can monitor and record low level artifacts of the file reading process.

      Wow. I bet there's a driver for that built right into the Linux kernel. One that requires no privilege escalation to access.

      Geez, get a clue. Junk science wants it's junk back.

    6. Re:Before you go on a "spy on anyone" rant... by cachimaster · · Score: 1

      You can try it yourself. There's a link to the repo in TFA.

    7. Re:Before you go on a "spy on anyone" rant... by JaredOfEuropa · · Score: 1

      God damn, nobody read the article anymore?

      You should know better by now...

      --
      If construction was anything like programming, an incorrectly fitted lock would bring down the entire building...
    8. Re:Before you go on a "spy on anyone" rant... by bws111 · · Score: 1

      Yeah, and the very first thing that code does is open /dev/sda in read mode. How poorly must you have your system configured that a regular user can do that?

    9. Re:Before you go on a "spy on anyone" rant... by phorm · · Score: 1

      Well, a lot of distros put the primary user(s) a group that allows access to external/plugabble storage devices, which would also include external hard drives.

    10. Re:Before you go on a "spy on anyone" rant... by bws111 · · Score: 1

      It is not reading 'a file'. It is reading the DISK. In any sane setup, and especially on servers, regular users can not access the disk. It is in no way a 'low privilege operation'.

    11. Re:Before you go on a "spy on anyone" rant... by Gr8Apes · · Score: 1

      SSDs.

      --
      The cesspool just got a check and balance.
    12. Re:Before you go on a "spy on anyone" rant... by Gr8Apes · · Score: 1

      Well damnit - it doesn't work on my SSD.

      --
      The cesspool just got a check and balance.
    13. Re:Before you go on a "spy on anyone" rant... by Anonymous Coward · · Score: 0

      Thank you for your research and sharing it with us. Also thank you for letting the trolls' comments roll off you like water on a ducks back.

  6. At least I have an excuse now by Anonymous Coward · · Score: 0

    Next time I'm pissed off at work, and I got into the lab to scream, I can just say that I'm conducing a HDD experiment/test.

  7. Great, but by 93+Escort+Wagon · · Score: 2

    Let me know when you can do the same thing with a microwave oven.

    --
    #DeleteChrome
    1. Re:Great, but by Anonymous Coward · · Score: 0

      Bro if you run the magnetron in reverse you can use a microwave oven as a 2.4ghz wifi antenna. Don't forget to remove the faraday cage. Oh and don't cook yourself dude. Peace out.

    2. Re:Great, but by Anonymous Coward · · Score: 0

      You don't have a smart microwave with storage yet?

  8. wow so leet by Anonymous Coward · · Score: 0

    Wow this is so much leeter than plugging a speaker into a microphone jack and running it backwards. All the techturds have used a speaker backwards as a microphone. Backwards speaker microphone is like a right of passage for every leet fakenerd.

  9. Please, God, 1TB SSD for $50 each... by ITapeFatCashews · · Score: 0

    I got six microphones in my home file server. I can't wait to replace them with 1TB SSD for $50 each in the next five years.

  10. Myopic. by Anonymous Coward · · Score: 0

    Myopic.

    Intentional or otherwise, this is unwanted.

    1. Re:Myopic. by Junta · · Score: 1

      The practicality of any sort of potential vulnerability must be considered. In a datacenter, even a human ear can generally not hear things. While someone will say 'well I tore my laptop apart and tore out the microphones and still have a spinning disk', this is a vanishingly small portion of the userbase.

      --
      XML is like violence. If it doesn't solve the problem, use more.
    2. Re:Myopic. by cachimaster · · Score: 1

      You can make this work even if you are inside a VM on your notebook. In fact, I did the whole talk while listening sound from inside a virtualbox VM, with no access to the physical mic.

    3. Re:Myopic. by bws111 · · Score: 1

      You mean inside a VM that just happens to have a real (not emulated) disk dedicated to it, and with user priviliges that allow direct access to said disk (IOW, root), right? And with both guest and host being very lightly loaded so little details like task switches don't complely hose your timing.

  11. NSA firmware by Anonymous Coward · · Score: 0

    With NSA firmware I'm sure it could pick up voices. Getting access to the "servo signal" used to push against the audio and track the magnetic groove doesn't seem like a difficult firmware modification for someone with source. I think it'd be mostly plumbing to put the signal in packets and get it out of the drive.

  12. hah! by Anonymous Coward · · Score: 0

    Very interesting read and fun watch, probably the watch was more interesting =) Don't shout at your disks folks! =)

  13. CREIMER RATING:This post is not interesting at all by Anonymous Coward · · Score: 0

    Nobody cares that you plan on upgrading your computer one day. Calling your hard drives "microphones" isn't clever or funny either.
    This isn't think kind of post that will make people run you out of town. But it's the sort of post that will keep people pissed off at you after you do something extremely dumb like concoct a post made totally out of lies and mistruths for no apparent reason other than to hit the submit button or some hamfisted attempt to monitize a comment.

  14. Re:CREIMER RATING:This post is not interesting at by Anonymous Coward · · Score: 0

    Not this shit again. Mods, please down vote this shit.

  15. Re:CREIMER RATING:This post is not interesting at by Anonymous Coward · · Score: 0

    Why not just ask creimer/cdreimer/fatcashews? As a highly regarded moderator (because of the "quality" of his posts!), he must have THOUSANDS of mod points!

  16. 130Hz failure -- article contains very little info by Anonymous Coward · · Score: 0

    I'd be curious to know if this research project actually delved deep enough to determine -- especially with the 130Hz tone test -- if it was the actual platters that vibrated, or the actuator arm vibrating (thus impacting the heads).

    I'd also be curious to know if this type of test could be done against server-class MHDDs that heavily advertise shock vibration as one of their key differences (compared to "consumer-class" MHDDs). I did notice in the video that it looks like a 2.5" MHDD was used, usually designed and intended for laptops, where shock and vibration are even more serious given the portability of the system. Some 2.5" MHDDs (ex. Toshiba), through SMART attributes (specifically attribute 191), let you monitor the G-shock rate/event count. I can't tell what exact manufacturer and model of drive was used; looks like maybe HGST or Toshiba. It matters.

    Regarding the 130Hz harmonic: I'm left wondering if this particular frequency has some effect on some part of the electrical or electronic busses, rather than the platters. libata in the Linux kernel "timing out" after 120 seconds is somewhat complicated to explain, due to how many places there are "timeouts" all across the board -- the PL used may have timeout wrappers around their read/write commands (read(2), write(2), and lseek(2) don't, or at least I've never seen it), ATA command/protocol timeouts, AHCI timeouts, SCSI/ATA emulation layer timeouts, and of course let's not forget MHDDs having their own timeouts (TLER or CCTL)). Many of the timeouts are configurable in Linux using sysctl or /proc tunables, but you have to know exactly what you're adjusting (many people do not).

    I actually reviewed the YT video, specifically where dmesg is used -- videos, BTW, are quite possibly THE WORST way to convey detailed technical information of this particular nature -- and it's hard for me to say if the actual drive fell off the bus vs. the drive F/W responding to ATA commands in a timely fashion but rejected the CDB. Determining this is made even more painful due to Linux's buffer cache and other caching (see: difference between hdparm -i and hdparm -I; hdparm -i is supposed to query the kernel's already-cached set of information from (in this case) the ATA IDENTIFY CDB during boot/disk tasting, compared to hdparm -I which always sends ATA IDENTIFY to the device). Comparatively as a data point, the BSDs do not implement a buffer cache: all I/O to block devices (ex. /dev/ada0) is direct (i.e. always O_DIRECT); caching is only done at VFS and higher layers.

    The dmesg output shown indicates something was trying to access LBA 133844 on /dev/sda. Analysis on this is further complicated by Linux's SCSI-to-ATA emulation layer -- do not confuse this with SAT/SATL, which isn't relevant here because it looks like you're using a native SATA hard disk hooked up to an actual SATA port on the HBA inside of your laptop and not, say, a SATA-to-USB adapter -- so lines like the below are actually shown using their SCSI command and CDB structure, **not** ATA command and CDB structure. I'll explain why the latter is more helpful in a moment. For example, the below taken from your video refers to the SCSI READ(10) command (command 0x28), which is the 10-byte CDB version of READ:

    [xxxxxxx.xxxxxx] sd 0:0:0:0: [sda] tag#0 CDB: Read(10) 28 00 00 10 56 a0 00 00 08 ...

    ATA protocol READ commands are usually 0x20 to 0x2F (excluding 0x28, which is reserved/unused), but common ones today are READ DMA EXT (0x25) (DMA-based 48-bit LBA read) or READ DMA QUEUED EXT (0x26) (NCQ-based 48-bit LBA read), so I know definitively the log line above is for SCSI.

    Likewise, failure lines like:

    [xxxxxxx.xxxxxx] sd 0:0:0:0: [sda] tag#0 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK ...aren't helpful either, because again, they're SCSI-esque and not ATA-esque. DID_BAD_TARGET is from the SCSI layer, and is some kind of ATA-to-SCSI translated host error co

  17. Re:130Hz failure -- article contains very little i by Anonymous Coward · · Score: 0

    Comparatively as a data point, the BSDs do not implement a buffer cache

    You're describing FreeBSD. Net- and OpenBSD have separate raw- (direct) and block (buffered) devices.

  18. I did this when I was 9 by Anonymous Coward · · Score: 0

    Easy shit. Iâ(TM)m not impressed at all.

  19. Re:130Hz failure -- article contains very little i by Anonymous Coward · · Score: 0

    I wasn't aware of that. Thank you!

  20. Re:130Hz failure -- article contains very little i by cachimaster · · Score: 1

    Hey anonymous,

    Heres the complete kernel log of one of my test. HDD disconnect starts at line 156. Maybe it helps you.

    https://pastebin.com/K22qc2Ju

    Regards,

    Alfred

  21. Done by Anonymous Coward · · Score: 0

    One morning, after the power went off for a few seconds in the middle of the night, I noticed my sister messing with the microwave oven. She asked, "How did you get your initials into the display?"

    She was disappointed when I told her that the acronym PF meant Power Failure.

  22. Re:130Hz failure -- article contains very little i by cachimaster · · Score: 1

    You provide great information. For the complete paper I might use some of it, for example I didn't look at the smart parameters but they might provide some info.

    BTW the firmware just completely blocks, as you can see in the video, it doesn't even answer the hdparm -I. But in my tests, I was also accessing the HDD constantly (this is to draw the delay graph showing above in the video) so it might be that a read() comand is queued and blocks, waiting for vibrations to stops, and it blocks all other commands being sent to the HDD.

    Another information lacking in the article: I managed to permanently damage an HDD. It didn't completely stop responding, but now the read delay is much bigger than before. While testing it at high vibrations, the HDD did some loud mechanical noises, so apparently the HDD did try to park itself multiple times. That HDD is now unusable for tests because it randomly delays reads over 10 ms (normally the read syscall takes about 500 ns).

  23. Earthquakes? Seismograph? by aklinux · · Score: 1

    I wonder if this would be more useful as a seismograph?

  24. what's a hdd? by Anonymous Coward · · Score: 0

    Solid state drives make this exercise pointless.

  25. 130Hz == Brown Note for drives by Anonymous Coward · · Score: 0

    they shit themselves

  26. CREIMER RATING:This is a disappointing reaction. by Anonymous Coward · · Score: 0

    It's always one step forward two steps back with you chris.
    Just when I thought you were close to becoming a real boy you start spazzing out. I'm afraid we'll have to send you back to special ed at this rate.

  27. Re:CREIMER RATING:This post is not interesting at by Anonymous Coward · · Score: 0

    He's a highly respected slashdot commentator. Also he's not afraid to admit his poop is like frozen yogurt on a forum about computers.

  28. Re:CREIMER RATING:This post is not interesting at by Anonymous Coward · · Score: 0

    6 accounts and none of them have any mod points bawwwwww!

  29. Are you wondering? by kerembaharlar · · Score: 1

    I think this website help us: http://www.fanatik.com.tr/2014...