Using RAID 0 with unequal capacity drives - K8V SE Deluxe

Discussion in 'Asus' started by Bill, Apr 25, 2004.

  1. Bill

    Bill Guest

    I am assembling a machine using the ASUS K8V SE Deluxe and would like to
    use the on board SATA RAID 0 capability.

    If I use two Seagate SATA drives (160 & 200 Gb) in a RAID 0 (strip)
    configuration, what happens to the extra 40 Gb on the larger drive? Can
    I partition the 200 Gb drive into a 160 and 40 Gb to enable the use of
    the 40 Gb as another drive? Is there a performance hit for using two
    unequal capacity SATA drives?
     
    Bill, Apr 25, 2004
    #1
    1. Advertisements

  2. Bill

    Andrew J Guest

    You will have one SCSI drive as far as your system knows that is
    320GB. You can't use any extra space and the cache on each drive will
    be disabled. Large file tranfers will be better but small ones will be
    worse. Seek time will not be faster There was a time when not using
    identicle drives caused a performance hit but these days not so much.
     
    Andrew J, Apr 25, 2004
    #2
    1. Advertisements

  3. Bill

    Milleron Guest

    You lose the 40 GB. The striped array will appear to be a single
    320-GB drive which you can partition any way you want AFTER creation
    of the array, but you cannot partition BEFORE you create it.
    (Literally speaking, of course, you could, but in the process of
    creating the array, those partitions would be lost.)

    The question about the performance hit is a good one. I don't know
    the answer. FAQs on the subject advise using identical drives if
    possible, though, so perhaps a size-mismatched RAID 0 does read and
    write more slowly. At any rate, I believe that any difference would
    be imperceptible and detectable only with benchmarking.

    --Stop reading here unless you want to hear my standard RAID-0 rant.--

    You do realize that even size-matched striped arrays themselves do not
    provide any perceptible performance improvement for desktop use, don't
    you? This statement is not intuitive because intuition tells you
    that any read or write should take only half as long on a RAID 0 as it
    would on a single disk, but in practice, there is amazingly little
    difference. Most (all ?) onboard RAID controllers utilize the CPU to
    do their thing, and this induces latency approximately equal to the
    read-write-time savings. Unless one is doing extensive video editing
    or other sophisticated multimedia work, there's not much use for RAID
    0 outside of servers and definitely not on machines used primarily for
    gaming (RAID 1 is another matter entirely). I have a 3Ware PCI-based
    RAID 0 that does not utilized the CPU, and even that provides no
    appreciable performance enhancement. Newer chipsets routing data
    through the IDE bus rather than the PCI bus may actually have the
    potential to give perceptible improvement but even these continue to
    use the computer's CPU, and, for now, HDDs don't seem to be able to
    stream data faster than the PCI bus can handle it.
    The main problem for me, though, is that striped arrays positively
    DOUBLE the chance of a disk failure -- i.e., no appreciable
    performance improvement with twice the chance of HDD failure. I
    cannot see the upside to this scenario.

    My next homebuilt will have a small WD Raptor for the OS and one or
    more very large 7200RPM drives for everything else. Haven't ruled out
    RAID 1 for the OS, but I'll never install RAID 0 in a home machine
    again unless the technology changes.

    Ron
    Ron
     
    Milleron, Apr 25, 2004
    #3
  4. Bill

    Andrew J Guest

    Well..... that's where you lost me. That sentece is false. If he has
    one drive and it goes bad he loses all his data. If he stripes with
    two and loses one, he loses all his data. Almost a complete wash. Your
    statement is almost like saying since your neighbor owns two cars he's
    twice as likely to crash. A quick look at his insurance policy will
    show that they don't believe that.
    No RAID setups( 0, 1 or 5) are a substitute for backing up anyway.


    Digital Media, Mike Newcomb writes:

    "Point 2: It is my understanding that A RAID 0 system does not
    "double" your failure rate or risk of failure. The impact from a
    statistical stand point is something less than "double" the risk. In
    order to ascertain what the actual risk increase is, a number of
    factors, such as MTBF (Mean Time Between Failure) rate, must be
    considered.

    See, link for forumla/light
    reading:http://www.itl.nist.gov/div898/handbook/apr/section1/apr182.htm

    In reality, the additional risk is insignificant when virtually all
    drives have a MTBF rate of more than 100,000 hours and you will
    probably have your system for less than 5 years. (Hint: there is 8,760
    hours in a year)".
     
    Andrew J, Apr 25, 2004
    #4
  5. Bill

    Rob Stow Guest

    Actually he is quite correct: the probability that a stripe set
    will fail is essentially proportional to the sum of the probability
    of the individual drive failures.

    Suppose that the probability that a drive will fail in a certain
    time interval "T" is "P", with P being a very small number.

    Then in you have a single drive, the probability that the drive
    fails during an interval "T" is obviously P.

    If you have two striped drives, then the probability of the losing every
    thing on the stripe set is:
    P(1-P) (Drive 0 fails, Drive 1 survives)
    +(1-P)P (Drive 0 survives, Drive 1 fails)
    + P^2 (Both drives fail)
    ---------------------------------------------
    2P - P^2 TOTAL propability of losing the stripe set

    Since P is very small, P^2 is negligible relative to 2P
    and is typically ignored.


    That page does *not* support your contention.
    S'matter of fact, the formula on that page for Fs(t) is
    essentially just another route to what I have done above:
    Fs(t) = 1 - (1-P)(1-P) = 2P - P^2


    As well, there is the statement along the left hand side
    of that web page "Add failure rates and multiply reliabilities
    in the series model." That statement is just a first-order
    approximation of the formulas on that page for Fs(t) and Rs(t).

    There is (was?) a nice article about MTBF, as applicable to
    hard drives and RAIDs at IBM's site. Home of many of the
    world's best scientists and engineers, in case you have
    forgotten.

    They cautioned against RAID 0 because ...
    If a single drive has an MTBF(single) of "T", then
    (as a first order approximation)
    MTBF(RAID 0, n drives) = MTBF(single) / n^2

    In other words, if you stripe 2 drives, then the MTBF
    of the stripe set is ONE-QUARTER of the MTBF of a single
    drive.


    As well MTBFs can be extremely misleading.
    As you said, there are only a few thousand hours in a year.
    Nobody tests a batch of drives for 20 years in order to
    get real empirical evidence of how long the drive can be
    expected to last. Instead they test a lot of drives for
    one or two years and extrapolate from that.

    Statistical modelling like that can be extremely accurate
    if all of the underlying assumptions are valid - but they
    can be wildly inaccurate if just one assumption turns out
    to be invalid. IBM found that out the hard way with their
    deathstar hard drives, WD found that out with their
    DiamondMax9 drives, and Fujitsu found that out ...



    And MTBFs can be extremely misleading in other ways.
    If half of a batch of drives will fail in 10,000 hours
    and the other half will fail in 190,000 hours, then the
    MTBF is 100,000 hours but I sure as heck wouldn't want
    one of those drives.

    In other words, those huge MTBF numbers means squat - I
    would much rather know the probability that a drive will
    fail during some more useful time interval.
     
    Rob Stow, Apr 25, 2004
    #5
  6. Bill

    anon Guest

    The cars analogy is incorrect, unless both are being used at the same time
    in which case the 'failure' rate is increased.
     
    anon, Apr 26, 2004
    #6
  7. Bill

    Bill Guest

    Thanks for the help. I think I will go without the RAID 0 set up. I had
    not considered the failure factor. I would have to agree that two
    drives are four times more likely to fail. MTBF only addresses
    hardware. Software corruption is far more common and very likely.
    Without RAID 0 only one drive at a time would be at risk. Since one of
    the drives would contain only data files, it could be easily restored
    and in my experience soft failures on data drives only affect individual
    data files, not the whole disk.
     
    Bill, Apr 26, 2004
    #7
    1. Advertisements

Ask a Question

Want to reply to this thread or ask your own question?

You'll need to choose a username for the site, which only take a couple of moments (here). After that, you can post your question and our members will help you out.