Slashdot Mirror


Backblaze Releases Billion-Hour Hard Drive Reliability Report (extremetech.com)

jones_supa writes: The storage services provider Backblaze has released its reliability report for Q1/2016 covering cumulative failure rates of mechanical hard disk drives by specific model numbers and by manufacturer. The company noted that as of this quarter, its 60,000 drives have cumulatively spun for over one billion hours (100,000 years). Hitachi Global Storage Technologies (HGST) is the clear leader here, with an annual failure rate of just 1% for three years running. The second position is also taken by a Japanese company: Toshiba. Third place goes to Western Digital (WD), with the company's ratings having improved in the past year. Seagate comes out the worst, though it is suspected that much of that rating was warped by the company's crash-happy 3 TB drive (ST3000DM001). Backblaze notes that 4 TB drives continue to be the sweet spot for building out its storage pods, but that it might move to 6, 8, or 10 TB drives as the price on the hardware comes down.

1 of 130 comments (clear)

  1. Re:Why does this matter? by BitZtream · · Score: -1, Flamebait

    Wrong.

    YOU don't understand how statistics ACTUALLY work.

    The stats on 5 drives ... tell you how THOSE 5 DRIVES behaved.

    The stats on 100,000 drives ... tell you how THOSE 100k DRIVES behaved.

    Neither gives you a single bit of information about the 100,001st drive. They both give a rough indication of drive reliability for short periods of time. They do not tell you shit about how long the drives will go long term. 100,000 drives for 1 year does not tell you how 1 drive will perform for 100,000 years. A billion hours doesn't tell you that either.

    They give you a high confidence in some probabilities, but statistics do not convey useful information like you seem to think, and basing things on that misguided notion is dangerous.

    The really scary part is that you got modded up a bunch because people think they understand statistics and they really have no clue :(

    Build a drive that self destructs after 2 hours, run a billion of them for 1 hour ... billion hours of time with no failures!!!!!! Most reliably drives ever made!!!!!! Does not fail!!!! Even with billions of hours of testing!!!!@$!@$!@$!@$

    --
    Persistent Volume manager for Kubernetes - https://github.com/dwimsey/openshift-pvmanager