Misperceptions about hard disk drive MTBFs

If you're using the Mean Time Between Failures (MBTF) rating as a gauge for buying hard disk drives, you're making a big mistake.

Manufacturers of hard disk drives typically label their products with various industry-standard statistics. One statistic that has sparked a lot of controversy in the hard disk drive arena is the Mean Time Between Failures (MTBF) rating.

Mean Time Between Failure ratings, usually calibrated in hours, are an index of the general lifetime of the item in bulk. So if a hard disk drive has an MTBF of 300,000 hours, that means if you run a batch of them for that long, at least half will have failed after 300,000 hours of use.

People have four misperceptions about Mean Time Between Failures when using it as a gauge to make hardware buying decisions.

  1. Mean Time Between Failures are derived from populations -- millions or tens of millions of units, not individual units. That is why MTBF ratings are misleading if used to describe the lifetime of a single unit. This is the biggest misunderstanding about MTBF.

  2. The MTBF is not constant; it can change with time. A hard disk drive that has been in operation continuously for three years may be more susceptible to failure due to changes in environment than one that was just installed. Mean Time Between Failures ratings are usually accompanied by some assumptions about usage (the "duty cycle").

  3. Many factors can affect the MTBF, such as whether or not a given component is temperature-controlled. If you take two identically rated hard disk drives, place one in a system that has no airflow to the hard disk drive cage and the other in a system that has airflow, the air-cooled drive will almost certainly last longer.

  4. A single unit can have multiple points of failure -- and some of those points can be tolerated and some cannot. This makes a single number harder to assess.

In short, an Mean Time Between Failures rating for a piece of hardware is best applied when buying many units at once. If you're equipping 1,000 desktops with hard disk drives, or creating a drive array, the MTBF for a given hard drive will give you a fairly good idea of how many of those drives are likely to fail in a given period of time.

But if you're buying one hard disk drive, the Mean Time Between Failures is not going to be of much use to you. You'll be better off relying on good backup and data retention practices than you are throwing yourself on the mercy of statistics. Sure, it wouldn't hurt to opt for a piece of hardware with a better MTBF, but don't assume that a longer MTBF will automatically protect you from mishap.

About the author:
Serdar Yegulalp is editor of the Windows Insight, (formerly the Windows Power Users Newsletter), a blog site devoted to hints, tips, tricks and news for users and administrators of Windows NT, Windows 2000, Windows XP, Windows Server 2003 and Vista. He has more than 12 years of Windows experience under his belt, and contributes regularly to SearchWinComputing.com and SearchSQLServer.com.

Hard disk drive management technical guide

  Be wary of preformatted external hard disk drives
  Hard disk drive MTBFs: The four biggest misperceptions
  Hard disk drives dying: Six signs a hard drive is about to fail
  Storage management software helps when hard disk drives fail
  Quick-formatting hard disk drives: A shortcut, but safe
  Erasing hard disk drive data: How many passes are needed?

Dig Deeper on Windows systems and network management

Start the conversation

Send me notifications when other members comment.

Please create a username to comment.