Viewing page 4 of 4 pages. Previous 1 2 3 4
POSTSCRIPT April 2, 2007: IS LOW HDD TEMPERATURE DESIRABLE?
An obvious assumption of this review is that high temperature is bad for hard drive health, and that lower temperature is better. The concept is widely accepted in the electronics industry, but a possible counterpoint from Google was brought up in the article discussion in the SPCR forum.
An oft-repeated quote (perhaps originating from Seagate?) is that...
"...increasing HDD temperature by 5°C has the same effect on reliability as switching from 10% to 100% HDD workload. Each one-degree drop of HDD temperature is equivalent to a 10% increase of HDD service life."
This information has a direct corollary in electronics cooling attributed to the US Army. Tony Kordyban, well-known authority on thermal management in electronics, listed the following as item #9 of Ten stupid things engineers do to mess their cooling in the magazine Electronic Cooling:
"Stupid Thing No. 9. Reducing temperature because 'every 10°C drop doubles the life.'
"This is still the gospel of the land. It started with the U.S. Department of Defense Military Handbook 217, which became the standard for electronics reliability. The 10°C rule was part of it.
"Too bad it's not true. Not even the military uses 217 anymore. But like your mom's rule about not swimming for one hour after eating, this rule lives on.
"The alternative is very messy. There are temperature limits that improve the reliability of electronics. But to apply them, you have to understand the physical processes that cause failures in each type of component. That's hard to boil down to a slogan."
If the 10°C rule for electronics is stupid, is the HDD temperature rule also stupid?
A Google study on its servers conducted last year which included over 100,000 hard drives seems to suggest that too low a temperature may have a negative effect on hard drive longevity. The May 2007 issue of Smart Computing magazine summarized the study as follows:
"Google Pinpoints Source Of Hard Drive Deaths
"Why do hard drives fail? In the past, experts have pointed to numerous factors that could contribute to a hard drives early (or not so early) demise, but new research from Google shows these conventional beliefs might be inaccurate.
"Excessive usage and high temperatures are often identified as drive-killing culprits, but Google found that these factors might not actually impact drives as severely as previously thought. Instead, the researchers discovered that parameters found in the self-monitoring facility, or SMART (Self-Monitoring Analysis and Reporting Technology), in drives tend to have more damaging potential.
"For example, drives that report higher-than-usual scan errors, which can indicate surface defects, during background scans are 10 times more likely to fail than drives with no errors. Also, reallocation counts, which occur when the drive remaps potentially damaged sectors to a new physical sector, can also contribute to a drives death. According to Google, drives with one or more reallocations fail more often than those with none.
"The study collected data between December 2005 and August 2006 from systems across all of Googles services and included more than 100,000 hard drives ranging in speeds from 5,400 to 7,200rpm and in sizes from 80 to 400GB."
Google's study is downloadble as a PDF here: Failure Trends in a Large Disk Drive Population.
The results of the study are not conclusive with regard to the effect of low temperature on hard drive reliability, but it does raise interesting questions about the generally accepted concept of heat being enemy number one of hard drives. You may want to consider this debate in the SPCR forums started by member (and SPCR author) jojo4u: Google study: effect of temperature on server hdds.
* * *
this article in the SPCR Forums.
|Help support this site, buy the Antec MX-1 External HDD Enclosure from one of our affiliate retailers!|