Google Hard Drive Study

H

HardOCP News

[H] News
Joined
Dec 31, 1969
Messages
0
Yesterday, Engadget posted a link to a study on hard drive failure done by Google that found heat was less of a factor in drive failure than stuff like manufacturer, model, and age. As the quote below states, Google didn’t mention any names.

Google studied a hundred thousand SATA and PATA drives with between 80 and 400GB storage and 5400 to 7200rpm, and while unfortunately they didn't call out specific brands or models that had high failure rates, they did find a few interesting patterns in failing hard drives.
Click to expand...
 
Just skimmed through the pdf. Interesting read. Wish they would have broke it down by brand/model. I mean that would be the best test of mfgs I could think of due to the sheer number of drives.
 
The whole temp thing interests me. There seems to be the general consensus that when it comes to computers, the cooler the better. This is great news for my jobs data center, I think I'll raise the temp a little so the AC doesn't have to work so hard in the summer. (We keep the room at 62*F)

I wonder if this can be applied to home computers that are power cycled on and off. I want to know if there is less failure for warmer hard drives or cooler drives that have to deal with smaller temperature changes between when it is on and off.

This makes me feel more confident about my choice to 5V the fan that cools my hard drives to cut down on noise. Hopefully this means I am also increasing their lifespan. I like win-win situations. :cool:
 
I know that google doesn't wish to be sued but why spend millions on this rather brilliant survey and then leave consumers out in the cold? That's kinda messed up, I mean, what about all the millions of people out there buying a drive that say fails every year and a half no matter the load when Google may know of a better, cheaper alternative that just necessitates a change of brand...?

Google, Release some specifics on the BEST drives, not the worst.. No one can sue you for talking GOOD about a brand!

~Adam
 
Let's be honest, Google's going to release the brand comparison as soon as they finish the report display page with ad columns.

That or it's pay-per-view ;)
 
This is good news to me as my laptop's HD often works at 60 or near 60C.

When Google the master of data centres talks about storage, people listen. The complete document is a very powerful tool in the HD business. Should the name of the worst drive maker was ever to leak out the result can be devastating for them.
 
Hypernova said:
Should the name of the worst drive maker was ever to leak out the result can be devastating for them.
Click to expand...

And should a consumer who has bought one of their hard drives lose crucial data, the result can be devastating for them.
 
One word: Maxtor

Don't EVER buy a maxtor....EVER!

/Seagate OEM + 5 yr warranty ftw!
 
Hypernova said:
This is good news to me as my laptop's HD often works at 60 or near 60C.
Click to expand...
Only for the first couple years of its life.
"What stands out are the 3 and 4 year old drives, where the trend for higher failures with higher temperature is much more constant and also more pronounced."

Here are 3 quotes I found interesting.
"The critical threshold analysis confirms what the charts visually imply: the critical threshold for scan errors is one. After the first scan error, drives are 39 times more likely to fail within 60 days than drives without scan errors."
"After their first reallocation, drives are over 14 times more likely to fail within 60 days than drives without reallocation counts, making the critical threshold for this
parameter also one."
"Despite those strong correlations, we find that failure prediction models based on SMART parameters alone are likely to be severely limited in their prediction accuracy, given that a large fraction of our failed drives have shown no SMART error signals whatsoever."
 
i couldn't find which page in the article said 100,000 drives. can someone link me to it?
 
You must log in or register to reply here.
Back
Top