25,000-Drive Study Gives Insight On How Long Hard Drives Actually Last

MrSeb writes with this excerpt, linking to several pretty graphs: "For more than 30 years, the realm of computing has been intrinsically linked to the humble hard drive. It has been a complex and sometimes torturous relationship, but there's no denying the huge role that hard drives have played in the growth and popularization of PCs, and more recently in the rapid expansion of online and cloud storage. Given our exceedingly heavy reliance on hard drives, it's very, very weird that one piece of vital information still eludes us: How long does a hard drive last? According to some new data, gathered from 25,000 hard drives that have been spinning for four years, it turns out that hard drives actually have a surprisingly low failure rate."

Comments

Um..

[Pikoro]

Yah, except for my Western Digital Green which failed 3 days after the warranty expired. And similar accounts on newegg...

Re:Um..

[alen]

over the last 20 years i've used almost every brand of hard drive and have had all the brands fail at least once. every single brand has had quality issues at one time or another

Re:Um..

[Joining Yet Again]

Maybe it's a CONSPIRACY in which they've invested ALL their manufacturing PRECISION into guaranteeing that the drives will fail precisely THREE DAYS after WARRANTY.

Consider this! You register for warranty, and you enter the purchase date, right? What if... WHAT IF... some FIRMWARE CODES in the drive pick up this transaction and STORE THE INFORMATION IN FLASH. Then then starting the day after warranty expiry the drive STARTS TO DO BAD THINGS f.e. not park properly or run just a little too slowly or maybe even there's like a secret drop of DESTRUCTION SAUCE which is released onto the platters at this time.

Anyway you see where I'm getting here? REPTILE OVERLORDS are conspiring with 9/11 truthers (yeah they're in on it! it's all a false flag operation) to destroy hard drives.

And this whole study.

Is.

SPONSORED BY A JEWISH-OWNED CORPORATION.

Yeah.

Re:Um..

[Gavagai80]

This would explain why I've never had a hard drive fail on me yet in my life: I've never registered for a warranty on one. If you don't get the warranty, the reptiles don't bother sabotaging you.

Re:Um..

[andy55]

Who is General Failure anyway, and why does he keep trying to read my hard drive??

Re:Um..

[greenfruitsalad]

For the last 4 years I've had to deal with WD RE2, RE3 and RE4 hard drives. Although they are enterprise sata hard drives, they seem to fail at a rate much worse than the consumer ones Backblaze based their report on. I see much fewer problems in the first year but they usually start dying when they reach 16000 power-on hours, with only about 40% exceeding 26000 hours.

Having said that, I count sector reallocation as a failure. In my experience, as soon as a disk has non-zero value in Reallocated_Sector_Ct and Reallocated_Event_Count, it usually fails completely within a few weeks or months.

Fortunately, WD has a tool on their website which you must run before they give you an RMA number. I managed to get its source code:

int main()
{
      printf ("Disk OK, no errors found.");
      return 0;
}

Re:Um..

[RabidReindeer]

Who is General Failure anyway, and why does he keep trying to read my hard drive??

I'm sorry, that's classified. And the NSA categorically denies doing it.

Re: Um..

[jd2112]

He is Kernal Panic's superior officer.

20% failure rate in 3 years is LOW?

[xxxJonBoyxxx]

>> hard drives actually have a surprisingly low failure rate.

You call a 20% failure rate in 3 years LOW? My career rate is closer to 5% over 5 years - who keeps buying all those crappy hard drives?

Re:20% failure rate in 3 years is LOW?

[the_other_chewey]

Careful. These are consumer grade drives. In other words, they're meant for use by typical consumers, where the disk spends 99.9999% of its time track following and running in a relatively low power state.

That would amount to about 32 seconds of activity per year.
There's more drive activity than that in a single Windows boot.
Stop making up numbers.

Google's own study was 4 times larger

[greg.allen.uk]

http://hardware.slashdot.org/story/07/02/18/0420247/google-releases-paper-on-disk-reliability

Re:Google's own study was 4 times larger

[tlhIngan]

Doing some more reading of their blog and when the floods hit Thailand they actually harvested harddrives from external drives (another blog-entry); makes me think maybe those drives are crappier by default / endure worse treatment on the way from the factory to the consumer.

They are, actually. They're often custom made for the purpose - because when you think about it - what's the point of a high speed hard drive when USB is the limiting factor?

USB mass storage doesn't support more than one outstanding request at a time, so features like NCQ and all that are pointless. Large caches were pointless in a world of USB 2.0 and the data can be pulled from the media faster than the interface (has there been any USB 2.0 hard drive that gets more than 20MB/sec transfer? That's less than half the theoretical... and most mechanisms can pull 40+MB/sec off the inner tracks). Likewise, there's no point putting high speed drives in there - the latency and seek times are pretty much the same, so 7200RPM vs 5400? No big difference.

And of course, they're popular and cheap and unless you can put value-add on there, people pay little, so the goal to make them really cheap is paramount. Heck, the later original Xboxes had 8GB drives that were bare bones cheap - Seagate got rid of a ton of bearings and other stuff.

Heck, in some USB3.0 drives, especially those by WD and Seagate, they don't use SATA anymore - the drive electronics speak USB 3.0 natively with onboard controllers.

Only four years?

[Bill_the_Engineer]

Four years isn't long enough. Come back to us when you reach 6 or 8 years. The study looked at drives during the warranty period (WD drives have 5 year warranty).

Also the information they presented doesn't show that low of a failure rate.

Re:No one else?

[WoodstockJeff]

http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/archive/disk_failures.pdf

"Failure Trends in a Large Disk Drive Population", dated 2007.

20% is bad...

[Lumpy]

99% of consumers have no backups and no raid, so 20% failure rate = 20% chance of losing EVERYTHING.

I call that an unacceptably high failure rate.

And note: I also have seen a 20% failure rate at home. Higher if I use the crap WD green drives.

Useless study

[slashmydots]

This study was completely useless. WHAT BRAND WERE THEY?! Hitachis and Fujitsus have a higher failure rate by a factor of about ten than a top of the line Seagate drive.

Re:Useless study

[Anonymous Coward]

Need lube to get more statements out of your ass?

Re:Useless study

[SJHillman]

Since you apparently already have the statistics, why do you need theirs?

Re:Brands/temperatures/power cycling

[jhumkey]

Only my personal experience but as for "power cycling" . . . I follow one basic rule.

If you turn it off every night (when you go home from work) . . . it'll work fine, and last five years . . . then you're in the danger zone.
If you LEAVE IT ON for weeks at a time and NEVER turn it off . . . it'll work fine, and last five years . . . then you're in the danger zone.
What you NEVER want to do is . . . run it for a year (like at a factory plant) then turn it off for a week vacation. You're toast. (In my limited experience of 28 years) . . . if you turn it off that week . . . there is a 75% chance . . . it'll never turn on again.

I don't know if the "grease" settles, or the metal binds . . . I just know if its been on a year . . . don't turn it off for more than an hour or two if you want it to continue to work.

Next step

[jones_supa]

Run the test longer and show us the data for span of 10 years. Additionally, reveal the brands and models of the disks. Thanks.

this is consistent with my data...

[decsnake]

I worked at an on-line service for several years way back in the late 90s and early 00s and this data is consistent with the data I collected then over perhaps an order of magnitude more units. While 25K drives may not be a lot in the scale of today's internet services it is more than enough to draw statistically valid conclusions, as opposed to that, oh, 1 drive in your desktop gaming system that failed 1 day after the warranty expired.

Re:Re-furbs

[gmclapp]

I've actually had the most luck with refurbished drives. If you find a brand on Newegg that's fairly new, you eliminate the re-furbs that failed due to wear and tear. The ones that are left are DOA drives that got sent back because of common manufacturing flaws. These drives are 100% QC tested and I've yet to have one fail. The awesome kicker is that the stigma of a re-furb virtually guarantees that they'll be cheaper as well.

Re:Re-furbs

[icebike]

If you are sure that they were a relatively new model, and the refurb was a FACTORY refurb, that might be a good method. If Joe Stocking Clerk did the refurb, who knows what you will get.

When installing, and periodically there after, It is wise to run something like smartctl -a /dev/sd? on your drives and check the power on hours and power cycle count. (Not to mention the reallocated sector count and spin retry).

You would be surprised how many refurbs are actually fairly heavily used, with a lot of hours.

My current server's raid array is averaging 5.9 years, but has only seen 53 power cycles over that time. I actually tend to believe (without a great deal of evidence) that power cycles are harder on drives than running constantly.

Google actually did a similar study some years ago. Their study of over 100,000 drives largely agreed with the present study, right down to the three-node distribution of failures over time.