Difference between revisions of "Miscellaneous/hdd-lifetime"

From BubbaWiki
Jump to navigation Jump to search
Line 1: Line 1:
=  How long will my Bubba HDD last?  =
=  How long will my Bubba HDD last?  =


So, your bubba have been running for a couple of years, how long will it last? There are alot of metrics around, MTBF, CDL, AFR but what does it all mean?
So, your bubba have been running for a couple of years, how long will it last? 


There is not easy answer to that question :(  
There is not easy answer to that question :(  


<br>


You have to realize that this is all statistical data, and that doesn't apply very well to your single datapoint (your bubba).


There are alot of metrics around, [http://en.wikipedia.org/wiki/MTBF MTBF], [http://en.wikipedia.org/wiki/Design_life CDL], [http://en.wikipedia.org/wiki/Annualized_failure_rate AFR]<br>




&lt;AFR calculation example of expected failure rates goes here&gt;


WD (excito's main HDD vendor) used to quote 30,000 hours of MTBF. But all that really means is that if you had a large sample of drives, half of them would be broken after 3.4 years.




Remember to always backup data you care about (pictures, docs etc). Rule of thumb I use is to have them on three places, and all of them can't be in the same room (same closet!)


<br>  
Another example, using Googles "real world"&nbsp;AFR data (link 2 below), the AFR for the different disk ages:
 
{| width="200" border="1" cellpadding="1" cellspacing="1"
|+ Google AFR numbers
|-
! scope="col" | Disk Age (years)
! scope="col" | AFR
|-
| 1
| 1.7%
|-
| 2
| 7.9%
|-
| 3
| 8.6%
|-
| 4
| 6.1%
|-
| 5
| 7.0%
|}
 
 
 
So if you have a server room with 1000 disk, you could expect 1.7% (or a total of 17) of them to be broken after year, a total of 96 after 2 years etc...
 
== Conclusion ==
 
Hopefully you've now realized that this is all statistical data, only really meaning full if you have a big array of disks. It doesn't apply very well (with great level of certainty) to your single datapoint (your bubba).<br>
 
 
 
So, all you can really do is to remember to always backup data you care about (pictures, docs etc). Rule of thumb I use is to have them on three places, and all of them can't be in the same room (same closet!)
 
 


== Some links  ==
== Some links  ==


*[http://wdc.custhelp.com/app/answers/detail/a_id/665/p/227,294/session/L3RpbWUvMTMxOTEyMDM3MC9zaWQvaEpEWksxSGs%3D WC Official Statement]  
#[http://wdc.custhelp.com/app/answers/detail/a_id/665/p/227,294/session/L3RpbWUvMTMxOTEyMDM3MC9zaWQvaEpEWksxSGs%3D WC Official Statement]  
*[http://storagemojo.com/2007/02/19/googles-disk-failure-experience/ Google's Experiences of BIG disk arrays]  
#[http://storagemojo.com/2007/02/19/googles-disk-failure-experience/ Google's Experiences of BIG disk arrays]  
*[http://www.eweek.com/c/a/Data-Storage/Hard-Disk-MTBF-Flap-or-Farce/ Why big MTBF numbers are pointless]  
#[http://www.eweek.com/c/a/Data-Storage/Hard-Disk-MTBF-Flap-or-Farce/ Why big MTBF numbers are pointless]  
*[http://db.usenix.org/events/fast07/tech/schroeder/schroeder_html/index.html More on MTBF]
#[http://db.usenix.org/events/fast07/tech/schroeder/schroeder_html/index.html More on MTBF]


<br>
<br>

Revision as of 08:03, 21 October 2011

 How long will my Bubba HDD last?

So, your bubba have been running for a couple of years, how long will it last? 

There is not easy answer to that question :(


There are alot of metrics around, MTBF, CDL, AFR


WD (excito's main HDD vendor) used to quote 30,000 hours of MTBF. But all that really means is that if you had a large sample of drives, half of them would be broken after 3.4 years.


Another example, using Googles "real world" AFR data (link 2 below), the AFR for the different disk ages:

Google AFR numbers
Disk Age (years) AFR
1 1.7%
2 7.9%
3 8.6%
4 6.1%
5 7.0%


So if you have a server room with 1000 disk, you could expect 1.7% (or a total of 17) of them to be broken after year, a total of 96 after 2 years etc...

Conclusion

Hopefully you've now realized that this is all statistical data, only really meaning full if you have a big array of disks. It doesn't apply very well (with great level of certainty) to your single datapoint (your bubba).


So, all you can really do is to remember to always backup data you care about (pictures, docs etc). Rule of thumb I use is to have them on three places, and all of them can't be in the same room (same closet!)


Some links

  1. WC Official Statement
  2. Google's Experiences of BIG disk arrays
  3. Why big MTBF numbers are pointless
  4. More on MTBF