Gentle persons:

In case you are interested, Google did a nice study of failures in their 
gi-normous collection of disk drives which is summarized in 
http://labs.google.com/papers/disk_failures.pdf.  As they say, they may 
have the most data available outside of manufacturer warranty databases.

Buried in the text you'll find a remark that they can't directly compare 
data points in their failure-rate vs age graph because they tend to buy 
whatever is the most cost-effective drive at the time of the purchase. 
It seems to me that the current discussion suffers similarly.

My own experience has been pretty random. Unlike in the good old days, 
when physically huge disk drives with laughably tiny data capacities 
seemed on the verge of failure every time they spun up, I've had very 
few hard drives fail in the last decade. Those that did came from 
different manufacturers and had different life histories. I'm in no 
position to damn any specific brand, and I own or have owned pretty much 
all of them. My suspicion is that periodic changes in manufacturing 
technologies within a brand are more important than differences in 
quality between brands.

Regards,
Kent




------------------------------------------------------------------------------
All of the data generated in your IT infrastructure is seriously valuable.
Why? It contains a definitive record of application performance, security 
threats, fraudulent activity, and more. Splunk takes this data and makes 
sense of it. IT sense. And common sense.
http://p.sf.net/sfu/splunk-d2d-c2
_______________________________________________
Emc-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/emc-users

Reply via email to