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
