Randall R Schulz wrote:
While this study is great, one should not forget that the google usage environment of hundreds of thousands disks is not directly comparable to what most people do at work or at home.
I.e. most people do not work in air-conditioned data centers and most desktops do not run 24x7.
My systems run 24x7 and are, technically, servers (which is why I run them continuously), though they do not generally experience the kind of continuous use that the Google servers do.
As far as environmental controls, it's also true I do not have air conditioning, but most of the time (outside a few summer days, when I sometimes will shut down the systems), the temperature where these machines are located is only a little warmer than the typical air-conditioned machine room.
So your usage conditions are very near to googles, maybe except the load on your servers in contrast to theirs. That means that as soon as you have used up a few (ten)thousand disks, your results will most probably be very similar to Google's. ;-))
So while the google paper is certainly informative and a rare beast in regard to the observation of a very large population of commodity harddisks, I would not dare to use any of it's conclusions lightly for my home usage pattern.
Well, it is empirical information.
It is, indeed, and one of only two afaik, so it is really a gem. And I don't even know what it means
to "use it's conclusions lightly." How would you suggest the results be biased to better reflect office use? No way. For this you better use data from the desktop computer departments of Procter@Gamble or GM, if you can get hold of it. ;-)
Are you just saying that if SMART gives a warning I should "be afraid, be very afraid?"
I did not say anything about smart and maybe the google anylysis is ok in showing, that smart is sometimes correct, sometimes not. However this is nothing new. Common sense tells us, that sometimes disks fail, suddenly "out of the blue". Otoh, experience tells us that sometimes they last longer than they should, according to some "smart" tests, at least.
From my personal point of view, I would value the security of my data against the (potentially) needless purchase of a new disk.
Maybe you could also use up your old one as a mirror or RAID disk, thus putting it to good use, as long as it delivers. regards Eberhard -- To unsubscribe, e-mail: opensuse+unsubscribe@opensuse.org For additional commands, e-mail: opensuse+help@opensuse.org