Ralph Becker-Szendy wrote: > On Sun, 3 Feb 2008, Igor Sobrado wrote: > > All this is true, for the temperature ranges they studied. > >> So, temperature is not a source of disk failures. > > WRONG! For the disks that were mounted in google's data center, there > was no clear correlation between higher temperatures and failure > rates, but this does NOT extrapolate to the general case. DO NOT USE > THE GOOGLE DATA AS AN EXCUSE TO RUN YOUR DISKS HOT, you'll be sorry. >
While it's not a quantitative study, I have observed a very significant increase in drive failures when the drives in a system run hot. The basic measure I've had the best success with, is that the drive must be completely comfortable for human contact. That is, if you touch it and it feels uncomfortably cold, it's probably too cold. If you touch it and it feels anything more than warm, it's probably too hot. Yeah, I know it's not terribly scientific, but it's been a fairly reliable indicator so far. One issue which bears some consideration for Soekris boxes is, how much thermal change does the box undergo? I would suspect that running a disk in an environment that regularly goes from 0C to ~ 40C would greatly reduce the life of the disk. Comments? -Chris _______________________________________________ Soekris-tech mailing list [email protected] http://lists.soekris.com/mailman/listinfo/soekris-tech
