On Sun, Aug 15, 2010 at 02:26:06PM -0500, Robert Nesius wrote: > Different performance profiles even though they may support the same specs, > and also the fact that even drives of the same size may not necessarily have > the same physical geometries or other physical characteristics. e.g., > different cache sizes - on a mirrored drive maybe one drive has to do a > cache flush while another one doesn't, thus causing the write to take longer > simply because one drive could absorb the write without going to the > platters while the other couldn't. What? If I ask "get this on the platter", it better be on a platter, not in the cache of some smart-less drive, waiting for the power failure. > That's assuming you didn't match cache > sizes, which most people likely would have the sense to not do even if they > were mixing/matching drives/vendors. I'm not sure what you mean here. > My experience in large-enterprise installs is that everyone uses the same > drives within their arrays and disk cabinets. My experience with large-scale restaurant operations is that the food is crap. What would happen to an admin if 3 out of the 6 drives in a cabinet fail? What would happen to the manager who signed the purchase order for 12 identical drives? Nothing -- failure has no consequences. (I am ignoring the 'find the tape and restore the stuff'. Downtime is real money, it must come from somewhere.) > We didn't experience massive > simultaneous failures, and the detection/replacement of failed drives was > just part of the service contract for the hardware. Originally we would > replace failed drives and rebuild arrays ourselves, but over the past eight > years the vendors took that over. > Lastly, diversifying drive as a risk-mitigation strategy can have the > opposite effect - one of the mix-in products may be far worse than the > others. So you'd rather have 6 identical crappy drives, or a prayer's chance that at least half are good? Cheers, florin -- Bruce Schneier expects the Spanish Inquisition. http://geekz.co.uk/schneierfacts/fact/163 -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 189 bytes Desc: not available Url : http://mailman.mn-linux.org/pipermail/tclug-list/attachments/20100816/b7a55246/attachment.pgp