We have a lot of Seagate, and haven't noticed problems nearly as severe as that, or as Backblaze saw. But none of this is very conclusive. One thing I would mention is that the resilvering process in Linux is very restrictive. It gives up after a single unreadable sector on the drives it needs to read - even if that sector isn't in use. I'd prefer it to reconstruct as much as it can, but I suppose it would be complicated to report which files were incomplete.
daniel feenberg NBER On 5/5/15, Mason Loring Bliss <[email protected]> wrote: > On Tue, May 05, 2015 at 08:46:34AM -0700, Rich Braun wrote: > >> RIP, Seagate? Do you share that sentiment? (And, are you monitoring all >> your drives' temperature and error counters?) > > Yeah, avoiding Seagate is a safe move. You're moving in the right direction > with Hitachi and WD. > > Note that SMART statistics are *not* necessarily comparable between drive > manufacturers, either in terms of what measures are provided and what > similarly-named measures mean. > > Useful reading: > > https://www.backblaze.com/blog/hard-drive-smart-stats/ > > -- > The creatures outside looked from pig to man, and from man to pig, and from > pig > to man again; but already it was impossible to say which was which. - G. > Orwell > > _______________________________________________ > bblisa mailing list > [email protected] > http://www.bblisa.org/mailman/listinfo/bblisa > > _______________________________________________ bblisa mailing list [email protected] http://www.bblisa.org/mailman/listinfo/bblisa
