On Mon, 9 Jan 2006, Ryan Richter wrote: > > One thing I forgot to mention was that 2.6.11.3 had the problem too when > I reverted to it. I remember now that the person who made the debian > bug report for this said it only happened with a 64-bit userspace - and > I switched from a 32- to 64-bit userspace when I did 2.6.11 -> 2.6.14 > (and I'm too lazy to switch back). I remembered you reported it originally on 2.6.14.N, so I wasn't searching amongst the 2.6.15 changes at all. Thanks for the info that it's at least as old as 2.6.11.3. > To get the backups back, I just ran a recent kernel with > try_direct_io=0. If there's nothing further for me to test at this > time, I guess I'll go back to doing that until there's something to try. > Is that OK? I think we'll allow you the luxury of making successful backups for now ;) Thanks for all your work on this, I'm sure it's irritating to you that we haven't found the answer yet. I'm still clueless about it (despite the excellent clues you've provided). And personally I don't like asking someone "try this, try that" until I've a pretty good hypothesis to devise a patch to test out. Still thinking it over. Someone else may have a better idea of what to try next. Hugh - : send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
