On Mon, Jan 31, 2011 at 3:16 PM, Jim Schutt <jaschut@xxxxxxxxxx> wrote: > > On Mon, 2011-01-31 at 15:57 -0700, Colin McCabe wrote: >> >> > If Ceph scrub works this way, then another >> > thing I really want to do is learn to tell my disks to not try >> > so hard to recover a sector, as I know I have at least one other >> > copy I can use to repair it, and because that minimizes the time >> > that osd is stalled. >> >> Do you set these kind of timeouts through smartctl or hdparm? > > > I've never done this on any drives that we use, so I > don't know and would really like to learn more. > > But here's an example of more info of the sort that > got me thinking about it: > http://en.wikipedia.org/wiki/Time-Limited_Error_Recovery Yeah, I'm vaguely familiar with this sort of thing from my time in the storage industry. I'm pretty sure it has to be configured in the hard drive firmware rather than at a higher layer of the stack. Of course the drives that, say, NetApp sells you will come configured this way. But how do you get this behavior from white box stuff? That's the question. Colin -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
