On Sat, Nov 06, 2004 at 12:47:46AM +0100, Lars Marowsky-Bree wrote: > I've had to think about this one a bit. But there's also a flaw in the > bypassed logic here (at least as implemented now, unless you got some > patch I've not yet seen). Namely, we don't ever reset it. We rely on userspace to reset it. So yes, it's not good if the first PG is not genuinely bypassed and has now become the newly-preferred PG: that would need a table reload. > So yes, we probably ought to remember that we switched PGs, but probably > also should clear that flag after some IO has succeeded once w/o causing > a PG switch over. At the moment, I still prefer to leave that to userspace. (On the grounds that there's policy involved here - how much I/O or elapsed time? Depends on the failure mode.) > Well there might be the reason to set them on the initial table load to > get us off started correctly. To set the number of the PG to be used first, like you suggested. That all seems to make for a coherent approach again, cleaner to use than before, though slightly more complex internally currently. Alasdair -- agk@xxxxxxxxxx