On Mon, Jun 04, 2012 at 07:00:17PM +0800, Liu Yuan wrote: > > I think the right fix is to simply give each recover_object_work() call > > it's own work_struct in a structure also containing the oid. While > > this means a memory allocation per object to be recovered it also means > > complete independence between recovery operations, including kicking off > > onces that have I/O pending ASAP and allowing multiple recoveries in > > parallel. I'm about to leave for a long haul flight and will try to > > implement this solution while I'm on the plane. > > > > > Okay, I'll apply first 3 patches and leave this one I didn't manage to finish my implementation in time. I'd suggest to put your change 3 in for now, but I plan to get back to this. |