On Mon, Jan 22, 2018 at 09:14:23PM +0100, Christoph Hellwig wrote: > > Link: https://lkml.org/lkml/2018/1/19/68 > > Suggested-by: Keith Busch <keith.bu...@intel.com> > > Signed-off-by: Keith Busch <keith.bu...@intel.com> > > Signed-off-by: Jianchao Wang <jianchao.w.w...@oracle.com> > > Why does this have a signoff from Keith?
Right, I hadn't signed off that. I just trying to get feeback if someting like that was closing the theoretical gap, which it does. I actually have something similar in my patch queue I was about to send around this area, though. I don't like having the IO path take on the error handling, and I think ending unstarted requests directly will be better long term.