On Thu, Nov 09, 2017 at 04:22:17PM -0500, Mike Snitzer wrote: > Your 0th header speaks to the NVMe multipath IO path leveraging NVMe's > lack of partial completion but I think it'd be useful to have this > header (that actually gets committed) speak to it. There is a comment above blk_steal_bios to this respect, which is in the tree. > Also, the block core patch to introduce blk_steal_bios() already went in > but should there be a QUEUE_FLAG that gets set by drivers like NVMe that > don't support partial completion? > > This would make it easier for other future drivers to know whether they > can use a more optimized IO path. As-is there is not real need for this. But if you want to use a similar path in dm-multipath feel free to add the flag when needed.