> We have a rather long freeze phase this time (which I think is a good > thing). This patch fixes a regression, even if it may not be the most > important one because it is in experimental code. But I still think that > this time in the hard freeze is the right time to commit patches like > this. I would be very hesitant with such a patch like in the two weeks > before the release, but at this point I'm very open to including it. > > All that requiring proper review and testing, of course. I reviewed it > and it looks good to me and Stefan seems to have reviewed it as well, so > I think it just needs a bit more testing.
My judgement came from Ming saying that coroutine pools and plug/unplug alone bring dataplane to the level of 2.0. It doesn't surprise me that write to eventfd is so optimized that it matters less than expected. If this patch is properly tested with rbd and gluster, it's okay for me to include it. Still, it feels good that for once I'm the one on the safe side. ;) Paolo
