Am 04.07.2014 um 09:27 hat Paolo Bonzini geschrieben: > Il 04/07/2014 09:23, Ming Lei ha scritto: > >I think it is good and better to go to 2.1, and it should save lots of > >write syscall. > > > >Also should regression be caused, the per thread trick may be > >resorted to, which should be simple. > > If we have the "right" solution (which we do, unlike the plug/unplug > case), and the benefit is there but limited, I don't see a reason to > rush another patch in 2.1. > > Some reasonable level of performance degradation or increased host > CPU utilization was expected in 2.1; of course 40% is not > reasonable. > > >With multi virtqueue's coming for virtio-blk, it should save more, and I > >also plan to use the improved qemu bh to help merge requests from > >multi queue, without introducing extra notifier. > > But virtio-blk multiqueue is 2.2 material, and so is coalescing of > irqfd writes. I think Kevin or Stefan should queue this patch (with > the smp_mb optimization, IMHO) for block-next.
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. Kevin
