On 2018/12/13 23:49, Stefan Hajnoczi wrote: > On Thu, Dec 13, 2018 at 11:08:04AM +0800, jiangyiwen wrote: >> On 2018/12/12 23:37, Michael S. Tsirkin wrote: >>> On Wed, Dec 12, 2018 at 05:29:31PM +0800, jiangyiwen wrote: >>>> When vhost support VIRTIO_VSOCK_F_MRG_RXBUF feature, >>>> it will merge big packet into rx vq. >>>> >>>> Signed-off-by: Yiwen Jiang <jiangyiwen@xxxxxxxxxx> >>> >>> I feel this approach jumps into making interface changes for >>> optimizations too quickly. For example, what prevents us >>> from taking a big buffer, prepending each chunk >>> with the header and writing it out without >>> host/guest interface changes? >>> >>> This should allow optimizations such as vhost_add_used_n >>> batching. >>> >>> I realize a header in each packet does have a cost, >>> but it also has advantages such as improved robustness, >>> I'd like to see more of an apples to apples comparison >>> of the performance gain from skipping them. >>> >>> >> >> Hi Michael, >> >> I don't fully understand what you mean, do you want to >> see a performance comparison that before performance and >> only use batching? >> >> In my opinion, guest don't fill big buffer in rx vq because >> the balance performance and guest memory pressure, add >> mergeable feature can improve big packets performance, >> as for small packets, I try to find out the reason, may be >> the fluctuation of test results, or in mergeable mode, when >> Host send a 4k packet to Guest, we should call vhost_get_vq_desc() >> twice in host(hdr + 4k data), and in guest we also should call >> virtqueue_get_buf() twice. > > I like the idea of making optimizations in small steps and measuring the > effect of each step. This way we'll know which aspect caused the > differences in benchmark results. > > Stefan > Yes, now I also focus on other project, but I will use some extra time to measure it. Thanks, Yiwen.
