On Mon, Mar 07, 2016 at 02:59:55AM +0000, Xie, Huawei wrote:

On 3/7/2016 10:47 AM, Yuanhan Liu wrote:

quoted

On Mon, Mar 07, 2016 at 02:32:46AM +0000, Xie, Huawei wrote:

quoted

On 3/4/2016 10:15 AM, Yuanhan Liu wrote:

quoted

On Thu, Mar 03, 2016 at 04:30:42PM +0000, Xie, Huawei wrote:

quoted

On 2/18/2016 9:48 PM, Yuanhan Liu wrote:
We could always allocate the head mbuf before the loop, then we save the
following branch and make the code more streamlined.
It reminds me that this change prevents the possibility of mbuf bulk
allocation, one solution is we pass the head mbuf from an additional
parameter.

Yep, that's also something I have thought of.

quoted

Btw, put unlikely before the check of mbuf_avail and checks elsewhere.

I don't think so. It would benifit for the small packets. What if,
however, when TSO or jumbo frame is enabled that we have big packets?

Prefer to favor the path that packet could fit in one mbuf.

Hmmm, why? While I know that TSO and mergeable buf is disable by default
in our vhost example vhost-switch, they are enabled by default in real
life.

mergable is only meaningful in RX path.
If you mean big packets in TX path,

Sorry, and yes, I meant that.

i personally favor the path that
packet fits in one mbuf.

Sorry, that will not convince me.

	--yliu