On Fri, 2016-12-02 at 16:53 -0800, Alexei Starovoitov wrote: > On 12/2/16 4:38 PM, Eric Dumazet wrote: > > On Fri, 2016-12-02 at 15:23 -0800, Martin KaFai Lau wrote: > >> When XDP prog is attached, it is currently limiting > >> MTU to be FRAG_SZ0 - ETH_HLEN - (2 * VLAN_HLEN) which is 1514 > >> in x86. > >> > >> AFAICT, since mlx4 is doing one page per packet for XDP, > >> we can at least raise the MTU limitation up to > >> PAGE_SIZE - ETH_HLEN - (2 * VLAN_HLEN) which this patch is > >> doing. It will be useful in the next patch which allows > >> XDP program to extend the packet by adding new header(s). > >> > >> Signed-off-by: Martin KaFai Lau <ka...@fb.com> > >> --- > > > > Have you tested your patch on a host with PAGE_SIZE = 64 KB ? > > > > Looks XDP really kills arches with bigger pages :( > > I'm afraid xdp mlx[45] support was not tested on arches > with 64k pages at all. Not just this patch. > I think people who care about such archs should test? > Note page per packet is not a hard requirement for all drivers > and all archs. For mlx[45] it was the easiest and the most > convenient way to achieve desired performance. > If there are ways to do the same performance differently, > I'm all ears :) >
My question was more like : Can we double check all these patches wont break mlx4 driver (non XDP path) on arches with PAGE_SIZE=64KB. I have no plan using XDP before a while, but I certainly know some customers are using mlx4 on powerpc.
