On Mon, May 22, 2017 at 1:42 PM, Jesper Dangaard Brouer
wrote:
> On Mon, 22 May 2017 08:39:35 +0200
> Jesper Dangaard Brouer wrote:
>
>> On Sun, 21 May 2017 15:10:29 -0700
>> Tom Herbert wrote:
>>
>> > On Sun, May 21, 2017 at 9:04 AM, Jesper Dangaard Brouer
>> > wrote:
>> > > On Sat, 20 May 201
On Mon, 22 May 2017 08:39:35 +0200
Jesper Dangaard Brouer wrote:
> On Sun, 21 May 2017 15:10:29 -0700
> Tom Herbert wrote:
>
> > On Sun, May 21, 2017 at 9:04 AM, Jesper Dangaard Brouer
> > wrote:
> > > On Sat, 20 May 2017 09:16:09 -0700
> > > Tom Herbert wrote:
> > >
> > >> > +/* XDP rx
On Sun, 21 May 2017 15:10:29 -0700
Tom Herbert wrote:
> On Sun, May 21, 2017 at 9:04 AM, Jesper Dangaard Brouer
> wrote:
> > On Sat, 20 May 2017 09:16:09 -0700
> > Tom Herbert wrote:
> >
> >> > +/* XDP rxhash have an associated type, which is related to the RSS
> >> > + * (Receive Side Scalin
On 05/21/2017 08:21 PM, Alexei Starovoitov wrote:
> On Sun, May 21, 2017 at 05:55:50PM +0200, Jesper Dangaard Brouer wrote:
>>> And it looks useful to me, but
>>
>>> 1. i'm worried that we'd be relying on something that mellanox didn't
>>> implement in their drivers before. Was it tested and guarn
On Sun, May 21, 2017 at 05:55:50PM +0200, Jesper Dangaard Brouer wrote:
> > And it looks useful to me, but
>
> > 1. i'm worried that we'd be relying on something that mellanox didn't
> > implement in their drivers before. Was it tested and guarnteed to
> > exist in the future revisions of firmwa
On Sun, May 21, 2017 at 9:04 AM, Jesper Dangaard Brouer
wrote:
> On Sat, 20 May 2017 09:16:09 -0700
> Tom Herbert wrote:
>
>> > +/* XDP rxhash have an associated type, which is related to the RSS
>> > + * (Receive Side Scaling) standard, but NIC HW have different mapping
>> > + * and support. Thu
On Sat, 20 May 2017 09:16:09 -0700
Tom Herbert wrote:
> > +/* XDP rxhash have an associated type, which is related to the RSS
> > + * (Receive Side Scaling) standard, but NIC HW have different mapping
> > + * and support. Thus, create mapping that is interesting for XDP. XDP
> > + * would primar
On Fri, 19 May 2017 20:07:52 -0700
Alexei Starovoitov wrote:
> On Thu, May 18, 2017 at 05:41:48PM +0200, Jesper Dangaard Brouer wrote:
> >
> > +/* XDP rxhash have an associated type, which is related to the RSS
> > + * (Receive Side Scaling) standard, but NIC HW have different mapping
> > + * a
On Thu, May 18, 2017 at 8:41 AM, Jesper Dangaard Brouer
wrote:
> Introducing a new XDP feature and associated bpf helper bpf_xdp_rxhash.
>
> The rxhash and type allow filtering on packets without touching
> packet memory. The performance difference on my system with a
> 100 Gbit/s mlx5 NIC is 12M
On Fri, 19 May 2017 20:34:00 -0700, Alexei Starovoitov wrote:
> On Fri, May 19, 2017 at 08:21:47PM -0700, Jakub Kicinski wrote:
> > On Fri, 19 May 2017 20:07:52 -0700, Alexei Starovoitov wrote:
> > > How about exposing 'struct mlx5_cqe64 *' to XDP programs as-is?
> > > We can make sure that XDP p
On Fri, May 19, 2017 at 08:21:47PM -0700, Jakub Kicinski wrote:
> On Fri, 19 May 2017 20:07:52 -0700, Alexei Starovoitov wrote:
> > How about exposing 'struct mlx5_cqe64 *' to XDP programs as-is?
> > We can make sure that XDP program does read only access into it and
> > it will see cqe->rss_hash_r
On Fri, 19 May 2017 20:07:52 -0700, Alexei Starovoitov wrote:
> How about exposing 'struct mlx5_cqe64 *' to XDP programs as-is?
> We can make sure that XDP program does read only access into it and
> it will see cqe->rss_hash_result, cqe->rss_hash_type and everything else
> in there, but this will
On Thu, May 18, 2017 at 05:41:48PM +0200, Jesper Dangaard Brouer wrote:
>
> +/* XDP rxhash have an associated type, which is related to the RSS
> + * (Receive Side Scaling) standard, but NIC HW have different mapping
> + * and support. Thus, create mapping that is interesting for XDP. XDP
> + *
On Thu, 18 May 2017 17:41:48 +0200
Jesper Dangaard Brouer wrote:
> Introducing a new XDP feature and associated bpf helper bpf_xdp_rxhash.
>
> The rxhash and type allow filtering on packets without touching
> packet memory. The performance difference on my system with a
> 100 Gbit/s mlx5 NIC is
Introducing a new XDP feature and associated bpf helper bpf_xdp_rxhash.
The rxhash and type allow filtering on packets without touching
packet memory. The performance difference on my system with a
100 Gbit/s mlx5 NIC is 12Mpps to 19Mpps.
TODO: desc RXHASH and associated type, and how XDP choose
15 matches
Mail list logo
