On 16-09-12 05:17 AM, Jesper Dangaard Brouer wrote:
> On Fri, 09 Sep 2016 14:29:38 -0700
> John Fastabend wrote:
>
>> e1000 supports a single TX queue so it is being shared with the stack
>> when XDP runs XDP_TX action. This requires taking the xmit lock to
>> ensure we don't corrupt the tx ring.
On Fri, 09 Sep 2016 14:29:38 -0700
John Fastabend wrote:
> e1000 supports a single TX queue so it is being shared with the stack
> when XDP runs XDP_TX action. This requires taking the xmit lock to
> ensure we don't corrupt the tx ring. To avoid taking and dropping the
> lock per packet this patc
On Fri, 9 Sep 2016 18:19:56 -0700 Tom Herbert wrote:
> On Fri, Sep 9, 2016 at 6:12 PM, John Fastabend
> wrote:
> > On 16-09-09 06:04 PM, Tom Herbert wrote:
> >> On Fri, Sep 9, 2016 at 5:01 PM, John Fastabend
> >> wrote:
> >>> On 16-09-09 04:44 PM, Tom Herbert wrote:
> On Fri, Sep 9
On Sun, Sep 11, 2016 at 08:15:28PM -0700, John Fastabend wrote:
>
> >>> But what is the action for XDP_TX if the queue is stopped? There is no
> >>> qdisc to back pressure in the XDP path. Would we just start dropping
> >>> packets then?
> >>
> >> Yep that is what the p
On 16-09-09 09:13 PM, Tom Herbert wrote:
> On Fri, Sep 9, 2016 at 8:26 PM, John Fastabend
> wrote:
>> On 16-09-09 08:12 PM, Tom Herbert wrote:
>>> On Fri, Sep 9, 2016 at 6:40 PM, Alexei Starovoitov
>>> wrote:
On Fri, Sep 09, 2016 at 06:19:56PM -0700, Tom Herbert wrote:
> On Fri, Sep 9,
On 16-09-10 08:36 AM, Tom Herbert wrote:
> On Fri, Sep 9, 2016 at 2:29 PM, John Fastabend
> wrote:
>> e1000 supports a single TX queue so it is being shared with the stack
>> when XDP runs XDP_TX action. This requires taking the xmit lock to
>> ensure we don't corrupt the tx ring. To avoid taking
On Fri, Sep 9, 2016 at 2:29 PM, John Fastabend wrote:
> e1000 supports a single TX queue so it is being shared with the stack
> when XDP runs XDP_TX action. This requires taking the xmit lock to
> ensure we don't corrupt the tx ring. To avoid taking and dropping the
> lock per packet this patch ad
On Fri, Sep 9, 2016 at 8:26 PM, John Fastabend wrote:
> On 16-09-09 08:12 PM, Tom Herbert wrote:
>> On Fri, Sep 9, 2016 at 6:40 PM, Alexei Starovoitov
>> wrote:
>>> On Fri, Sep 09, 2016 at 06:19:56PM -0700, Tom Herbert wrote:
On Fri, Sep 9, 2016 at 6:12 PM, John Fastabend
wrote:
>
On Fri, Sep 09, 2016 at 08:12:52PM -0700, Tom Herbert wrote:
> >> That probably means that the stack will always win out under load.
> >> Trying to used the same queue where half of the packets are well
> >> managed by a qdisc and half aren't is going to leave someone unhappy.
> >> Maybe in the thi
On 16-09-09 08:12 PM, Tom Herbert wrote:
> On Fri, Sep 9, 2016 at 6:40 PM, Alexei Starovoitov
> wrote:
>> On Fri, Sep 09, 2016 at 06:19:56PM -0700, Tom Herbert wrote:
>>> On Fri, Sep 9, 2016 at 6:12 PM, John Fastabend
>>> wrote:
On 16-09-09 06:04 PM, Tom Herbert wrote:
> On Fri, Sep 9,
On Fri, Sep 9, 2016 at 6:40 PM, Alexei Starovoitov
wrote:
> On Fri, Sep 09, 2016 at 06:19:56PM -0700, Tom Herbert wrote:
>> On Fri, Sep 9, 2016 at 6:12 PM, John Fastabend
>> wrote:
>> > On 16-09-09 06:04 PM, Tom Herbert wrote:
>> >> On Fri, Sep 9, 2016 at 5:01 PM, John Fastabend
>> >> wrote:
>
On Fri, Sep 09, 2016 at 06:19:56PM -0700, Tom Herbert wrote:
> On Fri, Sep 9, 2016 at 6:12 PM, John Fastabend
> wrote:
> > On 16-09-09 06:04 PM, Tom Herbert wrote:
> >> On Fri, Sep 9, 2016 at 5:01 PM, John Fastabend
> >> wrote:
> >>> On 16-09-09 04:44 PM, Tom Herbert wrote:
> On Fri, Sep 9
On Fri, Sep 9, 2016 at 6:12 PM, John Fastabend wrote:
> On 16-09-09 06:04 PM, Tom Herbert wrote:
>> On Fri, Sep 9, 2016 at 5:01 PM, John Fastabend
>> wrote:
>>> On 16-09-09 04:44 PM, Tom Herbert wrote:
On Fri, Sep 9, 2016 at 2:29 PM, John Fastabend
wrote:
> e1000 supports a singl
On 16-09-09 06:04 PM, Tom Herbert wrote:
> On Fri, Sep 9, 2016 at 5:01 PM, John Fastabend
> wrote:
>> On 16-09-09 04:44 PM, Tom Herbert wrote:
>>> On Fri, Sep 9, 2016 at 2:29 PM, John Fastabend
>>> wrote:
e1000 supports a single TX queue so it is being shared with the stack
when XDP r
On Fri, Sep 9, 2016 at 5:01 PM, John Fastabend wrote:
> On 16-09-09 04:44 PM, Tom Herbert wrote:
>> On Fri, Sep 9, 2016 at 2:29 PM, John Fastabend
>> wrote:
>>> e1000 supports a single TX queue so it is being shared with the stack
>>> when XDP runs XDP_TX action. This requires taking the xmit lo
On 16-09-09 04:44 PM, Tom Herbert wrote:
> On Fri, Sep 9, 2016 at 2:29 PM, John Fastabend
> wrote:
>> e1000 supports a single TX queue so it is being shared with the stack
>> when XDP runs XDP_TX action. This requires taking the xmit lock to
>> ensure we don't corrupt the tx ring. To avoid taking
On Fri, Sep 9, 2016 at 2:29 PM, John Fastabend wrote:
> e1000 supports a single TX queue so it is being shared with the stack
> when XDP runs XDP_TX action. This requires taking the xmit lock to
> ensure we don't corrupt the tx ring. To avoid taking and dropping the
> lock per packet this patch ad
On 16-09-09 02:29 PM, John Fastabend wrote:
> e1000 supports a single TX queue so it is being shared with the stack
> when XDP runs XDP_TX action. This requires taking the xmit lock to
> ensure we don't corrupt the tx ring. To avoid taking and dropping the
> lock per packet this patch adds a bundli
e1000 supports a single TX queue so it is being shared with the stack
when XDP runs XDP_TX action. This requires taking the xmit lock to
ensure we don't corrupt the tx ring. To avoid taking and dropping the
lock per packet this patch adds a bundling implementation to submit
a bundle of packets to t
19 matches
Mail list logo
