On 6/25/21 3:56 PM, Eli Britstein wrote:
>
> On 6/25/2021 3:09 PM, Balazs Nemeth wrote:
>> *External email: Use caution opening links or attachments*
>>
>>
>> Ilya,
>>
>> Sure, I'll rebase my patch and also ensure netdev_is_flow_api_enabled()
>> is called once per batch. I don't expect any issue
On 6/25/2021 3:09 PM, Balazs Nemeth wrote:
*External email: Use caution opening links or attachments*
Ilya,
Sure, I'll rebase my patch and also ensure netdev_is_flow_api_enabled()
is called once per batch. I don't expect any issue with that.
Thanks Balazs.
Regards,
Balazs
On Fri, Jun
Ilya,
Sure, I'll rebase my patch and also ensure netdev_is_flow_api_enabled()
is called once per batch. I don't expect any issue with that.
Regards,
Balazs
On Fri, Jun 25, 2021 at 2:00 PM Ilya Maximets wrote:
> On 6/25/21 1:04 PM, Ferriter, Cian wrote:
> > Hi Eli,
> >
> > I have some concerns
On 6/25/21 1:04 PM, Ferriter, Cian wrote:
> Hi Eli,
>
> I have some concerns about how we plug the packet state recover logic into
> dfc_processing() here. My concerns are inline below.
>
> I'm concerned that we are hurting performance in the partial HWOL case, as
> this patchset is
Hi Eli,
I have some concerns about how we plug the packet state recover logic into
dfc_processing() here. My concerns are inline below.
I'm concerned that we are hurting performance in the partial HWOL case, as this
patchset is introducing new direct (non-inline) function calls per packet to
Bleep bloop. Greetings Eli Britstein, I am a robot and I have tried out your
patch.
Thanks for your contribution.
I encountered some error that I wasn't expecting. See the details below.
checkpatch:
WARNING: Unexpected sign-offs from developers who are not authors or co-authors
or
Recover the packet if it was partially processed by the HW. Fallback to
lookup flow by mark association.
Signed-off-by: Eli Britstein
Reviewed-by: Gaetan Rivet
Acked-by: Sriharsha Basavapatna
Tested-by: Emma Finn
Tested-by: Marko Kovacevic
Signed-off-by: Ilya Maximets
---
lib/dpif-netdev.c
