Hello and happy new year,
In our company we are looking into scaling the odp_schedule() calls.
Currently we are manually doing Receive Side Scaling, which requires one
CPU to receive all the packets and pass them to other worker CPU in a
flow-deterministic way (i.e., not spreading the packets from
ODP has several mechanisms for controlling workload distribution. The hash
functions can distribute packets from a given PktIO to a group of queues,
however the classifier is the most flexible means of controlling this. A
CoS defines a target queue for the flow. This is the queue that receives
inpu
> -Original Message-
> From: lng-odp [mailto:lng-odp-boun...@lists.linaro.org] On Behalf Of Oriol
> Arcas
> Sent: Wednesday, January 03, 2018 7:12 PM
> To: LNG ODP Mailman List
> Subject: [lng-odp] RSS in ODP
>
> Hello and happy new year,
>
> In our compa
inal Message-
>> From: lng-odp [mailto:lng-odp-boun...@lists.linaro.org] On Behalf Of Oriol
>> Arcas
>> Sent: Wednesday, January 03, 2018 7:12 PM
>> To: LNG ODP Mailman List
>> Subject: [lng-odp] RSS in ODP
>>
>> Hello and happy new year,
>>
>> I
[mailto:lng-odp-boun...@lists.linaro.org] On Behalf Of
> Oriol
> >> Arcas
> >> Sent: Wednesday, January 03, 2018 7:12 PM
> >> To: LNG ODP Mailman List
> >> Subject: [lng-odp] RSS in ODP
> >>
> >> Hello and happy new year,
> >>
> >&g
t 10:24, Savolainen, Petri (Nokia - FI/Espoo)
> > wrote:
> > >
> > >
> > >> -Original Message-----
> > >> From: lng-odp [mailto:lng-odp-boun...@lists.linaro.org] On Behalf Of
> > Oriol
> > >> Arcas
> > >> Sent: Wedne
e direct mode (+ RSS), where each worker is polling
>> > from the its own pktin all the time (odp_pktin_recv()).
>> >
>> > On 4 January 2018 at 10:24, Savolainen, Petri (Nokia - FI/Espoo)
>> > wrote:
>> > >
>> > >
>> >
hed queues,
> >> > where each queue is assigned to a different sched group that is
> >> > assigned to a single thread/core.
> >> >
> >> > Other idea is to use direct mode (+ RSS), where each worker is polling
> >> > from the its own pktin
ch queue is assigned to a different sched group that is
>>> > assigned to a single thread/core.
>>> >
>>> > Other idea is to use direct mode (+ RSS), where each worker is polling
>>> > from the its own pktin all the time (odp_pktin_recv()).
>>> >
&g
queue is scheduled to a
>>>> > single thread but not on the same thread all the times - this may be
>>>> > enough for some implementations (to avoid some locks) but not enough
>>>> > for others.
>>>> >
>>>> > One problem is that al
> I'll dive into the details of queue scheduling and sticking to a CPU.
>>>>>
>>>>> Thank you all.
>>>>>
>>>>> --
>>>>> Oriol Arcas
>>>>> Software Engineer
>>>>> Starflow Networks
>>
; wrote:
>>>>>
>>>>>> Bill, Petri, Bogdan,
>>>>>>
>>>>>> Thank you for your fast feedback. It's been incredibly instructive.
>>>>>> We were
>>>>>> looking for something like
12 matches
Mail list logo