> -----Original Message-----
> From: dev <dev-boun...@dpdk.org> On Behalf Of Thomas Monjalon
> Sent: Thursday, October 31, 2019 10:50 PM
> To: Andrew Rybchenko <arybche...@solarflare.com>
> Cc: dev@dpdk.org; Ori Kam <or...@mellanox.com>;
> pbhagavat...@marvell.com; Yigit, Ferruh <ferruh.yi...@intel.com>;
> jer...@marvell.com; Mcnamara, John <john.mcnam...@intel.com>; Kovacevic,
> Marko <marko.kovace...@intel.com>; Adrien Mazarguil
> <adrien.mazarg...@6wind.com>; david.march...@redhat.com;
> ktray...@redhat.com
> Subject: Re: [dpdk-dev] [PATCH 1/2] ethdev: add flow action type update as an
> offload
>
> 31/10/2019 10:49, Andrew Rybchenko:
> > On 10/28/19 5:00 PM, Ori Kam wrote:
> > >> -----Original Message-----
> > > From: Andrew Rybchenko <arybche...@solarflare.com>
> > >> On 10/28/19 1:50 PM, Ori Kam wrote:
> > >>> Hi Pavan,
> > >>>
> > >>> Sorry for jumping in late.
> > >>>
> > >>> I don't understand why we need this feature. If the user didn't
> > >>> set any flow
> > >> with MARK
> > >>> then the user doesn't need to check it.
> > >> There is pretty long discussion on the topic already, please, read [1].
> > >>
> > >> [1]
> > >> https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fin
> > >> box.dpdk
> > >> .org%2Fdev%2F3251fc00-7598-1c4f-fc2a-
> > >>
> 380065f0a435%40solarflare.com%2F&data=02%7C01%7Corika%40mella
> n
> > >>
> ox.com%7Ce3f779d4b7c44b682d6508d75b9d8688%7Ca652971c7d2e4d9ba6a
> 4
> > >>
> d149256f461b%7C0%7C0%7C637078604439019114&sdata=sYooc%2FQ3
> C
> > >> kUZG3gRFPlZrm8xMfMB9gOWWex5YIkWhMc%3D&reserved=0
> > >>
> > > Thanks for the link, it was an interesting reading.
> > >
> > >>> Also it breaks compatibility.
> > >> Yes, there is a deprecation notice for it.
> > >>
> > >>> If my understanding is correct the MARK field is going to be moved
> > >>> to
> > >> dynamic field, and this
> > >>> will be way to control the use of MARK.
> > >> Yes and I think the offload should used to request dynamic field
> > >> register. Similar to timestamp in dynamic mbuf examples.
> > >> Application requests Rx timestamp offload, PMD registers dynamic
> > >> filed.
> > >>
> > > In general it was decided that there will be no capability for
> > > rte_flow API, due to the fact that it is impossible to support all
> > > possible combinations. For example a PMD can allow mark on Rx while not
> supporting it on e-switch (transfer) or on Tx.
> > > The only way to validate it is validating a flow. If the flow is
> > > validated then
> the action is supported.
> > > This is the exact approach we are implementing with the Meta feature.
> > > So as I see it, the logic should be something like this:
> > > 1. run devconfigure.
> > > 2. allocate mempool
> > > 3. setup queues.
> > > 4. run rte_flow_validate with mark action.
> > > If flow validated register mark in mbuf else don't register.
> > > If the PMD needs some special setting for mark he can update the queue
> when he gets the flow to validate.
> > > At this stage the device is not started so any change is allowed.
> >
> > I understand why there is capability reporting in rte_flow API when it
> > is about rte_flow API itself. The problem appears when rte_flow API
> > starts to interact with other functionality.
> > Which pattern/actions should application try in order to decide if
> > MARK is supported or not.
>
> Why application should decide whether MARK is supported or not?
> In my understanding it can be enabled dynamically per flow.
Sorry to break in the discussion, I think the mark offload will give below
benefits base on some real cases.
1. for PMD which not enable mark offload on all data paths, for example, the
vector PMD does not support mark, but non vector PMD does,
In this case, the offload can give driver a hint to choose the correct data
path, otherwise, when vPMD is selected at dev_start, a flow with mark action
has to be rejected.
2. extract the 32 bit mark from rx descriptor have considerable performance
cost, especially on vPMD.
so it will be nice if the driver knows that mark offload is not necessary for
application, then it can always select a faster path.
while, driver can track when the first flow with mark are issued and the last
flow with mark is delete than branch the code for mark extraction properly, but
this just give driver another option to simply this
Regards
Qi
>
> > The right answer is a pattern/action
> > which will be really used, but what to do if there are many
> > combinations or if these combinations are not know in advance.
> > Minimal? But I easily imagine cases when minimal is not supported, but
> > more complex real life patterns are supported.
> >
> > The main idea behind the offload is as much as you know in advance as
> > much you can optimize without overcomplicating drivers and HW.
> >
> > In the case of OVS, absence MARK offload would mean that OVS should
> > not even try to use partial offload even if it is enabled.
> > So, no efforts are required to try to convert flow into pattern and
> > validate the flow rule.
>
> That's an interesting feedback.
> I would like to understand why OVS cannot adapt its datapath on demand per
> port, per queue and per flow?
>