DPDK patches and discussions
 help / color / mirror / Atom feed
From: Ivan Malov <Ivan.Malov@oktetlabs.ru>
To: Thomas Monjalon <thomas@monjalon.net>,
	Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Cc: dev@dpdk.org, Andy Moreton <amoreton@xilinx.com>,
	orika@nvidia.com, ferruh.yigit@intel.com, olivier.matz@6wind.com
Subject: Re: [dpdk-dev] [PATCH v3 0/5] A means to negotiate delivery of Rx meta data
Date: Fri, 1 Oct 2021 11:55:03 +0300
Message-ID: <daf72ff3-e0d1-89c8-a597-5d60fab5152e@oktetlabs.ru> (raw)
In-Reply-To: <5427719.I9DohtKF8S@thomas>

Hi Thomas,

On 01/10/2021 11:11, Thomas Monjalon wrote:
> 01/10/2021 08:47, Andrew Rybchenko:
>> On 9/30/21 10:30 PM, Ivan Malov wrote:
>>> Hi Thomas,
>>>
>>> On 30/09/2021 19:18, Thomas Monjalon wrote:
>>>> 23/09/2021 13:20, Ivan Malov:
>>>>> In 2019, commit [1] announced changes in DEV_RX_OFFLOAD namespace
>>>>> intending to add new flags, RSS_HASH and FLOW_MARK. Since then,
>>>>> only the former has been added. The problem hasn't been solved.
>>>>> Applications still assume that no efforts are needed to enable
>>>>> flow mark and similar meta data delivery.
>>>>>
>>>>> The team behind net/sfc driver has to take over the efforts since
>>>>> the problem has started impacting us. Riverhead, a cutting edge
>>>>> Xilinx smart NIC family, has two Rx prefix types. Rx meta data
>>>>> is available only from long Rx prefix. Switching between the
>>>>> prefix formats can't happen in started state. Hence, we run
>>>>> into the same problem which [1] was aiming to solve.
>>>>
>>>> Sorry I don't understand what is Rx prefix?
>>>
>>> A small chunk of per-packet metadata in Rx packet buffer preceding the
>>> actual packet data. In terms of mbuf, this could be something lying
>>> before m->data_off.
> 
> I've never seen the word "Rx prefix".
> In general we talk about mbuf headroom and mbuf metadata,
> the rest being the mbuf payload and mbuf tailroom.
> I guess you mean mbuf metadata in the space of the struct rte_mbuf?

In this paragraph I describe the two ways how the NIC itself can provide 
metadata buffers of different sizes. Hence the term "Rx prefix". As you 
understand, the NIC HW is unaware of DPDK, mbufs and whatever else SW 
concepts. To NIC, this is "Rx prefix", that is, a chunk of per-packet 
metadata *preceding* the actual packet data. It's responsibility of the 
PMD to treat this the right way, care about headroom, payload and 
tailroom. I describe the two Rx prefix formats in NIC terminology just 
to provide the gist of the problem.

> 
>>>>> Rx meta data (mark, flag, tunnel ID) delivery is not an offload
>>>>> on its own since the corresponding flows must be active to set
>>>>> the data in the first place. Hence, adding offload flags
>>>>> similar to RSS_HASH is not a good idea.
>>>>
>>>> What means "active" here?
>>>
>>> Active = inserted and functional. What this paragraph is trying to say
>>> is that when you enable, say, RSS_HASH, that implies both computation of
>>> the hash and the driver's ability to extract in from packets
>>> ("delivery"). But when it comes to MARK, it's just "delivery". No
>>> "offload" here: the NIC won't set any mark in packets unless you create
>>> a flow rule to make it do so. That's the gist of it.
> 
> OK
> Yes I agree RTE_FLOW_ACTION_TYPE_MARK doesn't need any offload flag.
> Same for RTE_FLOW_ACTION_TYPE_SET_META.
> 
>>>>> Patch [1/5] of this series adds a generic API to let applications
>>>>> negotiate delivery of Rx meta data during initialisation period.
> 
> What is a metadata?
> Do you mean RTE_FLOW_ITEM_TYPE_META and RTE_FLOW_ITEM_TYPE_MARK?
> Metadata word could cover any field in the mbuf struct so it is vague.

Metadata here is *any* additional information provided by the NIC for 
each received packet. For example, Rx flag, Rx mark, RSS hash, packet 
classification info, you name it. I'd like to stress out that the 
suggested API comes with flags each of which is crystal clear on what 
concrete kind of metadata it covers, eg. Rx mark.

> 
>>>>> This way, an application knows right from the start which parts
>>>>> of Rx meta data won't be delivered. Hence, no necessity to try
>>>>> inserting flows requesting such data and handle the failures.
>>>>
>>>> Sorry I don't understand the problem you want to solve.
>>>> And sorry for not noticing earlier.
>>>
>>> No worries. *Some* PMDs do not enable delivery of, say, Rx mark with the
>>> packets by default (for performance reasons). If the application tries
>>> to insert a flow with action MARK, the PMD may not be able to enable
>>> delivery of Rx mark without the need to re-start Rx sub-system. And
>>> that's fraught with traffic disruption and similar bad consequences. In
>>> order to address it, we need to let the application express its interest
>>> in receiving mark with packets as early as possible. This way, the PMD
>>> can enable Rx mark delivery in advance. And, as an additional benefit,
>>> the application can learn *from the very beginning* whether it will be
>>> possible to use the feature or not. If this API tells the application
>>> that no mark delivery will be enabled, then the application can just
>>> skip many unnecessary attempts to insert wittingly unsupported flows
>>> during runtime.
> 
> I'm puzzled, because we could have the same reasoning for any offload.

We're not discussing *offloads*. An offload is when NIC *computes 
something* and *delivers* it. We are discussing precisely *delivery*.

> I don't understand why we are focusing on mark only
We are not focusing on mark on purpose. It's just how our discussion 
goes. I chose mark (could've chosen flag or anything else) just to show 
you an example.

> I would prefer we find a generic solution using the rte_flow API. > Can we make rte_flow_validate() working before port start?
> If validating a fake rule doesn't make sense,
> why not having a new function accepting a single action as parameter?

A noble idea, but if we feed the entire flow rule to the driver for 
validation, then the driver must not look specifically for actions FLAG 
or MARK in it (to enable or disable metadata delivery). This way, the 
driver is obliged to also validate match criteria, attributes, etc. And, 
if something is unsupported (say, some specific item), the driver will 
have to reject the rule as a whole thus leaving the application to join 
the dots itself.

Say, you ask the driver to validate the following rule:
pattern blah-blah-1 / blah-blah-2 / end action flag / end
intending to check support for FLAG delivery. Suppose, the driver 
doesn't support pattern item "blah-blah-1". It will throw an error right 
after seeing this unsupported item and won't even go further to see the 
action FLAG. How can application know whether its request for FLAG was 
heard or not?

And I'd not bind delivery of metadata to flow API. Consider the 
following example. We have a DPDK application sitting at the *host* and 
we have a *guest* with its *own* DPDK instance. The guest DPDK has asked 
the NIC (by virtue of flow API) to mark all outgoing packets. This 
packets reach the *host* DPDK. Say, the host application just wants to 
see the marked packets from the guest. Its own, (the host's) use of flow 
API is a don't care here. The host doesn't want to mark packets itself, 
it wants to see packets marked by the guest.

> 
>> Thomas, if I'm not mistaken, net/mlx5 dv_xmeta_en driver option
>> is vendor-specific way to address the same problem.
> 
> Not exactly, it is configuring the capabilities:
>    +------+-----------+-----------+-------------+-------------+
>    | Mode | ``MARK``  | ``META``  | ``META`` Tx | FDB/Through |
>    +======+===========+===========+=============+=============+
>    | 0    | 24 bits   | 32 bits   | 32 bits     | no          |
>    +------+-----------+-----------+-------------+-------------+
>    | 1    | 24 bits   | vary 0-32 | 32 bits     | yes         |
>    +------+-----------+-----------+-------------+-------------+
>    | 2    | vary 0-24 | 32 bits   | 32 bits     | yes         |
>    +------+-----------+-----------+-------------+-------------+
> 
> 

-- 
Ivan M

  parent reply	other threads:[~2021-10-01  8:55 UTC|newest]

Thread overview: 97+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-02 14:23 [dpdk-dev] [PATCH 0/5] A means to negotiate support for Rx meta information Ivan Malov
2021-09-02 14:23 ` [dpdk-dev] [PATCH 1/5] ethdev: add API " Ivan Malov
2021-09-02 14:47   ` Jerin Jacob
2021-09-02 16:14   ` Kinsella, Ray
2021-09-03  9:34   ` Jerin Jacob
2021-09-02 14:23 ` [dpdk-dev] [PATCH 2/5] net/sfc: provide API to negotiate supported Rx meta features Ivan Malov
2021-09-02 14:23 ` [dpdk-dev] [PATCH 3/5] net/sfc: allow to use EF100 native datapath Rx mark in flows Ivan Malov
2021-09-02 14:23 ` [dpdk-dev] [PATCH 4/5] common/sfc_efx/base: add RxQ flag to use Rx prefix user flag Ivan Malov
2021-09-02 14:23 ` [dpdk-dev] [PATCH 5/5] net/sfc: allow to discern user flag on EF100 native datapath Ivan Malov
2021-09-03  0:15 ` [dpdk-dev] [PATCH v2 0/5] A means to negotiate support for Rx meta information Ivan Malov
2021-09-03  0:15   ` [dpdk-dev] [PATCH v2 1/5] ethdev: add API " Ivan Malov
2021-09-03  0:15   ` [dpdk-dev] [PATCH v2 2/5] net/sfc: provide API to negotiate supported Rx meta features Ivan Malov
2021-09-03  0:15   ` [dpdk-dev] [PATCH v2 3/5] net/sfc: allow to use EF100 native datapath Rx mark in flows Ivan Malov
2021-09-03  0:15   ` [dpdk-dev] [PATCH v2 4/5] common/sfc_efx/base: add RxQ flag to use Rx prefix user flag Ivan Malov
2021-09-03  0:15   ` [dpdk-dev] [PATCH v2 5/5] net/sfc: allow to discern user flag on EF100 native datapath Ivan Malov
2021-09-23 11:20 ` [dpdk-dev] [PATCH v3 0/5] A means to negotiate delivery of Rx meta data Ivan Malov
2021-09-23 11:20   ` [dpdk-dev] [PATCH v3 1/5] ethdev: add API " Ivan Malov
2021-09-30 14:59     ` Ori Kam
2021-09-30 15:07       ` Andrew Rybchenko
2021-09-30 19:07       ` Ivan Malov
2021-10-01  6:50         ` Andrew Rybchenko
2021-10-03  7:42           ` Ori Kam
2021-10-03  9:30             ` Ivan Malov
2021-10-03 11:01               ` Ori Kam
2021-10-03 17:30                 ` Ivan Malov
2021-10-03 21:04                   ` Ori Kam
2021-10-03 23:50                     ` Ivan Malov
2021-10-04  6:56                       ` Ori Kam
2021-10-04 11:39                         ` Ivan Malov
2021-10-04 13:53                           ` Andrew Rybchenko
2021-10-05  6:30                             ` Ori Kam
2021-10-05  7:27                               ` Andrew Rybchenko
2021-10-05  8:17                                 ` Ori Kam
2021-10-05  8:38                                   ` Andrew Rybchenko
2021-10-05  9:41                                     ` Ori Kam
2021-10-05 10:01                                       ` Andrew Rybchenko
2021-10-05 10:10                                         ` Ori Kam
2021-10-05 11:11                                           ` Andrew Rybchenko
2021-10-06  8:30                                             ` Thomas Monjalon
2021-10-06  8:38                                               ` Andrew Rybchenko
2021-10-06  9:14                                                 ` Ori Kam
2021-09-30 21:48     ` Ajit Khaparde
2021-09-30 22:00       ` Ivan Malov
2021-09-30 22:12         ` Ajit Khaparde
2021-09-30 22:22           ` Ivan Malov
2021-10-03  7:05             ` Ori Kam
2021-09-23 11:20   ` [dpdk-dev] [PATCH v3 2/5] net/sfc: support " Ivan Malov
2021-09-23 11:20   ` [dpdk-dev] [PATCH v3 3/5] net/sfc: support flow mark delivery on EF100 native datapath Ivan Malov
2021-09-23 11:20   ` [dpdk-dev] [PATCH v3 4/5] common/sfc_efx/base: add RxQ flag to use Rx prefix user flag Ivan Malov
2021-09-23 11:20   ` [dpdk-dev] [PATCH v3 5/5] net/sfc: report user flag on EF100 native datapath Ivan Malov
2021-09-30 16:18   ` [dpdk-dev] [PATCH v3 0/5] A means to negotiate delivery of Rx meta data Thomas Monjalon
2021-09-30 19:30     ` Ivan Malov
2021-10-01  6:47       ` Andrew Rybchenko
2021-10-01  8:11         ` Thomas Monjalon
2021-10-01  8:54           ` Andrew Rybchenko
2021-10-01  9:32             ` Thomas Monjalon
2021-10-01  9:41               ` Andrew Rybchenko
2021-10-01  8:55           ` Ivan Malov [this message]
2021-10-01  9:48             ` Thomas Monjalon
2021-10-01 10:15               ` Andrew Rybchenko
2021-10-01 12:10                 ` Thomas Monjalon
2021-10-04  9:17                   ` Andrew Rybchenko
2021-10-04 23:50   ` [dpdk-dev] [PATCH v4 0/5] Negotiate the NIC's ability to deliver Rx metadata to the PMD Ivan Malov
2021-10-04 23:50     ` [dpdk-dev] [PATCH v4 1/5] ethdev: negotiate delivery of packet metadata from HW to PMD Ivan Malov
2021-10-05 12:03       ` Ori Kam
2021-10-05 12:50         ` Ivan Malov
2021-10-05 13:17           ` Andrew Rybchenko
2021-10-04 23:50     ` [dpdk-dev] [PATCH v4 2/5] net/sfc: support API to negotiate delivery of Rx metadata Ivan Malov
2021-10-04 23:50     ` [dpdk-dev] [PATCH v4 3/5] net/sfc: support flow mark delivery on EF100 native datapath Ivan Malov
2021-10-04 23:50     ` [dpdk-dev] [PATCH v4 4/5] common/sfc_efx/base: add RxQ flag to use Rx prefix user flag Ivan Malov
2021-10-04 23:50     ` [dpdk-dev] [PATCH v4 5/5] net/sfc: report user flag on EF100 native datapath Ivan Malov
2021-10-05 15:56   ` [dpdk-dev] [PATCH v5 0/5] ethdev: negotiate the NIC's ability to deliver Rx metadata to the PMD Ivan Malov
2021-10-05 15:56     ` [dpdk-dev] [PATCH v5 1/5] ethdev: negotiate delivery of packet metadata from HW to PMD Ivan Malov
2021-10-05 21:40       ` Ajit Khaparde
2021-10-06  6:04         ` Somnath Kotur
2021-10-06  6:10           ` Ori Kam
2021-10-06  7:22             ` Wisam Monther
2021-10-05 15:56     ` [dpdk-dev] [PATCH v5 2/5] net/sfc: support API to negotiate delivery of Rx metadata Ivan Malov
2021-10-05 15:56     ` [dpdk-dev] [PATCH v5 3/5] net/sfc: support flow mark delivery on EF100 native datapath Ivan Malov
2021-10-05 15:56     ` [dpdk-dev] [PATCH v5 4/5] common/sfc_efx/base: add RxQ flag to use Rx prefix user flag Ivan Malov
2021-10-05 15:56     ` [dpdk-dev] [PATCH v5 5/5] net/sfc: report user flag on EF100 native datapath Ivan Malov
2021-10-12 18:08       ` Ferruh Yigit
2021-10-12 19:39         ` Ivan Malov
2021-10-12 19:48         ` Ivan Malov
2021-10-12 19:38   ` [dpdk-dev] [PATCH v6 0/5] ethdev: negotiate the NIC's ability to deliver Rx metadata to the PMD Ivan Malov
2021-10-12 19:38     ` [dpdk-dev] [PATCH v6 1/5] ethdev: negotiate delivery of packet metadata from HW to PMD Ivan Malov
2021-10-12 19:38     ` [dpdk-dev] [PATCH v6 2/5] net/sfc: support API to negotiate delivery of Rx metadata Ivan Malov
2021-10-12 19:38     ` [dpdk-dev] [PATCH v6 3/5] net/sfc: support flow mark delivery on EF100 native datapath Ivan Malov
2021-10-12 19:38     ` [dpdk-dev] [PATCH v6 4/5] common/sfc_efx/base: add RxQ flag to use Rx prefix user flag Ivan Malov
2021-10-12 19:38     ` [dpdk-dev] [PATCH v6 5/5] net/sfc: report user flag on EF100 native datapath Ivan Malov
2021-10-12 19:46   ` [dpdk-dev] [PATCH v7 0/5] ethdev: negotiate the NIC's ability to deliver Rx metadata to the PMD Ivan Malov
2021-10-12 19:46     ` [dpdk-dev] [PATCH v7 1/5] ethdev: negotiate delivery of packet metadata from HW to PMD Ivan Malov
2021-10-12 19:46     ` [dpdk-dev] [PATCH v7 2/5] net/sfc: support API to negotiate delivery of Rx metadata Ivan Malov
2021-10-12 19:46     ` [dpdk-dev] [PATCH v7 3/5] net/sfc: support flow mark delivery on EF100 native datapath Ivan Malov
2021-10-12 19:46     ` [dpdk-dev] [PATCH v7 4/5] common/sfc_efx/base: add RxQ flag to use Rx prefix user flag Ivan Malov
2021-10-12 19:46     ` [dpdk-dev] [PATCH v7 5/5] net/sfc: report user flag on EF100 native datapath Ivan Malov
2021-10-12 23:25     ` [dpdk-dev] [PATCH v7 0/5] ethdev: negotiate the NIC's ability to deliver Rx metadata to the PMD Ferruh Yigit

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=daf72ff3-e0d1-89c8-a597-5d60fab5152e@oktetlabs.ru \
    --to=ivan.malov@oktetlabs.ru \
    --cc=amoreton@xilinx.com \
    --cc=andrew.rybchenko@oktetlabs.ru \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@intel.com \
    --cc=olivier.matz@6wind.com \
    --cc=orika@nvidia.com \
    --cc=thomas@monjalon.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

DPDK patches and discussions

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://inbox.dpdk.org/dev/0 dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dev dev/ https://inbox.dpdk.org/dev \
		dev@dpdk.org
	public-inbox-index dev

Example config snippet for mirrors.
Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.dev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git