DPDK patches and discussions
 help / color / mirror / Atom feed
From: Ori Kam <orika@nvidia.com>
To: "Dumitrescu, Cristian" <cristian.dumitrescu@intel.com>,
	"dev@dpdk.org" <dev@dpdk.org>,
	"NBU-Contact-Thomas Monjalon (EXTERNAL)" <thomas@monjalon.net>,
	Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>,
	Ray Kinsella <mdr@ashroe.eu>
Cc: Jerin Jacob <jerinjacobk@gmail.com>,
	Jerin Jacob <jerinj@marvell.com>,
	"skori@marvell.com" <skori@marvell.com>,
	"Vipin.Varghese@amd.com" <Vipin.Varghese@amd.com>,
	Alexander Kozyrev <akozyrev@nvidia.com>
Subject: RE: [PATCH v3 1/1] ethdev: mtr: support input color selection
Date: Tue, 12 Apr 2022 06:48:45 +0000	[thread overview]
Message-ID: <MW2PR12MB4666E7BF1C416608DF4E8FAAD6ED9@MW2PR12MB4666.namprd12.prod.outlook.com> (raw)
In-Reply-To: <DM8PR11MB5670ECDB54D90A374384ED29EBEA9@DM8PR11MB5670.namprd11.prod.outlook.com>

Adding some missing guys, that I know about.

Ori



> -----Original Message-----
> From: Dumitrescu, Cristian <cristian.dumitrescu@intel.com>
> Sent: Monday, April 11, 2022 5:46 PM
> To: dev@dpdk.org; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>; Andrew
> Rybchenko <andrew.rybchenko@oktetlabs.ru>; Ray Kinsella <mdr@ashroe.eu>
> Cc: Jerin Jacob <jerinjacobk@gmail.com>; Jerin Jacob <jerinj@marvell.com>; skori@marvell.com; Ori
> Kam <orika@nvidia.com>
> Subject: RE: [PATCH v3 1/1] ethdev: mtr: support input color selection
> 
> Hi folks,
> 
> Thanks to the community colleagues that participated to the call earlier today. Apologies for not CC-ing
> all the 9 attendants, as I don't have the email address for all of them.
> 
> We had a good meeting, I think we agreed on a good solution that will also simplify the API proposal.
> 
> Recap on the problem statement:
> 1. How do we decide on the input color for the current packet in a deterministic (implementation
> independent) way?
> 2. Multiple choices possible for a given packet: The same packet might contain multiple headers that
> can provide the input color. Examples: VLAN (the PCP and DEI fields), IP (DSCP field), others. Some
> headers of same type may show up in the same packet (e.g. outer/inner header).
> 3. Some of the possible choices might not be available for a given packet: Different packets may
> contain different headers.
> 
> Proposed solution:
> 1. Configure which protocols to enable. Example: we might want to consider Outer VLAN and Outer IP,
> but disable Inner VLAN and inner IP.
> 2. Configure on the priority of each of the enabled protocols (0 = highest priority). Example: If the
> current packet has an Outer VLAN header, but not an Outer IP header, then we get the input color
> from the Outer VLAN header; same, if there is an Outer IP header, but no Outer VLAN header, we get
> the priority from the Outer IP header. But what if the packet has both an Outer VLAN and an Outer IP
> header? In this case we need to consider the priority and pick the input color from the highest priority
> header.
> 3. Configure the default input color. What happens if the packet does not have an Outer VLAN header,
> nor an Outer IP header? Then the default input color is picked.
> 
> API guideline:
> enum rte_mtr_color_in_protocol {
> 	RTE_MTR_COLOR_IN_OUTER_VLAN,
> 	RTE_MTR_COLOR_IN_INNER_VLAN,
> 	RTE_MTR_COLOR_IN_OUTER_IP,
> 	RTE_MTR_COLOR_IN_INNER_IP,
> 	//more to add as needed. Per Ori's comment, we can add a reunion of the two protocols as
> well when needed, e.g. RTE_MTR_COLOR_IN_OUTER_VLAN_OUTER_IP that has a (4+6)-bit index
> (PCI, DEI, DSCP).
> }
> 
> int
> rte_mtr_color_in_protocol_priority_set(enum rte_mtr_color_in_protocol proto, uint32_t priority);
> //0 is highest priority
> 
> Regards,
> Cristian

  reply	other threads:[~2022-04-12  6:48 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-20  8:24 [dpdk-dev] [RFC PATCH] ethdev: mtr: enhance input color table features jerinj
2021-08-30  9:23 ` Jerin Jacob
2021-09-27 16:20   ` Ferruh Yigit
2021-10-11 15:14 ` Dumitrescu, Cristian
2021-11-17 12:00   ` Jerin Jacob
2021-12-07  9:55     ` Jerin Jacob
2021-12-07 18:00       ` Dumitrescu, Cristian
2022-01-10  9:35         ` Jerin Jacob
2022-02-14 11:56 ` [dpdk-dev] [v22.07] [PATCH] ethdev: mtr: support input color selection jerinj
2022-02-14 12:02   ` [dpdk-dev] [v22.07] [PATCH v2] " jerinj
2022-03-01  8:58     ` [PATCH v3 1/1] " skori
2022-03-01 10:49       ` [EXT] " Sunil Kumar Kori
2022-03-01 17:48       ` Dumitrescu, Cristian
2022-04-05 21:14         ` Dumitrescu, Cristian
2022-04-07 10:51         ` Jerin Jacob
2022-04-07 13:25           ` Dumitrescu, Cristian
2022-04-07 14:39             ` Jerin Jacob
2022-04-11 14:45               ` Dumitrescu, Cristian
2022-04-12  6:48                 ` Ori Kam [this message]
2022-04-21 18:02       ` [dpdk-dev] [PATCH v4] ethdev: mtr: support protocol based " jerinj
2022-04-26 10:19         ` Ray Kinsella
2022-05-01 12:52           ` Jerin Jacob
2022-04-26 12:08         ` Dumitrescu, Cristian
2022-05-01 12:56           ` Jerin Jacob
2022-05-01 14:46         ` [dpdk-dev] [PATCH v5] " jerinj
2022-05-04  8:52           ` Ray Kinsella
2022-05-05 10:56           ` Dumitrescu, Cristian
2022-05-12  7:36           ` Andrew Rybchenko
2022-05-12 11:03             ` Jerin Jacob
2022-05-19  7:05               ` Andrew Rybchenko

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=MW2PR12MB4666E7BF1C416608DF4E8FAAD6ED9@MW2PR12MB4666.namprd12.prod.outlook.com \
    --to=orika@nvidia.com \
    --cc=Vipin.Varghese@amd.com \
    --cc=akozyrev@nvidia.com \
    --cc=andrew.rybchenko@oktetlabs.ru \
    --cc=cristian.dumitrescu@intel.com \
    --cc=dev@dpdk.org \
    --cc=jerinj@marvell.com \
    --cc=jerinjacobk@gmail.com \
    --cc=mdr@ashroe.eu \
    --cc=skori@marvell.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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).