From: "Doherty, Declan" <declan.doherty@intel.com>
To: Thomas Monjalon <thomas@monjalon.net>,
Remy Horton <remy.horton@intel.com>,
Mohammad Abdul Awal <mohammad.abdul.awal@intel.com>
Cc: dev@dpdk.org, John McNamara <john.mcnamara@intel.com>,
Wenzhuo Lu <wenzhuo.lu@intel.com>,
Jingjing Wu <jingjing.wu@intel.com>,
Alejandro Lucero <alejandro.lucero@netronome.com>,
vincent.jardin@6wind.com
Subject: Re: [dpdk-dev] [PATCH v4 0/5] lib: add Port Representors
Date: Wed, 10 Jan 2018 13:46:58 +0000 [thread overview]
Message-ID: <e04bd0e1-dfd1-7cde-05c3-04629b33ec80@intel.com> (raw)
In-Reply-To: <2463277.U5nOFtZCo4@xps>
On 09/01/2018 11:22 PM, Thomas Monjalon wrote:
> Hi,
>
> 08/01/2018 15:37, Remy Horton:
>> Port Representors provide a logical presentation in DPDK of VF (virtual
>> function) ports for the purposes of control and monitoring. Each port
>> representor device represents a single VF and is associated with it's
>> parent physical function (PF) PMD which provides the back-end hooks for
>> the representor device ops and defines the control domain to which that
>> port belongs. This allows to use existing DPDK APIs to monitor and control
>> the port without the need to create and maintain VF specific APIs.
>
> Extending control plane ability of DPDK has been discussed
> multiple times.
It has, and I have yet to see a really strong reason as to why we would
not support control plane functions within DPDK, many of which are
already support today implicitly anyway through our ethdev APIs.
> The current agreed policy is:
> "
> The primary goal of DPDK is to provide a userspace dataplane.
> Managing VFs from a PF driver is a control plane feature and developers
> should generally rely on the Linux Kernel for that.
> "
> http://dpdk.org/doc/guides/contributing/design.html#pf-and-vf-considerations
>
My understanding is that this particular entry was based around the
discussion on the divergence of functionality between the Linux kernel
PF driver and the DPDK PF driver. I also don't really think the above
statement is valid as a blanket statement for the project as it makes
the assumption that DPDK is only deployed on Linux hosts, what about
FreeBSD? or in the future Windows?
A number of presentations at both Userspace in Dublin and the Summit
in San Jose discussed the support of control plane functionality by
DPDK and there wasn't any strong arguments or opposition against using
DPDK for control plane functions that I saw.
In any case this patchset is not introducing any new control plane APIs
that don't already exist within DPDK today, it only enables the creation
of a new type of virtual PMDs which are linked to the same base
infrastructure and which can be used to represent VFs in a control plane
application as we have implemented in this patch set.
> If we relax this policy, I think the representor solution should be
> a real port, not only "for the purposes of control and monitoring".
> It has been asked several times as replies to this series,
> but it is kindly ignored, saying it will be thought later.
>
I think we have stated in multiple discussions, especially during the
userspace presentation back in September that this solution supports
data path on the representors PMDs, and we have used the
infrastructure proposed here to do exactly what you are asking. As the
representor infrastructure doesn't preclude the support of a data
path, we have used it as it is presented here to implement a data path
for exception path packets for a prototype vswitch offload implementation.
> I don't see a general agreement on this series so far.
>
I think the main issue of contention is that there is a
misunderstanding that this implementation only supports control plane
management and monitoring, but that is not the case and it can be used
for full data path representors, with limited or no control plane
functionality if required, at the end of the day the only limitations
are based on what is implemented by the backend base driver were the
broker is running for the representor ports.
next prev parent reply other threads:[~2018-01-10 13:47 UTC|newest]
Thread overview: 75+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-11-17 14:42 [dpdk-dev] [PATCH v2 1/6] ethdev: added switch_domain and representor port flag Mohammad Abdul Awal
2017-11-17 14:42 ` [dpdk-dev] [PATCH v2 2/6] lib/representor: port representor library to manage broker infrastructure and representor PMDs Mohammad Abdul Awal
2017-11-17 23:03 ` Ferruh Yigit
2017-12-08 14:57 ` Mohammad Abdul Awal
2017-11-17 14:42 ` [dpdk-dev] [PATCH v2 3/6] eal: added --enable-representor command line argument in EAL to load representor broker infrastructure Mohammad Abdul Awal
2017-11-17 14:42 ` [dpdk-dev] [PATCH v2 4/6] net/representor: Implement port representor PMD Mohammad Abdul Awal
2017-11-20 7:46 ` Ferruh Yigit
2017-12-08 15:02 ` Remy Horton
2017-12-08 16:56 ` Mohammad Abdul Awal
2017-12-11 10:08 ` Remy Horton
2017-12-11 15:11 ` Mohammad Abdul Awal
2017-12-11 15:29 ` Remy Horton
2017-11-17 14:42 ` [dpdk-dev] [PATCH v2 5/6] net/i40e: Enable port representor PMD and broker for fortville PMD driver Mohammad Abdul Awal
2017-11-20 7:48 ` Ferruh Yigit
2017-11-17 14:42 ` [dpdk-dev] [PATCH v2 6/6] net/ixgbe: Enable port representor PMD and broker for ixgbe " Mohammad Abdul Awal
2017-11-20 19:57 ` [dpdk-dev] [PATCH v2 1/6] ethdev: added switch_domain and representor port flag Ferruh Yigit
2017-12-08 15:33 ` Mohammad Abdul Awal
2017-12-11 13:45 ` Alex Rosenbaum
2017-12-11 18:00 ` Mohammad Abdul Awal
2017-12-22 14:41 ` [dpdk-dev] [DPDK 0/5] lib: add Port Representors Remy Horton
2017-12-22 14:41 ` [dpdk-dev] [DPDK 1/5] lib: add Port Representor library Remy Horton
2017-12-22 14:41 ` [dpdk-dev] [DPDK 2/5] eal: add Port Representor command-line option Remy Horton
2017-12-22 14:41 ` [dpdk-dev] [DPDK 3/5] drivers/net/i40e: add Port Representor functionality Remy Horton
2017-12-22 14:41 ` [dpdk-dev] [DPDK 4/5] drivers/net/ixgbe: " Remy Horton
2017-12-22 14:41 ` [dpdk-dev] [DPDK 5/5] app/test-pmd: add Port Representor commands Remy Horton
2017-12-22 15:09 ` [dpdk-dev] [DPDK 0/5] lib: add Port Representors Remy Horton
2017-12-22 16:37 ` Neil Horman
2018-01-03 12:14 ` Mohammad Abdul Awal
2017-12-22 14:52 ` [dpdk-dev] [PATCH v3 " Remy Horton
2017-12-22 14:52 ` [dpdk-dev] [PATCH v3 1/5] lib: add Port Representor library Remy Horton
2017-12-22 14:52 ` [dpdk-dev] [PATCH v3 2/5] eal: add Port Representor command-line option Remy Horton
2017-12-22 14:52 ` [dpdk-dev] [PATCH v3 3/5] drivers/net/i40e: add Port Representor functionality Remy Horton
2017-12-22 14:52 ` [dpdk-dev] [PATCH v3 4/5] drivers/net/ixgbe: " Remy Horton
2017-12-22 14:52 ` [dpdk-dev] [PATCH v3 5/5] app/test-pmd: add Port Representor commands Remy Horton
2017-12-26 13:54 ` [dpdk-dev] [PATCH v3 0/5] lib: add Port Representors Neil Horman
2018-01-03 12:12 ` Mohammad Abdul Awal
2018-01-08 14:37 ` [dpdk-dev] [PATCH v4 " Remy Horton
2018-01-08 14:37 ` [dpdk-dev] [PATCH v4 1/5] lib: add Port Representor library Remy Horton
2018-01-09 22:06 ` Ferruh Yigit
2018-01-10 11:40 ` Remy Horton
2018-01-08 14:37 ` [dpdk-dev] [PATCH v4 2/5] eal: add Port Representor command-line option Remy Horton
2018-01-09 22:07 ` Ferruh Yigit
2018-01-08 14:37 ` [dpdk-dev] [PATCH v4 3/5] drivers/net/i40e: add Port Representor functionality Remy Horton
2018-01-09 22:09 ` Ferruh Yigit
2018-01-10 7:56 ` Xing, Beilei
2018-01-10 10:11 ` Mohammad Abdul Awal
2018-01-10 12:37 ` Xing, Beilei
2018-01-10 14:04 ` Mohammad Abdul Awal
2018-01-08 14:37 ` [dpdk-dev] [PATCH v4 4/5] drivers/net/ixgbe: " Remy Horton
2018-01-08 14:37 ` [dpdk-dev] [PATCH v4 5/5] app/test-pmd: add Port Representor commands Remy Horton
2018-01-09 22:10 ` Ferruh Yigit
2018-01-10 7:22 ` Remy Horton
2018-01-09 22:01 ` [dpdk-dev] [PATCH v4 0/5] lib: add Port Representors Ferruh Yigit
2018-01-10 14:17 ` Mohammad Abdul Awal
2018-01-09 23:22 ` Thomas Monjalon
2018-01-10 13:46 ` Doherty, Declan [this message]
2018-01-10 19:26 ` Thomas Monjalon
2018-01-15 12:12 ` Doherty, Declan
2018-01-15 16:09 ` Thomas Monjalon
2018-01-10 15:54 ` [dpdk-dev] [PATCH v5 " Remy Horton
2018-01-10 15:54 ` [dpdk-dev] [PATCH v5 1/5] lib: add Port Representor library Remy Horton
2018-01-30 9:23 ` Andrew Rybchenko
2018-01-10 15:54 ` [dpdk-dev] [PATCH v5 2/5] eal: add Port Representor command-line option Remy Horton
2018-01-10 15:54 ` [dpdk-dev] [PATCH v5 3/5] drivers/net/i40e: add Port Representor functionality Remy Horton
2018-01-10 15:54 ` [dpdk-dev] [PATCH v5 4/5] drivers/net/ixgbe: " Remy Horton
2018-01-10 15:54 ` [dpdk-dev] [PATCH v5 5/5] app/test-pmd: add Port Representor commands Remy Horton
2018-01-10 17:49 ` [dpdk-dev] [PATCH v5 0/5] lib: add Port Representors Remy Horton
2018-01-10 17:49 ` [dpdk-dev] [PATCH v5 1/5] lib: add Port Representor library Remy Horton
2018-01-10 17:49 ` [dpdk-dev] [PATCH v5 2/5] eal: add Port Representor command-line option Remy Horton
2018-01-10 17:49 ` [dpdk-dev] [PATCH v5 3/5] drivers/net/i40e: add Port Representor functionality Remy Horton
2018-01-10 17:49 ` [dpdk-dev] [PATCH v5 4/5] drivers/net/ixgbe: " Remy Horton
2018-01-10 17:49 ` [dpdk-dev] [PATCH v5 5/5] app/test-pmd: add Port Representor commands Remy Horton
2018-01-11 3:18 ` [dpdk-dev] [PATCH v4 0/5] lib: add Port Representors Yuanhan Liu
2018-01-11 8:37 ` Alex Rosenbaum
2018-01-11 9:38 ` Remy Horton
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=e04bd0e1-dfd1-7cde-05c3-04629b33ec80@intel.com \
--to=declan.doherty@intel.com \
--cc=alejandro.lucero@netronome.com \
--cc=dev@dpdk.org \
--cc=jingjing.wu@intel.com \
--cc=john.mcnamara@intel.com \
--cc=mohammad.abdul.awal@intel.com \
--cc=remy.horton@intel.com \
--cc=thomas@monjalon.net \
--cc=vincent.jardin@6wind.com \
--cc=wenzhuo.lu@intel.com \
/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).