From: Slava Ovsiienko <viacheslavo@nvidia.com>
To: "NBU-Contact-Thomas Monjalon (EXTERNAL)" <thomas@monjalon.net>,
Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>,
Hanumanth Reddy Pothula <hpothula@marvell.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
Aman Singh <aman.deep.singh@intel.com>,
Yuying Zhang <yuying.zhang@intel.com>,
"dev@dpdk.org" <dev@dpdk.org>,
Jerin Jacob Kollanukkaran <jerinj@marvell.com>,
Nithin Kumar Dabilpuram <ndabilpuram@marvell.com>,
Raslan Darawsheh <rasland@nvidia.com>, Ori Kam <orika@nvidia.com>
Subject: RE: [EXT] Re: [PATCH v3 1/1] app/testpmd: control passing Rx metadata to PMD
Date: Mon, 5 Dec 2022 09:43:30 +0000 [thread overview]
Message-ID: <DM6PR12MB375364FDCE6DE04E56956301DF189@DM6PR12MB3753.namprd12.prod.outlook.com> (raw)
In-Reply-To: <111350205.nniJfEyVGO@thomas>
> -----Original Message-----
> From: Thomas Monjalon <thomas@monjalon.net>
> Sent: Monday, December 5, 2022 10:29
> To: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>; Hanumanth Reddy
> Pothula <hpothula@marvell.com>
> Cc: dev@dpdk.org; Aman Singh <aman.deep.singh@intel.com>; Yuying Zhang
> <yuying.zhang@intel.com>; dev@dpdk.org; Jerin Jacob Kollanukkaran
> <jerinj@marvell.com>; Nithin Kumar Dabilpuram <ndabilpuram@marvell.com>;
> Raslan Darawsheh <rasland@nvidia.com>; Ori Kam <orika@nvidia.com>; Slava
> Ovsiienko <viacheslavo@nvidia.com>
> Subject: Re: [EXT] Re: [PATCH v3 1/1] app/testpmd: control passing Rx
> metadata to PMD
>
> 05/12/2022 08:59, Hanumanth Reddy Pothula:
> > From: Thomas Monjalon <thomas@monjalon.net>
> > > 02/12/2022 17:14, Hanumanth Reddy Pothula:
> > > > -----Original Message-----
> > > > > 27/10/2022 09:34, Thomas Monjalon:
> > > > > > 17/10/2022 10:32, Andrew Rybchenko:
> > > > > > > On 10/6/22 21:35, Hanumanth Pothula wrote:
> > > > > > > > Presently, Rx metadata is sent to PMD by default, leading
> > > > > > > > to a performance drop as processing for the same in rx
> > > > > > > > path takes extra cycles.
> > > > > > > >
> > > > > > > > Hence, introducing command line argument, 'nic-to-pmd-rx-
> > > metadata'
> > > > > > > > to control passing rx metadata to PMD. By default it’s
> disabled.
> > > > > > > >
> > > > > > > > Signed-off-by: Hanumanth Pothula <hpothula@marvell.com>
> > > > > > >
> > > > > > > Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
> > > > > > >
> > > > > > > Applied to dpdk-next-net/main, thanks.
> > > > > >
> > > > > > I'm not sure this patch is really acceptable.
> > > > > > It is disabling Rx metadata by default just for benchmarking
> > > > > > reason because your driver is doing some processing even if
> > > > > > metadata is not
> > > > > required.
> > > > > >
> > > > > > From a user perspective, if a command requesting metadata is
> > > > > > entered, it won't work until we enable this new option on startup.
> > > > > > It looks terrible.
> > > > > >
> > > > > > Please tell me I misunderstood something.
> > > > >
> > > > > While pulling, I see that the name is not compliant with others.
> > > > > I think it should start with "enable-", use hyphens and be sorted.
> > > > >
> > > > > I'll drop it from the pull for now, we can have it in -rc3.
> > > > >
> > > >
> > > > @Thomas Monjalon I missed your comment, sorry for the delayed
> > > response.
> > > >
> > > > Sending Rx metadata to PMD is added recently, which breaking our
> > > > driver
> > > performance.
> > > > Normally any feature added to testpmd will be disabled by default,
> > > > to
> > > make sure it won't affect other code(PMD).
> > > > Hence adding new testpmd command line argument to disable this
> > > feature by default.
> > >
> > > No, disabling by default doesn't mean you should enable with option.
> > > It should be enabled if required by a command.
> > >
> > Yeah, got it, user can enable/disable the feature on the fly without
> restarting the application(testpmd).
> > Will introduce new command, like below,
> > 'port config rx-nic-to-pmd-metadata on/off'
> >
> > Please let me know your thoughts on this command implementation.
> > If it's fine, will start implementing the command. Suggest if there is any
> other better way to implement the same.
>
> What about enabling automatically when a flow command requests metadata?
>
Another option - enable on defining metadata dynamic field/flag in mbuf.
mlx5 PMD, for example follows this approach.
Do we need disabling this in real application? If application is designed to use
metadata it is unlikely it stops using these ones.
With best regards,
Slava
next prev parent reply other threads:[~2022-12-05 9:43 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-01 4:41 [PATCH] app/testpmd: add command line argument 'rx-metadata' Hanumanth Pothula
2022-08-01 13:11 ` Hanumanth Pothula
2022-08-01 13:13 ` Hanumanth Pothula
2022-08-01 19:41 ` Ivan Malov
2022-08-02 16:45 ` [PATCH] app/testpmd: add command line argument 'nic-to-pmd-rx-metadata' Hanumanth Pothula
2022-08-02 16:45 ` [PATCH v2 1/2] version: 22.11-rc0 Hanumanth Pothula
2022-08-02 16:45 ` [PATCH v2 2/2] app/testpmd: add command line argument 'nic-to-pmd-rx-metadata' Hanumanth Pothula
2022-08-02 17:51 ` [PATCH v2 1/1] " Hanumanth Pothula
2022-08-30 12:36 ` Hanumanth Reddy Pothula
2022-09-01 8:03 ` Singh, Aman Deep
2022-10-04 14:48 ` Andrew Rybchenko
2022-10-06 18:35 ` [PATCH v3 1/1] app/testpmd: control passing Rx metadata to PMD Hanumanth Pothula
2022-10-17 8:32 ` Andrew Rybchenko
2022-10-27 7:34 ` Thomas Monjalon
2022-10-27 12:54 ` Thomas Monjalon
2022-12-02 16:14 ` [EXT] " Hanumanth Reddy Pothula
2022-12-02 19:41 ` Thomas Monjalon
2022-12-05 7:59 ` Hanumanth Reddy Pothula
2022-12-05 8:28 ` Thomas Monjalon
2022-12-05 9:43 ` Slava Ovsiienko [this message]
2022-12-20 20:02 ` [PATCH v4 1/2] ethdev: control Rx metadata negotiation Hanumanth Pothula
2022-12-20 20:02 ` [PATCH v4 2/2] app/testpmd: add command to process " Hanumanth Pothula
2022-12-20 21:23 ` Stephen Hemminger
2022-12-21 2:07 ` [PATCH v5 1/2] ethdev: fix ethdev configuration state on reset Hanumanth Pothula
2022-12-21 2:07 ` [PATCH v5 2/2] app/testpmd: add command to process Rx metadata negotiation Hanumanth Pothula
2023-01-18 10:32 ` Thomas Monjalon
2023-01-19 10:33 ` [EXT] " Hanumanth Reddy Pothula
2023-01-25 12:51 ` Thomas Monjalon
2023-01-24 18:04 ` Ferruh Yigit
2023-01-25 9:30 ` [EXT] " Hanumanth Reddy Pothula
2023-01-25 12:55 ` Thomas Monjalon
2023-01-25 13:55 ` Ferruh Yigit
2023-01-25 13:59 ` Thomas Monjalon
2023-01-25 14:42 ` Nithin Kumar Dabilpuram
2023-01-26 11:03 ` Thomas Monjalon
2023-01-27 5:02 ` Nithin Kumar Dabilpuram
2023-01-27 8:54 ` Thomas Monjalon
2023-01-27 10:42 ` Nithin Kumar Dabilpuram
2023-01-27 15:01 ` Thomas Monjalon
2023-01-31 16:17 ` Jerin Jacob
2023-01-31 23:03 ` Thomas Monjalon
2023-02-01 6:10 ` Ivan Malov
2023-02-01 7:16 ` Andrew Rybchenko
2023-02-01 8:53 ` Jerin Jacob
2023-02-01 9:00 ` Ori Kam
2023-02-01 9:05 ` Thomas Monjalon
2023-02-01 9:07 ` Andrew Rybchenko
2023-02-01 9:14 ` Jerin Jacob
2023-02-01 9:29 ` Andrew Rybchenko
2023-02-01 10:48 ` Jerin Jacob
2023-02-01 10:58 ` Andrew Rybchenko
2023-02-01 11:04 ` Thomas Monjalon
2023-02-01 11:15 ` Jerin Jacob
2023-02-01 11:35 ` Ferruh Yigit
2023-02-01 13:48 ` Jerin Jacob
2023-02-01 14:50 ` Ferruh Yigit
2023-02-01 15:22 ` Jerin Jacob
2023-02-02 8:43 ` Ferruh Yigit
2023-02-02 8:50 ` Ivan Malov
2023-02-02 9:17 ` Ferruh Yigit
2023-02-02 10:41 ` Ivan Malov
2023-02-02 10:48 ` Ivan Malov
2023-02-02 11:41 ` Thomas Monjalon
2023-02-02 11:55 ` Ivan Malov
2023-02-02 12:03 ` Thomas Monjalon
2023-02-02 12:21 ` Andrew Rybchenko
2023-02-01 11:20 ` Ivan Malov
2023-01-25 13:17 ` Ferruh Yigit
2023-01-25 13:21 ` Ferruh Yigit
2023-01-25 13:21 ` Ferruh Yigit
2023-01-16 10:43 ` [PATCH v5 1/2] ethdev: fix ethdev configuration state on reset Hanumanth Reddy Pothula
2023-01-18 10:29 ` Thomas Monjalon
2023-01-24 18:14 ` 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=DM6PR12MB375364FDCE6DE04E56956301DF189@DM6PR12MB3753.namprd12.prod.outlook.com \
--to=viacheslavo@nvidia.com \
--cc=aman.deep.singh@intel.com \
--cc=andrew.rybchenko@oktetlabs.ru \
--cc=dev@dpdk.org \
--cc=hpothula@marvell.com \
--cc=jerinj@marvell.com \
--cc=ndabilpuram@marvell.com \
--cc=orika@nvidia.com \
--cc=rasland@nvidia.com \
--cc=thomas@monjalon.net \
--cc=yuying.zhang@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).