From: "Dumitrescu, Cristian" <cristian.dumitrescu@intel.com>
To: "Danilewicz, MarcinX" <marcinx.danilewicz@intel.com>,
"dev@dpdk.org" <dev@dpdk.org>,
"Singh, Jasvinder" <jasvinder.singh@intel.com>
Cc: "Ajmera, Megha" <megha.ajmera@intel.com>,
"Liu, Yu Y" <yu.y.liu@intel.com>
Subject: RE: [PATCH v6] sched: enable CMAN at runtime
Date: Tue, 21 Jun 2022 13:27:32 +0000 [thread overview]
Message-ID: <DM8PR11MB5670BDBDF8EA3E5E57E500E9EBB39@DM8PR11MB5670.namprd11.prod.outlook.com> (raw)
In-Reply-To: <20220621081607.993440-1-marcinx.danilewicz@intel.com>
Hi Marcin,
The code changes in the library (rte-sched.c) look good to me, but I do have some questions for the qos_sched app and the Soft NIC driver on how CMAN gets enabled/disabled.
How do we control whether congestion management (CMAN) should be disabled on enabled (WRED/PIE)? It looks to me like you are always enabling WRED by default, which is incorrect: we should have CMAN disabled by default (in init.c).
My preferred way to configure CMAN is:
a) CMAN should be disabled by default
b) If the CMAN parameters get configured in the profile.cfg, then and only then CMAN should be enabled according to the configuration.
In init.c, we can safely set the subport CMAN parameters to NULL as the built-in default when the profile.cfg is not provided, so we can safely remove the WRED params from there.
In cfg_file.c, we need to have a good way to disable/enable CMAN.
In profile.cfg, please remove the WRED lines as opposed to commenting them out.
Is this OK with you?
Also, have you tested the qos_sched app and the Soft NIC driver with all 3 configuration files?
Thanks,
Cristian
next prev parent reply other threads:[~2022-06-21 13:27 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-05-11 13:53 [PATCH] " Marcin Danilewicz
2022-05-12 13:10 ` [PATCH v2] " Marcin Danilewicz
2022-05-30 11:19 ` Dumitrescu, Cristian
2022-05-30 14:03 ` Danilewicz, MarcinX
2022-06-02 9:57 ` Danilewicz, MarcinX
2022-05-30 11:35 ` Dumitrescu, Cristian
2022-06-07 10:40 ` Danilewicz, MarcinX
2022-06-08 9:42 ` [PATCH v3] " Marcin Danilewicz
2022-06-08 11:59 ` Dumitrescu, Cristian
2022-06-08 15:29 ` Danilewicz, MarcinX
2022-06-13 9:09 ` [PATCH v4] " Marcin Danilewicz
2022-06-17 11:48 ` Dumitrescu, Cristian
2022-06-20 13:56 ` [PATCH v5] ched: " Marcin Danilewicz
2022-06-20 14:49 ` Dumitrescu, Cristian
2022-06-21 8:20 ` Danilewicz, MarcinX
2022-06-21 8:16 ` [PATCH v6] sched: " Marcin Danilewicz
2022-06-21 13:27 ` Dumitrescu, Cristian [this message]
2022-06-22 15:12 ` Danilewicz, MarcinX
2022-07-04 9:19 ` [PATCH v7] " Marcin Danilewicz
2022-07-05 17:05 ` [PATCH v8] " Marcin Danilewicz
2022-07-05 18:00 ` Ajmera, Megha
2022-07-05 22:26 ` Danilewicz, MarcinX
2022-07-06 8:53 ` Singh, Jasvinder
2022-07-07 13:07 ` Danilewicz, MarcinX
2022-07-07 16:28 ` Singh, Jasvinder
2022-07-07 21:22 ` Danilewicz, MarcinX
2022-07-08 13:14 ` [PATCH v9] " Marcin Danilewicz
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=DM8PR11MB5670BDBDF8EA3E5E57E500E9EBB39@DM8PR11MB5670.namprd11.prod.outlook.com \
--to=cristian.dumitrescu@intel.com \
--cc=dev@dpdk.org \
--cc=jasvinder.singh@intel.com \
--cc=marcinx.danilewicz@intel.com \
--cc=megha.ajmera@intel.com \
--cc=yu.y.liu@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).