From: Patrick McHardy <kaber@trash•net>
To: netdev@vger•kernel.org
Subject: Re: net_sched 00/07: classful multiqueue dummy scheduler
Date: Fri, 04 Sep 2009 18:42:31 +0200 [thread overview]
Message-ID: <4AA14377.9020200@trash.net> (raw)
In-Reply-To: <20090904164111.27300.29929.sendpatchset@x2.localnet>
[-- Attachment #1: Type: text/plain, Size: 1279 bytes --]
Patrick McHardy wrote:
> These patches contain a classful multiqueue ("mq") dummy scheduler to fix a
> couple of problems with the current multiqueue TC API integration. The
> changelogs of patch 05 and 07 contain more details.
>
> The mq scheduler does two things:
>
> - present device TX queues as classes, allowing to attach different qdiscs
> to them, which are grafted to the TX queues
>
> - present accumulated statistics of all device queue root qdiscs
>
> Its used by default for multiqueue devices instead of the regular pfifo_fast
> qdisc, but can also be attached manually to restore multiqueue behaviour
> after attaching a non-multiqueue (shared) qdisc.
>
> Patches 1-4 contain some preparatory cleanups because I was getting tired
> of copying unnecessary checks and dummy functions :)
>
> Patch 5 introduces a dev->qdisc pointer, which points to the root qdisc from
> userspace's point of view. This is later used for the mq qdisc, which isn't
> actually attached to any device queues. Patch 7 contains the mq scheduler.
>
> I've tested the scheduler with a hacked macvlan version which uses 4 queues,
> but since I don't own a multiqueue capable device I couldn't test this on
> real hardware.
And for reference, this is the script I used for testing:
[-- Attachment #2: test.sh --]
[-- Type: application/x-sh, Size: 928 bytes --]
next prev parent reply other threads:[~2009-09-04 16:42 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-09-04 16:41 net_sched 00/07: classful multiqueue dummy scheduler Patrick McHardy
2009-09-04 16:41 ` net_sched 01/07: fix class grafting errno codes Patrick McHardy
2009-09-04 16:41 ` net_sched 02/07: make cls_ops->tcf_chain() optional Patrick McHardy
2009-09-05 8:13 ` Jarek Poplawski
2009-09-05 11:57 ` Jarek Poplawski
2009-09-05 12:32 ` Jarek Poplawski
2009-09-05 17:03 ` Patrick McHardy
2009-09-06 9:06 ` David Miller
2009-09-04 16:41 ` net_sched 03/07: make cls_ops->change and cls_ops->delete optional Patrick McHardy
2009-09-04 16:41 ` net_sched 04/07: remove some unnecessary checks in classful schedulers Patrick McHardy
2009-09-04 16:41 ` net_sched 05/07: reintroduce dev->qdisc for use by sch_api Patrick McHardy
2009-09-06 18:57 ` Jarek Poplawski
2009-09-07 13:16 ` Patrick McHardy
2009-09-07 16:49 ` Jarek Poplawski
2009-09-04 16:41 ` net_sched 06/07: move dev_graft_qdisc() to sch_generic.c Patrick McHardy
2009-09-04 16:41 ` net_sched 07/07: add classful multiqueue dummy scheduler Patrick McHardy
2009-09-06 20:04 ` Jarek Poplawski
2009-09-07 13:27 ` Patrick McHardy
2009-09-07 18:22 ` Jarek Poplawski
2009-09-07 19:24 ` Jarek Poplawski
2009-09-07 19:49 ` Eric Dumazet
2009-09-09 16:02 ` Patrick McHardy
2009-09-09 19:52 ` Jarek Poplawski
2009-09-10 11:28 ` Patrick McHardy
2009-09-11 21:38 ` Jarek Poplawski
2009-09-11 22:10 ` David Miller
2009-09-11 22:21 ` Jarek Poplawski
2009-09-11 22:27 ` David Miller
2009-09-09 16:01 ` Patrick McHardy
2009-09-04 16:42 ` Patrick McHardy [this message]
2009-09-07 8:50 ` net_sched 00/07: " David Miller
2009-09-07 9:46 ` Jarek Poplawski
2009-09-07 13:00 ` Eric Dumazet
2009-09-07 13:29 ` Patrick McHardy
2009-09-07 14:23 ` Patrick McHardy
2009-09-07 17:21 ` Eric Dumazet
2009-09-07 17:28 ` Patrick McHardy
2009-09-07 17:30 ` Eric Dumazet
2009-09-07 17:33 ` Patrick McHardy
2009-09-07 17:38 ` Eric Dumazet
2009-09-07 17:46 ` Patrick McHardy
2009-09-08 9:31 ` David Miller
2009-09-08 15:53 ` Patrick McHardy
2009-09-05 7:27 ` David Miller
2009-09-05 17:02 ` Patrick McHardy
2009-09-06 9:01 ` David Miller
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=4AA14377.9020200@trash.net \
--to=kaber@trash$(echo .)net \
--cc=netdev@vger$(echo .)kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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