From: Jonathan Morton <chromatix99@gmail.com>
To: Eric Dumazet <eric.dumazet@gmail.com>
Cc: "Toke Høiland-Jørgensen" <toke@toke.dk>,
netdev@vger.kernel.org, cake@lists.bufferbloat.net
Subject: Re: [Cake] [PATCH net-next v3] Add Common Applications Kept Enhanced (cake) qdisc
Date: Wed, 25 Apr 2018 19:52:03 +0300 [thread overview]
Message-ID: <CF30AEA0-96EA-4880-93F0-25BC56030288@gmail.com> (raw)
In-Reply-To: <8bae2ee1-efcc-1571-2a30-5b7779de2c88@gmail.com>
> We can see here the high cost of forcing software GSO :/
>
> Really, this should be done only :
> 1) If requested by the admin ( tc .... gso ....)
>
> 2) If packet size is above a threshold.
> The threshold could be set by the admin, and/or based on a fraction of the bandwidth parameter.
>
> I totally understand why you prefer to segment yourself for < 100 Mbit links.
>
> But this makes no sense on 10Gbit+
It is absolutely necessary, so far as I can see, to segment GSO superpackets when overhead compensation is selected - as it very often should be, even on pure Ethernet links. Without that, the calculation of link occupancy time will be wrong. (The actual transmission time of an Ethernet frame is rather more than just 14 bytes longer than the underlying IP packet.)
Another reason to apply GSO segmentation is to achieve maximal smoothness of flow isolation. This should still be achievable within some tolerance at high link rates, but calculating this tolerance is complicated by the triple-isolate algorithm.
If there's a way to obtain the individual packet sizes without incurring the full segmentation overhead, it may be worth considering (at high link rates only). I would want to leave it on by default, because some of Cake's demonstrably superior latency performance depends on seeing the real packets, not the aggregates, and the overhead only becomes significant above 100Mbps on weak MIPS CPUs and 1Gbps on vaguely modern x86 stuff.
- Jonathan Morton
next prev parent reply other threads:[~2018-04-25 16:52 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-04-25 13:42 Toke Høiland-Jørgensen
2018-04-25 13:42 ` [Cake] [PATCH ipruote2-next v4] Add support for cake qdisc Toke Høiland-Jørgensen
2018-04-25 14:52 ` [Cake] [PATCH net-next v3] Add Common Applications Kept Enhanced (cake) qdisc Eric Dumazet
2018-04-25 15:22 ` Toke Høiland-Jørgensen
2018-04-25 15:48 ` Eric Dumazet
2018-04-25 15:51 ` Eric Dumazet
2018-04-25 16:06 ` Toke Høiland-Jørgensen
2018-04-25 16:29 ` Eric Dumazet
2018-04-25 16:52 ` Jonathan Morton [this message]
2018-04-25 16:57 ` Eric Dumazet
2018-04-25 18:34 ` Toke Høiland-Jørgensen
2018-04-25 18:48 ` David Miller
2018-04-25 19:02 ` Eric Dumazet
2018-04-25 19:15 ` Toke Høiland-Jørgensen
2018-04-25 17:54 ` Sebastian Moeller
2018-04-25 16:55 ` Toke Høiland-Jørgensen
2018-04-25 16:59 ` Eric Dumazet
2018-04-25 16:00 ` Eric Dumazet
2018-04-25 16:17 ` Toke Høiland-Jørgensen
2018-04-25 17:43 ` Eric Dumazet
2018-04-25 18:35 ` Toke Høiland-Jørgensen
2018-04-25 18:39 ` David Miller
2018-04-25 18:46 ` Toke Høiland-Jørgensen
2018-04-27 10:54 ` kbuild test robot
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
List information: https://lists.bufferbloat.net/postorius/lists/cake.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CF30AEA0-96EA-4880-93F0-25BC56030288@gmail.com \
--to=chromatix99@gmail.com \
--cc=cake@lists.bufferbloat.net \
--cc=eric.dumazet@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=toke@toke.dk \
/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