From: d@taht.net (Dave Täht)
To: Jonathan Morton <chromatix99@gmail.com>
Cc: Stephen Hemminger <shemminger@vyatta.com>, bloat@lists.bufferbloat.net
Subject: Re: [Bloat] Random idea in reaction to all the discussion of TCP flavours - timestamps?
Date: Tue, 15 Mar 2011 19:02:39 -0600 [thread overview]
Message-ID: <87bp1b6fo0.fsf@cruithne.co.teklibre.org> (raw)
In-Reply-To: <823E2A7B-4F46-4159-8029-BD3B075CC4CE@gmail.com> (Jonathan Morton's message of "Wed, 16 Mar 2011 02:49:42 +0200")
Jonathan Morton <chromatix99@gmail.com> writes:
> On 16 Mar, 2011, at 1:46 am, Dave Täht wrote:
>
>>> 1) Wired devices, where we want to push more 10+ Gbps, so we can assume
>>> a posted skb is transmitted immediately. Even a basic qdisc can be a
>>> performance bottleneck. Set TX ring size to 256 or 1024+ buffers to
>>> avoid taking too many interrupts.
>>
>> To talk to this a bit, the huge dynamic range discrepancy between a
>> 10GigE device and what it may be connected to worries me. Some form of
>> fair queuing should be applied before the data hits the driver.
>
> You mean plugging a 10GigE card into a 10Base-T hub? :-D
More like 10GigE into a 1Gig switch. Or spewing out the entire contents
of a stream to one destination across the internet.
>
> For less ridiculous topologies, the queues would mostly be in other devices.
But you flood them less with fair queuing, which was my point.
Nagle:
http://en.wikipedia.org/wiki/Fair_queuing
> - Jonathan
>
--
Dave Taht
http://nex-6.taht.net
next prev parent reply other threads:[~2011-03-16 1:02 UTC|newest]
Thread overview: 70+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-03-15 10:36 Jim Gettys
2011-03-15 14:40 ` Jim Gettys
2011-03-15 16:47 ` Jonathan Morton
2011-03-15 17:59 ` Don Marti
2011-03-15 18:14 ` Rick Jones
2011-03-15 18:31 ` John W. Linville
2011-03-15 19:40 ` Jonathan Morton
2011-03-15 19:59 ` Rick Jones
2011-03-15 20:51 ` John W. Linville
2011-03-15 21:31 ` Rick Jones
2011-03-16 0:32 ` John W. Linville
2011-03-16 1:02 ` Rick Jones
2011-03-15 22:01 ` Jonathan Morton
2011-03-15 22:19 ` Stephen Hemminger
2011-03-15 22:26 ` Jonathan Morton
2011-03-15 22:36 ` Rick Jones
2011-03-15 22:40 ` Jonathan Morton
2011-03-15 22:42 ` Stephen Hemminger
2011-03-15 22:52 ` Eric Dumazet
2011-03-15 23:02 ` Rick Jones
2011-03-15 23:12 ` Jonathan Morton
2011-03-15 23:25 ` Rick Jones
2011-03-15 23:33 ` Jonathan Morton
2011-03-15 23:46 ` Dave Täht
2011-03-16 0:49 ` Jonathan Morton
2011-03-16 1:02 ` Dave Täht [this message]
2011-03-16 1:28 ` Jonathan Morton
2011-03-16 1:59 ` Dave Täht
2011-03-16 2:23 ` Jonathan Morton
2011-03-16 22:22 ` [Bloat] Random idea in reaction to all the discussion of TCPflavours " Richard Scheffenegger
2011-03-16 23:38 ` richard
2011-03-16 23:50 ` Rick Jones
2011-03-17 12:05 ` Fred Baker
2011-03-17 12:18 ` Fred Baker
2011-03-17 17:27 ` Dave Täht
2011-03-18 18:30 ` Richard Scheffenegger
2011-03-18 18:49 ` Fred Baker
2011-03-20 11:40 ` Jonathan Morton
2011-03-20 22:18 ` david
2011-03-20 22:45 ` Jonathan Morton
2011-03-20 22:50 ` Dave Täht
2011-03-20 22:55 ` grenville armitage
2011-03-20 23:04 ` Dave Täht
2011-03-20 23:14 ` Jonathan Morton
2011-03-20 23:19 ` Dave Täht
2011-03-20 23:23 ` Dave Täht
2011-03-20 22:58 ` Jonathan Morton
2011-03-21 1:28 ` david
2011-03-21 1:56 ` Wesley Eddy
2011-03-18 18:27 ` [Bloat] Random idea in reaction to all the discussion ofTCPflavours " Richard Scheffenegger
2011-03-16 22:07 ` [Bloat] Random idea in reaction to all the discussion of TCPflavours " Richard Scheffenegger
2011-03-17 0:10 ` Jonathan Morton
2011-03-16 0:47 ` [Bloat] Random idea in reaction to all the discussion of TCP flavours " John W. Linville
2011-03-16 20:07 ` Jim Gettys
2011-03-17 2:26 ` Jonathan Morton
2011-03-17 18:22 ` Rick Jones
2011-03-17 21:50 ` Jonathan Morton
2011-03-17 22:20 ` Rick Jones
2011-03-17 22:56 ` Jonathan Morton
2011-03-18 1:36 ` Justin McCann
2011-03-18 5:51 ` Eric Dumazet
2011-03-15 16:34 ` Jonathan Morton
2011-03-15 18:13 ` Stephen Hemminger
2011-03-16 5:41 ` Fred Baker
2011-03-16 6:26 ` Jonathan Morton
2011-03-16 8:55 ` [Bloat] Random idea in reaction to all the discussion of TCPflavours " Richard Scheffenegger
2011-03-16 9:04 ` [Bloat] Random idea in reaction to all the discussion of TCP flavours " BeckW
2011-03-16 22:48 ` Fred Baker
2011-03-16 23:23 ` Jonathan Morton
2011-03-17 8:34 ` BeckW
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/bloat.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87bp1b6fo0.fsf@cruithne.co.teklibre.org \
--to=d@taht.net \
--cc=bloat@lists.bufferbloat.net \
--cc=chromatix99@gmail.com \
--cc=shemminger@vyatta.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