General list for discussing Bufferbloat
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: Jesper Dangaard Brouer <hawk@comx.dk>
Cc: Van Jacobson <van@parc.com>,
	bloat-devel@lists.bufferbloat.net, herbert@gondor.apana.org.au,
	bloat@lists.bufferbloat.net
Subject: Re: [Bloat] GSO (was: Please enter issues into the issue tracker - Issue system organisation needed)
Date: Fri, 25 Feb 2011 17:33:47 +0100	[thread overview]
Message-ID: <1298651627.2659.84.camel@edumazet-laptop> (raw)
In-Reply-To: <1298648937.28000.41.camel@traveldev.cxnet.dk>

Le vendredi 25 février 2011 à 16:48 +0100, Jesper Dangaard Brouer a
écrit :

> Yes, both servers (/proc/sys/net/ipv4/tcp_sack = 1).
> 
> I think that the bufferbloat theory is that SACKs will not work, due to
> the long delays introduced by buffers(bloat).   In this case, you can
> see on the graph, a max RTT around 150 ms and an average of 20 ms.  
> 
> While another, more well behaved path in the network to the speed
> server, I would only see a max RTT around 25 ms and an average of 15 ms,
> see:
> http://people.netfilter.org/hawk/dropbox/bloat_vs_GSO/speed-to-pc314a-1.png
> 
> You can also see this path had an ave of 90Mbit/s, but with significant
> throughput drops (the 92Mbit/s line is an artificial line on the graph).
> This behavior is probaly caused by the GSO effect.
> 
> Disabling GSO on speed server fixed the problem as can be seen on graph:
> http://people.netfilter.org/hawk/dropbox/bloat_vs_GSO/speed-to-grantoften-solved.png
> 
> The really strange part when troubleshooting this issue was that the
> throughput as fine between the two customer end-boxes ("grantoften" and
> "pc314a") as can be see here:
> http://people.netfilter.org/hawk/dropbox/bloat_vs_GSO/pc314a-to-grantoften-1.png
> 
> 

Its a bit hard to interpret these graphs, I am a bit lost...
What exactly is sampled ? Is it from tcpdump analysis or output from
HTB/SFQ stats ?

For sure, one TSO drop really drops a full range of [XX] tcp segments,
while with TSO off, a drop is one segment drop.

This certainly can explain bad artifacts, as receiver interprets this as
a huge congestion indication.

TSO/GRO are good only in the datacenter domain, where we want 10Gb flows
between two nodes with low CPU impact.



  parent reply	other threads:[~2011-02-25 16:34 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-02-24 14:19 [Bloat] Please enter issues into the issue tracker - Issue system organisation needed Jim Gettys
2011-02-24 15:00 ` Fred Baker
2011-02-24 16:32   ` Jim Gettys
2011-02-24 17:08     ` Eric Dumazet
2011-02-24 18:31       ` Dave Täht
2011-02-24 19:29         ` Eric Dumazet
2011-02-25 10:12           ` [Bloat] smokeping for Windows Seth Teller
2011-02-25 10:51             ` Jim Gettys
2011-02-25 11:21           ` [Bloat] GSO (was: Please enter issues into the issue tracker - Issue system organisation needed) Jesper Dangaard Brouer
2011-02-25 11:54             ` Eric Dumazet
2011-02-25 15:48               ` Jesper Dangaard Brouer
2011-02-25 16:19                 ` Eric Dumazet
2011-02-25 16:33                 ` Eric Dumazet [this message]
2011-02-25 17:15                   ` Jesper Dangaard Brouer
2011-02-26  2:41                     ` [Bloat] GSO Dave Täht
2011-03-02  8:30                       ` Jesper Dangaard Brouer
2011-03-04  2:23                         ` Dave Täht
2011-02-25 15:40         ` [Bloat] Please enter issues into the issue tracker - Issue system organisation needed John W. Linville

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=1298651627.2659.84.camel@edumazet-laptop \
    --to=eric.dumazet@gmail.com \
    --cc=bloat-devel@lists.bufferbloat.net \
    --cc=bloat@lists.bufferbloat.net \
    --cc=hawk@comx.dk \
    --cc=herbert@gondor.apana.org.au \
    --cc=van@parc.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