netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Cong Wang <amwang@redhat.com>
To: Eric Dumazet <erdnetdev@gmail.com>
Cc: netdev@vger.kernel.org, Ben Greear <greearb@candelatech.com>,
	David Miller <davem@davemloft.net>,
	Stephen Hemminger <shemminger@vyatta.com>,
	Rick Jones <rick.jones2@hp.com>, Thomas Graf <tgraf@redhat.com>
Subject: Re: TCP delayed ACK heuristic
Date: Wed, 19 Dec 2012 14:54:39 +0800	[thread overview]
Message-ID: <1355900079.6665.13.camel@cr0> (raw)
In-Reply-To: <1355848224.9380.30.camel@edumazet-glaptop>

On Tue, 2012-12-18 at 08:30 -0800, Eric Dumazet wrote:
>  
> 
> ACKS might also be delayed because of bidirectional traffic, and is more
> controlled by the application response time. TCP stack can not easily
> estimate it.

So we still need a knob?

> 
> If you focus on bulk receive, LRO/GRO should already lower number of
> ACKS to an acceptable level and without major disruption.

Indeed.

> 
> Stretch acks are not only the receiver concern, there are issues for the
> sender that you cannot always control/change.
> 
> I recommend reading RFC2525 2.13
> 

Very helpful information!

On the sender's side, it needs to "notify" the receiver not to send
stretch acks when it is in slow-start. But I think the receiver can
detect slow-start too on its own side (based one the window size?).

Thanks!

  reply	other threads:[~2012-12-19  6:54 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <270756364.27707018.1355842632348.JavaMail.root@redhat.com>
2012-12-18 15:11 ` TCP delayed ACK heuristic Cong Wang
2012-12-18 16:30   ` Eric Dumazet
2012-12-19  6:54     ` Cong Wang [this message]
2012-12-18 16:39   ` David Laight
2012-12-18 17:54     ` Rick Jones
2012-12-19  9:52       ` David Laight
2012-12-19  7:00     ` Cong Wang
2012-12-19 18:39       ` Rick Jones
2012-12-19 20:59         ` David Miller
2012-12-20  3:23           ` Cong Wang
2012-12-20  9:57             ` David Laight
2012-12-20 12:41               ` Cong Wang
2012-12-19 23:08         ` Eric Dumazet

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=1355900079.6665.13.camel@cr0 \
    --to=amwang@redhat.com \
    --cc=davem@davemloft.net \
    --cc=erdnetdev@gmail.com \
    --cc=greearb@candelatech.com \
    --cc=netdev@vger.kernel.org \
    --cc=rick.jones2@hp.com \
    --cc=shemminger@vyatta.com \
    --cc=tgraf@redhat.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).