mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: kuznet@ms2.inr.ac.ru
To: Mika.Liljeberg@welho.com (Mika Liljeberg)
Cc: ak@muc.de, davem@redhat.com, linux-kernel@vger.kernel.org
Subject: Re: TCP acking too fast
Date: Sun, 14 Oct 2001 23:12:31 +0400 (MSK DST)	[thread overview]
Message-ID: <200110141912.XAA06706@ms2.inr.ac.ru> (raw)
In-Reply-To: <3BC9DE09.747F45B2@welho.com> from "Mika Liljeberg" at Oct 14, 1 09:48:41 pm

Hello!

> > But sending ACK on buffer drain at least for short
> > packets is real demand, which cannot be relaxed.
> 
> Why? This one has me stumped.

To remove sick delays with nagling transfers (1) and to remove
deadlocks due to starvation on rcvbuf (2) at receiver and on sndbuf
at sender (3).

Actually, (2) is solved nowadays with compressing queue. (3) can be solved
acking each other segment. But (1) remains. The solution used in 2.2,
when delack timeout was reduced to short value on short packets with PSH
set worked with probability of 50% on very slow links i.e. in the case
when wrong delay is not important at all and not covering cases
where absence of long gaps is really important.

Actually, any alternative idea how to solve this could be very useful.

Alexey

  reply	other threads:[~2001-10-14 19:12 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2001-10-14  0:23 Mika Liljeberg
2001-10-14  6:40 ` David S. Miller
2001-10-14  7:05   ` Mika Liljeberg
2001-10-14  7:47   ` David S. Miller
2001-10-14  7:51     ` Mika Liljeberg
2001-10-14  8:12     ` David S. Miller
2001-10-14  8:39       ` Mika Liljeberg
2001-10-14  9:03       ` David S. Miller
2001-10-14  9:15         ` Mika Liljeberg
2001-10-14  9:16         ` David S. Miller
2001-10-14  9:25         ` Andi Kleen
2001-10-14  9:39         ` David S. Miller
2001-10-14 11:30           ` Andi Kleen
2001-10-14 11:49             ` Mika Liljeberg
2001-10-14 14:05               ` Andi Kleen
2001-10-14 14:26                 ` Mika Liljeberg
2001-10-14 16:12                   ` Andi Kleen
2001-10-14 16:55                     ` Mika Liljeberg
2001-10-14 17:07                       ` kuznet
2001-10-14 17:26                         ` Mika Liljeberg
2001-10-14 17:35                           ` kuznet
2001-10-14 17:56                             ` Mika Liljeberg
2001-10-14 18:20                               ` kuznet
2001-10-14 18:48                                 ` Mika Liljeberg
2001-10-14 19:12                                   ` kuznet [this message]
2001-10-14 19:32                                     ` Mika Liljeberg
2001-10-14 19:40                                       ` kuznet
2001-10-14 20:06                                         ` Mika Liljeberg
2001-10-15 18:40                                           ` kuznet
2001-10-15 19:15                                             ` Mika Liljeberg
2001-10-15 19:38                                               ` Mika Liljeberg
2001-10-14 13:14             ` [PATCH] " Mika Liljeberg
2001-10-14 16:36             ` kuznet
2001-10-14  7:50   ` David S. Miller
2001-10-14  7:53     ` Mika Liljeberg
2001-10-15 20:59 ` Bill Davidsen

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=200110141912.XAA06706@ms2.inr.ac.ru \
    --to=kuznet@ms2.inr.ac.ru \
    --cc=Mika.Liljeberg@welho.com \
    --cc=ak@muc.de \
    --cc=davem@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    /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

all inboxes | Powered by JetHome®