netdev
[Top] [All Lists]

Re: 2.6.10 TCP troubles -- suggested patch

To: "David S. Miller" <davem@xxxxxxxxxxxxx>
Subject: Re: 2.6.10 TCP troubles -- suggested patch
From: Alexey Kuznetsov <kuznet@xxxxxxxxxxxxx>
Date: Sat, 12 Feb 2005 17:31:05 +0300
Cc: Rick Jones <rick.jones2@xxxxxx>, hubert.tonneau@xxxxxxxxxxxxxx, shemminger@xxxxxxxx, romieu@xxxxxxxxxxxxx, kuznet@xxxxxxxxxxxxx, netdev@xxxxxxxxxxx
Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=ms2.inr.ac.ru; b=lUpJSpMmu0fleKOIeaiV4a+zEnhM9wIONAj9odyKDsgTAPBFo051mLg96PFI2dGoqog514KE6EmkY+UagIr1EKNDsrAgbVGgRFQU7RIo1RWGl8A6iSj7l1UD+XooSqsGbnBdPurrunzZK0r/u/9Wyzz+7Kh1hu31GV5cZXmo3Io=;
In-reply-to: <20050211170958.17fcde21.davem@davemloft.net>
References: <0525M9211@server5.heliogroup.fr> <420D37A3.6020209@hp.com> <20050211170958.17fcde21.davem@davemloft.net>
Sender: netdev-bounce@xxxxxxxxxxx
User-agent: Mutt/1.5.6i
Hello!

> > In some cases at least if the sender does not completely fill cwnd the
> > ACKs will  be delayed.  And IIRC under 2.6.10 with TSO enabled, the
> > sender does not always  fill cwnd.
> 
> At a maximum, "1/tcp_tso_win_divisor" of the cwnd will ever be left
> empty.
> 
> By default, this is 1/8 of the cwnd.

In any case, receiver cannot know sender cwnd, so that "fill" or "not fill"
is is not a question.

What is broken in that implementation is that it does not feel slow start.
ACK avoidance while slow start is certain disaster. Currrent theory is that
MacOS X thinks that we do not do slow start.

Alexey

<Prev in Thread] Current Thread [Next in Thread>