netdev
[Top] [All Lists]

Re: Assertions when lowering tcp_tso_win_divisor

To: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Subject: Re: Assertions when lowering tcp_tso_win_divisor
From: "David S. Miller" <davem@xxxxxxxxxxxxx>
Date: Tue, 16 Nov 2004 16:31:42 -0800
Cc: sri@xxxxxxxxxx, netdev@xxxxxxxxxxx
In-reply-to: <E1CUA74-0002hr-00@xxxxxxxxxxxxxxxxxxxxxxxx>
References: <20041116104755.32bdb7a7.davem@xxxxxxxxxxxxx> <E1CUA74-0002hr-00@xxxxxxxxxxxxxxxxxxxxxxxx>
Sender: netdev-bounce@xxxxxxxxxxx
On Wed, 17 Nov 2004 07:39:42 +1100
Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx> wrote:

> Could you elaborate the code path that you've spotted that causes this
> when the divisor is changed?
> 
> Perhaps we're not caching the MSS value everywhere where we should be?

Currently I think your theory is better than mine, that
2.6.9 TCP is buggy wrt. TSO. :-)

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