netdev
[Top] [All Lists]

Re: Memory leak in 2.6.11-rc1?

To: "David S. Miller" <davem@xxxxxxxxxxxxx>, Robert.Olsson@xxxxxxxxxxx, akpm@xxxxxxxx, torvalds@xxxxxxxx, alexn@xxxxxxxxx, kas@xxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx
Subject: Re: Memory leak in 2.6.11-rc1?
From: Phil Oester <kernel@xxxxxxxxxxxx>
Date: Sun, 30 Jan 2005 08:57:02 -0800
In-reply-to: <20050130153449.B25000@xxxxxxxxxxxxxxxxxxxxxx>
References: <20050127082809.A20510@xxxxxxxxxxxxxxxxxxxxxx> <20050127004732.5d8e3f62.akpm@xxxxxxxx> <16888.58622.376497.380197@xxxxxxxxxxxx> <20050127164918.C3036@xxxxxxxxxxxxxxxxxxxxxx> <20050127123326.2eafab35.davem@xxxxxxxxxxxxx> <20050128001701.D22695@xxxxxxxxxxxxxxxxxxxxxx> <20050127163444.1bfb673b.davem@xxxxxxxxxxxxx> <20050128085858.B9486@xxxxxxxxxxxxxxxxxxxxxx> <20050130132343.A25000@xxxxxxxxxxxxxxxxxxxxxx> <20050130153449.B25000@xxxxxxxxxxxxxxxxxxxxxx>
Sender: netdev-bounce@xxxxxxxxxxx
User-agent: Mutt/1.4.1i
On Sun, Jan 30, 2005 at 03:34:49PM +0000, Russell King wrote:
> I think the case against the IPv4 fragmentation code is mounting.
> However, without knowing what the expected conditions for this code,
> (eg, are skbs on the fraglist supposed to have NULL skb->dst?) I'm
> unable to progress this any further.  However, I think it's quite
> clear that there is something bad going on here.

Interesting...the gateway which exhibits the problem fastest in my
area does have a large number of fragmented UDP packets running through it,
as shown by tcpdump 'ip[6:2] & 0x1fff != 0'.

> Why many more people aren't seeing this I've no idea.

Perhaps you (and I) experience more fragments than the average user???

Nice detective work!

Phil

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