[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <4BC31AA0.5070006@gmail.com>
Date: Mon, 12 Apr 2010 14:05:36 +0100
From: stephen mulcahy <smulcahy@...il.com>
To: Eric Dumazet <eric.dumazet@...il.com>
CC: netdev <netdev@...r.kernel.org>,
Ben Hutchings <ben@...adent.org.uk>,
Ayaz Abdulla <aabdulla@...dia.com>, 572201@...s.debian.org
Subject: Re: forcedeth driver hangs under heavy load
Eric Dumazet wrote:
> Le lundi 12 avril 2010 à 13:39 +0100, stephen mulcahy a écrit :
> I am not sure I understand. Are you saying that using 2.6.30-2-amd64
> kernel also makes your forcedeth adapter being not functional ?
Hi Eric,
If I run my tests with the 2.6.30-2-amd64 kernel the network doesn't
malfunction.
If I run my tests with the 2.6.32-3-amd64 kernel the network does
malfunction.
If I take the forcedeth.ko module from the 2.6.30-2-amd64 kernel and
drop that into /lib/modules/2.6.32-3-amd64/kernel/drivers/net/ and then
reboot to 2.6.32-3-amd64 and rerun my tests - the network does malfunction.
> Are both way non functional (RX and TX), or only one side ?
Whats the best way of testing this? (tcpdump listening on both hosts and
then running pings between the systems?)
-stephen
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists