netdev
[Top] [All Lists]
<prev [Date] next>
[Advanced]
 <prev [Thread] next>

Re: TCP-Protection is really a pain...

from [Christian Schmid] [Permanent Link][Original]
To: Jeff Garzik <jgarzik@xxxxxxxxx>
Subject: Re: TCP-Protection is really a pain...
From: Christian Schmid <webmaster@xxxxxxxxxxxxxx>
Date: Thu, 03 Feb 2005 23:29:10 +0100
Cc: Stephen Hemminger <shemminger@xxxxxxxx>, netdev@xxxxxxxxxxx
In-reply-to: <4202A206.7060100@pobox.com>
References: <4201A382.1020208@rapidforum.com> <20050202205437.571a702b@localhost.localdomain> <4201B4EA.2030101@rapidforum.com> <20050203113335.46396c11@dxpl.pdx.osdl.net> <42028278.7040008@rapidforum.com> <20050203121503.4f122779@dxpl.pdx.osdl.net> <42028747.6060602@rapidforum.com> <4202A206.7060100@pobox.com>
Sender: netdev-bounce@xxxxxxxxxxx
User-agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8a3) Gecko/20040817 
I turned it off and without it, I was unable to reproduce any stalls anymore.

Jeff Garzik wrote: 
Christian Schmid wrote:

What exactly is tcp segmentation offload? Where can I read more about it? Should I disable it or is this not a good idea?


It's an optimization designed to reduce CPU usage for zero-copy apps (those that use sendfile(2)).

It would be a useful datapoint to disable TSO, and see if that improves things for you.

    Jeff





[More with this subject...]
<Prev in Thread] Current Thread [Next in Thread>
Previous by Date:  Re: [PATCH] arp_queue: serializing unlink + kfree_skb, David S. Miller
Next by Date:  pointers in the sk_buff structure., sudeep list
Previous by Thread:  Re: TCP-Protection is really a pain..., Jeff Garzik
Next by Thread:  Which function at link layer sends packet?, cranium 2003
Indexes:  [Date] [Thread] [Top] [All Lists]