lkml.org 
[lkml]   [2003]   [Dec]   [5]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: Extremely slow network with e1000 & ip_conntrack
Hi,

Okay, I reproduced it with tg3 on 2.6.0-test11 as well, by turning on
TSO with ethtool. So it does seem to be an incompatibility between TSO
& conntrack.

"David S. Miller" <davem@redhat.com> wrote:
> This workaround explains everything. The TSO packets have to be
> "un-TSO'd" in order for netfilter to look at the packet and parse
> the contents. This means copying all the data around, allocating
> several networking buffers, etc.

But, if netfilter needs to see all the contents in order to function,
shouldn't TSO break other parts of netfilter as well? Why is only
conntrack affected?

Jeff Garzik <jgarzik@pobox.com> wrote:
> Regardless, the problem is identified -- when TSO+conntrack is present,
> we "TSO" net traffic then "un-TSO" it.

This "un-TSO"ing more or less defeats the purpose of TSO, right?

> It's simply better to not use TSO at all, for this case.

If that is the case, I suppose so.

Thanks,
Stephen

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:59    [W:0.045 / U:4.780 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site