[ovs-dev] [PATCH 1/8] datapath: Disable large receive offload.

Jesse Gross jesse at nicira.com
Thu Mar 4 19:28:54 UTC 2010


On Thu, Mar 4, 2010 at 1:26 PM, Ben Pfaff <blp at nicira.com> wrote:

> On Thu, Mar 04, 2010 at 01:22:06PM -0500, Jesse Gross wrote:
> > LRO can play fast and loose with the packets that it merges, which
> > isn't very polite when you are bridging packets for other operating
> > systems.  This disables LRO on any underlying devices that are added
> > to the datapath, which is the same as what the bridge does.
> >
> > Note that this does not disable GRO, which has a more strict set of
> > rules about what is merged and is therefore safe for bridging.  Both
> > are typically done in software anyways.
>
> Thanks.  I had wondered whether we were missing something important in
> this area, and I'm glad that you found it.
>
> Could the tests for 2.6.24 or later be written as #if[n]def for some LRO
> macro?  Then we could be a little more resilient against feature
> backports.
>

Good idea, I changed it to #ifndef NETIF_F_LRO.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.openvswitch.org/pipermail/ovs-dev/attachments/20100304/b2c08da5/attachment-0003.html>


More information about the dev mailing list