On Wed, Oct 01, 2014 at 04:02:37PM -0700, Jarno Rajahalme wrote:
> flow inserts and removals are simplified:
>
> - No need for classifier internal mutex, as dpif-netdev already has a
> 'flow_mutex'
> - Number of memory allocations/frees can be halved
>
> Lookup code path is a bit more effcient as well, as we can rely on
s/effcient/efficient/
> netdev_flow_key always having inline data.
>
> Signed-off-by: Jarno Rajahalme <jrajaha...@nicira.com>
Didn't I just review a patch that improves the batched lookup in the
classifier? Yes:
http://openvswitch.org/pipermail/dev/2014-September/046230.html
So what's the intended interaction?
(I haven't read this patch yet.)
_______________________________________________
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
