On Wed, Mar 30, 2016 at 03:20:33AM +0000, Daniele Di Proietto wrote: > On 29/03/2016 06:44, "Karl Rister" <kris...@redhat.com> wrote: > >One other area of the sequence code that I thought was curious was a > >single mutex that covered all sequences. If updating the API is a > >possibility I would think going to a mutex per sequence might be an > >appropriate change as well. That said, I don't have data that > >specifically points this out as a problem. > > If we find this to be a bottleneck I think we can have a finer-grained > locking.
I designed the seq code to be really simple and figured that we might need to revisit it one day. I'd be happy to see it improved. _______________________________________________ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev
