not require scalability and determinism.
> >
> > BR, Jan
> >
> > > -Original Message-
> > > From: Ben Pfaff [mailto:b...@ovn.org]
> > > Sent: Monday, 25 September, 2017 18:48
> > > To: Jan Scheurich
> > > Cc: Nitin Katiyar ; ovs-dev@op
Message-
> > From: Ben Pfaff [mailto:b...@ovn.org]
> > Sent: Monday, 25 September, 2017 18:48
> > To: Jan Scheurich
> > Cc: Nitin Katiyar ; ovs-dev@openvswitch.org
> > Subject: Re: [ovs-dev] Proposal for enabling dp_hash irrespective of OF
> > version
>
-
> From: Ben Pfaff [mailto:b...@ovn.org]
> Sent: Monday, 25 September, 2017 18:48
> To: Jan Scheurich
> Cc: Nitin Katiyar ; ovs-dev@openvswitch.org
> Subject: Re: [ovs-dev] Proposal for enabling dp_hash irrespective of OF
> version
>
> If the new selection method is superio
If the new selection method is superior to the default one, is there a
reason to require the controller to select it at all?
On Mon, Sep 25, 2017 at 04:28:26PM +, Jan Scheurich wrote:
> Hi Ben,
>
> The current hard-coded default select group implementation requires every
> single L4 flow to
Hi Ben,
The current hard-coded default select group implementation requires every
single L4 flow to be load-balanced in an upcall and creates a dedicated
megaflow for every 5-tuple. This is clearly not scalable in deployments where
the number of parallel L4 flows and the L4 flow setup rate is u
On Mon, Sep 25, 2017 at 11:15:55AM +, Nitin Katiyar wrote:
> Hi,
> I have a proposal to add a provision for using "dp_hash" as selection method
> (which can currently be used with OF1.5 based controllers only) irrespective
> of the OF version being used by controller.
>
> The link for docume
Hi,
I have a proposal to add a provision for using "dp_hash" as selection method
(which can currently be used with OF1.5 based controllers only) irrespective of
the OF version being used by controller.
The link for document is :
https://docs.google.com/document/d/13Jiwbs0atV_Y8Vatj6SmQeB_qdM-Ay
