Hi all,
The latest OVS drops all packets that don't match a flow. Is it possible
to change this behavior back to packet_in to the OpenFlow controller?
Any options?
One issues for us is if we add the rule
"priority=0,actions=output:CONTROLLER", we receive packet_in with reason
"to_controller
Hi all,
I use the latest OVS (master branch) running only DPDK ports. I have
connected an OpenFlow controller that iteratively sends LLDP packets via
OpenFlow Packet Out messages across all ports.
I see that LLDP messages finally ends up in lib/netdev-dpdk.c and
successfully goes throught r
yimeng zhao mailto:exahe...@gmail.com>>
Date: Wednesday, September 3, 2014 at 8:08 AM
To: Alexander Shalimov mailto:ashali...@arccn.ru>>
Cc: "discuss@openvswitch.org <mailto:discuss@openvswitch.org>"
mailto:discuss@openvswitch.org>>
Subject: Re: [ovs-discuss] p
Hi,
We recently finished with throughput measurements of OVS. We saw that
phy-to-phy throughput became higher with the increasing number of flows:
#1. 1 flow, phy-to-phy, 64 bytes packets => 1Mpps
#2. 32 flows (1 src ip, 32 dst ips), phy-to-phy, 64 bytes packets => 9Mpps
Could anyone explain w
Hi Alexandru,
We have developed a framework for testing OpenFlow controllers called
hcprobe (http://arccn.github.io/hcprobe/). It has specific language to
create your own tests.
We used hcprobe for advanced controllers testing
http://arccn.ru/knowledge-base?lang=en&document=1389794238.
С у
Could you please clarify why It's not true? Why you don't want to allow flow
management from the dpctl? Personally for me it looks very useful tool.
Thanks,
Alexander.
Ben Pfaff wrote:
>On Wed, Jun 05, 2013 at 05:12:15PM +0400, Alexander Shalimov wrote:
>> Could you pleas
