On 4/14/16, 3:24 PM, "dev on behalf of ngh...@us.ibm.com" <
dev-boun...@openvswitch.org on behalf of ngh...@us.ibm.com> wrote:
There are four sessions established from ovn-controller to the following:
OVN Southbound — JSONRPC based
Local ovsdb — JSONRPC based
Local vswitchd — openflow based from o
ot;Scale Test" team within the Open vSwitch organization on
> github. I made you the owner of this team. I believe that means that,
> if you want to transfer the ovn-scale-test repo into the Open vSwitch
> organization, you can now do it.
>
> On Tue, Apr 12, 2016 at 10:21:
Hi Ben,
In my opinion, put the scale test in a separate repo under
https://github.com/openvswitch/ is a better choice. As you said OVS is
quickly evolving and the review process is heavyweight and slow, workload
is already high, put scale test into it can cause more overhead.
The review & merge p
depends
on are there any better place to put the repo to :)
BR
Huang Lei
On Mon, Apr 11, 2016 at 11:52 AM, Baohua Yang wrote:
> interesting work!
> will it be integrated back to rally repo?
>
> On Mon, Apr 11, 2016 at 10:21 AM, Lei Huang wrote:
>
>> Hi,
>>
>>
Hi,
In last few months we created a ovn scalability test tool, it is
implemented based on openstack/rally project, its repo is
https://github.com/l8huang/ovn-scale-test.
Its basic usage is creating thounsands of ovs sandboxes(to simulate HVs) on
multiple BMs, and create and bind lports to these s
Hi,
During a scalability test, we found that the ovn northbound ovsdb-server’s
memory usage becomes very high while creating and binding ports, the test
step is:
1. Create 1000 sandboxes
2. Create 5 lswitches and create 200 lports for each of lswitches, on
northbound
3. For each of lport crea
Hi,
We run a scalability test case to test lport creation and binding.
The git version is 06d4d4b on master branch with a patch to disable alive
probe messages between ovsdb-server and ova-controller.
The test environment is deployed as below:
- a rally node, used to run test case
- a ovn c
