Re: [dpdk-ci] Minutes of DPDK Lab Meeting, February 26th

[Thomas Monjalon <thomas@monjalon.net>]

04/03/2019 09:06, Stokes, Ian:
> > -----Original Message-----
> > From: O'Driscoll, Tim
> > Sent: Thursday, February 28, 2019 3:25 PM
> > To: Thomas Monjalon <thomas@monjalon.net>; ci@dpdk.org
> > Cc: Aaron Conole <aconole@redhat.com>; Stokes, Ian <ian.stokes@intel.com>
> > Subject: RE: [dpdk-ci] Minutes of DPDK Lab Meeting, February 26th
> > 
> > > -----Original Message-----
> > > From: Thomas Monjalon [mailto:thomas@monjalon.net]
> > > Sent: Thursday, February 28, 2019 3:20 PM
> > > To: ci@dpdk.org
> > > Cc: O'Driscoll, Tim <tim.odriscoll@intel.com>
> > > Subject: Re: [dpdk-ci] Minutes of DPDK Lab Meeting, February 26th
> > >
> > > Hi,
> > >
> > > 28/02/2019 15:49, O'Driscoll, Tim:
> > > > OVS Tests:
> > > > - Jeremy and Aaron are working on setup of the temporary hardware.
> > > > - There are two options for hardware to run this on when the setup
> > > > is
> > > complete: 1) use existing vendor hardware; 2) obtain standalone
> > > servers for OVS testing. The OVS team's preference is option 2. It's
> > > not realistic to expect a vendor to provide hardware to run a
> > > competitor's products so we'd need to find a different way to procure
> > > this. Aaron will check with Rashid to see if budget is available from
> > > Red Hat. I'll check with Trishan to see if the DPDK project budget could
> > cover this.
> > > > - The OVS focus is on functional tests, not performance tests. The
> > > DPDK lab is currently set up so that each vendor has complete control
> > > over performance tests & results on their hardware. If we use separate
> > > hardware for the OVS tests, we need to ensure that we restrict scope
> > > to functional tests so that it does not conflict with this principle
> > > in future.
> > >
> > > I am not sure to understand.
> > > In my opinion, the purpose of this lab is to have properly tuned
> > > hardware for running a large set of tests. We should be able to run
> > > various tests on the same machine. So the OVS tests, like any new test
> > > scenario, should be run on the same machine as the performance tests.
> > > I think we just need to have a job queue to run tests one by one,
> > > avoiding a test to disturb results of another one.
> > >
> > > Why are we looking for additional machines?
> > 
> > That was my assumption too. I believe the reason is that the OVS team want
> > to validate with multiple vendor NICs to be sure that nothing is broken.
> > We only have Intel and Mellanox hardware in our lab at present, so we
> > don't cover all vendors.
> > 
> > Aaron and Ian can provide more details.
> 
> Hi Thomas,
> 
> So from the OVS point of view, one of challenges when consuming DPDK is ensuring device compatibility across the community, in particular with the ongoing/upcoming HWOL development work. There is a risk that the implementation for HWOL for vendor x may not be compatible or suitable for vendor y etc.
> 
> To help address this risk, it was proposed back in DPDK userspace 2018 that if the OVS community could provide a server, it could be used to co-locate a variety of vendor NICs. We could then leverage the OVS Zero Day robot to apply and conduct functional testing for OVS development patches and ensure patches do not break existing functionality.

Yes it seems to be the scope of the DPDK Community Lab.

> To date Aaron has received a number of NICs from various vendors, however a server (possibly 2) would still be needed to deploy the NICS.
> 
> It was proposed that possibly the DPDK Lab in UNL aid with this.
> 
> The aim here is purely functional and the system would not be used to benchmark the NICs in question. It would be purely to stop regressions being introduced into OVS DPDK and also act as a feedback to the DPDK community if changes were needed in DPDK itself.

So far I don't see the need for new servers.

> It might be possible to run the tests on the existing hardware in UNL but I guess this might not cover the NIC vendors Aaron has received to date. I wonder would it interrupt the existing DPDK workloads on those servers also so there was an open question on whether OVS DPDK should be deployed on a separate board.

Which vendor is not available in the DPDK Community Lab?

> @Aaron, have I missed anything from your side?
> 
> Thanks
> Ian