[Bloat] [Galene] Re: testing latency under load on webrtc with galene?

Luca Muscariello muscariello at ieee.org
Thu Mar 4 16:22:04 EST 2021


Yes, Chromium is expensive as it took 360 cores for 100 clients.
We had to use a test application like the one you've shared
to scale to thousands.

At the time we started running these experiments I'm not sure
your code was already available.
We've also used jitsi hammer until it was discontinued.

As long as you can send a video sample and as long as the
test app includes rate adaptation, it's almost everything
one could ask for.

Luca





On Thu, Mar 4, 2021 at 8:09 PM Sean DuBois <sean at siobud.com> wrote:

> I would really love to build a general WebRTC tester. Spinning up lots of
> Chromium instances is super expensive. Even if you do the mock webcam
> you are doing way more then needed.
>
> I created[0] which spins up many PeerConnections to load test a server.
> I think this would be a great alternative to the testing that exists
> today.
>
> * You can send pre-encoded video or RTP packets directly.
> * You can receive RTP and not pay the costs of processing
> * You get direct access to Receiver Reports, Transport Wide Congestion
>   Control and Receiver Estimated Max Bandwidth.
> * Way easier to deploy. We can build a small static binary.
>
> If anyone is interested would love to help them kick off a project. We
> can make it general enough to test Galene, Janus, Jitsi, Ion etc... If
> it gets acceptance from the greater WebRTC community it could really
> grow!
>
> [0] https://github.com/pion/rtsp-bench/blob/master/client/main.go
>
> On Tue, Mar 02, 2021 at 05:01:42PM +0100, Luca Muscariello wrote:
> > Dave,
> >
> > we have done extensive WebRTC (and several other online meeting
> > apps) testing lately and this paper
> > https://ieeexplore.ieee.org/document/9153228 reports a
> > methodology for WebRTC based on Chromium and Selenium Grid and
> > as test orchestrator Jitsi Torture.
> >
> > I would avoid feeding clients with BBB as video as it is not
> > representative of a meeting as encoders are optimized for
> > different kinds of video. There are several video samples
> > out there.
> >
> > We have scaled up clients to hundreds with this methodology.
> > The paper is short so many details have been omitted but there
> > are not many other options to do this kind of test at scale.
> >
> > Luca
> >
> >
> >
> >
> >
> >
> >
> > describes the methodology
> >
> >
> >
> > On Tue, Mar 2, 2021 at 2:15 AM Dave Taht <dave.taht at gmail.com> wrote:
> >
> > > Given that we have a worldwide network of flent servers...
> > >
> > > Given how easy galene is to hack on... and a 10 minute install...
> > >
> > > given some webrtc scripting... a few more stats... some javascript...
> > > skull sweat... funding...
> > >
> > > It seems plausible to be able to construct a suite of tests that could
> > > indeed track jitter
> > > delay and loss across the internet over webrtc. Perpetually uploading
> > > bigbuckbunny or some
> > > other suitable movie might be an option, but I have a fondness for
> > > extracting a sub 30 second segment from  "Max Headroom", which if
> > > those here have not seen it, predicted much of the fine mess we're all
> > > in now.
> > >
> > > I guess my question is mostly, is a "headless" test feasible? In the
> > > context of samknow's lack of webrtc test... lowpowered hw....
> > >
> > > --
> > > "For a successful technology, reality must take precedence over public
> > > relations, for Mother Nature cannot be fooled" - Richard Feynman
> > >
> > > dave at taht.net <Dave Täht> CTO, TekLibre, LLC Tel: 1-831-435-0729
> > > _______________________________________________
> > > Bloat mailing list
> > > Bloat at lists.bufferbloat.net
> > > https://lists.bufferbloat.net/listinfo/bloat
> > >
>
> > _______________________________________________
> > Galene mailing list -- galene at lists.galene.org
> > To unsubscribe send an email to galene-leave at lists.galene.org
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.bufferbloat.net/pipermail/bloat/attachments/20210304/3a23d59a/attachment.html>


More information about the Bloat mailing list