Track: WebRTC and Real-Time Applications |
| SFU Cascading with Janus |
| Cascaded conferencing has been around for quite some time already, especially in the context of audio mixing. The main idea at the time was linking separate conference bridges somehow, in particular at the mixing level, so that they could cooperate and interact to help scale conference rooms. While the world of communications has changed considerably since then, the same fundamental concepts can still help WebRTC applications, even when using SFUs rather than mixers. In fact, cascading SFU instances can help distributing injected streams across multiple WebRTC servers, which can be useful in different ways: it can help scaling the distribution of streams to a wide audience (e.g., large webinars), making it easier for users to connect to the server closest to them even when it's not the one hosting the room (e.g., geodistribution), or more in general help implementing applications that may benefit from taking advantage of more than one server at the same time, whether those applications are conference related or not. This talk will present the work that was made in that direction for the open source Janus WebRTC Server, starting from how such a functionality was handled up to now (e.g., to facilitate large scenarios like IETF meetings), and how that had to be changed to acconodate support for PeerConnections with multiple audio and video streams. |
|
| Presentation Video |
