1378514 - [wfh] poor vp8 simulcast performance

Status: RESOLVED INCOMPLETE

(Core :: WebRTC, defect, P1)

Description

[bbaldino]

Attachment: firefox_2_stream_sim_360p_180p.pcapng

User Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36

Steps to reproduce:

Tested simulcast for Firefox with jitsi


Actual results:

Output video framerate from firefox is very low.  

Attached a wireshark trace with firefox encoding 2 simulcast streams (180p and 360p), can see large gaps between the packet number 132 and 216, for example. They represent subsequent packets of stream 4244151133, and they are about half a second apart.  3 streams (720p, 360p, 180p) gave similar results.

This was on the official nightly build, version 56.0a1 (2017-06-29) (64-bit)

(Applying the following wireshark filter will help reduce the noise: "(((rtp && udp.dstport == 10000 && rtp.p_type == 100)))"


Expected results:

Should output 30fps for all simulcast streams.

Comment 1

[Nils Ohlmeier [:drno]]

Byron do you have an idea why the simulcast from Firefox appears to be so bursty?

Comment 2

[Byron Campen [:bwc]]

That would be a question for an expert on webrtc.org, I think.

Comment 3

[bbaldino]

Seeing what appear to be better results in 56.0a1 (2017-07-14) (64-bit), framerate on the receive side looks pretty consistent and frame output in wireshark looks pretty good.  We don't have the full rid layer parsing on the bridge yet, so I think our layer selection isn't the best at the moment, but at least the stream being forwarded has good framerate.

Comment 4

[Emma Humphries ☕️🎸🧞‍♀️✨ (she/they) [:emceeaich] (Pacific Time) use needinfo]

This is a P1 bug without an assignee. 

P1 are bugs which are being worked on for the current release cycle/iteration/sprint. 

If the bug is not assigned by Monday, 28 August, the bug's priority will be reset to '--'.

Comment 5

[Bulk Bug Changes for mreavy's org]

Mass change P1->P2 to align with new Mozilla triage process

Comment 6

[Sylvestre Ledru [:Sylvestre]]

Moving to p3 because no activity for at least 1 year(s).
See https://github.com/mozilla/bug-handling/blob/master/policy/triage-bugzilla.md#how-do-you-triage for more information

Comment 7

[Alfredo]

Any update?

Comment 8

[Patricia Lawless]

Setting this to P1 for investigation and analysis so we can determine its true impact to the user.

Comment 9

[Michael Froman [:mjf]]

Marking this resolved/incomplete after no relevant updates in 4 years with Comment 3 indicating the issue had improved with release of v56.