* sfu/buffer: parse the dependency descriptor without allocating
Every VP9 and AV1 SVC packet allocated six objects in the dependency
descriptor parse: the descriptor, a clone of the frame template with
its three slices, a resolution copy, and a frame entity that took the
address of a parameter.
The pooled ExtDependencyDescriptor now owns the storage for the
descriptor, the template and the resolution, with fixed arrays for the
template's slices. The reader copies the matching template into that
storage.
Delta frame parse: 6 allocs, 176 B, 174 ns -> 0 allocs, 0 B, 122 ns.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* sfu/dd: never copy a parsed frame into a structure template
A caller can hand Unmarshal a descriptor whose FrameDependencies points
at one of the structure's templates. Copying the packet's custom fields
into it would change the template for every later packet, so the reader
allocates a fresh template in that case.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
* sfu/buffer: stop allocating per ingested packet
Buffer.Write allocated six objects for every RTP packet. They were
the parsed rtp.Packet, a copy of it in patchExtPacket, and the flow
state, whose address two rare log calls took. The rest were an
AbsCaptureTime, present on about one packet per second, and the
extension slice that pion grows with append.
Unmarshal into a pooled scratch packet. Give ExtPacket its own backing
rtp.Packet and an [8]rtp.Extension array, and copy the header into
them. Patch the payload in place. If the abs-capture-time extension is
present, parse it. Log a copy of the flow state.
Per packet, Write plus ReadExtended. Opus: 6 allocs, 448 B -> 0.
VP8: 6 allocs, 416 B -> 1 alloc, 32 B. Opus 240 -> 142 ns, VP8 269 -> 204 ns.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* sfu/buffer: point extension payloads at the bucket copy on read
Queued ExtPackets kept extension payload slices into the write input,
which the transport reuses for the next packet. ReadExtended now parses
the header again from the bucket copy, so extensions and CSRCs point
into RawPacket like the payload does.
The test writes every packet through one input buffer and checks the
audio level of each packet read back.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* sfu/buffer: test that a dropped padding packet keeps the shifted sequence number on read
The bucket stores the shifted number, so re-parsing the header on read
returns it. This test guards that.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
pion no longer starts the repair stream reader when a custom BufferFactory
is set, so the mid/rid/rsid extensions were never observed and simulcast RTX
streams were never paired with their primary streams.
Extract the extensions on the buffer write path instead. Migrated publishers
send no extensions at all, so pair those from SimTracks.
Adds an integration test covering both paths, and moves the vnet setup it
shares with the downtrack test into pkg/testutils/vnettest.
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Flush the downtrack sequencer on stream restart (Resync, ReceiverRestart,
codec change) so NACK retransmissions can't use metadata that no longer
matches the resynced bucket. Add a defensive bounds guard on the RTX and
forward payload slicing.
Cap the PacketHistory and FrameIntegrityChecker catch-up loops to the ring
size so a large sequence/frame-number jump can't drive a big per-packet
iteration count.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Fix skipped packets accounting.
No need to copy unskipped packet RTP header to skipped packet.
That was causing padding bytes to be counted.
Also use Header.PaddingSize as base PaddingSize is deprecated.
* PaddingSize in header in utils
Reverting
- https://github.com/livekit/livekit/pull/4521
- https://github.com/livekit/livekit/pull/4525
There are TWCC feedback packets that are larger than MTU. Seems to
happen under a couple of conditions
1. Bad client data, i. e. severely out-of-order packets, bad sequence
numbers, etc.
2. On an ICE restart - this is rare, but it seemed to be flaky network
with some packets arriving and some not and causing a lot of gaps.
Either case, not much to do. If fargmentation/re-assembly back to
publisher works, the feedback will make it through. If not, feedbacks
will be missed and clients have to work with some missing data which is
not unexpected and the protocol is designed to handle.
However, filed pion/interceptor issue just in case - https://github.com/pion/interceptor/issues/416
Not a major issue, but just avoiding duplicate creation of NACK module.
RTCP feedback of `nack` and `nack pli` end up getting treated as `nack`
and was double creating.
* Log large packets receive/send.
Seeing cases of servers reporting need for segmentation/re-assembly of
packets. So, logging packet receive/send for RTP/RTCP to check if
anything is seeing more than 1400 byte packets.
* log downtrack RTCP too
* Add debug for receiver restart.
Have a suspicion that something is deadlocking between restart receiver
and buffer bind during replay. Adding debug to get a better picture of
state of receiver restart.
* consistent logging
* Set up audio config in audio level module when config is updated.
It is possible to get audio config after bind (bind is where the audio
level module is created) for remote tracks. So, split out setting audio
level config in audio level module and invoke it when config is updated.
* coderabbit review
* prevent divide-by-0
* not active before config
* Reducing some info level logs.
Also, relaxing the check for runaway RTCP receiver report to allow for
rollover to catch up if it is not too far away.
* set logger
With audio simulcast codecs, it is possible that the clock rate of the
primary codec is different from the secondary codec. If a subscriber
binds to the secondary codec, the clock rate should be set correctly. Do
it at bind time.
* Do not restart receiver on codec change mid-session.
This is not supported and was an erroneous change during the
receiver_base/buffer_base + RTP stream restart consolidation. Also make
the codec munger creation more resilient.
* fix test
In some paths, it is better to preserve pre-recorded time. So, make the
base implementations preserve the RTCP Sender Report receive time.
Also, add a method to enable forwarding packet arrival time. Could be
used across relay.
* Rework receiver restart.
- Protect against concurrent restarts
- Clean up and consolidate code around restarts
- Use `RestartStream` of buffer rather than creating new buffers.
* fix test
* Minor refactor in buffer base and audio level
- Make a function for `restartStream`. Will be useful
when external signal needs to restart a stream. Also restart all the
bits (audio level, dd parser and frame rate calculator)
- make an audio level mode with RTP timestamp so that some state can be
moved out of buffer base
* clean up
* log restart
This is not all of it as it is not possible (or at least I do not know
of a way) to get all suggestions for a repo/project. Did this via loop
searching mainly and taking the modernize suggestions.
* Return extended sequence number only and not packet.
Callers need only the extended sequence number.
Extended packet could get release if the forwarder processes it before
caller accesses it causing a data race.
* grow bucket in a go routine
* Refactor receiver and buffer into Base and higher layer.
To be able to share code/functionality with relay.
* WIP
* WIP
* WIP
* WIP
* WIP
* WIP
* WIP
* WIP
* clean up
* deps
* fix test
* fix test
* Store buffer after creating it.
Also changing signature of creator function as it could call TrackInfo()
and get into a deadlock.
* fix double unlock
* add some more debug logging
* Refactor receiver and buffer into Base and higher layer.
To be able to share code/functionality with relay.
* WIP
* WIP
* WIP
* WIP
* WIP
* WIP
* WIP
* WIP
* clean up
* deps
* fix test
* fix test
