Files
fegger 6516b45b02 perf(codec): pass YUV through to the renderer and use slice threading
The receiver decoded H.264 to YUV420P, converted it to RGBA via a
CPU-intensive swscale pass, then uploaded 4 bytes/pixel to an SDL
texture — only for the GPU to convert back to RGB during rendering.
This eliminated the swscale pass entirely (40-60% of receiver CPU at
1080p) and cut the texture upload by 62%.

- DecodedFrame now carries three YUV420P planes with their strides
  instead of a packed RGBA buffer; the decoder copies the planes
  directly from the AVFrame (zero conversion for the common software
  path). Non-YUV420P decoder output (e.g. NV12 from v4l2m2m) is
  converted once to YUV420P.
- The SDL renderer uploads via SDL_UpdateYUVTexture with
  SDL_PIXELFORMAT_IYUV; the GPU does the YUV→RGB conversion during
  rendering.
- Decoder threading: slice-level with 4 threads (parallelizes within a
  frame, no added latency), not frame-level (which buffers multiple
  frames — the initial thread_count=0 broke the loopback test because
  the H.264 decoder introduced a multi-frame delay before producing
  output).
- The round-trip test converts decoded YUV back to RGBA for pixel
  comparison via a test-local swscale call (the pipeline itself never
  converts).

meson test 5/5 in both configurations, valgrind clean.
2026-09-09 09:45:22 +02:00

171 lines
6.1 KiB
C++

// Phase 5 integration test: the local UDP sender -> receiver loopback without
// the interactive parts. Synthetic frames go through the real chain —
// encode, RTP packetization, a localhost UDP socket, depacketization, and
// decode (with in-band SPS/PPS, since there is no signaling channel).
#include "screencast/codec/decoder.h"
#include "screencast/codec/encoder.h"
#include "screencast/network/h264_packetizer.h"
#include "screencast/network/transport.h"
#include <atomic>
#include <chrono>
#include <cstdint>
#include <cstdio>
#include <cstdlib>
#include <memory>
#include <thread>
#include <vector>
namespace {
[[noreturn]] void fail(const char* what) {
std::fprintf(stderr, "test_loopback: FAIL: %s\n", what);
std::abort();
}
void check(bool condition, const char* what) {
if (!condition) {
fail(what);
}
}
template <typename T> void expect_result(const char* what, const sc::CodecResult<T>& result) {
if (sc::is_codec_error(result)) {
std::fprintf(stderr, "test_loopback: FAIL: %s: %s\n", what, sc::codec_error(result).message.c_str());
std::abort();
}
}
constexpr int kWidth = 64;
constexpr int kHeight = 64;
constexpr int kFrameCount = 10;
constexpr uint64_t kNsPerFrame = 40'000'000; // 25 fps
sc::CapturedFrame make_frame(uint32_t index) {
sc::CapturedFrame frame;
frame.width = kWidth;
frame.height = kHeight;
frame.timestamp_ns = static_cast<uint64_t>(index) * kNsPerFrame;
frame.pixel_format = sc::PixelFormat::Rgba;
frame.stride = kWidth * 4;
frame.pixels.resize(static_cast<std::size_t>(kWidth) * kHeight * 4);
auto* pixels = reinterpret_cast<std::uint8_t*>(frame.pixels.data());
for (int y = 0; y < kHeight; ++y) {
for (int x = 0; x < kWidth; ++x) {
const std::size_t offset = (static_cast<std::size_t>(y) * kWidth + x) * 4;
pixels[offset + 0] = static_cast<std::uint8_t>((x + static_cast<int>(index) * 4) & 0xFF);
pixels[offset + 1] = static_cast<std::uint8_t>((y + static_cast<int>(index) * 2) & 0xFF);
pixels[offset + 2] = static_cast<std::uint8_t>(((x ^ y) + static_cast<int>(index)) & 0xFF);
pixels[offset + 3] = 0xFF;
}
}
return frame;
}
// Receiver state driven entirely by the transport's receive thread.
struct ReceiverSink {
sc::H264Depacketizer depacketizer;
std::unique_ptr<sc::Decoder> decoder;
std::atomic<int> decoded_frames{0};
bool saw_frame = false;
int last_width = 0;
int last_height = 0;
void on_packet(sc::RtpPacket packet) {
const sc::DepacketizeResult result = depacketizer.depacketize(packet);
if (!result.access_unit.has_value()) {
return;
}
sc::EncodedFrame encoded;
encoded.data = std::move(*result.access_unit);
encoded.rtp_timestamp = packet.header.timestamp;
auto decoded_result = decoder->decode(encoded);
if (sc::is_codec_error(decoded_result)) {
return;
}
for (const sc::DecodedFrame& decoded : sc::codec_value(decoded_result)) {
last_width = decoded.width;
last_height = decoded.height;
saw_frame = decoded.width > 0 && !decoded.plane_y.empty();
decoded_frames.fetch_add(1);
}
}
};
} // namespace
int main() {
// Encoder on the sender side.
sc::EncoderConfig encoder_config;
encoder_config.codec_name = "h264";
encoder_config.width = kWidth;
encoder_config.height = kHeight;
encoder_config.frame_rate_num = 25;
encoder_config.frame_rate_den = 1;
encoder_config.bitrate_kbps = 2000;
auto encoder_result = sc::EncoderFactory::create(encoder_config);
expect_result("encoder create", encoder_result);
auto encoder = std::move(sc::codec_value(encoder_result));
// The receiver decodes purely from the bitstream (in-band SPS/PPS).
sc::DecoderConfig decoder_config;
decoder_config.codec_name = "h264";
auto decoder_result = sc::DecoderFactory::create(decoder_config);
expect_result("decoder create", decoder_result);
ReceiverSink sink;
sink.decoder = std::move(sc::codec_value(decoder_result));
// Bind the receiver to the first free port in a small range.
auto receiver_transport = sc::RtpTransportFactory::create();
uint16_t bound_port = 0;
for (uint16_t port = 45904; port < 45934; ++port) {
if (receiver_transport->start(sc::Endpoint{"0.0.0.0", port},
[&sink](sc::RtpPacket packet) { sink.on_packet(std::move(packet)); })) {
bound_port = port;
break;
}
}
check(bound_port != 0, "receiver transport bound");
// Sender transport: no bind (OS picks the source port), peer is loopback.
auto sender_transport = sc::RtpTransportFactory::create();
check(sender_transport->start(sc::Endpoint{"", 0}, [](sc::RtpPacket) {}), "sender transport started");
sender_transport->set_peer(sc::Endpoint{"127.0.0.1", bound_port});
sc::H264Packetizer packetizer;
for (uint32_t index = 0; index < kFrameCount; ++index) {
const sc::CapturedFrame frame = make_frame(index);
auto encoded_result = encoder->encode(frame);
expect_result("encode", encoded_result);
for (const sc::EncodedFrame& encoded : sc::codec_value(encoded_result)) {
for (const sc::RtpPacket& packet : packetizer.packetize(encoded)) {
check(sender_transport->send(packet), "send packet");
}
}
}
// Wait (bounded) for the receiver to decode the frames.
const auto deadline = std::chrono::steady_clock::now() + std::chrono::seconds(5);
while (sink.decoded_frames.load() < kFrameCount && std::chrono::steady_clock::now() < deadline) {
std::this_thread::sleep_for(std::chrono::milliseconds(10));
}
check(sink.decoded_frames.load() >= kFrameCount / 2, "most frames decoded");
check(sink.saw_frame, "decoded frame has pixels");
check(sink.last_width == kWidth && sink.last_height == kHeight, "decoded dimensions");
sender_transport->stop();
receiver_transport->stop();
std::printf("test_loopback: %d frames decoded over UDP loopback\n", sink.decoded_frames.load());
return 0;
}