hl-valdemar/terebi
1
0
Fork 0
Code Issues Pull Requests Actions Packages Releases Wiki Activity

perf: prefer VideoToolbox decoding with software fallback

Browse Source
This commit is contained in:
Valdemar Høgsvig Lorenzen
2026-10-17 01:11:58 +02:00
parent 599c1492ee
commit fcad96de62
8 changed files with 513 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files
TODO.md
+4 -1
View File
@@ -8,7 +8,10 @@
- [x] expand Cast H.264/AAC remux coverage with keyframe-aligned segments; preserve seek accuracy, timestamps and receiver compatibility
- [x] reuse decoder/encoder state during sequential Cast playback; reset on random seeks and preserve independent keyframes and AAC continuity
- `.build/cast-media-check --codec-work`: 60s of 720p/30 B-frame video plus 44.1kHz PCM→AAC over loopback HTTP; three paired runs reduced median relay CPU from 3.56s to 2.58s (27%) and generation time from 4.97s to 4.43s (11%); physical-receiver playback still needs manual verification
- [ ] evaluate VideoToolbox hardware video decoding for native and Cast playback; retain software fallback for unsupported formats
- [x] evaluate VideoToolbox hardware video decoding for native and Cast playback; retain software fallback for unsupported formats
- M4, three paired 12s/720p/30 MP4 runs: H.264/HEVC/VP9 native decode process CPU fell 77/88/92%; Cast relay process CPU fell 48/58/68%, with generation 2–7% slower. Prefer these measured codecs; AV1 keeps dav1d. Unpaced native decoding is slower; H.264 seek preview rose from 1.8ms to 4.1ms. These are process CPU measurements, not energy measurements.
- `make check-video-decoding` covers native Metal upload, mapped-frame lifetime, exact seek/step/EOF, dependent-packet seek fallback, Cast independent IDRs/AAC, and unsupported codecs; `video-decoding-software-check` and `cast-media-software-check` provide matched baselines. Unsafe seek starts use software decoding (until reopen for native playback).
- Existing Cast millisecond-timestamp limiting drops VP9 MKV frames in the software baseline; a direct relay comparison confirmed VideoToolbox preserves the same output PTS/counts. This evaluation does not change that limiter.
- [ ] benchmark cold start, cached/uncached seeks and sustained playback separately to prioritize the actual bottlenecks
- do not enable Miruro HTTP persistence without preserving origin/header checks, or increase caches/shorten Cast segments without measuring the memory/request/codec tradeoffs
- [ ] add playlist support