The jitter ring was a port of the Linux client's, but Linux runs on PipeWire
(adaptive resampling masks host↔DAC drift + a shallow buffer); AAudio hands us a
raw realtime callback and we own the buffer, so the same code crackled only on
Android. Three converging causes, all fixed:
- Heap free on the realtime audio thread every quantum (Android's Scudo free() has
unbounded tail latency → XRun → click). Decoded buffers are now recycled back to
the producer via a free-list instead of freed on the audio thread; the ring is
pre-reserved so extend() never reallocates there.
- The ring collapsed to ~15 ms on the tiny LowLatency burst and re-primed (a fresh
silence) on every single empty callback. Now ~40 ms prime / ~150 ms hard cap,
decoupled from the burst size, with de-prime hysteresis (re-prime only after a
sustained drain).
- AAudio's anti-glitch knobs were unused: prime the HW buffer above its 2-burst
default and grow it on getXRunCount(). The post-open log now reports
perf/sharing/buffer so a fall to a resampled legacy path is visible.
Steady-state audio latency ~15 → ~40 ms (within lip-sync tolerance; matches the
Moonlight/Sunshine operating point). cargo-ndk build both ABIs + fmt + clippy green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
enricobuehler
4e79e6cdad