marfrit/libva-multiplanar
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Iteration 5 close — A+G+B+E all GREEN

Browse Source 
Heavyweight four-track iteration. All Phase 1 success criteria met:

- Track A (DEBUG sweep): ~339 lines of iter1/iter3/iter4 instrumentation
  removed across 7 fork commits. Driver builds clean; per-frame log
  noise zero (1 v4l2-request line per 2000-frame stress).

- Track G (PGO-disabled Firefox rebuild): firefox 150.0.1-1.1 built
  on boltzmann (single-pass non-PGO, ~2h27m). 68.7 MB pkg, 169 MB
  libxul (21× smaller than iter3 PGO-instrumented). 2.7× faster
  decode through firefox-fourier sandbox.

- Track E (multi-context): LAST_OUTPUT_* moved from process-global
  static to per-driver_data. Two concurrent mpv with 2s stagger
  both decode clean.

- Track B (libplacebo segfault): 35s mpv --vo=gpu, 0 segfaults
  (mpv falls through to GLES via Panfrost gracefully).

Phase 5 sonnet review came back YELLOW with 4 caveats; 3 resolved
in code (additional 107-line sweep, readback_warned removed),
1 documented as iter6+ candidate (cap_pool resolution-change race
latent under untested consumer probe patterns).

iter5-end driver sha256: 4bed52ec5d44b389. firefox-fourier 1.1
sha256: aa94c7290ee7be76. README iteration table updated.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Markus Fritsche
2026-05-05 17:39:35 +00:00
parent f36c6b040d
commit 8e6d9e6966
2 changed files with 127 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1
View File
@@ -38,6 +38,7 @@ Per the [`feedback_replicate_baseline_first.md`](../../.claude/projects/-home-mf
| 2 | Closed 2026-05-04 | "Harden the iter1 deliverable: fix the three known bugs without regressing scope." | DONE. Fix 1 (resolution-change format-cache invalidation), Fix 2 (DRM_FORMAT_MOD_INVALID conditional for non-64 pitch), Fix 3 (decoupled `cap_pool` with LRU recycling for DMA-BUF lifecycle). mpv vaapi DMA-BUF playback "smooth" per operator inspection. See `phase8_iteration2_close.md`. |
| 3 | Closed 2026-05-05 | "F+A: verify the Firefox RDD sandbox hypothesis by patched-binary, while resolving the carryover frame-11 EINVAL on the same rig." | F GREEN — patched Firefox decodes through libva without `MOZ_DISABLE_RDD_SANDBOX=1` (broker policy + seccomp ioctl `'\|'` allow + driver `select() → poll()` migration). A REPRODUCED — frame-11 EINVAL fires deterministically on a single-slice P-frame, Y2 instrumentation logs the failing controls. Track A's fix deferred to iter4. See `phase8_iteration3_close.md`. |
| 4 | Closed 2026-05-05 | "Track A solo — fix the iter1+2+3 carryover frame-11 EINVAL." | GREEN. Three correctness fixes landed (DPB `fields=FRAME_REF` + skip stale entries, fresh `request_fd` per frame, B-slice L1 reflist `.fields` copy-paste). mpv direct stress test verified 2130 BeginPictures over 90s with 0 EINVAL events of any kind — real-time HW decode through libva-v4l2-request-fourier. See `phase8_iteration4_close.md`. |
| 5 | Closed 2026-05-05 | "A+G+B+E quad: DEBUG sweep + PGO-disabled Firefox rebuild + libplacebo segfault + multi-context safety." | GREEN, all four tracks. ~339 lines of instrumentation removed (iter1+iter3+iter4 noise) — driver builds clean, per-frame log noise zero. firefox-fourier 150.0.1-1.1 rebuilt non-PGO (169 MB libxul, 21× smaller, 2.7× faster decode). LAST_OUTPUT_* moved per-driver-data. mpv `--vo=gpu` 0 segfaults. One iter6+ caveat: cap_pool resolution-change race latent under untested consumer probe patterns (Phase 5 sonnet C4). See `phase8_iteration5_close.md`. |
## Predecessor work that this campaign builds on