Commit Graph
5 Commits
Author SHA1 Message Date
MattJackson c51b3181f2 mux: pipelined PES highway — read+decrypt → demux → parse on 3 threads
Introduces the freemkv mux throughput highway: a three-stage thread
pipeline that replaces the inline single-thread read path for any
file-backed source (ISO and m2ts file URLs both route through it).

  Thread A: read + decrypt  (PrefetchedSectorSource / BytePrefetcher)
  Thread B: M2TS demux      (DemuxThread)
  Thread C: codec parse     (PipelinedPesStream, on caller thread)

Each handoff uses a bounded crossbeam channel with a recycled buffer
pool — no allocations or memcpys in the steady-state hot loop.

Component map:

* io/byte_prefetcher.rs (new) — std::io::Read producer thread with
  recycled Vec<u8> pool. Pairs with PrefetchedSectorSource (sector
  side) so demux_thread::spawn_zero_copy can wire either upstream.
* sector/prefetched.rs — recycled buffer pool added; into_channels()
  peels off the rx/recycle_tx/shell triple for zero-copy demux.
* mux/demux_thread.rs (new) — owns the TsDemuxer/PsDemuxer, runs
  feed() on its thread, ships Vec<PesPacket> batches.
* mux/pipelined_stream.rs (new) — the read-side Stream impl. Pulls
  packets from the demux thread and runs codec parse on the caller.
* mux/resolve.rs — build_iso_pipeline (public) / build_m2ts_pipeline
  (private) assemble the three stages; iso:// and m2ts:// both
  return PipelinedPesStream.
* mux/m2ts.rs — collapsed to a write-only sink (Mode::Read deleted;
  the read direction lives on the highway now).
* mux/codec/h264.rs — find_start_code uses memchr SIMD memmem::find.
* mux/codec/hevc.rs — tightened frame_data initial capacity.
* mux/ts.rs — boundary-packet handling avoids the per-batch 16 MiB
  remainder copy; PesAssembler starts at 16 KiB to dodge the 64-page
  first-touch fault tax that the previous 256 KiB pre-alloc paid on
  every PES boundary.
* mux/disc.rs — gains DiscStream::new_pipeline + read_pipeline as
  the legacy autorip ingress (drive + multipass paths still need
  on_event / skip_errors before they migrate to the highway).
* io/file_sector_source/* — per-OS prefetch() syscall hook
  (Linux readahead, macOS F_RDADVISE, Windows/other no-op).
* decrypt.rs — FREEMKV_DECRYPT_THREADS renamed to FREEMKV_THREADS;
  pool sized to all cores by default.

Measured on rip1 testbed (Civil War UHD, 62 GiB ISO → null://):

  60 → 322 MB/s warm cache (old new_pipeline path)
  60 → 660 MB/s warm cache (highway path, this commit)
  60 → 126 MB/s sustained disk-bound

The IsoSectorReader baseline reader was deleted in favour of
FileSectorSource so the freemkv CLI and autorip exercise the same
read path.
2026-05-19 13:35:32 -07:00
MattJackson 44e2c64d7e 0.18 round 2 (Halt threading): DiscStream accepts Halt at construction
Adds a Halt field to DiscStream, populated via the new
`with_halt(halt)` builder. The internal recovery / fill_extents
loops check `halt.is_cancelled()` directly. The existing
`set_halt(Arc<AtomicBool>)` method stays through the deprecation
window for callers (autorip mux) that haven't migrated; marked
#[deprecated] with a pointer to the constructor-time path.

Both signals are unified inside DiscStream: either Halt or the
legacy Arc<AtomicBool> triggers cancellation, so callers can mix
during the deprecation window without breaking stop behaviour.

See (internal)/memory/0_18_redesign.md and
0_18_round3_migration_audit.md.

Single contributor: MattJackson.
2026-05-09 10:58:54 -07:00
MattJackson bbfb887a35 0.18 round 1+2 integration fixes
Two clippy issues surfaced when round 1 polish + round 2 FrameSink
migrations both landed on libfreemkv main:

- src/halt.rs: clippy::new_without_default fires when a public new()
  exists without Default. The polish pass dropped the derive thinking
  it was redundant — clippy disagrees, so add a manual impl that
  forwards to new(). Doc-comment notes why both exist.

- src/disc/read_error.rs:372: pre-existing
  assert_eq!(.., true) trips clippy::bool_assert_comparison. Pre-0.18
  precommits passed because that lint sat outside the gate; the
  round-2 commits brought enough new clippy surface that it now
  shows up. Trivial cleanup: assert!(...) instead of assert_eq!.

Single contributor: MattJackson.
2026-05-09 10:00:06 -07:00
MattJackson 925c30686b 0.18 round 1 polish: address libfreemkv code-review findings
Applies must-fix + in-scope should-fix items from the round-1 code
review:

- M1: FileSectorSource::open takes &Path (was &str — non-UTF-8 panic)
- M2: drop FileSectorSource's BufReader (defeated by absolute seeks)
- M3: WritebackFile Drop impl finalises the writeback pipeline
- M4: Pipeline::finish preserves panic payload in error message
- M5: pes::Stream is left without a : Send supertrait — concrete
  in-tree impls (MkvStream, M2tsStream) hold Box<dyn Read> /
  Box<dyn Write> trait objects that aren't Send, so the simple
  trait tightening would cascade into a wider Send audit. Per the
  review's escape clause the FrameSource blanket impl keeps its
  T: Send bound and the constraint is documented loudly there.
- S6: document Pipeline::send post-Flow::Stop semantics
- S9: truncate stale Stream docs (E9001/E9000 was runtime-only)
- S10: document WritebackPipeline.fd lifetime invariant
- S11: pub use pes::Stream as PesStream to disambiguate from
  disc::Stream codec enum at crate root
- S12: rename DEFAULT_DEPTH → DEFAULT_PIPELINE_DEPTH; add
  WRITE_THROUGH_DEPTH constant
- N14: drop Halt's Default derive (redundant with Halt::new)
- N17: Pipeline::spawn propagates thread-spawn error instead of expect
- N19: deprecation since = "0.18.0" (was "0.18.0-dev", non-conventional)
- N21: rename Apply enum to Flow

Deferred to follow-up commits: SectorReader/SectorSource competition
(migration commit), WritebackFile::create/open orphans (migration
commit), AACS round-trip test (design doc defers), various nits.

See (internal)/memory/0_18_redesign.md.

Single contributor: MattJackson.
2026-05-09 09:52:25 -07:00
MattJackson 6e17ef0859 0.18 primitive: crate::halt::Halt cancellation token
One-bit cooperative cancellation flag. Replaces ad-hoc Arc<AtomicBool>
patterns scattered across libfreemkv (DiscStream::set_halt) and the
HALT_FLAGS global registry in autorip. See
(internal)/memory/0_18_redesign.md.

Single contributor: MattJackson (no attribution trailers).
2026-05-09 08:50:13 -07:00