Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions quest/m1/drop-set.md
Original file line number Diff line number Diff line change
Expand Up @@ -288,6 +288,14 @@ case needs an update to arrive between START and the first group. Cover it
deterministically, through the track hooks rather than wire timing, when the
drop runs are reworked here.

### A covered cut is still reported

`DropCursor::cut` reports a group as cut even when a fetched copy covers it,
noted in [moq-dev/moq#7053](https://github.com/moq-dev/moq/pull/7053) and again
by [moq-dev/moq#7149](https://github.com/moq-dev/moq/pull/7149), which made a
fetched copy settle such a group. Decided 2026-10-29 (maintainer): settle it
here, where a cut run gets a reason and a covering copy can clear it.

### Cancelled fetches hold the end

Found 2026-10-28 by [moq-dev/moq#7149](https://github.com/moq-dev/moq/pull/7149):
Expand Down
1 change: 1 addition & 0 deletions quest/m2/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -252,6 +252,7 @@ lite-07; bitrate enforcement is not part of this release.
- [A malformed track says so downstream](/quest/m2/malformed-track-status.md) - subscribers and bindings see a malformed track, not INTERNAL_ERROR
- [Branch checks lint examples](/quest/m2/lint-examples.md) - `just check` runs clippy on the selected crates' examples
- [Drop kio's epoch fence](/quest/m2/crossbeam-pin-fence.md) - waiting on crossbeam#1352, then the `Read::drop` fence goes
- [A cancelled miss stops waiting](/quest/m2/fill-wait-cancel-test.md) - a test proves a relay miss waiting on its own fill ends when no reader wants it
- [Quiet logs for clean ends](/quest/m2/quiet-clean-close-logs.md) - clean probe ends and unroutable requests log at debug
- [No MOQ_* knobs outside the binaries](/quest/m2/env-knobs.md) - test, bench, and library knobs leave the `MOQ_*` prefix
- [Clean ALSA playback onset](/quest/m2/audio-alsa-onset.md) - no onset restarts or clicks over PulseAudio
Expand Down
25 changes: 25 additions & 0 deletions quest/m2/fill-wait-cancel-test.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
# [XS] A cancelled miss stops waiting for the relay's own fill

## Goal

A test proves that a relay's cache miss waiting on its subscription's own
fill stops waiting, and releases its task, once no reader wants the group or
the track is aborted.

## Plan

Found 2026-10-29 by review of [moq-dev/moq#7135](https://github.com/moq-dev/moq/pull/7135).
There, a miss for the joined group waits until the subscription's own request
has delivered or failed before sending a FETCH, and the wait also ends when no
reader wants the group or the track is aborted. That last part has no test:
the PR found no way for a test to observe a released task.

Decided 2026-10-29 (maintainer): m2. Add the smallest test-only hook that can
see the wait end (for example a counter of live waits in
`rs/moq-net/src/ietf/subscriber.rs`, compiled only for tests), then cover a
cancelled reader and an aborted track. Rejected the same day: a time limit
after which the relay FETCHes the joined group's start anyway, since losing
that group is the documented contract and a late FETCH risks the duplicate
group #7135 fixed.

Public API: none. Wire: none.
6 changes: 6 additions & 0 deletions quest/m2/perf/single-delivery-write.md
Original file line number Diff line number Diff line change
Expand Up @@ -22,4 +22,10 @@ lock-free path here, in m2.
- Keep the shared reservation and canonical-content rules #6922 added.
- A measured no-win abandons the quest.

Also in scope (decided 2026-10-29, from [moq-dev/moq#7139](https://github.com/moq-dev/moq/pull/7139)):
after #7139, batched `write_frames` still costs about 20% more instructions per
frame than before #6922 (459 against 380; 6 to 12% wall clock), from the same
canonical-storage design. Measure the `group_write_frames/batch32/*` cases
beside lite FETCH, and fix both paths together where they share the cost.

Public API: none. Wire: none.
Loading