a65cb291e8
* test(#4105): guard the #3889 hang fixture — must genuinely hang by itself and self-terminate RED at this sha: against the current never-settling-promise body the guard fails on the matrix line (Node 24: the unheld promise never self-terminates, ceiling expires) and off it (v22-class runtimes: the child exits rc=1 after ~60ms, never reaching the still-hanging checkpoint). Same shape as the #4104 self-exit regression: spawn the exact served body, observe liveness past the chunk bound and natural exit — no elapsed-value assertions. * fix(#4105): park the #3889 hang fixture on a settling timer The never-settling promise held no libuv handle, so the hang T1/T4 rely on was a property of the runtime's test-runner shutdown behavior, not of the fixture: v24/v26 happen to hold the loop open; v22-class runtimes exit rc=1 after ~60ms (# cancelled 1), so the chunk never reaches the timeout path and the two timeout assertions assert nothing. Park on a settling 10s timer (the #4104 idiom): an explicit handle makes the hang the fixture's on every Node line, 10s >> the 2000ms chunk bound (margin asserted structurally in the #4105 guard), ~0% CPU while parked, and guaranteed self-termination if a kill orphans it. Behavior on the Node 24 matrix line is unchanged — the chunk is still killed by the harness timeout (~2006ms) with the identical diagnostic. * test(#4105): drive the fixture guard off the child's exit event + runner timeout Review-driven restructure (Memtrace flaky_test_fixed_sleep on the 200ms poll interval): the guard now waits on the child's natural 'exit' event — no polling interval, no hand-rolled watchdog setTimeout. The immortal-body bound is the node:test per-test { timeout: 2 * HANG_PARK_MS } backstop, the health-validation #663 house pattern and the no-elapsed-assertion-compliant form. t.after still reaps the child on every path. Same failing-first arms: still-hanging checkpoint, natural-exit (no signal), exit code 0. * changeset(#4105) * changeset(#4105): backfill PR number --------- Co-authored-by: sim <sim@local>
950 B
type, pr
| type | pr |
|---|---|
| Fixed | 4349 |
The #3889 chunk-timeout tests now keep testing the timeout diagnostic regardless of the Node line's test-runner shutdown behavior — the hang fixture returned a never-settling promise that holds no event-loop handle, so whether the chunk actually hung (and got killed by the per-chunk timeout, exercising the diagnostic) was decided by the runtime: on Node 24/26 the runner happens to hold the loop open, but on other lines the child exits on its own in ~60ms and the two timeout assertions silently assert nothing, failing later as a confusing 72ms chunk failure. The fixture now parks on a settling 10s timer (the #4104 idiom): the hang is a property of the fixture on every runtime, it stays ~0% CPU while parked, and it self-terminates if orphaned; a new regression guard pins that property (still hanging past the chunk bound, natural exit). Behavior on Node 24 (the CI/bench matrix line) is unchanged. (#4105)