rs-clock-hot — measured, still hint
Status
hint. Wall-clock JSONL: rs-clock-hot.jsonl. Not corpus-triaged. The 2026-10-22 corpus verdict does not cover this slug.
Measurement
Instant::now every iteration versus one sample. rustc 1.99.1, -C opt-level=3, linux x64, load 0.23. The earlier 438× pair had an after of 0.008 ms. This rerun keeps the loop with black_box. One once sample was 0.205 ms; the rest sat at 0.137–0.145 ms.
| role | case | median_ms | ops | ratio |
|---|---|---|---|---|
| after | sample_once | 0.137 | 100000 | 1 |
| before | sample_each_iter | 2.721 | 100000 | 19.899 |
After samples once and does not read the clock inside the loop. Code that needs a fresh timestamp every pass has nothing to hoist. Default stays hint. This ratio is not a general speedup.
Unblock
Do not set the default to error from this file alone. A changing input, a cold path, or another ABI can erase the difference. Corpus triage is still required before any default change.