cs-file-read-hot — measured, still hint
Status
hint. Wall-clock JSONL: cs-file-read-hot.jsonl. Not corpus-triaged. The 2026-10-22 corpus verdict does not cover this slug.
Measurement
File.ReadAllText of one one-byte file, 2000 times, versus reading once. .NET 10.0.13, linux x64, load 0.07. One read_once sample was 1.740 ms; the median is the 0.015–0.026 ms cluster. The earlier .NET 8 pair was about 1560×.
| role | case | median_ms | ops | ratio |
|---|---|---|---|---|
| after | read_once | 0.0178 | 2000 | 1 |
| before | read_each_iter | 6.0142 | 2000 | 337.876 |
The bench reopens one one-byte file. A path that changes every iteration cannot be hoisted; the measured cost is the open and read. 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.