format: a one-thread pool decodes on the caller only; keep 1 MiB scratch

Review follow-ups. With run_with_helpers a one-thread rayon pool gave each read a second core (the caller plus the worker), so --decode-threads 1 no longer matched h5py's one core per call; such a pool now adds no helper. Per-thread decode scratch is kept up to 1 MiB per buffer (was 4 MiB), bounding what never-exiting pool workers hold. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
2026-09-26 11:22:07 -05:00
parent 8295d01614
commit bf4aefcd00
2 changed files with 11 additions and 2 deletions
@@ -47,6 +47,12 @@ pub fn pool_can_parallelise() -> bool {
 /// item beyond the caller's first.
 pub(crate) fn helper_count(items: usize) -> usize {
    let pool = rayon::current_num_threads();
+    // A one-thread pool means "decode on the calling thread" (the setting
+    // benchmarks use to compare with h5py, where each call decodes on its
+    // caller): no helper, so one read never uses two cores.
+    if pool <= 1 {
+        return 0;
+    }
    let others = if rayon::current_thread_index().is_some() {
        pool.saturating_sub(1)
    } else {