test(py): detect a held GIL, and errors h5py does not raise

test_threads_read_the_same_file passed with the GIL held. The new
test_reads_release_the_gil measures the longest stall of a spinning
Python thread while another reads: with py.detach removed from the read
it stalled 0.062 s of a 0.064 s read and failed; with it, about 3 ms.
test_errors_match_h5py now compares the result whenever h5py reads the
key, instead of only checking that we raise when h5py raises, over a
longer key list.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

crates/clawhdf5-py/tests/test_read_vs_h5py.py

@@ -266,7 +266,10 @@ def keys_for(shape):
 # checked against the values written instead (test_vlen_big_endian).
 H5PY_MISREADS = {"vlen/f8_be"}
 
-ERROR_KEYS_1D = [slice(None, None, -1), 10**6, -(10**6), None, (0, 0, 0, 0, 0), [3, 1], (Ellipsis, Ellipsis), 1.5, "nope"]
+ERROR_KEYS_1D = [
+    slice(None, None, -1), 10**6, -(10**6), None, (0, 0, 0, 0, 0), [3, 1], (Ellipsis, Ellipsis), 1.5, "nope",
+    np.array(1.0), np.array(True), np.array(10**6), [0, 0], [], (), Ellipsis, (0,), [-1], np.array([1, 2]),
+]
 
 
 # ---------------------------------------------------------------------------
@@ -322,12 +325,13 @@ def test_errors_match_h5py(h5py, pair):
     for name in ["num/le_i4_1d", "num/be_f8_2d_gzip", "str/vlen", "num/scalar_f8"]:
         for key in ERROR_KEYS_1D:
             try:
-                theirs[name][key]
+                expected = theirs[name][key]
             except Exception as e:  # noqa: BLE001
                 with pytest.raises(type(e)):
                     ours[name][key]
             else:
-                pass  # valid for this shape; covered by the value test
+                # h5py reads it, so must we (and the same values).
+                assert_same(ours[name][key], expected, f"{name}[{key!r}]")
 
 
 def test_compound_fields_match_h5py(pair):
@@ -454,8 +458,7 @@ def test_only_the_selected_chunks_are_read(h5py, tmp_path):
 
 
 def test_threads_read_the_same_file(pair):
-    """Reads from many threads at once (the GIL is released during each
-    read) return exactly what h5py returns."""
+    """Reads from many threads at once return exactly what h5py returns."""
     ours, theirs, _ = pair
     names = ["num/le_f8_2d_gzip", "num/i4_3d_shuffle", "str/vlen_2d_gzip", "cmp/padded_chunked", "num/be_i8_1d"]
     expected = {n: theirs[n][()] for n in names}
@@ -477,6 +480,55 @@ def test_threads_read_the_same_file(pair):
     assert not errors, errors[:3]
 
 
+def test_reads_release_the_gil(h5py, tmp_path):
+    """While one thread is inside a long read, another Python thread keeps
+    running. With the GIL held for the read, the other thread would stall
+    for the whole read; the test measures its longest stall."""
+    import sys
+    import time
+
+    path = str(tmp_path / "gil.h5")
+    data = np.arange(2048 * 4096, dtype="<f4").reshape(2048, 4096)
+    with h5py.File(path, "w") as f:
+        f.create_dataset("d", data=data, chunks=(64, 4096), compression="gzip", compression_opts=1)
+    ds = clawhdf5.File(path, "r")["d"]
+    key = (slice(0, 1000), slice(None))  # under half: the uncached selection path
+    t0 = time.perf_counter()
+    ds[key]
+    one_read = time.perf_counter() - t0
+    assert one_read > 0.03, f"a read took only {one_read:.3f} s; too short to measure"
+
+    old = sys.getswitchinterval()
+    sys.setswitchinterval(0.001)
+    stop = threading.Event()
+    gaps = []
+
+    def spin():
+        last = time.perf_counter()
+        worst = 0.0
+        while not stop.is_set():
+            now = time.perf_counter()
+            worst = max(worst, now - last)
+            last = now
+        gaps.append(worst)
+
+    try:
+        t = threading.Thread(target=spin)
+        t.start()
+        time.sleep(0.01)
+        t0 = time.perf_counter()
+        for _ in range(2):
+            ds[key]
+        reading = time.perf_counter() - t0
+        stop.set()
+        t.join()
+    finally:
+        sys.setswitchinterval(old)
+    np.testing.assert_array_equal(ds[key], data[:1000])
+    # Held, the spinner would stall for about one read.
+    assert gaps[0] < one_read / 3, f"spinner stalled {gaps[0]:.3f} s during reads of {one_read:.3f} s ({reading:.3f} s)"
+
+
 def _v4_index_fixture(h5py, path):
     """One 2-D dataset per v4 chunk index (HDF5 1.10+ layout, libver='latest')."""
     data = (np.arange(37 * 23, dtype="<i4") * 7 - 1000).reshape(37, 23)