PeriodicBlockStepper.step: mid-batch launch failure test; async-error docstring note

Review follow-up (non-blocking items): a launch failure on the second of
three steps fails closed without the batch wait, keeps step_count at its
entry value and blocks download; the docstring now states, as for
FixedPatchStepper, that async faults surface at the single wait.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Claude
2026-10-21 01:31:09 +00:00
co-authored by Claude Opus 5.5
parent 3648ad70ef
commit f3f1e3d588
2 changed files with 24 additions and 2 deletions
+5 -2
View File
@@ -207,8 +207,11 @@ class PeriodicBlockStepper:
"""Advance n steps: halo refresh, then core pull/collide, per step.
All n steps are enqueued in order on the one stream and the host waits
once before returning (same launches and bits as n step(1) calls). On a
failure the instance is failed and step_count keeps its entry value.
once before returning (same launches and bits as n step(1) calls).
Asynchronous device errors surface at that single wait, so they are not
attributed to the step that caused them; call step(1) repeatedly to
localize one. On any failure the instance is failed and step_count keeps
its entry value.
"""
if isinstance(n, bool) or not isinstance(n, Integral) or n < 0:
raise ValueError("n must be a nonnegative integer")
+19
View File
@@ -78,6 +78,25 @@ class BlockStepSync(unittest.TestCase):
run.step(2)
self.assertEqual((run.step_count, run._status), (1, "failed"))
def test_launch_failure_mid_batch_fails_closed_without_waiting(self):
run, log = backend()
calls = []
step = run._step
def failing(*args, **kwargs):
calls.append(1)
if len(calls) == 2:
raise RuntimeError("launch failure")
return step(*args, **kwargs)
run._step = failing
with self.assertRaises(RuntimeError):
run.step(3)
self.assertNotIn("sync", [name for name, _ in log])
self.assertEqual((run.step_count, run._status), (0, "failed"))
with self.assertRaises(RuntimeError):
run.download()
if __name__ == "__main__":
unittest.main()