lifecycle: Simulation jet update failure fails the instance like FixedPatchStepper
Simulation.set_jet_amplitude validated before upload and committed host state after it, but after an uncertain device write nothing stopped reuse. Record the failure in Simulation._failed and refuse every public device call except close() (FixedPatchStepper already uses status 'failed'). Invalid input stays side-effect free and retryable. Adds host fault tests for both owners and states the rule in docs/lifecycle.md. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
2b10b01c49
commit
7afb5addde
3 files changed
+154
-5
No files matched your search
@@ -0,0 +1,124 @@
|
||||
"""Jet amplitude update failure contract (host doubles only, no CUDA numerics).
|
||||
|
||||
Both owners validate before any device write, commit host state only after the
|
||||
upload returns, and refuse every later call except close() after an uncertain
|
||||
device write.
|
||||
"""
|
||||
from types import SimpleNamespace
|
||||
|
||||
import numpy as np
|
||||
import pytest
|
||||
|
||||
pytest.importorskip("pycuda.driver")
|
||||
from CelerisLab.body.jets import Jet, Radial, Sector
|
||||
from tests.unit.test_pinned_body_remap import ready
|
||||
from tests.unit.test_simulation_lifecycle import make_simulation
|
||||
|
||||
BAD = (float("nan"), float("inf"), 1.)
|
||||
|
||||
|
||||
class Curved:
|
||||
"""Records uploads; ``fail`` raises once the write was attempted."""
|
||||
def __init__(self):
|
||||
self.writes, self.fail = [], False
|
||||
|
||||
def set_jet_amplitude(self, index, amplitude, stream):
|
||||
self.writes.append((index, amplitude))
|
||||
if self.fail:
|
||||
raise RuntimeError("upload failed")
|
||||
|
||||
|
||||
def simulation(monkeypatch):
|
||||
sim = make_simulation(monkeypatch)
|
||||
jet = Jet(Sector((6., 5.), 0., .5, 4.), Radial((6., 5.)), "uniform", 1e-3)
|
||||
sim._failed, sim._initialized = None, True
|
||||
sim.bodies, sim.field = SimpleNamespace(jets=[jet]), SimpleNamespace(curved=Curved())
|
||||
return sim, jet
|
||||
|
||||
|
||||
def test_simulation_invalid_input_writes_nothing_and_stays_usable(monkeypatch):
|
||||
sim, jet = simulation(monkeypatch)
|
||||
for amplitude in BAD:
|
||||
with pytest.raises(ValueError):
|
||||
sim.set_jet_amplitude(0, amplitude)
|
||||
with pytest.raises(IndexError):
|
||||
sim.set_jet_amplitude(1, 2e-3)
|
||||
assert sim.field.curved.writes == [] and sim.bodies.jets[0] is jet and sim._failed is None
|
||||
sim.set_jet_amplitude(0, 2e-3) # retry after a rejected input
|
||||
assert sim.field.curved.writes == [(0, 2e-3)] and sim.bodies.jets[0].amplitude == 2e-3
|
||||
sim.close()
|
||||
|
||||
|
||||
def test_simulation_upload_failure_keeps_host_and_blocks_reuse(monkeypatch):
|
||||
sim, jet = simulation(monkeypatch)
|
||||
sim.field.curved.fail = True
|
||||
with pytest.raises(RuntimeError, match="upload failed"):
|
||||
sim.set_jet_amplitude(0, 2e-3)
|
||||
assert sim.bodies.jets[0] is jet and sim._failed is not None
|
||||
sim.field.curved.fail = False
|
||||
for call in (lambda: sim.set_jet_amplitude(0, 2e-3), lambda: sim.run(1), sim.step,
|
||||
sim.sync_bodies, sim.initialize, sim.get_ddf, sim.get_macroscopic,
|
||||
lambda: sim.read_surface_exchange(0), lambda: sim.read_body(0),
|
||||
sim.read_bodies, sim.snapshot, sim.restore, sim.save_checkpoint,
|
||||
lambda: sim.load_checkpoint("x.h5"), lambda: sim.update_runtime_params(omega=1.)):
|
||||
with pytest.raises(RuntimeError, match="Simulation failed"):
|
||||
call()
|
||||
assert sim.field.curved.writes == [(0, 2e-3)]
|
||||
sim.close() # cleanup still works
|
||||
assert sim._closed and sim.ctx.is_closed
|
||||
|
||||
|
||||
def test_simulation_before_initialize_commits_host_only(monkeypatch):
|
||||
sim, _ = simulation(monkeypatch)
|
||||
sim._initialized = False
|
||||
sim.set_jet_amplitude(0, -2e-3)
|
||||
assert sim.field.curved.writes == [] and sim.bodies.jets[0].amplitude == -2e-3
|
||||
sim.close()
|
||||
|
||||
|
||||
def stepper_state(run):
|
||||
boundary = run._level_boundaries[2]
|
||||
return boundary.tables["surface_velocity"].copy(), boundary.jets, run._level_jets[2]
|
||||
|
||||
|
||||
def test_stepper_invalid_input_writes_nothing_and_stays_ready():
|
||||
run, module, _, _, _ = ready()
|
||||
try:
|
||||
velocity, jets, level_jets = stepper_state(run)
|
||||
module.cuda.memcpy_htod.reset_mock()
|
||||
for args, kw, error in [((0, a), {"level": 2}, ValueError) for a in BAD] + [
|
||||
((1, .01), {"level": 2}, IndexError), ((0, .01), {"level": 3}, ValueError)]:
|
||||
with pytest.raises(error):
|
||||
run.set_jet_amplitude(*args, **kw)
|
||||
module.cuda.memcpy_htod.assert_not_called()
|
||||
np.testing.assert_array_equal(run._level_boundaries[2].tables["surface_velocity"], velocity)
|
||||
assert (run._level_boundaries[2].jets, run._level_jets[2]) == (jets, level_jets)
|
||||
assert run._status == "ready"
|
||||
run.set_jet_amplitude(0, .017, level=2)
|
||||
assert run._level_jets[2][0].amplitude == .017
|
||||
finally:
|
||||
run.close()
|
||||
|
||||
|
||||
@pytest.mark.parametrize("where", ["upload", "synchronize"])
|
||||
def test_stepper_device_failure_keeps_host_and_blocks_reuse(where):
|
||||
run, module, _, _, _ = ready()
|
||||
try:
|
||||
velocity, jets, level_jets = stepper_state(run)
|
||||
if where == "upload":
|
||||
module.cuda.memcpy_htod.side_effect = RuntimeError("upload failed")
|
||||
else:
|
||||
run._stream.synchronize.side_effect = RuntimeError("upload failed")
|
||||
with pytest.raises(RuntimeError, match="upload failed"):
|
||||
run.set_jet_amplitude(0, .017, level=2)
|
||||
np.testing.assert_array_equal(run._level_boundaries[2].tables["surface_velocity"], velocity)
|
||||
assert (run._level_boundaries[2].jets, run._level_jets[2]) == (jets, level_jets)
|
||||
assert run._status == "failed"
|
||||
module.cuda.memcpy_htod.side_effect = None
|
||||
run._stream.synchronize.side_effect = None
|
||||
for call in (lambda: run.set_jet_amplitude(0, .017, level=2), run.step, run.download):
|
||||
with pytest.raises(RuntimeError, match="failed"):
|
||||
call()
|
||||
finally:
|
||||
run.close()
|
||||
assert run._status == "closed"
|
||||
Reference in new issue
Block a user