def test_interrupt_stops_running_tasks_quickly(self, scheduler):
# Windows implements `queue.get` using polling,
# which means we can set an exception to interrupt the call to `get`.
# Python 3 on other platforms requires sending SIGINT to the main thread.
if os.name == "nt":
from _thread import interrupt_main
else:
main_thread = threading.get_ident()
def interrupt_main():
import signal
signal.pthread_kill(main_thread, signal.SIGINT)
def long_task():
for i in range(50):
time.sleep(0.1)
e = LocalDaskExecutor(scheduler)
try:
interrupter = threading.Timer(0.5, interrupt_main)
interrupter.start()
start = time.time()
with e.start():
e.wait(e.submit(long_task))
except KeyboardInterrupt:
pass
except Exception:
assert False, "Failed to interrupt"
stop = time.time()
if stop - start > 4:
assert False, "Failed to interrupt"
def test_submit(self):
e = LocalDaskExecutor()
with e.start():
assert e.submit(lambda: 1).compute() == 1
assert e.submit(lambda x: x, 1).compute() == 1
assert e.submit(lambda x: x, x=1).compute() == 1
assert e.submit(lambda: prefect).compute() is prefect
def test_map_doesnt_do_anything_for_empty_list_input(self):
def map_fn(*args):
raise ValueError("map_fn was called")
e = LocalDaskExecutor()
with e.start():
res = e.wait(e.map(map_fn))
assert res == []
def test_map_iterates_over_multiple_args(self):
def map_fn(x, y):
return x + y
e = LocalDaskExecutor()
with e.start():
res = e.wait(e.map(map_fn, [1, 2], [1, 3]))
assert res == [2, 5]
def test_map_fails_with_processes_executor(self):
def map_fn(x, y):
return x + y
e = LocalDaskExecutor(scheduler="processes")
with pytest.raises(RuntimeError):
with e.start():
res = e.wait(e.map(map_fn, [1, 2], [1, 3]))
def test_map_with_threads_scheduler(self):
def map_fn(x, y):
return x + y
e = LocalDaskExecutor(scheduler="threads")
with e.start():
res = e.wait(e.map(map_fn, [1, 2], [1, 3]))
assert res == [2, 5]
def test_wait(self):
e = LocalDaskExecutor()
with e.start():
assert e.wait(1) == 1
assert e.wait(prefect) is prefect
assert e.wait(e.submit(lambda: 1)) == 1
assert e.wait(e.submit(lambda x: x, 1)) == 1
assert e.wait(e.submit(lambda x: x, x=1)) == 1
assert e.wait(e.submit(lambda: prefect)) is prefect
def test_submit_sets_task_name(self):
e = LocalDaskExecutor()
with e.start():
f = e.submit(lambda x: x + 1,
1,
extra_context={"task_name": "inc"})
(res, ) = e.wait([f])
assert f.key.startswith("inc-")
assert res == 2
def test_configurable_scheduler(self):
e = LocalDaskExecutor(scheduler="synchronous")
assert e.scheduler == "synchronous"
def check_scheduler(val):
assert dask.config.get("scheduler") == val
with dask.config.set(scheduler="threads"):
check_scheduler("threads")
with e.start():
e.submit(check_scheduler, "synchronous")
def test_temporary_pool_created_of_proper_size_and_kind(
self, scheduler, num_workers):
from dask.system import CPU_COUNT
from multiprocessing.pool import Pool, ThreadPool
e = LocalDaskExecutor(scheduler, num_workers=num_workers)
with e.start():
if scheduler == "synchronous":
assert e._pool is None
else:
sol = num_workers or CPU_COUNT
kind = ThreadPool if scheduler == "threads" else Pool
assert isinstance(e._pool, kind)
assert e._pool._processes == sol
assert e._pool is None
def test_only_compute_once(self, scheduler, tmpdir):
e = LocalDaskExecutor(scheduler)
def inc(x, path):
if os.path.exists(path):
raise ValueError("Should only run once!")
with open(path, "wb"):
pass
return x + 1
with e.start():
f1 = e.submit(inc, 0, str(tmpdir.join("f1")))
f2 = e.submit(inc, f1, str(tmpdir.join("f2")))
f3 = e.submit(inc, f2, str(tmpdir.join("f3")))
assert e.wait([f1]) == [1]
assert e.wait([f2]) == [2]
assert e.wait([f3]) == [3]
assert e.wait([f1, f2, f3]) == [1, 2, 3]
def test_only_compute_once(self):
e = LocalDaskExecutor()
count = 0
def inc(x):
nonlocal count
count += 1
return x + 1
with e.start():
f1 = e.submit(inc, 0)
f2 = e.submit(inc, f1)
f3 = e.submit(inc, f2)
assert e.wait([f1]) == [1]
assert count == 1
assert e.wait([f2]) == [2]
assert count == 2
assert e.wait([f3]) == [3]
assert count == 3
assert e.wait([f1, f2, f3]) == [1, 2, 3]
assert count == 3
def test_is_pickleable_after_start(self):
e = LocalDaskExecutor()
with e.start():
post = cloudpickle.loads(cloudpickle.dumps(e))
assert isinstance(post, LocalDaskExecutor)
