wehub-resource-sync
61 lines
2.0 KiB
Python
61 lines
2.0 KiB
Python
import sys
|
|
|
|
import numpy as np
|
|
import pytest
|
|
|
|
import ray
|
|
from ray._private.test_utils import get_other_nodes
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"ray_start_cluster",
|
|
[{"num_cpus": 4, "num_nodes": 3, "do_init": True}],
|
|
indirect=True,
|
|
)
|
|
def test_actor_creation_node_failure(ray_start_cluster):
|
|
# TODO(swang): Refactor test_raylet_failed, etc to reuse the below code.
|
|
cluster = ray_start_cluster
|
|
|
|
@ray.remote
|
|
class Child:
|
|
def __init__(self, death_probability):
|
|
self.death_probability = death_probability
|
|
|
|
def ping(self):
|
|
# Exit process with some probability.
|
|
exit_chance = np.random.rand()
|
|
if exit_chance < self.death_probability:
|
|
sys.exit(-1)
|
|
|
|
num_children = 25
|
|
# Children actors will die about half the time.
|
|
death_probability = 0.5
|
|
|
|
children = [Child.remote(death_probability) for _ in range(num_children)]
|
|
while len(cluster.list_all_nodes()) > 1:
|
|
for j in range(2):
|
|
# Submit some tasks on the actors. About half of the actors will
|
|
# fail.
|
|
children_out = [child.ping.remote() for child in children]
|
|
# Wait a while for all the tasks to complete. This should trigger
|
|
# reconstruction for any actor creation tasks that were forwarded
|
|
# to nodes that then failed.
|
|
ready, _ = ray.wait(
|
|
children_out, num_returns=len(children_out), timeout=5 * 60.0
|
|
)
|
|
assert len(ready) == len(children_out)
|
|
|
|
# Replace any actors that died.
|
|
for i, out in enumerate(children_out):
|
|
try:
|
|
ray.get(out)
|
|
except ray.exceptions.RayActorError:
|
|
children[i] = Child.remote(death_probability)
|
|
# Remove a node. Any actor creation tasks that were forwarded to this
|
|
# node must be resubmitted.
|
|
cluster.remove_node(get_other_nodes(cluster, True)[-1])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(pytest.main(["-sv", __file__]))
|