mirror of
https://github.com/vale981/ray
synced 2025-03-06 18:41:40 -05:00
a33cbec12a
* start
* check formatting
* undo changes from base branch
* Client builder API docs
* indent
* 8
* minor fixes
* absolute path to runtime env docs
* fix runtime_env link
* Update worker.init docs
* drop clientbuilder docs, link to 1.4.1 docs instead. Specify local:// behavior when address passed
* add debug info for ray.init("local")
* local:// attaches a driver directly
* update ray.init return wording
* remote init.connect() from example
* drop local:// docs, add section on when to use ray client
* link to 1.4.1 docs in code example instead of mentioning clientbuilder
* fix backticks, doc mentions of ray.util.connect
* remove ray.util.connect mentions from examples and comments
* update tune example
* wording
* localhost:<port> also works if you're on the head node
* add quotes
* drop mentions of ray client from ray.init docstring
* local->remote
* fix section ref
* update ray start output
* fix section link
* try to fix doc again
* fix link wording
* drop local:// from docs and special handling from code
* update ray start message
* lint
* doc lint
* remove local:// codepath
* remove 'internal_config'
* Update doc/source/cluster/ray-client.rst
Co-authored-by: Ameer Haj Ali <ameerh@berkeley.edu>
* doc suggestion
* Update doc/source/cluster/ray-client.rst
Co-authored-by: Ameer Haj Ali <ameerh@berkeley.edu>
51 lines
1.3 KiB
Python
51 lines
1.3 KiB
Python
from collections import Counter
|
|
import sys
|
|
import time
|
|
import ray
|
|
""" This script is meant to be run from a pod in the same Kubernetes namespace
|
|
as your Ray cluster.
|
|
"""
|
|
|
|
|
|
@ray.remote
|
|
def gethostname(x):
|
|
import platform
|
|
import time
|
|
time.sleep(0.01)
|
|
return x + (platform.node(), )
|
|
|
|
|
|
def wait_for_nodes(expected):
|
|
# Wait for all nodes to join the cluster.
|
|
while True:
|
|
resources = ray.cluster_resources()
|
|
node_keys = [key for key in resources if "node" in key]
|
|
num_nodes = sum(resources[node_key] for node_key in node_keys)
|
|
if num_nodes < expected:
|
|
print("{} nodes have joined so far, waiting for {} more.".format(
|
|
num_nodes, expected - num_nodes))
|
|
sys.stdout.flush()
|
|
time.sleep(1)
|
|
else:
|
|
break
|
|
|
|
|
|
def main():
|
|
wait_for_nodes(3)
|
|
|
|
# Check that objects can be transferred from each node to each other node.
|
|
for i in range(10):
|
|
print("Iteration {}".format(i))
|
|
results = [
|
|
gethostname.remote(gethostname.remote(())) for _ in range(100)
|
|
]
|
|
print(Counter(ray.get(results)))
|
|
sys.stdout.flush()
|
|
|
|
print("Success!")
|
|
sys.stdout.flush()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
ray.init("ray://example-cluster-ray-head:10001")
|
|
main()
|