mirror of
https://github.com/vale981/ray
synced 2025-03-06 10:31:39 -05:00
1dc03cd49d
## Why are these changes needed? There are two issues fixed in this PR: - make sure wait for session count alive node - upgrade the machine to match what's tested in oss ray. ## Related issue number https://github.com/ray-project/ray/issues/19084
59 lines
1.3 KiB
Python
59 lines
1.3 KiB
Python
import argparse
|
|
import time
|
|
|
|
import ray
|
|
|
|
ray.init(address="auto")
|
|
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument(
|
|
"num_nodes",
|
|
type=int,
|
|
help="Wait for this number of nodes (includes head)")
|
|
|
|
parser.add_argument(
|
|
"max_time_s", type=int, help="Wait for this number of seconds")
|
|
|
|
parser.add_argument(
|
|
"--feedback_interval_s",
|
|
type=int,
|
|
default=10,
|
|
help="Wait for this number of seconds")
|
|
|
|
args = parser.parse_args()
|
|
|
|
curr_nodes = 0
|
|
start = time.time()
|
|
next_feedback = start
|
|
max_time = start + args.max_time_s
|
|
|
|
|
|
def num_alive_nodes():
|
|
n = 0
|
|
for node in ray.nodes():
|
|
if node.get("Alive", False):
|
|
n += 1
|
|
return n
|
|
|
|
|
|
while not curr_nodes >= args.num_nodes:
|
|
now = time.time()
|
|
|
|
if now >= max_time:
|
|
raise RuntimeError(
|
|
f"Maximum wait time reached, but only "
|
|
f"{curr_nodes}/{args.num_nodes} nodes came up. Aborting.")
|
|
|
|
if now >= next_feedback:
|
|
passed = now - start
|
|
print(f"Waiting for more nodes to come up: "
|
|
f"{curr_nodes}/{args.num_nodes} "
|
|
f"({passed:.0f} seconds passed)")
|
|
next_feedback = now + args.feedback_interval_s
|
|
|
|
time.sleep(5)
|
|
curr_nodes = num_alive_nodes()
|
|
|
|
passed = time.time() - start
|
|
print(f"Cluster is up: {curr_nodes}/{args.num_nodes} nodes online after "
|
|
f"{passed:.0f} seconds")
|