mirror of
https://github.com/vale981/ray
synced 2025-03-10 05:16:49 -04:00
331b71ea8d
Adds a unit-tested and restructured ray_release package for running release tests.
Relevant changes in behavior:
Per default, Buildkite will wait for the wheels of the current commit to be available. Alternatively, users can a) specify a different commit hash, b) a wheels URL (which we will also wait for to be available) or c) specify a branch (or user/branch combination), in which case the latest available wheels will be used (e.g. if master is passed, behavior matches old default behavior).
The main subpackages are:
Cluster manager: Creates cluster envs/computes, starts cluster, terminates cluster
Command runner: Runs commands, e.g. as client command or sdk command
File manager: Uploads/downloads files to/from session
Reporter: Reports results (e.g. to database)
Much of the code base is unit tested, but there are probably some pieces missing.
Example build (waited for wheels to be built): https://buildkite.com/ray-project/kf-dev/builds/51#_
Wheel build: https://buildkite.com/ray-project/ray-builders-branch/builds/6023
53 lines
1.2 KiB
Python
53 lines
1.2 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
|
|
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 = len(ray.nodes())
|
|
|
|
passed = time.time() - start
|
|
print(
|
|
f"Cluster is up: {curr_nodes}/{args.num_nodes} nodes online after "
|
|
f"{passed:.0f} seconds"
|
|
)
|