mirror of
https://github.com/vale981/ray
synced 2025-03-08 19:41:38 -05:00
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
61 lines
1.5 KiB
Python
61 lines
1.5 KiB
Python
"""Small cluster training
|
|
|
|
This training run will start 4 workers on 4 nodes (including head node).
|
|
|
|
Test owner: Yard1 (primary), krfricke
|
|
|
|
Acceptance criteria: Should run through and report final results.
|
|
"""
|
|
import json
|
|
import os
|
|
import time
|
|
|
|
import ray
|
|
from lightgbm_ray import RayParams
|
|
|
|
from ray.util.lightgbm.release_test_util import train_ray
|
|
|
|
if __name__ == "__main__":
|
|
addr = os.environ.get("RAY_ADDRESS")
|
|
job_name = os.environ.get("RAY_JOB_NAME", "train_small")
|
|
if addr.startswith("anyscale://"):
|
|
ray.init(address=addr, job_name=job_name)
|
|
else:
|
|
ray.init(address="auto")
|
|
|
|
output = os.environ["TEST_OUTPUT_JSON"]
|
|
ray_params = RayParams(
|
|
elastic_training=False,
|
|
max_actor_restarts=2,
|
|
num_actors=4,
|
|
cpus_per_actor=4,
|
|
gpus_per_actor=0,
|
|
)
|
|
|
|
start = time.time()
|
|
|
|
@ray.remote(num_cpus=0)
|
|
def train():
|
|
os.environ["TEST_OUTPUT_JSON"] = output
|
|
train_ray(
|
|
path="/data/classification.parquet",
|
|
num_workers=4,
|
|
num_boost_rounds=100,
|
|
num_files=25,
|
|
regression=False,
|
|
use_gpu=False,
|
|
ray_params=ray_params,
|
|
lightgbm_params=None,
|
|
)
|
|
|
|
ray.get(train.remote())
|
|
taken = time.time() - start
|
|
|
|
result = {
|
|
"time_taken": taken,
|
|
}
|
|
test_output_json = os.environ.get("TEST_OUTPUT_JSON", "/tmp/train_small.json")
|
|
with open(test_output_json, "wt") as f:
|
|
json.dump(result, f)
|
|
|
|
print("PASSED.")
|