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
77 lines
2.2 KiB
Python
77 lines
2.2 KiB
Python
import abc
|
|
from typing import Dict, Any, Optional
|
|
|
|
from ray_release.cluster_manager.cluster_manager import ClusterManager
|
|
from ray_release.file_manager.file_manager import FileManager
|
|
|
|
|
|
class CommandRunner(abc.ABC):
|
|
def __init__(
|
|
self,
|
|
cluster_manager: ClusterManager,
|
|
file_manager: FileManager,
|
|
working_dir: str,
|
|
):
|
|
self.cluster_manager = cluster_manager
|
|
self.file_manager = file_manager
|
|
self.working_dir = working_dir
|
|
|
|
self.result_output_json = "/tmp/release_test_out.json"
|
|
|
|
@property
|
|
def command_env(self):
|
|
return {"TEST_OUTPUT_JSON": self.result_output_json}
|
|
|
|
def get_full_command_env(self, env: Optional[Dict] = None):
|
|
full_env = self.command_env.copy()
|
|
|
|
if env:
|
|
full_env.update(env)
|
|
|
|
return full_env
|
|
|
|
def prepare_local_env(self, ray_wheels_url: Optional[str] = None):
|
|
"""Prepare local environment, e.g. install dependencies."""
|
|
raise NotImplementedError
|
|
|
|
def prepare_remote_env(self):
|
|
"""Prepare remote environment, e.g. upload files."""
|
|
raise NotImplementedError
|
|
|
|
def wait_for_nodes(self, num_nodes: int, timeout: float = 900.0):
|
|
"""Wait for cluster nodes to be up.
|
|
|
|
Args:
|
|
num_nodes (int): Number of nodes to wait for.
|
|
timeout (float): Timeout in seconds to wait for nodes before
|
|
raising a ``PrepareCommandTimeoutError``.
|
|
|
|
Returns:
|
|
None
|
|
|
|
Raises:
|
|
PrepareCommandTimeoutError
|
|
"""
|
|
raise NotImplementedError
|
|
|
|
def run_command(
|
|
self, command: str, env: Optional[Dict] = None, timeout: float = 3600.0
|
|
) -> float:
|
|
"""Run command."""
|
|
raise NotImplementedError
|
|
|
|
def run_prepare_command(
|
|
self, command: str, env: Optional[Dict] = None, timeout: float = 3600.0
|
|
):
|
|
"""Run prepare command.
|
|
|
|
Command runners may choose to run this differently than the
|
|
test command.
|
|
"""
|
|
return self.run_command(command, env, timeout)
|
|
|
|
def get_last_logs(self):
|
|
raise NotImplementedError
|
|
|
|
def fetch_results(self) -> Dict[str, Any]:
|
|
raise NotImplementedError
|