async def submit_job(self, req: Request) -> Response:
result = await self._parse_and_validate_request(req, JobSubmitRequest)
# Request parsing failed, returned with Response object.
if isinstance(result, Response):
return result
else:
submit_request = result
try:
job_id = self._job_manager.submit_job(
entrypoint=submit_request.entrypoint,
job_id=submit_request.job_id,
runtime_env=submit_request.runtime_env,
metadata=submit_request.metadata)
resp = JobSubmitResponse(job_id=job_id)
except (TypeError, ValueError):
return Response(text=traceback.format_exc(),
status=aiohttp.web.HTTPBadRequest.status_code)
except Exception:
return Response(
text=traceback.format_exc(),
status=aiohttp.web.HTTPInternalServerError.status_code)
return Response(
text=json.dumps(dataclasses.asdict(resp)),
content_type="application/json",
status=aiohttp.web.HTTPOk.status_code,
)
def submit_job(
self,
*,
entrypoint: str,
job_id: Optional[str] = None,
runtime_env: Optional[Dict[str, Any]] = None,
metadata: Optional[Dict[str, str]] = None,
) -> str:
runtime_env = runtime_env or {}
metadata = metadata or {}
metadata.update(self._default_metadata)
self._upload_working_dir_if_needed(runtime_env)
req = JobSubmitRequest(
entrypoint=entrypoint,
job_id=job_id,
runtime_env=runtime_env,
metadata=metadata,
)
logger.debug(f"Submitting job with job_id={job_id}.")
r = self._do_request("POST",
"/api/jobs/",
json_data=dataclasses.asdict(req))
if r.status_code == 200:
return JobSubmitResponse(**r.json()).job_id
else:
self._raise_error(r)
def submit_job(
self,
*,
entrypoint: str,
job_id: Optional[str] = None,
runtime_env: Optional[Dict[str, Any]] = None,
metadata: Optional[Dict[str, str]] = None,
) -> str:
"""Submit and execute a job asynchronously.
When a job is submitted, it runs once to completion or failure. Retries or
different runs with different parameters should be handled by the
submitter. Jobs are bound to the lifetime of a Ray cluster, so if the
cluster goes down, all running jobs on that cluster will be terminated.
Example:
>>> from ray.job_submission import JobSubmissionClient
>>> client = JobSubmissionClient("http://127.0.0.1:8265") # doctest: +SKIP
>>> client.submit_job( # doctest: +SKIP
... entrypoint="python script.py",
... runtime_env={
... "working_dir": "./",
... "pip": ["requests==2.26.0"]
... }
... ) # doctest: +SKIP
'raysubmit_4LamXRuQpYdSMg7J'
Args:
entrypoint: The shell command to run for this job.
job_id: A unique ID for this job.
runtime_env: The runtime environment to install and run this job in.
metadata: Arbitrary data to store along with this job.
Returns:
The job ID of the submitted job. If not specified, this is a randomly
generated unique ID.
Raises:
RuntimeError: If the request to the job server fails, or if the specified
job_id has already been used by a job on this cluster.
"""
runtime_env = runtime_env or {}
metadata = metadata or {}
metadata.update(self._default_metadata)
self._upload_working_dir_if_needed(runtime_env)
self._upload_py_modules_if_needed(runtime_env)
# Run the RuntimeEnv constructor to parse local pip/conda requirements files.
runtime_env = RuntimeEnv(**runtime_env).to_dict()
req = JobSubmitRequest(
entrypoint=entrypoint,
job_id=job_id,
runtime_env=runtime_env,
metadata=metadata,
)
logger.debug(f"Submitting job with job_id={job_id}.")
r = self._do_request("POST", "/api/jobs/", json_data=dataclasses.asdict(req))
if r.status_code == 200:
return JobSubmitResponse(**r.json()).job_id
else:
self._raise_error(r)