def run(entry_workflow: Workflow,
storage: Optional[Union[str, Storage]] = None,
workflow_id: Optional[str] = None) -> ray.ObjectRef:
"""Run a workflow asynchronously. See "api.run()" for details."""
if workflow_id is None:
# Workflow ID format: {Entry workflow UUID}.{Unix time to nanoseconds}
workflow_id = f"{entry_workflow.id}.{time.time():.9f}"
if isinstance(storage, str):
set_global_storage(create_storage(storage))
elif isinstance(storage, Storage):
set_global_storage(storage)
elif storage is not None:
raise TypeError("'storage' should be None, str, or Storage type.")
storage_url = get_global_storage().storage_url
logger.info(f"Workflow job created. [id=\"{workflow_id}\", storage_url="
f"\"{storage_url}\"].")
try:
workflow_context.init_workflow_step_context(workflow_id, storage_url)
commit_step(entry_workflow)
# TODO(suquark): Move this to a detached named actor,
# so the workflow shares fate with the actor.
# The current plan is resuming the workflow on the detached named
# actor. This is extremely simple to implement, but I am not sure
# of its performance.
output = recovery.resume_workflow_job(workflow_id,
get_global_storage())
logger.info(f"Workflow job {workflow_id} started.")
finally:
workflow_context.set_workflow_step_context(None)
return output
def run_or_resume(self, workflow_id: str) -> ray.ObjectRef:
"""Run or resume a workflow.
Args:
workflow_id: The ID of the workflow.
Returns:
An object reference that can be used to retrieve the
workflow result.
"""
if workflow_id in self._workflow_outputs:
raise ValueError(f"The output of workflow[id={workflow_id}] "
"already exists.")
output = recovery.resume_workflow_job(workflow_id, self._store)
self._workflow_outputs[workflow_id] = output
logger.info(f"Workflow job [id={workflow_id}] started.")
return output
def resume(workflow_id: str,
storage: Optional[Union[str, Storage]] = None) -> ray.ObjectRef:
"""Resume a workflow asynchronously. See "api.resume()" for details.
"""
if isinstance(storage, str):
store = create_storage(storage)
elif isinstance(storage, Storage):
store = storage
elif storage is None:
store = get_global_storage()
else:
raise TypeError("'storage' should be None, str, or Storage type.")
logger.info(f"Resuming workflow [id=\"{workflow_id}\", storage_url="
f"\"{store.storage_url}\"].")
output = recovery.resume_workflow_job(workflow_id, store)
logger.info(f"Workflow job {workflow_id} resumed.")
return output
def resume(workflow_id: str, workflow_root_dir=None) -> ray.ObjectRef:
"""
Resume a workflow asynchronously. This workflow maybe fail previously.
Args:
workflow_id: The ID of the workflow. The ID is used to identify
the workflow.
workflow_root_dir: The path of an external storage used for
checkpointing.
Returns:
The execution result of the workflow, represented by Ray ObjectRef.
"""
assert ray.is_initialized()
if workflow_root_dir is not None:
store = storage.create_storage(workflow_root_dir)
else:
store = storage.get_global_storage()
r = recovery.resume_workflow_job(workflow_id, store)
if isinstance(r, ray.ObjectRef):
return r
# skip saving the DAG of a recovery workflow
r.skip_saving_workflow_dag = True
return run(r, workflow_root_dir, workflow_id)