def update_step_status(self, workflow_id: str, step_id: str,
status: common.WorkflowStatus):
# Note: For virtual actor, we could add more steps even if
# the workflow finishes.
self._step_status.setdefault(workflow_id, {})
if status == common.WorkflowStatus.SUCCESSFUL:
self._step_status[workflow_id].pop(step_id, None)
else:
self._step_status.setdefault(workflow_id, {})[step_id] = status
remaining = len(self._step_status[workflow_id])
if status != common.WorkflowStatus.RUNNING:
self._step_output_cache.pop((workflow_id, step_id), None)
if status != common.WorkflowStatus.FAILED and remaining != 0:
return
wf_store = workflow_storage.WorkflowStorage(workflow_id, self._store)
if status == common.WorkflowStatus.FAILED:
if workflow_id in self._workflow_outputs:
cancel_job(self._workflow_outputs.pop(workflow_id).output)
wf_store.save_workflow_meta(
common.WorkflowMetaData(common.WorkflowStatus.FAILED))
self._step_status.pop(workflow_id)
else:
# remaining = 0
wf_store.save_workflow_meta(
common.WorkflowMetaData(common.WorkflowStatus.SUCCESSFUL))
self._step_status.pop(workflow_id)
def get_output(self, workflow_id: str) -> "ray.ObjectRef":
"""Get the output of a running workflow.
Args:
workflow_id: The ID of a workflow job.
Returns:
An object reference that can be used to retrieve the
workflow result.
"""
if workflow_id in self._workflow_outputs:
return self._workflow_outputs[workflow_id].output
wf_store = workflow_storage.WorkflowStorage(workflow_id, self._store)
meta = wf_store.load_workflow_meta()
if meta is None:
raise ValueError(f"No such workflow {workflow_id}")
if meta == common.WorkflowStatus.FAILED:
raise ValueError(
f"Workflow {workflow_id} failed, please resume it")
step_id = wf_store.get_entrypoint_step_id()
result = recovery.resume_workflow_step(workflow_id, step_id,
self._store.storage_url)
latest_output = LatestWorkflowOutput(result.persisted_output,
workflow_id, step_id)
self._workflow_outputs[workflow_id] = latest_output
wf_store = workflow_storage.WorkflowStorage(workflow_id, self._store)
wf_store.save_workflow_meta(
common.WorkflowMetaData(common.WorkflowStatus.RUNNING))
self._step_status.setdefault(workflow_id, {})
# "persisted_output" is the return value of a step or the state of
# a virtual actor.
return result.persisted_output
def run_or_resume(self, workflow_id: str, ignore_existing: bool = False
) -> "WorkflowExecutionResult":
"""Run or resume a workflow.
Args:
workflow_id: The ID of the workflow.
ignore_existing: Ignore we already have an existing output. When
set false, raise an exception if there has already been a workflow
running with this id
Returns:
Workflow execution result that contains the state and output.
"""
if workflow_id in self._workflow_outputs and not ignore_existing:
raise RuntimeError(f"The output of workflow[id={workflow_id}] "
"already exists.")
wf_store = workflow_storage.WorkflowStorage(workflow_id, self._store)
step_id = wf_store.get_entrypoint_step_id()
result = recovery.resume_workflow_step(workflow_id, step_id,
self._store.storage_url)
latest_output = LatestWorkflowOutput(result.persisted_output,
workflow_id, step_id)
self._workflow_outputs[workflow_id] = latest_output
self._step_output_cache[workflow_id, step_id] = latest_output
wf_store.save_workflow_meta(
common.WorkflowMetaData(common.WorkflowStatus.RUNNING))
if workflow_id not in self._step_status:
self._step_status[workflow_id] = {}
logger.info(f"Workflow job [id={workflow_id}] started.")
return result
def update_step_status(self, workflow_id: str, step_id: str,
status: common.WorkflowStatus):
if status == common.WorkflowStatus.FINISHED:
self._step_status[workflow_id].pop(step_id, None)
else:
self._step_status.setdefault(workflow_id, {})[step_id] = status
remaining = len(self._step_status[workflow_id])
if status != common.WorkflowStatus.RESUMABLE and remaining != 0:
return
wf_store = workflow_storage.WorkflowStorage(workflow_id, self._store)
if status == common.WorkflowStatus.RESUMABLE:
if workflow_id in self._workflow_outputs:
cancel_job(self._workflow_outputs.pop(workflow_id))
wf_store.save_workflow_meta(
common.WorkflowMetaData(common.WorkflowStatus.RESUMABLE))
self._step_status.pop(workflow_id)
else:
# remaining = 0
wf_store.save_workflow_meta(
common.WorkflowMetaData(common.WorkflowStatus.FINISHED))
self._step_status.pop(workflow_id)
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.remote(workflow_id,
self._store.storage_url)
self._workflow_outputs[workflow_id] = output
wf_store = workflow_storage.WorkflowStorage(workflow_id, self._store)
wf_store.save_workflow_meta(
common.WorkflowMetaData(common.WorkflowStatus.RUNNING))
self._step_status[workflow_id] = {}
logger.info(f"Workflow job [id={workflow_id}] started.")
return output
def cancel_workflow(self, workflow_id: str) -> None:
self._step_status.pop(workflow_id)
cancel_job(self._workflow_outputs.pop(workflow_id).output)
wf_store = workflow_storage.WorkflowStorage(workflow_id, self._store)
wf_store.save_workflow_meta(
common.WorkflowMetaData(common.WorkflowStatus.CANCELED))
