def get_run():
candidate_run = self.get_run_by_id(pipeline_run.run_id)
field_diff = _check_run_equality(pipeline_run, candidate_run)
if field_diff:
raise DagsterRunConflict(
'Found conflicting existing run with same id {run_id}. Runs differ in:'
'\n{field_diff}'.format(
run_id=pipeline_run.run_id,
field_diff=_format_field_diff(field_diff),
), )
return candidate_run
def get_or_create_run(
self,
pipeline_name=None,
run_id=None,
environment_dict=None,
mode=None,
solid_subset=None,
step_keys_to_execute=None,
status=None,
tags=None,
root_run_id=None,
parent_run_id=None,
pipeline_snapshot=None,
execution_plan_snapshot=None,
):
# The last usage of this method is in dagster-airflow. When the usage is removed, this method
# should be deleted.
# https://github.com/dagster-io/dagster/issues/2412
pipeline_run = self._construct_run_with_snapshots(
pipeline_name=pipeline_name,
run_id=run_id,
environment_dict=environment_dict,
mode=mode,
solid_subset=solid_subset,
step_keys_to_execute=step_keys_to_execute,
status=status,
tags=tags,
root_run_id=root_run_id,
parent_run_id=parent_run_id,
pipeline_snapshot=pipeline_snapshot,
execution_plan_snapshot=execution_plan_snapshot,
)
if self.has_run(pipeline_run.run_id):
candidate_run = self.get_run_by_id(pipeline_run.run_id)
field_diff = _check_run_equality(pipeline_run, candidate_run)
if field_diff:
raise DagsterRunConflict(
'Found conflicting existing run with same id {run_id}. Runs differ in:'
'\n{field_diff}'.format(
run_id=pipeline_run.run_id,
field_diff=_format_field_diff(field_diff),
), )
return candidate_run
return self._run_storage.add_run(pipeline_run)
def get_or_create_run(self, pipeline_run):
# This eventually needs transactional/locking semantics
if self.has_run(pipeline_run.run_id):
candidate_run = self.get_run_by_id(pipeline_run.run_id)
if not candidate_run == pipeline_run:
raise DagsterRunConflict(
'Found conflicting existing run with same id. Expected {pipeline_run}, found {candidate_run}.'
.format(pipeline_run=pipeline_run,
candidate_run=candidate_run))
return candidate_run
else:
# We will need a more principled way of doing this
try:
return self.create_run(pipeline_run)
except DagsterRunAlreadyExists:
if not self.has_run(pipeline_run.run_id):
check.failed(
'Inconsistent run storage: could not get or create pipeline run with run_id {run_id}'
.format(run_id=pipeline_run.run_id))
return self.get_run_by_id(pipeline_run.run_id)
def get_or_create_run(
self,
pipeline_name=None,
run_id=None,
environment_dict=None,
mode=None,
selector=None,
step_keys_to_execute=None,
status=None,
tags=None,
root_run_id=None,
parent_run_id=None,
pipeline_snapshot=None,
execution_plan_snapshot=None,
):
if tags and IS_AIRFLOW_INGEST_PIPELINE_STR in tags:
if AIRFLOW_EXECUTION_DATE_STR not in tags:
tags[AIRFLOW_EXECUTION_DATE_STR] = get_current_datetime_in_utc(
).isoformat()
pipeline_run = PipelineRun(
pipeline_name=pipeline_name,
run_id=run_id,
environment_dict=environment_dict,
mode=mode,
selector=selector,
step_keys_to_execute=step_keys_to_execute,
status=status,
tags=tags,
root_run_id=root_run_id,
parent_run_id=parent_run_id,
)
if pipeline_snapshot is not None:
from dagster.core.snap.pipeline_snapshot import create_pipeline_snapshot_id
pipeline_snapshot_id = create_pipeline_snapshot_id(
pipeline_snapshot)
if not self._run_storage.has_pipeline_snapshot(
pipeline_snapshot_id):
returned_pipeline_snapshot_id = self._run_storage.add_pipeline_snapshot(
pipeline_snapshot)
check.invariant(
pipeline_snapshot_id == returned_pipeline_snapshot_id)
pipeline_run = pipeline_run.with_pipeline_snapshot_id(
pipeline_snapshot_id)
if execution_plan_snapshot is not None:
from dagster.core.snap.execution_plan_snapshot import create_execution_plan_snapshot_id
check.invariant(execution_plan_snapshot.pipeline_snapshot_id ==
pipeline_snapshot_id)
execution_plan_snapshot_id = create_execution_plan_snapshot_id(
execution_plan_snapshot)
if not self._run_storage.has_execution_plan_snapshot(
execution_plan_snapshot_id):
returned_execution_plan_snapshot_id = self._run_storage.add_execution_plan_snapshot(
execution_plan_snapshot)
check.invariant(execution_plan_snapshot_id ==
returned_execution_plan_snapshot_id)
pipeline_run = pipeline_run.with_execution_plan_snapshot_id(
execution_plan_snapshot_id)
if self.has_run(pipeline_run.run_id):
candidate_run = self.get_run_by_id(pipeline_run.run_id)
field_diff = _check_run_equality(pipeline_run, candidate_run)
if field_diff:
raise DagsterRunConflict(
'Found conflicting existing run with same id {run_id}. Runs differ in:'
'\n{field_diff}'.format(
run_id=pipeline_run.run_id,
field_diff=_format_field_diff(field_diff),
), )
return candidate_run
return self._run_storage.add_run(pipeline_run)