Exemplo n.º 1
0
    def create_execution_plan_index(self,
                                    external_pipeline,
                                    environment_dict,
                                    mode,
                                    step_keys_to_execute=None):
        check.inst_param(external_pipeline, 'external_pipeline',
                         ExternalPipeline)
        check.dict_param(environment_dict, 'environment_dict')
        check.str_param(mode, 'mode')
        check.opt_list_param(step_keys_to_execute,
                             'step_keys_to_execute',
                             of_type=str)

        return ExecutionPlanIndex(
            execution_plan_snapshot=snapshot_from_execution_plan(
                create_execution_plan(
                    pipeline=self.get_pipeline(external_pipeline.name),
                    environment_dict=environment_dict,
                    mode=mode,
                    step_keys_to_execute=step_keys_to_execute,
                ),
                external_pipeline.pipeline_snapshot_id,
            ),
            pipeline_index=external_pipeline.pipeline_index,
        )
Exemplo n.º 2
0
def test_run_created_in_0_7_9_snapshot_id_change():
    test_dir = file_relative_path(
        __file__, 'snapshot_0_7_9_shapshot_id_creation_change/sqlite')
    with restore_directory(test_dir):

        instance = DagsterInstance.from_ref(InstanceRef.from_dir(test_dir))
        # run_id = 'e297fa70-49e8-43f8-abfe-1634f02644f6'

        old_pipeline_snapshot_id = '88528edde2ed64da3c39cca0da8ba2f7586c1a5d'
        old_execution_plan_snapshot_id = '2246f8e5a10d21e15fbfa3773d7b2d0bc1fa9d3d'

        pipeline_snapshot = instance.get_pipeline_snapshot(
            old_pipeline_snapshot_id)
        ep_snapshot = instance.get_execution_plan_snapshot(
            old_execution_plan_snapshot_id)

        # It is the pipeline snapshot that changed
        # Verify that snapshot ids are not equal. This changed in 0.7.10
        assert create_pipeline_snapshot_id(
            pipeline_snapshot) != old_pipeline_snapshot_id

        # We also changed execution plan schema in 0.7.11.post1
        assert create_execution_plan_snapshot_id(
            ep_snapshot) != old_execution_plan_snapshot_id

        # This previously failed with a check error
        assert ExecutionPlanIndex(ep_snapshot,
                                  PipelineIndex(pipeline_snapshot))
Exemplo n.º 3
0
    def resolve_executionPlan(self, graphene_info):
        if not (self._pipeline_run.execution_plan_snapshot_id
                and self._pipeline_run.pipeline_snapshot_id):
            return None

        from .execution import DauphinExecutionPlan

        instance = graphene_info.context.instance
        pipeline_snapshot = instance.get_pipeline_snapshot(
            self._pipeline_run.pipeline_snapshot_id)
        execution_plan_snapshot = instance.get_execution_plan_snapshot(
            self._pipeline_run.execution_plan_snapshot_id)
        return (DauphinExecutionPlan(
            ExecutionPlanIndex(
                execution_plan_snapshot=execution_plan_snapshot,
                pipeline_index=PipelineIndex(pipeline_snapshot),
            )) if execution_plan_snapshot and pipeline_snapshot else None)
Exemplo n.º 4
0
def get_pipeline_run_observable(graphene_info, run_id, after=None):
    check.inst_param(graphene_info, 'graphene_info', ResolveInfo)
    check.str_param(run_id, 'run_id')
    check.opt_int_param(after, 'after')
    instance = graphene_info.context.instance
    run = instance.get_run_by_id(run_id)

    if not run:

        def _get_error_observable(observer):
            observer.on_next(
                graphene_info.schema.
                type_named('PipelineRunLogsSubscriptionFailure')(
                    missingRunId=run_id,
                    message='Could not load run with id {}'.format(run_id)))

        return Observable.create(_get_error_observable)  # pylint: disable=E1101

    execution_plan_index = (ExecutionPlanIndex(
        execution_plan_snapshot=instance.get_execution_plan_snapshot(
            run.execution_plan_snapshot_id),
        pipeline_index=PipelineIndex(
            instance.get_pipeline_snapshot(run.pipeline_snapshot_id)),
    ) if run.pipeline_snapshot_id and run.execution_plan_snapshot_id else None)

    # pylint: disable=E1101
    return Observable.create(
        PipelineRunObservableSubscribe(instance, run_id, after_cursor=after)
    ).map(lambda events: graphene_info.schema.type_named(
        'PipelineRunLogsSubscriptionSuccess')(
            run=graphene_info.schema.type_named('PipelineRun')(run),
            messages=[
                from_event_record(event, run.pipeline_name,
                                  execution_plan_index) for event in events
            ],
        ))
Exemplo n.º 5
0
def _do_execute_plan(graphene_info, execution_params, pipeline_def):
    check.inst_param(graphene_info, 'graphene_info', ResolveInfo)
    check.inst_param(execution_params, 'execution_params', ExecutionParams)

    run_id = execution_params.execution_metadata.run_id

    mode = execution_params.mode or pipeline_def.get_default_mode_name()

    pipeline_run = graphene_info.context.instance.get_run_by_id(run_id)

    execution_plan = create_execution_plan(
        pipeline=pipeline_def,
        environment_dict=execution_params.environment_dict,
        mode=mode,
    )

    if not pipeline_run:
        # TODO switch to raising a UserFacingError if the run_id cannot be found
        # https://github.com/dagster-io/dagster/issues/1876
        pipeline_run = graphene_info.context.instance.create_run_for_pipeline(
            pipeline_def=pipeline_def,
            execution_plan=execution_plan,
            run_id=run_id,
            environment_dict=execution_params.environment_dict,
            mode=mode,
            tags=execution_params.execution_metadata.tags or {},
        )

    execution_plan = create_execution_plan(
        pipeline=pipeline_def,
        environment_dict=execution_params.environment_dict,
        mode=pipeline_run.mode,
    )

    if execution_params.step_keys:
        for step_key in execution_params.step_keys:
            if not execution_plan.has_step(step_key):
                raise UserFacingGraphQLError(
                    graphene_info.schema.type_named('InvalidStepError')(
                        invalid_step_key=step_key))

        execution_plan = execution_plan.build_subset_plan(
            execution_params.step_keys)

    event_logs = []

    def _on_event_record(record):
        if record.is_dagster_event:
            event_logs.append(record)

    graphene_info.context.instance.add_event_listener(run_id, _on_event_record)

    execute_plan(
        execution_plan=execution_plan,
        environment_dict=execution_params.environment_dict,
        pipeline_run=pipeline_run,
        instance=graphene_info.context.instance,
    )

    dauphin_pipeline = DauphinPipeline.from_pipeline_def(pipeline_def)

    execution_plan_index = ExecutionPlanIndex.from_plan_and_index(
        execution_plan, pipeline_def.get_pipeline_index())

    def to_graphql_event(event_record):
        return from_dagster_event_record(event_record,
                                         pipeline_run.pipeline_name,
                                         execution_plan_index)

    return graphene_info.schema.type_named('ExecutePlanSuccess')(
        pipeline=dauphin_pipeline,
        has_failures=any(
            er for er in event_logs if er.is_dagster_event
            and er.dagster_event.event_type == DagsterEventType.STEP_FAILURE),
        step_events=list(map(to_graphql_event, event_logs)),
        raw_event_records=list(map(serialize_dagster_namedtuple, event_logs)),
    )