Esempio n. 1
0
    def topological_step_levels(self):
        if self._topological_step_levels is None:
            self._topological_step_levels = [[
                self._step_index[step_key]
                for step_key in sorted(step_key_level)
            ] for step_key_level in toposort(self.execution_deps())]

        return self._topological_step_levels
Esempio n. 2
0
def _get_steps_to_execute_by_level(step_dict, step_handles_to_execute,
                                   executable_map):
    return [[
        cast(ExecutionStep, _get_step_by_key(step_dict, step_key))
        for step_key in sorted(step_key_level)
    ] for step_key_level in toposort(
        _get_executable_step_deps(step_dict, step_handles_to_execute,
                                  executable_map))]
Esempio n. 3
0
 def get_steps_to_execute_by_level(self) -> List[List[ExecutionStep]]:
     return [
         [
             cast(ExecutionStep, self.get_step_by_key(step_key))
             for step_key in sorted(step_key_level)
         ]
         for step_key_level in toposort(self.get_executable_step_deps())
     ]
Esempio n. 4
0
 def topological_step_levels(self):
     return [[
         self.step_dict[step_key] for step_key in sorted(step_key_level)
     ] for step_key_level in toposort(self.deps)]
Esempio n. 5
0
def _core_resource_initialization_event_generator(
    resource_defs: Dict[str, ResourceDefinition],
    resource_configs: Dict[str, ResourceConfig],
    resource_log_manager: DagsterLogManager,
    resource_managers: Deque[EventGenerationManager],
    execution_plan: Optional[ExecutionPlan],
    pipeline_run: Optional[PipelineRun],
    resource_keys_to_init: Optional[Set[str]],
    instance: Optional[DagsterInstance],
    resource_instances_to_override: Optional[Dict[str, "InitializedResource"]],
    emit_persistent_events: Optional[bool],
):
    if emit_persistent_events:
        check.invariant(
            execution_plan,
            "If emit_persistent_events is enabled, then execution_plan must be provided",
        )
    resource_instances_to_override = check.opt_dict_param(
        resource_instances_to_override, "resource_instances_to_override")
    resource_keys_to_init = check.opt_set_param(resource_keys_to_init,
                                                "resource_keys_to_init")
    resource_instances: Dict[str, "InitializedResource"] = {}
    resource_init_times = {}
    try:
        if emit_persistent_events and resource_keys_to_init:
            yield DagsterEvent.resource_init_start(
                execution_plan,
                resource_log_manager,
                resource_keys_to_init,
            )

        resource_dependencies = _resolve_resource_dependencies(resource_defs)

        for level in toposort(resource_dependencies):
            for resource_name in level:

                if resource_name in resource_instances_to_override:
                    # use the given resource instances instead of re-initiating it from resource def
                    resource_def = ResourceDefinition.hardcoded_resource(
                        resource_instances_to_override[resource_name])
                else:
                    resource_def = resource_defs[resource_name]
                if not resource_name in resource_keys_to_init:
                    continue

                resource_context = InitResourceContext(
                    resource_def=resource_def,
                    resource_config=resource_configs[resource_name].config,
                    pipeline_run=pipeline_run,
                    # Add tags with information about the resource
                    log_manager=resource_log_manager.with_tags(
                        resource_name=resource_name,
                        resource_fn_name=str(
                            resource_def.resource_fn.__name__),
                    ),
                    resource_instance_dict=resource_instances,
                    required_resource_keys=resource_def.required_resource_keys,
                    instance=instance,
                    pipeline_def_for_backwards_compat=execution_plan.
                    pipeline_def if execution_plan else None,
                )
                manager = single_resource_generation_manager(
                    resource_context, resource_name, resource_def)
                for event in manager.generate_setup_events():
                    if event:
                        yield event
                initialized_resource = check.inst(manager.get_object(),
                                                  InitializedResource)
                resource_instances[
                    resource_name] = initialized_resource.resource
                resource_init_times[
                    resource_name] = initialized_resource.duration
                resource_managers.append(manager)

        if emit_persistent_events and resource_keys_to_init:
            yield DagsterEvent.resource_init_success(execution_plan,
                                                     resource_log_manager,
                                                     resource_instances,
                                                     resource_init_times)
        yield ScopedResourcesBuilder(resource_instances)
    except DagsterUserCodeExecutionError as dagster_user_error:
        # Can only end up in this state if we attempt to initialize a resource, so
        # resource_keys_to_init cannot be empty
        if emit_persistent_events:
            yield DagsterEvent.resource_init_failure(
                execution_plan,
                resource_log_manager,
                resource_keys_to_init,
                serializable_error_info_from_exc_info(
                    dagster_user_error.original_exc_info),
            )
        raise dagster_user_error
Esempio n. 6
0
def _core_resource_initialization_event_generator(
    execution_plan,
    environment_config,
    pipeline_run,
    resource_keys_to_init,
    resource_log_manager,
    resource_managers,
    instance,
):
    pipeline_def = execution_plan.pipeline_def
    resource_instances = {}
    mode_definition = pipeline_def.get_mode_definition(pipeline_run.mode)
    resource_init_times = {}
    try:
        if resource_keys_to_init:
            yield DagsterEvent.resource_init_start(
                execution_plan, resource_log_manager, resource_keys_to_init,
            )

        resource_dependencies = _resolve_resource_dependencies(mode_definition.resource_defs)

        for level in toposort(resource_dependencies):
            for resource_name in level:
                resource_def = mode_definition.resource_defs[resource_name]
                if not resource_name in resource_keys_to_init:
                    continue

                resource_context = InitResourceContext(
                    resource_def=resource_def,
                    resource_config=environment_config.resources.get(resource_name, {}).get(
                        "config"
                    ),
                    pipeline_run=pipeline_run,
                    # Add tags with information about the resource
                    log_manager=resource_log_manager.with_tags(
                        resource_name=resource_name,
                        resource_fn_name=str(resource_def.resource_fn.__name__),
                    ),
                    resource_instance_dict=resource_instances,
                    required_resource_keys=resource_def.required_resource_keys,
                    instance_for_backwards_compat=instance,
                    pipeline_def_for_backwards_compat=pipeline_def,
                )
                manager = single_resource_generation_manager(
                    resource_context, resource_name, resource_def
                )
                for event in manager.generate_setup_events():
                    if event:
                        yield event
                initialized_resource = check.inst(manager.get_object(), InitializedResource)
                resource_instances[resource_name] = initialized_resource.resource
                resource_init_times[resource_name] = initialized_resource.duration
                resource_managers.append(manager)

        if resource_keys_to_init:
            yield DagsterEvent.resource_init_success(
                execution_plan, resource_log_manager, resource_instances, resource_init_times
            )
        yield ScopedResourcesBuilder(resource_instances)
    except DagsterUserCodeExecutionError as dagster_user_error:
        yield DagsterEvent.resource_init_failure(
            execution_plan,
            resource_log_manager,
            resource_keys_to_init,
            serializable_error_info_from_exc_info(dagster_user_error.original_exc_info),
        )
        raise dagster_user_error
Esempio n. 7
0
 def get_all_steps_by_level(self) -> List[List[IExecutionStep]]:
     return [[
         self.get_step_by_key(step_key)
         for step_key in sorted(step_key_level)
     ] for step_key_level in toposort(self.get_all_step_deps())]
Esempio n. 8
0
 def execution_step_levels(self):
     return [[
         self.step_dict[step_key] for step_key in sorted(step_key_level)
     ] for step_key_level in toposort(self.execution_deps())]
Esempio n. 9
0
 def get_steps_to_execute_by_level(self):
     return [[
         self.get_step_by_key(step_key)
         for step_key in sorted(step_key_level)
     ] for step_key_level in toposort(self.get_executable_step_deps())]
Esempio n. 10
0
 def get_all_steps_by_level(self):
     return [[
         self.get_step_by_key(step_key)
         for step_key in sorted(step_key_level)
     ] for step_key_level in toposort(self.get_all_step_deps())]
Esempio n. 11
0
def _core_resource_initialization_event_generator(
    resource_defs: Dict[str, ResourceDefinition],
    resource_configs: Dict[str, ResourceConfig],
    resource_log_manager: DagsterLogManager,
    resource_managers: Deque[EventGenerationManager],
    execution_plan: Optional[ExecutionPlan],
    pipeline_run: Optional[PipelineRun],
    resource_keys_to_init: Optional[AbstractSet[str]],
    instance: Optional[DagsterInstance],
    emit_persistent_events: Optional[bool],
    pipeline_def_for_backwards_compat: Optional[PipelineDefinition],
):

    pipeline_name = None
    contains_generator = False
    if emit_persistent_events:
        check.invariant(
            pipeline_run and execution_plan,
            "If emit_persistent_events is enabled, then pipeline_run and execution_plan must be provided",
        )
        pipeline_name = cast(PipelineRun, pipeline_run).pipeline_name
    resource_keys_to_init = check.opt_set_param(resource_keys_to_init,
                                                "resource_keys_to_init")
    resource_instances: Dict[str, "InitializedResource"] = {}
    resource_init_times = {}
    try:
        if emit_persistent_events and resource_keys_to_init:
            yield DagsterEvent.resource_init_start(
                cast(str, pipeline_name),
                cast(ExecutionPlan, execution_plan),
                resource_log_manager,
                resource_keys_to_init,
            )

        resource_dependencies = _resolve_resource_dependencies(resource_defs)

        for level in toposort(resource_dependencies):
            for resource_name in level:
                resource_def = resource_defs[resource_name]
                if not resource_name in resource_keys_to_init:
                    continue

                resource_fn = cast(Callable[[InitResourceContext], Any],
                                   resource_def.resource_fn)
                resources = ScopedResourcesBuilder(resource_instances).build(
                    resource_def.required_resource_keys)
                resource_context = InitResourceContext(
                    resource_def=resource_def,
                    resource_config=resource_configs[resource_name].config,
                    pipeline_run=pipeline_run,
                    # Add tags with information about the resource
                    log_manager=resource_log_manager.with_tags(
                        resource_name=resource_name,
                        resource_fn_name=str(resource_fn.__name__),
                    ),
                    resources=resources,
                    instance=instance,
                    pipeline_def_for_backwards_compat=
                    pipeline_def_for_backwards_compat,
                )
                manager = single_resource_generation_manager(
                    resource_context, resource_name, resource_def)
                for event in manager.generate_setup_events():
                    if event:
                        yield event
                initialized_resource = check.inst(manager.get_object(),
                                                  InitializedResource)
                resource_instances[
                    resource_name] = initialized_resource.resource
                resource_init_times[
                    resource_name] = initialized_resource.duration
                contains_generator = contains_generator or initialized_resource.is_generator
                resource_managers.append(manager)

        if emit_persistent_events and resource_keys_to_init:
            yield DagsterEvent.resource_init_success(
                cast(str, pipeline_name),
                cast(ExecutionPlan, execution_plan),
                resource_log_manager,
                resource_instances,
                resource_init_times,
            )
        yield ScopedResourcesBuilder(resource_instances, contains_generator)
    except DagsterUserCodeExecutionError as dagster_user_error:
        # Can only end up in this state if we attempt to initialize a resource, so
        # resource_keys_to_init cannot be empty
        if emit_persistent_events:
            yield DagsterEvent.resource_init_failure(
                cast(str, pipeline_name),
                cast(ExecutionPlan, execution_plan),
                resource_log_manager,
                resource_keys_to_init,
                serializable_error_info_from_exc_info(
                    dagster_user_error.original_exc_info),
            )
        raise dagster_user_error