_local

Local Bakend

This backend runs Fractal workflows using FractalThreadPoolExecutor (a custom version of Python ThreadPoolExecutor) to run tasks in several threads. Incidentally, it also represents the reference implementation for a backend.

_process_workflow(*, workflow, dataset, logger_name, workflow_dir_local, first_task_index, last_task_index)

Internal processing routine

Schedules the workflow using a FractalThreadPoolExecutor.

Cf. process_workflow for the call signature.

Source code in fractal_server/app/runner/v2/_local/__init__.py

def _process_workflow(
    *,
    workflow: WorkflowV2,
    dataset: DatasetV2,
    logger_name: str,
    workflow_dir_local: Path,
    first_task_index: int,
    last_task_index: int,
) -> dict:
    """
    Internal processing routine

    Schedules the workflow using a `FractalThreadPoolExecutor`.

    Cf.
    [process_workflow][fractal_server.app.runner.v2._local.process_workflow]
    for the call signature.
    """

    with FractalThreadPoolExecutor() as executor:
        new_dataset_attributes = execute_tasks_v2(
            wf_task_list=workflow.task_list[
                first_task_index : (last_task_index + 1)  # noqa
            ],  # noqa
            dataset=dataset,
            executor=executor,
            workflow_dir_local=workflow_dir_local,
            workflow_dir_remote=workflow_dir_local,
            logger_name=logger_name,
            submit_setup_call=_local_submit_setup,
        )
    return new_dataset_attributes

process_workflow(*, workflow, dataset, workflow_dir_local, workflow_dir_remote=None, first_task_index=None, last_task_index=None, logger_name, user_cache_dir=None, slurm_user=None, slurm_account=None, worker_init=None) async

Run a workflow

This function is responsible for running a workflow on some input data, saving the output and taking care of any exception raised during the run.

NOTE: This is the local backend's public interface, which also works as a reference implementation for other backends.

Parameters:

Name	Type	Description	Default
workflow	WorkflowV2	The workflow to be run	required
dataset	DatasetV2	Initial dataset.	required
workflow_dir_local	Path	Working directory for this run.	required
workflow_dir_remote	Optional[Path]	Working directory for this run, on the user side. This argument is present for compatibility with the standard backend interface, but for the local backend it cannot be different from workflow_dir_local.	None
first_task_index	Optional[int]	Positional index of the first task to execute; if None, start from 0.	None
last_task_index	Optional[int]	Positional index of the last task to execute; if None, proceed until the last task.	None
logger_name	str	Logger name	required
slurm_user	Optional[str]	Username to impersonate to run the workflow. This argument is present for compatibility with the standard backend interface, but is ignored in the local backend.	None
slurm_account	Optional[str]	SLURM account to use when running the workflow. This argument is present for compatibility with the standard backend interface, but is ignored in the local backend.	None
user_cache_dir	Optional[str]	Cache directory of the user who will run the workflow. This argument is present for compatibility with the standard backend interface, but is ignored in the local backend.	None
worker_init	Optional[str]	Any additional, usually backend specific, information to be passed to the backend executor. This argument is present for compatibility with the standard backend interface, but is ignored in the local backend.	None

Raises:

Type	Description
TaskExecutionError	wrapper for errors raised during tasks' execution (positive exit codes).
JobExecutionError	wrapper for errors raised by the tasks' executors (negative exit codes).

Returns:

Name	Type	Description
output_dataset_metadata	dict	The updated metadata for the dataset, as returned by the last task of the workflow

Source code in fractal_server/app/runner/v2/_local/__init__.py

async def process_workflow(
    *,
    workflow: WorkflowV2,
    dataset: DatasetV2,
    workflow_dir_local: Path,
    workflow_dir_remote: Optional[Path] = None,
    first_task_index: Optional[int] = None,
    last_task_index: Optional[int] = None,
    logger_name: str,
    # Slurm-specific
    user_cache_dir: Optional[str] = None,
    slurm_user: Optional[str] = None,
    slurm_account: Optional[str] = None,
    worker_init: Optional[str] = None,
) -> dict:
    """
    Run a workflow

    This function is responsible for running a workflow on some input data,
    saving the output and taking care of any exception raised during the run.

    NOTE: This is the `local` backend's public interface, which also works as
    a reference implementation for other backends.

    Args:
        workflow:
            The workflow to be run
        dataset:
            Initial dataset.
        workflow_dir_local:
            Working directory for this run.
        workflow_dir_remote:
            Working directory for this run, on the user side. This argument is
            present for compatibility with the standard backend interface, but
            for the `local` backend it cannot be different from
            `workflow_dir_local`.
        first_task_index:
            Positional index of the first task to execute; if `None`, start
            from `0`.
        last_task_index:
            Positional index of the last task to execute; if `None`, proceed
            until the last task.
        logger_name: Logger name
        slurm_user:
            Username to impersonate to run the workflow. This argument is
            present for compatibility with the standard backend interface, but
            is ignored in the `local` backend.
        slurm_account:
            SLURM account to use when running the workflow. This argument is
            present for compatibility with the standard backend interface, but
            is ignored in the `local` backend.
        user_cache_dir:
            Cache directory of the user who will run the workflow. This
            argument is present for compatibility with the standard backend
            interface, but is ignored in the `local` backend.
        worker_init:
            Any additional, usually backend specific, information to be passed
            to the backend executor. This argument is present for compatibility
            with the standard backend interface, but is ignored in the `local`
            backend.

    Raises:
        TaskExecutionError: wrapper for errors raised during tasks' execution
                            (positive exit codes).
        JobExecutionError: wrapper for errors raised by the tasks' executors
                           (negative exit codes).

    Returns:
        output_dataset_metadata:
            The updated metadata for the dataset, as returned by the last task
            of the workflow
    """

    if workflow_dir_remote and (workflow_dir_remote != workflow_dir_local):
        raise NotImplementedError(
            "Local backend does not support different directories "
            f"{workflow_dir_local=} and {workflow_dir_remote=}"
        )

    # Set values of first_task_index and last_task_index
    num_tasks = len(workflow.task_list)
    first_task_index, last_task_index = set_start_and_last_task_index(
        num_tasks,
        first_task_index=first_task_index,
        last_task_index=last_task_index,
    )

    new_dataset_attributes = await async_wrap(_process_workflow)(
        workflow=workflow,
        dataset=dataset,
        logger_name=logger_name,
        workflow_dir_local=workflow_dir_local,
        first_task_index=first_task_index,
        last_task_index=last_task_index,
    )
    return new_dataset_attributes