parsl.executors.ExtremeScaleExecutor

class parsl.executors.ExtremeScaleExecutor(label='ExtremeScaleExecutor', provider=LocalProvider( channel=LocalChannel( envs={}, script_dir=None, userhome='/home/docs/checkouts/readthedocs.org/user_builds/parsl/checkouts/latest/docs' ), cmd_timeout=30, init_blocks=4, launcher=SingleNodeLauncher(), max_blocks=10, min_blocks=0, move_files=None, nodes_per_block=1, parallelism=1, walltime='00:15:00', worker_init='' ), launch_cmd=None, address='127.0.0.1', worker_ports=None, worker_port_range=(54000, 55000), interchange_port_range=(55000, 56000), storage_access=None, working_dir=None, worker_debug=False, ranks_per_node=1, heartbeat_threshold=120, heartbeat_period=30, managed=True)[source]

Executor designed for leadership class supercomputer scale

The ExtremeScaleExecutor extends the Executor interface to enable task execution on supercomputing systems (>1K Nodes). When functions and their arguments are submitted to the interface, a future is returned that tracks the execution of the function on a distributed compute environment.

The ExtremeScaleExecutor system has the following components:
  1. The ExtremeScaleExecutor instance which is run as part of the Parsl script
  2. The Interchange which is acts as a load-balancing proxy between workers and Parsl
  3. The MPI based mpi_worker_pool which coordinates task execution over several nodes With MPI communication between workers, we can exploit low latency networking on HPC systems.
  4. ZeroMQ pipes that connect the ExtremeScaleExecutor, Interchange and the mpi_worker_pool

Our design assumes that there is a single MPI application (mpi_worker_pool) running over a block and that there might be several such instances.

Here is a diagram

             |  Data   |  Executor   |  Interchange  | External Process(es)
             |  Flow   |             |               |
        Task | Kernel  |             |               |
      +----->|-------->|------------>|->outgoing_q---|-> mpi_worker_pool
      |      |         |             | batching      |    |         |
Parsl<---Fut-|         |             | load-balancing|  result   exception
          ^  |         |             | watchdogs     |    |         |
          |  |         |   Q_mngmnt  |               |    V         V
          |  |         |    Thread<--|-incoming_q<---|--- +---------+
          |  |         |      |      |               |
          |  |         |      |      |               |
          +----update_fut-----+
Parameters:
  • provider (ExecutionProvider) –
    Provider to access computation resources. Can be any providers in parsl.providers:
    Cobalt, Condor, GoogleCloud, GridEngine, Jetstream, Local, GridEngine, Slurm, or Torque.
  • label (str) – Label for this executor instance.
  • launch_cmd (str) – Command line string to launch the mpi_worker_pool from the provider.
  • address (string) – An address to connect to the main Parsl process which is reachable from the network in which workers will be running. This can be either a hostname as returned by hostname or an IP address. Most login nodes on clusters have several network interfaces available, only some of which can be reached from the compute nodes. Some trial and error might be necessary to indentify what addresses are reachable from compute nodes.
  • worker_ports ((int, int)) – Specify the ports to be used by workers to connect to Parsl. If this option is specified, worker_port_range will not be honored.
  • worker_port_range ((int, int)) – Worker ports will be chosen between the two integers provided.
  • interchange_port_range ((int, int)) – Port range used by Parsl to communicate with the Interchange.
  • working_dir (str) – Working dir to be used by the executor.
  • worker_debug (Bool) – Enables engine debug logging.
  • managed (Bool) – If this executor is managed by the DFK or externally handled.
  • ranks_per_node (int) – Specify the ranks to be launched per node.
  • heartbeat_threshold (int) – Seconds since the last message from the counterpart in the communication pair: (interchange, manager) after which the counterpart is assumed to be un-available. Default:120s
  • heartbeat_period (int) – Number of seconds after which a heartbeat message indicating liveness is sent to the counterpart (interchange, manager). Default:30s
__init__(label='ExtremeScaleExecutor', provider=LocalProvider( channel=LocalChannel( envs={}, script_dir=None, userhome='/home/docs/checkouts/readthedocs.org/user_builds/parsl/checkouts/latest/docs' ), cmd_timeout=30, init_blocks=4, launcher=SingleNodeLauncher(), max_blocks=10, min_blocks=0, move_files=None, nodes_per_block=1, parallelism=1, walltime='00:15:00', worker_init='' ), launch_cmd=None, address='127.0.0.1', worker_ports=None, worker_port_range=(54000, 55000), interchange_port_range=(55000, 56000), storage_access=None, working_dir=None, worker_debug=False, ranks_per_node=1, heartbeat_threshold=120, heartbeat_period=30, managed=True)[source]

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__([label, provider, launch_cmd, …]) Initialize self.
hold_worker(worker_id) Puts the workers on hold, preventing scheduling of additional tasks to it.
scale_in(blocks) Scale in the number of active blocks by specified amount.
scale_out([blocks]) Scales out the number of blocks by “blocks”
shutdown([hub, targets, block]) Shutdown the executor, including all workers and controllers.
start() Create the Interchange process and connect to it.
status() Return status of all blocks.
submit(func, *args, **kwargs) Submits work to the the outgoing_q.
weakref_cb([q]) We do not use this yet.

Attributes

connected_workers
outstanding
run_dir Path to the run directory.
scaling_enabled Specify if scaling is enabled.