def test_several_periodic_action_on_computation():
a = Agent("a", MagicMock())
class TestComputation(MessagePassingComputation):
def __init__(self):
super().__init__("test")
self.mock1 = MagicMock()
self.mock2 = MagicMock()
def on_start(self):
self.add_periodic_action(0.1, self.action1)
self.add_periodic_action(0.2, self.action2)
def action1(self):
self.mock1()
def action2(self):
self.mock2()
c = TestComputation()
a.add_computation(c)
a.start()
a.run()
sleep(0.25)
a.stop()
assert 1 <= c.mock1.call_count <= 2
assert c.mock2.call_count == 1
def test_periodic_action_not_called_when_paused():
a = Agent("a", MagicMock())
class TestComputation(MessagePassingComputation):
def __init__(self):
super().__init__("test")
self.mock = MagicMock()
def on_start(self):
self.add_periodic_action(0.1, self.action)
def action(self):
self.mock()
c = TestComputation()
a.add_computation(c)
a.start()
a.run()
sleep(0.25)
assert 1 <= c.mock.call_count <= 2
c.mock.reset_mock()
a.pause_computations("test")
sleep(0.25)
assert c.mock.call_count == 0
a.stop()
def test_oneshot_delayed_action_on_computation():
# To implement a one-shot action, add a periodic action and remove it
# the first time it is called:
a = Agent("a", MagicMock())
class TestComputation(MessagePassingComputation):
def __init__(self):
super().__init__("test")
self.mock = MagicMock()
def on_start(self):
self.handle = self.add_periodic_action(0.1, self.action)
def action(self):
self.mock()
self.remove_periodic_action(self.handle)
c = TestComputation()
a.add_computation(c)
a.start()
a.run()
sleep(0.25)
# the action is remove on firts call there must be one single call
assert c.mock.call_count == 1
c.mock.reset_mock()
sleep(0.2)
c.mock.assert_not_called()
a.stop()
def test_remove_periodic_action_on_computation():
a = Agent("a", MagicMock())
class TestComputation(MessagePassingComputation):
def __init__(self):
super().__init__("test")
self.mock = MagicMock()
def on_start(self):
self.handle = self.add_periodic_action(0.1, self.action)
def action(self):
self.mock()
def test_remove(self):
self.remove_periodic_action(self.handle)
c = TestComputation()
a.add_computation(c)
a.start()
a.run()
sleep(0.25)
assert c.mock.call_count == 2
c.test_remove()
c.mock.reset_mock()
sleep(0.5)
c.mock.assert_not_called()
a.stop()
def directory_discovery():
# Agent hosting the directory
agt_dir = Agent('agt_dir', InProcessCommunicationLayer())
directory = Directory(agt_dir.discovery)
agt_dir.add_computation(directory.directory_computation)
agt_dir.discovery.use_directory('agt_dir', agt_dir.address)
agt_dir.start()
agt_dir.run(directory.directory_computation.name)
# standard agents
agt1 = Agent('agt1', InProcessCommunicationLayer())
agt1.discovery.use_directory('agt_dir', agt_dir.address)
agt1.start()
agt2 = Agent('agt2', InProcessCommunicationLayer())
agt2.discovery.use_directory('agt_dir', agt_dir.address)
agt2.start()
yield agt_dir, agt1, agt2
for c in agt1.computations():
agt1.remove_computation(c.name)
for c in agt1.discovery.agent_computations(agt1.name):
agt1.discovery.unregister_computation(c)
for c in agt2.computations():
agt2.remove_computation(c.name)
for c in agt2.discovery.agent_computations(agt2.name):
agt2.discovery.unregister_computation(c)
wait_run()
agt1.stop()
agt2.stop()
agt_dir.stop()
def agents():
# Agent hosting the directory
agt_dir = Agent('agt_dir', InProcessCommunicationLayer())
directory = Directory(agt_dir.discovery)
agt_dir.add_computation(directory.directory_computation)
agt_dir.discovery.use_directory('agt_dir', agt_dir.address)
agt_dir.start()
agt_dir.run(directory.directory_computation.name)
# standard agents
agt1 = Agent('agt1', InProcessCommunicationLayer())
agt1.discovery.use_directory('agt_dir', agt_dir.address)
agt1.start()
agt2 = Agent('agt2', InProcessCommunicationLayer())
agt2.discovery.use_directory('agt_dir', agt_dir.address)
agt2.start()
yield agt_dir, agt1, agt2
agt1.stop()
agt2.stop()
agt_dir.stop()
def test_periodic_action_on_computation():
a = Agent("a", MagicMock())
class TestComputation(MessagePassingComputation):
def __init__(self):
super().__init__("test")
self.mock = MagicMock()
def on_start(self):
self.add_periodic_action(0.1, self.action)
def action(self):
self.mock()
c = TestComputation()
a.add_computation(c)
a.start()
a.run()
sleep(0.25)
a.stop()
assert c.mock.call_count == 2
class Orchestrator(object):
"""
Centralized organisation of the set of agents used to solve a dcop.
Notes
-----
Central orchestration is only used for bootstrapping the system and to
collect metrics.
As the orchestrator will generally run in a separate process, it uses an
agent object and communicates with other agents using messages.
Main responsibilities:
* deploying the computations
* collecting metrics
* running and stopping agents (note that the orchestrator does not
create nor start agents, it just request them to run their computations)
A typical use scenario:
* create and start the agents for the dcop (thread or process based)
* create the orchestrator, giving him the dcop and its distribution on
agents
* deploy the computations
* run the computations
* stop everything
Examples
--------
orchestrator.start()
orchestrator.deploy_computations()
orchestrator.start_replication() # only needed for resilient system
orchestrator.run()`
orchestrator.stop_agents()`
orchestrator.stop()`
Parameters
----------
algo: AlgorithmDef,
algorithm used to solve the dcop
cg: ComputationGraph,
computation graph
agent_mapping: Distribution,
initial distribution of computations on agents
comm: CommunicationLayer,
An instance of communication layer object
dcop: DCOP
The DCOP
infinity=float
infinity
collector: Queue
A queue used to collect metrics
collect_moment: str
metrics collection mode (e.g. 'value_change')
"""
def __init__(self, algo: AlgorithmDef, cg: ComputationGraph,
agent_mapping: Distribution,
comm: CommunicationLayer,
dcop: DCOP,
infinity=float('inf'),
collector: Queue=None,
collect_moment: str='value_change',
collect_period: float=None,
ui_port: int = None):
self._own_agt = Agent(ORCHESTRATOR, comm, ui_port=ui_port)
self.directory = Directory(self._own_agt.discovery)
self._own_agt.add_computation(self.directory.directory_computation)
self._own_agt.discovery.use_directory(ORCHESTRATOR,
self._own_agt.address)
self.discovery = self._own_agt.discovery
self.messaging = comm.messaging
self.logger = self._own_agt.logger
self.dcop = dcop
self.status = 'OK'
# For scenario execution
self._events_iterator = None
self._event_timer = None # type: threading.Timer
self._timeout_timer = None
self._stopping = threading.Event()
self.mgt = AgentsMgt(algo, cg, agent_mapping, dcop,
self._own_agt, self, infinity, collector=collector,
collect_moment=collect_moment,
collect_period=collect_period)
@property
def address(self):
return self._own_agt.address
def set_error_handler(self, callback: Callable):
"""
Set a callback that will be called if the orchestrator thread stops
due to an unexpected error.
Parameters
----------
callback: a signle-argument callable
the callback must accept a single argument, which will the the
exception that caused the orchestrator thread to stop.
"""
self._own_agt.on_fatal_error = callback
def start(self):
"""
Start the orchestrator.
Notes
-----
The orchestrator, and it's directory, must be
started in order to receive registration messages, which means you
must always start the orchestrator before the agents.
"""
self._own_agt.start()
self._own_agt.run(self.directory.directory_computation.name)
self._own_agt.add_computation(self.mgt, ORCHESTRATOR_MGT)
self._own_agt.run(self.mgt.name)
def stop(self):
"""
Stop the orchestrator.
Notes
-----
Once stopped, the orchestrator will not receive
nor send any new message. This means that agents must be stopped before
stopping the orchestrator.
"""
self.logger.info('Requesting orchestrator to stop')
self._own_agt.stop()
if self._event_timer is not None:
self._event_timer.cancel()
self._event_timer = None
def deploy_computations(self, once_registered=True):
"""
Deploy the computation for the dcop.
The computations are deployed according to the Computation Graph
and the initial distribution (given to the Orchestrator's constructor).
Parameters
----------
once_registered: bool
wait until all agents have registered before starting deployment.
"""
if once_registered:
self.logger.info('Waiting for all registration before deploying '
'computations')
self.mgt.all_registered.wait()
self.logger.info('deploying computations')
self._mgt_method('_orchestrator_deploy_computations', None)
def start_replication(self, k_target: int):
"""
Ask all agents to replicate their computations.
Notes
-----
deploy_computations must be called before, otherwise agents have no
computation to replicate !
Parameters
----------
k_target: int
number of replica for each computation (aka resiliency level).
"""
# We must be sure computations have been deployed first
self.logger.info('Waiting until agents are ready to run before '
'starting replication')
self.mgt.ready_to_run.wait()
self.mgt.ready_to_run = threading.Event()
self.logger.info('Starting replication')
self._mgt_method('_orchestrator_start_replication', k_target)
def run(self, scenario: Scenario=None,
timeout: Optional[float]=None, repair_only=False):
"""Run the DCOP, with a scenario if given.
When `run()` is called, the orchestrator asks all orchestrated agents to
start their computations. If the agents are not ready, the orchestrator
automatically waits until agents are ready (i.e. computations have
been deployed).
Parameters
----------
scenario: Scenario
an optional Scenario object whose events will be injected into
the system.
timeout: float
time, in seconds, after which all agents, and the orchestrator
itself, must be stopped.
"""
self.repair_only = repair_only
self.logger.info('Waiting until agents are ready to run')
self.mgt.ready_to_run.wait()
self.logger.info('Requesting agents to run')
self._mgt_method('_orchestrator_run_computations', None)
if timeout is not None:
self.logger.info('Setting timer for %s timeour ', timeout)
self._timeout_timer = threading.Timer(timeout,
self._on_timeout)
self._timeout_timer.daemon = True
self._timeout_timer.start()
self.mgt.ready_to_run = threading.Event()
else:
self.logger.info('Not timeout, stop with ctrl+c or on algo end ')
if scenario is not None:
self.logger.info('Setting scenario ')
self._events_iterator = iter(scenario)
self._process_event()
else:
self.logger.info('No scenario ')
self.mgt.wait_stop_agents()
self._own_agt.clean_shutdown()
self._own_agt.join()
def stop_agents(self, timeout: float):
self.logger.info('Requesting all agents to stop')
self._stopping.set()
# WARNING: must NOT access the mgt directly, all its action
# must be done in the agent's tread. That's the reason we use a msg
# here. It must have MSG_MGT type to have higher priority, in case the
# orchestrator's queue is full of other messages.
if self._event_timer is not None:
self._event_timer.cancel()
self._event_timer = None
self._mgt_method('_orchestrator_stop_agents', None)
self.mgt.wait_stop_agents(timeout)
self.mgt.ready_to_run.set()
def current_global_cost(self):
return self.mgt.current_global_cost()
def current_solution(self):
return self.mgt.current_solution()
def end_metrics(self):
return self.mgt.global_metrics('END', self.mgt.last_agt_stop_time)
def replication_metrics(self):
return self.mgt._replication_metrics
def wait_ready(self):
"""Blocks until the Orchestrator is ready to perform another action.
This can be used to wait until the dcop has finished running,
for example when using a timeout.
Notes
-----
When calling `wait_ready` after `run()` with a timeout, you may be
blocked for a longer time than the timeout, as orchestrator also wait
until all agents have stopped.
Examples
--------
orchestrator.run(timeout=5)
orchestrator.wait_ready()
"""
self.mgt.ready_to_run.wait()
return self._own_agt.is_running and not self._stopping.is_set()
def _process_event(self):
# FIXME: hack too avoid overlapping events
waited = [a for a, state in self.mgt._agts_state.items()
if state != 'running']
if waited:
self.logger.warning(f"Event while agents {waited} are still processing"
f" previous event, wait 20 s ")
self._event_timer = threading.Timer(20, self._process_event)
self._event_timer.start()
return
try:
evt = next(self._events_iterator)
except StopIteration:
self.logger.info("All events processed for scenario")
self._events_iterator = None
return
if evt.is_delay:
self.logger.info('Delay: wait %s s for next event', evt.delay)
self._event_timer = threading.Timer(evt.delay, self._process_event)
self._event_timer.start()
else:
self.logger.info('posting event to mgt %s', evt)
self._mgt_method('_orchestrator_scenario_event', evt)
self._process_event()
def _mgt_method(self, method: str, arg: Any):
self.messaging.post_msg(
ORCHESTRATOR_MGT, ORCHESTRATOR_MGT,
Message(method, arg), msg_type=5)
def _on_timeout(self):
"""Run timeout callback"""
self.status = "TIMEOUT"
self.logger.info("Timeout, requesting agents to stop")
self.stop_agents(5)
self.mgt.ready_to_run.set()