def test_json(self):
a = {"d": [1, 2, "v"], "p": 1}
b = {"a": "b"}
rs = ResultSet()
rs.add(a, b)
rs.add(b, a)
assert [[a, b], [b, a]] == eval(rs.json())
def test_json(self):
a = {"d": [1, 2, "v"], "p": 1}
b = {"a": "b"}
rs = ResultSet()
rs.add(a, b)
rs.add(b, a)
self.assertEqual([[a, b], [b, a]], eval(rs.json()))
class Orchestrator(object):
"""Orchestrator.
It is responsible for orchestrating the execution of all experiments and
aggregate results.
"""
def __init__(self, settings, summary_freq=4):
"""Constructor
Parameters
----------
settings : Settings
The settings of the simulator
summary_freq : int
Frequency (in number of experiment) at which summary messages
are displayed
"""
self.settings = settings
self.results = ResultSet()
self.seq = SequenceNumber()
self.exp_durations = collections.deque(maxlen=30)
self.n_success = 0
self.n_fail = 0
self.summary_freq = summary_freq
self._stop = False
if self.settings.PARALLEL_EXECUTION:
self.pool = mp.Pool(settings.N_PROCESSES)
def stop(self):
"""Stop the execution of the orchestrator
"""
logger.info('Orchestrator is stopping')
self._stop = True
if self.settings.PARALLEL_EXECUTION:
self.pool.terminate()
self.pool.join()
def run(self):
"""Run the orchestrator.
This call is blocking, whether multiple processes are used or not. This
methods returns only after all experiments are executed.
"""
# Create queue of experiment configurations
queue = collections.deque(self.settings.EXPERIMENT_QUEUE)
# Calculate number of experiments and number of processes
self.n_exp = len(queue) * self.settings.N_REPLICATIONS
self.n_proc = self.settings.N_PROCESSES \
if self.settings.PARALLEL_EXECUTION \
else 1
logger.info('Starting simulations: %d experiments, %d process(es)' %
(self.n_exp, self.n_proc))
if self.settings.PARALLEL_EXECUTION:
# This job queue is used only to keep track of which jobs have
# finished and which are still running. Currently this information
# is used only to handle keyboard interrupts correctly
job_queue = collections.deque()
# Schedule experiments from the queue
while queue:
experiment = queue.popleft()
for _ in range(self.settings.N_REPLICATIONS):
job_queue.append(
self.pool.apply_async(
run_scenario,
args=(self.settings, experiment, self.seq.assign(),
self.n_exp),
callback=self.experiment_callback))
self.pool.close()
# This solution is probably not optimal, but at least makes
# KeyboardInterrupt work fine, which is crucial if launching the
# simulation remotely via screen.
# What happens here is that we keep waiting for possible
# KeyboardInterrupts till the last process terminates successfully.
# We may have to wait up to 5 seconds after the last process
# terminates before exiting, which is really negligible
try:
while job_queue:
job = job_queue.popleft()
while not job.ready():
time.sleep(5)
except KeyboardInterrupt:
self.pool.terminate()
self.pool.join()
else: # Single-process execution
while queue:
experiment = queue.popleft()
for _ in range(self.settings.N_REPLICATIONS):
self.experiment_callback(
run_scenario(self.settings, experiment,
self.seq.assign(), self.n_exp))
if self._stop:
self.stop()
logger.info(
'END | Planned: %d, Completed: %d, Succeeded: %d, Failed: %d',
self.n_exp, self.n_fail + self.n_success, self.n_success,
self.n_fail)
def experiment_callback(self, args):
"""Callback method called by run_scenario
Parameters
----------
args : tuple
Tuple of arguments
"""
# If args is None, that means that an exception was raised during the
# execution of the experiment. In such case, ignore it
if not args:
self.n_fail += 1
return
# Extract parameters
params, results, duration = args
self.n_success += 1
# Store results
self.results.add(params, results)
self.exp_durations.append(duration)
if self.n_success % self.summary_freq == 0:
# Number of experiments scheduled to be executed
n_scheduled = self.n_exp - (self.n_fail + self.n_success)
# Compute ETA
n_cores = min(mp.cpu_count(), self.n_proc)
mean_duration = sum(self.exp_durations) / len(self.exp_durations)
eta = timestr(n_scheduled * mean_duration / n_cores, False)
# Print summary
logger.info(
'SUMMARY | Completed: %d, Failed: %d, Scheduled: %d, ETA: %s',
self.n_success, self.n_fail, n_scheduled, eta)
class Orchestrator(object):
"""Orchestrator.
It is responsible for orchestrating the execution of all experiments and
aggregate results.
"""
def __init__(self, settings, summary_freq=4):
"""Constructor
Parameters
----------
settings : Settings
The settings of the simulator
summary_freq : int
Frequency (in number of experiment) at which summary messages
are displayed
"""
self.settings = settings
self.results = ResultSet()
self.seq = SequenceNumber()
self.exp_durations = collections.deque(maxlen=30)
self.n_success = 0
self.n_fail = 0
self.summary_freq = summary_freq
self._stop = False
if self.settings.PARALLEL_EXECUTION:
self.pool = mp.Pool(settings.N_PROCESSES)
def stop(self):
"""Stop the execution of the orchestrator
"""
logger.info('Orchestrator is stopping')
self._stop = True
if self.settings.PARALLEL_EXECUTION:
self.pool.terminate()
self.pool.join()
def run(self):
"""Run the orchestrator.
This call is blocking, whether multiple processes are used or not. This
methods returns only after all experiments are executed.
"""
# Create queue of experiment configurations
queue = collections.deque(self.settings.EXPERIMENT_QUEUE)
# Calculate number of experiments and number of processes
self.n_exp = len(queue) * self.settings.N_REPLICATIONS
self.n_proc = self.settings.N_PROCESSES \
if self.settings.PARALLEL_EXECUTION \
else 1
logger.info('Starting simulations: %d experiments, %d process(es)'
% (self.n_exp, self.n_proc))
if self.settings.PARALLEL_EXECUTION:
# This job queue is used only to keep track of which jobs have
# finished and which are still running. Currently this information
# is used only to handle keyboard interrupts correctly
job_queue = collections.deque()
# Schedule experiments from the queue
while queue:
experiment = queue.popleft()
for _ in range(self.settings.N_REPLICATIONS):
job_queue.append(self.pool.apply_async(run_scenario,
args=(self.settings, experiment,
self.seq.assign(), self.n_exp),
callback=self.experiment_callback))
self.pool.close()
# This solution is probably not optimal, but at least makes
# KeyboardInterrupt work fine, which is crucial if launching the
# simulation remotely via screen.
# What happens here is that we keep waiting for possible
# KeyboardInterrupts till the last process terminates successfully.
# We may have to wait up to 5 seconds after the last process
# terminates before exiting, which is really negligible
try:
while job_queue:
job = job_queue.popleft()
while not job.ready():
time.sleep(5)
except KeyboardInterrupt:
self.pool.terminate()
self.pool.join()
else: # Single-process execution
while queue:
experiment = queue.popleft()
for _ in range(self.settings.N_REPLICATIONS):
self.experiment_callback(run_scenario(self.settings,
experiment, self.seq.assign(),
self.n_exp))
if self._stop:
self.stop()
logger.info('END | Planned: %d, Completed: %d, Succeeded: %d, Failed: %d',
self.n_exp, self.n_fail + self.n_success, self.n_success, self.n_fail)
def experiment_callback(self, args):
"""Callback method called by run_scenario
Parameters
----------
args : tuple
Tuple of arguments
"""
# If args is None, that means that an exception was raised during the
# execution of the experiment. In such case, ignore it
if not args:
self.n_fail += 1
return
# Extract parameters
params, results, duration = args
self.n_success += 1
# Store results
self.results.add(params, results)
self.exp_durations.append(duration)
if self.n_success % self.summary_freq == 0:
# Number of experiments scheduled to be executed
n_scheduled = self.n_exp - (self.n_fail + self.n_success)
# Compute ETA
n_cores = min(mp.cpu_count(), self.n_proc)
mean_duration = sum(self.exp_durations)/len(self.exp_durations)
eta = timestr(n_scheduled*mean_duration/n_cores, False)
# Print summary
logger.info('SUMMARY | Completed: %d, Failed: %d, Scheduled: %d, ETA: %s',
self.n_success, self.n_fail, n_scheduled, eta)
class Orchestrator(object):
"""Orchestrator.
It is responsible for orchestrating the execution of all experiments and
aggregate results.
"""
def __init__(self, settings, summary_freq=4):
"""Constructor
Parameters
----------
settings : Settings
The settings of the simulator
summary_freq : int
Frequency (in number of experiment) at which summary messages
are displayed
"""
self.settings = settings
self.results = ResultSet()
self.seq = SequenceNumber()
self.exp_durations = collections.deque(maxlen=30)
self.summary_freq = summary_freq
self._stop = False
if settings.PARALLEL_EXECUTION:
self.pool = mp.Pool(settings.N_PROCESSES)
def stop(self):
"""Stop the execution of the orchestrator
"""
logger.info('Orchestrator is stopping')
self._stop = True
if self.settings.PARALLEL_EXECUTION:
self.pool.terminate()
self.pool.join()
def run(self):
"""Run the orchestrator.
This call is blocking, whether multiple processes are used or not. This
methods returns only after all experiments are executed.
"""
# Create queue of experiment configurations
if 'EXPERIMENT_QUEUE' in self.settings and self.settings.EXPERIMENT_QUEUE:
queue = collections.deque(self.settings.EXPERIMENT_QUEUE)
else:
queue = collections.deque()
n_contents = self.settings.N_CONTENTS
for topology_name in self.settings.TOPOLOGIES:
for network_cache in self.settings.NETWORK_CACHE:
for alpha in self.settings.ALPHA:
for strategy_name in self.settings.STRATEGIES:
params = dict(alpha=alpha,
topology_name=topology_name,
network_cache=network_cache,
strategy_name=strategy_name,
n_contents=n_contents,
strategy_params={})
queue.append(params)
# Calc number of experiments nad number of processes
self.n_exp = len(queue) * self.settings.N_REPLICATIONS
self.n_proc = self.settings.N_PROCESSES \
if self.settings.PARALLEL_EXECUTION \
else 1
logger.info('Starting simulations: %d experiments, %d process(es)'
% (self.n_exp, self.n_proc))
# Schedule experiments from the queue
while queue:
experiment = queue.popleft()
for _ in range(self.settings.N_REPLICATIONS):
if self.settings.PARALLEL_EXECUTION:
last_job = self.pool.apply_async(run_scenario,
args=(self.settings, experiment,
self.seq.assign(), self.n_exp),
callback=self.experiment_callback)
else:
self.experiment_callback(run_scenario(self.settings,
experiment, self.seq.assign(),
self.n_exp))
if self._stop:
self.stop()
# If parallel execution, wait for all processes to terminate
if self.settings.PARALLEL_EXECUTION:
self.pool.close()
# This solution is not optimal, but at least makes KeyboardInterrupt
# work fine, which is crucial if launching the simulation remotely
# via screen.
# What happens here is that we keep waiting for possible
# KeyboardInterrupts till the last scheduled process terminates
# successfully. The last scheduled process is not necessarily the last
# finishing one but nothing bad is going to happen in such case, it
# will only not be possible interrupting the simulation between the
# last scheduled process ends and the last ending process ends, which
# is likely a matter of seconds.
try:
while not last_job.ready(): time.sleep(5)
except KeyboardInterrupt:
self.pool.terminate()
self.pool.join()
return
self.pool.join()
def experiment_callback(self, args):
"""Callback method called by run_scenario
Parameters
----------
args : tuple
Tuple of arguments
"""
# Extract parameters
params, results, seq, duration = args
# Store results
self.results.add((params, results))
self.exp_durations.append(duration)
if seq % self.summary_freq == 0:
# Number of experiments scheduled to be executed
n_scheduled = self.n_exp - seq
# Compute ETA
n_cores = min(mp.cpu_count(), self.n_proc)
mean_duration = sum(self.exp_durations)/len(self.exp_durations)
eta = timestr(n_scheduled*mean_duration/n_cores, False)
# Print summary
logger.info('SUMMARY | Completed: %d, Scheduled: %d, ETA: %s',
seq, n_scheduled, eta)