def setUp(self):
data = open(
os.path.normpath(
os.path.join(
os.path.dirname(__file__),
"./resources/files/lifestage_single.json"))).read()
self.lifestage = LifeStage(json=data)
start_lat = 38
start_lon = -76
start_depth = -5
temp_time = datetime.utcnow()
self.start_time = datetime(temp_time.year, temp_time.month,
temp_time.day,
temp_time.hour).replace(tzinfo=pytz.utc)
self.loc = Location4D(latitude=start_lat,
longitude=start_lon,
depth=start_depth,
time=self.start_time)
self.particles = []
# Create particles
for i in range(0, 3):
p = LarvaParticle()
p.location = self.loc
self.particles.append(p)
# 48 timesteps at an hour each = 2 days of running
self.times = list(range(0, 172800, 3600)) # in seconds
self.temps = []
self.salts = []
for w in range(0, 48):
self.temps.append(random.randint(20, 40))
self.salts.append(random.randint(10, 30))
def setUp(self):
data = open(os.path.normpath(os.path.join(os.path.dirname(__file__), "./resources/files/lifestage_single.json"))).read()
self.lifestage = LifeStage(json=data)
start_lat = 38
start_lon = -76
start_depth = -5
temp_time = datetime.utcnow()
self.start_time = datetime(temp_time.year, temp_time.month, temp_time.day, temp_time.hour).replace(tzinfo=pytz.utc)
self.loc = Location4D(latitude=start_lat, longitude=start_lon, depth=start_depth, time=self.start_time)
self.particles = []
# Create particles
for i in xrange(0, 3):
p = LarvaParticle()
p.location = self.loc
self.particles.append(p)
# 48 timesteps at an hour each = 2 days of running
self.times = range(0, 172800, 3600) # in seconds
self.temps = []
self.salts = []
for w in xrange(0, 48):
self.temps.append(random.randint(20, 40))
self.salts.append(random.randint(10, 30))
class LarvaParticleTest(unittest.TestCase):
def setUp(self):
self.p = LarvaParticle()
def test_growth(self):
assert self.p.lifestage_index == 0
self.p.grow(0.5)
assert self.p.lifestage_index == 0
self.p.grow(0.5)
assert self.p.lifestage_index == 1
self.p.grow(0.5)
assert self.p.lifestage_index == 1
assert self.p.lifestage_progress == 1.5
def test_over_growth(self):
self.p.grow(1.5)
assert self.p.lifestage_index == 1
assert self.p.lifestage_progress == 1.5
self.p.grow(1.6)
assert self.p.lifestage_progress == 3.1
assert self.p.lifestage_index == 3
class LarvaParticleTest(unittest.TestCase):
def setUp(self):
self.p = LarvaParticle()
def test_growth(self):
assert self.p.lifestage_index == 0
self.p.grow(0.5)
assert self.p.lifestage_index == 0
self.p.grow(0.5)
assert self.p.lifestage_index == 1
self.p.grow(0.5)
assert self.p.lifestage_index == 1
assert self.p.lifestage_progress == 1.5
def test_over_growth(self):
self.p.grow(1.5)
assert self.p.lifestage_index == 1
assert self.p.lifestage_progress == 1.5
self.p.grow(1.6)
assert self.p.lifestage_progress == 3.1
assert self.p.lifestage_index == 3
def test_attempts(self):
start_lat = 38
start_lon = -76
settle = Settlement(json='{"upper": 100.0, "lower": 200.0, "type": "benthic"}')
# Particle above the upper bound
particle = LarvaParticle()
particle.location = Location4D(latitude=start_lat, longitude=start_lon, depth=-50, time=self.start_time)
# Set bathymetry BETWEEN lower (200) and upper (100)
settle.attempt(particle, -150)
# We should have moved vertically to the bottom and settled
assert particle.location.depth == -150
assert particle.location.latitude == particle.locations[-2].latitude
assert particle.location.longitude == particle.locations[-2].longitude
assert particle.location.time == particle.locations[-2].time
assert particle.settled
settle = Settlement(json='{"upper": 100.0, "lower": 200.0, "type": "benthic"}')
# Particle above the upper bound
particle = LarvaParticle()
particle.location = Location4D(latitude=start_lat, longitude=start_lon, depth=-250, time=self.start_time)
# Set bathymetry BELOW lower (200) and upper (100)
settle.attempt(particle, -400)
# We should not have moved
assert len(particle.locations) == 1
assert not particle.settled
settle = Settlement(json='{"upper": 100.0, "lower": 200.0, "type": "pelagic"}')
# Particle above the upper bound
particle = LarvaParticle()
particle.location = Location4D(latitude=start_lat, longitude=start_lon, depth=-50, time=self.start_time)
# Set bathymetry BELOW lower (200) and upper (100)
settle.attempt(particle, -400)
# We should not have moved
assert len(particle.locations) == 1
assert not particle.settled
settle = Settlement(json='{"upper": 100.0, "lower": 200.0, "type": "pelagic"}')
# Particle is between the upper and lower bounds
particle = LarvaParticle()
particle.location = Location4D(latitude=start_lat, longitude=start_lon, depth=-150, time=self.start_time)
# Set bathymetry BELOW lower (200) and upper (100)
settle.attempt(particle, -400)
# We should have settled, but not moved anywhere
assert len(particle.locations) == 1
assert particle.settled
def test_attempts(self):
start_lat = 38
start_lon = -76
settle = Settlement(
json='{"upper": 100.0, "lower": 200.0, "type": "benthic"}')
# Particle above the upper bound
particle = LarvaParticle()
particle.location = Location4D(latitude=start_lat,
longitude=start_lon,
depth=-50,
time=self.start_time)
# Set bathymetry BETWEEN lower (200) and upper (100)
settle.attempt(particle, -150)
# We should have moved vertically to the bottom and settled
assert particle.location.depth == -150
assert particle.location.latitude == particle.locations[-2].latitude
assert particle.location.longitude == particle.locations[-2].longitude
assert particle.location.time == particle.locations[-2].time
assert particle.settled
settle = Settlement(
json='{"upper": 100.0, "lower": 200.0, "type": "benthic"}')
# Particle above the upper bound
particle = LarvaParticle()
particle.location = Location4D(latitude=start_lat,
longitude=start_lon,
depth=-250,
time=self.start_time)
# Set bathymetry BELOW lower (200) and upper (100)
settle.attempt(particle, -400)
# We should not have moved
assert len(particle.locations) == 1
assert not particle.settled
settle = Settlement(
json='{"upper": 100.0, "lower": 200.0, "type": "pelagic"}')
# Particle above the upper bound
particle = LarvaParticle()
particle.location = Location4D(latitude=start_lat,
longitude=start_lon,
depth=-50,
time=self.start_time)
# Set bathymetry BELOW lower (200) and upper (100)
settle.attempt(particle, -400)
# We should not have moved
assert len(particle.locations) == 1
assert not particle.settled
settle = Settlement(
json='{"upper": 100.0, "lower": 200.0, "type": "pelagic"}')
# Particle is between the upper and lower bounds
particle = LarvaParticle()
particle.location = Location4D(latitude=start_lat,
longitude=start_lon,
depth=-150,
time=self.start_time)
# Set bathymetry BELOW lower (200) and upper (100)
settle.attempt(particle, -400)
# We should have settled, but not moved anywhere
assert len(particle.locations) == 1
assert particle.settled
def run(self, hydrodataset, **kwargs):
# Add ModelController description to logfile
logger.info(self)
# Add the model descriptions to logfile
for m in self._models:
logger.info(m)
# Calculate the model timesteps
# We need times = len(self._nstep) + 1 since data is stored one timestep
# after a particle is forced with the final timestep's data.
times = range(0, (self._step * self._nstep) + 1, self._step)
# Calculate a datetime object for each model timestep
# This method is duplicated in DataController and ForceParticle
# using the 'times' variables above. Will be useful in those other
# locations for particles released at different times
# i.e. released over a few days
modelTimestep, self.datetimes = AsaTransport.get_time_objects_from_model_timesteps(
times, start=self.start)
time_chunk = self._time_chunk
horiz_chunk = self._horiz_chunk
low_memory = kwargs.get("low_memory", False)
# Should we remove the cache file at the end of the run?
remove_cache = kwargs.get("remove_cache", True)
self.bathy_path = kwargs.get("bathy", None)
self.cache_path = kwargs.get("cache", None)
if self.cache_path is None:
# Generate temp filename for dataset cache
default_cache_dir = os.path.join(os.path.dirname(__file__),
"_cache")
temp_name = AsaRandom.filename(prefix=str(
datetime.now().microsecond),
suffix=".nc")
self.cache_path = os.path.join(default_cache_dir, temp_name)
logger.progress((1, "Setting up particle start locations"))
point_locations = []
if isinstance(self.geometry, Point):
point_locations = [self.reference_location] * self._npart
elif isinstance(self.geometry, Polygon) or isinstance(
self.geometry, MultiPolygon):
point_locations = [
Location4D(latitude=loc.y,
longitude=loc.x,
depth=self._depth,
time=self.start)
for loc in AsaTransport.fill_polygon_with_points(
goal=self._npart, polygon=self.geometry)
]
# Initialize the particles
logger.progress((2, "Initializing particles"))
for x in xrange(0, self._npart):
p = LarvaParticle(id=x)
p.location = point_locations[x]
# We don't need to fill the location gaps here for environment variables
# because the first data collected actually relates to this original
# position.
# We do need to fill in fields such as settled, halted, etc.
p.fill_status_gap()
# Set the inital note
p.note = p.outputstring()
p.notes.append(p.note)
self.particles.append(p)
# This is where it makes sense to implement the multiprocessing
# looping for particles and models. Can handle each particle in
# parallel probably.
#
# Get the number of cores (may take some tuning) and create that
# many workers then pass particles into the queue for the workers
mgr = multiprocessing.Manager()
nproc = multiprocessing.cpu_count() - 1
if nproc <= 0:
raise ValueError(
"Model does not run using less than two CPU cores")
# Each particle is a task, plus the DataController
number_of_tasks = len(self.particles) + 1
# We need a process for each particle and one for the data controller
nproc = min(number_of_tasks, nproc)
# When a particle requests data
data_request_lock = mgr.Lock()
# PID of process with lock
has_data_request_lock = mgr.Value('int', -1)
nproc_lock = mgr.Lock()
# Create the task queue for all of the particles and the DataController
tasks = multiprocessing.JoinableQueue(number_of_tasks)
# Create the result queue for all of the particles and the DataController
results = mgr.Queue(number_of_tasks)
# Create the shared state objects
get_data = mgr.Value('bool', True)
# Number of tasks
n_run = mgr.Value('int', number_of_tasks)
updating = mgr.Value('bool', False)
# When something is reading from cache file
read_lock = mgr.Lock()
# list of PIDs that are reading
has_read_lock = mgr.list()
read_count = mgr.Value('int', 0)
# When something is writing to the cache file
write_lock = mgr.Lock()
# PID of process with lock
has_write_lock = mgr.Value('int', -1)
point_get = mgr.Value('list', [0, 0, 0])
active = mgr.Value('bool', True)
logger.progress((3, "Initializing and caching hydro model's grid"))
try:
ds = CommonDataset.open(hydrodataset)
# Query the dataset for common variable names
# and the time variable.
logger.debug("Retrieving variable information from dataset")
common_variables = self.get_common_variables_from_dataset(ds)
logger.debug("Pickling time variable to disk for particles")
timevar = ds.gettimevar(common_variables.get("u"))
f, timevar_pickle_path = tempfile.mkstemp()
os.close(f)
f = open(timevar_pickle_path, "wb")
pickle.dump(timevar, f)
f.close()
ds.closenc()
except:
logger.warn("Failed to access remote dataset %s" % hydrodataset)
raise DataControllerError("Inaccessible DAP endpoint: %s" %
hydrodataset)
# Add data controller to the queue first so that it
# can get the initial data and is not blocked
logger.debug('Starting DataController')
logger.progress((4, "Starting processes"))
data_controller = parallel.DataController(hydrodataset,
common_variables,
n_run,
get_data,
write_lock,
has_write_lock,
read_lock,
read_count,
time_chunk,
horiz_chunk,
times,
self.start,
point_get,
self.reference_location,
low_memory=low_memory,
cache=self.cache_path)
tasks.put(data_controller)
# Create DataController worker
data_controller_process = parallel.Consumer(tasks,
results,
n_run,
nproc_lock,
active,
get_data,
name="DataController")
data_controller_process.start()
logger.debug('Adding %i particles as tasks' % len(self.particles))
for part in self.particles:
forcing = parallel.ForceParticle(
part,
hydrodataset,
common_variables,
timevar_pickle_path,
times,
self.start,
self._models,
self.reference_location.point,
self._use_bathymetry,
self._use_shoreline,
self._use_seasurface,
get_data,
n_run,
read_lock,
has_read_lock,
read_count,
point_get,
data_request_lock,
has_data_request_lock,
reverse_distance=self.reverse_distance,
bathy=self.bathy_path,
shoreline_path=self.shoreline_path,
cache=self.cache_path,
time_method=self.time_method)
tasks.put(forcing)
# Create workers for the particles.
procs = [
parallel.Consumer(tasks,
results,
n_run,
nproc_lock,
active,
get_data,
name="ForceParticle-%d" % i)
for i in xrange(nproc - 1)
]
for w in procs:
w.start()
logger.debug('Started %s' % w.name)
# Get results back from queue, test for failed particles
return_particles = []
retrieved = 0.
error_code = 0
logger.info("Waiting for %i particle results" % len(self.particles))
logger.progress((5, "Running model"))
while retrieved < number_of_tasks:
try:
# Returns a tuple of code, result
code, tempres = results.get(timeout=240)
except Queue.Empty:
# Poll the active processes to make sure they are all alive and then continue with loop
if not data_controller_process.is_alive(
) and data_controller_process.exitcode != 0:
# Data controller is zombied, kill off other processes.
get_data.value == False
results.put((-2, "DataController"))
new_procs = []
old_procs = []
for p in procs:
if not p.is_alive() and p.exitcode != 0:
# Do what the Consumer would do if something finished.
# Add something to results queue
results.put((-3, "ZombieParticle"))
# Decrement nproc (DataController exits when this is 0)
with nproc_lock:
n_run.value = n_run.value - 1
# Remove task from queue (so they can be joined later on)
tasks.task_done()
# Start a new Consumer. It will exit if there are no tasks available.
np = parallel.Consumer(tasks,
results,
n_run,
nproc_lock,
active,
get_data,
name=p.name)
new_procs.append(np)
old_procs.append(p)
# Release any locks the PID had
if p.pid in has_read_lock:
with read_lock:
read_count.value -= 1
has_read_lock.remove(p.pid)
if has_data_request_lock.value == p.pid:
has_data_request_lock.value = -1
try:
data_request_lock.release()
except:
pass
if has_write_lock.value == p.pid:
has_write_lock.value = -1
try:
write_lock.release()
except:
pass
for p in old_procs:
try:
procs.remove(p)
except ValueError:
logger.warn(
"Did not find %s in the list of processes. Continuing on."
% p.name)
for p in new_procs:
procs.append(p)
logger.warn(
"Started a new consumer (%s) to replace a zombie consumer"
% p.name)
p.start()
else:
# We got one.
retrieved += 1
if code == None:
logger.warn("Got an unrecognized response from a task.")
elif code == -1:
logger.warn("Particle %s has FAILED!!" % tempres.uid)
elif code == -2:
error_code = code
logger.warn(
"DataController has FAILED!! Removing cache file so the particles fail."
)
try:
os.remove(self.cache_path)
except OSError:
logger.debug(
"Could not remove cache file, it probably never existed"
)
pass
elif code == -3:
error_code = code
logger.info(
"A zombie process was caught and task was removed from queue"
)
elif isinstance(tempres, Particle):
logger.info("Particle %d finished" % tempres.uid)
return_particles.append(tempres)
# We mulitply by 95 here to save 5% for the exporting
logger.progress(
(round((retrieved / number_of_tasks) * 90.,
1), "Particle %d finished" % tempres.uid))
elif tempres == "DataController":
logger.info("DataController finished")
logger.progress((round((retrieved / number_of_tasks) * 90.,
1), "DataController finished"))
else:
logger.info("Got a strange result on results queue")
logger.info(str(tempres))
logger.info("Retrieved %i/%i results" %
(int(retrieved), number_of_tasks))
if len(return_particles) != len(self.particles):
logger.warn(
"Some particles failed and are not included in the output")
# The results queue should be empty at this point
assert results.empty() is True
# Should be good to join on the tasks now that the queue is empty
logger.info("Joining the task queue")
tasks.join()
# Join all processes
logger.info("Joining the processes")
for w in procs + [data_controller_process]:
# Wait 10 seconds
w.join(10.)
if w.is_alive():
# Process is hanging, kill it.
logger.info(
"Terminating %s forcefully. This should have exited itself."
% w.name)
w.terminate()
logger.info('Workers complete')
self.particles = return_particles
# Remove Manager so it shuts down
del mgr
# Remove pickled timevar
os.remove(timevar_pickle_path)
# Remove the cache file
if remove_cache is True:
try:
os.remove(self.cache_path)
except OSError:
logger.debug(
"Could not remove cache file, it probably never existed")
logger.progress((96, "Exporting results"))
if len(self.particles) > 0:
# If output_formats and path specified,
# output particle run data to disk when completed
if "output_formats" in kwargs:
# Make sure output_path is also included
if kwargs.get("output_path", None) != None:
formats = kwargs.get("output_formats")
output_path = kwargs.get("output_path")
if isinstance(formats, list):
for format in formats:
logger.info("Exporting to: %s" % format)
try:
self.export(output_path, format=format)
except:
logger.error("Failed to export to: %s" %
format)
else:
logger.warn(
'The output_formats parameter should be a list, not saving any output!'
)
else:
logger.warn(
'No output path defined, not saving any output!')
else:
logger.warn('No output format defined, not saving any output!')
else:
logger.warn("Model didn't actually do anything, check the log.")
if error_code == -2:
raise DataControllerError("Error in the DataController")
else:
raise ModelError("Error in the model")
logger.progress((99, "Model Run Complete"))
return
def setup_run(self, **kwargs):
logger.setLevel(logging.PROGRESS)
self.redis_url = None
self.redis_log_channel = None
self.redis_results_channel = None
if "redis" in kwargs.get("output_formats", []):
from paegan.logger.redis_handler import RedisHandler
self.redis_url = kwargs.get("redis_url")
self.redis_log_channel = kwargs.get("redis_log_channel")
self.redis_results_channel = kwargs.get("redis_results_channel")
rhandler = RedisHandler(self.redis_log_channel, self.redis_url)
rhandler.setLevel(logging.PROGRESS)
logger.addHandler(rhandler)
# Relax.
time.sleep(0.5)
# Add ModelController description to logfile
logger.info(unicode(self))
# Add the model descriptions to logfile
for m in self._models:
logger.info(unicode(m))
# Calculate the model timesteps
# We need times = len(self._nstep) + 1 since data is stored one timestep
# after a particle is forced with the final timestep's data.
self.times = range(0, (self._step*self._nstep)+1, self._step)
# Calculate a datetime object for each model timestep
# This method is duplicated in CachingDataController and CachingForcer
# using the 'times' variables above. Will be useful in those other
# locations for particles released at different times
# i.e. released over a few days
self.modelTimestep, self.datetimes = AsaTransport.get_time_objects_from_model_timesteps(self.times, start=self.start)
logger.progress((1, "Setting up particle start locations"))
point_locations = []
if isinstance(self.geometry, Point):
point_locations = [self.reference_location] * self._npart
elif isinstance(self.geometry, Polygon) or isinstance(self.geometry, MultiPolygon):
point_locations = [Location4D(latitude=loc.y, longitude=loc.x, depth=self._depth, time=self.start) for loc in AsaTransport.fill_polygon_with_points(goal=self._npart, polygon=self.geometry)]
# Initialize the particles
logger.progress((2, "Initializing particles"))
for x in xrange(0, self._npart):
p = LarvaParticle(id=x)
p.location = point_locations[x]
# We don't need to fill the location gaps here for environment variables
# because the first data collected actually relates to this original
# position.
# We do need to fill in fields such as settled, halted, etc.
p.fill_status_gap()
# Set the inital note
p.note = p.outputstring()
p.notes.append(p.note)
self.particles.append(p)
if kwargs.get("manager", True):
# Get the number of cores (may take some tuning) and create that
# many workers then pass particles into the queue for the workers
self.mgr = multiprocessing.Manager()
# This tracks if the system is 'alive'. Most looping whiles will check this
# and break out if it is False. This is True until something goes very wrong.
self.active = self.mgr.Value('bool', True)
# Each particle is a task, plus the CachingDataController
self.number_of_tasks = self.get_number_of_tasks()
# Either spin up the number of cores, or the number of tasks
self.nproc = min(multiprocessing.cpu_count() - 1, self.number_of_tasks)
# Number of tasks that we need to run. This is decremented everytime something exits.
self.n_run = self.mgr.Value('int', self.number_of_tasks)
# The lock that controls access to the 'n_run' variable
self.nproc_lock = self.mgr.Lock()
# Create the task queue for all of the particles and the CachingDataController
self.tasks = multiprocessing.JoinableQueue(self.number_of_tasks)
# Create the result queue for all of the particles and the CachingDataController
self.results = self.mgr.Queue(self.number_of_tasks)
logger.progress((3, "Initializing and caching hydro model's grid"))
try:
ds = CommonDataset.open(self.hydrodataset)
except Exception:
logger.exception("Failed to access dataset %s" % self.hydrodataset)
raise BaseDataControllerError("Inaccessible Dataset: %s" % self.hydrodataset)
# Query the dataset for common variable names
# and the time variable.
logger.debug("Retrieving variable information from dataset")
self.common_variables = self.get_common_variables_from_dataset(ds)
self.timevar = None
try:
assert self.common_variables.get("u") in ds._current_variables
assert self.common_variables.get("v") in ds._current_variables
assert self.common_variables.get("x") in ds._current_variables
assert self.common_variables.get("y") in ds._current_variables
self.timevar = ds.gettimevar(self.common_variables.get("u"))
except AssertionError:
logger.exception("Could not locate variables needed to run model: %s" % unicode(self.common_variables))
raise BaseDataControllerError("A required data variable was not found in %s" % self.hydrodataset)
model_start = self.timevar.get_dates()[0]
model_end = self.timevar.get_dates()[-1]
try:
assert self.start > model_start
assert self.start < model_end
except AssertionError:
raise BaseDataControllerError("Start time for model (%s) is not available in source dataset (%s/%s)" % (self.datetimes[0], model_start, model_end))
try:
assert self.datetimes[-1] > model_start
assert self.datetimes[-1] < model_end
except AssertionError:
raise BaseDataControllerError("End time for model (%s) is not available in source dataset (%s/%s)" % (self.datetimes[-1], model_start, model_end))
ds.closenc()
def setup_run(self, hydrodataset, **kwargs):
self.hydrodataset = hydrodataset
logger.setLevel(logging.PROGRESS)
# Relax.
time.sleep(0.5)
# Add ModelController description to logfile
logger.info(str(self))
# Add the model descriptions to logfile
for m in self._models:
logger.info(str(m))
# Calculate the model timesteps
# We need times = len(self._nstep) + 1 since data is stored one timestep
# after a particle is forced with the final timestep's data.
self.times = list(range(0, (self._step * self._nstep) + 1, self._step))
# Calculate a datetime object for each model timestep
# This method is duplicated in CachingDataController and CachingForcer
# using the 'times' variables above. Will be useful in those other
# locations for particles released at different times
# i.e. released over a few days
self.modelTimestep, self.datetimes = AsaTransport.get_time_objects_from_model_timesteps(
self.times, start=self.start)
logger.progress((1, "Setting up particle start locations"))
point_locations = []
if isinstance(self.geometry, Point):
point_locations = [self.reference_location] * self._npart
elif isinstance(self.geometry, Polygon) or isinstance(
self.geometry, MultiPolygon):
point_locations = [
Location4D(latitude=loc.y,
longitude=loc.x,
depth=self._depth,
time=self.start)
for loc in AsaTransport.fill_polygon_with_points(
goal=self._npart, polygon=self.geometry)
]
# Initialize the particles
logger.progress((2, "Initializing particles"))
for x in range(0, self._npart):
p = LarvaParticle(id=x)
p.location = point_locations[x]
# We don't need to fill the location gaps here for environment variables
# because the first data collected actually relates to this original
# position.
# We do need to fill in fields such as settled, halted, etc.
p.fill_status_gap()
# Set the inital note
p.note = p.outputstring()
p.notes.append(p.note)
self.particles.append(p)
logger.progress((3, "Initializing and caching hydro model's grid %s" %
self.hydrodataset))
try:
ds = CommonDataset.open(self.hydrodataset)
# Query the dataset for common variable names
# and the time variable.
logger.debug("Retrieving variable information from dataset")
self.common_variables = self.get_common_variables_from_dataset(ds)
except Exception:
logger.exception("Failed to access dataset %s" % self.hydrodataset)
raise BaseDataControllerError("Inaccessible Dataset: %s" %
self.hydrodataset)
self.timevar = None
try:
assert self.common_variables.get("u") in ds._current_variables
assert self.common_variables.get("v") in ds._current_variables
assert self.common_variables.get("x") in ds._current_variables
assert self.common_variables.get("y") in ds._current_variables
self.timevar = ds.gettimevar(self.common_variables.get("u"))
model_start = self.timevar.get_dates()[0]
model_end = self.timevar.get_dates()[-1]
except AssertionError:
logger.exception(
"Could not locate variables needed to run model: %s" %
str(self.common_variables))
raise BaseDataControllerError(
"A required data variable was not found in %s" %
self.hydrodataset)
finally:
ds.closenc()
try:
assert self.start > model_start
assert self.start < model_end
except AssertionError:
raise BaseDataControllerError(
"Start time for model (%s) is not available in source dataset (%s/%s)"
% (self.datetimes[0], model_start, model_end))
try:
assert self.datetimes[-1] > model_start
assert self.datetimes[-1] < model_end
except AssertionError:
raise BaseDataControllerError(
"End time for model (%s) is not available in source dataset (%s/%s)"
% (self.datetimes[-1], model_start, model_end))
def run(self, hydrodataset, **kwargs):
# Add ModelController description to logfile
logger.info(self)
# Add the model descriptions to logfile
for m in self._models:
logger.info(m)
# Calculate the model timesteps
# We need times = len(self._nstep) + 1 since data is stored one timestep
# after a particle is forced with the final timestep's data.
times = range(0,(self._step*self._nstep)+1,self._step)
# Calculate a datetime object for each model timestep
# This method is duplicated in DataController and ForceParticle
# using the 'times' variables above. Will be useful in those other
# locations for particles released at different times
# i.e. released over a few days
modelTimestep, self.datetimes = AsaTransport.get_time_objects_from_model_timesteps(times, start=self.start)
time_chunk = self._time_chunk
horiz_chunk = self._horiz_chunk
low_memory = kwargs.get("low_memory", False)
# Should we remove the cache file at the end of the run?
remove_cache = kwargs.get("remove_cache", True)
self.bathy_path = kwargs.get("bathy", None)
self.cache_path = kwargs.get("cache", None)
if self.cache_path is None:
# Generate temp filename for dataset cache
default_cache_dir = os.path.join(os.path.dirname(__file__), "_cache")
temp_name = AsaRandom.filename(prefix=str(datetime.now().microsecond), suffix=".nc")
self.cache_path = os.path.join(default_cache_dir, temp_name)
logger.progress((1, "Setting up particle start locations"))
point_locations = []
if isinstance(self.geometry, Point):
point_locations = [self.reference_location] * self._npart
elif isinstance(self.geometry, Polygon) or isinstance(self.geometry, MultiPolygon):
point_locations = [Location4D(latitude=loc.y, longitude=loc.x, depth=self._depth, time=self.start) for loc in AsaTransport.fill_polygon_with_points(goal=self._npart, polygon=self.geometry)]
# Initialize the particles
logger.progress((2, "Initializing particles"))
for x in xrange(0, self._npart):
p = LarvaParticle(id=x)
p.location = point_locations[x]
# We don't need to fill the location gaps here for environment variables
# because the first data collected actually relates to this original
# position.
# We do need to fill in fields such as settled, halted, etc.
p.fill_status_gap()
# Set the inital note
p.note = p.outputstring()
p.notes.append(p.note)
self.particles.append(p)
# This is where it makes sense to implement the multiprocessing
# looping for particles and models. Can handle each particle in
# parallel probably.
#
# Get the number of cores (may take some tuning) and create that
# many workers then pass particles into the queue for the workers
mgr = multiprocessing.Manager()
nproc = multiprocessing.cpu_count() - 1
if nproc <= 0:
raise ValueError("Model does not run using less than two CPU cores")
# Each particle is a task, plus the DataController
number_of_tasks = len(self.particles) + 1
# We need a process for each particle and one for the data controller
nproc = min(number_of_tasks, nproc)
# When a particle requests data
data_request_lock = mgr.Lock()
# PID of process with lock
has_data_request_lock = mgr.Value('int',-1)
nproc_lock = mgr.Lock()
# Create the task queue for all of the particles and the DataController
tasks = multiprocessing.JoinableQueue(number_of_tasks)
# Create the result queue for all of the particles and the DataController
results = mgr.Queue(number_of_tasks)
# Create the shared state objects
get_data = mgr.Value('bool', True)
# Number of tasks
n_run = mgr.Value('int', number_of_tasks)
updating = mgr.Value('bool', False)
# When something is reading from cache file
read_lock = mgr.Lock()
# list of PIDs that are reading
has_read_lock = mgr.list()
read_count = mgr.Value('int', 0)
# When something is writing to the cache file
write_lock = mgr.Lock()
# PID of process with lock
has_write_lock = mgr.Value('int',-1)
point_get = mgr.Value('list', [0, 0, 0])
active = mgr.Value('bool', True)
logger.progress((3, "Initializing and caching hydro model's grid"))
try:
ds = CommonDataset.open(hydrodataset)
# Query the dataset for common variable names
# and the time variable.
logger.debug("Retrieving variable information from dataset")
common_variables = self.get_common_variables_from_dataset(ds)
logger.debug("Pickling time variable to disk for particles")
timevar = ds.gettimevar(common_variables.get("u"))
f, timevar_pickle_path = tempfile.mkstemp()
os.close(f)
f = open(timevar_pickle_path, "wb")
pickle.dump(timevar, f)
f.close()
ds.closenc()
except:
logger.warn("Failed to access remote dataset %s" % hydrodataset)
raise DataControllerError("Inaccessible DAP endpoint: %s" % hydrodataset)
# Add data controller to the queue first so that it
# can get the initial data and is not blocked
logger.debug('Starting DataController')
logger.progress((4, "Starting processes"))
data_controller = parallel.DataController(hydrodataset, common_variables, n_run, get_data, write_lock, has_write_lock, read_lock, read_count,
time_chunk, horiz_chunk, times,
self.start, point_get, self.reference_location,
low_memory=low_memory,
cache=self.cache_path)
tasks.put(data_controller)
# Create DataController worker
data_controller_process = parallel.Consumer(tasks, results, n_run, nproc_lock, active, get_data, name="DataController")
data_controller_process.start()
logger.debug('Adding %i particles as tasks' % len(self.particles))
for part in self.particles:
forcing = parallel.ForceParticle(part,
hydrodataset,
common_variables,
timevar_pickle_path,
times,
self.start,
self._models,
self.reference_location.point,
self._use_bathymetry,
self._use_shoreline,
self._use_seasurface,
get_data,
n_run,
read_lock,
has_read_lock,
read_count,
point_get,
data_request_lock,
has_data_request_lock,
reverse_distance=self.reverse_distance,
bathy=self.bathy_path,
shoreline_path=self.shoreline_path,
shoreline_feature=self.shoreline_feature,
cache=self.cache_path,
time_method=self.time_method)
tasks.put(forcing)
# Create workers for the particles.
procs = [ parallel.Consumer(tasks, results, n_run, nproc_lock, active, get_data, name="ForceParticle-%d"%i)
for i in xrange(nproc - 1) ]
for w in procs:
w.start()
logger.debug('Started %s' % w.name)
# Get results back from queue, test for failed particles
return_particles = []
retrieved = 0.
error_code = 0
logger.info("Waiting for %i particle results" % len(self.particles))
logger.progress((5, "Running model"))
while retrieved < number_of_tasks:
try:
# Returns a tuple of code, result
code, tempres = results.get(timeout=240)
except Queue.Empty:
# Poll the active processes to make sure they are all alive and then continue with loop
if not data_controller_process.is_alive() and data_controller_process.exitcode != 0:
# Data controller is zombied, kill off other processes.
get_data.value == False
results.put((-2, "DataController"))
new_procs = []
old_procs = []
for p in procs:
if not p.is_alive() and p.exitcode != 0:
# Do what the Consumer would do if something finished.
# Add something to results queue
results.put((-3, "ZombieParticle"))
# Decrement nproc (DataController exits when this is 0)
with nproc_lock:
n_run.value = n_run.value - 1
# Remove task from queue (so they can be joined later on)
tasks.task_done()
# Start a new Consumer. It will exit if there are no tasks available.
np = parallel.Consumer(tasks, results, n_run, nproc_lock, active, get_data, name=p.name)
new_procs.append(np)
old_procs.append(p)
# Release any locks the PID had
if p.pid in has_read_lock:
with read_lock:
read_count.value -= 1
has_read_lock.remove(p.pid)
if has_data_request_lock.value == p.pid:
has_data_request_lock.value = -1
try:
data_request_lock.release()
except:
pass
if has_write_lock.value == p.pid:
has_write_lock.value = -1
try:
write_lock.release()
except:
pass
for p in old_procs:
try:
procs.remove(p)
except ValueError:
logger.warn("Did not find %s in the list of processes. Continuing on." % p.name)
for p in new_procs:
procs.append(p)
logger.warn("Started a new consumer (%s) to replace a zombie consumer" % p.name)
p.start()
else:
# We got one.
retrieved += 1
if code == None:
logger.warn("Got an unrecognized response from a task.")
elif code == -1:
logger.warn("Particle %s has FAILED!!" % tempres.uid)
elif code == -2:
error_code = code
logger.warn("DataController has FAILED!! Removing cache file so the particles fail.")
try:
os.remove(self.cache_path)
except OSError:
logger.debug("Could not remove cache file, it probably never existed")
pass
elif code == -3:
error_code = code
logger.info("A zombie process was caught and task was removed from queue")
elif isinstance(tempres, Particle):
logger.info("Particle %d finished" % tempres.uid)
return_particles.append(tempres)
# We mulitply by 95 here to save 5% for the exporting
logger.progress((round((retrieved / number_of_tasks) * 90.,1), "Particle %d finished" % tempres.uid))
elif tempres == "DataController":
logger.info("DataController finished")
logger.progress((round((retrieved / number_of_tasks) * 90.,1), "DataController finished"))
else:
logger.info("Got a strange result on results queue")
logger.info(str(tempres))
logger.info("Retrieved %i/%i results" % (int(retrieved),number_of_tasks))
if len(return_particles) != len(self.particles):
logger.warn("Some particles failed and are not included in the output")
# The results queue should be empty at this point
assert results.empty() is True
# Should be good to join on the tasks now that the queue is empty
logger.info("Joining the task queue")
tasks.join()
# Join all processes
logger.info("Joining the processes")
for w in procs + [data_controller_process]:
# Wait 10 seconds
w.join(10.)
if w.is_alive():
# Process is hanging, kill it.
logger.info("Terminating %s forcefully. This should have exited itself." % w.name)
w.terminate()
logger.info('Workers complete')
self.particles = return_particles
# Remove Manager so it shuts down
del mgr
# Remove pickled timevar
os.remove(timevar_pickle_path)
# Remove the cache file
if remove_cache is True:
try:
os.remove(self.cache_path)
except OSError:
logger.debug("Could not remove cache file, it probably never existed")
logger.progress((96, "Exporting results"))
if len(self.particles) > 0:
# If output_formats and path specified,
# output particle run data to disk when completed
if "output_formats" in kwargs:
# Make sure output_path is also included
if kwargs.get("output_path", None) != None:
formats = kwargs.get("output_formats")
output_path = kwargs.get("output_path")
if isinstance(formats, list):
for format in formats:
logger.info("Exporting to: %s" % format)
try:
self.export(output_path, format=format)
except:
logger.error("Failed to export to: %s" % format)
else:
logger.warn('The output_formats parameter should be a list, not saving any output!')
else:
logger.warn('No output path defined, not saving any output!')
else:
logger.warn('No output format defined, not saving any output!')
else:
logger.warn("Model didn't actually do anything, check the log.")
if error_code == -2:
raise DataControllerError("Error in the DataController")
else:
raise ModelError("Error in the model")
logger.progress((99, "Model Run Complete"))
return
def setUp(self):
self.p = LarvaParticle()
def setup_run(self, hydrodataset, **kwargs):
self.hydrodataset = hydrodataset
logger.setLevel(logging.PROGRESS)
# Relax.
time.sleep(0.5)
# Add ModelController description to logfile
logger.info(str(self))
# Add the model descriptions to logfile
for m in self._models:
logger.info(str(m))
# Calculate the model timesteps
# We need times = len(self._nstep) + 1 since data is stored one timestep
# after a particle is forced with the final timestep's data.
self.times = list(range(0, (self._step*self._nstep)+1, self._step))
# Calculate a datetime object for each model timestep
# This method is duplicated in CachingDataController and CachingForcer
# using the 'times' variables above. Will be useful in those other
# locations for particles released at different times
# i.e. released over a few days
self.modelTimestep, self.datetimes = AsaTransport.get_time_objects_from_model_timesteps(self.times, start=self.start)
logger.progress((1, "Setting up particle start locations"))
point_locations = []
if isinstance(self.geometry, Point):
point_locations = [self.reference_location] * self._npart
elif isinstance(self.geometry, Polygon) or isinstance(self.geometry, MultiPolygon):
point_locations = [Location4D(latitude=loc.y, longitude=loc.x, depth=self._depth, time=self.start) for loc in AsaTransport.fill_polygon_with_points(goal=self._npart, polygon=self.geometry)]
# Initialize the particles
logger.progress((2, "Initializing particles"))
for x in range(0, self._npart):
p = LarvaParticle(id=x)
p.location = point_locations[x]
# We don't need to fill the location gaps here for environment variables
# because the first data collected actually relates to this original
# position.
# We do need to fill in fields such as settled, halted, etc.
p.fill_status_gap()
# Set the inital note
p.note = p.outputstring()
p.notes.append(p.note)
self.particles.append(p)
logger.progress((3, "Initializing and caching hydro model's grid %s" % self.hydrodataset))
try:
ds = CommonDataset.open(self.hydrodataset)
# Query the dataset for common variable names
# and the time variable.
logger.debug("Retrieving variable information from dataset")
self.common_variables = self.get_common_variables_from_dataset(ds)
except Exception:
logger.exception("Failed to access dataset %s" % self.hydrodataset)
raise BaseDataControllerError("Inaccessible Dataset: %s" % self.hydrodataset)
self.timevar = None
try:
assert self.common_variables.get("u") in ds._current_variables
assert self.common_variables.get("v") in ds._current_variables
assert self.common_variables.get("x") in ds._current_variables
assert self.common_variables.get("y") in ds._current_variables
self.timevar = ds.gettimevar(self.common_variables.get("u"))
model_start = self.timevar.get_dates()[0]
model_end = self.timevar.get_dates()[-1]
except AssertionError:
logger.exception("Could not locate variables needed to run model: %s" % str(self.common_variables))
raise BaseDataControllerError("A required data variable was not found in %s" % self.hydrodataset)
finally:
ds.closenc()
try:
assert self.start > model_start
assert self.start < model_end
except AssertionError:
raise BaseDataControllerError("Start time for model (%s) is not available in source dataset (%s/%s)" % (self.datetimes[0], model_start, model_end))
try:
assert self.datetimes[-1] > model_start
assert self.datetimes[-1] < model_end
except AssertionError:
raise BaseDataControllerError("End time for model (%s) is not available in source dataset (%s/%s)" % (self.datetimes[-1], model_start, model_end))
def setUp(self):
self.p = LarvaParticle()
