def test_wfp_check_processor():
p = Pipeline()
s = Stage()
t = Task()
t.executable = ['/bin/date']
s.add_tasks(t)
p.add_stages(s)
amgr = Amgr(hostname=hostname, port=port)
amgr._setup_mqs()
wfp = WFprocessor(sid=amgr._sid,
workflow=[p],
pending_queue=amgr._pending_queue,
completed_queue=amgr._completed_queue,
mq_hostname=amgr._mq_hostname,
port=amgr._port,
resubmit_failed=False)
wfp.start_processor()
assert wfp.check_processor()
wfp.terminate_processor()
assert not wfp.check_processor()
def add_md_stg(rid,cycle):
#md stg h
md_tsk = Task()
md_stg = Stage()
md_tsk.name = 'mdtsk-{replica}-{cycle}'.format(replica=rid, cycle=cycle)
md_tsk.link_input_data += ['%s/inpcrd' %replica_sandbox,
'%s/prmtop' %replica_sandbox,
'%s/mdin-{replica}-{cycle}'.format(replica=rid, cycle=0) %replica_sandbox]
md_tsk.arguments = ['-O',
'-i', 'mdin-{replica}-{cycle}'.format(replica=rid, cycle=0),
'-p', 'prmtop',
'-c', 'inpcrd',
'-o', 'out',
'-r', '%s/restrt-{replica}-{cycle}'.format(replica=rid, cycle=cycle) %replica_sandbox,
'-x', 'mdcrd',
'-inf', '%s/mdinfo-{replica}-{cycle}'.format(replica=rid, cycle=cycle) %replica_sandbox]
md_tsk.executable = ['/home/scm177/mantel/AMBER/amber14/bin/sander']
md_tsk.cpu_reqs = {
'processes': replica_cores,
'process_type': '',
'threads_per_process': 1,
'thread_type': None
}
md_tsk.pre_exec = ['export dummy_variable=19', 'echo $SHARED']
md_stg.add_tasks(md_tsk)
md_stg.post_exec = {
'condition': md_post,
'on_true': suspend,
'on_false': exchange_stg
}
return md_stg
def test_wfp_initialization(s, i, b, l):
p = Pipeline()
st = Stage()
t = Task()
t.executable = ['/bin/date']
st.add_tasks(t)
p.add_stages(st)
wfp = WFprocessor(sid='rp.session.local.0000',
workflow=set([p]),
pending_queue=['pending'],
completed_queue=['completed'],
mq_hostname=hostname,
port=port,
resubmit_failed=True)
assert len(wfp._uid.split('.')) == 2
assert 'wfprocessor' == wfp._uid.split('.')[0]
assert wfp._pending_queue == ['pending']
assert wfp._completed_queue == ['completed']
assert wfp._mq_hostname == hostname
assert wfp._port == port
assert wfp._wfp_process == None
assert wfp._workflow == set([p])
if not isinstance(s, unicode):
wfp = WFprocessor(sid=s,
workflow=set([p]),
pending_queue=l,
completed_queue=l,
mq_hostname=s,
port=i,
resubmit_failed=b)
def test_stage_post_exec():
global p1
p1.name = 'p1'
s = Stage()
s.name = 's1'
for t in range(NUM_TASKS):
s.add_tasks(create_single_task())
s.post_exec = condition
p1.add_stages(s)
res_dict = {
'resource': 'local.localhost',
'walltime': 30,
'cpus': 1,
}
os.environ['RADICAL_PILOT_DBURL'] = MLAB
appman = AppManager(rts='radical.pilot', hostname=hostname, port=port)
appman.resource_desc = res_dict
appman.workflow = [p1]
appman.run()
def generate_aggregating_stage():
"""
Function to concatenate the MD trajectory (h5 contact map)
"""
s2 = Stage()
s2.name = 'aggregating'
# Aggregation task
t2 = Task()
# https://github.com/radical-collaboration/hyperspace/blob/MD/microscope/experiments/MD_to_CVAE/MD_to_CVAE.py
t2.pre_exec = []
t2.pre_exec += [
'. /sw/summit/python/2.7/anaconda2/5.3.0/etc/profile.d/conda.sh'
]
t2.pre_exec += ['conda activate rp.copy']
t2.pre_exec += [
'cd /gpfs/alpine/bip179/scratch/hrlee/hyperspace/microscope/experiments/MD_to_CVAE'
]
t2.executable = ['/ccs/home/hrlee/.conda/envs/rp.copy/bin/python'
] # MD_to_CVAE.py
t2.arguments = [
'/gpfs/alpine/bip179/scratch/hrlee/hyperspace/microscope/experiments/MD_to_CVAE/MD_to_CVAE.py',
'-f',
'/gpfs/alpine/bip179/scratch/hrlee/hyperspace/microscope/experiments/MD_exps/fs-pep'
]
# Add the aggregation task to the aggreagating stage
s2.add_tasks(t2)
return s2
def add_ex_stg(rid, cycle):
#ex stg here
ex_tsk = Task()
ex_stg = Stage()
ex_tsk.name = 'extsk-{replica}-{cycle}'.format(replica=rid, cycle=cycle)
for rid in range(len(waiting_replicas)):
ex_tsk.link_input_data += ['%s/mdinfo-{replica}-{cycle}'.format(replica=rid, cycle=self.cycle)%replica_sandbox]
ex_tsk.arguments = ['t_ex_gibbs.py', len(waiting_replicas)] #This needs to be fixed
ex_tsk.executable = ['python']
ex_tsk.cpu_reqs = {
'processes': 1,
'process_type': '',
'threads_per_process': 1,
'thread_type': None
}
ex_tsk.pre_exec = ['export dummy_variable=19']
ex_stg.add_tasks(ex_tsk)
ex_stg.post_exec = {
'condition': post_ex,
'on_true': terminate_replicas,
'on_false': continue_md
}
return ex_stg
def generate_agent_stage(self) -> Stage:
stage = Stage()
stage.name = self.AGENT_STAGE_NAME
cfg = self.cfg.agent_stage
stage_api = self.api.agent_stage
task_idx = 0
output_path = stage_api.task_dir(self.stage_idx, task_idx, mkdir=True)
assert output_path is not None
# Update base parameters
cfg.task_config.experiment_directory = self.cfg.experiment_directory
cfg.task_config.stage_idx = self.stage_idx
cfg.task_config.task_idx = task_idx
cfg.task_config.node_local_path = self.cfg.node_local_path
cfg.task_config.output_path = output_path
# Write yaml configuration
cfg_path = stage_api.config_path(self.stage_idx, task_idx)
cfg.task_config.dump_yaml(cfg_path)
task = generate_task(cfg)
task.arguments += ["-c", cfg_path.as_posix()]
stage.add_tasks(task)
return stage
def generate_machine_learning_stage(self) -> Stage:
stage = Stage()
stage.name = self.MACHINE_LEARNING_STAGE_NAME
cfg = self.cfg.machine_learning_stage
stage_api = self.api.machine_learning_stage
task_idx = 0
output_path = stage_api.task_dir(self.stage_idx, task_idx, mkdir=True)
assert output_path is not None
# Update base parameters
cfg.task_config.experiment_directory = self.cfg.experiment_directory
cfg.task_config.stage_idx = self.stage_idx
cfg.task_config.task_idx = task_idx
cfg.task_config.node_local_path = self.cfg.node_local_path
cfg.task_config.output_path = output_path
cfg.task_config.model_tag = stage_api.unique_name(output_path)
if self.stage_idx > 0:
# Machine learning should use model selection API
cfg.task_config.init_weights_path = None
# Write yaml configuration
cfg_path = stage_api.config_path(self.stage_idx, task_idx)
cfg.task_config.dump_yaml(cfg_path)
task = generate_task(cfg)
task.arguments += ["-c", cfg_path.as_posix()]
stage.add_tasks(task)
return stage
def test_pipeline_pass_uid():
p = Pipeline()
p._uid = 'test'
p.name = 'p1'
s1 = Stage()
s2 = Stage()
p.add_stages([s1, s2])
p._pass_uid()
assert s1.parent_pipeline['uid'] == p.uid
assert s1.parent_pipeline['name'] == p.name
assert s2.parent_pipeline['uid'] == p.uid
assert s2.parent_pipeline['name'] == p.name
def test_pipeline_validate_entities(t, l, i, b, se):
p = Pipeline()
data_type = [t, l, i, b, se]
for data in data_type:
with pytest.raises(TypeError):
p._validate_entities(data)
s = Stage()
assert isinstance(p._validate_entities(s), list)
s1 = Stage()
s2 = Stage()
assert [s1, s2] == p._validate_entities([s1, s2])
def get_pipeline(tasks):
# Create a Pipeline object
p = Pipeline()
# Create a Stage 1
s1 = Stage()
# Create a Task object according to the app_name
t1 = Task()
t1.pre_exec = ['module load gromacs/5.0/INTEL-140-MVAPICH2-2.0']
t1.executable = app_coll['grompp']['executable']
t1.arguments = app_coll['grompp']['arguments']
t1.cores = app_coll['grompp']['cores']
t1.link_input_data = [
'$SHARED/grompp.mdp > grompp.mdp',
'$SHARED/input.gro > input.gro',
'$SHARED/topol.top > topol.top'
]
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
# Create a Stage 2
s2 = Stage()
for cnt in range(tasks):
# Create a Task object according to the app_name
t2 = Task()
t2.pre_exec = ['module load gromacs/5.0/INTEL-140-MVAPICH2-2.0','export OMP_NUM_THREADS=1']
t2.executable = app_coll['mdrun']['executable']
t2.arguments = app_coll['mdrun']['arguments']
t2.cores = app_coll['mdrun']['cores']
t2.copy_input_data = ['$Pipeline_%s_Stage_%s_Task_%s/topol.tpr'%(p.uid, s1.uid,t1.uid)]
# Add the Task to the Stage
s2.add_tasks(t2)
# Add Stage to the Pipeline
p.add_stages(s2)
return p
def test_sync_with_master(self, mocked_init, mocked_Logger, mocked_Profiler):
# --------------------------------------------------------------------------
#
def component_execution(packets, conn_params, queue):
tmgr = BaseTmgr(None, None, None, None, None, None)
tmgr._log = mocked_Logger
tmgr._prof = mocked_Profiler
mq_connection2 = pika.BlockingConnection(rmq_conn_params)
mq_channel2 = mq_connection2.channel()
for obj_type, obj, in packets:
tmgr._sync_with_master(obj, obj_type, mq_channel2, conn_params,
queue)
if mq_channel2.is_open:
mq_channel2.close()
task = Task()
task.parent_stage = {'uid':'stage.0000', 'name': 'stage.0000'}
packets = [('Task', task)]
stage = Stage()
stage.parent_pipeline = {'uid':'pipe.0000', 'name': 'pipe.0000'}
packets.append(('Stage', stage))
hostname = os.environ.get('RMQ_HOSTNAME', 'localhost')
port = int(os.environ.get('RMQ_PORT', '5672'))
username = os.environ.get('RMQ_USERNAME','guest')
password = os.environ.get('RMQ_PASSWORD','guest')
credentials = pika.PlainCredentials(username, password)
rmq_conn_params = pika.ConnectionParameters(host=hostname, port=port,
credentials=credentials)
mq_connection = pika.BlockingConnection(rmq_conn_params)
mq_channel = mq_connection.channel()
mq_channel.queue_declare(queue='master')
master_thread = mt.Thread(target=component_execution,
name='tmgr_sync',
args=(packets, rmq_conn_params, 'master'))
master_thread.start()
time.sleep(1)
try:
while packets:
packet = packets.pop(0)
_, _, body = mq_channel.basic_get(queue='master')
msg = json.loads(body)
self.assertEqual(msg['object'], packet[1].to_dict())
self.assertEqual(msg['type'], packet[0])
except Exception as ex:
print(ex)
print(json.loads(body))
master_thread.join()
mq_channel.queue_delete(queue='master')
mq_channel.close()
mq_connection.close()
raise ex
else:
master_thread.join()
mq_channel.queue_delete(queue='master')
mq_channel.close()
mq_connection.close()
def test_amgr_synchronizer():
amgr = Amgr(hostname=hostname, port=port)
amgr._setup_mqs()
p = Pipeline()
s = Stage()
# Create and add 10 tasks to the stage
for cnt in range(10):
t = Task()
t.executable = 'some-executable-%s' % cnt
s.add_tasks(t)
p.add_stages(s)
p._assign_uid(amgr._sid)
p._validate()
amgr.workflow = [p]
sid = 'test.0016'
rmgr = BaseRmgr({}, sid, None, {})
tmgr = BaseTmgr(sid=sid,
pending_queue=['pending-1'],
completed_queue=['completed-1'],
rmgr=rmgr,
mq_hostname=hostname,
port=port,
rts=None)
amgr._rmgr = rmgr
rmgr._task_manager = tmgr
for t in p.stages[0].tasks:
assert t.state == states.INITIAL
assert p.stages[0].state == states.INITIAL
assert p.state == states.INITIAL
# Start the synchronizer method in a thread
amgr._terminate_sync = mt.Event()
sync_thread = mt.Thread(target=amgr._synchronizer,
name='synchronizer-thread')
sync_thread.start()
# Start the synchronizer method in a thread
proc = mp.Process(target=func_for_synchronizer_test, name='temp-proc',
args=(amgr._sid, p, tmgr))
proc.start()
proc.join()
amgr._terminate_sync.set()
sync_thread.join()
for t in p.stages[0].tasks:
assert t.state == states.COMPLETED
def create_inversion_dict_stage(cmt_file_db, param_path, task_counter):
"""Creates stage for the creation of the inversion files. This stage is
tiny, but required before the actual inversion.
:param cmt_file_db:
:param param_path:
:param task_counter:
:return:
"""
# Get database parameter path
databaseparam_path = os.path.join(param_path,
"Database/DatabaseParameters.yml")
# Load Parameters
DB_params = read_yaml_file(databaseparam_path)
# Earthquake specific database parameters: Dir and Cid
Cdir, Cid = get_Centry_path(DB_params["databasedir"], cmt_file_db)
# Function
inv_dict_func = os.path.join(bin_path, "write_inversion_dicts.py")
# Create Process Paths Stage (CPP)
# Create a Stage object
inv_dict_stage = Stage()
inv_dict_stage.name = "Creating"
# Create Task
inv_dict_task = Task()
# This way the task gets the name of the path file
inv_dict_task.name = "Inversion-Dictionaries"
inv_dict_task.pre_exec = [ # Conda activate
DB_params["conda-activate"]
]
inv_dict_task.executable = [DB_params["bin-python"]] # Assign exec
# to the task
inv_dict_task.arguments = [
inv_dict_func, "-f", cmt_file_db, "-p", param_path
]
# In the future maybe to database dir as a total log?
inv_dict_task.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), inv_dict_task.name))
inv_dict_task.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), inv_dict_task.name))
inv_dict_stage.add_tasks(inv_dict_task)
task_counter += 1
return inv_dict_stage, task_counter
def generate_stage(self):
s = Stage()
s.name = self.name
s.add_tasks(
{self.generate_task(**x)
for x in self._ensemble_product()})
return s
def generate_pipeline(nid):
# Create a Pipeline object
p = Pipeline()
p.name = 'p%s' % nid
# Create a Stage object
s1 = Stage()
s1.name = 's1'
# Create a Task object which creates a file named 'output.txt' of size 1 MB
t1 = Task()
t1.name = 't2'
t1.executable = ['/bin/echo']
t1.arguments = ['hello']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
# Create another Stage object to hold character count tasks
s2 = Stage()
s2.name = 's2'
s2_task_uids = []
for cnt in range(10):
# Create a Task object
t2 = Task()
t2.name = 't%s' % (cnt + 1)
t2.executable = ['/bin/echo']
t2.arguments = ['world']
# Copy data from the task in the first stage to the current task's location
t2.copy_input_data = [
'$Pipeline_%s_Stage_%s_Task_%s/output.txt' % (p.name, s1.name, t1.name)]
# Add the Task to the Stage
s2.add_tasks(t2)
s2_task_uids.append(t2.name)
# Add Stage to the Pipeline
p.add_stages(s2)
return p
def main():
cmd = "{0} 'ls {1}'".format(ssh, dir_)
p = Popen(cmd, shell=True, stdout=PIPE, stderr=PIPE)
out, _ = p.communicate()
out = out.decode('utf-8').strip().split(linesep)
fullpaths = [op.join(dir_, p) for p in out]
print(fullpaths)
# Start radical entk pipeline
p = Pipeline()
for i in range(iterations):
s = Stage()
for fp in fullpaths:
t = Task()
t.name = 'Incrementation {}'.format(i)
t.pre_exec = [
'source /home/vhayot/miniconda3/etc/profile.d/conda.sh',
'conda activate radenv'
]
t.executable = 'python /home/vhayot/inc.py'
if i == 0:
t.arguments = [fp, out_dir, i]
else:
# Note: assuming all data is accessible through shared dir
# radical entk functions without sharedfs, however
t.arguments = [
op.join(out_dir,
"it-{0}-{1}".format(i - 1, op.basename(fp))),
out_dir, i
]
s.add_tasks(t)
# Create a new stage everytime there's a dependency
p.add_stages(s)
appman = AppManager(hostname=hostname, port=port)
appman.resource_desc = {
'resource': 'xsede.bridges',
'walltime': 20,
'cpus': 5,
'project': 'mc3bggp',
'schema': 'gsissh'
}
appman.workflow = set([p])
appman.run()
def test_wfp_workflow_incomplete():
p = Pipeline()
s = Stage()
t = Task()
t.executable = ['/bin/date']
s.add_tasks(t)
p.add_stages(s)
amgr = Amgr(hostname=hostname, port=port)
amgr._setup_mqs()
wfp = WFprocessor(sid=amgr._sid,
workflow=[p],
pending_queue=amgr._pending_queue,
completed_queue=amgr._completed_queue,
mq_hostname=amgr._mq_hostname,
port=amgr._port,
resubmit_failed=False)
wfp._initialize_workflow()
assert wfp.workflow_incomplete()
amgr.workflow = [p]
profiler = ru.Profiler(name='radical.entk.temp')
p.stages[0].state == states.SCHEDULING
p.state == states.SCHEDULED
for t in p.stages[0].tasks:
t.state = states.COMPLETED
import json
import pika
task_as_dict = json.dumps(t.to_dict())
mq_connection = pika.BlockingConnection(
pika.ConnectionParameters(host=amgr._mq_hostname, port=amgr._port))
mq_channel = mq_connection.channel()
mq_channel.basic_publish(exchange='',
routing_key='%s-completedq-1' % amgr._sid,
body=task_as_dict)
amgr._terminate_sync = Event()
sync_thread = Thread(target=amgr._synchronizer, name='synchronizer-thread')
sync_thread.start()
proc = Process(target=func_for_dequeue_test,
name='temp-proc',
args=(wfp, ))
proc.start()
proc.join()
amgr._terminate_sync.set()
sync_thread.join()
assert not wfp.workflow_incomplete()
def test_wfp_dequeue():
p = Pipeline()
s = Stage()
t = Task()
t.executable = '/bin/date'
s.add_tasks(t)
p.add_stages(s)
amgr = Amgr(hostname=hostname, port=port)
amgr._setup_mqs()
wfp = WFprocessor(sid=amgr._sid,
workflow=[p],
pending_queue=amgr._pending_queue,
completed_queue=amgr._completed_queue,
mq_hostname=amgr._hostname,
port=amgr._port,
resubmit_failed=False)
wfp.initialize_workflow()
assert p.state == states.INITIAL
assert p.stages[0].state == states.INITIAL
for t in p.stages[0].tasks:
assert t.state == states.INITIAL
p.state == states.SCHEDULED
p.stages[0].state == states.SCHEDULING
for t in p.stages[0].tasks:
t.state = states.COMPLETED
task_as_dict = json.dumps(t.to_dict())
mq_connection = pika.BlockingConnection(
pika.ConnectionParameters(host=amgr._hostname, port=amgr._port))
mq_channel = mq_connection.channel()
mq_channel.basic_publish(exchange='',
routing_key='%s' % amgr._completed_queue[0],
body=task_as_dict)
wfp.start_processor()
th = mt.Thread(target=func_for_dequeue_test, name='temp-proc', args=(p, ))
th.start()
th.join()
wfp.terminate_processor()
assert p.state == states.DONE
assert p.stages[0].state == states.DONE
for t in p.stages[0].tasks:
assert t.state == states.DONE
def test_state_order():
"""
**Purpose**: Test if the Pipeline, Stage and Task are assigned their states in the correct order
"""
def create_single_task():
t1 = Task()
t1.name = 'simulation'
t1.executable = ['/bin/date']
t1.copy_input_data = []
t1.copy_output_data = []
return t1
p1 = Pipeline()
p1.name = 'p1'
s = Stage()
s.name = 's1'
s.tasks = create_single_task()
s.add_tasks(create_single_task())
p1.add_stages(s)
res_dict = {
'resource': 'local.localhost',
'walltime': 5,
'cpus': 1,
'project': ''
}
os.environ['RADICAL_PILOT_DBURL'] = MLAB
os.environ['RP_ENABLE_OLD_DEFINES'] = 'True'
appman = Amgr(hostname=hostname, port=port)
appman.resource_desc = res_dict
appman.workflow = [p1]
appman.run()
p_state_hist = p1.state_history
assert p_state_hist == ['DESCRIBED', 'SCHEDULING', 'DONE']
s_state_hist = p1.stages[0].state_history
assert s_state_hist == ['DESCRIBED', 'SCHEDULING', 'SCHEDULED', 'DONE']
tasks = p1.stages[0].tasks
for t in tasks:
t_state_hist = t.state_history
assert t_state_hist == ['DESCRIBED', 'SCHEDULING', 'SCHEDULED', 'SUBMITTING', 'SUBMITTED',
'EXECUTED', 'DEQUEUEING', 'DEQUEUED', 'DONE']
def test_pipeline_stage_addition():
p = Pipeline()
s1 = Stage()
t = Task()
t.executable = '/bin/date'
s1.tasks = t
s2 = Stage()
t = Task()
t.executable = '/bin/date'
s2.tasks = t
p.add_stages([s1, s2])
assert type(p.stages) == list
assert p._stage_count == 2
assert p._cur_stage == 1
assert p.stages[0] == s1
assert p.stages[1] == s2
def describe_MD_pipline():
p = Pipeline()
p.name = 'MD'
# Docking stage
s1 = Stage()
s1.name = 'Docking'
# Docking task
t1 = Task()
t1.executable = ['sleep']
t1.arguments = ['30']
# Add the Docking task to the Docking Stage
s1.add_tasks(t1)
# Add Docking stage to the pipeline
p.add_stages(s1)
# MD stage
s2 = Stage()
s2.name = 'Simulation'
# Each Task() is an OpenMM executable that will run on a single GPU.
# Set sleep time for local testing
for i in range(6):
t2 = Task()
t2.executable = ['sleep']
t2.arguments = ['60']
# Add the MD task to the Docking Stage
s2.add_tasks(t2)
# Add post-exec to the Stage
s2.post_exec = {
'condition': func_condition,
'on_true': func_on_true,
'on_false': func_on_false
}
# Add MD stage to the MD Pipeline
p.add_stages(s2)
return p
def generate_pipeline():
# Create a Pipeline object
p = Pipeline()
p.name = 'p1'
# Create a Stage object
s1 = Stage()
s1.name = 's1'
# Create a Task object which creates a file named 'output.txt' of size 1 MB
t1 = Task()
t1.name = 't1'
t1.executable = ['/bin/echo']
t1.arguments = ['"Hello World"']
t1.stdout = 'temp.txt'
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
# Create a Stage object
s2 = Stage()
s2.name = 's2'
# Create a Task object which creates a file named 'output.txt' of size 1 MB
t2 = Task()
t2.name = 't2'
t2.executable = ['/bin/cat']
t2.arguments = [
'$Pipeline_%s_Stage_%s_Task_%s/temp.txt' % (p.name, s1.name, t1.name)
]
t2.stdout = 'output.txt'
t2.download_output_data = ['output.txt']
# Add the Task to the Stage
s2.add_tasks(t2)
# Add Stage to the Pipeline
p.add_stages(s2)
return p
def generate_ML_stage(num_ML=1):
"""
Function to generate the learning stage
"""
s3 = Stage()
s3.name = 'learning'
# learn task
for i in range(num_ML):
t3 = Task()
# https://github.com/radical-collaboration/hyperspace/blob/MD/microscope/experiments/CVAE_exps/train_cvae.py
t3.pre_exec = []
t3.pre_exec = ['module reset']
t3.pre_exec += [
'. /sw/summit/python/2.7/anaconda2/5.3.0/etc/profile.d/conda.sh'
]
t3.pre_exec += ['module load cuda/9.1.85']
t3.pre_exec += ['conda activate rp.copy']
t3.pre_exec += ['export CUDA_VISIBLE_DEVICES=0']
t3.pre_exec += [
'export PYTHONPATH=/gpfs/alpine/scratch/hrlee/bip179/hyperspace/microscope/experiments/CVAE_exps:$PYTHONPATH'
]
t3.pre_exec += [
'cd /gpfs/alpine/scratch/hrlee/bip179/hyperspace/microscope/experiments/CVAE_exps'
]
time_stamp = int(time.time())
dim = i + 3
cvae_dir = 'cvae_runs_%.2d_%d' % (dim, time_stamp)
t3.pre_exec += ['mkdir -p {0} && cd {0}'.format(cvae_dir)]
t3.executable = ['/ccs/home/hrlee/.conda/envs/rp.copy/bin/python'
] # train_cvae.py
t3.arguments = [
'/gpfs/alpine/bip179/scratch/hrlee/hyperspace/microscope/experiments/CVAE_exps/train_cvae.py',
'-f',
'/gpfs/alpine/bip179/scratch/hrlee/hyperspace/microscope/experiments/MD_to_CVAE/cvae_input.h5',
'-d', dim
]
t3.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 4,
'thread_type': 'OpenMP'
}
t3.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': 'CUDA'
}
# Add the learn task to the learning stage
s3.add_tasks(t3)
time.sleep(1)
return s3
def test_stage_to_dict():
s = Stage()
d = s.to_dict()
assert d == {'uid': 'stage.0000',
'name': None,
'state': states.INITIAL,
'state_history': [states.INITIAL],
'parent_pipeline': {'uid': None, 'name': None}}
def generate_pipeline():
def func_condition():
global CUR_NEW_STAGE, MAX_NEW_STAGE
if CUR_NEW_STAGE <= MAX_NEW_STAGE:
func_on_true()
func_on_false()
def func_on_true():
global CUR_NEW_STAGE
CUR_NEW_STAGE += 1
s = Stage()
for i in range(10):
t = Task()
t.executable = '/bin/sleep'
t.arguments = ['30']
s.add_tasks(t)
# Add post-exec to the Stage
s.post_exec = func_condition
p.add_stages(s)
def func_on_false():
print('Done')
# Create a Pipeline object
p = Pipeline()
# Create a Stage object
s1 = Stage()
for i in range(10):
t1 = Task()
t1.executable = 'sleep'
t1.arguments = ['30']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add post-exec to the Stage
s1.post_exec = func_condition
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def test_amgr_synchronizer():
logger = ru.get_logger('radical.entk.temp_logger')
profiler = ru.Profiler(name='radical.entk.temp')
amgr = Amgr(hostname=hostname, port=port)
mq_connection = pika.BlockingConnection(pika.ConnectionParameters(host=hostname, port=port))
mq_channel = mq_connection.channel()
amgr._setup_mqs()
p = Pipeline()
s = Stage()
# Create and add 100 tasks to the stage
for cnt in range(100):
t = Task()
t.executable = ['some-executable-%s' % cnt]
s.add_tasks(t)
p.add_stages(s)
p._assign_uid(amgr._sid)
p._validate()
amgr.workflow = [p]
for t in p.stages[0].tasks:
assert t.state == states.INITIAL
assert p.stages[0].state == states.INITIAL
assert p.state == states.INITIAL
# Start the synchronizer method in a thread
amgr._terminate_sync = Event()
sync_thread = Thread(target=amgr._synchronizer, name='synchronizer-thread')
sync_thread.start()
# Start the synchronizer method in a thread
proc = Process(target=func_for_synchronizer_test, name='temp-proc',
args=(amgr._sid, p, logger, profiler))
proc.start()
proc.join()
for t in p.stages[0].tasks:
assert t.state == states.SCHEDULING
assert p.stages[0].state == states.SCHEDULING
assert p.state == states.SCHEDULING
amgr._terminate_sync.set()
sync_thread.join()
def write_sources(cmt_file_db, param_path, task_counter):
""" This function creates a stage that modifies the CMTSOLUTION files
before the simulations are run.
:param cmt_file_db: cmtfile in the database
:param param_path: path to parameter file directory
:param task_counter: total task count up until now in pipeline
:return: EnTK Stage
"""
# Get Database parameters
databaseparam_path = os.path.join(param_path,
"Database/DatabaseParameters.yml")
DB_params = read_yaml_file(databaseparam_path)
# Earthquake specific database parameters: Dir and Cid
Cdir, Cid = get_Centry_path(DB_params["databasedir"], cmt_file_db)
# Path to function
write_source_func = os.path.join(bin_path, "write_sources.py")
# Create a Stage object
w_sources = Stage()
w_sources.name = "Write-Sources"
# Create Task for stage
w_sources_t = Task()
w_sources_t.name = "Task-Sources"
w_sources_t.pre_exec = [ # Conda activate
DB_params["conda-activate"]
]
w_sources_t.executable = DB_params["bin-python"] #
# Assign executable
# to the task
w_sources_t.arguments = [write_source_func, cmt_file_db]
# In the future maybe to database dir as a total log?
w_sources_t.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), w_sources_t.name))
w_sources_t.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), w_sources_t.name))
# Add Task to the Stage
w_sources.add_tasks(w_sources_t)
task_counter += 1
return w_sources, task_counter
def create_process_path_files(cmt_file_db, param_path, task_counter):
"""This function creates the path files used for processing both
synthetic and observed data in ASDF format, as well as the following
windowing procedure.
:param cmt_file_db: cmtfile in the database
:param param_path: path to parameter file directory
:param pipelinedir: path to pipeline directory
:return: EnTK Stage
"""
# Get database parameter path
databaseparam_path = os.path.join(param_path,
"Database/DatabaseParameters.yml")
# Load Parameters
DB_params = read_yaml_file(databaseparam_path)
# Earthquake specific database parameters: Dir and Cid
Cdir, Cid = get_Centry_path(DB_params["databasedir"], cmt_file_db)
# Process path function
create_process_path_bin = os.path.join(bin_path, "create_path_files.py")
# Create Process Paths Stage (CPP)
# Create a Stage object
cpp = Stage()
cpp.name = "CreateProcessPaths"
# Create Task
cpp_t = Task()
cpp_t.name = "CPP-Task"
cpp_t.pre_exec = [ # Conda activate
DB_params["conda-activate"]
]
cpp_t.executable = DB_params["bin-python"] # Assign executable
# to the task
cpp_t.arguments = [create_process_path_bin, cmt_file_db]
# In the future maybe to database dir as a total log?
cpp_t.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), cpp_t.name))
cpp_t.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), cpp_t.name))
task_counter += 1
cpp.add_tasks(cpp_t)
return cpp, task_counter
def create_inversion_stage(cmt_file_db, param_path, task_counter):
"""Creates inversion stage.
:param cmt_file_db:
:param param_path:
:return:
"""
# Get database parameter path
databaseparam_path = os.path.join(param_path,
"Database/DatabaseParameters.yml")
# Load Parameters
DB_params = read_yaml_file(databaseparam_path)
# Earthquake specific database parameters: Dir and Cid
Cdir, Cid = get_Centry_path(DB_params["databasedir"], cmt_file_db)
# Function
inversion_func = os.path.join(bin_path, "inversion.py")
# Create a Stage object
inversion_stage = Stage()
inversion_stage.name = "CMT3D"
# Create Task
inversion_task = Task()
# This way the task gets the name of the path file
inversion_task.name = "Inversion"
inversion_task.pre_exec = [ # Conda activate
DB_params["conda-activate"]
]
inversion_task.executable = DB_params["bin-python"] # Assign exec
# to the task
inversion_task.arguments = [
inversion_func, "-f", cmt_file_db, "-p", param_path
]
# In the future maybe to database dir as a total log?
inversion_task.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), inversion_task.name))
inversion_task.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), inversion_task.name))
inversion_stage.add_tasks(inversion_task)
return inversion_stage
