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_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 generate_pipeline():
global CUR_TASKS, CUR_CORES, duration, MAX_NEW_STAGE
def func_condition():
global CUR_NEW_STAGE, MAX_NEW_STAGE
if CUR_NEW_STAGE < MAX_NEW_STAGE:
return True
return False
def func_on_true():
global CUR_NEW_STAGE
CUR_NEW_STAGE += 1
for t in p.stages[CUR_NEW_STAGE].tasks:
cores = randint(1,16)
t.arguments = ['-c', str(cores), '-t', str(duration)]
def func_on_false():
print 'Done'
# Create a Pipeline object
p = Pipeline()
for s in range(MAX_NEW_STAGE+1):
# Create a Stage object
s1 = Stage()
for i in range(CUR_TASKS):
t1 = Task()
t1.pre_exec = ['export PATH=/u/sciteam/balasubr/modules/stress-ng-0.09.34:$PATH']
t1.executable = ['stress-ng']
t1.arguments = [ '-c', str(CUR_CORES), '-t', str(duration)]
t1.cpu_reqs = {
'processes': 1,
'process_type': '',
'threads_per_process': CUR_CORES,
'thread_type': ''
}
# Add the Task to the Stage
s1.add_tasks(t1)
# Add post-exec to the Stage
s1.post_exec = {
'condition': func_condition,
'on_true': func_on_true,
'on_false': func_on_false
}
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def generate_pipeline(name, stages):
# Create a Pipeline object
p = Pipeline()
p.name = name
for s_cnt in range(stages):
# Create a Stage object
s = Stage()
s.name = 'Stage %s'%s_cnt
for t_cnt in range(5):
# Create a Task object
t = Task()
t.name = 'my-task' # Assign a name to the task (optional)
t.executable = '/bin/echo' # Assign executable to the task
# Assign arguments for the task executable
t.arguments = ['I am task %s in %s in %s'%(t_cnt, s_cnt, name)]
# Add the Task to the Stage
s.add_tasks(t)
# Add Stage to the Pipeline
p.add_stages(s)
return p
def describe_MD_stages():
# Docking stage
s1 = Stage()
s1.name = 'Docking.%d' % CUR_NEW_STAGE
# Docking task
t1 = Task()
t1.executable = ['sleep']
t1.arguments = ['3']
# Add the Docking task to the Docking Stage
s1.add_tasks(t1)
# MD stage
s2 = Stage()
s2.name = 'Simulation.%d' % CUR_NEW_STAGE
# 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 = ['5']
# Add the MD task to the Docking Stage
s2.add_tasks(t2)
# Add post-exec to the Stage
s2.post_exec = func_condition
return [s1, 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 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 post_stage():
if (not os.path.exists(f'{run_dir}/aggregator/stop.aggregator')):
nstages = len(p.stages)
s = Stage()
s.name = f"{nstages}"
t = Task()
t.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 4,
'thread_type': 'OpenMP'
}
t.gpu_reqs = {
'processes': 0,
'process_type': None,
'threads_per_process': 0,
'thread_type': None
}
t.name = f" {i}_{nstages} "
t.executable = PYTHON
t.arguments = [
f'{current_dir}/simulation.py',
f'{run_dir}/simulations/all/{i}_{nstages}', ADIOS_XML
]
subprocess.getstatusoutput(
f'ln -s {run_dir}/simulations/all/{i}_{nstages} {run_dir}/simulations/new/{i}_{nstages}'
)
s.add_tasks(t)
s.post_exec = post_stage
p.add_stages(s)
def test_stage_task_addition(self, mocked_init):
s = Stage()
s._p_pipeline = {'uid': None, 'name': None}
s._uid = 'stage.0000'
s._name = None
s._tasks = set()
t1 = mock.MagicMock(spec=Task)
t2 = mock.MagicMock(spec=Task)
s.add_tasks(set([t1, t2]))
self.assertIsInstance(s.tasks, set)
self.assertEqual(s._task_count, 2)
self.assertIn(t1, s.tasks)
self.assertIn(t2, s.tasks)
s = Stage()
s._uid = 'stage.0000'
s._name = None
s._p_pipeline = {'uid': None, 'name': None}
s._tasks = set()
t1 = mock.MagicMock(spec=Task)
t2 = mock.MagicMock(spec=Task)
s.add_tasks([t1, t2])
self.assertIsInstance(s.tasks, set)
self.assertEqual(s._task_count, 2)
self.assertIn(t1, s.tasks)
self.assertIn(t2, s.tasks)
def generate_ml_stage(self) -> Stage:
stage = Stage()
stage.name = "learning"
cfg = self.cfg.ml_stage
task = Task()
task.cpu_reqs = cfg.cpu_reqs.dict()
task.gpu_reqs = cfg.gpu_reqs.dict()
task.pre_exec = cfg.pre_exec
task.executable = cfg.executable
task.arguments = cfg.arguments
# Update base parameters
cfg.run_config.input_path = self.aggregated_data_path(
self.cur_iteration)
cfg.run_config.output_path = self.model_path(self.cur_iteration)
if self.cur_iteration > 0:
cfg.run_config.init_weights_path = self.latest_ml_checkpoint_path(
self.cur_iteration - 1)
cfg_path = self.experiment_dirs["ml_runs"].joinpath(
f"ml_{self.cur_iteration:03d}.yaml")
cfg.run_config.dump_yaml(cfg_path)
task.arguments += ["-c", cfg_path]
stage.add_tasks(task)
return stage
def generate_pipeline():
# Create a Pipeline object
p = Pipeline()
# Create a Stage object
s1 = Stage()
# Create a Task object which creates a file named 'output.txt' of size 1 MB
for x in range(10):
t1 = Task()
t1.executable = 'cat'
t1.arguments = ['file1.txt', 'file2.txt', '>', 'output.txt']
t1.copy_input_data = ['$SHARED/file1.txt', '$SHARED/file2.txt']
t1.download_output_data = [
'output.txt > %s/output_%s.txt' % (cur_dir, x + 1)
]
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def test_amgr_synchronizer():
amgr = Amgr(hostname=host, port=port, username=username, password=password)
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._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,
rmq_conn_params=amgr._rmq_conn_params,
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()
# Wait for AppManager to finish the message exchange
# no need to set *)terminate_sync* but a timeout instead
# amgr._terminate_sync.set()
sync_thread.join(15)
for t in p.stages[0].tasks:
assert t.state == states.COMPLETED
def test_stage_exceptions(self, mocked_generate_id, l, i, b, se):
"""
***Purpose***: Test if correct exceptions are raised when attributes are
assigned unacceptable values.
"""
s = Stage()
data_type = [l, i, b, se]
for data in data_type:
if not isinstance(data, str):
with self.assertRaises(TypeError):
s.name = data
# if isinstance(data,str):
# with self.assertRaises(ValueError):
# s.name = data
with self.assertRaises(TypeError):
s.tasks = data
with self.assertRaises(TypeError):
s.add_tasks(data)
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,
rmq_conn_params=amgr._rmq_conn_params,
resubmit_failed=False)
wfp.start_processor()
assert wfp.check_processor()
wfp.terminate_processor()
assert not wfp.check_processor()
def generate_aggregating_stage(self) -> Stage:
stage = Stage()
stage.name = "aggregating"
cfg = self.cfg.aggregation_stage
# Aggregation task
task = Task()
task.cpu_reqs = cfg.cpu_reqs.dict()
task.pre_exec = cfg.pre_exec
task.executable = cfg.executable
task.arguments = cfg.arguments
# Update base parameters
cfg.run_config.experiment_directory = self.cfg.experiment_directory
cfg.run_config.output_path = self.aggregated_data_path(
self.cur_iteration)
cfg_path = self.experiment_dirs["aggregation_runs"].joinpath(
f"aggregation_{self.cur_iteration:03d}.yaml")
cfg.run_config.dump_yaml(cfg_path)
task.arguments += ["-c", cfg_path]
stage.add_tasks(task)
return stage
def test_wfp_start_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)
assert wfp.start_processor()
assert not wfp._enqueue_thread
assert not wfp._dequeue_thread
assert not wfp._enqueue_thread_terminate.is_set()
assert not wfp._dequeue_thread_terminate.is_set()
assert not wfp._wfp_terminate.is_set()
assert wfp._wfp_process.is_alive()
wfp._wfp_terminate.set()
wfp._wfp_process.join()
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 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 generate_aggregating_task(self):
"""
Function to concatenate the MD trajectory (h5 contact map)
"""
p = Pipeline()
p.name = 'aggragating'
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 %s' % conda_path]
t2.pre_exec += ['cd %s' % agg_path]
t2.executable = ['%s/bin/python' % conda_path] # MD_to_CVAE.py
t2.arguments = [
'%s/MD_to_CVAE.py' % agg_path,
'--sim_path', md_path,
'--train_frames', 100000]
# assign hardware the task
t2.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 4,
'thread_type': 'OpenMP'
}
# Add the aggregation task to the aggreagating stage
s2.add_tasks(t2)
p.add_stages(s2)
return p
def func_on_true():
global CUR_NEW_STAGE, CUR_TASKS, CUR_CORES, duration
CUR_NEW_STAGE += 1
s = Stage()
for i in range(CUR_TASKS):
t = Task()
t.pre_exec = [
'export PATH=/u/sciteam/balasubr/modules/stress-ng-0.09.34:$PATH'
]
t.executable = ['stress-ng']
t.arguments = ['-c', str(CUR_CORES), '-t', str(duration)]
t.cpu_reqs = {
'processes': 1,
'process_type': '',
'threads_per_process': CUR_CORES,
'thread_type': ''
}
# Add the Task to the Stage
s.add_tasks(t)
# Add post-exec to the Stage
s.post_exec = {
'condition': func_condition,
'on_true': func_on_true,
'on_false': func_on_false
}
p.add_stages(s)
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 %s' % conda_path]
t2.pre_exec += ['module unload python']
t2.pre_exec += ['module load ibm-wml-ce']
t2.pre_exec += ['cd %s' % agg_path]
#t2.executable = ['%s/bin/python' % conda_path] # MD_to_CVAE.py
t2.executable = [
'/sw/summit/ibm-wml-ce/anaconda-base/envs/ibm-wml-ce-1.7.0-2/bin/python'
]
t2.arguments = ['%s/MD_to_CVAE.py' % agg_path, '--sim_path', md_path]
# Add the aggregation task to the aggreagating stage
s2.add_tasks(t2)
return s2
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': condition,
'on_true': on_true,
'on_false': on_false
}
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_outlier_detection_stage(self) -> Stage:
stage = Stage()
stage.name = "outlier_detection"
cfg = self.cfg.od_stage
task = Task()
task.cpu_reqs = cfg.cpu_reqs.dict()
task.gpu_reqs = cfg.gpu_reqs.dict()
task.pre_exec = cfg.pre_exec
task.executable = cfg.executable
task.arguments = cfg.arguments
self.outlier_pdbs_path(self.cur_iteration).mkdir()
# Update base parameters
cfg.run_config.experiment_directory = self.cfg.experiment_directory
cfg.run_config.input_path = self.aggregated_data_path(
self.cur_iteration)
cfg.run_config.output_path = self.outlier_pdbs_path(self.cur_iteration)
cfg.run_config.weights_path = self.latest_ml_checkpoint_path(
self.cur_iteration)
cfg.run_config.restart_points_path = self.restart_points_path(
self.cur_iteration)
cfg_path = self.experiment_dirs["od_runs"].joinpath(
f"od_{self.cur_iteration:03d}.yaml")
cfg.run_config.dump_yaml(cfg_path)
task.arguments += ["-c", cfg_path]
stage.add_tasks(task)
return stage
def test_stage_task_addition():
s = Stage()
t1 = Task()
t1.executable = ['/bin/date']
t2 = Task()
t2.executable = ['/bin/date']
s.add_tasks(set([t1, t2]))
assert type(s.tasks) == set
assert s._task_count == 2
assert t1 in s.tasks
assert t2 in s.tasks
s = Stage()
t1 = Task()
t1.executable = ['/bin/date']
t2 = Task()
t2.executable = ['/bin/date']
s.add_tasks([t1, t2])
assert type(s.tasks) == set
assert s._task_count == 2
assert t1 in s.tasks
assert t2 in s.tasks
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 generate_pipeline():
# Create a Pipeline object
p = Pipeline()
p.name = 'p1'
# Create a Stage object
s1 = Stage()
s1.name = 's1'
s1_task_uids = []
for cnt in range(128):
# Create a Task object
t1 = Task()
t1.name = 't%s' % (cnt + 1)
# to make a python script executable:
# 1) add to first line "shebang": #!/usr/bin/env python
# 2) chmod +x SerialCode.py
# The executable always has to be in the Target Machine
t1.executable = '~/SerialCode.py'
# Add the Task to the Stage
s1.add_tasks(t1)
s1_task_uids.append(t1.name)
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def test_wfp_initialization(s, b, l):
p = Pipeline()
stage = Stage()
t = Task()
t.executable = '/bin/date'
stage.add_tasks(t)
p.add_stages(stage)
rmq_conn_params = pika.ConnectionParameters(host=hostname, port=port)
wfp = WFprocessor(sid='rp.session.local.0000',
workflow=set([p]),
pending_queue=['pending'],
completed_queue=['completed'],
rmq_conn_params=rmq_conn_params,
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._rmq_conn_params == rmq_conn_params
assert wfp._wfp_process is None
assert wfp._workflow == set([p])
if not isinstance(s, str):
wfp = WFprocessor(sid=s,
workflow=set([p]),
pending_queue=l,
completed_queue=l,
rmq_conn_params=rmq_conn_params,
resubmit_failed=b)
def generate_pipeline(name, stages):
# Create a Pipeline object
p = Pipeline()
p.name = name
for s_cnt in range(stages):
# Create a Stage object
s = Stage()
s.name = 'Stage %s' % s_cnt
for t_cnt in range(5):
# Create a Task object
t = Task()
t.name = 'my-task' # Assign a name to the task (optional)
t.executable = '/bin/echo' # Assign executable to the task
# Assign arguments for the task executable
t.arguments = ['I am task %s in %s in %s' % (t_cnt, s_cnt, name)]
# Add the Task to the Stage
s.add_tasks(t)
# Add Stage to the Pipeline
p.add_stages(s)
return p
def test_stage_task_addition():
s = Stage()
t1 = Task()
t1.executable = '/bin/date'
t2 = Task()
t2.executable = '/bin/date'
s.add_tasks(set([t1, t2]))
assert type(s.tasks) == set
assert s._task_count == 2
assert t1 in s.tasks
assert t2 in s.tasks
s = Stage()
t1 = Task()
t1.executable = '/bin/date'
t2 = Task()
t2.executable = '/bin/date'
s.add_tasks([t1, t2])
assert type(s.tasks) == set
assert s._task_count == 2
assert t1 in s.tasks
assert t2 in s.tasks
def generate_pipeline(nid):
p = Pipeline()
s1 = Stage()
s2 = Stage()
t1 = Task()
p.name = 'p%s' % nid
s1.name = 's1'
s2.name = 's2'
t1.name = 't1'
t1.executable = '/bin/echo'
t1.arguments = ['hello']
s1.add_tasks(t1)
p.add_stages(s1)
for cnt in range(10):
tn = Task()
tn.name = 't%s' % (cnt + 1)
tn.executable = '/bin/echo'
tn.arguments = ['world']
# Copy data from the task in first stage to the current task's location
tn.copy_input_data = ['$Pipeline_%s_Stage_%s_Task_%s/output.txt'
% (p.name, s1.name, t1.name)]
s2.add_tasks(tn)
p.add_stages(s2)
return p
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 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_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 get_pipeline(shared_fs=False, size=1):
p = Pipeline()
p.name = 'p'
n = 4
s1 = Stage()
s1.name = 's1'
for x in range(n):
t = Task()
t.name = 't%s'%x
# dd if=/dev/random bs=<byte size of a chunk> count=<number of chunks> of=<output file name>
t.executable = 'dd'
if not shared_fs:
t.arguments = ['if=/dev/urandom','bs=%sM'%size, 'count=1', 'of=$NODE_LFS_PATH/s1_t%s.txt'%x]
else:
t.arguments = ['if=/dev/urandom','bs=%sM'%size, 'count=1', 'of=/home/vivek91/s1_t%s.txt'%x]
t.cpu_reqs['processes'] = 1
t.cpu_reqs['threads_per_process'] = 24
t.cpu_reqs['thread_type'] = ''
t.cpu_reqs['process_type'] = ''
t.lfs_per_process = 1024
s1.add_tasks(t)
p.add_stages(s1)
s2 = Stage()
s2.name = 's2'
for x in range(n):
t = Task()
t.executable = ['dd']
if not shared_fs:
t.arguments = ['if=$NODE_LFS_PATH/s1_t%s.txt'%x,'bs=%sM'%size, 'count=1', 'of=$NODE_LFS_PATH/s2_t%s.txt'%x]
else:
t.arguments = ['if=/home/vivek91/s1_t%s.txt'%x,'bs=%sM'%size, 'count=1', 'of=/home/vivek91/s2_t%s.txt'%x]
t.cpu_reqs['processes'] = 1
t.cpu_reqs['threads_per_process'] = 24
t.cpu_reqs['thread_type'] = ''
t.cpu_reqs['process_type'] = ''
t.tag = 't%s'%x
s2.add_tasks(t)
p.add_stages(s2)
return p
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_stage_check_complete():
s = Stage()
t1 = Task()
t1.executable = ['/bin/date']
t2 = Task()
t2.executable = ['/bin/date']
s.add_tasks([t1, t2])
assert s._check_stage_complete() == False
s._set_tasks_state(states.DONE)
assert s._check_stage_complete() == True
def test_amgr_synchronizer():
logger = ru.Logger('radical.entk.temp_logger')
profiler = ru.Profiler(name='radical.entk.temp')
amgr = Amgr(hostname=hostname, port=port)
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 generate_pipeline():
def func_condition():
global CUR_NEW_STAGE, MAX_NEW_STAGE
if CUR_NEW_STAGE <= MAX_NEW_STAGE:
return True
return False
def func_on_true():
global CUR_NEW_STAGE
CUR_NEW_STAGE += 1
shuffle(p.stages[CUR_NEW_STAGE:])
def func_on_false():
print 'Done'
# Create a Pipeline object
p = Pipeline()
for s in range(MAX_NEW_STAGE+1):
# Create a Stage object
s1 = Stage()
for i in range(CUR_TASKS):
t1 = Task()
t1.executable = '/bin/sleep'
t1.arguments = [ '30']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add post-exec to the Stage
s1.post_exec = {
condition': func_condition,
on_true': func_on_true,
on_false': func_on_false
}
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def test_stage_set_tasks_state():
s = Stage()
t1 = Task()
t1.executable = ['/bin/date']
t2 = Task()
t2.executable = ['/bin/date']
s.add_tasks([t1, t2])
with pytest.raises(ValueError):
s._set_tasks_state(2)
s._set_tasks_state(states.DONE)
assert t1.state == states.DONE
assert t2.state == states.DONE
def on_true():
global NUM_TASKS, CUR_STAGE
NUM_TASKS *= 2
s = Stage()
s.name = 's%s'%CUR_STAGE
for t in range(NUM_TASKS):
s.add_tasks(create_single_task())
s.post_exec = condition
p1.add_stages(s)
def create_pipeline():
p = Pipeline()
s = Stage()
t1 = Task()
t1.name = 'simulation'
t1.executable = ['sleep']
t1.arguments = ['10']
s.add_tasks(t1)
p.add_stages(s)
return p
def test_wfp_enqueue():
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()
amgr.workflow = [p]
profiler = ru.Profiler(name='radical.entk.temp')
for t in p.stages[0].tasks:
assert t.state == states.INITIAL
assert p.stages[0].state == states.INITIAL
assert p.state == states.INITIAL
amgr._terminate_sync = Event()
sync_thread = Thread(target=amgr._synchronizer, name='synchronizer-thread')
sync_thread.start()
proc = Process(target=func_for_enqueue_test, name='temp-proc', args=(wfp,))
proc.start()
proc.join()
amgr._terminate_sync.set()
sync_thread.join()
for t in p.stages[0].tasks:
assert t.state == states.SCHEDULED
assert p.stages[0].state == states.SCHEDULED
assert p.state == states.SCHEDULING
def create_pipeline():
p = Pipeline()
s = Stage()
t1 = Task()
t1.name = 'simulation'
t1.executable = ['/bin/echo']
t1.arguments = ['hello']
t1.copy_input_data = []
t1.copy_output_data = []
s.add_tasks(t1)
p.add_stages(s)
return p
def generate_pipeline():
def func_condition():
p.suspend()
print 'Suspending pipeline %s for 10 seconds' %p.uid
sleep(10)
return True
def func_on_true():
print 'Resuming pipeline %s' %p.uid
p.resume()
def func_on_false():
pass
# Create a Pipeline object
p = Pipeline()
# Create a Stage object
s1 = Stage()
for i in range(10):
t1 = Task()
t1.executable = '/bin/sleep'
t1.arguments = ['30']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add post-exec to the Stage
s1.post_exec = {
'condition': func_condition,
'on_true': func_on_true,
'on_false': func_on_false
}
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def test_integration_local():
"""
**Purpose**: Run an EnTK application on localhost
"""
def create_single_task():
t1 = Task()
t1.name = 'simulation'
t1.executable = ['/bin/echo']
t1.arguments = ['hello']
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
appman = AppManager(hostname=hostname, port=port)
appman.resource_desc = res_dict
appman.workflow = [p1]
appman.run()
def generate_pipeline():
# Create a Pipeline object
p = Pipeline()
# Create a Stage object
s1 = Stage()
# Create a Task object which creates a file named 'output.txt' of size 1 MB
t1 = Task()
t1.executable = ['/bin/sleep']
t1.arguments = ['300']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def generate_pipeline():
# Create a Pipeline object
p = Pipeline()
# Create a Stage object
s1 = Stage()
# Create a Task object which creates a file named 'output.txt' of size 1 MB
t1 = Task()
t1.executable = ['mv']
t1.arguments = ['temp','/tmp/']
t1.upload_input_data = ['%s/temp'%cur_dir]
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def test_wfp_initialize_workflow():
p = Pipeline()
s = Stage()
t = Task()
t.executable = ['/bin/date']
s.add_tasks(t)
p.add_stages(s)
wfp = WFprocessor(sid='test',
workflow=[p],
pending_queue=list(),
completed_queue=list(),
mq_hostname=hostname,
port=port,
resubmit_failed=False)
wfp._initialize_workflow()
assert p.uid is not None
assert p.stages[0].uid is not None
for t in p.stages[0].tasks:
assert t.uid is not None
def generate_pipeline():
# Create a Pipeline object
p = Pipeline()
# Create a Stage object
s1 = Stage()
# Create a Task object which creates a file named 'output.txt' of size 1 MB
for x in range(10):
t1 = Task()
t1.executable = 'cat'
t1.arguments = ['file1.txt','file2.txt','>','output.txt']
t1.copy_input_data = ['$SHARED/file1.txt', '$SHARED/file2.txt']
t1.download_output_data = ['output.txt > %s/output_%s.txt' %(cur_dir,x+1)]
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def generate_pipeline():
# Create a Pipeline object
p = Pipeline()
p.name = 'p1'
# Create a Stage object
s1 = Stage()
s1.name = 's1'
# Create 4K tasks to ensure we don't hit any RMQ connection drops
for _ in range(4096):
t1 = Task()
t1.executable = ['/bin/echo']
t1.arguments = ['"Hello World"']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
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/false']
# t1.arguments = ['"Hello World"','>>','temp.txt']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def test_stage_exceptions(t, l, i, b, se):
"""
***Purpose***: Test if correct exceptions are raised when attributes are
assigned unacceptable values.
"""
s = Stage()
data_type = [t, l, i, b, se]
for data in data_type:
print 'Using: %s, %s' % (data, type(data))
if not isinstance(data, str):
with pytest.raises(TypeError):
s.name = data
with pytest.raises(TypeError):
s.tasks = data
with pytest.raises(TypeError):
s.add_tasks(data)
def test_stage_pass_uid():
s = Stage()
s._uid = 's'
s.name = 's1'
s.parent_pipeline['uid'] = 'p'
s.parent_pipeline['name'] = 'p1'
t1 = Task()
t2 = Task()
s.add_tasks([t1,t2])
s._pass_uid()
assert t1.parent_stage['uid'] == s.uid
assert t1.parent_stage['name'] == s.name
assert t1.parent_pipeline['uid'] == s.parent_pipeline['uid']
assert t1.parent_pipeline['name'] == s.parent_pipeline['name']
assert t2.parent_stage['uid'] == s.uid
assert t2.parent_stage['name'] == s.name
assert t2.parent_pipeline['uid'] == s.parent_pipeline['uid']
assert t2.parent_pipeline['name'] == s.parent_pipeline['name']
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 = {
'condition': func_condition,
'on_true': func_on_true,
'on_false': func_on_false
}
p.add_stages(s)
def generate_pipeline():
# Create a Pipeline object
p = Pipeline()
# Create a Stage object
s1 = Stage()
# Create a Task object which creates a file named 'output.txt' of size 1 MB
t1 = Task()
t1.executable = '/bin/bash'
t1.arguments = ['-l', '-c', 'base64 /dev/urandom | head -c 1000000 > output.txt']
# 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()
# Create a Task object
t2 = Task()
t2.executable = '/bin/bash'
t2.arguments = ['-l', '-c', 'grep -o . output.txt | sort | uniq -c > ccount.txt']
# Copy data from the task in the first stage to the current task's location
t2.copy_input_data = ['$Pipline_%s_Stage_%s_Task_%s/output.txt' % (p.uid, s1.uid, t1.uid)]
# Add the Task to the Stage
s2.add_tasks(t2)
# Add Stage to the Pipeline
p.add_stages(s2)
# Create another Stage object to hold checksum tasks
s3 = Stage()
# Create a Task object
t3 = Task()
t3.executable = '/bin/bash'
t3.arguments = ['-l', '-c', 'sha1sum ccount.txt > chksum.txt']
# Copy data from the task in the first stage to the current task's location
t3.copy_input_data = ['$Pipline_%s_Stage_%s_Task_%s/ccount.txt' % (p.uid, s2.uid, t2.uid)]
# Download the output of the current task to the current location
t3.download_output_data = ['chksum.txt > chksum_%s.txt' % cnt]
# Add the Task to the Stage
s3.add_tasks(t3)
# Add Stage to the Pipeline
p.add_stages(s3)
return p
def generate_pipeline():
def func_condition():
global CUR_NEW_STAGE, MAX_NEW_STAGE
if CUR_NEW_STAGE <= MAX_NEW_STAGE:
return True
return 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 = {
'condition': func_condition,
'on_true': func_on_true,
'on_false': func_on_false
}
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 = {
'condition': func_condition,
'on_true': func_on_true,
'on_false': func_on_false
}
# Add Stage to the Pipeline
p.add_stages(s1)
return p
stage_uids = list()
task_uids = dict()
Stages = 3
Replicas = 4
for N_Stg in range(Stages):
stg = Stage() ## initialization
task_uids['Stage_%s'%N_Stg] = list()
if N_Stg == 0:
for n0 in range(Replicas):
t = Task()
t.executable = ['/usr/local/packages/gromacs/5.1.4/INTEL-140-MVAPICH2-2.0/bin/gmx_mpi_d'] #MD Engine
t.upload_input_data = ['in.gro', 'in.top', 'FNF.itp', 'martini_v2.2.itp', 'in.mdp']
t.pre_exec = ['module load gromacs', '/usr/local/packages/gromacs/5.1.4/INTEL-140-MVAPICH2-2.0/bin/gmx_mpi_d grompp -f in.mdp -c in.gro -o in.tpr -p in.top']
t.arguments = ['mdrun', '-s', 'in.tpr', '-deffnm', 'out']
t.cores = 32
stg.add_tasks(t)
task_uids['Stage_%s'%N_Stg].append(t.uid)
p.add_stages(stg)
stage_uids.append(stg.uid)
else:
for n0 in range(Replicas):
t = Task()
t.executable = ['/usr/local/packages/gromacs/5.1.4/INTEL-140-MVAPICH2-2.0/bin/gmx_mpi_d'] #MD Engine
t.copy_input_data = ['$Pipeline_%s_Stage_%s_Task_%s/out.gro > in.gro'%(p.uid, stage_uids[N_Stg-1], task_uids['Stage_%s'%(N_Stg-1)][n0]), '$Pipeline_%s_Stage_%s_Task_%s/in.top'%(p.uid, stage_uids[N_Stg-1], task_uids['Stage_%s'%(N_Stg-1)][n0]), '$Pipeline_%s_Stage_%s_Task_%s/FNF.itp'%(p.uid, stage_uids[N_Stg-1], task_uids['Stage_%s'%(N_Stg-1)][n0]), '$Pipeline_%s_Stage_%s_Task_%s/martini_v2.2.itp'%(p.uid, stage_uids[N_Stg-1], task_uids['Stage_%s'%(N_Stg-1)][n0]), '$Pipeline_%s_Stage_%s_Task_%s/in.mdp'%(p.uid, stage_uids[N_Stg-1], task_uids['Stage_%s'%(N_Stg-1)][n0])]
t.pre_exec = ['module load gromacs', '/usr/local/packages/gromacs/5.1.4/INTEL-140-MVAPICH2-2.0/bin/gmx_mpi_d grompp -f in.mdp -c in.gro -o in.tpr -p in.top']
t.arguments = ['mdrun', '-s', 'in.tpr', '-deffnm', 'out']
t.cores = 32
if __name__ == '__main__':
# Create a Pipeline object
p = Pipeline()
# Create a Stage object
s = Stage()
# Create a Task object
t = Task()
t.name = 'my-first-task' # Assign a name to the task (optional, do not use ',' or '_')
t.executable = '/bin/echo' # Assign executable to the task
t.arguments = ['Hello World'] # Assign arguments for the task executable
# Add Task to the Stage
s.add_tasks(t)
# Add Stage to the Pipeline
p.add_stages(s)
# Create Application Manager
appman = AppManager(hostname=hostname, port=port)
# Create a dictionary describe four mandatory keys:
# resource, walltime, and cpus
# resource is 'local.localhost' to execute locally
res_dict = {
'resource': 'local.localhost',
'walltime': 10,
'cpus': 1