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_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 test_pipeline_decrement_stage():
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])
p._increment_stage()
p._increment_stage()
assert p._stage_count == 2
assert p._cur_stage == 2
assert p._completed_flag.is_set() == True
p._decrement_stage()
assert p._stage_count == 2
assert p._cur_stage == 1
assert p._completed_flag.is_set() == False
p._decrement_stage()
assert p._stage_count == 2
assert p._cur_stage == 0
assert p._completed_flag.is_set() == False
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_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_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 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 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 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 GeneratePipeline(pcfg, ecfg, pipe_name, exp_dir):
# Append the exp_dir to the ecfg dictionary to simplify things a bit
ecfg['exp_dir'] = exp_dir
# Append the input file to the list of options (if need be)
if "input_data_file" in ecfg.keys():
ecfg['options']['input_data_file'] = ecfg['input_data_file']
# Append the pipeline id to the list of options
ecfg['options']['pipeline_id'] = pipe_name
# Initialize the pipeline object
p = Pipeline()
# Give the pipeline a name
p.name = pipe_name
# Loop through the necessary stages for this module
stage_names = ["pre-process", "fit", "project", "post-process"]
for this_stage in stage_names:
if this_stage in pcfg.keys():
# Populate the pipeline with the stages
p.add_stages(
GenerateStage(pcfg[this_stage], ecfg, p.name, this_stage))
return (p)
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_pipeline_decrement_stage():
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])
p._increment_stage()
p._increment_stage()
assert p._stage_count == 2
assert p._cur_stage == 2
assert p._completed_flag.is_set() == True
p._decrement_stage()
assert p._stage_count == 2
assert p._cur_stage == 1
assert p._completed_flag.is_set() == False
p._decrement_stage()
assert p._stage_count == 2
assert p._cur_stage == 0
assert p._completed_flag.is_set() == False
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 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 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 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 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_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_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 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=$NODE_LFS_PATH/s2_t%s.txt'%x]
else:
t.arguments = ['if=/home/vivek91/s1_t%s.txt'%x,'bs=%sM'%size, 'count=1', 'of=/home/vivek91/s2_t%s.txt'%x]
t.cpu_reqs['processes'] = 1
t.cpu_reqs['threads_per_process'] = 24
t.cpu_reqs['thread_type'] = ''
t.cpu_reqs['process_type'] = ''
t.tag = 't%s'%x
s2.add_tasks(t)
p.add_stages(s2)
return p
def generate_pipeline():
def func_condition():
global CUR_NEW_STAGE, MAX_NEW_STAGE
if CUR_NEW_STAGE <= MAX_NEW_STAGE:
func_on_true()
func_on_false()
def func_on_true():
global CUR_NEW_STAGE
CUR_NEW_STAGE += 1
s = Stage()
for i in range(10):
t = Task()
t.executable = '/bin/sleep'
t.arguments = ['30']
s.add_tasks(t)
# Add post-exec to the Stage
s.post_exec = func_condition
p.add_stages(s)
def func_on_false():
print('Done')
# Create a Pipeline object
p = Pipeline()
# Create a Stage object
s1 = Stage()
for i in range(10):
t1 = Task()
t1.executable = 'sleep'
t1.arguments = ['30']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add post-exec to the Stage
s1.post_exec = func_condition
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def get_pipeline(shared_fs=False, size=1):
p = Pipeline()
p.name = 'p'
n = 4
s1 = Stage()
s1.name = 's1'
for x in range(n):
t = Task()
t.name = 't%s'%x
# dd if=/dev/random bs=<byte size of a chunk> count=<number of chunks> of=<output file name>
t.executable = ['dd']
if not shared_fs:
t.arguments = ['if=/dev/urandom','bs=%sM'%size, 'count=1', 'of=$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_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 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_pipeline_stage_addition(self, mocked_generate_id, mocked_Lock,
mocked_Event):
p = Pipeline()
s1 = mock.MagicMock(spec=Stage)
s2 = mock.MagicMock(spec=Stage)
p.add_stages([s1, s2])
self.assertEqual(type(p.stages), list)
self.assertEqual(p._stage_count, 2)
self.assertEqual(p._cur_stage, 1)
self.assertEqual(p.stages[0], s1)
self.assertEqual(p.stages[1], 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',
'$SHARED/topol.top > topol.top'
]
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
# Create a Stage 2
s2 = Stage()
for cnt in range(tasks):
# Create a Task object according to the app_name
t2 = Task()
t2.pre_exec = [
'module load gromacs/5.0/INTEL-140-MVAPICH2-2.0',
'export OMP_NUM_THREADS=%s' % num_cores
]
t2.executable = app_coll['mdrun']['executable']
t2.arguments = app_coll['mdrun']['arguments']
#t2.cores = app_coll['mdrun']['cores']
t2.cores = num_cores
t2.copy_input_data = [
'$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_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 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 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 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
for t in p.stages[CUR_NEW_STAGE].tasks:
dur = randint(10, 30)
t.arguments = [str(dur)]
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 _ in range(CUR_TASKS):
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
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 = [
'$Pipeline_%s_Stage_%s_Task_%s/output.txt' %
(p.name, s1.name, t1.name)
]
# Add the Task to the Stage
s2.add_tasks(t2)
s2_task_uids.append(t2.name)
# Add Stage to the Pipeline
p.add_stages(s2)
return p
def describe_MD_pipeline():
p = Pipeline()
p.name = 'MD'
# MD stage
s1 = Stage()
s1.name = 'OpenMM'
# Each Task() is an OpenMM executable that will run on a single GPU.
# Set sleep time for local testing
# for i in range(18):
task = Task()
task.name = 'md'
task.pre_exec = []
# task.pre_exec += ['export MINICONDA=/gpfs/alpine/scratch/jdakka/bip178/miniconda']
# task.pre_exec += ['export PATH=$MINICONDA/bin:$PATH']
# task.pre_exec += ['export LD_LIBRARY_PATH=$MINICONDA/lib:$LD_LIBRARY_PATH']
task.pre_exec += ['module load python/2.7.15-anaconda2-5.3.0']
task.pre_exec += ['module load cuda/9.1.85']
task.pre_exec += ['module load gcc/6.4.0']
task.pre_exec += ['source activate openmm']
task.pre_exec += ['cd /gpfs/alpine/scratch/jdakka/bip178/benchmarks/MD_exps/fs-pep/results_2']
task.executable = '/ccs/home/jdakka/.conda/envs/openmm/bin/python'
task.arguments = ['run_openmm.py', '-f',
'/gpfs/alpine/scratch/jdakka/bip178/benchmarks/MD_exps/fs-pep/pdb/100-fs-peptide-400K.pdb']
task.cpu_reqs = {'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': None
}
task.gpu_reqs = {'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': 'CUDA'
}
# Add the MD task to the Docking Stage
s1.add_tasks(task)
# Add MD stage to the MD Pipeline
p.add_stages(s1)
return p
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 create_pipeline():
p = Pipeline()
s = Stage()
t = Task()
t.name = 'simulation'
t.executable = ['/bin/echo']
t.arguments = ['hello']
t.copy_input_data = []
t.copy_output_data = []
s.add_tasks(t)
p.add_stages(s)
return p
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_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 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 test_pipeline_assignment_exceptions(t, l, i, b, se):
p = Pipeline()
data_type = [t, l, i, b, se]
for data in data_type:
if not isinstance(data, str):
with pytest.raises(TypeError):
p.name = data
with pytest.raises(TypeError):
p.stages = data
with pytest.raises(TypeError):
p.add_stages(data)
def test_pipeline_assignment_exceptions(t, l, i, b, se):
p = Pipeline()
data_type = [t, l, i, b, se]
for data in data_type:
if not isinstance(data, str):
with pytest.raises(TypeError):
p.name = data
with pytest.raises(TypeError):
p.stages = data
with pytest.raises(TypeError):
p.add_stages(data)
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 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_amgr_run_mock():
p = Pipeline()
s = Stage()
t = Task()
t.name = 'simulation'
t.executable = ['/bin/date']
s.tasks = t
p.add_stages(s)
res_dict = {
'resource': 'local.localhost',
'walltime': 5,
'cpus': 1,
'project': ''
}
appman = Amgr(hostname=hostname, port=port, rts="mock")
appman.resource_desc = res_dict
appman.workflow = [p]
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/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 = ['$Pipline_%s_Stage_%s_Task_%s/ccount.txt' % (p.uid, s2.uid, t2.uid)]
# Download the output of the current task to the current location
t3.download_output_data = ['chksum.txt > chksum_%s.txt' % cnt]
# Add the Task to the Stage
s3.add_tasks(t3)
# Add Stage to the Pipeline
p.add_stages(s3)
return p
# Create a Pipeline object
p = Pipeline()
# Create a Stage object
s1 = Stage()
# Create a Task object which creates a file named 'output.txt' of size 1 MB
t1 = Task()
t1.executable = '/bin/bash'
t1.arguments = ['-l', '-c', 'base64 /dev/urandom | head -c 1000000 > output.txt']
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
# Create another Stage object
s2 = Stage()
s2.name = 'Stage 2'
# Create a Task object
t2 = Task()
t2.executable = ['/bin/bash']
t2.arguments = ['-l', '-c', 'grep -o . output.txt | sort | uniq -c > ccount.txt']
# Copy data from the task in the first stage to the current task's location
t2.copy_input_data = ['$Pipline_%s_Stage_%s_Task_%s/output.txt' % (p.uid, s1.uid, t1.uid)]
# Download the output of the current task to the current location
t2.download_output_data = ['ccount.txt']
# Add the Task to the Stage
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
stg.add_tasks(t)
task_uids['Stage_%s'%N_Stg].append(t.uid)
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
}
# Assign resource request description to the Application Manager
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
def init_cycle(self, replicas, replica_cores, python_path, md_executable, exchange_method, min_temp, max_temp, timesteps, basename, pre_exec): # "cycle" = 1 MD stage plus the subsequent exchange computation
"""
Initial cycle consists of:
1) Create tarball of MD input data
2) Transfer the tarball to pilot sandbox
3) Untar the tarball
4) Run first cycle
"""
#Initialize Pipeline
self._prof.prof('InitTar', uid=self._uid)
p = Pipeline()
p.name = 'initpipeline'
md_dict = dict() #bookkeeping
tar_dict = dict() #bookkeeping
#Write the input files
self._prof.prof('InitWriteInputs', uid=self._uid)
writeInputs.writeInputs(
max_temp=max_temp,
min_temp=min_temp,
replicas=replicas,
timesteps=timesteps,
basename=basename)
self._prof.prof('EndWriteInputs', uid=self._uid)
self._prof.prof('InitTar', uid=self._uid)
#Create Tarball of input data
tar = tarfile.open("input_files.tar", "w")
for name in [
basename + ".prmtop", basename + ".inpcrd", basename + ".mdin"
]:
tar.add(name)
for r in range(replicas):
tar.add('mdin_{0}'.format(r))
tar.close()
#delete all input files outside the tarball
for r in range(replicas):
os.remove('mdin_{0}'.format(r))
self._prof.prof('EndTar', uid=self._uid)
#Create Untar Stage
repo = git.Repo('.', search_parent_directories=True)
aux_function_path = repo.working_tree_dir
untar_stg = Stage()
untar_stg.name = 'untarStg'
#Untar Task
untar_tsk = Task()
untar_tsk.name = 'untartsk'
untar_tsk.executable = ['python']
untar_tsk.upload_input_data = [
str(aux_function_path)+'/repex/untar_input_files.py', 'input_files.tar'
]
untar_tsk.arguments = ['untar_input_files.py', 'input_files.tar']
untar_tsk.cpu_reqs = 1
#untar_tsk.post_exec = ['']
untar_stg.add_tasks(untar_tsk)
p.add_stages(untar_stg)
tar_dict[0] = '$Pipeline_%s_Stage_%s_Task_%s' % (
p.name, untar_stg.name, untar_tsk.name)
# First MD stage: needs to be defined separately since workflow is not built from a predetermined order, also equilibration needs to happen first.
md_stg = Stage()
md_stg.name = 'mdstg0'
self._prof.prof('InitMD_0', uid=self._uid)
# MD tasks
for r in range(replicas):
md_tsk = AMBERTask(cores=replica_cores, md_executable=md_executable, pre_exec=pre_exec)
md_tsk.name = 'mdtsk-{replica}-{cycle}'.format(replica=r, cycle=0)
md_tsk.link_input_data += [
'%s/inpcrd' % tar_dict[0],
'%s/prmtop' % tar_dict[0],
'%s/mdin_{0}'.format(r) %
tar_dict[0] #Use for full temperature exchange
]
md_tsk.arguments = [
'-O',
'-p',
'prmtop',
'-i',
'mdin_{0}'.format(r),
'-c',
'inpcrd',
'-o',
'out-{replica}-{cycle}'.format(replica=r, cycle=0),
'-r',
'restrt'.format(replica=r, cycle=0),
#'-r', 'rstrt-{replica}-{cycle}'.format(replica=r,cycle=0),
'-x',
'mdcrd-{replica}-{cycle}'.format(replica=r, cycle=0),
#'-o', '$NODE_LFS_PATH/out-{replica}-{cycle}'.format(replica=r,cycle=0),
#'-r', '$NODE_LFS_PATH/rstrt-{replica}-{cycle}'.format(replica=r,cycle=0),
#'-x', '$NODE_LFS_PATH/mdcrd-{replica}-{cycle}'.format(replica=r,cycle=0),
'-inf',
'mdinfo_{0}'.format(r)
]
md_dict[r] = '$Pipeline_%s_Stage_%s_Task_%s' % (
p.name, md_stg.name, md_tsk.name)
md_stg.add_tasks(md_tsk)
self.md_task_list.append(md_tsk)
#print md_tsk.uid
p.add_stages(md_stg)
#stage_uids.append(md_stg.uid)
# First Exchange Stage
ex_stg = Stage()
ex_stg.name = 'exstg0'
self._prof.prof('InitEx_0', uid=self._uid)
# Create Exchange Task
ex_tsk = Task()
ex_tsk.name = 'extsk0'
#ex_tsk.pre_exec = ['module load python/2.7.10']
ex_tsk.executable = [python_path]
ex_tsk.upload_input_data = [exchange_method]
for r in range(replicas):
ex_tsk.link_input_data += ['%s/mdinfo_%s' % (md_dict[r], r)]
ex_tsk.pre_exec = ['mv *.py exchange_method.py']
ex_tsk.arguments = ['exchange_method.py', '{0}'.format(replicas), '0']
ex_tsk.cores = 1
ex_tsk.mpi = False
ex_tsk.download_output_data = ['exchangePairs_0.dat']
ex_stg.add_tasks(ex_tsk)
#task_uids.append(ex_tsk.uid)
p.add_stages(ex_stg)
self.ex_task_list.append(ex_tsk)
#self.ex_task_uids.append(ex_tsk.uid)
self.book.append(md_dict)
return p