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_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 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_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
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 specfem_clean_up(cmt_file_db, param_path, task_counter):
""" Cleaning up the simulation directories since we don"t need all the
files for the future.
: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 parameters
databaseparam_path = os.path.join(param_path,
"Database/DatabaseParameters.yml")
# Database 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)
# Path to function
clean_up_func = os.path.join(bin_path, "clean_up_simdirs.py")
# Create a Stage object
clean_up = Stage()
clean_up.name = "Clean-Up"
# Create Task for stage
clean_up_t = Task()
clean_up_t.name = "Task-Clean-Up"
clean_up_t.pre_exec = [ # Conda activate
DB_params["conda-activate"]
]
clean_up_t.executable = DB_params["bin-python"] # Assign executable
# to the task
clean_up_t.arguments = [clean_up_func, cmt_file_db]
# In the future maybe to database dir as a total log?
clean_up_t.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), clean_up_t.name))
clean_up_t.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), clean_up_t.name))
# Add Task to the Stage
clean_up.add_tasks(clean_up_t)
return clean_up, task_counter
def data_request(cmt_file_db, param_path, task_counter):
""" This function creates the request for the observed data and returns
it as an EnTK Stage
:param cmt_file_db: cmt_file 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
request_data_func = os.path.join(bin_path, "request_data.py")
# Create a Stage object
datarequest = Stage()
datarequest_t = Task()
datarequest_t.name = "data-request"
datarequest_t.pre_exec = [ # Conda activate
DB_params["conda-activate"]
]
datarequest_t.executable = DB_params["bin-python"] # Assign executable
# to the task
datarequest_t.arguments = [request_data_func, cmt_file_db]
# In the future maybe to database dir as a total log?
datarequest_t.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), datarequest_t.name))
datarequest_t.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), datarequest_t.name))
# Add Task to the Stage
datarequest.add_tasks(datarequest_t)
# Increase task-counter
task_counter += 1
return datarequest, task_counter
def create_entry(cmt_filename, param_path, task_counter):
"""This function creates the Entk stage for creation of a database entry.
:param cmt_filename: cmt_filename
:param param_path: parameter directory
:param pipelinedir: Directory of the 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_filename)
# Create a Stage object
database_entry = Stage()
t1 = Task()
t1.name = "database-entry"
t1.pre_exec = PRE_EXECS
t1.executable = 'create-entry' # Assign
# executable to the task
t1.arguments = ['-f %s' % cmt_filename, '-p %s' % param_path]
# In the future maybe to database dir as a total log?
t1.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), t1.name))
t1.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), t1.name))
# Increase task-counter
task_counter += 1
# Add Task to the Stage
database_entry.add_tasks(t1)
return database_entry, task_counter
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 = ['cat']
t1.arguments = ['file1.txt','file2.txt']
t1.stdout = 'output.txt'
t1.copy_input_data = ['$SHARED/file1.txt', '$SHARED/file2.txt']
t1.download_output_data = ['output.txt > %s/output.txt' %cur_dir]
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def generate_pipeline():
# Create a Pipeline object
p = Pipeline()
# Create a Stage object
s1 = Stage()
# Create a Task object which creates a file named 'output.txt' of size 1 MB
t1 = Task()
t1.executable = 'cat'
t1.arguments = ['file1.txt', 'file2.txt']
t1.stdout = 'output.txt'
t1.copy_input_data = ['$SHARED/file1.txt', '$SHARED/file2.txt']
t1.download_output_data = ['output.txt > %s/output.txt' % cur_dir]
# Add the Task to the Stage
s1.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(s1)
return p
def create_processing_stage(cmt_file_db, param_path, task_counter):
"""This function creates the ASDF processing stage.
: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)
# Processing param dir
process_obs_param_dir = os.path.join(param_path, "ProcessObserved")
process_syn_param_dir = os.path.join(param_path, "ProcessSynthetic")
# Process path list
# Important step! This creates a processing list prior to having created
# the actual process path files. It is tested so it definitely works!
# this way the processes can be distributed for each ASDF file on one
# processor or more (MPI enabled!)
processing_list, _, _ = get_processing_list(cmt_file_db,
process_obs_param_dir,
process_syn_param_dir,
verbose=True)
# The following little work around help getting around the fact that
# multiple tasks cannot read the same file.
# Get all available bands
bands = []
for file in processing_list:
bands.append(os.path.basename(file).split(".")[-2])
bands = list(set(bands))
# List of stages
stages = []
for band in bands:
# Processing sublist
sub_list = [x for x in processing_list if band in x]
# Process path function
process_func = os.path.join(bin_path, "process_asdf.py")
# Create Process Paths Stage (CPP)
# Create a Stage object
process_stage = Stage()
process_stage.name = "Processing"
# Number of Processes:
N = len(processing_list)
# Loop over process path files
for process_path in sub_list:
# Create Task
processing_task = Task()
# This way the task gets the name of the path file
processing_task.name = "Processing-" \
+ os.path.basename(process_path)
processing_task.pre_exec = [ # Conda activate
DB_params["conda-activate"]
]
processing_task.executable = DB_params[
"bin-python"] # Assign exec.
# to the task
# Create Argument list
arguments = [process_func, "-f", process_path]
if DB_params["verbose"]:
arguments.append("-v")
processing_task.arguments = arguments
# In the future maybe to database dir as a total log?
processing_task.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), processing_task.name))
processing_task.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), processing_task.name))
processing_task.cpu_reqs = {
"processes": 1,
"process_type": "MPI",
"threads_per_process": 1,
"thread_type": "OpenMP"
}
task_counter += 1
process_stage.add_tasks(processing_task)
stages.append(process_stage)
return stages, task_counter
def test_task_exceptions(s, l, i, b):
"""
**Purpose**: Test if all attribute assignments raise exceptions for invalid values
"""
t = Task()
data_type = [s, l, i, b]
for data in data_type:
if not isinstance(data, str):
with pytest.raises(TypeError):
t.name = data
with pytest.raises(TypeError):
t.path = data
with pytest.raises(TypeError):
t.parent_stage = data
with pytest.raises(TypeError):
t.parent_pipeline = data
with pytest.raises(TypeError):
t.stdout = data
with pytest.raises(TypeError):
t.stderr = data
if not isinstance(data, list):
with pytest.raises(TypeError):
t.pre_exec = data
with pytest.raises(TypeError):
t.executable = data
with pytest.raises(TypeError):
t.arguments = data
with pytest.raises(TypeError):
t.post_exec = data
with pytest.raises(TypeError):
t.upload_input_data = data
with pytest.raises(TypeError):
t.copy_input_data = data
with pytest.raises(TypeError):
t.link_input_data = data
with pytest.raises(TypeError):
t.move_input_data = data
with pytest.raises(TypeError):
t.copy_output_data = data
with pytest.raises(TypeError):
t.download_output_data = data
with pytest.raises(TypeError):
t.move_output_data = data
if not isinstance(data, str) and not isinstance(data, unicode):
with pytest.raises(ValueError):
t.cpu_reqs = {
'processes': 1,
'process_type': data,
'threads_per_process': 1,
'thread_type': None
}
t.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': data
}
t.gpu_reqs = {
'processes': 1,
'process_type': data,
'threads_per_process': 1,
'thread_type': None
}
t.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': data
}
if not isinstance(data, int):
with pytest.raises(TypeError):
t.cpu_reqs = {
'processes': data,
'process_type': None,
'threads_per_process': 1,
'thread_type': None
}
t.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': data,
'thread_type': None
}
t.gpu_reqs = {
'processes': data,
'process_type': None,
'threads_per_process': 1,
'thread_type': None
}
t.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': data,
'thread_type': None
}
def test_task_to_dict():
"""
**Purpose**: Test if the 'to_dict' function of Task class converts all expected attributes of the Task into a
dictionary
"""
t = Task()
d = t.to_dict()
assert d == {
'uid': None,
'name': None,
'state': states.INITIAL,
'state_history': [states.INITIAL],
'pre_exec': [],
'executable': [],
'arguments': [],
'post_exec': [],
'cpu_reqs': {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': None
},
'gpu_reqs': {
'processes': 0,
'process_type': None,
'threads_per_process': 0,
'thread_type': None
},
'lfs_per_process': 0,
'upload_input_data': [],
'copy_input_data': [],
'link_input_data': [],
'move_input_data': [],
'copy_output_data': [],
'move_output_data': [],
'download_output_data': [],
'stdout': None,
'stderr': None,
'exit_code': None,
'path': None,
'tag': None,
'parent_stage': {
'uid': None,
'name': None
},
'parent_pipeline': {
'uid': None,
'name': None
}
}
t = Task()
t.uid = 'test.0000'
t.name = 'new'
t.pre_exec = ['module load abc']
t.executable = ['sleep']
t.arguments = ['10']
t.cpu_reqs['processes'] = 10
t.cpu_reqs['threads_per_process'] = 2
t.gpu_reqs['processes'] = 5
t.gpu_reqs['threads_per_process'] = 3
t.lfs_per_process = 1024
t.upload_input_data = ['test1']
t.copy_input_data = ['test2']
t.link_input_data = ['test3']
t.move_input_data = ['test4']
t.copy_output_data = ['test5']
t.move_output_data = ['test6']
t.download_output_data = ['test7']
t.stdout = 'out'
t.stderr = 'err'
t.exit_code = 1
t.path = 'a/b/c'
t.tag = 'task.0010'
t.parent_stage = {'uid': 's1', 'name': 'stage1'}
t.parent_pipeline = {'uid': 'p1', 'name': 'pipeline1'}
d = t.to_dict()
assert d == {
'uid': 'test.0000',
'name': 'new',
'state': states.INITIAL,
'state_history': [states.INITIAL],
'pre_exec': ['module load abc'],
'executable': ['sleep'],
'arguments': ['10'],
'post_exec': [],
'cpu_reqs': {
'processes': 10,
'process_type': None,
'threads_per_process': 2,
'thread_type': None
},
'gpu_reqs': {
'processes': 5,
'process_type': None,
'threads_per_process': 3,
'thread_type': None
},
'lfs_per_process': 1024,
'upload_input_data': ['test1'],
'copy_input_data': ['test2'],
'link_input_data': ['test3'],
'move_input_data': ['test4'],
'copy_output_data': ['test5'],
'move_output_data': ['test6'],
'download_output_data': ['test7'],
'stdout': 'out',
'stderr': 'err',
'exit_code': 1,
'path': 'a/b/c',
'tag': 'task.0010',
'parent_stage': {
'uid': 's1',
'name': 'stage1'
},
'parent_pipeline': {
'uid': 'p1',
'name': 'pipeline1'
}
}
def main(cmt_filename):
'''This tiny function runs shit
Args:
cmt_filename: str containing the path to the cmt solution that is
supposed to be inverted for
Usage:
From the commandline:
python pipeline <path/to/cmtsolution>
'''
# Path to pipeline file
pipelinepath = os.path.abspath(__file__)
pipelinedir = os.path.dirname(pipelinepath)
# Define parameter directory
param_path = os.path.join(os.path.dirname(pipelinedir), "params")
databaseparam_path = os.path.join(param_path,
"Database/DatabaseParameters.yml")
DB_params = read_yaml_file(databaseparam_path)
print(DB_params)
# Earthquake specific database parameters
# Dir and eq_id
eq_dir, eq_id = get_eq_entry_path(DB_params["databasedir"], cmt_filename)
# Earthquake file in the database
cmt_file_db = os.path.join(eq_dir, "eq_" + eq_id + ".cmt")
# Create a Pipeline object
p = Pipeline()
# ---- DATABASE ENTRY TASK ---------------------------------------------- #
# Path to function
create_database_func = os.path.join(pipelinedir,
"01_Create_Database_Entry.py")
# Create a Stage object
database_entry = Stage()
t1 = Task()
t1.name = 'database-entry'
t1.pre_exec = [ # Conda activate
DB_params["conda-activate"]
]
t1.executable = [DB_params['bin-python']] # Assign executable to the task
t1.arguments = [create_database_func, os.path.abspath(cmt_filename)]
# In the future maybe to database dir as a total log?
t1.stdout = os.path.join(pipelinedir,
"database-entry." + eq_id + ".stdout")
t1.stderr = os.path.join(pipelinedir,
"database-entry." + eq_id + ".stderr")
# Add Task to the Stage
database_entry.add_tasks(t1)
# Add Stage to the Pipeline
p.add_stages(database_entry)
# # ---- REQUEST DATA ----------------------------------------------------- #
#
# # Path to function
# request_data_func = os.path.join(pipelinedir, "02_Request_Data.py")
#
# # Create a Stage object
# datarequest = Stage()
#
# datarequest_t = Task()
# datarequest_t.name = 'data-request'
# datarequest_t.pre_exec = [ # Conda activate
# DB_params["conda-activate"]]
# datarequest_t.executable = [DB_params['bin-python']] # Assign executable
# # to the task
# datarequest_t.arguments = [request_data_func, cmt_file_db]
#
# # In the future maybe to database dir as a total log?
# datarequest_t.stdout = os.path.join(pipelinedir,
# "datarequest." + eq_id + ".stdout")
# datarequest_t.stderr = os.path.join(pipelinedir,
# "datarequest." + eq_id + ".stderr")
#
# # Add Task to the Stage
# datarequest.add_tasks(datarequest_t)
#
# # Add Stage to the Pipeline
# p.add_stages(datarequest)
# ---- Write Sources ---------------------------------------------------- #
# Path to function
write_source_func = os.path.join(pipelinedir, "03_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 = 'Write-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(pipelinedir,
"write_sources." + eq_id + ".stdout")
w_sources_t.stderr = os.path.join(pipelinedir,
"write_sources." + eq_id + ".stderr")
# Add Task to the Stage
w_sources.add_tasks(w_sources_t)
# Add Stage to the Pipeline
p.add_stages(w_sources)
# ---- Run Specfem ----------------------------------------------------- #
specfemspec_path = os.path.join(param_path,
"SpecfemParams/SpecfemParams.yml")
comp_and_modules_path = os.path.join(
param_path, "SpecfemParams/"
"CompilersAndModules.yml")
# Load Parameters
specfemspecs = read_yaml_file(specfemspec_path)
cm_dict = read_yaml_file(comp_and_modules_path)
attr = [
"CMT", "CMT_rr", "CMT_tt", "CMT_pp", "CMT_rt", "CMT_rp", "CMT_tp",
"CMT_depth", "CMT_lat", "CMT_lon"
]
simdir = os.path.join(eq_dir, "CMT_SIMs")
# Create a Stage object
runSF3d = Stage()
runSF3d.name = 'Simulation'
for at in attr[0]:
sf_t = Task()
sf_t.name = 'run-' + at
# Module Loading
sf_t.pre_exec = [ # Get rid of existing modules
'module purge'
]
for module in cm_dict["modulelist"]:
sf_t.pre_exec.append("module load %s" % module)
sf_t.pre_exec.append("module load %s" % cm_dict["gpu_module"])
# Change directory to specfem directories
sf_t.pre_exec.append( # Change directory
"cd %s" % os.path.join(simdir, at))
sf_t.executable = ['./bin/xspecfem3D'] # Assign executable
# In the future maybe to database dir as a total log?
sf_t.stdout = os.path.join(pipelinedir,
"run_specfem." + eq_id + ".stdout")
sf_t.stderr = os.path.join(pipelinedir,
"run_specfem." + eq_id + ".stderr")
sf_t.gpu_reqs = {
'processes': 6,
'process_type': 'MPI',
'threads_per_process': 1,
'thread_type': 'OpenMP'
}
# Add Task to the Stage
runSF3d.add_tasks(sf_t)
# Add Simulation stage to the Pipeline
p.add_stages(runSF3d)
# 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': 'princeton.tiger_gpu',
'project': 'geo',
'queue': 'gpu',
'schema': 'local',
'walltime': 300,
'cpus': 2,
'gpus': 6
}
# Assign resource request description to the Application Manager
appman.resource_desc = res_dict
# Assign the workflow as a set or list of Pipelines to the Application Manager
# Note: The list order is not guaranteed to be preserved
appman.workflow = set([p])
# Run the Application Manager
appman.run()
def test_task_exceptions(s,l,i,b):
"""
**Purpose**: Test if all attribute assignments raise exceptions for invalid values
"""
t = Task()
data_type = [s,l,i,b]
for data in data_type:
if not isinstance(data,str):
with pytest.raises(TypeError):
t.name = data
with pytest.raises(TypeError):
t.path = data
with pytest.raises(TypeError):
t.parent_stage = data
with pytest.raises(TypeError):
t.parent_pipeline = data
with pytest.raises(TypeError):
t.stdout = data
with pytest.raises(TypeError):
t.stderr = data
if not isinstance(data,list):
with pytest.raises(TypeError):
t.pre_exec = data
with pytest.raises(TypeError):
t.arguments = data
with pytest.raises(TypeError):
t.post_exec = data
with pytest.raises(TypeError):
t.upload_input_data = data
with pytest.raises(TypeError):
t.copy_input_data = data
with pytest.raises(TypeError):
t.link_input_data = data
with pytest.raises(TypeError):
t.move_input_data = data
with pytest.raises(TypeError):
t.copy_output_data = data
with pytest.raises(TypeError):
t.download_output_data = data
with pytest.raises(TypeError):
t.move_output_data = data
if not isinstance(data, str) and not isinstance(data, list):
with pytest.raises(TypeError):
t.executable = data
if not isinstance(data, str) and not isinstance(data, unicode):
with pytest.raises(ValueError):
t.cpu_reqs = {
'processes': 1,
'process_type': data,
'threads_per_process': 1,
'thread_type': None
}
t.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': data
}
t.gpu_reqs = {
'processes': 1,
'process_type': data,
'threads_per_process': 1,
'thread_type': None
}
t.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': data
}
if not isinstance(data, int):
with pytest.raises(TypeError):
t.cpu_reqs = {
'processes': data,
'process_type': None,
'threads_per_process': 1,
'thread_type': None
}
t.cpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': data,
'thread_type': None
}
t.gpu_reqs = {
'processes': data,
'process_type': None,
'threads_per_process': 1,
'thread_type': None
}
t.gpu_reqs = {
'processes': 1,
'process_type': None,
'threads_per_process': data,
'thread_type': None
}
def run_specfem(cmt_file_db, param_path, task_counter):
""" This function runs the necessary Specfem simulations.
: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")
# Database 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)
specfemspec_path = os.path.join(param_path,
"SpecfemParams/SpecfemParams.yml")
comp_and_modules_path = os.path.join(
param_path, "SpecfemParams/"
"CompilersAndModules.yml")
# Load Parameters
specfemspecs = read_yaml_file(specfemspec_path)
cm_dict = read_yaml_file(comp_and_modules_path)
# Simulations to be run
attr = [
"CMT", "CMT_rr", "CMT_tt", "CMT_pp", "CMT_rt", "CMT_rp", "CMT_tp",
"CMT_depth", "CMT_lat", "CMT_lon"
]
# Simulation directory
simdir = os.path.join(os.path.dirname(cmt_file_db), "CMT_SIMs")
# Create a Stage object
runSF3d = Stage()
runSF3d.name = "Simulation"
for at in attr:
sf_t = Task()
sf_t.name = "run-" + at
# Module Loading
sf_t.pre_exec = [ # Get rid of existing modules
"module purge"
]
# Append to pre_execution module list.
for module in cm_dict["modulelist"]:
sf_t.pre_exec.append("module load %s" % module)
if specfemspecs["GPU_MODE"] is True:
sf_t.pre_exec.append("module load %s" % cm_dict["gpu_module"])
# Change directory to specfem directories
sf_t.pre_exec.append( # Change directory
"cd %s" % os.path.join(simdir, at))
sf_t.executable = "./bin/xspecfem3D" # Assigned executable
# In the future maybe to database dir as a total log?
sf_t.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), sf_t.name))
sf_t.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), sf_t.name))
print(sf_t.cpu_reqs)
# Increase Task counter
task_counter += 1
# Add Task to the Stage
runSF3d.add_tasks(sf_t)
return runSF3d, task_counter
def create_windowing_stage(cmt_file_db, param_path, task_counter):
"""This function creates the ASDF windowing stage.
: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)
# Windowing parameter file directory
window_process_dir = os.path.join(param_path, "CreateWindows")
# Window path list
# Important step! This creates a windowing list prior to having created
# the actual window path files. It is tested so it definitely works!
# This way the windowing processes can be distributed for each ASDF file
# pair on one processor (No MPI support!)
window_path_list, _ = get_windowing_list(cmt_file_db,
window_process_dir,
verbose=False)
# Process path function
window_func = os.path.join(bin_path, "window_selection_asdf.py")
# The following little work around help getting around the fact that
# multiple tasks cannot read the same file.
# Create two stages one for #bodywaves or general entries and one for
# surfaces waves.
bodywave_list = []
surfacewave_list = []
for file in window_path_list:
name = os.path.basename(file)
if "surface" in name:
surfacewave_list.append(file)
else:
bodywave_list.append(file)
stage_list = []
if len(bodywave_list) > 0:
stage_list.append(bodywave_list)
if len(surfacewave_list) > 0:
stage_list.append(surfacewave_list)
# List of stages
stages = []
for window_list in stage_list:
# Create Process Paths Stage (CPP)
# Create a Stage object
window_stage = Stage()
window_stage.name = "Windowing"
# Loop over process path files
for window_path in window_list:
# Create Task
window_task = Task()
# This way the task gets the name of the path file
window_task.name = os.path.basename(window_path)
window_task.pre_exec = [ # Conda activate
DB_params["conda-activate"]
]
window_task.executable = [DB_params["bin-python"]] # Assign exec
# to the task
# Create Argument list
arguments = [window_func, "-f", window_path]
if DB_params["verbose"]:
arguments.append("-v")
window_task.arguments = arguments
# In the future maybe to database dir as a total log?
window_task.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), window_task.name))
window_task.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), window_task.name))
window_stage.add_tasks(window_task)
task_counter += 1
stages.append(window_stage)
return stages, task_counter
def convert_traces(cmt_file_db, param_path, task_counter):
"""This function creates the to-ASDF conversion stage. Meaning, in this
stage, both synthetic and observed traces are converted to ASDF files.
: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
"""
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)
# File and directory
cmt_dir = os.path.dirname(cmt_file_db)
sim_dir = os.path.join(cmt_dir, "CMT_SIMs")
## Create a Stage object
conversion_stage = Stage()
conversion_stage.name = "Convert"
# Conversion binary
conversion_bin = os.path.join(bin_path, "convert_to_asdf.py")
attr = [
"CMT", "CMT_rr", "CMT_tt", "CMT_pp", "CMT_rt", "CMT_rp", "CMT_tp",
"CMT_depth", "CMT_lat", "CMT_lon"
]
##### Converting the synthetic data
if DB_params["verbose"]:
print("\nConverting synthetic traces to ASDF ... \n")
for _i, at in enumerate(attr[:DB_params["npar"] + 1]):
# Path file
syn_path_file = os.path.join(sim_dir, at, at + ".yml")
# Create Task for stage
c_task = Task()
c_task.name = at
c_task.pre_exec = [DB_params["conda-activate"]]
c_task.executable = DB_params["bin-python"] # Assign executable
# to the task
arguments = [conversion_bin, "-f", syn_path_file]
if DB_params["verbose"]:
arguments.append("-v")
c_task.arguments = arguments
# In the future maybe to database dir as a total log?
c_task.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), c_task.name))
c_task.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), c_task.name))
# Increase Task counter
task_counter += 1
conversion_stage.add_tasks(c_task)
##### Converting the observed data
if DB_params["verbose"]:
print("\nConverting observed traces to ASDF ... \n")
obs_path_file = os.path.join(cmt_dir, "seismograms", "obs", "observed.yml")
# Create Task for stage
c_task = Task()
c_task.name = "Observed"
c_task.pre_exec = [DB_params["conda-activate"]]
c_task.executable = DB_params["bin-python"] # Assign executable
# to the task
# Create Argument list
arguments = [conversion_bin, "-f", obs_path_file]
if DB_params["verbose"]:
arguments.append("-v")
c_task.arguments = arguments
# In the future maybe to database dir as a total log?
c_task.stdout = os.path.join(
"%s" % Cdir, "logs", "stdout.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), c_task.name))
c_task.stderr = os.path.join(
"%s" % Cdir, "logs", "stderr.pipeline_%s.task_%s.%s" %
(Cid, str(task_counter).zfill(4), c_task.name))
# Increase Task counter
task_counter += 1
conversion_stage.add_tasks(c_task)
return conversion_stage, task_counter
def test_task_to_dict():
"""
**Purpose**: Test if the 'to_dict' function of Task class converts all expected attributes of the Task into a
dictionary
"""
t = Task()
d = t.to_dict()
assert d == { 'uid': None,
'name': None,
'state': states.INITIAL,
'state_history': [states.INITIAL],
'pre_exec': [],
'executable': str(),
'arguments': [],
'post_exec': [],
'cpu_reqs': { 'processes': 1,
'process_type': None,
'threads_per_process': 1,
'thread_type': None
},
'gpu_reqs': { 'processes': 0,
'process_type': None,
'threads_per_process': 0,
'thread_type': None
},
'lfs_per_process': 0,
'upload_input_data': [],
'copy_input_data': [],
'link_input_data': [],
'move_input_data': [],
'copy_output_data': [],
'move_output_data': [],
'download_output_data': [],
'stdout': None,
'stderr': None,
'exit_code': None,
'path': None,
'tag': None,
'parent_stage': {'uid':None, 'name': None},
'parent_pipeline': {'uid':None, 'name': None}}
t = Task()
t.uid = 'test.0000'
t.name = 'new'
t.pre_exec = ['module load abc']
t.executable = ['sleep']
t.arguments = ['10']
t.cpu_reqs['processes'] = 10
t.cpu_reqs['threads_per_process'] = 2
t.gpu_reqs['processes'] = 5
t.gpu_reqs['threads_per_process'] = 3
t.lfs_per_process = 1024
t.upload_input_data = ['test1']
t.copy_input_data = ['test2']
t.link_input_data = ['test3']
t.move_input_data = ['test4']
t.copy_output_data = ['test5']
t.move_output_data = ['test6']
t.download_output_data = ['test7']
t.stdout = 'out'
t.stderr = 'err'
t.exit_code = 1
t.path = 'a/b/c'
t.tag = 'task.0010'
t.parent_stage = {'uid': 's1', 'name': 'stage1'}
t.parent_pipeline = {'uid': 'p1', 'name': 'pipeline1'}
d = t.to_dict()
assert d == { 'uid': 'test.0000',
'name': 'new',
'state': states.INITIAL,
'state_history': [states.INITIAL],
'pre_exec': ['module load abc'],
'executable': 'sleep',
'arguments': ['10'],
'post_exec': [],
'cpu_reqs': { 'processes': 10,
'process_type': None,
'threads_per_process': 2,
'thread_type': None
},
'gpu_reqs': { 'processes': 5,
'process_type': None,
'threads_per_process': 3,
'thread_type': None
},
'lfs_per_process': 1024,
'upload_input_data': ['test1'],
'copy_input_data': ['test2'],
'link_input_data': ['test3'],
'move_input_data': ['test4'],
'copy_output_data': ['test5'],
'move_output_data': ['test6'],
'download_output_data': ['test7'],
'stdout': 'out',
'stderr': 'err',
'exit_code': 1,
'path': 'a/b/c',
'tag': 'task.0010',
'parent_stage': {'uid': 's1', 'name': 'stage1'},
'parent_pipeline': {'uid': 'p1', 'name': 'pipeline1'}}
t.executable = 'sleep'
d = t.to_dict()
assert d == { 'uid': 'test.0000',
'name': 'new',
'state': states.INITIAL,
'state_history': [states.INITIAL],
'pre_exec': ['module load abc'],
'executable': 'sleep',
'arguments': ['10'],
'post_exec': [],
'cpu_reqs': { 'processes': 10,
'process_type': None,
'threads_per_process': 2,
'thread_type': None
},
'gpu_reqs': { 'processes': 5,
'process_type': None,
'threads_per_process': 3,
'thread_type': None
},
'lfs_per_process': 1024,
'upload_input_data': ['test1'],
'copy_input_data': ['test2'],
'link_input_data': ['test3'],
'move_input_data': ['test4'],
'copy_output_data': ['test5'],
'move_output_data': ['test6'],
'download_output_data': ['test7'],
'stdout': 'out',
'stderr': 'err',
'exit_code': 1,
'path': 'a/b/c',
'tag': 'task.0010',
'parent_stage': {'uid': 's1', 'name': 'stage1'},
'parent_pipeline': {'uid': 'p1', 'name': 'pipeline1'}}
