Added a maximum job time argument to ARC

and passing it to the submit scripts

arc/job/job.py

@@ -7,7 +7,7 @@
 import csv
 import logging
 
-from arc.settings import arc_path, servers, submit_filename, delete_command,\
+from arc.settings import arc_path, servers, submit_filename, delete_command, t_max_format,\
     input_filename, output_filename, rotor_scan_resolution, list_available_nodes_command
 from arc.job.submit import submit_scripts
 from arc.job.inputs import input_files
@@ -66,6 +66,7 @@ class Job(object):
     `occ`              ``int``           The number of occupied orbitals (core + val) from a molpro CCSD sp calc
     `initial_trsh`     ``dict``          Troubleshooting methods to try by default. Keys are server names, values are trshs
     `project_directory` ``str``          The path to the project directory
+    `max_job_time`     ``int``           The maximal allowed job time on the server in hours
     ================ =================== ===============================================================================
 
     self.job_status:
@@ -76,7 +77,8 @@ class Job(object):
     def __init__(self, project, settings, species_name, xyz, job_type, level_of_theory, multiplicity, project_directory,
                  charge=0, conformer=-1, fine=False, shift='', software=None, is_ts=False, scan='', pivots=None,
                  memory=1500, comments='', trsh='', ess_trsh_methods=None, occ=None, initial_trsh=None, job_num=None,
-                 job_server_name=None, job_name=None, job_id=None, server=None, date_time=None, run_time=None):
+                 job_server_name=None, job_name=None, job_id=None, server=None, date_time=None, run_time=None,
+                 max_job_time=5):
         self.project = project
         self.settings=settings
         self.date_time = date_time if date_time is not None else datetime.datetime.now()
@@ -92,6 +94,7 @@ def __init__(self, project, settings, species_name, xyz, job_type, level_of_theo
         self.ess_trsh_methods = ess_trsh_methods if ess_trsh_methods is not None else list()
         self.trsh = trsh
         self.initial_trsh = initial_trsh if initial_trsh is not None else dict()
+        self.max_job_time = max_job_time
         job_types = ['conformer', 'opt', 'freq', 'optfreq', 'sp', 'composite', 'scan', 'gsm', 'irc', 'ts_guess']
         # the 'conformer' job type is identical to 'opt', but we differentiate them to be identifiable in Scheduler
         if job_type not in job_types:
@@ -315,7 +318,19 @@ def write_completed_job_to_csv_file(self):
 
     def write_submit_script(self):
         un = servers[self.server]['un']  # user name
-        self.submit = submit_scripts[self.software].format(name=self.job_server_name, un=un)
+        if self.max_job_time > 9999 or self.max_job_time == 0:
+            self.max_job_time = 9999
+        if t_max_format[servers[self.server]['cluster_soft']] == 'days':
+            # e.g., 5-0:00:00
+            d, h = divmod(self.max_job_time, 24)
+            t_max = '{0}-{0}:00:00'.format(d, h)
+        elif t_max_format[servers[self.server]['cluster_soft']] == 'hours':
+            # e.g., 120:00:00
+            t_max = '{0}:00:00'.format(self.max_job_time)
+        else:
+            raise JobError('Could not determine format for maximal job time')
+        self.submit = submit_scripts[servers[self.server]['cluster_soft']][self.software.lower()].format(
+            name=self.job_server_name, un=un, t_max=t_max)
         if not os.path.exists(self.local_path):
             os.makedirs(self.local_path)
         with open(os.path.join(self.local_path, submit_filename[servers[self.server]['cluster_soft']]), 'wb') as f:

arc/main.py

@@ -72,6 +72,7 @@ class ARC(object):
     `t_min`                ``tuple``  The minimum temperature for kinetics computations, e.g., (500, str('K'))
     `t_max`                ``tuple``  The maximum temperature for kinetics computations, e.g., (3000, str('K'))
     `t_count`              ``int``    The number of temperature points between t_min and t_max for kinetics computations
+    `max_job_time`         ``int``    The maximal allowed job time on the server in hours
     `rmgdb`                ``RMGDatabase``  The RMG database object
     ====================== ========== ==================================================================================
 
@@ -82,7 +83,7 @@ def __init__(self, input_dict=None, project=None, arc_species_list=None, arc_rxn
                  conformer_level='', composite_method='', opt_level='', freq_level='', sp_level='', scan_level='',
                  ts_guess_level='', fine=True, generate_conformers=True, scan_rotors=True, use_bac=True,
                  model_chemistry='', ess_settings=None, initial_trsh=None, t_min=None, t_max=None, t_count=None,
-                 verbose=logging.INFO, project_directory=None):
+                 verbose=logging.INFO, project_directory=None, max_job_time=5):
 
         self.__version__ = '1.0.0'
         self.verbose = verbose
@@ -93,6 +94,7 @@ def __init__(self, input_dict=None, project=None, arc_species_list=None, arc_rxn
         self.lib_long_desc = ''
         self.unique_species_labels = list()
         self.rmgdb = rmgdb.make_rmg_database_object()
+        self.max_job_time = max_job_time
 
         if input_dict is None:
             if project is None:
@@ -356,6 +358,7 @@ def as_dict(self):
         restart_dict['t_min'] = self.t_min
         restart_dict['t_max'] = self.t_max
         restart_dict['t_count'] = self.t_count
+        restart_dict['max_job_time'] = self.max_job_time
         return restart_dict
 
     def from_dict(self, input_dict, project=None, project_directory=None):
@@ -377,6 +380,7 @@ def from_dict(self, input_dict, project=None, project_directory=None):
         self.t0 = time.time()  # init time
         self.execution_time = None
         self.verbose = input_dict['verbose'] if 'verbose' in input_dict else self.verbose
+        self.max_job_time = input_dict['max_job_time'] if 'max_job_time' in input_dict else 5
 
         if self.ess_settings is not None:
             self.settings['ssh'] = True
@@ -554,7 +558,8 @@ def execute(self):
                                    scan_level=self.scan_level, ts_guess_level=self.ts_guess_level ,fine=self.fine,
                                    settings=self.settings, generate_conformers=self.generate_conformers,
                                    scan_rotors=self.scan_rotors, initial_trsh=self.initial_trsh, rmgdatabase=self.rmgdb,
-                                   restart_dict=self.restart_dict, project_directory=self.project_directory)
+                                   restart_dict=self.restart_dict, project_directory=self.project_directory,
+                                   max_job_time=self.max_job_time)
 
         self.save_project_info_file()
 

arc/scheduler.py

@@ -71,6 +71,7 @@ class Scheduler(object):
     `save_restart`          ``bool``  Whether to start saving a restart file. ``True`` only after all species are loaded
                                         (otherwise saves a partial file and may cause loss of information)
     `restart_path`          ``str``   Path to the `restart.yml` file to be saved
+    `max_job_time`          ``int``   The maximal allowed job time on the server in hours
     `testing`               ``bool``  Used for internal ARC testing (generating the object w/o executing it)
     `rmgdb`                 ``RMGDatabase``  The RMG database object
     ======================= ========= ==================================================================================
@@ -104,13 +105,14 @@ class Scheduler(object):
     """
     def __init__(self, project, settings, species_list, composite_method, conformer_level, opt_level, freq_level,
                  sp_level, scan_level, ts_guess_level, project_directory, rmgdatabase, fine=False, scan_rotors=True,
-                 generate_conformers=True, initial_trsh=None, rxn_list=None, restart_dict=None,
+                 generate_conformers=True, initial_trsh=None, rxn_list=None, restart_dict=None, max_job_time=5,
                  testing=False):
         self.rmgdb = rmgdatabase
         self.restart_dict = restart_dict
         self.species_list = species_list
         self.rxn_list = rxn_list if rxn_list is not None else list()
         self.project = project
+        self.max_job_time = max_job_time
         self.settings = settings
         self.project_directory = project_directory
         self.job_dict = dict()
@@ -468,7 +470,7 @@ def run_job(self, label, xyz, level_of_theory, job_type, fine=False, software=No
                   level_of_theory=level_of_theory, multiplicity=species.multiplicity, charge=species.charge, fine=fine,
                   shift=shift, software=software, is_ts=species.is_ts, memory=memory, trsh=trsh, conformer=conformer,
                   ess_trsh_methods=ess_trsh_methods, scan=scan, pivots=pivots, occ=occ, initial_trsh=self.initial_trsh,
-                  project_directory=self.project_directory)
+                  project_directory=self.project_directory, max_job_time=self.max_job_time)
         if conformer < 0:
             # this is NOT a conformer job
             self.running_jobs[label].append(job.job_name)  # mark as a running job