When the machine sending command to the server looses connectivity, ARC crashes wirh:
"""---------------------------------------------------------------------------
gaierror Traceback (most recent call last)
<ipython-input-5-f62c9e69185c> in <module>()
1 arc0 = arc.ARC(project='Arc-cooptima-methylpropylether-cbsqb3', composite_method='cbs-qb3', rmg_species_list=[], arc_species_list=arc_species_list,ess_settings = {'gaussian': 'c3ddb', 'molpro': 'pharos', 'qchem': 'pharos'})
----> 2 arc0.execute()
/home/dranasinghe/Software/ARC/arc/main.pyc in execute(self)
234 scan_level=self.scan_level, fine=self.fine, settings=self.settings,
235 generate_conformers=self.generate_conformers, scan_rotors=self.scan_rotors,
--> 236 initial_trsh=self.initial_trsh)
237 prc = Processor(project=self.project, species_dict=self.scheduler.species_dict, output=self.scheduler.output,
238 use_bac=self.use_bac, model_chemistry=self.model_chemistry)
/home/dranasinghe/Software/ARC/arc/scheduler.pyc in __init__(self, project, settings, species_list, composite_method, conformer_level, opt_level, freq_level, sp_level, scan_level, fine, generate_conformers, scan_rotors, initial_trsh)
151 self.species_dict[species.label].generate_conformers()
152 self.timer = True
--> 153 self.schedule_jobs()
154
155 def schedule_jobs(self):
/home/dranasinghe/Software/ARC/arc/scheduler.pyc in schedule_jobs(self)
261 and not self.job_dict[label]['scan'][job_name].job_id in self.servers_jobs_ids:
262 job = self.job_dict[label]['scan'][job_name]
--> 263 successful_server_termination = self.end_job(job=job, label=label, job_name=job_name)
264 if successful_server_termination:
265 self.check_scan_job(label=label, job=job)
/home/dranasinghe/Software/ARC/arc/scheduler.pyc in end_job(self, job, label, job_name)
325 fine=job.fine, software=job.software, shift=job.shift, trsh=job.trsh, memory=job.memory,
326 conformer=job.conformer, ess_trsh_methods=job.ess_trsh_methods, scan=job.scan,
--> 327 pivots=job.pivots, occ=job.occ)
328 self.running_jobs[label].pop(self.running_jobs[label].index(job_name))
329 self.timer = False
/home/dranasinghe/Software/ARC/arc/scheduler.pyc in run_job(self, label, xyz, level_of_theory, job_type, fine, software, shift, trsh, memory, conformer, ess_trsh_methods, scan, pivots, occ)
303 self.job_dict[label][job_type] = dict()
304 self.job_dict[label][job_type][job.job_name] = job
--> 305 self.job_dict[label][job_type][job.job_name].run()
306 else:
307 # Running a conformer job. Append differently to job_dict.
/home/dranasinghe/Software/ARC/arc/job/job.pyc in run(self)
508 logging.info('Running job {name} for {label}'.format(name=self.job_name, label=self.species_name))
509 logging.debug('writing submit script...')
--> 510 self.write_submit_script()
511 logging.debug('writing input file...')
512 self.write_input_file()
/home/dranasinghe/Software/ARC/arc/job/job.pyc in write_submit_script(self)
285 f.write(self.submit)
286 if self.settings['ssh']:
--> 287 self._upload_submit_file()
288
289 def write_input_file(self):
/home/dranasinghe/Software/ARC/arc/job/job.pyc in _upload_submit_file(self)
483 ssh.send_command_to_server(command='mkdir -p {0}'.format(self.remote_path))
484 remote_file_path = os.path.join(self.remote_path, submit_filename[servers[self.server]['cluster_soft']])
--> 485 ssh.upload_file(remote_file_path=remote_file_path, file_string=self.submit)
486
487 def _upload_input_file(self):
/home/dranasinghe/Software/ARC/arc/job/ssh.pyc in upload_file(self, remote_file_path, local_file_path, file_string)
64 raise InputError('Cannot upload a non-existing file.'
65 ' Check why file in path {0} is missing.'.format(local_file_path))
---> 66 sftp, ssh = self.connect()
67 with sftp.open(remote_file_path, "w") as f_remote:
68 if file_string:
/home/dranasinghe/Software/ARC/arc/job/ssh.pyc in connect(self)
168 ssh.set_missing_host_key_policy(paramiko.AutoAddPolicy())
169 ssh.load_system_host_keys(filename=self.key)
--> 170 ssh.connect(hostname=self.address, username=self.un)
171 sftp = ssh.open_sftp()
172 return sftp, ssh
/home/dranasinghe/anaconda2/envs/rmg_env/lib/python2.7/site-packages/paramiko/client.pyc in connect(self, hostname, port, username, password, pkey, key_filename, timeout, allow_agent, look_for_keys, compress, sock, gss_auth, gss_kex, gss_deleg_creds, gss_host, banner_timeout, auth_timeout, gss_trust_dns, passphrase)
332 errors = {}
333 # Try multiple possible address families (e.g. IPv4 vs IPv6)
--> 334 to_try = list(self._families_and_addresses(hostname, port))
335 for af, addr in to_try:
336 try:
/home/dranasinghe/anaconda2/envs/rmg_env/lib/python2.7/site-packages/paramiko/client.pyc in _families_and_addresses(self, hostname, port)
202 guess = True
203 addrinfos = socket.getaddrinfo(
--> 204 hostname, port, socket.AF_UNSPEC, socket.SOCK_STREAM
205 )
206 for (family, socktype, proto, canonname, sockaddr) in addrinfos:
gaierror: [Errno -2] Name or service not known
"""
or:
Traceback (most recent call last):
File "/home/alongd/Code/ARC//ARC.py", line 95, in <module>
main()
File "/home/alongd/Code/ARC//ARC.py", line 78, in main
arc_object.execute()
File "/home/alongd/Code/ARC/arc/main.py", line 413, in execute
project_directory=self.project_directory)
File "/home/alongd/Code/ARC/arc/scheduler.py", line 175, in __init__
self.schedule_jobs()
File "/home/alongd/Code/ARC/arc/scheduler.py", line 253, in schedule_jobs
successful_server_termination = self.end_job(job=job, label=label, job_name=job_name)
File "/home/alongd/Code/ARC/arc/scheduler.py", line 349, in end_job
pivots=job.pivots, occ=job.occ)
File "/home/alongd/Code/ARC/arc/scheduler.py", line 327, in run_job
self.job_dict[label][job_type][job.job_name].run()
File "/home/alongd/Code/ARC/arc/job/job.py", line 507, in run
self.write_submit_script()
File "/home/alongd/Code/ARC/arc/job/job.py", line 284, in write_submit_script
self._upload_submit_file()
File "/home/alongd/Code/ARC/arc/job/job.py", line 482, in _upload_submit_file
ssh.upload_file(remote_file_path=remote_file_path, file_string=self.submit)
File "/home/alongd/Code/ARC/arc/job/ssh.py", line 66, in upload_file
sftp, ssh = self.connect()
File "/home/alongd/Code/ARC/arc/job/ssh.py", line 180, in connect
ssh.connect(hostname=self.address, username=self.un)
File "/home/alongd/anaconda2/envs/rmg_env/lib/python2.7/site-packages/paramiko/client.py", line 334, in connect
to_try = list(self._families_and_addresses(hostname, port))
File "/home/alongd/anaconda2/envs/rmg_env/lib/python2.7/site-packages/paramiko/client.py", line 204, in _families_and_addresses
hostname, port, socket.AF_UNSPEC, socket.SOCK_STREAM
socket.gaierror: [Errno -2] Name or service not known
or:
---------------------------------------------------------------------------
gaierror Traceback (most recent call last)
<ipython-input-3-580c043d58f4> in <module>()
3 # fine=True, generate_conformers=True, scan_rotors=True, use_bac=True, model_chemistry
4 arc0 = arc.ARC(project='ArcDemo', rmg_species_list=rmg_species_list, arc_species_list=arc_species_list)
----> 5 arc0.execute()
/home/alongd/Code/ARC/arc/main.pyc in execute(self)
411 generate_conformers=self.generate_conformers, scan_rotors=self.scan_rotors,
412 initial_trsh=self.initial_trsh, restart_dict=self.restart_dict,
--> 413 project_directory=self.project_directory)
414 prc = Processor(project=self.project, species_dict=self.scheduler.species_dict, output=self.scheduler.output,
415 use_bac=self.use_bac, model_chemistry=self.model_chemistry)
/home/alongd/Code/ARC/arc/scheduler.pyc in __init__(self, project, settings, species_list, composite_method, conformer_level, opt_level, freq_level, sp_level, scan_level, project_directory, fine, generate_conformers, scan_rotors, initial_trsh, restart_dict)
173 self.species_dict[species.label].generate_conformers()
174 self.timer = True
--> 175 self.schedule_jobs()
176
177 def schedule_jobs(self):
/home/alongd/Code/ARC/arc/scheduler.pyc in schedule_jobs(self)
180 """
181 if self.generate_conformers:
--> 182 self.run_conformer_jobs()
183 while self.running_jobs != {}: # loop while jobs are still running
184 logging.debug('Currently running jobs:\n{0}'.format(self.running_jobs))
/home/alongd/Code/ARC/arc/scheduler.pyc in run_conformer_jobs(self)
370 for i, xyz in enumerate(self.species_dict[label].conformers):
371 self.run_job(label=label, xyz=xyz, level_of_theory=self.conformer_level, job_type='conformer',
--> 372 conformer=i)
373 else:
374 if 'opt' not in self.job_dict[label] and 'composite' not in self.job_dict[label]\
/home/alongd/Code/ARC/arc/scheduler.pyc in run_job(self, label, xyz, level_of_theory, job_type, fine, software, shift, trsh, memory, conformer, ess_trsh_methods, scan, pivots, occ)
330 self.running_jobs[label].append('conformer{0}'.format(conformer)) # mark as a running job
331 self.job_dict[label]['conformers'][conformer] = job # save job object
--> 332 self.job_dict[label]['conformers'][conformer].run() # run the job
333 if job.server not in self.servers:
334 self.servers.append(job.server)
/home/alongd/Code/ARC/arc/job/job.pyc in run(self)
507 self.write_submit_script()
508 logging.debug('writing input file...')
--> 509 self.write_input_file()
510 if self.settings['ssh']:
511 ssh = SSH_Client(self.server)
/home/alongd/Code/ARC/arc/job/job.pyc in write_input_file(self)
474 f.write(self.input)
475 if self.settings['ssh']:
--> 476 self._upload_input_file()
477
478 def _upload_submit_file(self):
/home/alongd/Code/ARC/arc/job/job.pyc in _upload_input_file(self)
486 ssh.send_command_to_server(command='mkdir -p {0}'.format(self.remote_path))
487 remote_file_path = os.path.join(self.remote_path, input_filename[self.software])
--> 488 ssh.upload_file(remote_file_path=remote_file_path, file_string=self.input)
489
490 def _download_output_file(self):
/home/alongd/Code/ARC/arc/job/ssh.pyc in upload_file(self, remote_file_path, local_file_path, file_string)
64 raise InputError('Cannot upload a non-existing file.'
65 ' Check why file in path {0} is missing.'.format(local_file_path))
---> 66 sftp, ssh = self.connect()
67 with sftp.open(remote_file_path, "w") as f_remote:
68 if file_string:
/home/alongd/Code/ARC/arc/job/ssh.pyc in connect(self)
178 # This sometimes gives "SSHException: Error reading SSH protocol banner[Error 104] Connection reset by peer"
179 # Try again:
--> 180 ssh.connect(hostname=self.address, username=self.un)
181 sftp = ssh.open_sftp()
182 return sftp, ssh
/home/alongd/anaconda2/envs/rmg_env/lib/python2.7/site-packages/paramiko/client.pyc in connect(self, hostname, port, username, password, pkey, key_filename, timeout, allow_agent, look_for_keys, compress, sock, gss_auth, gss_kex, gss_deleg_creds, gss_host, banner_timeout, auth_timeout, gss_trust_dns, passphrase)
332 errors = {}
333 # Try multiple possible address families (e.g. IPv4 vs IPv6)
--> 334 to_try = list(self._families_and_addresses(hostname, port))
335 for af, addr in to_try:
336 try:
/home/alongd/anaconda2/envs/rmg_env/lib/python2.7/site-packages/paramiko/client.pyc in _families_and_addresses(self, hostname, port)
202 guess = True
203 addrinfos = socket.getaddrinfo(
--> 204 hostname, port, socket.AF_UNSPEC, socket.SOCK_STREAM
205 )
206 for (family, socktype, proto, canonname, sockaddr) in addrinfos:
gaierror: [Errno -3] Temporary failure in name resolution
alongd
commented
5 years ago
When the machine sending command to the server looses connectivity, ARC crashes wirh:
or:
or: