Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Initiated jobs #431

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
+12 −11
Open

Initiated jobs #431

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
986312e
bug fix: change from 'local' to dictionary server name
dranasinghe Oct 10, 2020
5dc5a71
moved job .cvs files form ARC to .arc folder.
dranasinghe Oct 10, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions arc/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@
logger = logging.getLogger('arc')

arc_path = os.path.abspath(os.path.dirname(os.path.dirname(__file__))) # absolute path to the ARC folder
local_arc_path = os.path.join(os.getenv("HOME"), '.arc')
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We have this in https://github.com/ReactionMechanismGenerator/ARC/blob/master/arc/imports.py#L14
No need to have it here


VERSION = '1.1.0'

Expand Down
10 changes: 5 additions & 5 deletions arc/job/job.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
from pprint import pformat
from typing import Dict, Optional, Union

from arc.common import arc_path, get_logger
from arc.common import arc_path, get_logger, local_arc_path
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

import local_arc_path from arc.imports

from arc.exceptions import JobError, InputError
from arc.imports import settings, input_files, submit_scripts
from arc.job.local import (get_last_modified_time,
Expand Down Expand Up @@ -424,7 +424,7 @@ def _set_job_number(self):
"""
Used as the entry number in the database, as well as the job name on the server.
"""
csv_path = os.path.join(arc_path, 'initiated_jobs.csv')
csv_path = os.path.join(local_arc_path, 'initiated_jobs.csv')
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this means we'll always have a .arc folder locally. So by default, If I run from two machines on the same server, I'll get different job counters. I think this isn't the desired behaviour. Instead, I think we should only use the local arch path for the CSV files if the respective file (not folder) exists.

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

. arc is per user. If I am not mistaken if I run from two different machines I get two different job counts. I was thinking about how it working on the delta. there are multiple users using the same ARC repo. Therefore the counter is for everyone. I was afraid a permission error might occur when multiple people write to the same file. The CSV file was created automatically. Are you suggesting that we create a CSV file in the .arc folder and if the csv file exists then write to the .arc folder?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, check if it exists in .arc first. Other users would like to keep a songle counter while submitting from different machines onto a single server.

if not os.path.isfile(csv_path):
# check file, make index file and write headers if file doesn't exists
with open(csv_path, 'w') as f:
Expand All @@ -445,7 +445,7 @@ def _write_initiated_job_to_csv_file(self):
"""
Write an initiated ARCJob into the initiated_jobs.csv file.
"""
csv_path = os.path.join(arc_path, 'initiated_jobs.csv')
csv_path = os.path.join(local_arc_path, 'initiated_jobs.csv')
if self.conformer < 0: # this is not a conformer search job
conformer = '-'
else:
Expand All @@ -463,7 +463,7 @@ def write_completed_job_to_csv_file(self):
"""
if self.job_status[0] != 'done' or self.job_status[1]['status'] != 'done':
self.determine_job_status()
csv_path = os.path.join(arc_path, 'completed_jobs.csv')
csv_path = os.path.join(local_arc_path, 'completed_jobs.csv')
if not os.path.isfile(csv_path):
# check file, make index file and write headers if file doesn't exists
with open(csv_path, 'w') as f:
Expand All @@ -473,7 +473,7 @@ def write_completed_job_to_csv_file(self):
'final_time', 'run_time', 'job_status_(server)', 'job_status_(ESS)',
'ESS troubleshooting methods used', 'comments']
writer.writerow(row)
csv_path = os.path.join(arc_path, 'completed_jobs.csv')
csv_path = os.path.join(local_arc_path, 'completed_jobs.csv')
if self.conformer < 0: # this is not a conformer search job
conformer = '-'
else:
Expand Down
12 changes: 6 additions & 6 deletions arc/job/ssh.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -275,11 +275,11 @@ def check_running_jobs_ids(self) -> list:
cmd = check_status_command[servers[self.server]['cluster_soft']] + ' -u $USER'
stdout = self._send_command_to_server(cmd)[0]
for i, status_line in enumerate(stdout):
if servers['local']['cluster_soft'].lower() == 'slurm' and i > 0:
if servers[self.server]['cluster_soft'].lower() == 'slurm' and i > 0:
running_jobs_ids.append(int(status_line.split()[0]))
elif servers['local']['cluster_soft'].lower() in ['oge', 'sge'] and i > 1:
elif servers[self.server]['cluster_soft'].lower() in ['oge', 'sge'] and i > 1:
running_jobs_ids.append(int(status_line.split()[0]))
elif servers['local']['cluster_soft'].lower() == 'pbs' and i > 4:
elif servers[self.server]['cluster_soft'].lower() == 'pbs' and i > 4:
running_jobs_ids.append(int(status_line.split('.')[0]))
return running_jobs_ids

Expand Down Expand Up @@ -308,13 +308,13 @@ def submit_job(self, remote_path: str) -> Tuple[str, int]:
if 'Requested node configuration is not available' in line:
logger.warning(f'User may be requesting more resources than are available. Please check server '
f'settings, such as cpus and memory, in ARC/arc/settings/settings.py')
elif servers['local']['cluster_soft'].lower() in ['oge', 'sge'] and 'submitted' in stdout[0].lower():
elif servers[self.server]['cluster_soft'].lower() in ['oge', 'sge'] and 'submitted' in stdout[0].lower():
job_id = int(stdout[0].split()[2])
job_status = 'running'
elif servers['local']['cluster_soft'].lower() == 'slurm' and 'submitted' in stdout[0].lower():
elif servers[self.server]['cluster_soft'].lower() == 'slurm' and 'submitted' in stdout[0].lower():
job_id = int(stdout[0].split()[3])
job_status = 'running'
elif servers['local']['cluster_soft'].lower() == 'pbs':
elif servers[self.server]['cluster_soft'].lower() == 'pbs':
job_id = int(stdout[0].split('.')[0])
job_status = 'running'
else:
Expand Down