Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
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
6 changes: 5 additions & 1 deletion collectoss/application/config.py
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,11 @@ def redact_setting_value(section_name, setting_name, value):
"core_worker_count": 5,
"secondary_worker_count": 5,
"facade_worker_count": 5,
"refresh_materialized_views_interval_in_days": 1
"refresh_materialized_views_interval_in_days": 1,
"non_repo_domain_tasks_interval_in_days": 30,
"retry_errored_repos_interval_in_days": 1,
"process_contributors_interval_in_seconds": 3600,
"create_collection_status_records_interval_in_days": 1
},
"Redis": {
"cache_group": 0,
Expand Down
38 changes: 28 additions & 10 deletions collectoss/tasks/init/celery_app.py
Original file line number Diff line number Diff line change
Expand Up @@ -237,28 +237,46 @@ def setup_periodic_tasks(sender, **kwargs):
sender.add_periodic_task(collection_interval, collection_monitor.s())

#Do longer tasks less often
logger.info(f"Scheduling data analysis every 30 days")
thirty_days_in_seconds = 30*24*60*60
sender.add_periodic_task(thirty_days_in_seconds, non_repo_domain_tasks.s())
non_repo_domain_interval = int(config.get_value('Celery', 'non_repo_domain_tasks_interval_in_days'))
if non_repo_domain_interval > 0:
logger.info(f"Scheduling data analysis every {non_repo_domain_interval} days")
non_repo_domain_interval_in_seconds = non_repo_domain_interval * 24 * 60 * 60
sender.add_periodic_task(non_repo_domain_interval_in_seconds, non_repo_domain_tasks.s())
else:
logger.info(f"Data analysis task is disabled.")

mat_views_interval = int(config.get_value('Celery', 'refresh_materialized_views_interval_in_days'))
if mat_views_interval > 0:
logger.info(f"Scheduling refresh materialized view every night at 1am CDT")
logger.info(f"Scheduling refresh materialized view every {mat_views_interval} days")
sender.add_periodic_task(datetime.timedelta(days=mat_views_interval), refresh_materialized_views.s())
else:
logger.info(f"Refresh materialized view task is disabled.")

# logger.info(f"Scheduling update of collection weights on midnight each day")
# sender.add_periodic_task(crontab(hour=0, minute=0),collection_update_weights.s())

logger.info(f"Setting 404 repos to be marked for retry on midnight each day")
sender.add_periodic_task(crontab(hour=0, minute=0),retry_errored_repos.s())
retry_errored_repos_interval = int(config.get_value('Celery', 'retry_errored_repos_interval_in_days'))
if retry_errored_repos_interval > 0:
logger.info(f"Scheduling retry errored repos every {retry_errored_repos_interval} days")
retry_errored_repos_interval_in_seconds = retry_errored_repos_interval * 24 * 60 * 60
sender.add_periodic_task(retry_errored_repos_interval_in_seconds, retry_errored_repos.s())
else:
logger.info(f"Retry errored repos task is disabled.")

one_hour_in_seconds = 60*60
sender.add_periodic_task(one_hour_in_seconds, process_contributors.s())
process_contributors_interval = int(config.get_value('Celery', 'process_contributors_interval_in_seconds'))
if process_contributors_interval > 0:
logger.info(f"Scheduling process contributors every {process_contributors_interval/3600} hours")
sender.add_periodic_task(process_contributors_interval, process_contributors.s())
else:
logger.info(f"Process contributors task is disabled.")

one_day_in_seconds = 24*60*60
sender.add_periodic_task(one_day_in_seconds, create_collection_status_records.s())
create_collection_status_records_interval = int(config.get_value('Celery', 'create_collection_status_records_interval_in_days'))
if create_collection_status_records_interval > 0:
logger.info(f"Scheduling create collection status records every {create_collection_status_records_interval} days")
create_collection_status_records_interval_in_seconds = create_collection_status_records_interval * 24 * 60 * 60
sender.add_periodic_task(create_collection_status_records_interval_in_seconds, create_collection_status_records.s())
else:
logger.info(f"Create collection status records task is disabled.")

@after_setup_logger.connect
def setup_loggers(*args,**kwargs):
Expand Down
Loading