rkuo-danswer bec0f9fb23
permission sync in cloud and beat expiry adjustment (#3544)
* try fixing exception in cloud

* raise beat expiry ... 60 seconds might be starving certain tasks completely

* adjust expiry down to 10 min

* raise concurrency overflow for indexing worker.

* parent pid check

* fix comment

* fix parent pid check, also actually raise an exception from the task if the spawned task exit status is bad

* fix pid check

* some cleanup and task wait fixes

* review fixes

* comment some code so we don't change too many things at once

---------

Co-authored-by: Richard Kuo (Danswer) <rkuo@onyx.app>
Co-authored-by: Richard Kuo <rkuo@rkuo.com>
2024-12-31 01:05:57 +00:00

93 lines
2.8 KiB
Python

from datetime import timedelta
from typing import Any
from onyx.configs.constants import OnyxCeleryPriority
from onyx.configs.constants import OnyxCeleryTask
# choosing 15 minutes because it roughly gives us enough time to process many tasks
# we might be able to reduce this greatly if we can run a unified
# loop across all tenants rather than tasks per tenant
BEAT_EXPIRES_DEFAULT = 15 * 60 # 15 minutes (in seconds)
# we set expires because it isn't necessary to queue up these tasks
# it's only important that they run relatively regularly
tasks_to_schedule = [
{
"name": "check-for-vespa-sync",
"task": OnyxCeleryTask.CHECK_FOR_VESPA_SYNC_TASK,
"schedule": timedelta(seconds=20),
"options": {
"priority": OnyxCeleryPriority.HIGH,
"expires": BEAT_EXPIRES_DEFAULT,
},
},
{
"name": "check-for-connector-deletion",
"task": OnyxCeleryTask.CHECK_FOR_CONNECTOR_DELETION,
"schedule": timedelta(seconds=20),
"options": {
"priority": OnyxCeleryPriority.HIGH,
"expires": BEAT_EXPIRES_DEFAULT,
},
},
{
"name": "check-for-indexing",
"task": OnyxCeleryTask.CHECK_FOR_INDEXING,
"schedule": timedelta(seconds=15),
"options": {
"priority": OnyxCeleryPriority.HIGH,
"expires": BEAT_EXPIRES_DEFAULT,
},
},
{
"name": "check-for-prune",
"task": OnyxCeleryTask.CHECK_FOR_PRUNING,
"schedule": timedelta(seconds=15),
"options": {
"priority": OnyxCeleryPriority.HIGH,
"expires": BEAT_EXPIRES_DEFAULT,
},
},
{
"name": "kombu-message-cleanup",
"task": OnyxCeleryTask.KOMBU_MESSAGE_CLEANUP_TASK,
"schedule": timedelta(seconds=3600),
"options": {
"priority": OnyxCeleryPriority.LOWEST,
"expires": BEAT_EXPIRES_DEFAULT,
},
},
{
"name": "monitor-vespa-sync",
"task": OnyxCeleryTask.MONITOR_VESPA_SYNC,
"schedule": timedelta(seconds=5),
"options": {
"priority": OnyxCeleryPriority.HIGH,
"expires": BEAT_EXPIRES_DEFAULT,
},
},
{
"name": "check-for-doc-permissions-sync",
"task": OnyxCeleryTask.CHECK_FOR_DOC_PERMISSIONS_SYNC,
"schedule": timedelta(seconds=30),
"options": {
"priority": OnyxCeleryPriority.HIGH,
"expires": BEAT_EXPIRES_DEFAULT,
},
},
{
"name": "check-for-external-group-sync",
"task": OnyxCeleryTask.CHECK_FOR_EXTERNAL_GROUP_SYNC,
"schedule": timedelta(seconds=20),
"options": {
"priority": OnyxCeleryPriority.HIGH,
"expires": BEAT_EXPIRES_DEFAULT,
},
},
]
def get_tasks_to_schedule() -> list[dict[str, Any]]:
return tasks_to_schedule