tea/browsertrix
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

operator: adjust state transition rules to ensure 'running' state always accounted for in db (#1989)

Browse Source 
don't rely on current status, always set state to running when running
to ensure idempotency in case of multiple calls
This commit is contained in:
Ilya Kreymer 2024-08-05 16:00:21 -07:00 committed by GitHub
parent 1c153dfd3c
commit 4a2725aaa6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 17 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
backend/btrixcloud/operator/crawls.py
View File

@ -807,27 +807,25 @@ class CrawlOperator(BaseOperator):
status.resync_after = self.fast_retry_secs
return status
# set state to running (if not already)
if status.state not in RUNNING_STATES:
# if true (state is set), also run webhook
if await self.set_state(
"running",
status,
crawl,
allowed_from=["starting", "waiting_capacity"],
):
if not crawl.qa_source_crawl_id:
self.run_task(
self.event_webhook_ops.create_crawl_started_notification(
crawl.id, crawl.oid, scheduled=crawl.scheduled
)
# if true (state is set), also run webhook
if await self.set_state(
"running",
status,
crawl,
allowed_from=["starting", "waiting_capacity"],
):
if not crawl.qa_source_crawl_id:
self.run_task(
self.event_webhook_ops.create_crawl_started_notification(
crawl.id, crawl.oid, scheduled=crawl.scheduled
)
else:
self.run_task(
self.event_webhook_ops.create_qa_analysis_started_notification(
crawl.id, crawl.oid, crawl.qa_source_crawl_id
)
)
else:
self.run_task(
self.event_webhook_ops.create_qa_analysis_started_notification(
crawl.id, crawl.oid, crawl.qa_source_crawl_id
)
)
# update lastActiveTime if crawler is running
if crawler_running: