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.

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

nautilus: mgr/volumes: unregister job upon async threads exception #33569

Merged
merged 1 commit into from Feb 27, 2020
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
12 changes: 7 additions & 5 deletions src/pybind/mgr/volumes/fs/async_job.py
Expand Up @@ -28,6 +28,7 @@ def run(self):
thread_name = thread_id.getName()

while retries < JobThread.MAX_RETRIES_ON_EXCEPTION:
vol_job = None
try:
# fetch next job to execute
with self.async_job.lock:
Expand All @@ -40,10 +41,6 @@ def run(self):

# execute the job (outside lock)
self.async_job.execute_job(vol_job[0], vol_job[1], should_cancel=lambda: thread_id.should_cancel())

# when done, unregister the job
with self.async_job.lock:
self.async_job.unregister_async_job(vol_job[0], vol_job[1], thread_id)
retries = 0
except NotImplementedException:
raise
Expand All @@ -56,7 +53,12 @@ def run(self):
exc_type, exc_value, exc_traceback = sys.exc_info()
log.warning("traceback: {0}".format("".join(
traceback.format_exception(exc_type, exc_value, exc_traceback))))
time.sleep(1)
finally:
# when done, unregister the job
if vol_job:
with self.async_job.lock:
self.async_job.unregister_async_job(vol_job[0], vol_job[1], thread_id)
time.sleep(1)
log.error("thread [{0}] reached exception limit, bailing out...".format(thread_name))
self.vc.cluster_log("thread {0} bailing out due to exception".format(thread_name))

Expand Down