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

Kill all grid engine jobs on shutdown #5083

Merged
merged 1 commit into from
Sep 16, 2024
Merged
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
9 changes: 8 additions & 1 deletion src/toil/batchSystems/abstractGridEngineBatchSystem.py
Original file line number Diff line number Diff line change
Expand Up @@ -256,6 +256,8 @@ def _runStep(self):
newJob = self.newJobsQueue.get()
if newJob is None:
logger.debug('Received queue sentinel.')
# Send out kill signals before stopping
self.killJobs()
return False
if self.killJobs():
activity = True
Expand Down Expand Up @@ -413,7 +415,7 @@ def issueBatchJob(self, command: str, jobDesc, job_environment: Optional[Dict[st
gpus = accelerator['count']
else:
gpus = jobDesc.accelerators

self.newJobsQueue.put((jobID, jobDesc.cores, jobDesc.memory, command, get_job_kind(jobDesc.get_names()),
job_environment, gpus))
logger.debug("Issued the job command: %s with job id: %s and job name %s", command, str(jobID),
Expand Down Expand Up @@ -496,6 +498,11 @@ def shutdown(self) -> None:
"""
Signals thread to shutdown (via sentinel) then cleanly joins the thread
"""

for jobID in self.getIssuedBatchJobIDs():
# Send kill signals to any jobs that might be running
self.killQueue.put(jobID)

self.shutdownLocal()
newJobsQueue = self.newJobsQueue
self.newJobsQueue = None
Expand Down
Loading