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.

Sign up for GitHub

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

Jump to bottom

Fixes NOT_RESPONDING kept while shutdown #503

Merged
merged 1 commit into from
Jun 3, 2024
Merged

Fixes NOT_RESPONDING kept while shutdown #503

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
12 changes: 5 additions & 7 deletions resources/playbook/roles/bibigrid/files/slurm/fail.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ process_string() {
}

mkdir -p worker_logs
mkdir -p worker_logs/fail
mkdir -p worker_logs/fail/out
mkdir -p worker_logs/fail/err

Expand All @@ -34,16 +35,13 @@ function log {

log "Fail-Script started"

# $1 is in slurm node format for example: bibigrid-worker0-cid-[0-1],bibigrid-worker1-cid-0 and needs no converting
scontrol update NodeName="$1" state=RESUME reason=FailedStartup # no sudo needed cause executed by slurm user

hosts=$(scontrol show hostnames "$1")

echo "Hosts $hosts used"
log "Hosts $hosts used"

# delete servers
python3 /usr/local/bin/delete_server.py "${hosts}"
# $1 is in slurm node format for example: bibigrid-worker0-cid-[0-1],bibigrid-worker1-cid-0 and needs no converting
scontrol update NodeName="$1" state=POWER_DOWN reason=FailedStartup # no sudo needed cause executed by slurm user

echo "Finished delete_server.py execution."
log "Nodes $1 set to POWER_DOWN."

exit $?
Loading