Skip to content

Keep CSCS startup channel active #225

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

Closed
robobryce wants to merge 1 commit into from
Closed

Keep CSCS startup channel active #225

Show file tree
Hide file tree
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
28 changes: 20 additions & 8 deletions tutorials/pyhpc/brev/cscs-launch-tutorial.bash
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,6 +164,7 @@ wait_until_ready() {
local timeout=$3
local deadline=0
local last_state=
local next_progress=0

while true; do
local ready_line=
Expand Down Expand Up @@ -193,16 +194,22 @@ wait_until_ready() {
RUNNING)
if [ "${deadline}" -eq 0 ]; then
deadline=$((SECONDS + timeout))
next_progress=$((SECONDS + 30))
fi
if [ -n "${ready_line}" ]; then
local node=${ready_line#READY node=}
printf 'CSCS_WEB_NODE=%s\n' "${node}"
printf 'CSCS_WEB_LOG=%s\n' "${log}"
return 0
fi
if [ "${SECONDS}" -ge "${next_progress}" ]; then
echo "Job ${job_id}: RUNNING (services are still starting)"
next_progress=$((SECONDS + 30))
fi
;;
PENDING*|CONFIGURING*|REQUEUED*|RESV_DEL_HOLD*)
deadline=0
next_progress=0
;;
COMPLETED*|FAILED*|CANCELLED*|TIMEOUT*|NODE_FAIL*|OUT_OF_MEMORY*|PREEMPTED*|BOOT_FAIL*|DEADLINE*)
echo "Error: job ${job_id} entered ${state} before the services became ready." >&2
Expand All @@ -222,10 +229,10 @@ wait_until_ready() {

ACTIVE_JOB_ID=
cancel_active_job() {
trap - HUP INT TERM
echo "Launcher interrupted; stopping job ${ACTIVE_JOB_ID}." >&2
stop_job "${ACTIVE_JOB_ID}" || true
exit 130
local status=$1
trap '' HUP INT TERM PIPE
stop_job "${ACTIVE_JOB_ID}" >/dev/null 2>&1 || true
exit "${status}"
}

login_main() {
Expand Down Expand Up @@ -317,18 +324,23 @@ login_main() {
esac
local log="${state_dir}/slurm-${job_id}.log"

ACTIVE_JOB_ID=${job_id}
trap 'cancel_active_job 129' HUP
trap 'cancel_active_job 130' INT
trap 'cancel_active_job 143' TERM
trap 'cancel_active_job 141' PIPE
printf 'CSCS_WEB_JOB_ID=%s\n' "${job_id}"
echo "Waiting for JupyterLab and both Nsight Streamers to become ready..."
ACTIVE_JOB_ID=${job_id}
trap cancel_active_job HUP INT TERM
local wait_status=0
wait_until_ready "${job_id}" "${log}" "${start_timeout}" || wait_status=$?
trap - HUP INT TERM
ACTIVE_JOB_ID=
if [ "${wait_status}" -ne 0 ]; then
trap - HUP INT TERM PIPE
ACTIVE_JOB_ID=
return "${wait_status}"
fi
printf 'CSCS_WEB_REPO=%s\n' "${repo}"
trap - HUP INT TERM PIPE
ACTIVE_JOB_ID=
}

batch_main() {
Expand Down
5 changes: 5 additions & 0 deletions tutorials/pyhpc/brev/cscs-run-tutorial.bash
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,6 +202,11 @@ ssh -F "${ssh_config}" -S "${control_path}" ach-daint "${remote_command}" \
launch_status=${PIPESTATUS[0]}
set -e
if [ "${launch_status}" -ne 0 ]; then
partial_job_id=$(sed -n 's/^CSCS_WEB_JOB_ID=//p' "${launch_output}" | tail -n1)
echo "Error: the connection to the Daint launcher ended with SSH status ${launch_status} before a ready node was reported." >&2
if [ -n "${partial_job_id}" ]; then
echo "Submitted job: ${partial_job_id}. Verify that it stopped before retrying." >&2
fi
exit "${launch_status}"
fi

Expand Down
Loading