Skip to content

fix: preserve batch wrapper exit status #2838

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

Open
AdamRajfer wants to merge 1 commit into
base: main
Choose a base branch
from
+4 −2
Open

fix: preserve batch wrapper exit status #2838

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
2 changes: 1 addition & 1 deletion benchmarks/nemotron_3.5_super/sbatch_external_vllm.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -285,7 +285,7 @@ main_job_id=$(
--comment="$SLURM_COMMENT" \
--exclusive \
--segment=$NUM_NODES \
--wrap 'exec bash -lc "$batch_command"'
--wrap 'exec bash -c "$batch_command"'
)
main_job_id=${main_job_id%%;*}

Expand Down
4 changes: 3 additions & 1 deletion tests/unit_tests/test_opensandbox_cleanup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -621,6 +621,8 @@ def test_slurm_launcher_submits_one_dependent_cpu_cleanup_job(tmp_path: Path) ->
]
main_call, cleanup_call = read_sbatch_calls(calls_path)
assert "--parsable" in main_call
wrap_index = main_call.index("--wrap")
assert main_call[wrap_index + 1] == 'exec bash -c "$batch_command"'

submit_dir = str(Path.cwd().resolve())
repo_root = SBATCH_SCRIPT.resolve().parents[2]
Expand Down Expand Up @@ -698,7 +700,7 @@ def test_slurm_launcher_reports_cleanup_submission_failure(tmp_path: Path) -> No

@pytest.mark.parametrize(
("first_step", "eval_status", "expected_status"),
[("eval", 37, 37), ("eval", 143, 143), ("server", 0, 41)],
[("eval", 0, 0), ("eval", 37, 37), ("eval", 143, 143), ("server", 0, 41)],
)
def test_slurm_batch_command_preserves_status_and_stops_server(
tmp_path: Path, first_step: str, eval_status: int, expected_status: int
Expand Down
Loading