Skip to content

[clustermgtd] Add retry to compute fleet status retrieval in clustermgtd #704

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

Merged
gmarciani merged 1 commit into from
May 14, 2026
+18 −7
Merged

[clustermgtd] Add retry to compute fleet status retrieval in clustermgtd #704

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
3 changes: 3 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,9 @@ This file is used to list changes made in each version of the aws-parallelcluste
3.16.0
------

**ENHANCEMENTS**
- Mitigate the impact of transient IMDS failures during compute fleet status retrieval.

**BUG FIXES**
- Fix clustermgtd failing to detect compute node bootstrap timeouts, which prevented the cluster from entering protected mode.

Expand Down
16 changes: 10 additions & 6 deletions src/slurm_plugin/clustermgtd.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,14 +97,19 @@ class ComputeFleetStatusManager:
COMPUTE_FLEET_STATUS_ATTRIBUTE = "status"
COMPUTE_FLEET_LAST_UPDATED_TIME_ATTRIBUTE = "lastStatusUpdatedTime"

@staticmethod
@retry(stop_max_attempt_number=3, wait_fixed=seconds(1))
def _get_fleet_status():
compute_fleet_raw_data = check_command_output("get-compute-fleet-status.sh")
log.debug("Retrieved compute fleet data: %s", compute_fleet_raw_data)
return ComputeFleetStatus(
json.loads(compute_fleet_raw_data).get(ComputeFleetStatusManager.COMPUTE_FLEET_STATUS_ATTRIBUTE)
)

@staticmethod
def get_status(fallback=None):
try:
compute_fleet_raw_data = check_command_output("get-compute-fleet-status.sh")
log.debug("Retrieved compute fleet data: %s", compute_fleet_raw_data)
return ComputeFleetStatus(
json.loads(compute_fleet_raw_data).get(ComputeFleetStatusManager.COMPUTE_FLEET_STATUS_ATTRIBUTE)
)
return ComputeFleetStatusManager._get_fleet_status()
except Exception as e:
if isinstance(e, CalledProcessError):
error = e.stdout.rstrip()
Expand All @@ -115,7 +120,6 @@ def get_status(fallback=None):
error,
fallback,
)

return fallback

@staticmethod
Expand Down
6 changes: 5 additions & 1 deletion tests/slurm_plugin/test_clustermgtd.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2304,6 +2304,7 @@ class TestComputeFleetStatusManager:
)
def test_get_status(self, mocker, get_item_response, fallback, expected_status):
check_command_output_mocked = mocker.patch("slurm_plugin.clustermgtd.check_command_output", autospec=True)
mocker.patch("retrying.time.sleep")
compute_fleet_status_manager = ComputeFleetStatusManager()

if get_item_response is Exception:
Expand All @@ -2312,7 +2313,10 @@ def test_get_status(self, mocker, get_item_response, fallback, expected_status):
check_command_output_mocked.return_value = get_item_response
status = compute_fleet_status_manager.get_status(fallback)
assert_that(status).is_equal_to(expected_status)
check_command_output_mocked.assert_called_once_with("get-compute-fleet-status.sh")
if get_item_response is Exception or get_item_response == "":
assert_that(check_command_output_mocked.call_count).is_equal_to(3)
else:
check_command_output_mocked.assert_called_once_with("get-compute-fleet-status.sh")

@pytest.mark.parametrize(
"desired_status, update_item_response",
Expand Down
Loading