Skip to content

[Test] Add a check before we do updates #7403

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
himani2411 merged 1 commit into from
May 21, 2026
+14 −11
Merged

[Test] Add a check before we do updates #7403

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
9 changes: 7 additions & 2 deletions tests/integration-tests/clusters_factory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,7 +192,7 @@ def start(self, wait_running=False):
logging.error("Failed starting cluster with error:\n%s\nand output:\n%s", e.stderr, e.stdout)
raise

def stop(self):
def stop(self, wait_stopped=False):
"""Run pcluster stop and return the result."""
cmd_args = ["pcluster", "update-compute-fleet", "--cluster-name", self.name, "--status"]
scheduler = self.config["Scheduling"]["Scheduler"]
Expand All @@ -203,7 +203,12 @@ def stop(self):
try:
result = run_pcluster_command(cmd_args, log_error=False, custom_cli_credentials=self.custom_cli_credentials)
logging.info("Cluster {0} stopped successfully".format(self.name))

if wait_stopped:
retry(
wait_fixed=seconds(10),
stop_max_delay=minutes(2),
retry_on_result=lambda describe_result: "STOPPED" != describe_result["status"],
)(self.describe_compute_fleet)()
return result.stdout
except subprocess.CalledProcessError as e:
logging.error("Failed stopping cluster with error:\n%s\nand output:\n%s", e.stderr, e.stdout)
Expand Down
16 changes: 7 additions & 9 deletions tests/integration-tests/tests/cli_commands/test_cli_commands.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,6 @@
import re
import tarfile
import tempfile
import time

import boto3
import botocore
Expand Down Expand Up @@ -295,14 +294,13 @@ def _test_pcluster_compute_fleet(cluster, expected_num_nodes):
last_stop_time = compute_fleet["lastStatusUpdatedTime"]

logging.info("Testing pcluster start functionalities")
# Do a complicated sequence of start and stop and see if commands will still work
cluster.start()
time.sleep(15)
cluster.stop()
time.sleep(15)
cluster.stop()
time.sleep(30)
cluster.start()
# Do a complicated sequence of start and stop and see if commands will still work.
# We must wait for terminal states between commands to avoid racing with clusterstatusmgtd's
# ~60s poll loop, which transitions *_REQUESTED -> *ING and would cause conditional DDB write failures.
cluster.start(wait_running=True)
cluster.stop(wait_stopped=True)
cluster.stop(wait_stopped=True) # idempotent on already-stopped fleet
cluster.start(wait_running=True)
compute_fleet = cluster.describe_compute_fleet()
last_start_time = compute_fleet["lastStatusUpdatedTime"]
logging.info("Checking last status update time is updated")
Expand Down
Loading