Skip to content

More robust bench execution for Dynamo over k8s #793

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
amaslenn merged 1 commit into from
Feb 2, 2026
Merged

More robust bench execution for Dynamo over k8s #793

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
25 changes: 10 additions & 15 deletions src/cloudai/systems/kubernetes/kubernetes_system.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -310,23 +310,18 @@ def _run_genai_perf(self, job: KubernetesJob) -> None:

frontend_pod = self._get_dynamo_pod_by_role(role="frontend")

logging.debug(f"Executing genai-perf in pod={frontend_pod} cmd={genai_perf_cmd}")
kubectl_exec_cmd = ["kubectl", "exec", "-n", self.default_namespace, frontend_pod, "--", *genai_perf_cmd]
logging.debug(f"Executing genai-perf in pod={frontend_pod} cmd={kubectl_exec_cmd}")
try:
genai_results = lazy.k8s.stream.stream(
self.core_v1.connect_get_namespaced_pod_exec,
name=frontend_pod,
namespace=self.default_namespace,
command=genai_perf_cmd,
stderr=True,
stdin=False,
stdout=True,
tty=False,
_request_timeout=60 * 10,
)
result = subprocess.run(kubectl_exec_cmd, capture_output=True, text=True, timeout=60 * 10)
logging.debug(f"genai-perf exited with code {result.returncode}")
with (job.test_run.output_path / "genai_perf.log").open("w") as f:
f.write(genai_results)
except lazy.k8s.client.ApiException as e:
logging.error(f"Error executing genai-perf command in pod '{frontend_pod}': {e}")
f.write(result.stdout)
if result.stderr:
f.write("\nSTDERR:\n")
f.write(result.stderr)
except Exception as e:
logging.debug(f"Error executing genai-perf command in pod '{frontend_pod}': {e}")

cp_logs_cmd = " ".join(
[
Expand Down