You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
fix(evidence): SKIP absent Dynamo workload instead of failing submission
The robust-operator section recorded Result: FAIL when the Dynamo operator
was present but no DynamoGraphDeployment existed, collapsing a failed API
query and a successful zero-row query into the same 0. With section FAILs
now propagating to a nonzero exit, a stock Dynamo inference bundle +
--cncf-submission failed on the default path: the service-metrics section
deploys and cleans up its own DGD before the operator section runs, so the
operator section saw zero DGDs.
Distinguish a failed DGD query (fail closed) from a successful query with
zero rows (absent prerequisite -> SKIP), matching the SKIP treatment given
to absent gateway/operator/autoscaler prerequisites. Add a subprocess test
for the new branch and assert each section collector emits exactly one
column-zero verdict.
Fixes the cross-review finding on PR #1730.
Signed-off-by: Yuan Chen <yuanchen97@gmail.com>
echo"**Result: PASS** — Dynamo operator running, CRDs registered, DynamoGraphDeployment reconciled with ${running_pods} healthy workload pod(s).">>"${EVIDENCE_FILE}"
2486
2496
elif [ "${dgd_count}"-gt 0 ];then
2487
2497
echo"**Result: FAIL** — DynamoGraphDeployment found but no healthy workload pods.">>"${EVIDENCE_FILE}"
2488
2498
else
2489
-
echo"**Result: FAIL** — No DynamoGraphDeployment found.">>"${EVIDENCE_FILE}"
2499
+
echo"**Result: SKIP (prerequisite absent)** — Dynamo operator present but no DynamoGraphDeployment exists; deploy an inference workload (e.g. demos/workloads/inference/vllm-agg.yaml) to exercise operator reconciliation.">>"${EVIDENCE_FILE}"
0 commit comments