admin/stonks-oracle
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: use kubectl wait for job completion detection in inttest pipeline

Browse Source 
The polling loop checked conditions[0].type which missed the Complete
condition when it wasn't at index 0. Switch to kubectl wait
--for=condition=complete which handles condition matching reliably.
This commit is contained in:
Celes Renata
2026-04-20 07:47:10 +00:00
parent 40d4fd8197
commit 5289f0f195
1 changed files with 11 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
infra/inttest/run_pipeline.sh
+11 -12
View File
@@ -428,24 +428,23 @@ envsubst < "$REPO_ROOT/infra/inttest/runner.yaml" \
| kubectl apply -n "$NAMESPACE" -f - | kubectl apply -n "$NAMESPACE" -f -
log "Waiting for test runner to complete (timeout: 600s) ..." log "Waiting for test runner to complete (timeout: 600s) ..."
# Wait for either complete or failed — whichever comes first # Use kubectl wait which handles condition matching reliably.
# Wait for Complete first; if that times out, check for Failed.
JOB_DONE=false JOB_DONE=false
for i in $(seq 1 120); do if kubectl wait --for=condition=complete job/inttest-runner -n "$NAMESPACE" --timeout=600s 2>/dev/null; then
STATUS=$(kubectl get job inttest-runner -n "$NAMESPACE" -o jsonpath='{.status.conditions[0].type}' 2>/dev/null || true) log "Test runner completed successfully"
if [ "$STATUS" = "Complete" ]; then stage_end "integration_tests" "ok"
log "Test runner completed successfully" JOB_DONE=true
stage_end "integration_tests" "ok" else
JOB_DONE=true # Check if it failed (non-zero exit) vs timed out
break FAILED=$(kubectl get job inttest-runner -n "$NAMESPACE" -o jsonpath='{.status.conditions[?(@.type=="Failed")].status}' 2>/dev/null || true)
elif [ "$STATUS" = "Failed" ]; then if [ "$FAILED" = "True" ]; then
log "Test runner job reported failure (tests failed)" log "Test runner job reported failure (tests failed)"
stage_fail "integration_tests" stage_fail "integration_tests"
PIPELINE_EXIT_CODE=1 PIPELINE_EXIT_CODE=1
JOB_DONE=true JOB_DONE=true
break
fi fi
sleep 5 fi
done
if [ "$JOB_DONE" = false ]; then if [ "$JOB_DONE" = false ]; then
log "Test runner timed out after 600s" log "Test runner timed out after 600s"
debug_pod_failure "inttest-runner" "app=inttest-runner" debug_pod_failure "inttest-runner" "app=inttest-runner"