Skip to content

(feat) raise Kubernetes events #1815

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
gianlucam76 merged 1 commit into from
May 28, 2026
Merged

(feat) raise Kubernetes events #1815

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
24 changes: 24 additions & 0 deletions controllers/clustersummary_controller.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -531,12 +531,23 @@ func (r *ClusterSummaryReconciler) prepareForDeployment(ctx context.Context,
func (r *ClusterSummaryReconciler) proceedDeployingClusterSummary(ctx context.Context,
clusterSummaryScope *scope.ClusterSummaryScope, logger logr.Logger) (reconcile.Result, error) {

// Snapshot existing failure messages before deploying so we can detect
// new conflicts vs. ongoing ones and avoid re-raising an event every retry.
preDeployFailures := collectFailureMessages(clusterSummaryScope.ClusterSummary)

err := r.deploy(ctx, clusterSummaryScope, logger)
if err != nil {
var conflictErr *deployer.ConflictError
ok := errors.As(err, &conflictErr)
if ok {
logger.V(logs.LogInfo).Error(err, "failed to deploy because of conflict")
if _, alreadyKnown := preDeployFailures[conflictErr.Error()]; !alreadyKnown {
clusterSummary := clusterSummaryScope.ClusterSummary
r.eventRecorder.Eventf(clusterSummary, nil, corev1.EventTypeWarning, "Conflict",
configv1beta1.ClusterSummaryKind, "Conflict detected for cluster %s %s/%s: %s",
clusterSummary.Spec.ClusterType, clusterSummary.Spec.ClusterNamespace,
clusterSummary.Spec.ClusterName, conflictErr.Error())
}
r.setNextReconcileTime(clusterSummaryScope, r.ConflictRetryTime)
return reconcile.Result{Requeue: true, RequeueAfter: r.ConflictRetryTime}, nil
}
Expand Down Expand Up @@ -2095,3 +2106,16 @@ func getClusterSummaryWithInstantiatedCharts(ctx context.Context, cs *configv1be

return &csCopy, nil
}

// collectFailureMessages returns the set of FailureMessages currently recorded
// across all FeatureSummaries. Used to detect whether a conflict is new (not
// yet in the status) versus ongoing (already reported in a previous reconcile).
func collectFailureMessages(cs *configv1beta1.ClusterSummary) map[string]struct{} {
msgs := make(map[string]struct{}, len(cs.Status.FeatureSummaries))
for i := range cs.Status.FeatureSummaries {
if msg := cs.Status.FeatureSummaries[i].FailureMessage; msg != nil {
msgs[*msg] = struct{}{}
}
}
return msgs
}
17 changes: 17 additions & 0 deletions controllers/clustersummary_deployer.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -238,17 +238,29 @@ func (r *ClusterSummaryReconciler) proceedDeployingFeature(ctx context.Context,
func (r *ClusterSummaryReconciler) handleDeployerError(deployerError error, clusterSummaryScope *scope.ClusterSummaryScope,
f feature, currentHash []byte, logger logr.Logger) (bool, error) {

clusterSummary := clusterSummaryScope.ClusterSummary

// Check if error is a NonRetriableError type
var nonRetriableError *configv1beta1.NonRetriableError
if errors.As(deployerError, &nonRetriableError) {
nonRetriableStatus := libsveltosv1beta1.FeatureStatusFailedNonRetriable
r.updateFeatureStatus(clusterSummaryScope, f.id, &nonRetriableStatus, currentHash, deployerError, logger)
r.eventRecorder.Eventf(clusterSummary, nil, corev1.EventTypeWarning, "FailedNonRetriable",
configv1beta1.ClusterSummaryKind,
"Feature %s for cluster %s %s/%s failed with non-retriable error: %s",
f.id, clusterSummary.Spec.ClusterType, clusterSummary.Spec.ClusterNamespace,
clusterSummary.Spec.ClusterName, deployerError.Error())
return true, nil
}
var templateError *configv1beta1.TemplateInstantiationError
if errors.As(deployerError, &templateError) {
nonRetriableStatus := libsveltosv1beta1.FeatureStatusFailedNonRetriable
r.updateFeatureStatus(clusterSummaryScope, f.id, &nonRetriableStatus, currentHash, deployerError, logger)
r.eventRecorder.Eventf(clusterSummary, nil, corev1.EventTypeWarning, "FailedNonRetriable",
configv1beta1.ClusterSummaryKind,
"Feature %s for cluster %s %s/%s failed to instantiate template: %s",
f.id, clusterSummary.Spec.ClusterType, clusterSummary.Spec.ClusterNamespace,
clusterSummary.Spec.ClusterName, deployerError.Error())
return true, nil
}
var healthCheckError *clusterops.HealthCheckError
Expand All @@ -261,6 +273,11 @@ func (r *ClusterSummaryReconciler) handleDeployerError(deployerError error, clus
nonRetriableStatus := libsveltosv1beta1.FeatureStatusFailedNonRetriable
resultError := errors.New("the maximum number of consecutive errors has been reached")
r.updateFeatureStatus(clusterSummaryScope, f.id, &nonRetriableStatus, currentHash, resultError, logger)
r.eventRecorder.Eventf(clusterSummary, nil, corev1.EventTypeWarning, "FailedNonRetriable",
configv1beta1.ClusterSummaryKind,
"Feature %s for cluster %s %s/%s will no longer be retried: maximum consecutive failures reached",
f.id, clusterSummary.Spec.ClusterType, clusterSummary.Spec.ClusterNamespace,
clusterSummary.Spec.ClusterName)
return true, nil
}

Expand Down