lukaszraczylo/kubernetes-images-sync-operator
1
0
Fork 0
mirror of https://github.com/lukaszraczylo/kubernetes-images-sync-operator.git synced 2026-06-09 23:19:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

fixup! fixup! fixup! fixup! fixup! fixup! fixup! fixup! fixup! General improvements

Browse Source
This commit is contained in:
Lukasz Raczylo
2025-01-10 13:19:11 +00:00
parent 970908555b
commit a9dc08da40
3 changed files with 54 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files
chart/Chart.yaml
+2 -2
View File
@@ -10,9 +10,9 @@ description: |
type: application
version: 0.2.33
version: 0.2.34
appVersion: "0.2.33"
appVersion: "0.2.34"
home: https://github.com/lukaszraczylo/kubernetes-images-sync-operator
chart/values.yaml
+1 -1
View File
@@ -12,7 +12,7 @@ sa:
- ALL
image:
repository: ghcr.io/lukaszraczylo/kubernetes-images-sync-operator
tag: 0.2.33
tag: 0.2.34
resources:
limits:
cpu: 500m
internal/controller/raczylo.com/clusterimage_controller.go
+51 -35
View File
@@ -157,6 +157,13 @@ func (r *ClusterImageReconciler) handlePendingClusterImage(ctx context.Context,
}
func (r *ClusterImageReconciler) handleRunningClusterImage(ctx context.Context, clusterImage *raczylocomv1.ClusterImage, l logr.Logger) (ctrl.Result, error) {
// Get the latest version before proceeding
latest := &raczylocomv1.ClusterImage{}
if err := r.Get(ctx, types.NamespacedName{Name: clusterImage.Name, Namespace: clusterImage.Namespace}, latest); err != nil {
return ctrl.Result{}, err
}
clusterImage = latest
// Check for existing job for this ClusterImage
existingJob := &v1batch.Job{}
jobName := fmt.Sprintf("img-export-%s", clusterImage.Name)
@@ -171,16 +178,26 @@ func (r *ClusterImageReconciler) handleRunningClusterImage(ctx context.Context,
return ctrl.Result{}, nil
}
// If we have retries left, consider retrying
if clusterImage.Status.RetryCount < 3 {
clusterImage.Status.Progress = shared.STATUS_RETRYING
clusterImage.Status.RetryCount++
} else {
// Exceeded retries; mark as FAILED
clusterImage.Status.Progress = shared.STATUS_FAILED
// Get latest version before updating status
latest := &raczylocomv1.ClusterImage{}
if err := r.Get(ctx, types.NamespacedName{Name: clusterImage.Name, Namespace: clusterImage.Namespace}, latest); err != nil {
return ctrl.Result{}, err
}
if err := r.Status().Update(ctx, clusterImage); err != nil {
// If we have retries left, consider retrying
if latest.Status.RetryCount < 3 {
latest.Status.Progress = shared.STATUS_RETRYING
latest.Status.RetryCount++
} else {
// Exceeded retries; mark as FAILED
latest.Status.Progress = shared.STATUS_FAILED
}
if err := r.Status().Update(ctx, latest); err != nil {
if errors.IsConflict(err) {
// Resource was modified, requeue and try again
return ctrl.Result{Requeue: true}, nil
}
l.Error(err, "unable to update ClusterImage status after job not found")
return ctrl.Result{}, err
}
@@ -192,18 +209,17 @@ func (r *ClusterImageReconciler) handleRunningClusterImage(ctx context.Context,
}
// Check job status and update ClusterImage accordingly
// Get latest version before updating status
latest := &raczylocomv1.ClusterImage{}
if err := r.Get(ctx, types.NamespacedName{Name: clusterImage.Name, Namespace: clusterImage.Namespace}, latest); err != nil {
return ctrl.Result{}, err
}
clusterImage = latest
if existingJob.Status.Succeeded > 0 {
clusterImage.Status.Progress = shared.STATUS_SUCCESS
// Get latest version before updating status
latest := &raczylocomv1.ClusterImage{}
if err := r.Get(ctx, types.NamespacedName{Name: clusterImage.Name, Namespace: clusterImage.Namespace}, latest); err != nil {
return ctrl.Result{}, err
}
latest.Status.Progress = shared.STATUS_SUCCESS
r.ActiveJobs--
// Update the status before cleaning up the job
if err := r.Status().Update(ctx, clusterImage); err != nil {
if err := r.Status().Update(ctx, latest); err != nil {
if errors.IsConflict(err) {
// Resource was modified, requeue and try again
return ctrl.Result{Requeue: true}, nil
@@ -431,6 +447,14 @@ func (r *ClusterImageReconciler) updateClusterImageExportStatus(ctx context.Cont
func (r *ClusterImageReconciler) handleJobRestarts(ctx context.Context, job *v1batch.Job, clusterImage *raczylocomv1.ClusterImage) error {
l := log.FromContext(ctx)
// Get the latest version before proceeding
latest := &raczylocomv1.ClusterImage{}
if err := r.Get(ctx, types.NamespacedName{Name: clusterImage.Name, Namespace: clusterImage.Namespace}, latest); err != nil {
return err
}
clusterImage = latest
podList := &v1.PodList{}
if err := r.List(ctx, podList, client.InNamespace(job.Namespace), client.MatchingLabels(job.Spec.Selector.MatchLabels)); err != nil {
return err
@@ -449,22 +473,21 @@ func (r *ClusterImageReconciler) handleJobRestarts(ctx context.Context, job *v1b
if newRestarts > 0 {
l.Info("Container restarts detected", "job", job.Name, "newRestarts", newRestarts, "totalRestarts", totalRestarts)
// Get latest version before updating
latest := &raczylocomv1.ClusterImage{}
if err := r.Get(ctx, types.NamespacedName{Name: clusterImage.Name, Namespace: clusterImage.Namespace}, latest); err != nil {
return err
}
// Update retry count with new restarts
clusterImage.Status.RetryCount += newRestarts
if clusterImage.Status.RetryCount >= 3 {
// Get latest version before updating status
latest := &raczylocomv1.ClusterImage{}
if err := r.Get(ctx, types.NamespacedName{Name: clusterImage.Name, Namespace: clusterImage.Namespace}, latest); err != nil {
return err
}
latest.Status.RetryCount = clusterImage.Status.RetryCount + newRestarts
if latest.Status.RetryCount >= 3 {
// Max retries reached
latest.Status.Progress = shared.STATUS_FAILED
latest.Status.RetryCount = clusterImage.Status.RetryCount
if err := r.Status().Update(ctx, latest); err != nil {
if errors.IsConflict(err) {
// Resource was modified, try again
// Resource was modified, requeue and try again
return nil
}
return fmt.Errorf("failed to update status to FAILED: %w", err)
@@ -475,18 +498,11 @@ func (r *ClusterImageReconciler) handleJobRestarts(ctx context.Context, job *v1b
return fmt.Errorf("failed to cleanup resources: %w", err)
}
} else {
// Get latest version before updating status
latest := &raczylocomv1.ClusterImage{}
if err := r.Get(ctx, types.NamespacedName{Name: clusterImage.Name, Namespace: clusterImage.Namespace}, latest); err != nil {
return err
}
// Still have retries left
latest.Status.Progress = shared.STATUS_RETRYING
latest.Status.RetryCount = clusterImage.Status.RetryCount
if err := r.Status().Update(ctx, latest); err != nil {
if errors.IsConflict(err) {
// Resource was modified, try again
// Resource was modified, requeue and try again
return nil
}
return fmt.Errorf("failed to update status to RETRYING: %w", err)