Skip to content

fix: clean up backups even when jobs failed #28

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

Open
jwnx wants to merge 2 commits into
base: flyio-2.6.0
Choose a base branch
from
+16 −7
Open

fix: clean up backups even when jobs failed #28

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4e46e17
fix: clean up backups even when jobs failed
jwnx Feb 16, 2026
aa6af2c
fix: use BackupRunning instead of non-existent BackupUnknown
jwnx Feb 16, 2026
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
23 changes: 16 additions & 7 deletions percona/controller/pgcluster/backup.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ import (

"github.com/pkg/errors"
batchv1 "k8s.io/api/batch/v1"
k8serrors "k8s.io/apimachinery/pkg/api/errors"
metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
"k8s.io/apimachinery/pkg/types"
"k8s.io/client-go/util/retry"
Expand Down Expand Up @@ -67,7 +68,10 @@ func (r *PGClusterReconciler) cleanupOutdatedBackups(ctx context.Context, cr *v2
}

for _, pgBackup := range pbList {
if pgBackup.Status.State != v2.BackupSucceeded || pgBackup.CompareVersion("2.4.0") < 0 {
if (pgBackup.Status.State != v2.BackupSucceeded &&
pgBackup.Status.State != v2.BackupFailed &&
pgBackup.Status.State != v2.BackupStarting &&
pgBackup.Status.State != v2.BackupRunning) || pgBackup.CompareVersion("2.4.0") < 0 {
continue
}

Expand All @@ -87,14 +91,19 @@ func (r *PGClusterReconciler) cleanupOutdatedBackups(ctx context.Context, cr *v2
// After the pg-backup is deleted, the job is not deleted immediately.
// We need to set the DeletionTimestamp for a job so that `reconcileBackupJob` doesn't create a new pg-backup before the job deletion.
job := new(batchv1.Job)
if err := r.Client.Get(ctx, types.NamespacedName{Name: pgBackup.Status.JobName, Namespace: pgBackup.Namespace}, job); err != nil {
err := r.Client.Get(ctx, types.NamespacedName{Name: pgBackup.Status.JobName, Namespace: pgBackup.Namespace}, job)
if err != nil && !k8serrors.IsNotFound(err) {
return errors.Wrap(err, "get backup job")
}
prop := metav1.DeletePropagationForeground
if err := r.Client.Delete(ctx, job, &client.DeleteOptions{
PropagationPolicy: &prop,
}); err != nil {
return errors.Wrapf(err, "delete job %s/%s", job.Name, job.Namespace)

// Only try to delete the job if it exists
if err == nil {
prop := metav1.DeletePropagationForeground
if err := r.Client.Delete(ctx, job, &client.DeleteOptions{
PropagationPolicy: &prop,
}); err != nil {
return errors.Wrapf(err, "delete job %s/%s", job.Name, job.Namespace)
}
}
if err := r.Client.Delete(ctx, &pgBackup); err != nil {
return errors.Wrapf(err, "delete backup %s/%s", pgBackup.Name, pgBackup.Namespace)
Expand Down
Loading