Implement autobackup-operator controllers, tests, CI and packaging

PVCs and CloudNativePG Clusters need S3 buckets and backup schedules
provisioned consistently. This operator watches the
backups.unkin.net/{schedule,destination} annotations on those objects and
provisions everything needed to back them up, with no new CRDs.

- Add a PVC controller that provisions cephrgw ObjectStoreUser/Bucket/BucketAccess,
  auto-generates a restic repo-password Secret and creates a k8up Schedule scoped
  to the PVC via spec.backup.volumes[].persistentVolumeClaim.claimName.
- Add a CNPG Cluster controller that provisions the same bucket stack, idempotently
  patches spec.backup.barmanObjectStore (leaving a user-set destinationPath alone
  with a Warning event) and creates a ScheduledBackup.
- Resolve destinations through a ConfigMap lookup table; requeue until the
  BucketAccess is Ready before creating schedule resources; own-reference created
  resources and retain bucket data by default.
- Add schedule-mapping helpers (k8up 5-field/shortcut pass-through, CNPG 6-field
  seconds-first) and deterministic, length-bounded name derivation.
- Add unit tests (schedule mapping, name derivation, destination resolution) and
  envtest controller tests for both paths, wiring the external CRDs into envtest.
- Add kubebuilder-generated RBAC, a Dockerfile (distroless/nonroot), Woodpecker
  lint/test/build pipelines and a tag-triggered image push to the artifactapi
  docker-internal registry, plus a version-bump Makefile and deploy manifests.
This commit is contained in:
2026-08-14 00:08:37 +10:00
parent 3d63975b24
commit 9da206dc7c
4631 changed files with 1334852 additions and 1 deletions
@@ -0,0 +1,168 @@
/*
Copyright 2018 The Kubernetes Authors.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
*/
package internal
import (
"context"
"fmt"
"k8s.io/client-go/tools/cache"
"k8s.io/client-go/util/workqueue"
"sigs.k8s.io/controller-runtime/pkg/client"
"sigs.k8s.io/controller-runtime/pkg/event"
"sigs.k8s.io/controller-runtime/pkg/handler"
logf "sigs.k8s.io/controller-runtime/pkg/internal/log"
"sigs.k8s.io/controller-runtime/pkg/predicate"
)
var log = logf.RuntimeLog.WithName("source").WithName("EventHandler")
var _ cache.ResourceEventHandler = &EventHandler[client.Object, any]{}
// NewEventHandler creates a new EventHandler.
func NewEventHandler[object client.Object, request comparable](
ctx context.Context,
queue workqueue.TypedRateLimitingInterface[request],
handler handler.TypedEventHandler[object, request],
predicates []predicate.TypedPredicate[object]) *EventHandler[object, request] {
return &EventHandler[object, request]{
ctx: ctx,
handler: handler,
queue: queue,
predicates: predicates,
}
}
// EventHandler adapts a handler.EventHandler interface to a cache.ResourceEventHandler interface.
type EventHandler[object client.Object, request comparable] struct {
// ctx stores the context that created the event handler
// that is used to propagate cancellation signals to each handler function.
ctx context.Context
handler handler.TypedEventHandler[object, request]
queue workqueue.TypedRateLimitingInterface[request]
predicates []predicate.TypedPredicate[object]
}
// OnAdd creates CreateEvent and calls Create on EventHandler.
func (e *EventHandler[object, request]) OnAdd(obj any, isInInitialList bool) {
c := event.TypedCreateEvent[object]{
IsInInitialList: isInInitialList,
}
// Pull Object out of the object
if o, ok := obj.(object); ok {
c.Object = o
} else {
log.Error(nil, "OnAdd missing Object",
"object", obj, "type", fmt.Sprintf("%T", obj))
return
}
for _, p := range e.predicates {
if !p.Create(c) {
return
}
}
// Invoke create handler
ctx, cancel := context.WithCancel(e.ctx)
defer cancel()
e.handler.Create(ctx, c, e.queue)
}
// OnUpdate creates UpdateEvent and calls Update on EventHandler.
func (e *EventHandler[object, request]) OnUpdate(oldObj, newObj any) {
u := event.TypedUpdateEvent[object]{}
if o, ok := oldObj.(object); ok {
u.ObjectOld = o
} else {
log.Error(nil, "OnUpdate missing ObjectOld",
"object", oldObj, "type", fmt.Sprintf("%T", oldObj))
return
}
// Pull Object out of the object
if o, ok := newObj.(object); ok {
u.ObjectNew = o
} else {
log.Error(nil, "OnUpdate missing ObjectNew",
"object", newObj, "type", fmt.Sprintf("%T", newObj))
return
}
for _, p := range e.predicates {
if !p.Update(u) {
return
}
}
// Invoke update handler
ctx, cancel := context.WithCancel(e.ctx)
defer cancel()
e.handler.Update(ctx, u, e.queue)
}
// OnDelete creates DeleteEvent and calls Delete on EventHandler.
func (e *EventHandler[object, request]) OnDelete(obj any) {
d := event.TypedDeleteEvent[object]{}
// Deal with tombstone events by pulling the object out. Tombstone events wrap the object in a
// DeleteFinalStateUnknown struct, so the object needs to be pulled out.
// Copied from sample-controller
// This should never happen if we aren't missing events, which we have concluded that we are not
// and made decisions off of this belief. Maybe this shouldn't be here?
var ok bool
if _, ok = obj.(client.Object); !ok {
// If the object doesn't have Metadata, assume it is a tombstone object of type DeletedFinalStateUnknown
tombstone, ok := obj.(cache.DeletedFinalStateUnknown)
if !ok {
log.Error(nil, "Error decoding objects. Expected cache.DeletedFinalStateUnknown",
"type", fmt.Sprintf("%T", obj),
"object", obj)
return
}
// Set DeleteStateUnknown to true
d.DeleteStateUnknown = true
// Set obj to the tombstone obj
obj = tombstone.Obj
}
// Pull Object out of the object
if o, ok := obj.(object); ok {
d.Object = o
} else {
log.Error(nil, "OnDelete missing Object",
"object", obj, "type", fmt.Sprintf("%T", obj))
return
}
for _, p := range e.predicates {
if !p.Delete(d) {
return
}
}
// Invoke delete handler
ctx, cancel := context.WithCancel(e.ctx)
defer cancel()
e.handler.Delete(ctx, d, e.queue)
}
+150
View File
@@ -0,0 +1,150 @@
package internal
import (
"context"
"errors"
"fmt"
"reflect"
"time"
"k8s.io/apimachinery/pkg/api/meta"
"k8s.io/apimachinery/pkg/runtime"
"k8s.io/apimachinery/pkg/util/wait"
toolscache "k8s.io/client-go/tools/cache"
"k8s.io/client-go/util/workqueue"
logf "sigs.k8s.io/controller-runtime/pkg/internal/log"
"sigs.k8s.io/controller-runtime/pkg/cache"
"sigs.k8s.io/controller-runtime/pkg/client"
"sigs.k8s.io/controller-runtime/pkg/handler"
"sigs.k8s.io/controller-runtime/pkg/predicate"
)
var logKind = logf.RuntimeLog.WithName("source").WithName("Kind")
// Kind is used to provide a source of events originating inside the cluster from Watches (e.g. Pod Create).
type Kind[object client.Object, request comparable] struct {
// Type is the type of object to watch. e.g. &v1.Pod{}
Type object
// Cache used to watch APIs
Cache cache.Cache
Handler handler.TypedEventHandler[object, request]
Predicates []predicate.TypedPredicate[object]
// startedErr may contain an error if one was encountered during startup. If its closed and does not
// contain an error, startup and syncing finished.
startedErr chan error
startCancel func()
}
// Start is internal and should be called only by the Controller to register an EventHandler with the Informer
// to enqueue reconcile.Requests.
func (ks *Kind[object, request]) Start(ctx context.Context, queue workqueue.TypedRateLimitingInterface[request]) error {
if isNil(ks.Type) {
return fmt.Errorf("must create Kind with a non-nil object")
}
if isNil(ks.Cache) {
return fmt.Errorf("must create Kind with a non-nil cache")
}
if isNil(ks.Handler) {
return errors.New("must create Kind with non-nil handler")
}
// cache.GetInformer will block until its context is cancelled if the cache was already started and it can not
// sync that informer (most commonly due to RBAC issues).
ctx, ks.startCancel = context.WithCancel(ctx)
ks.startedErr = make(chan error, 1) // Buffer chan to not leak goroutines if WaitForSync isn't called
go func() {
var (
i cache.Informer
lastErr error
)
// Tries to get an informer until it returns true,
// an error or the specified context is cancelled or expired.
if err := wait.PollUntilContextCancel(ctx, 10*time.Second, true, func(ctx context.Context) (bool, error) {
// Lookup the Informer from the Cache and add an EventHandler which populates the Queue
i, lastErr = ks.Cache.GetInformer(ctx, ks.Type)
if lastErr != nil {
kindMatchErr := &meta.NoKindMatchError{}
switch {
case errors.As(lastErr, &kindMatchErr):
logKind.Error(lastErr, "if kind is a CRD, it should be installed before calling Start",
"kind", kindMatchErr.GroupKind)
case runtime.IsNotRegisteredError(lastErr):
logKind.Error(lastErr, "kind must be registered to the Scheme")
default:
logKind.Error(lastErr, "failed to get informer from cache")
}
return false, nil // Retry.
}
return true, nil
}); err != nil {
if lastErr != nil {
ks.startedErr <- fmt.Errorf("failed to get informer from cache: %w", lastErr)
return
}
ks.startedErr <- err
return
}
handlerRegistration, err := i.AddEventHandlerWithOptions(NewEventHandler(ctx, queue, ks.Handler, ks.Predicates), toolscache.HandlerOptions{
Logger: &logKind,
})
if err != nil {
ks.startedErr <- err
return
}
// First, wait for the cache to sync. For real caches this waits for startup.
// For fakes with Synced=false, this returns immediately allowing fast failure.
if !ks.Cache.WaitForCacheSync(ctx) {
ks.startedErr <- errors.New("cache did not sync")
close(ks.startedErr)
return
}
// Then wait for this specific handler to receive all initial events.
if !toolscache.WaitForCacheSync(ctx.Done(), handlerRegistration.HasSynced) {
ks.startedErr <- errors.New("handler did not sync")
}
close(ks.startedErr)
}()
return nil
}
func (ks *Kind[object, request]) String() string {
if !isNil(ks.Type) {
return fmt.Sprintf("kind source: %T", ks.Type)
}
return "kind source: unknown type"
}
// WaitForSync implements SyncingSource to allow controllers to wait with starting
// workers until the cache is synced.
func (ks *Kind[object, request]) WaitForSync(ctx context.Context) error {
select {
case err := <-ks.startedErr:
return err
case <-ctx.Done():
ks.startCancel()
if errors.Is(ctx.Err(), context.Canceled) {
return nil
}
return fmt.Errorf("timed out waiting for cache to be synced for Kind %T", ks.Type)
}
}
func isNil(arg any) bool {
if v := reflect.ValueOf(arg); !v.IsValid() || ((v.Kind() == reflect.Ptr ||
v.Kind() == reflect.Interface ||
v.Kind() == reflect.Slice ||
v.Kind() == reflect.Map ||
v.Kind() == reflect.Chan ||
v.Kind() == reflect.Func) && v.IsNil()) {
return true
}
return false
}