Implement the Repo maintanence Job configuration design.

Remove the resource parameters from the velero server CLI.

Signed-off-by: Xun Jiang <[email protected]>

changelogs/unreleased/8145-blackpiglet

@@ -0,0 +1 @@
+Implement the Repo maintenance Job configuration.

design/repo_maintenance_job_config.md

@@ -49,8 +49,6 @@ velero server \
 ### Structure
 The data structure for ```repo-maintenance-job-config``` is as below:
 ```go
-type MaintenanceConfigMap map[string]Configs
-
 type Configs struct {
     // LoadAffinity is the config for data path load affinity.
     LoadAffinity []*LoadAffinity `json:"loadAffinity,omitempty"`    
@@ -80,15 +78,19 @@ type Resources struct {
 ```
 
 The ConfigMap content is a map.
-If there is a key value as `global` in the map, the key's value is applied to all BackupRepositories maintenance jobs that don't their own specific configuration in the ConfigMap.
+If there is a key value as `global` in the map, the key's value is applied to all BackupRepositories maintenance jobs that cannot find their own specific configuration in the ConfigMap.
 The other keys in the map is the combination of three elements of a BackupRepository:
-* The namespace in which BackupRepository backs up volume data
-* The BackupRepository referenced BackupStorageLocation's name
-* The BackupRepository's type. Possible values are `kopia` and `restic`
+* The namespace in which BackupRepository backs up volume data.
+* The BackupRepository referenced BackupStorageLocation's name.
+* The BackupRepository's type. Possible values are `kopia` and `restic`.
+
+Those three keys can identify a [unique BackupRepository](https://github.com/vmware-tanzu/velero/blob/2fc6300f2239f250b40b0488c35feae59520f2d3/pkg/repository/backup_repo_op.go#L32-L37).
+
 If there is a key match with BackupRepository, the key's value is applied to the BackupRepository's maintenance jobs.
 By this way, it's possible to let user configure before the BackupRepository is created.
 This is especially convenient for administrator configuring during the Velero installation.
-For example, the following BackupRepository's key should be `test-default-kopia`
+For example, the following BackupRepository's key should be `test-default-kopia`.
+
 ``` yaml
 - apiVersion: velero.io/v1
   kind: BackupRepository

pkg/cmd/cli/install/install.go

@@ -23,7 +23,6 @@ import (
 	"strings"
 	"time"
 
-	"github.com/vmware-tanzu/velero/pkg/repository"
 	"github.com/vmware-tanzu/velero/pkg/uploader"
 
 	"github.com/pkg/errors"
@@ -85,7 +84,6 @@ type Options struct {
 	DefaultSnapshotMoveData         bool
 	DisableInformerCache            bool
 	ScheduleSkipImmediately         bool
-	MaintenanceCfg                  repository.MaintenanceConfig
 }
 
 // BindFlags adds command line values to the options struct.
@@ -130,11 +128,6 @@ func (o *Options) BindFlags(flags *pflag.FlagSet) {
 	flags.BoolVar(&o.DefaultSnapshotMoveData, "default-snapshot-move-data", o.DefaultSnapshotMoveData, "Bool flag to configure Velero server to move data by default for all snapshots supporting data movement. Optional.")
 	flags.BoolVar(&o.DisableInformerCache, "disable-informer-cache", o.DisableInformerCache, "Disable informer cache for Get calls on restore. With this enabled, it will speed up restore in cases where there are backup resources which already exist in the cluster, but for very large clusters this will increase velero memory usage. Default is false (don't disable). Optional.")
 	flags.BoolVar(&o.ScheduleSkipImmediately, "schedule-skip-immediately", o.ScheduleSkipImmediately, "Skip the first scheduled backup immediately after creating a schedule. Default is false (don't skip).")
-	flags.IntVar(&o.MaintenanceCfg.KeepLatestMaitenanceJobs, "keep-latest-maintenance-jobs", o.MaintenanceCfg.KeepLatestMaitenanceJobs, "Number of latest maintenance jobs to keep each repository. Optional.")
-	flags.StringVar(&o.MaintenanceCfg.CPURequest, "maintenance-job-cpu-request", o.MaintenanceCfg.CPURequest, "CPU request for maintenance jobs. Default is no limit.")
-	flags.StringVar(&o.MaintenanceCfg.MemRequest, "maintenance-job-mem-request", o.MaintenanceCfg.MemRequest, "Memory request for maintenance jobs. Default is no limit.")
-	flags.StringVar(&o.MaintenanceCfg.CPULimit, "maintenance-job-cpu-limit", o.MaintenanceCfg.CPULimit, "CPU limit for maintenance jobs. Default is no limit.")
-	flags.StringVar(&o.MaintenanceCfg.MemLimit, "maintenance-job-mem-limit", o.MaintenanceCfg.MemLimit, "Memory limit for maintenance jobs. Default is no limit.")
 }
 
 // NewInstallOptions instantiates a new, default InstallOptions struct.
@@ -231,7 +224,6 @@ func (o *Options) AsVeleroOptions() (*install.VeleroOptions, error) {
 		DefaultSnapshotMoveData:         o.DefaultSnapshotMoveData,
 		DisableInformerCache:            o.DisableInformerCache,
 		ScheduleSkipImmediately:         o.ScheduleSkipImmediately,
-		MaintenanceCfg:                  o.MaintenanceCfg,
 	}, nil
 }
 

pkg/cmd/cli/nodeagent/server.go

@@ -59,6 +59,7 @@ import (
 	"github.com/vmware-tanzu/velero/pkg/metrics"
 	"github.com/vmware-tanzu/velero/pkg/nodeagent"
 	"github.com/vmware-tanzu/velero/pkg/repository"
+	velerotypes "github.com/vmware-tanzu/velero/pkg/types"
 	"github.com/vmware-tanzu/velero/pkg/util/filesystem"
 	"github.com/vmware-tanzu/velero/pkg/util/logging"
 
@@ -292,7 +293,7 @@ func (s *nodeAgentServer) run() {
 		s.logger.WithError(err).Fatal("Unable to create the pod volume restore controller")
 	}
 
-	var loadAffinity *nodeagent.LoadAffinity
+	var loadAffinity *velerotypes.LoadAffinity
 	if s.dataPathConfigs != nil && len(s.dataPathConfigs.LoadAffinity) > 0 {
 		loadAffinity = s.dataPathConfigs.LoadAffinity[0]
 	}
@@ -302,7 +303,20 @@ func (s *nodeAgentServer) run() {
 		backupPVCConfig = s.dataPathConfigs.BackupPVCConfig
 	}
 
-	dataUploadReconciler := controller.NewDataUploadReconciler(s.mgr.GetClient(), s.mgr, s.kubeClient, s.csiSnapshotClient.SnapshotV1(), s.dataPathMgr, loadAffinity, backupPVCConfig, clock.RealClock{}, s.nodeName, s.config.dataMoverPrepareTimeout, s.logger, s.metrics)
+	dataUploadReconciler := controller.NewDataUploadReconciler(
+		s.mgr.GetClient(),
+		s.mgr,
+		s.kubeClient,
+		s.csiSnapshotClient.SnapshotV1(),
+		s.dataPathMgr,
+		loadAffinity,
+		backupPVCConfig,
+		clock.RealClock{},
+		s.nodeName,
+		s.config.dataMoverPrepareTimeout,
+		s.logger,
+		s.metrics,
+	)
 	if err = dataUploadReconciler.SetupWithManager(s.mgr); err != nil {
 		s.logger.WithError(err).Fatal("Unable to create the data upload controller")
 	}

pkg/cmd/server/server.go

@@ -139,8 +139,8 @@ type serverConfig struct {
 	defaultSnapshotMoveData                                                 bool
 	disableInformerCache                                                    bool
 	scheduleSkipImmediately                                                 bool
-	maintenanceCfg                                                          repository.MaintenanceConfig
-	backukpRepoConfig                                                       string
+	backupRepoConfig                                                        string
+	repoMaintenanceJobConfig                                                string
 }
 
 func NewCommand(f client.Factory) *cobra.Command {
@@ -172,9 +172,6 @@ func NewCommand(f client.Factory) *cobra.Command {
 			defaultSnapshotMoveData:        false,
 			disableInformerCache:           defaultDisableInformerCache,
 			scheduleSkipImmediately:        false,
-			maintenanceCfg: repository.MaintenanceConfig{
-				KeepLatestMaitenanceJobs: repository.DefaultKeepLatestMaitenanceJobs,
-			},
 		}
 	)
 
@@ -248,17 +245,20 @@ func NewCommand(f client.Factory) *cobra.Command {
 	command.Flags().BoolVar(&config.defaultSnapshotMoveData, "default-snapshot-move-data", config.defaultSnapshotMoveData, "Move data by default for all snapshots supporting data movement.")
 	command.Flags().BoolVar(&config.disableInformerCache, "disable-informer-cache", config.disableInformerCache, "Disable informer cache for Get calls on restore. With this enabled, it will speed up restore in cases where there are backup resources which already exist in the cluster, but for very large clusters this will increase velero memory usage. Default is false (don't disable).")
 	command.Flags().BoolVar(&config.scheduleSkipImmediately, "schedule-skip-immediately", config.scheduleSkipImmediately, "Skip the first scheduled backup immediately after creating a schedule. Default is false (don't skip).")
-	command.Flags().IntVar(&config.maintenanceCfg.KeepLatestMaitenanceJobs, "keep-latest-maintenance-jobs", config.maintenanceCfg.KeepLatestMaitenanceJobs, "Number of latest maintenance jobs to keep each repository. Optional.")
-	command.Flags().StringVar(&config.maintenanceCfg.CPURequest, "maintenance-job-cpu-request", config.maintenanceCfg.CPURequest, "CPU request for maintenance job. Default is no limit.")
-	command.Flags().StringVar(&config.maintenanceCfg.MemRequest, "maintenance-job-mem-request", config.maintenanceCfg.MemRequest, "Memory request for maintenance job. Default is no limit.")
-	command.Flags().StringVar(&config.maintenanceCfg.CPULimit, "maintenance-job-cpu-limit", config.maintenanceCfg.CPULimit, "CPU limit for maintenance job. Default is no limit.")
-	command.Flags().StringVar(&config.maintenanceCfg.MemLimit, "maintenance-job-mem-limit", config.maintenanceCfg.MemLimit, "Memory limit for maintenance job. Default is no limit.")
 
-	command.Flags().StringVar(&config.backukpRepoConfig, "backup-repository-config", config.backukpRepoConfig, "The name of configMap containing backup repository configurations.")
+	command.Flags().StringVar(
+		&config.backupRepoConfig,
+		"backup-repository-config",
+		config.backupRepoConfig,
+		"The name of configMap containing backup repository configurations.",
+	)
+	command.Flags().StringVar(
+		&config.repoMaintenanceJobConfig,
+		"repo-maintenance-job-config",
+		config.repoMaintenanceJobConfig,
+		"The name of ConfigMap containing repository maintenance Job configurations.",
+	)
 
-	// maintenance job log setting inherited from velero server
-	config.maintenanceCfg.FormatFlag = config.formatFlag
-	config.maintenanceCfg.LogLevelFlag = logLevelFlag
 	return command
 }
 
@@ -667,7 +667,18 @@ func (s *server) initRepoManager() error {
 	s.repoLocker = repository.NewRepoLocker()
 	s.repoEnsurer = repository.NewEnsurer(s.mgr.GetClient(), s.logger, s.config.resourceTimeout)
 
-	s.repoManager = repository.NewManager(s.namespace, s.mgr.GetClient(), s.repoLocker, s.repoEnsurer, s.credentialFileStore, s.credentialSecretStore, s.config.maintenanceCfg, s.logger)
+	s.repoManager = repository.NewManager(
+		s.namespace,
+		s.mgr.GetClient(),
+		s.repoLocker,
+		s.repoEnsurer,
+		s.credentialFileStore,
+		s.credentialSecretStore,
+		s.config.repoMaintenanceJobConfig,
+		s.logger,
+		s.logLevel,
+		s.config.formatFlag,
+	)
 
 	return nil
 }
@@ -881,7 +892,14 @@ func (s *server) runControllers(defaultVolumeSnapshotLocations map[string]string
 	}
 
 	if _, ok := enabledRuntimeControllers[controller.BackupRepo]; ok {
-		if err := controller.NewBackupRepoReconciler(s.namespace, s.logger, s.mgr.GetClient(), s.config.repoMaintenanceFrequency, s.config.backukpRepoConfig, s.repoManager).SetupWithManager(s.mgr); err != nil {
+		if err := controller.NewBackupRepoReconciler(
+			s.namespace,
+			s.logger,
+			s.mgr.GetClient(),
+			s.config.repoMaintenanceFrequency,
+			s.config.backupRepoConfig,
+			s.repoManager,
+		).SetupWithManager(s.mgr); err != nil {
 			s.logger.Fatal(err, "unable to create controller", "controller", controller.BackupRepo)
 		}
 	}

pkg/controller/backup_repository_controller.go

@@ -55,19 +55,19 @@ type BackupRepoReconciler struct {
 	logger               logrus.FieldLogger
 	clock                clocks.WithTickerAndDelayedExecution
 	maintenanceFrequency time.Duration
-	backukpRepoConfig    string
+	backupRepoConfig     string
 	repositoryManager    repository.Manager
 }
 
 func NewBackupRepoReconciler(namespace string, logger logrus.FieldLogger, client client.Client,
-	maintenanceFrequency time.Duration, backukpRepoConfig string, repositoryManager repository.Manager) *BackupRepoReconciler {
+	maintenanceFrequency time.Duration, backupRepoConfig string, repositoryManager repository.Manager) *BackupRepoReconciler {
 	c := &BackupRepoReconciler{
 		client,
 		namespace,
 		logger,
 		clocks.RealClock{},
 		maintenanceFrequency,
-		backukpRepoConfig,
+		backupRepoConfig,
 		repositoryManager,
 	}
 
@@ -229,7 +229,7 @@ func (r *BackupRepoReconciler) getIdentiferByBSL(ctx context.Context, req *veler
 }
 
 func (r *BackupRepoReconciler) initializeRepo(ctx context.Context, req *velerov1api.BackupRepository, log logrus.FieldLogger) error {
-	log.WithField("repoConfig", r.backukpRepoConfig).Info("Initializing backup repository")
+	log.WithField("repoConfig", r.backupRepoConfig).Info("Initializing backup repository")
 
 	// confirm the repo's BackupStorageLocation is valid
 	repoIdentifier, err := r.getIdentiferByBSL(ctx, req)
@@ -244,7 +244,7 @@ func (r *BackupRepoReconciler) initializeRepo(ctx context.Context, req *velerov1
 		})
 	}
 
-	config, err := getBackupRepositoryConfig(ctx, r, r.backukpRepoConfig, r.namespace, req.Name, req.Spec.RepositoryType, log)
+	config, err := getBackupRepositoryConfig(ctx, r, r.backupRepoConfig, r.namespace, req.Name, req.Spec.RepositoryType, log)
 	if err != nil {
 		log.WithError(err).Warn("Failed to get repo config, repo config is ignored")
 	} else if config != nil {

pkg/controller/data_upload_controller.go

@@ -21,6 +21,7 @@ import (
 	"fmt"
 	"time"
 
+	snapshotter "github.com/kubernetes-csi/external-snapshotter/client/v7/clientset/versioned/typed/volumesnapshot/v1"
 	"github.com/pkg/errors"
 	"github.com/sirupsen/logrus"
 	corev1 "k8s.io/api/core/v1"
@@ -39,8 +40,6 @@ import (
 	"sigs.k8s.io/controller-runtime/pkg/predicate"
 	"sigs.k8s.io/controller-runtime/pkg/reconcile"
 
-	snapshotter "github.com/kubernetes-csi/external-snapshotter/client/v7/clientset/versioned/typed/volumesnapshot/v1"
-
 	"github.com/vmware-tanzu/velero/pkg/apis/velero/shared"
 	velerov1api "github.com/vmware-tanzu/velero/pkg/apis/velero/v1"
 	velerov2alpha1api "github.com/vmware-tanzu/velero/pkg/apis/velero/v2alpha1"
@@ -49,6 +48,7 @@ import (
 	"github.com/vmware-tanzu/velero/pkg/exposer"
 	"github.com/vmware-tanzu/velero/pkg/metrics"
 	"github.com/vmware-tanzu/velero/pkg/nodeagent"
+	velerotypes "github.com/vmware-tanzu/velero/pkg/types"
 	"github.com/vmware-tanzu/velero/pkg/uploader"
 	"github.com/vmware-tanzu/velero/pkg/util/kube"
 )
@@ -71,15 +71,26 @@ type DataUploadReconciler struct {
 	logger              logrus.FieldLogger
 	snapshotExposerList map[velerov2alpha1api.SnapshotType]exposer.SnapshotExposer
 	dataPathMgr         *datapath.Manager
-	loadAffinity        *nodeagent.LoadAffinity
+	loadAffinity        *velerotypes.LoadAffinity
 	backupPVCConfig     map[string]nodeagent.BackupPVC
 	preparingTimeout    time.Duration
 	metrics             *metrics.ServerMetrics
 }
 
-func NewDataUploadReconciler(client client.Client, mgr manager.Manager, kubeClient kubernetes.Interface, csiSnapshotClient snapshotter.SnapshotV1Interface,
-	dataPathMgr *datapath.Manager, loadAffinity *nodeagent.LoadAffinity, backupPVCConfig map[string]nodeagent.BackupPVC, clock clocks.WithTickerAndDelayedExecution,
-	nodeName string, preparingTimeout time.Duration, log logrus.FieldLogger, metrics *metrics.ServerMetrics) *DataUploadReconciler {
+func NewDataUploadReconciler(
+	client client.Client,
+	mgr manager.Manager,
+	kubeClient kubernetes.Interface,
+	csiSnapshotClient snapshotter.SnapshotV1Interface,
+	dataPathMgr *datapath.Manager,
+	loadAffinity *velerotypes.LoadAffinity,
+	backupPVCConfig map[string]nodeagent.BackupPVC,
+	clock clocks.WithTickerAndDelayedExecution,
+	nodeName string,
+	preparingTimeout time.Duration,
+	log logrus.FieldLogger,
+	metrics *metrics.ServerMetrics,
+) *DataUploadReconciler {
 	return &DataUploadReconciler{
 		client:              client,
 		mgr:                 mgr,

pkg/controller/data_upload_controller_test.go

@@ -231,8 +231,20 @@ func initDataUploaderReconcilerWithError(needError ...error) (*DataUploadReconci
 	fakeSnapshotClient := snapshotFake.NewSimpleClientset(vsObject, vscObj)
 	fakeKubeClient := clientgofake.NewSimpleClientset(daemonSet)
 
-	return NewDataUploadReconciler(fakeClient, nil, fakeKubeClient, fakeSnapshotClient.SnapshotV1(), dataPathMgr, nil, map[string]nodeagent.BackupPVC{},
-		testclocks.NewFakeClock(now), "test-node", time.Minute*5, velerotest.NewLogger(), metrics.NewServerMetrics()), nil
+	return NewDataUploadReconciler(
+		fakeClient,
+		nil,
+		fakeKubeClient,
+		fakeSnapshotClient.SnapshotV1(),
+		dataPathMgr,
+		nil,
+		map[string]nodeagent.BackupPVC{},
+		testclocks.NewFakeClock(now),
+		"test-node",
+		time.Minute*5,
+		velerotest.NewLogger(),
+		metrics.NewServerMetrics(),
+	), nil
 }
 
 func dataUploadBuilder() *builder.DataUploadBuilder {