diff --git a/changelogs/unreleased/8145-blackpiglet b/changelogs/unreleased/8145-blackpiglet new file mode 100644 index 00000000000..6e64442bc94 --- /dev/null +++ b/changelogs/unreleased/8145-blackpiglet @@ -0,0 +1 @@ +Implement the Repo maintenance Job configuration. diff --git a/design/repo_maintenance_job_config.md b/design/repo_maintenance_job_config.md index ad055795de6..998cb4e2c88 100644 --- a/design/repo_maintenance_job_config.md +++ b/design/repo_maintenance_job_config.md @@ -1,7 +1,7 @@ # Repository maintenance job configuration design ## Abstract -Add this design to make the repository maintenance job can read configuration from a dedicate ConfigMap and make the Job's necessary parts configurable, e.g. `PodSpec.Affinity` and `PodSpec.resources`. +Add this design to make the repository maintenance job can read configuration from a dedicate ConfigMap and make the Job's necessary parts configurable, e.g. `PodSpec.Affinity` and `PodSpec.Resources`. ## Background Repository maintenance is split from the Velero server to a k8s Job in v1.14 by design [repository maintenance job](Implemented/repository-maintenance.md). @@ -49,14 +49,12 @@ 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"` - // Resources is the config for the CPU and memory resources setting. - Resource Resources `json:"resources,omitempty"` + // PodResources is the config for the CPU and memory resources setting. + PodResources *kube.PodResources `json:"podResources,omitempty"` } type LoadAffinity struct { @@ -64,31 +62,28 @@ type LoadAffinity struct { NodeSelector metav1.LabelSelector `json:"nodeSelector"` } -type Resources struct { - // The repository maintenance job CPU request setting - CPURequest string `json:"cpuRequest,omitempty"` - - // The repository maintenance job memory request setting - MemRequest string `json:"memRequest,omitempty"` - - // The repository maintenance job CPU limit setting - CPULimit string `json:"cpuLimit,omitempty"` - - // The repository maintenance job memory limit setting - MemLimit string `json:"memLimit,omitempty"` +type PodResources struct { + CPURequest string `json:"cpuRequest,omitempty"` + MemoryRequest string `json:"memoryRequest,omitempty"` + CPULimit string `json:"cpuLimit,omitempty"` + MemoryLimit string `json:"memoryLimit,omitempty"` } ``` 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 @@ -119,11 +114,11 @@ A sample of the ```repo-maintenance-job-config``` ConfigMap is as below: cat < repo-maintenance-job-config.json { "global": { - resources: { + podResources: { "cpuRequest": "100m", "cpuLimit": "200m", - "memRequest": "100Mi", - "memLimit": "200Mi" + "memoryRequest": "100Mi", + "memoryLimit": "200Mi" }, "loadAffinity": [ { @@ -177,18 +172,18 @@ config := Configs { LoadAffinity: nil, // Resources is the config for the CPU and memory resources setting. - Resources: Resources{ + PodResources: &kube.PodResources{ // The repository maintenance job CPU request setting CPURequest: "0m", // The repository maintenance job memory request setting - MemRequest: "0Mi", + MemoryRequest: "0Mi", // The repository maintenance job CPU limit setting CPULimit: "0m", // The repository maintenance job memory limit setting - MemLimit: "0Mi", + MemoryLimit: "0Mi", }, } ``` @@ -204,17 +199,32 @@ For example, the ConfigMap content has two elements. ``` json { "global": { - "resources": { + "loadAffinity": [ + { + "nodeSelector": { + "matchExpressions": [ + { + "key": "cloud.google.com/machine-family", + "operator": "In", + "values": [ + "e2" + ] + } + ] + } + }, + ], + "podResources": { "cpuRequest": "100m", "cpuLimit": "200m", - "memRequest": "100Mi", - "memLimit": "200Mi" + "memoryRequest": "100Mi", + "memoryLimit": "200Mi" } }, "ns1-default-kopia": { - "resources": { - "memRequest": "400Mi", - "memLimit": "800Mi" + "podResources": { + "memoryRequest": "400Mi", + "memoryLimit": "800Mi" } } } @@ -223,19 +233,29 @@ The config value used for BackupRepository backing up volume data in namespace ` ``` go config := Configs { // LoadAffinity is the config for data path load affinity. - LoadAffinity: nil, - - // The repository maintenance job CPU request setting - CPURequest: "100m", - - // The repository maintenance job memory request setting - MemRequest: "400Mi", - - // The repository maintenance job CPU limit setting - CPULimit: "200m", - - // The repository maintenance job memory limit setting - MemLimit: "800Mi", + LoadAffinity: []*kube.LoadAffinity{ + { + NodeSelector: metav1.LabelSelector{ + MatchExpressions: []metav1.LabelSelectorRequirement{ + { + Key: "cloud.google.com/machine-family", + Operator: metav1.LabelSelectorOpIn, + Values: []string{"e2"}, + }, + }, + }, + }, + }, + PodResources: &kube.PodResources{ + // The repository maintenance job CPU request setting + CPURequest: "", + // The repository maintenance job memory request setting + MemoryRequest: "400Mi", + // The repository maintenance job CPU limit setting + CPULimit: "", + // The repository maintenance job memory limit setting + MemoryLimit: "800Mi", + } } ``` diff --git a/pkg/cmd/cli/install/install.go b/pkg/cmd/cli/install/install.go index b73438e78aa..39fd727b4fa 100644 --- a/pkg/cmd/cli/install/install.go +++ b/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 } diff --git a/pkg/cmd/cli/nodeagent/server.go b/pkg/cmd/cli/nodeagent/server.go index 7365c4e8c40..a4fdd8ba15c 100644 --- a/pkg/cmd/cli/nodeagent/server.go +++ b/pkg/cmd/cli/nodeagent/server.go @@ -293,7 +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 *kube.LoadAffinity if s.dataPathConfigs != nil && len(s.dataPathConfigs.LoadAffinity) > 0 { loadAffinity = s.dataPathConfigs.LoadAffinity[0] s.logger.Infof("Using customized loadAffinity %v", loadAffinity) @@ -315,7 +315,21 @@ func (s *nodeAgentServer) run() { } } - dataUploadReconciler := controller.NewDataUploadReconciler(s.mgr.GetClient(), s.mgr, s.kubeClient, s.csiSnapshotClient.SnapshotV1(), s.dataPathMgr, loadAffinity, backupPVCConfig, podResources, 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, + podResources, + 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") } diff --git a/pkg/cmd/server/server.go b/pkg/cmd/server/server.go index 3a2b0702433..f7d2d9c5a16 100644 --- a/pkg/cmd/server/server.go +++ b/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) } } diff --git a/pkg/controller/backup_repository_controller.go b/pkg/controller/backup_repository_controller.go index 0bc457a1727..4ec0e4e800e 100644 --- a/pkg/controller/backup_repository_controller.go +++ b/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 { diff --git a/pkg/controller/data_upload_controller.go b/pkg/controller/data_upload_controller.go index 5b3169621f1..3ba33772d8d 100644 --- a/pkg/controller/data_upload_controller.go +++ b/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" @@ -71,31 +70,49 @@ type DataUploadReconciler struct { logger logrus.FieldLogger snapshotExposerList map[velerov2alpha1api.SnapshotType]exposer.SnapshotExposer dataPathMgr *datapath.Manager - loadAffinity *nodeagent.LoadAffinity + loadAffinity *kube.LoadAffinity backupPVCConfig map[string]nodeagent.BackupPVC podResources corev1.ResourceRequirements 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, podResources corev1.ResourceRequirements, - 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 *kube.LoadAffinity, + backupPVCConfig map[string]nodeagent.BackupPVC, + podResources corev1.ResourceRequirements, + clock clocks.WithTickerAndDelayedExecution, + nodeName string, + preparingTimeout time.Duration, + log logrus.FieldLogger, + metrics *metrics.ServerMetrics, +) *DataUploadReconciler { return &DataUploadReconciler{ - client: client, - mgr: mgr, - kubeClient: kubeClient, - csiSnapshotClient: csiSnapshotClient, - Clock: clock, - nodeName: nodeName, - logger: log, - snapshotExposerList: map[velerov2alpha1api.SnapshotType]exposer.SnapshotExposer{velerov2alpha1api.SnapshotTypeCSI: exposer.NewCSISnapshotExposer(kubeClient, csiSnapshotClient, log)}, - dataPathMgr: dataPathMgr, - loadAffinity: loadAffinity, - backupPVCConfig: backupPVCConfig, - podResources: podResources, - preparingTimeout: preparingTimeout, - metrics: metrics, + client: client, + mgr: mgr, + kubeClient: kubeClient, + csiSnapshotClient: csiSnapshotClient, + Clock: clock, + nodeName: nodeName, + logger: log, + snapshotExposerList: map[velerov2alpha1api.SnapshotType]exposer.SnapshotExposer{ + velerov2alpha1api.SnapshotTypeCSI: exposer.NewCSISnapshotExposer( + kubeClient, + csiSnapshotClient, + log, + ), + }, + dataPathMgr: dataPathMgr, + loadAffinity: loadAffinity, + backupPVCConfig: backupPVCConfig, + podResources: podResources, + preparingTimeout: preparingTimeout, + metrics: metrics, } } diff --git a/pkg/controller/data_upload_controller_test.go b/pkg/controller/data_upload_controller_test.go index 5de53c10035..ac618655524 100644 --- a/pkg/controller/data_upload_controller_test.go +++ b/pkg/controller/data_upload_controller_test.go @@ -231,8 +231,21 @@ 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{}, - corev1.ResourceRequirements{}, 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{}, + corev1.ResourceRequirements{}, + testclocks.NewFakeClock(now), + "test-node", + time.Minute*5, + velerotest.NewLogger(), + metrics.NewServerMetrics(), + ), nil } func dataUploadBuilder() *builder.DataUploadBuilder { diff --git a/pkg/exposer/csi_snapshot.go b/pkg/exposer/csi_snapshot.go index da31a8f662a..4dcc50d1291 100644 --- a/pkg/exposer/csi_snapshot.go +++ b/pkg/exposer/csi_snapshot.go @@ -66,7 +66,7 @@ type CSISnapshotExposeParam struct { VolumeSize resource.Quantity // Affinity specifies the node affinity of the backup pod - Affinity *nodeagent.LoadAffinity + Affinity *kube.LoadAffinity // BackupPVCConfig is the config for backupPVC (intermediate PVC) of snapshot data movement BackupPVCConfig map[string]nodeagent.BackupPVC @@ -194,7 +194,15 @@ func (e *csiSnapshotExposer) Expose(ctx context.Context, ownerObject corev1.Obje } }() - backupPod, err := e.createBackupPod(ctx, ownerObject, backupPVC, csiExposeParam.OperationTimeout, csiExposeParam.HostingPodLabels, csiExposeParam.Affinity, csiExposeParam.Resources) + backupPod, err := e.createBackupPod( + ctx, + ownerObject, + backupPVC, + csiExposeParam.OperationTimeout, + csiExposeParam.HostingPodLabels, + csiExposeParam.Affinity, + csiExposeParam.Resources, + ) if err != nil { return errors.Wrap(err, "error to create backup pod") } @@ -425,8 +433,15 @@ func (e *csiSnapshotExposer) createBackupPVC(ctx context.Context, ownerObject co return created, err } -func (e *csiSnapshotExposer) createBackupPod(ctx context.Context, ownerObject corev1.ObjectReference, backupPVC *corev1.PersistentVolumeClaim, operationTimeout time.Duration, - label map[string]string, affinity *nodeagent.LoadAffinity, resources corev1.ResourceRequirements) (*corev1.Pod, error) { +func (e *csiSnapshotExposer) createBackupPod( + ctx context.Context, + ownerObject corev1.ObjectReference, + backupPVC *corev1.PersistentVolumeClaim, + operationTimeout time.Duration, + label map[string]string, + affinity *kube.LoadAffinity, + resources corev1.ResourceRequirements, +) (*corev1.Pod, error) { podName := ownerObject.Name containerName := string(ownerObject.UID) @@ -474,6 +489,11 @@ func (e *csiSnapshotExposer) createBackupPod(ctx context.Context, ownerObject co userID := int64(0) + affinityList := make([]*kube.LoadAffinity, 0) + if affinity != nil { + affinityList = append(affinityList, affinity) + } + pod := &corev1.Pod{ ObjectMeta: metav1.ObjectMeta{ Name: podName, @@ -502,7 +522,7 @@ func (e *csiSnapshotExposer) createBackupPod(ctx context.Context, ownerObject co }, }, }, - Affinity: toSystemAffinity(affinity), + Affinity: kube.ToSystemAffinity(affinityList), Containers: []corev1.Container{ { Name: containerName, @@ -532,42 +552,3 @@ func (e *csiSnapshotExposer) createBackupPod(ctx context.Context, ownerObject co return e.kubeClient.CoreV1().Pods(ownerObject.Namespace).Create(ctx, pod, metav1.CreateOptions{}) } - -func toSystemAffinity(loadAffinity *nodeagent.LoadAffinity) *corev1.Affinity { - if loadAffinity == nil { - return nil - } - - requirements := []corev1.NodeSelectorRequirement{} - for k, v := range loadAffinity.NodeSelector.MatchLabels { - requirements = append(requirements, corev1.NodeSelectorRequirement{ - Key: k, - Values: []string{v}, - Operator: corev1.NodeSelectorOpIn, - }) - } - - for _, exp := range loadAffinity.NodeSelector.MatchExpressions { - requirements = append(requirements, corev1.NodeSelectorRequirement{ - Key: exp.Key, - Values: exp.Values, - Operator: corev1.NodeSelectorOperator(exp.Operator), - }) - } - - if len(requirements) == 0 { - return nil - } - - return &corev1.Affinity{ - NodeAffinity: &corev1.NodeAffinity{ - RequiredDuringSchedulingIgnoredDuringExecution: &corev1.NodeSelector{ - NodeSelectorTerms: []corev1.NodeSelectorTerm{ - { - MatchExpressions: requirements, - }, - }, - }, - }, - } -} diff --git a/pkg/exposer/csi_snapshot_test.go b/pkg/exposer/csi_snapshot_test.go index afde0b7f072..0cbe65ffb49 100644 --- a/pkg/exposer/csi_snapshot_test.go +++ b/pkg/exposer/csi_snapshot_test.go @@ -19,31 +19,27 @@ package exposer import ( "context" "fmt" - "reflect" "testing" "time" - "k8s.io/utils/pointer" - snapshotv1api "github.com/kubernetes-csi/external-snapshotter/client/v7/apis/volumesnapshot/v1" snapshotFake "github.com/kubernetes-csi/external-snapshotter/client/v7/clientset/versioned/fake" "github.com/pkg/errors" "github.com/stretchr/testify/assert" + appsv1 "k8s.io/api/apps/v1" + corev1 "k8s.io/api/core/v1" "k8s.io/apimachinery/pkg/api/resource" metav1 "k8s.io/apimachinery/pkg/apis/meta/v1" "k8s.io/apimachinery/pkg/runtime" "k8s.io/client-go/kubernetes/fake" clientTesting "k8s.io/client-go/testing" - - appsv1 "k8s.io/api/apps/v1" - corev1 "k8s.io/api/core/v1" + "k8s.io/utils/pointer" + clientFake "sigs.k8s.io/controller-runtime/pkg/client/fake" velerov1 "github.com/vmware-tanzu/velero/pkg/apis/velero/v1" "github.com/vmware-tanzu/velero/pkg/nodeagent" velerotest "github.com/vmware-tanzu/velero/pkg/test" "github.com/vmware-tanzu/velero/pkg/util/boolptr" - - clientFake "sigs.k8s.io/controller-runtime/pkg/client/fake" ) type reactor struct { @@ -820,105 +816,6 @@ func TestPeekExpose(t *testing.T) { } } -func TestToSystemAffinity(t *testing.T) { - tests := []struct { - name string - loadAffinity *nodeagent.LoadAffinity - expected *corev1.Affinity - }{ - { - name: "loadAffinity is nil", - }, - { - name: "loadAffinity is empty", - loadAffinity: &nodeagent.LoadAffinity{}, - }, - { - name: "with match label", - loadAffinity: &nodeagent.LoadAffinity{ - NodeSelector: metav1.LabelSelector{ - MatchLabels: map[string]string{ - "key-1": "value-1", - }, - }, - }, - expected: &corev1.Affinity{ - NodeAffinity: &corev1.NodeAffinity{ - RequiredDuringSchedulingIgnoredDuringExecution: &corev1.NodeSelector{ - NodeSelectorTerms: []corev1.NodeSelectorTerm{ - { - MatchExpressions: []corev1.NodeSelectorRequirement{ - { - Key: "key-1", - Values: []string{"value-1"}, - Operator: corev1.NodeSelectorOpIn, - }, - }, - }, - }, - }, - }, - }, - }, - { - name: "with match expression", - loadAffinity: &nodeagent.LoadAffinity{ - NodeSelector: metav1.LabelSelector{ - MatchLabels: map[string]string{ - "key-2": "value-2", - }, - MatchExpressions: []metav1.LabelSelectorRequirement{ - { - Key: "key-3", - Values: []string{"value-3-1", "value-3-2"}, - Operator: metav1.LabelSelectorOpNotIn, - }, - { - Key: "key-4", - Values: []string{"value-4-1", "value-4-2", "value-4-3"}, - Operator: metav1.LabelSelectorOpDoesNotExist, - }, - }, - }, - }, - expected: &corev1.Affinity{ - NodeAffinity: &corev1.NodeAffinity{ - RequiredDuringSchedulingIgnoredDuringExecution: &corev1.NodeSelector{ - NodeSelectorTerms: []corev1.NodeSelectorTerm{ - { - MatchExpressions: []corev1.NodeSelectorRequirement{ - { - Key: "key-2", - Values: []string{"value-2"}, - Operator: corev1.NodeSelectorOpIn, - }, - { - Key: "key-3", - Values: []string{"value-3-1", "value-3-2"}, - Operator: corev1.NodeSelectorOpNotIn, - }, - { - Key: "key-4", - Values: []string{"value-4-1", "value-4-2", "value-4-3"}, - Operator: corev1.NodeSelectorOpDoesNotExist, - }, - }, - }, - }, - }, - }, - }, - }, - } - - for _, test := range tests { - t.Run(test.name, func(t *testing.T) { - affinity := toSystemAffinity(test.loadAffinity) - assert.True(t, reflect.DeepEqual(affinity, test.expected)) - }) - } -} - func Test_csiSnapshotExposer_createBackupPVC(t *testing.T) { backup := &velerov1.Backup{ TypeMeta: metav1.TypeMeta{ diff --git a/pkg/install/deployment.go b/pkg/install/deployment.go index 9ac46ece869..4a1b6cef172 100644 --- a/pkg/install/deployment.go +++ b/pkg/install/deployment.go @@ -27,7 +27,6 @@ import ( "github.com/vmware-tanzu/velero/internal/velero" "github.com/vmware-tanzu/velero/pkg/builder" - "github.com/vmware-tanzu/velero/pkg/repository" ) type podTemplateOption func(*podTemplateConfig) @@ -52,7 +51,6 @@ type podTemplateConfig struct { privilegedNodeAgent bool disableInformerCache bool scheduleSkipImmediately bool - maintenanceConfig repository.MaintenanceConfig } func WithImage(image string) podTemplateOption { @@ -179,12 +177,6 @@ func WithScheduleSkipImmediately(b bool) podTemplateOption { } } -func WithMaintenanceConfig(config repository.MaintenanceConfig) podTemplateOption { - return func(c *podTemplateConfig) { - c.maintenanceConfig = config - } -} - func Deployment(namespace string, opts ...podTemplateOption) *appsv1.Deployment { // TODO: Add support for server args c := &podTemplateConfig{ @@ -242,26 +234,6 @@ func Deployment(namespace string, opts ...podTemplateOption) *appsv1.Deployment args = append(args, fmt.Sprintf("--fs-backup-timeout=%v", c.podVolumeOperationTimeout)) } - if c.maintenanceConfig.KeepLatestMaitenanceJobs > 0 { - args = append(args, fmt.Sprintf("--keep-latest-maintenance-jobs=%d", c.maintenanceConfig.KeepLatestMaitenanceJobs)) - } - - if c.maintenanceConfig.CPULimit != "" { - args = append(args, fmt.Sprintf("--maintenance-job-cpu-limit=%s", c.maintenanceConfig.CPULimit)) - } - - if c.maintenanceConfig.CPURequest != "" { - args = append(args, fmt.Sprintf("--maintenance-job-cpu-request=%s", c.maintenanceConfig.CPURequest)) - } - - if c.maintenanceConfig.MemLimit != "" { - args = append(args, fmt.Sprintf("--maintenance-job-mem-limit=%s", c.maintenanceConfig.MemLimit)) - } - - if c.maintenanceConfig.MemRequest != "" { - args = append(args, fmt.Sprintf("--maintenance-job-mem-request=%s", c.maintenanceConfig.MemRequest)) - } - deployment := &appsv1.Deployment{ ObjectMeta: objectMeta(namespace, "velero"), TypeMeta: metav1.TypeMeta{ diff --git a/pkg/install/deployment_test.go b/pkg/install/deployment_test.go index 426a53df696..8d5f5449868 100644 --- a/pkg/install/deployment_test.go +++ b/pkg/install/deployment_test.go @@ -22,8 +22,6 @@ import ( "github.com/stretchr/testify/assert" corev1 "k8s.io/api/core/v1" - - "github.com/vmware-tanzu/velero/pkg/repository" ) func TestDeployment(t *testing.T) { @@ -70,18 +68,4 @@ func TestDeployment(t *testing.T) { deploy = Deployment("velero", WithDisableInformerCache(true)) assert.Len(t, deploy.Spec.Template.Spec.Containers[0].Args, 2) assert.Equal(t, "--disable-informer-cache=true", deploy.Spec.Template.Spec.Containers[0].Args[1]) - - deploy = Deployment("velero", WithMaintenanceConfig(repository.MaintenanceConfig{ - KeepLatestMaitenanceJobs: 3, - CPURequest: "100m", - MemRequest: "256Mi", - CPULimit: "200m", - MemLimit: "512Mi", - })) - assert.Len(t, deploy.Spec.Template.Spec.Containers[0].Args, 6) - assert.Equal(t, "--keep-latest-maintenance-jobs=3", deploy.Spec.Template.Spec.Containers[0].Args[1]) - assert.Equal(t, "--maintenance-job-cpu-limit=200m", deploy.Spec.Template.Spec.Containers[0].Args[2]) - assert.Equal(t, "--maintenance-job-cpu-request=100m", deploy.Spec.Template.Spec.Containers[0].Args[3]) - assert.Equal(t, "--maintenance-job-mem-limit=512Mi", deploy.Spec.Template.Spec.Containers[0].Args[4]) - assert.Equal(t, "--maintenance-job-mem-request=256Mi", deploy.Spec.Template.Spec.Containers[0].Args[5]) } diff --git a/pkg/install/resources.go b/pkg/install/resources.go index 752bc025b9e..5273b365611 100644 --- a/pkg/install/resources.go +++ b/pkg/install/resources.go @@ -30,7 +30,6 @@ import ( v1crds "github.com/vmware-tanzu/velero/config/crd/v1/crds" v2alpha1crds "github.com/vmware-tanzu/velero/config/crd/v2alpha1/crds" velerov1api "github.com/vmware-tanzu/velero/pkg/apis/velero/v1" - "github.com/vmware-tanzu/velero/pkg/repository" "github.com/vmware-tanzu/velero/pkg/util/logging" ) @@ -265,7 +264,6 @@ type VeleroOptions struct { ScheduleSkipImmediately bool FormatFlag *logging.FormatFlag LogLevelFlag *logging.LevelFlag - MaintenanceCfg repository.MaintenanceConfig } func AllCRDs() *unstructured.UnstructuredList { @@ -350,7 +348,6 @@ func AllResources(o *VeleroOptions) *unstructured.UnstructuredList { WithPodVolumeOperationTimeout(o.PodVolumeOperationTimeout), WithUploaderType(o.UploaderType), WithScheduleSkipImmediately(o.ScheduleSkipImmediately), - WithMaintenanceConfig(o.MaintenanceCfg), } if len(o.Features) > 0 { diff --git a/pkg/nodeagent/node_agent.go b/pkg/nodeagent/node_agent.go index f7a9629dc32..8922df39216 100644 --- a/pkg/nodeagent/node_agent.go +++ b/pkg/nodeagent/node_agent.go @@ -70,25 +70,18 @@ type BackupPVC struct { ReadOnly bool `json:"readOnly,omitempty"` } -type PodResources struct { - CPURequest string `json:"cpuRequest,omitempty"` - MemoryRequest string `json:"memoryRequest,omitempty"` - CPULimit string `json:"cpuLimit,omitempty"` - MemoryLimit string `json:"memoryLimit,omitempty"` -} - type Configs struct { // LoadConcurrency is the config for data path load concurrency per node. LoadConcurrency *LoadConcurrency `json:"loadConcurrency,omitempty"` // LoadAffinity is the config for data path load affinity. - LoadAffinity []*LoadAffinity `json:"loadAffinity,omitempty"` + LoadAffinity []*kube.LoadAffinity `json:"loadAffinity,omitempty"` // BackupPVCConfig is the config for backupPVC (intermediate PVC) of snapshot data movement BackupPVCConfig map[string]BackupPVC `json:"backupPVC,omitempty"` // PodResources is the resource config for various types of pods launched by node-agent, i.e., data mover pods. - PodResources *PodResources `json:"podResources,omitempty"` + PodResources *kube.PodResources `json:"podResources,omitempty"` } // IsRunning checks if the node agent daemonset is running properly. If not, return the error found diff --git a/pkg/repository/maintenance.go b/pkg/repository/maintenance.go index ffe9f89fd42..651d699ab74 100644 --- a/pkg/repository/maintenance.go +++ b/pkg/repository/maintenance.go @@ -18,10 +18,13 @@ package repository import ( "context" + "encoding/json" "fmt" "sort" "time" + "github.com/pkg/errors" + "github.com/sirupsen/logrus" appsv1 "k8s.io/api/apps/v1" batchv1 "k8s.io/api/batch/v1" v1 "k8s.io/api/core/v1" @@ -31,8 +34,7 @@ import ( "k8s.io/apimachinery/pkg/util/wait" "sigs.k8s.io/controller-runtime/pkg/client" - "github.com/pkg/errors" - + velerov1api "github.com/vmware-tanzu/velero/pkg/apis/velero/v1" "github.com/vmware-tanzu/velero/pkg/repository/provider" "github.com/vmware-tanzu/velero/pkg/util/kube" "github.com/vmware-tanzu/velero/pkg/util/logging" @@ -40,21 +42,18 @@ import ( ) const RepositoryNameLabel = "velero.io/repo-name" -const DefaultKeepLatestMaitenanceJobs = 3 +const DefaultKeepLatestMaintenanceJobs = 3 const DefaultMaintenanceJobCPURequest = "0" const DefaultMaintenanceJobCPULimit = "0" const DefaultMaintenanceJobMemRequest = "0" const DefaultMaintenanceJobMemLimit = "0" -// MaintenanceConfig is the configuration for the repo maintenance job -type MaintenanceConfig struct { - KeepLatestMaitenanceJobs int - CPURequest string - MemRequest string - CPULimit string - MemLimit string - LogLevelFlag *logging.LevelFlag - FormatFlag *logging.FormatFlag +type JobConfigs struct { + // LoadAffinities is the config for repository maintenance job load affinity. + LoadAffinities []*kube.LoadAffinity `json:"loadAffinity,omitempty"` + + // PodResources is the config for the CPU and memory resources setting. + PodResources *kube.PodResources `json:"podResources,omitempty"` } func generateJobName(repo string) string { @@ -68,7 +67,14 @@ func generateJobName(repo string) string { return jobName } -func buildMaintenanceJob(m MaintenanceConfig, param provider.RepoParam, cli client.Client, namespace string) (*batchv1.Job, error) { +func buildMaintenanceJob( + config *JobConfigs, + param provider.RepoParam, + cli client.Client, + namespace string, + logLevel logrus.Level, + logFormat *logging.FormatFlag, +) (*batchv1.Job, error) { // Get the Velero server deployment deployment := &appsv1.Deployment{} err := cli.Get(context.TODO(), types.NamespacedName{Name: "velero", Namespace: namespace}, deployment) @@ -92,20 +98,17 @@ func buildMaintenanceJob(m MaintenanceConfig, param provider.RepoParam, cli clie image := veleroutil.GetVeleroServerImage(deployment) // Set resource limits and requests - if m.CPURequest == "" { - m.CPURequest = DefaultMaintenanceJobCPURequest + cpuRequest := DefaultMaintenanceJobCPURequest + memRequest := DefaultMaintenanceJobMemRequest + cpuLimit := DefaultMaintenanceJobCPULimit + memLimit := DefaultMaintenanceJobMemLimit + if config != nil && config.PodResources != nil { + cpuRequest = config.PodResources.CPURequest + memRequest = config.PodResources.MemoryRequest + cpuLimit = config.PodResources.CPULimit + memLimit = config.PodResources.MemoryLimit } - if m.MemRequest == "" { - m.MemRequest = DefaultMaintenanceJobMemRequest - } - if m.CPULimit == "" { - m.CPULimit = DefaultMaintenanceJobCPULimit - } - if m.MemLimit == "" { - m.MemLimit = DefaultMaintenanceJobMemLimit - } - - resources, err := kube.ParseResourceRequirements(m.CPURequest, m.MemRequest, m.CPULimit, m.MemLimit) + resources, err := kube.ParseResourceRequirements(cpuRequest, memRequest, cpuLimit, memLimit) if err != nil { return nil, errors.Wrap(err, "failed to parse resource requirements for maintenance job") } @@ -115,8 +118,8 @@ func buildMaintenanceJob(m MaintenanceConfig, param provider.RepoParam, cli clie args = append(args, fmt.Sprintf("--repo-name=%s", param.BackupRepo.Spec.VolumeNamespace)) args = append(args, fmt.Sprintf("--repo-type=%s", param.BackupRepo.Spec.RepositoryType)) args = append(args, fmt.Sprintf("--backup-storage-location=%s", param.BackupLocation.Name)) - args = append(args, fmt.Sprintf("--log-level=%s", m.LogLevelFlag.String())) - args = append(args, fmt.Sprintf("--log-format=%s", m.FormatFlag.String())) + args = append(args, fmt.Sprintf("--log-level=%s", logLevel.String())) + args = append(args, fmt.Sprintf("--log-format=%s", logFormat.String())) // build the maintenance job job := &batchv1.Job{ @@ -156,7 +159,8 @@ func buildMaintenanceJob(m MaintenanceConfig, param provider.RepoParam, cli clie }, } - if affinity := veleroutil.GetAffinityFromVeleroServer(deployment); affinity != nil { + if config != nil && len(config.LoadAffinities) > 0 { + affinity := kube.ToSystemAffinity(config.LoadAffinities) job.Spec.Template.Spec.Affinity = affinity } @@ -262,3 +266,89 @@ func getLatestMaintenanceJob(cli client.Client, ns string) (*batchv1.Job, error) return &jobList.Items[0], nil } + +// getMaintenanceJobConfig is called to get the Maintenance Job Config for the +// BackupRepository specified by the repo parameter. +// +// Params: +// +// veleroNamespace: the Velero-installed namespace. It's used to retrieve the BackupRepository. +// repo: the BackupRepository to get the Job config. +func getMaintenanceJobConfig( + ctx context.Context, + cli client.Client, + logger logrus.FieldLogger, + veleroNamespace string, + repoMaintenanceJobConfig string, + repo *velerov1api.BackupRepository, +) (*JobConfigs, error) { + var cm v1.ConfigMap + if err := cli.Get( + ctx, + types.NamespacedName{ + Namespace: veleroNamespace, + Name: repoMaintenanceJobConfig, + }, + &cm, + ); err != nil { + if apierrors.IsNotFound(err) { + return nil, nil + } else { + return nil, errors.Wrapf( + err, + "fail to get repo maintenance job configs %s", repoMaintenanceJobConfig) + } + } + + if cm.Data == nil { + return nil, errors.Errorf("data is not available in config map %s", repoMaintenanceJobConfig) + } + + configMap := make(map[string]JobConfigs) + for k, v := range cm.Data { + var config JobConfigs + if err := json.Unmarshal([]byte(v), &config); err != nil { + return nil, errors.Wrapf(err, "fail to unmarshal configs from %s", repoMaintenanceJobConfig) + } + configMap[k] = config + } + + // Generate the BackupRepository key. + // If using the BackupRepository name as the is more intuitive, + // but the BackupRepository generation is dynamic. We cannot assume + // they are ready when installing Velero. + // Instead we use the volume source namespace, BSL name, and the uploader + // type to represent the BackupRepository. The combination of those three + // keys can identify a unique BackupRepository. + repoJobConfigKey := repo.Spec.VolumeNamespace + "-" + + repo.Spec.BackupStorageLocation + "-" + repo.Spec.RepositoryType + + var result *JobConfigs + if _, ok := configMap[repoJobConfigKey]; ok { + logger.Debugf("Find the repo maintenance config %s for repo %s", repoJobConfigKey, repo.Name) + result = new(JobConfigs) + *result = configMap[repoJobConfigKey] + } + + if _, ok := configMap["global"]; ok { + logger.Debugf("Find the global repo maintenance config for repo %s", repo.Name) + + if result == nil { + result = new(JobConfigs) + } + + if result.PodResources == nil && configMap["global"].PodResources != nil { + result.PodResources = configMap["global"].PodResources + } + + if len(result.LoadAffinities) == 0 { + result.LoadAffinities = configMap["global"].LoadAffinities + } + } + + if result != nil { + logger.Debugf("The content of the Maintenance Job Config: %+v", *result) + } + + return result, nil +} diff --git a/pkg/repository/maintenance_test.go b/pkg/repository/maintenance_test.go index ca88c1577d5..6c073e795ee 100644 --- a/pkg/repository/maintenance_test.go +++ b/pkg/repository/maintenance_test.go @@ -25,6 +25,7 @@ import ( "github.com/sirupsen/logrus" "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" appsv1 "k8s.io/api/apps/v1" batchv1 "k8s.io/api/batch/v1" v1 "k8s.io/api/core/v1" @@ -36,6 +37,8 @@ import ( velerov1api "github.com/vmware-tanzu/velero/pkg/apis/velero/v1" "github.com/vmware-tanzu/velero/pkg/repository/provider" + velerotest "github.com/vmware-tanzu/velero/pkg/test" + "github.com/vmware-tanzu/velero/pkg/util/kube" "github.com/vmware-tanzu/velero/pkg/util/logging" ) @@ -266,20 +269,22 @@ func TestGetLatestMaintenanceJob(t *testing.T) { func TestBuildMaintenanceJob(t *testing.T) { testCases := []struct { name string - m MaintenanceConfig + m *JobConfigs deploy *appsv1.Deployment + logLevel logrus.Level + logFormat *logging.FormatFlag expectedJobName string expectedError bool }{ { name: "Valid maintenance job", - m: MaintenanceConfig{ - CPURequest: "100m", - MemRequest: "128Mi", - CPULimit: "200m", - MemLimit: "256Mi", - LogLevelFlag: logging.LogLevelFlag(logrus.InfoLevel), - FormatFlag: logging.NewFormatFlag(), + m: &JobConfigs{ + PodResources: &kube.PodResources{ + CPURequest: "100m", + MemoryRequest: "128Mi", + CPULimit: "200m", + MemoryLimit: "256Mi", + }, }, deploy: &appsv1.Deployment{ ObjectMeta: metav1.ObjectMeta{ @@ -299,19 +304,23 @@ func TestBuildMaintenanceJob(t *testing.T) { }, }, }, + logLevel: logrus.InfoLevel, + logFormat: logging.NewFormatFlag(), expectedJobName: "test-123-maintain-job", expectedError: false, }, { name: "Error getting Velero server deployment", - m: MaintenanceConfig{ - CPURequest: "100m", - MemRequest: "128Mi", - CPULimit: "200m", - MemLimit: "256Mi", - LogLevelFlag: logging.LogLevelFlag(logrus.InfoLevel), - FormatFlag: logging.NewFormatFlag(), + m: &JobConfigs{ + PodResources: &kube.PodResources{ + CPURequest: "100m", + MemoryRequest: "128Mi", + CPULimit: "200m", + MemoryLimit: "256Mi", + }, }, + logLevel: logrus.InfoLevel, + logFormat: logging.NewFormatFlag(), expectedJobName: "", expectedError: true, }, @@ -350,7 +359,7 @@ func TestBuildMaintenanceJob(t *testing.T) { cli := fake.NewClientBuilder().WithScheme(scheme).WithRuntimeObjects(objs...).Build() // Call the function to test - job, err := buildMaintenanceJob(tc.m, param, cli, "velero") + job, err := buildMaintenanceJob(tc.m, param, cli, "velero", logrus.InfoLevel, logging.NewFormatFlag()) // Check the error if tc.expectedError { @@ -373,12 +382,12 @@ func TestBuildMaintenanceJob(t *testing.T) { // Check resources expectedResources := v1.ResourceRequirements{ Requests: v1.ResourceList{ - v1.ResourceCPU: resource.MustParse(tc.m.CPURequest), - v1.ResourceMemory: resource.MustParse(tc.m.MemRequest), + v1.ResourceCPU: resource.MustParse(tc.m.PodResources.CPURequest), + v1.ResourceMemory: resource.MustParse(tc.m.PodResources.MemoryRequest), }, Limits: v1.ResourceList{ - v1.ResourceCPU: resource.MustParse(tc.m.CPULimit), - v1.ResourceMemory: resource.MustParse(tc.m.MemLimit), + v1.ResourceCPU: resource.MustParse(tc.m.PodResources.CPULimit), + v1.ResourceMemory: resource.MustParse(tc.m.PodResources.MemoryLimit), }, } assert.Equal(t, expectedResources, container.Resources) @@ -389,8 +398,8 @@ func TestBuildMaintenanceJob(t *testing.T) { fmt.Sprintf("--repo-name=%s", param.BackupRepo.Spec.VolumeNamespace), fmt.Sprintf("--repo-type=%s", param.BackupRepo.Spec.RepositoryType), fmt.Sprintf("--backup-storage-location=%s", param.BackupLocation.Name), - fmt.Sprintf("--log-level=%s", tc.m.LogLevelFlag.String()), - fmt.Sprintf("--log-format=%s", tc.m.FormatFlag.String()), + fmt.Sprintf("--log-level=%s", tc.logLevel.String()), + fmt.Sprintf("--log-format=%s", tc.logFormat.String()), } assert.Equal(t, expectedArgs, container.Args) @@ -406,3 +415,178 @@ func TestBuildMaintenanceJob(t *testing.T) { }) } } + +func TestGetMaintenanceJobConfig(t *testing.T) { + ctx := context.Background() + logger := logrus.New() + veleroNamespace := "velero" + repoMaintenanceJobConfig := "repo-maintenance-job-config" + repo := &velerov1api.BackupRepository{ + ObjectMeta: metav1.ObjectMeta{ + Namespace: veleroNamespace, + Name: repoMaintenanceJobConfig, + }, + Spec: velerov1api.BackupRepositorySpec{ + BackupStorageLocation: "default", + RepositoryType: "kopia", + VolumeNamespace: "test", + }, + } + + testCases := []struct { + name string + repoJobConfig *v1.ConfigMap + expectedConfig *JobConfigs + expectedError error + }{ + { + name: "Config not exist", + expectedConfig: nil, + expectedError: nil, + }, + { + name: "Invalid JSON", + repoJobConfig: &v1.ConfigMap{ + ObjectMeta: metav1.ObjectMeta{ + Namespace: veleroNamespace, + Name: repoMaintenanceJobConfig, + }, + Data: map[string]string{ + "test-default-kopia": "{\"cpuRequest:\"100m\"}", + }, + }, + expectedConfig: nil, + expectedError: fmt.Errorf("fail to unmarshal configs from %s", repoMaintenanceJobConfig), + }, + { + name: "Find config specific for BackupRepository", + repoJobConfig: &v1.ConfigMap{ + ObjectMeta: metav1.ObjectMeta{ + Namespace: veleroNamespace, + Name: repoMaintenanceJobConfig, + }, + Data: map[string]string{ + "test-default-kopia": "{\"podResources\":{\"cpuRequest\":\"100m\",\"cpuLimit\":\"200m\",\"memoryRequest\":\"100Mi\",\"memoryLimit\":\"200Mi\"},\"loadAffinity\":[{\"nodeSelector\":{\"matchExpressions\":[{\"key\":\"cloud.google.com/machine-family\",\"operator\":\"In\",\"values\":[\"e2\"]}]}}]}", + }, + }, + expectedConfig: &JobConfigs{ + PodResources: &kube.PodResources{ + CPURequest: "100m", + CPULimit: "200m", + MemoryRequest: "100Mi", + MemoryLimit: "200Mi", + }, + LoadAffinities: []*kube.LoadAffinity{ + { + NodeSelector: metav1.LabelSelector{ + MatchExpressions: []metav1.LabelSelectorRequirement{ + { + Key: "cloud.google.com/machine-family", + Operator: metav1.LabelSelectorOpIn, + Values: []string{"e2"}, + }, + }, + }, + }, + }, + }, + expectedError: nil, + }, + { + name: "Find config specific for global", + repoJobConfig: &v1.ConfigMap{ + ObjectMeta: metav1.ObjectMeta{ + Namespace: veleroNamespace, + Name: repoMaintenanceJobConfig, + }, + Data: map[string]string{ + "global": "{\"podResources\":{\"cpuRequest\":\"50m\",\"cpuLimit\":\"100m\",\"memoryRequest\":\"50Mi\",\"memoryLimit\":\"100Mi\"},\"loadAffinity\":[{\"nodeSelector\":{\"matchExpressions\":[{\"key\":\"cloud.google.com/machine-family\",\"operator\":\"In\",\"values\":[\"n2\"]}]}}]}", + }, + }, + expectedConfig: &JobConfigs{ + PodResources: &kube.PodResources{ + CPURequest: "50m", + CPULimit: "100m", + MemoryRequest: "50Mi", + MemoryLimit: "100Mi", + }, + LoadAffinities: []*kube.LoadAffinity{ + { + NodeSelector: metav1.LabelSelector{ + MatchExpressions: []metav1.LabelSelectorRequirement{ + { + Key: "cloud.google.com/machine-family", + Operator: metav1.LabelSelectorOpIn, + Values: []string{"n2"}, + }, + }, + }, + }, + }, + }, + expectedError: nil, + }, + { + name: "Specific config supersede global config", + repoJobConfig: &v1.ConfigMap{ + ObjectMeta: metav1.ObjectMeta{ + Namespace: veleroNamespace, + Name: repoMaintenanceJobConfig, + }, + Data: map[string]string{ + "global": "{\"podResources\":{\"cpuRequest\":\"50m\",\"cpuLimit\":\"100m\",\"memoryRequest\":\"50Mi\",\"memoryLimit\":\"100Mi\"},\"loadAffinity\":[{\"nodeSelector\":{\"matchExpressions\":[{\"key\":\"cloud.google.com/machine-family\",\"operator\":\"In\",\"values\":[\"n2\"]}]}}]}", + "test-default-kopia": "{\"podResources\":{\"cpuRequest\":\"100m\",\"cpuLimit\":\"200m\",\"memoryRequest\":\"100Mi\",\"memoryLimit\":\"200Mi\"},\"loadAffinity\":[{\"nodeSelector\":{\"matchExpressions\":[{\"key\":\"cloud.google.com/machine-family\",\"operator\":\"In\",\"values\":[\"e2\"]}]}}]}", + }, + }, + expectedConfig: &JobConfigs{ + PodResources: &kube.PodResources{ + CPURequest: "100m", + CPULimit: "200m", + MemoryRequest: "100Mi", + MemoryLimit: "200Mi", + }, + LoadAffinities: []*kube.LoadAffinity{ + { + NodeSelector: metav1.LabelSelector{ + MatchExpressions: []metav1.LabelSelectorRequirement{ + { + Key: "cloud.google.com/machine-family", + Operator: metav1.LabelSelectorOpIn, + Values: []string{"e2"}, + }, + }, + }, + }, + }, + }, + expectedError: nil, + }, + } + + for _, tc := range testCases { + t.Run(tc.name, func(t *testing.T) { + var fakeClient client.Client + if tc.repoJobConfig != nil { + fakeClient = velerotest.NewFakeControllerRuntimeClient(t, tc.repoJobConfig) + } else { + fakeClient = velerotest.NewFakeControllerRuntimeClient(t) + } + + jobConfig, err := getMaintenanceJobConfig( + ctx, + fakeClient, + logger, + veleroNamespace, + repoMaintenanceJobConfig, + repo, + ) + + if tc.expectedError != nil { + require.Contains(t, err.Error(), tc.expectedError.Error()) + } else { + require.NoError(t, err) + } + require.Equal(t, tc.expectedConfig, jobConfig) + }) + } +} diff --git a/pkg/repository/manager.go b/pkg/repository/manager.go index b5875a7355a..828ebf33cb0 100644 --- a/pkg/repository/manager.go +++ b/pkg/repository/manager.go @@ -29,6 +29,7 @@ import ( velerov1api "github.com/vmware-tanzu/velero/pkg/apis/velero/v1" "github.com/vmware-tanzu/velero/pkg/repository/provider" "github.com/vmware-tanzu/velero/pkg/util/filesystem" + "github.com/vmware-tanzu/velero/pkg/util/logging" ) // SnapshotIdentifier uniquely identifies a snapshot @@ -92,14 +93,18 @@ type Manager interface { } type manager struct { - namespace string - providers map[string]provider.Provider - client client.Client - repoLocker *RepoLocker - repoEnsurer *Ensurer - fileSystem filesystem.Interface - maintenanceCfg MaintenanceConfig - log logrus.FieldLogger + namespace string + providers map[string]provider.Provider + // client is the Velero controller manager's client. + // It's limited to resources in the Velero namespace. + client client.Client + repoLocker *RepoLocker + repoEnsurer *Ensurer + fileSystem filesystem.Interface + repoMaintenanceJobConfig string + log logrus.FieldLogger + logLevel logrus.Level + logFormat *logging.FormatFlag } // NewManager create a new repository manager. @@ -110,18 +115,22 @@ func NewManager( repoEnsurer *Ensurer, credentialFileStore credentials.FileStore, credentialSecretStore credentials.SecretStore, - maintenanceCfg MaintenanceConfig, + repoMaintenanceJobConfig string, log logrus.FieldLogger, + logLevel logrus.Level, + logFormat *logging.FormatFlag, ) Manager { mgr := &manager{ - namespace: namespace, - client: client, - providers: map[string]provider.Provider{}, - repoLocker: repoLocker, - repoEnsurer: repoEnsurer, - fileSystem: filesystem.NewFileSystem(), - maintenanceCfg: maintenanceCfg, - log: log, + namespace: namespace, + client: client, + providers: map[string]provider.Provider{}, + repoLocker: repoLocker, + repoEnsurer: repoEnsurer, + fileSystem: filesystem.NewFileSystem(), + repoMaintenanceJobConfig: repoMaintenanceJobConfig, + log: log, + logLevel: logLevel, + logFormat: logFormat, } mgr.providers[velerov1api.BackupRepositoryTypeRestic] = provider.NewResticRepositoryProvider(credentialFileStore, mgr.fileSystem, mgr.log) @@ -204,9 +213,28 @@ func (m *manager) PruneRepo(repo *velerov1api.BackupRepository) error { return nil } + jobConfig, err := getMaintenanceJobConfig( + context.Background(), + m.client, + m.log, + m.namespace, + m.repoMaintenanceJobConfig, + repo, + ) + if err != nil { + log.Infof("Cannot find the repo-maintenance-job-config ConfigMap: %s. Use default value.", err.Error()) + } + log.Info("Start to maintenance repo") - maintenanceJob, err := buildMaintenanceJob(m.maintenanceCfg, param, m.client, m.namespace) + maintenanceJob, err := buildMaintenanceJob( + jobConfig, + param, + m.client, + m.namespace, + m.logLevel, + m.logFormat, + ) if err != nil { return errors.Wrap(err, "error to build maintenance job") } @@ -219,8 +247,11 @@ func (m *manager) PruneRepo(repo *velerov1api.BackupRepository) error { log.Debug("Creating maintenance job") defer func() { - if err := deleteOldMaintenanceJobs(m.client, param.BackupRepo.Name, - m.maintenanceCfg.KeepLatestMaitenanceJobs); err != nil { + if err := deleteOldMaintenanceJobs( + m.client, + param.BackupRepo.Name, + DefaultKeepLatestMaintenanceJobs, + ); err != nil { log.WithError(err).Error("Failed to delete maintenance job") } }() diff --git a/pkg/repository/manager_test.go b/pkg/repository/manager_test.go index 07b51fc7486..fbdfede54e5 100644 --- a/pkg/repository/manager_test.go +++ b/pkg/repository/manager_test.go @@ -19,6 +19,7 @@ package repository import ( "testing" + "github.com/sirupsen/logrus" "github.com/stretchr/testify/assert" "github.com/stretchr/testify/require" kbclient "sigs.k8s.io/controller-runtime/pkg/client" @@ -28,7 +29,7 @@ import ( func TestGetRepositoryProvider(t *testing.T) { var fakeClient kbclient.Client - mgr := NewManager("", fakeClient, nil, nil, nil, nil, MaintenanceConfig{}, nil).(*manager) + mgr := NewManager("", fakeClient, nil, nil, nil, nil, "", nil, logrus.InfoLevel, nil).(*manager) repo := &velerov1.BackupRepository{} // empty repository type diff --git a/pkg/util/kube/pod.go b/pkg/util/kube/pod.go index 9def5d514af..08224544224 100644 --- a/pkg/util/kube/pod.go +++ b/pkg/util/kube/pod.go @@ -30,6 +30,11 @@ import ( corev1client "k8s.io/client-go/kubernetes/typed/core/v1" ) +type LoadAffinity struct { + // NodeSelector specifies the label selector to match nodes + NodeSelector metav1.LabelSelector `json:"nodeSelector"` +} + // IsPodRunning does a well-rounded check to make sure the specified pod is running stably. // If not, return the error found func IsPodRunning(pod *corev1api.Pod) error { @@ -201,3 +206,48 @@ func CollectPodLogs(ctx context.Context, podGetter corev1client.CoreV1Interface, return nil } + +func ToSystemAffinity(loadAffinities []*LoadAffinity) *corev1api.Affinity { + if len(loadAffinities) == 0 { + return nil + } + + result := new(corev1api.Affinity) + result.NodeAffinity = new(corev1api.NodeAffinity) + result.NodeAffinity.RequiredDuringSchedulingIgnoredDuringExecution = new(corev1api.NodeSelector) + result.NodeAffinity.RequiredDuringSchedulingIgnoredDuringExecution.NodeSelectorTerms = + make([]corev1api.NodeSelectorTerm, 0) + + for _, loadAffinity := range loadAffinities { + requirements := []corev1api.NodeSelectorRequirement{} + for k, v := range loadAffinity.NodeSelector.MatchLabels { + requirements = append(requirements, corev1api.NodeSelectorRequirement{ + Key: k, + Values: []string{v}, + Operator: corev1api.NodeSelectorOpIn, + }) + } + + for _, exp := range loadAffinity.NodeSelector.MatchExpressions { + requirements = append(requirements, corev1api.NodeSelectorRequirement{ + Key: exp.Key, + Values: exp.Values, + Operator: corev1api.NodeSelectorOperator(exp.Operator), + }) + } + + if len(requirements) == 0 { + return nil + } + + result.NodeAffinity.RequiredDuringSchedulingIgnoredDuringExecution.NodeSelectorTerms = + append( + result.NodeAffinity.RequiredDuringSchedulingIgnoredDuringExecution.NodeSelectorTerms, + corev1api.NodeSelectorTerm{ + MatchExpressions: requirements, + }, + ) + } + + return result +} diff --git a/pkg/util/kube/pod_test.go b/pkg/util/kube/pod_test.go index 7ccb2257817..2557a65b748 100644 --- a/pkg/util/kube/pod_test.go +++ b/pkg/util/kube/pod_test.go @@ -19,6 +19,7 @@ package kube import ( "context" "io" + "reflect" "strings" "testing" "time" @@ -697,3 +698,106 @@ func TestCollectPodLogs(t *testing.T) { }) } } + +func TestToSystemAffinity(t *testing.T) { + tests := []struct { + name string + loadAffinities []*LoadAffinity + expected *corev1api.Affinity + }{ + { + name: "loadAffinity is nil", + }, + { + name: "loadAffinity is empty", + loadAffinities: []*LoadAffinity{}, + }, + { + name: "with match label", + loadAffinities: []*LoadAffinity{ + { + NodeSelector: metav1.LabelSelector{ + MatchLabels: map[string]string{ + "key-1": "value-1", + }, + }, + }, + }, + expected: &corev1api.Affinity{ + NodeAffinity: &corev1api.NodeAffinity{ + RequiredDuringSchedulingIgnoredDuringExecution: &corev1api.NodeSelector{ + NodeSelectorTerms: []corev1api.NodeSelectorTerm{ + { + MatchExpressions: []corev1api.NodeSelectorRequirement{ + { + Key: "key-1", + Values: []string{"value-1"}, + Operator: corev1api.NodeSelectorOpIn, + }, + }, + }, + }, + }, + }, + }, + }, + { + name: "with match expression", + loadAffinities: []*LoadAffinity{ + { + NodeSelector: metav1.LabelSelector{ + MatchLabels: map[string]string{ + "key-2": "value-2", + }, + MatchExpressions: []metav1.LabelSelectorRequirement{ + { + Key: "key-3", + Values: []string{"value-3-1", "value-3-2"}, + Operator: metav1.LabelSelectorOpNotIn, + }, + { + Key: "key-4", + Values: []string{"value-4-1", "value-4-2", "value-4-3"}, + Operator: metav1.LabelSelectorOpDoesNotExist, + }, + }, + }, + }, + }, + expected: &corev1api.Affinity{ + NodeAffinity: &corev1api.NodeAffinity{ + RequiredDuringSchedulingIgnoredDuringExecution: &corev1api.NodeSelector{ + NodeSelectorTerms: []corev1api.NodeSelectorTerm{ + { + MatchExpressions: []corev1api.NodeSelectorRequirement{ + { + Key: "key-2", + Values: []string{"value-2"}, + Operator: corev1api.NodeSelectorOpIn, + }, + { + Key: "key-3", + Values: []string{"value-3-1", "value-3-2"}, + Operator: corev1api.NodeSelectorOpNotIn, + }, + { + Key: "key-4", + Values: []string{"value-4-1", "value-4-2", "value-4-3"}, + Operator: corev1api.NodeSelectorOpDoesNotExist, + }, + }, + }, + }, + }, + }, + }, + }, + } + + for _, test := range tests { + t.Run(test.name, func(t *testing.T) { + affinity := ToSystemAffinity(test.loadAffinities) + assert.True(t, reflect.DeepEqual(affinity, test.expected)) + }) + } +} diff --git a/pkg/util/kube/resource_requirements.go b/pkg/util/kube/resource_requirements.go index a1974516ca6..c66e9727139 100644 --- a/pkg/util/kube/resource_requirements.go +++ b/pkg/util/kube/resource_requirements.go @@ -22,6 +22,13 @@ import ( "k8s.io/apimachinery/pkg/api/resource" ) +type PodResources struct { + CPURequest string `json:"cpuRequest,omitempty"` + MemoryRequest string `json:"memoryRequest,omitempty"` + CPULimit string `json:"cpuLimit,omitempty"` + MemoryLimit string `json:"memoryLimit,omitempty"` +} + // ParseResourceRequirements takes a set of CPU and memory requests and limit string // values and returns a ResourceRequirements struct to be used in a Container. // An error is returned if we cannot parse the request/limit.