Implement the Repo maintanence Job configuration design.

Remove the resource parameters from the velero server CLI. Signed-off-by: Xun Jiang <xun.jiang@broadcom.com>
2026-01-05 13:05:17 +00:00 · 2024-08-21 15:14:53 +08:00
parent b92143dad1
commit 26cc41f26d
25 changed files with 1275 additions and 577 deletions
--- 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 +84,8 @@ type Options struct {
 	DefaultSnapshotMoveData         bool
 	DisableInformerCache            bool
 	ScheduleSkipImmediately         bool
-	MaintenanceCfg                  repository.MaintenanceConfig
+	PodResources                    kubeutil.PodResources
+	KeepLatestMaintenanceJobs       int
 }

 // BindFlags adds command line values to the options struct.
@@ -130,11 +130,37 @@ 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.")
+
+	flags.IntVar(
+		&o.KeepLatestMaintenanceJobs,
+		"keep-latest-maintenance-jobs",
+		o.KeepLatestMaintenanceJobs,
+		"Number of latest maintenance jobs to keep each repository. Optional.",
+	)
+	flags.StringVar(
+		&o.PodResources.CPURequest,
+		"maintenance-job-cpu-request",
+		o.PodResources.CPURequest,
+		"CPU request for maintenance jobs. Default is no limit.",
+	)
+	flags.StringVar(
+		&o.PodResources.MemoryRequest,
+		"maintenance-job-mem-request",
+		o.PodResources.MemoryRequest,
+		"Memory request for maintenance jobs. Default is no limit.",
+	)
+	flags.StringVar(
+		&o.PodResources.CPULimit,
+		"maintenance-job-cpu-limit",
+		o.PodResources.CPULimit,
+		"CPU limit for maintenance jobs. Default is no limit.",
+	)
+	flags.StringVar(
+		&o.PodResources.MemoryLimit,
+		"maintenance-job-mem-limit",
+		o.PodResources.MemoryLimit,
+		"Memory limit for maintenance jobs. Default is no limit.",
+	)
 }

 // NewInstallOptions instantiates a new, default InstallOptions struct.
@@ -231,7 +257,8 @@ func (o *Options) AsVeleroOptions() (*install.VeleroOptions, error) {
 		DefaultSnapshotMoveData:         o.DefaultSnapshotMoveData,
 		DisableInformerCache:            o.DisableInformerCache,
 		ScheduleSkipImmediately:         o.ScheduleSkipImmediately,
-		MaintenanceCfg:                  o.MaintenanceCfg,
+		PodResources:                    o.PodResources,
+		KeepLatestMaintenanceJobs:       o.KeepLatestMaintenanceJobs,
 	}, nil
 }

--- a/pkg/cmd/cli/nodeagent/server.go
+++ b/pkg/cmd/cli/nodeagent/server.go
@@ -294,7 +294,7 @@ 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)
@@ -316,7 +316,21 @@ 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")
 	}
--- a/pkg/cmd/server/config/config.go
+++ b/pkg/cmd/server/config/config.go
@@ -11,9 +11,9 @@ import (
 	"github.com/vmware-tanzu/velero/pkg/cmd/util/flag"
 	"github.com/vmware-tanzu/velero/pkg/constant"
 	"github.com/vmware-tanzu/velero/pkg/podvolume"
-	"github.com/vmware-tanzu/velero/pkg/repository"
 	"github.com/vmware-tanzu/velero/pkg/types"
 	"github.com/vmware-tanzu/velero/pkg/uploader"
+	"github.com/vmware-tanzu/velero/pkg/util/kube"
 	"github.com/vmware-tanzu/velero/pkg/util/logging"
 )

@@ -47,6 +47,12 @@ const (
 	// defaultCredentialsDirectory is the path on disk where credential
 	// files will be written to
 	defaultCredentialsDirectory = "/tmp/credentials"
+
+	DefaultKeepLatestMaintenanceJobs = 3
+	DefaultMaintenanceJobCPURequest  = "0"
+	DefaultMaintenanceJobCPULimit    = "0"
+	DefaultMaintenanceJobMemRequest  = "0"
+	DefaultMaintenanceJobMemLimit    = "0"
 )

 var (
@@ -164,9 +170,11 @@ type Config struct {
 	DefaultSnapshotMoveData        bool
 	DisableInformerCache           bool
 	ScheduleSkipImmediately        bool
-	MaintenanceCfg                 repository.MaintenanceConfig
-	BackukpRepoConfig              string
 	CredentialsDirectory           string
+	BackupRepoConfig               string
+	RepoMaintenanceJobConfig       string
+	PodResources                   kube.PodResources
+	KeepLatestMaintenanceJobs      int
 }

 func GetDefaultConfig() *Config {
@@ -197,13 +205,13 @@ func GetDefaultConfig() *Config {
 		DisableInformerCache:           defaultDisableInformerCache,
 		ScheduleSkipImmediately:        false,
 		CredentialsDirectory:           defaultCredentialsDirectory,
-	}
-
-	config.MaintenanceCfg = repository.MaintenanceConfig{
-		KeepLatestMaitenanceJobs: repository.DefaultKeepLatestMaitenanceJobs,
-		// maintenance job log setting inherited from velero server
-		FormatFlag:   config.LogFormat,
-		LogLevelFlag: config.LogLevel,
+		PodResources: kube.PodResources{
+			CPURequest:    DefaultMaintenanceJobCPULimit,
+			CPULimit:      DefaultMaintenanceJobCPURequest,
+			MemoryRequest: DefaultMaintenanceJobMemRequest,
+			MemoryLimit:   DefaultMaintenanceJobMemLimit,
+		},
+		KeepLatestMaintenanceJobs: DefaultKeepLatestMaintenanceJobs,
 	}

 	return config
@@ -238,11 +246,48 @@ func (c *Config) BindFlags(flags *pflag.FlagSet) {
 	flags.BoolVar(&c.DefaultSnapshotMoveData, "default-snapshot-move-data", c.DefaultSnapshotMoveData, "Move data by default for all snapshots supporting data movement.")
 	flags.BoolVar(&c.DisableInformerCache, "disable-informer-cache", c.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).")
 	flags.BoolVar(&c.ScheduleSkipImmediately, "schedule-skip-immediately", c.ScheduleSkipImmediately, "Skip the first scheduled backup immediately after creating a schedule. Default is false (don't skip).")
-	flags.IntVar(&c.MaintenanceCfg.KeepLatestMaitenanceJobs, "keep-latest-maintenance-jobs", c.MaintenanceCfg.KeepLatestMaitenanceJobs, "Number of latest maintenance jobs to keep each repository. Optional.")
-	flags.StringVar(&c.MaintenanceCfg.CPURequest, "maintenance-job-cpu-request", c.MaintenanceCfg.CPURequest, "CPU request for maintenance job. Default is no limit.")
-	flags.StringVar(&c.MaintenanceCfg.MemRequest, "maintenance-job-mem-request", c.MaintenanceCfg.MemRequest, "Memory request for maintenance job. Default is no limit.")
-	flags.StringVar(&c.MaintenanceCfg.CPULimit, "maintenance-job-cpu-limit", c.MaintenanceCfg.CPULimit, "CPU limit for maintenance job. Default is no limit.")
-	flags.StringVar(&c.MaintenanceCfg.MemLimit, "maintenance-job-mem-limit", c.MaintenanceCfg.MemLimit, "Memory limit for maintenance job. Default is no limit.")
-	flags.StringVar(&c.BackukpRepoConfig, "backup-repository-config", c.BackukpRepoConfig, "The name of configMap containing backup repository configurations.")
 	flags.Var(&c.DefaultVolumeSnapshotLocations, "default-volume-snapshot-locations", "List of unique volume providers and default volume snapshot location (provider1:location-01,provider2:location-02,...)")
+
+	flags.IntVar(
+		&c.KeepLatestMaintenanceJobs,
+		"keep-latest-maintenance-jobs",
+		c.KeepLatestMaintenanceJobs,
+		"Number of latest maintenance jobs to keep each repository. Optional.",
+	)
+	flags.StringVar(
+		&c.PodResources.CPURequest,
+		"maintenance-job-cpu-request",
+		c.PodResources.CPURequest,
+		"CPU request for maintenance job. Default is no limit.",
+	)
+	flags.StringVar(
+		&c.PodResources.MemoryRequest,
+		"maintenance-job-mem-request",
+		c.PodResources.MemoryRequest,
+		"Memory request for maintenance job. Default is no limit.",
+	)
+	flags.StringVar(
+		&c.PodResources.CPULimit,
+		"maintenance-job-cpu-limit",
+		c.PodResources.CPULimit,
+		"CPU limit for maintenance job. Default is no limit.",
+	)
+	flags.StringVar(
+		&c.PodResources.MemoryLimit,
+		"maintenance-job-mem-limit",
+		c.PodResources.MemoryLimit,
+		"Memory limit for maintenance job. Default is no limit.",
+	)
+	flags.StringVar(
+		&c.BackupRepoConfig,
+		"backup-repository-config",
+		c.BackupRepoConfig,
+		"The name of configMap containing backup repository configurations.",
+	)
+	flags.StringVar(
+		&c.RepoMaintenanceJobConfig,
+		"repo-maintenance-job-config",
+		c.RepoMaintenanceJobConfig,
+		"The name of ConfigMap containing repository maintenance Job configurations.",
+	)
 }
--- a/pkg/cmd/server/config/config_test.go
+++ b/pkg/cmd/server/config/config_test.go
@@ -9,11 +9,11 @@ import (

 func TestGetDefaultConfig(t *testing.T) {
 	config := GetDefaultConfig()
-	assert.Equal(t, "info", config.MaintenanceCfg.LogLevelFlag.String())
+	assert.Equal(t, "0", config.PodResources.CPULimit)
 }

 func TestBindFlags(t *testing.T) {
 	config := GetDefaultConfig()
 	config.BindFlags(pflag.CommandLine)
-	assert.Equal(t, "info", config.MaintenanceCfg.LogLevelFlag.String())
+	assert.Equal(t, "0", config.PodResources.CPULimit)
 }
--- a/pkg/cmd/server/server.go
+++ b/pkg/cmd/server/server.go
@@ -469,7 +469,20 @@ 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.config.PodResources,
+		s.config.KeepLatestMaintenanceJobs,
+		s.logger,
+		s.logLevel,
+		s.config.LogFormat,
+	)

 	return nil
 }
@@ -683,7 +696,14 @@ func (s *server) runControllers(defaultVolumeSnapshotLocations map[string]string
 	}

 	if _, ok := enabledRuntimeControllers[constant.ControllerBackupRepo]; 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", constant.ControllerBackupRepo)
 		}
 	}