Expose Medusa backup size

CHANGELOG/CHANGELOG-1.11.md

@@ -14,3 +14,5 @@ Changelog for the K8ssandra Operator, new PRs should update the `unreleased` sec
 When cutting a new release, update the `unreleased` heading to the tag being generated and date, like `## vX.Y.Z - YYYY-MM-DD` and create a new placeholder section for  `unreleased` entries.
 
 ## unreleased
+
+* [ENHANCEMENT] [#1122](https://github.com/k8ssandra/k8ssandra-operator/issues/1122) Expose backup size in MedusaBackup CRD

apis/medusa/v1alpha1/medusabackup_types.go

@@ -42,6 +42,8 @@ type MedusaBackupStatus struct {
 	TotalNodes    int32               `json:"totalNodes,omitempty"`
 	FinishedNodes int32               `json:"finishedNodes,omitempty"`
 	Nodes         []*MedusaBackupNode `json:"nodes,omitempty"`
+	TotalFiles    int64               `json:"totalFiles,omitempty"`
+	TotalSize     string              `json:"totalSize,omitempty"`
 	Status        string              `json:"status,omitempty"`
 }
 
@@ -57,6 +59,8 @@ type MedusaBackupNode struct {
 //+kubebuilder:printcolumn:name="Started",type=date,JSONPath=".status.startTime",description="Backup start time"
 //+kubebuilder:printcolumn:name="Finished",type=date,JSONPath=".status.finishTime",description="Backup finish time"
 //+kubebuilder:printcolumn:name="Nodes",type=string,JSONPath=".status.totalNodes",description="Total number of nodes at the time of the backup"
+//+kubebuilder:printcolumn:name="Files",type=integer,JSONPath=".status.totalFiles",description="Total number of files in the backup"
+//+kubebuilder:printcolumn:name="Size",type=string,JSONPath=".status.totalSize",description="Human-readable total size of the backup"
 //+kubebuilder:printcolumn:name="Completed",type=string,JSONPath=".status.finishedNodes",description="Number of nodes that completed this backup"
 //+kubebuilder:printcolumn:name="Status",type=string,JSONPath=".status.status",description="Backup completion status"
 

config/crd/bases/medusa.k8ssandra.io_medusabackups.yaml

@@ -27,6 +27,14 @@ spec:
       jsonPath: .status.totalNodes
       name: Nodes
       type: string
+    - description: Total number of files in the backup
+      jsonPath: .status.totalFiles
+      name: Files
+      type: integer
+    - description: Human-readable total size of the backup
+      jsonPath: .status.totalSize
+      name: Size
+      type: string
     - description: Number of nodes that completed this backup
       jsonPath: .status.finishedNodes
       name: Completed
@@ -98,9 +106,14 @@ spec:
                 type: string
               status:
                 type: string
+              totalFiles:
+                format: int64
+                type: integer
               totalNodes:
                 format: int32
                 type: integer
+              totalSize:
+                type: string
             type: object
         type: object
     served: true

controllers/medusa/medusabackupjob_controller.go

@@ -274,6 +274,8 @@ func (r *MedusaBackupJobReconciler) createMedusaBackup(ctx context.Context, back
 				backupResource.Status.FinishTime = finishTime
 				backupResource.Status.TotalNodes = backupSummary.TotalNodes
 				backupResource.Status.FinishedNodes = backupSummary.FinishedNodes
+				backupResource.Status.TotalFiles = backupSummary.TotalObjects
+				backupResource.Status.TotalSize = humanize(backupSummary.TotalSize)
 				backupResource.Status.Nodes = make([]*medusav1alpha1.MedusaBackupNode, len(backupSummary.Nodes))
 				for i, node := range backupSummary.Nodes {
 					backupResource.Status.Nodes[i] = &medusav1alpha1.MedusaBackupNode{
@@ -336,3 +338,13 @@ func (r *MedusaBackupJobReconciler) SetupWithManager(mgr ctrl.Manager) error {
 		For(&medusav1alpha1.MedusaBackupJob{}, builder.WithPredicates(predicate.GenerationChangedPredicate{})).
 		Complete(r)
 }
+
+func humanize(bytes int64) string {
+	units := []string{"B", "KB", "MB", "GB", "TB", "PB"}
+	size := float64(bytes)
+	i := 0
+	for ; size >= 1024 && i < len(units)-1; i++ {
+		size /= 1024
+	}
+	return fmt.Sprintf("%.2f %s", size, units[i])
+}

controllers/medusa/medusabackupjob_controller_test.go

@@ -33,6 +33,9 @@ const (
 	defaultBackupName   = "backup1"
 	dc1PodPrefix        = "192.168.1."
 	dc2PodPrefix        = "192.168.2."
+	fakeBackupFileCount = int64(13)
+	fakeBackupByteSize  = int64(42)
+	fakeBackupHumanSize = "42.00 B"
 )
 
 func testMedusaBackupDatacenter(t *testing.T, ctx context.Context, f *framework.Framework, namespace string) {
@@ -243,6 +246,8 @@ func createAndVerifyMedusaBackup(dcKey framework.ClusterKey, dc *cassdcapi.Cassa
 	require.Equal(medusaBackup.Status.TotalNodes, dc.Spec.Size, "backup total nodes doesn't match dc nodes")
 	require.Equal(medusaBackup.Status.FinishedNodes, dc.Spec.Size, "backup finished nodes doesn't match dc nodes")
 	require.Equal(len(medusaBackup.Status.Nodes), int(dc.Spec.Size), "backup topology doesn't match dc topology")
+	require.Equal(medusaBackup.Status.TotalFiles, fakeBackupFileCount, "backup total files doesn't match")
+	require.Equal(medusaBackup.Status.TotalSize, fakeBackupHumanSize, "backup total size doesn't match")
 	require.Equal(medusa.StatusType_SUCCESS.String(), medusaBackup.Status.Status, "backup status is not success")
 
 	require.Equal(int(dc.Spec.Size), len(medusaClientFactory.GetRequestedBackups(dc.DatacenterName())))
@@ -354,6 +359,8 @@ func (c *fakeMedusaClient) GetBackups(ctx context.Context) ([]*medusa.BackupSumm
 			FinishTime:    10,
 			TotalNodes:    3,
 			FinishedNodes: 3,
+			TotalObjects:  fakeBackupFileCount,
+			TotalSize:     fakeBackupByteSize,
 			Status:        *medusa.StatusType_SUCCESS.Enum(),
 			Nodes: []*medusa.BackupNode{
 				{
@@ -502,3 +509,22 @@ func reconcileMedusaStandaloneDeployment(ctx context.Context, t *testing.T, f *f
 
 	require.NoError(t, err, "Failed to update Medusa Deployment status")
 }
+
+func TestHumanize(t *testing.T) {
+	t.Run("humanizeTrivialSizes", humanizeTrivialSizes)
+	t.Run("humanizeArbitrarySizes", humanizeArbitrarySizes)
+}
+
+func humanizeTrivialSizes(t *testing.T) {
+	assert.Equal(t, "1.00 B", humanize(1))
+	assert.Equal(t, "1.00 KB", humanize(1024))
+	assert.Equal(t, "1.00 MB", humanize(1024*1024))
+	assert.Equal(t, "1.00 GB", humanize(1024*1024*1024))
+}
+
+func humanizeArbitrarySizes(t *testing.T) {
+	assert.Equal(t, "127.50 KB", humanize(130557))
+	assert.Equal(t, "4.03 GB", humanize(4325130557))
+	assert.Equal(t, "7.67 TB", humanize(8434729356343))
+	assert.Equal(t, "1096.52 PB", humanize(1234567890123456790))
+}

docs/content/en/tasks/backup-restore/_index.md

@@ -128,7 +128,7 @@ K8ssandra Operator will detect the `MedusaBackupJob` object creation and trigger
 To monitor the backup completion, check if the `finishTime` is set in the `MedusaBackupJob` object status. Example:
 
 ```sh
-% kubectl get medusabackupjob/medusa-backup1 -o yaml
+% kubectl get medusabackupjob/backup1 -o yaml
 
 kind: MedusaBackupJob
 metadata:
@@ -159,7 +159,7 @@ medusa-backup1   19m       19m
 
 All pods having completed the backup will be in the `finished` list.
 At the end of the backup operation, a `MedusaBackup` custom resource will be created with the same name as the `MedusaBackupJob` object. It materializes the backup locally on the Kubernetes cluster.
-The MedusaBackup object status contains the total number of node in the cluster at the time of the backup, the number of nodes that successfully achieved the backup, and the topology of the DC at the time of the backup:
+The MedusaBackup object status contains the total number of node in the cluster at the time of the backup, the number of nodes that successfully achieved the backup, the topology of the DC at the time of the backup, the number of files backed up and their total size:
 
 ```yaml
 apiVersion: medusa.k8ssandra.io/v1alpha1
@@ -189,6 +189,8 @@ status:
         - -1058110708807841300
         - -107256661843445790
   status: SUCCESS
+  totalFiles: 120
+  totalSize: 127.67 KB  
 spec:
   backupType: differential
   cassandraDatacenter: dc1
@@ -199,9 +201,9 @@ The `kubectl get`` output for MedusaBackup objects will show a subset of this in
 
 ```sh
 kubectl get MedusaBackup -A
-NAME             STARTED   FINISHED   NODES   COMPLETED   STATUS
-backup1          29m       28m        2       2           SUCCESS
-medusa-backup1   23m       23m        2       2           SUCCESS
+NAME             STARTED   FINISHED   NODES   FILES   SIZE       COMPLETED   STATUS
+backup1          29m       28m        2       120     127.67 KB  2           SUCCESS
+medusa-backup1   23m       23m        2       137     241.61 KB  2           SUCCESS
 ```
 
 For a restore to be possible, a `MedusaBackup` object must exist.

go.mod

@@ -27,7 +27,7 @@ require (
 	github.com/stretchr/testify v1.8.2
 	go.uber.org/zap v1.24.0
 	google.golang.org/grpc v1.49.0
-	google.golang.org/protobuf v1.30.0
+	google.golang.org/protobuf v1.31.0
 	gopkg.in/resty.v1 v1.12.0
 	gopkg.in/yaml.v2 v2.4.0
 	k8s.io/api v0.26.4

go.sum

@@ -1598,8 +1598,8 @@ google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQ
 google.golang.org/protobuf v1.27.1/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
 google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
 google.golang.org/protobuf v1.28.1/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
-google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=
-google.golang.org/protobuf v1.30.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
+google.golang.org/protobuf v1.31.0 h1:g0LDEJHgrBl9N9r17Ru3sqWhkIx2NB67okBHPwC7hs8=
+google.golang.org/protobuf v1.31.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
 gopkg.in/airbrake/gobrake.v2 v2.0.9/go.mod h1:/h5ZAUhDkGaJfjzjKLSjv6zCL6O0LLBxU4K+aSYdM/U=
 gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw=
 gopkg.in/asn1-ber.v1 v1.0.0-20170511165959-379148ca0225/go.mod h1:cuepJuh7vyXfUyUwEgHQXw849cJrilpS5NeIjOWESAw=