Merge branch 'main' into add-e2e-tests-for-PR9452

changelogs/unreleased/9547-blackpiglet

@@ -0,0 +1 @@
+If BIA return updateObj with SkipFromBackupAnnotation, treat it as skip the resource from backup.

changelogs/unreleased/9570-H-M-Quang-Ngo

@@ -0,0 +1 @@
+Add schedule_expected_interval_seconds metric for dynamic backup alerting thresholds (#9559)

pkg/apis/velero/v1/labels_annotations.go

@@ -102,6 +102,15 @@ const (
 	// even if the resource contains a matching selector label.
 	ExcludeFromBackupLabel = "velero.io/exclude-from-backup"
 
+	// SkipFromBackupAnnotation is the annotation used by internal BackupItemActions
+	// to indicate that a resource should be skipped from backup,
+	// even if it doesn't have the ExcludeFromBackupLabel.
+	// This is used in cases where we want to skip backup of a resource based on some logic in a plugin.
+	//
+	// Notice: SkipFromBackupAnnotation's priority is higher than MustIncludeAdditionalItemAnnotation.
+	// If SkipFromBackupAnnotation is set, the resource will be skipped even if MustIncludeAdditionalItemAnnotation is set.
+	SkipFromBackupAnnotation = "velero.io/skip-from-backup"
+
 	// defaultVGSLabelKey is the default label key used to group PVCs under a VolumeGroupSnapshot
 	DefaultVGSLabelKey = "velero.io/volume-group"
 

pkg/backup/backed_up_items_map.go

@@ -98,6 +98,14 @@ func (m *backedUpItemsMap) AddItem(key itemKey) {
 	m.totalItems[key] = struct{}{}
 }
 
+func (m *backedUpItemsMap) DeleteItem(key itemKey) {
+	m.Lock()
+	defer m.Unlock()
+
+	delete(m.backedUpItems, key)
+	delete(m.totalItems, key)
+}
+
 func (m *backedUpItemsMap) AddItemToTotal(key itemKey) {
 	m.Lock()
 	defer m.Unlock()

pkg/backup/item_backupper.go

@@ -244,6 +244,14 @@ func (ib *itemBackupper) backupItemInternal(logger logrus.FieldLogger, obj runti
 		return false, itemFiles, kubeerrs.NewAggregate(backupErrs)
 	}
 
+	// If err is nil and updatedObj is nil, it means the item is skipped by plugin action,
+	// we should return here to avoid backing up the item, and avoid potential NPE in the following code.
+	if updatedObj == nil {
+		log.Infof("Remove item from the backup's backupItems list and totalItems list because it's skipped by plugin action.")
+		ib.backupRequest.BackedUpItems.DeleteItem(key)
+		return false, itemFiles, nil
+	}
+
 	itemFiles = append(itemFiles, additionalItemFiles...)
 	obj = updatedObj
 	if metadata, err = meta.Accessor(obj); err != nil {
@@ -398,6 +406,13 @@ func (ib *itemBackupper) executeActions(
 		}
 
 		u := &unstructured.Unstructured{Object: updatedItem.UnstructuredContent()}
+
+		if _, ok := u.GetAnnotations()[velerov1api.SkipFromBackupAnnotation]; ok {
+			log.Infof("Resource (groupResource=%s, namespace=%s, name=%s) is skipped from backup by action %s.",
+				groupResource.String(), namespace, name, actionName)
+			return nil, itemFiles, nil
+		}
+
 		if actionName == csiBIAPluginName {
 			if additionalItemIdentifiers == nil && u.GetAnnotations()[velerov1api.SkippedNoCSIPVAnnotation] == "true" {
 				// snapshot was skipped by CSI plugin

pkg/controller/schedule_controller.go

@@ -129,6 +129,13 @@ func (c *scheduleReconciler) Reconcile(ctx context.Context, req ctrl.Request) (c
 	} else {
 		schedule.Status.Phase = velerov1.SchedulePhaseEnabled
 		schedule.Status.ValidationErrors = nil
+
+		// Compute expected interval between consecutive scheduled backup runs.
+		// Only meaningful when the cron expression is valid.
+		now := c.clock.Now()
+		nextRun := cronSchedule.Next(now)
+		nextNextRun := cronSchedule.Next(nextRun)
+		c.metrics.SetScheduleExpectedIntervalSeconds(schedule.Name, nextNextRun.Sub(nextRun).Seconds())
 	}
 
 	scheduleNeedsPatch := false

pkg/metrics/metrics.go

@@ -80,6 +80,9 @@ const (
 	DataDownloadFailureTotal = "data_download_failure_total"
 	DataDownloadCancelTotal  = "data_download_cancel_total"
 
+	// schedule metrics
+	scheduleExpectedIntervalSeconds = "schedule_expected_interval_seconds"
+
 	// repo maintenance metrics
 	repoMaintenanceSuccessTotal = "repo_maintenance_success_total"
 	repoMaintenanceFailureTotal = "repo_maintenance_failure_total"
@@ -347,6 +350,14 @@ func NewServerMetrics() *ServerMetrics {
 				},
 				[]string{scheduleLabel, backupNameLabel},
 			),
+			scheduleExpectedIntervalSeconds: prometheus.NewGaugeVec(
+				prometheus.GaugeOpts{
+					Namespace: metricNamespace,
+					Name:      scheduleExpectedIntervalSeconds,
+					Help:      "Expected interval between consecutive scheduled backups, in seconds",
+				},
+				[]string{scheduleLabel},
+			),
 			repoMaintenanceSuccessTotal: prometheus.NewCounterVec(
 				prometheus.CounterOpts{
 					Namespace: metricNamespace,
@@ -644,6 +655,9 @@ func (m *ServerMetrics) RemoveSchedule(scheduleName string) {
 	if c, ok := m.metrics[csiSnapshotFailureTotal].(*prometheus.CounterVec); ok {
 		c.DeleteLabelValues(scheduleName, "")
 	}
+	if g, ok := m.metrics[scheduleExpectedIntervalSeconds].(*prometheus.GaugeVec); ok {
+		g.DeleteLabelValues(scheduleName)
+	}
 }
 
 // InitMetricsForNode initializes counter metrics for a node.
@@ -758,6 +772,14 @@ func (m *ServerMetrics) SetBackupLastSuccessfulTimestamp(backupSchedule string,
 	}
 }
 
+// SetScheduleExpectedIntervalSeconds records the expected interval in seconds,
+// between consecutive backups for a schedule.
+func (m *ServerMetrics) SetScheduleExpectedIntervalSeconds(scheduleName string, seconds float64) {
+	if g, ok := m.metrics[scheduleExpectedIntervalSeconds].(*prometheus.GaugeVec); ok {
+		g.WithLabelValues(scheduleName).Set(seconds)
+	}
+}
+
 // SetBackupTotal records the current number of existent backups.
 func (m *ServerMetrics) SetBackupTotal(numberOfBackups int64) {
 	if g, ok := m.metrics[backupTotal].(prometheus.Gauge); ok {

pkg/metrics/metrics_test.go

@@ -259,6 +259,90 @@ func TestMultipleAdhocBackupsShareMetrics(t *testing.T) {
 	assert.Equal(t, float64(1), validationFailureMetric, "All adhoc validation failures should be counted together")
 }
 
+// TestSetScheduleExpectedIntervalSeconds verifies that the expected interval metric
+// is properly recorded for schedules.
+func TestSetScheduleExpectedIntervalSeconds(t *testing.T) {
+	tests := []struct {
+		name            string
+		scheduleName    string
+		intervalSeconds float64
+		description     string
+	}{
+		{
+			name:            "every 5 minutes schedule",
+			scheduleName:    "frequent-backup",
+			intervalSeconds: 300,
+			description:     "Expected interval should be 5m in seconds",
+		},
+		{
+			name:            "daily schedule",
+			scheduleName:    "daily-backup",
+			intervalSeconds: 86400,
+			description:     "Expected interval should be 24h in seconds",
+		},
+		{
+			name:            "monthly schedule",
+			scheduleName:    "monthly-backup",
+			intervalSeconds: 2678400, // 31 days in seconds
+			description:     "Expected interval should be 31 days in seconds",
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			m := NewServerMetrics()
+			m.SetScheduleExpectedIntervalSeconds(tc.scheduleName, tc.intervalSeconds)
+
+			metric := getMetricValue(t, m.metrics[scheduleExpectedIntervalSeconds].(*prometheus.GaugeVec), tc.scheduleName)
+			assert.Equal(t, tc.intervalSeconds, metric, tc.description)
+		})
+	}
+}
+
+// TestScheduleExpectedIntervalNotInitializedByDefault verifies that the expected
+// interval metric is not initialized by InitSchedule, so it only appears for
+// schedules with a valid cron expression.
+func TestScheduleExpectedIntervalNotInitializedByDefault(t *testing.T) {
+	m := NewServerMetrics()
+	m.InitSchedule("test-schedule")
+
+	// The metric should not have any values after InitSchedule
+	ch := make(chan prometheus.Metric, 1)
+	m.metrics[scheduleExpectedIntervalSeconds].(*prometheus.GaugeVec).Collect(ch)
+	close(ch)
+
+	count := 0
+	for range ch {
+		count++
+	}
+	assert.Equal(t, 0, count, "scheduleExpectedIntervalSeconds should not be initialized by InitSchedule")
+}
+
+// TestRemoveScheduleCleansUpExpectedInterval verifies that RemoveSchedule
+// cleans up the expected interval metric.
+func TestRemoveScheduleCleansUpExpectedInterval(t *testing.T) {
+	m := NewServerMetrics()
+	m.InitSchedule("test-schedule")
+	m.SetScheduleExpectedIntervalSeconds("test-schedule", 3600)
+
+	// Verify metric exists
+	metric := getMetricValue(t, m.metrics[scheduleExpectedIntervalSeconds].(*prometheus.GaugeVec), "test-schedule")
+	assert.Equal(t, float64(3600), metric)
+
+	// Remove schedule and verify metric is cleaned up
+	m.RemoveSchedule("test-schedule")
+
+	ch := make(chan prometheus.Metric, 1)
+	m.metrics[scheduleExpectedIntervalSeconds].(*prometheus.GaugeVec).Collect(ch)
+	close(ch)
+
+	count := 0
+	for range ch {
+		count++
+	}
+	assert.Equal(t, 0, count, "scheduleExpectedIntervalSeconds should be removed after RemoveSchedule")
+}
+
 // TestInitScheduleWithEmptyName verifies that InitSchedule works correctly
 // with an empty schedule name (for adhoc backups).
 func TestInitScheduleWithEmptyName(t *testing.T) {

pkg/util/podvolume/pod_volume_test.go

@@ -156,7 +156,7 @@ func TestGetVolumesByPod(t *testing.T) {
 					Volumes: []corev1api.Volume{
 						// PVB Volumes
 						{Name: "pvbPV1"}, {Name: "pvbPV2"}, {Name: "pvbPV3"},
-						/// Excluded from PVB because colume mounting default service account token
+						/// Excluded from PVB because volume mounting default service account token
 						{Name: "default-token-5xq45"},
 					},
 				},

site/config.yaml

@@ -12,7 +12,7 @@ params:
   hero:
     backgroundColor: med-blue
   versioning: true
-  latest: v1.17
+  latest: v1.18
   versions:
     - main
     - v1.18