mirror of
https://github.com/vmware-tanzu/velero.git
synced 2026-08-15 11:46:06 +00:00
Add schedule_expected_interval_seconds metric
Add a new Prometheus gauge metric that exposes the expected interval between consecutive scheduled backups. This enables dynamic alerting thresholds per schedule backups. Signed-off-by: Quang Ngo <quang.ngo@canonical.com>
This commit is contained in:
@@ -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
|
||||
|
||||
@@ -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 {
|
||||
|
||||
@@ -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) {
|
||||
|
||||
Reference in New Issue
Block a user