Add maintenance windows for planned work

This commit is contained in:
Maxim
2026-08-06 19:35:33 +03:00
parent c01b4b6630
commit 5401b5b0f2
8 changed files with 334 additions and 59 deletions

View File

@@ -6,16 +6,18 @@ import (
)
type AlertEvent struct {
EventID int64 `json:"eventId"`
ID string `json:"id"`
Severity string `json:"severity"`
Source string `json:"source"`
Title string `json:"title"`
Message string `json:"message"`
FirstSeen int64 `json:"firstSeen"`
LastSeen int64 `json:"lastSeen"`
ResolvedAt *int64 `json:"resolvedAt,omitempty"`
AcknowledgedAt *int64 `json:"acknowledgedAt,omitempty"`
EventID int64 `json:"eventId"`
ID string `json:"id"`
Severity string `json:"severity"`
Source string `json:"source"`
Title string `json:"title"`
Message string `json:"message"`
FirstSeen int64 `json:"firstSeen"`
LastSeen int64 `json:"lastSeen"`
ResolvedAt *int64 `json:"resolvedAt,omitempty"`
AcknowledgedAt *int64 `json:"acknowledgedAt,omitempty"`
Planned bool `json:"planned"`
MaintenanceReason string `json:"maintenanceReason,omitempty"`
}
type RecoveryEvent struct {
@@ -24,13 +26,17 @@ type RecoveryEvent struct {
}
func (s *Store) SyncAlerts(alerts []Alert) ([]Alert, error) {
return s.SyncAlertsWithMaintenance(alerts, nil, "")
}
func (s *Store) SyncAlertsWithMaintenance(alerts, plannedAlerts []Alert, maintenanceReason string) ([]Alert, error) {
tx, err := s.db.Begin()
if err != nil {
return alerts, err
}
defer tx.Rollback()
now := time.Now().Unix()
rows, err := tx.Query(`SELECT id,alert_key FROM alert_events WHERE resolved_at IS NULL`)
rows, err := tx.Query(`SELECT id,alert_key,planned FROM alert_events WHERE resolved_at IS NULL`)
if err != nil {
return alerts, err
}
@@ -38,28 +44,43 @@ func (s *Store) SyncAlerts(alerts []Alert) ([]Alert, error) {
for rows.Next() {
var id int64
var key string
if err := rows.Scan(&id, &key); err != nil {
var planned bool
if err := rows.Scan(&id, &key, &planned); err != nil {
rows.Close()
return alerts, err
}
active[key] = id
active[alertEventKey(key, planned)] = id
}
rows.Close()
seen := map[string]bool{}
for _, alert := range alerts {
seen[alert.ID] = true
if id, ok := active[alert.ID]; ok {
_, err = tx.Exec(`UPDATE alert_events SET severity=?,source=?,title=?,message=?,last_seen=? WHERE id=?`, alert.Severity, alert.Source, alert.Title, alert.Message, now, id)
} else {
result, insertErr := tx.Exec(`INSERT INTO alert_events(alert_key,severity,source,title,message,first_seen,last_seen) VALUES(?,?,?,?,?,?,?)`, alert.ID, alert.Severity, alert.Source, alert.Title, alert.Message, now, now)
if insertErr != nil {
return alerts, insertErr
syncGroup := func(group []Alert, planned bool) error {
for _, alert := range group {
key := alertEventKey(alert.ID, planned)
seen[key] = true
reason := ""
if planned {
reason = maintenanceReason
}
if id, ok := active[key]; ok {
_, err = tx.Exec(`UPDATE alert_events SET severity=?,source=?,title=?,message=?,last_seen=?,maintenance_reason=? WHERE id=?`, alert.Severity, alert.Source, alert.Title, alert.Message, now, reason, id)
} else {
result, insertErr := tx.Exec(`INSERT INTO alert_events(alert_key,severity,source,title,message,first_seen,last_seen,planned,maintenance_reason) VALUES(?,?,?,?,?,?,?,?,?)`, alert.ID, alert.Severity, alert.Source, alert.Title, alert.Message, now, now, planned, reason)
if insertErr != nil {
return insertErr
}
active[key], _ = result.LastInsertId()
}
if err != nil {
return err
}
active[alert.ID], _ = result.LastInsertId()
}
if err != nil {
return alerts, err
}
return nil
}
if err = syncGroup(alerts, false); err != nil {
return alerts, err
}
if err = syncGroup(plannedAlerts, true); err != nil {
return alerts, err
}
for key, id := range active {
if !seen[key] {
@@ -74,7 +95,7 @@ func (s *Store) SyncAlerts(alerts []Alert) ([]Alert, error) {
if err = tx.Commit(); err != nil {
return alerts, err
}
rows, err = s.db.Query(`SELECT id,alert_key,severity,source,title,message,first_seen,last_seen FROM alert_events WHERE resolved_at IS NULL AND acknowledged_at IS NULL ORDER BY CASE severity WHEN 'critical' THEN 0 WHEN 'warning' THEN 1 ELSE 2 END,first_seen DESC`)
rows, err = s.db.Query(`SELECT id,alert_key,severity,source,title,message,first_seen,last_seen FROM alert_events WHERE resolved_at IS NULL AND acknowledged_at IS NULL AND planned=0 ORDER BY CASE severity WHEN 'critical' THEN 0 WHEN 'warning' THEN 1 ELSE 2 END,first_seen DESC`)
if err != nil {
return alerts, err
}
@@ -90,6 +111,13 @@ func (s *Store) SyncAlerts(alerts []Alert) ([]Alert, error) {
return visible, rows.Err()
}
func alertEventKey(id string, planned bool) string {
if planned {
return id + "\x00planned"
}
return id + "\x00active"
}
func (s *Store) AcknowledgeAlert(eventID int64) error {
_, err := s.db.Exec(`UPDATE alert_events SET acknowledged_at=? WHERE id=? AND acknowledged_at IS NULL`, time.Now().Unix(), eventID)
return err
@@ -99,7 +127,7 @@ func (s *Store) AlertHistory(limit int) ([]AlertEvent, error) {
if limit < 1 || limit > 500 {
limit = 200
}
rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message,first_seen,last_seen,resolved_at,acknowledged_at FROM alert_events ORDER BY first_seen DESC LIMIT ?`, limit)
rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message,first_seen,last_seen,resolved_at,acknowledged_at,planned,maintenance_reason FROM alert_events ORDER BY first_seen DESC LIMIT ?`, limit)
if err != nil {
return nil, err
}
@@ -108,7 +136,7 @@ func (s *Store) AlertHistory(limit int) ([]AlertEvent, error) {
for rows.Next() {
var e AlertEvent
var resolved, acked sql.NullInt64
if err = rows.Scan(&e.EventID, &e.ID, &e.Severity, &e.Source, &e.Title, &e.Message, &e.FirstSeen, &e.LastSeen, &resolved, &acked); err != nil {
if err = rows.Scan(&e.EventID, &e.ID, &e.Severity, &e.Source, &e.Title, &e.Message, &e.FirstSeen, &e.LastSeen, &resolved, &acked, &e.Planned, &e.MaintenanceReason); err != nil {
return nil, err
}
if resolved.Valid {
@@ -123,7 +151,7 @@ func (s *Store) AlertHistory(limit int) ([]AlertEvent, error) {
}
func (s *Store) PendingEmailAlerts() ([]Alert, error) {
rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NULL AND acknowledged_at IS NULL AND email_sent_at IS NULL ORDER BY first_seen`)
rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NULL AND acknowledged_at IS NULL AND email_sent_at IS NULL AND planned=0 ORDER BY first_seen`)
if err != nil {
return nil, err
}
@@ -155,7 +183,7 @@ func (s *Store) MarkAlertsEmailed(alerts []Alert) error {
}
func (s *Store) PendingImmediateAlerts() ([]Alert, error) {
rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NULL AND acknowledged_at IS NULL AND email_sent_at IS NULL AND (severity='critical' OR alert_key='ups-battery') ORDER BY first_seen`)
rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NULL AND acknowledged_at IS NULL AND email_sent_at IS NULL AND planned=0 AND (severity='critical' OR alert_key='ups-battery') ORDER BY first_seen`)
if err != nil {
return nil, err
}
@@ -171,7 +199,7 @@ func (s *Store) PendingImmediateAlerts() ([]Alert, error) {
return out, rows.Err()
}
func (s *Store) PendingRecoveries() ([]RecoveryEvent, error) {
rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NOT NULL AND email_sent_at IS NOT NULL AND recovery_sent_at IS NULL ORDER BY resolved_at`)
rows, err := s.db.Query(`SELECT id,alert_key,severity,source,title,message FROM alert_events WHERE resolved_at IS NOT NULL AND email_sent_at IS NOT NULL AND recovery_sent_at IS NULL AND planned=0 ORDER BY resolved_at`)
if err != nil {
return nil, err
}