v0.168.0: customer-configurable backup window (Mentési időablak)
ONE setting (window start W) drives every nightly leg at fixed, never-stored offsets: DB dump at W, tier-2 at W+60m, off-box at W+105m (wrap-safe). Precedence settings > controller.yaml db_dump_schedule > 02:30. - scheduler.UpdateDaily: retime a daily job at runtime (no restart) via a per-job buffered resched chan + a select case in runDailyJob. - new pure package internal/backupwindow (LegTimes/GateWindow/EffectiveWindow). - quiesce disk-tier window gate: scheduled cycles run only inside [W+2h,W+6h) with a safety valve (age>cadence+24h runs regardless); manual TriggerNow never gated. Backend.Due now also returns the backup age (from the agent's own /backup/due). - backup page: Mentési időablak card (time input + derived leg/gate rows); POST /backups/window validates -> saves -> UpdateDaily x3 -> flash. Tests: 5 groups, all red-proofed. Agent/cadence//backup/due untouched.
This commit is contained in:
@@ -20,6 +20,8 @@ import (
|
||||
"path/filepath"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"gitea.dooplex.hu/admin/felhom-controller/internal/backupwindow"
|
||||
)
|
||||
|
||||
// ErrBackupInProgress is returned by TriggerNow when a scheduled or manual quiesce cycle is already
|
||||
@@ -27,9 +29,11 @@ import (
|
||||
var ErrBackupInProgress = errors.New("quiesce: a backup cycle is already in progress")
|
||||
|
||||
// Backend is the agent local-API surface the loop needs (satisfied by an adapter over
|
||||
// *agentapi.Client). Kept minimal (bool/string) so the loop is testable with plain fakes.
|
||||
// *agentapi.Client). Kept minimal (bool/int/string) so the loop is testable with plain fakes.
|
||||
// Due also returns the age of the newest successful backup in seconds (nil = none yet) — the
|
||||
// window gate's safety valve reads it so a box powered on only outside its window never starves.
|
||||
type Backend interface {
|
||||
Due(ctx context.Context) (bool, error)
|
||||
Due(ctx context.Context) (due bool, ageSecs *int64, err error)
|
||||
StartBackup(ctx context.Context) (jobID string, err error)
|
||||
BackupStatus(ctx context.Context) (phase string, err error)
|
||||
}
|
||||
@@ -68,6 +72,13 @@ type Options struct {
|
||||
StatusPoll time.Duration // how often to poll /backup/status while quiesced
|
||||
MaxQuiesce time.Duration // hard bound on app downtime (unquiesce no matter what)
|
||||
Logger *log.Logger
|
||||
// WindowStartFn returns the CURRENT effective backup-window start "HH:MM" (customer-configurable,
|
||||
// so it is read fresh each poll — a window change must take effect without restart). When nil the
|
||||
// window gate is disabled and a due cycle runs whenever the agent says due (pre-v0.168.0 behavior).
|
||||
WindowStartFn func() string
|
||||
// Cadence is the agent's backup cadence, used only by the gate's safety valve (run regardless of
|
||||
// the window once the last successful backup is older than Cadence+24h). Defaults to 24h.
|
||||
Cadence time.Duration
|
||||
}
|
||||
|
||||
// Loop is the quiesce background loop.
|
||||
@@ -80,6 +91,9 @@ type Loop struct {
|
||||
maxQuiesce time.Duration
|
||||
logger *log.Logger
|
||||
now func() time.Time
|
||||
// windowStartFn (nil = gate disabled) + cadence drive the scheduled-cycle window gate (Part 3).
|
||||
windowStartFn func() string
|
||||
cadence time.Duration
|
||||
// mu single-flights the quiesce cycle across the scheduled loop AND the manual trigger, so the
|
||||
// two can never stop the same stacks concurrently (the persisted marker covers crash-safety across
|
||||
// restarts; this covers concurrency within the process — which a manual trigger introduces).
|
||||
@@ -100,10 +114,14 @@ func New(o Options) *Loop {
|
||||
if o.Logger == nil {
|
||||
o.Logger = log.Default()
|
||||
}
|
||||
if o.Cadence <= 0 {
|
||||
o.Cadence = 24 * time.Hour
|
||||
}
|
||||
return &Loop{
|
||||
backend: o.Backend, stacks: o.Stacks, markerPath: o.MarkerPath,
|
||||
poll: o.Poll, statusPoll: o.StatusPoll, maxQuiesce: o.MaxQuiesce,
|
||||
logger: o.Logger, now: time.Now,
|
||||
windowStartFn: o.WindowStartFn, cadence: o.Cadence,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -159,7 +177,7 @@ func (l *Loop) runOnce(ctx context.Context) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
due, err := l.backend.Due(ctx)
|
||||
due, ageSecs, err := l.backend.Due(ctx)
|
||||
if err != nil {
|
||||
return fmt.Errorf("check due: %w", err)
|
||||
}
|
||||
@@ -167,6 +185,17 @@ func (l *Loop) runOnce(ctx context.Context) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// Window gate (Part 3) — SCHEDULED path only. TriggerNow calls quiesceAndPoll directly and is
|
||||
// never gated. Disabled when no window fn is wired (pre-v0.168.0 behavior).
|
||||
if l.windowStartFn != nil {
|
||||
window := l.windowStartFn()
|
||||
if !scheduledRunAllowed(l.now().In(budapestLocation()), window, ageSecs, l.cadence) {
|
||||
from, to := gateBounds(window)
|
||||
l.logger.Printf("[DEBUG] [quiesce] scheduled backup due but outside the backup window [%s–%s) — deferring to the next poll inside it", from, to)
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
return l.quiesceAndPoll(ctx)
|
||||
}
|
||||
|
||||
@@ -286,6 +315,63 @@ func (l *Loop) quiesceAndPoll(ctx context.Context) error {
|
||||
}
|
||||
}
|
||||
|
||||
// ---- window gate (Part 3, v0.168.0) -----------------------------------------------------
|
||||
|
||||
var (
|
||||
quiesceBudapest *time.Location
|
||||
quiesceBudapestOnce sync.Once
|
||||
)
|
||||
|
||||
func budapestLocation() *time.Location {
|
||||
quiesceBudapestOnce.Do(func() {
|
||||
loc, err := time.LoadLocation("Europe/Budapest")
|
||||
if err != nil {
|
||||
quiesceBudapest = time.UTC
|
||||
return
|
||||
}
|
||||
quiesceBudapest = loc
|
||||
})
|
||||
return quiesceBudapest
|
||||
}
|
||||
|
||||
const (
|
||||
gateOpenOffsetMin = 120 // gate opens at W+2h
|
||||
gateSpanMin = 240 // 4h span → [W+2h, W+6h)
|
||||
)
|
||||
|
||||
// scheduledRunAllowed decides whether a DUE, scheduled whole-guest backup may run at `now` (passed by
|
||||
// the caller as Budapest wall-clock — only its hour/minute are read). True when now is inside the gate
|
||||
// window [W+2h, W+6h); otherwise true ONLY if the safety valve holds — the newest successful backup is
|
||||
// missing (nil) or older than cadence+24h — so a box powered on only outside its window never starves.
|
||||
// An unparseable window fails OPEN (allow) rather than block backups forever.
|
||||
func scheduledRunAllowed(now time.Time, windowStart string, lastAgeSecs *int64, cadence time.Duration) bool {
|
||||
startMin, err := backupwindow.ParseHHMM(windowStart)
|
||||
if err != nil {
|
||||
return true
|
||||
}
|
||||
nowMin := now.Hour()*60 + now.Minute()
|
||||
if within(nowMin, mod1440(startMin+gateOpenOffsetMin), gateSpanMin) {
|
||||
return true
|
||||
}
|
||||
// Outside the window: only the safety valve may run it.
|
||||
if lastAgeSecs == nil {
|
||||
return true // no recorded backup yet — never withhold the first one
|
||||
}
|
||||
return time.Duration(*lastAgeSecs)*time.Second > cadence+24*time.Hour
|
||||
}
|
||||
|
||||
// gateBounds returns the gate window [W+2h, W+6h) as HH:MM for the deferral log line.
|
||||
func gateBounds(windowStart string) (from, to string) {
|
||||
return backupwindow.GateWindow(windowStart)
|
||||
}
|
||||
|
||||
func mod1440(m int) int { return ((m % 1440) + 1440) % 1440 }
|
||||
|
||||
// within reports whether minute-of-day p falls in [start, start+span) modulo 24h (wrap-safe).
|
||||
func within(p, start, span int) bool {
|
||||
return mod1440(p-start) < span
|
||||
}
|
||||
|
||||
func (l *Loop) restartAll(stacks []string) {
|
||||
for _, s := range stacks {
|
||||
if err := l.stacks.StartStack(s); err != nil {
|
||||
|
||||
Reference in New Issue
Block a user