Files
felhom-agent/internal/backup/schedule.go
T
admin 6e86483185 restore-test: verdict is liveness, not start-task exitstatus (v0.7.0)
Fixes the crying-wolf false-fail surfaced by the live hub-enrollment runbook:
PVE's guest-start task exits "WARNINGS: 1" for the benign systemd-nesting
advisory, and WaitTask treated any non-OK exitstatus as failure, so the verdict
was decided by an advisory exit code before the real boot check ran. Every
modern-distro restore-test reported pass:false.

- proxmox.WaitOptions.AllowWarnings (opt-in; default keeps all callers strict)
- restore-test start step accepts warnings, surfaces them, verdict stays waitRunning
- RestoreTestResult.StartWarnings/.WarningsRecognized + version-free "enable
  nesting" recognizer (can't rot back at systemd 258+); GuestAPI.TaskLogTail
- hub.RestoreTest.warnings/.warnings_recognized wire fields (consumed by hub v0.7.5)
- scheduler logs clean / passed-with-recognized / passed-with-unrecognized warnings
- tests: WaitTask warnings matrix; restore-test pass/fail-on-liveness; version-free
  regression guard (systemd 256-300)

Single agent bump 0.6.0 -> 0.7.0 covering the agent half of both task phases.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-09 19:30:03 +02:00

121 lines
4.2 KiB
Go

package backup
import (
"context"
"log/slog"
"time"
"gitea.dooplex.hu/admin/felhom-agent/internal/reconcile"
)
// RestoreTestRunner is the reconcile-engine seam the scheduler drives (*reconcile.Engine
// satisfies it). Kept narrow so the scheduler is unit-testable with a fake.
type RestoreTestRunner interface {
RunRestoreTest(ctx context.Context, spec reconcile.RestoreTestSpec) reconcile.RestoreTestResult
}
// CandidatePicker resolves the archive volid to restore-test (newest backup), or "" when
// there is none yet (the tick then no-ops).
type CandidatePicker func(ctx context.Context) (string, error)
// Scheduler runs the self-restore-test on an agent-internal cadence. It is the fourth daemon
// goroutine; it does real restore→boot→destroy, so it only runs when the cadence is enabled
// AND a valid scratch band is configured (validated by the caller before construction).
type Scheduler struct {
runner RestoreTestRunner
pick CandidatePicker
store *Store
spec reconcile.RestoreTestSpec // archive is filled per-tick
cadence time.Duration
logger *slog.Logger
now func() time.Time
}
// SchedulerOptions configures a Scheduler.
type SchedulerOptions struct {
Runner RestoreTestRunner
Pick CandidatePicker
Store *Store
Spec reconcile.RestoreTestSpec // RestoreStorage, ScratchMin/Max, SourceTier, BootTimeout
Cadence time.Duration // 0 → disabled
Logger *slog.Logger
}
// NewScheduler builds a Scheduler.
func NewScheduler(opts SchedulerOptions) *Scheduler {
logger := opts.Logger
if logger == nil {
logger = slog.Default()
}
return &Scheduler{
runner: opts.Runner,
pick: opts.Pick,
store: opts.Store,
spec: opts.Spec,
cadence: opts.Cadence,
logger: logger,
now: func() time.Time { return time.Now().UTC() },
}
}
// Run fires a restore-test on the cadence until ctx is cancelled. A 0 cadence disables it
// (the goroutine just waits for shutdown). It does NOT fire immediately on start (a restore
// is heavy; the first runs one interval in) — on-demand runs use the selftest harness.
// Returns nil on ctx cancellation.
func (s *Scheduler) Run(ctx context.Context) error {
if s.cadence <= 0 || s.runner == nil || s.pick == nil {
s.logger.Info("backup: restore-test cadence disabled")
<-ctx.Done()
return nil
}
s.logger.Info("backup: restore-test scheduler starting", "cadence", s.cadence)
t := time.NewTicker(s.cadence)
defer t.Stop()
for {
select {
case <-ctx.Done():
s.logger.Info("backup: restore-test scheduler shutting down", "reason", ctx.Err())
return nil
case <-t.C:
s.tick(ctx)
}
}
}
// tick runs one scheduled restore-test: pick a backup → run → record. No-ops cleanly when
// no backup exists yet. Deterministic given s.now — tests call it directly.
func (s *Scheduler) tick(ctx context.Context) {
archive, err := s.pick(ctx)
if err != nil {
s.logger.Warn("backup: restore-test could not pick a candidate; skipping", "err", err)
return
}
if archive == "" {
s.logger.Info("backup: restore-test skipped; no backup available yet")
return
}
spec := s.spec
spec.Archive = archive
res := s.runner.RunRestoreTest(ctx, spec)
if res.Skipped {
return // already logged by the engine (no free scratch VMID)
}
rt := ToHubRestoreTest(res, s.now())
s.store.RecordRestoreTest(rt)
switch {
case !rt.Pass:
// A failing restore-test is the loudest DR signal there is.
s.logger.Error("backup: scheduled restore-test FAILED", "archive", rt.SourceArchive, "err", rt.Error)
case len(res.StartWarnings) == 0:
s.logger.Info("backup: scheduled restore-test passed", "archive", rt.SourceArchive, "duration_s", rt.DurationSeconds)
case res.WarningsRecognized:
// Passed; the only warnings are the known-benign (e.g. systemd-nesting) advisory.
s.logger.Info("backup: scheduled restore-test passed with warnings (recognized)",
"archive", rt.SourceArchive, "duration_s", rt.DurationSeconds, "warnings", res.StartWarnings)
default:
// Passed liveness, but an UNRECOGNIZED start warning stood out — worth an operator look.
s.logger.Warn("backup: scheduled restore-test passed with UNRECOGNIZED warnings",
"archive", rt.SourceArchive, "duration_s", rt.DurationSeconds, "warnings", res.StartWarnings)
}
}