v0.6.0-rc1: slice 6 Phase A — backup + the self-restore-test (local target)

The guest-level backup layer + the journaled self-restore-test (restore→boot→verify→
teardown) that closes "a backup you haven't restored isn't a backup". All benign
(reuses the slice-4 classifier/gate/journal; no new destructive class/crypto). Local
target only; PBS = Phase B. Restore to a NEW guest only. Backups crash-consistent.

- proxmox: DestroyLXC, VzdumpOptions.Notes (notes-template), LatestBackupVolID.
- reconcile: Engine.RunRestoreTest (journal Scratch entry BEFORE mutation; net link-down
  pre-boot; defer teardown always; benign gated destroy) + Recover extended to reap a
  leaked scratch guest (Scratch flag, special-cased before the UPID path; idempotent).
- internal/backup: runner (vzdump + archive resolve + bulk-gap = backup!=1) + cadence
  scheduler (4th daemon goroutine, default 24h) + in-memory report store.
- hub: Backup/RestoreTest filled; collector seams; cross-repo golden byte-identical +
  bidirectional key-set tests; hub handler logs a FAILED restore-test prominently.
- config BackupConfig (band 990000-990009 default); --selftest=backup / restore-test.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-09 13:49:39 +02:00
parent e548ab57fe
commit b527430ec7
23 changed files with 1727 additions and 46 deletions
+6 -6
View File
@@ -33,7 +33,7 @@ func TestCollect_StorageTargetsFromObserver(t *testing.T) {
obs := fakeObserver{targets: []StorageTarget{
{Name: "local-lvm", Type: StorageTypeLVMThin, State: StorageStateAttached, Reachable: true},
}}
c := NewCollector(px, fakeProber{status: "active"}, obs, "h", "0.5.0", quietLogger())
c := NewCollector(px, fakeProber{status: "active"}, obs, nil, nil, "h", "0.5.0", quietLogger())
r, err := c.Collect(context.Background())
if err != nil {
t.Fatalf("Collect: %v", err)
@@ -45,7 +45,7 @@ func TestCollect_StorageTargetsFromObserver(t *testing.T) {
func TestCollect_StorageObserverErrorDegradesToEmpty(t *testing.T) {
px := &fakePx{node: "n", ns: newTestNodeStatus()}
c := NewCollector(px, fakeProber{status: "active"}, fakeObserver{err: errors.New("proxmox down")}, "h", "0.5.0", quietLogger())
c := NewCollector(px, fakeProber{status: "active"}, fakeObserver{err: errors.New("proxmox down")}, nil, nil, "h", "0.5.0", quietLogger())
r, err := c.Collect(context.Background())
if err != nil {
t.Fatalf("a storage observe error must not sink the heartbeat: %v", err)
@@ -64,7 +64,7 @@ func TestCollect_HostAndGuests(t *testing.T) {
},
cfg: map[int]proxmox.GuestConfig{100: {Cores: 2, Memory: 2048}},
}
c := NewCollector(px, fakeProber{status: "active"}, nil, "demo-host-01", "0.3.0", quietLogger())
c := NewCollector(px, fakeProber{status: "active"}, nil, nil, nil, "demo-host-01", "0.3.0", quietLogger())
r, err := c.Collect(context.Background())
if err != nil {
t.Fatalf("Collect: %v", err)
@@ -104,7 +104,7 @@ func TestCollect_GuestConfigFailureKeepsStatusOmitsSpec(t *testing.T) {
cfg: map[int]proxmox.GuestConfig{100: {Cores: 2}},
cfgErr: map[int]error{200: errors.New("config read failed")},
}
c := NewCollector(px, fakeProber{status: "active"}, nil, "h", "0.3.1", quietLogger())
c := NewCollector(px, fakeProber{status: "active"}, nil, nil, nil, "h", "0.3.1", quietLogger())
r, err := c.Collect(context.Background())
if err != nil {
t.Fatalf("a per-guest failure must NOT fail the whole report: %v", err)
@@ -125,7 +125,7 @@ func TestCollect_GuestConfigFailureKeepsStatusOmitsSpec(t *testing.T) {
func TestCollect_NodeStatusFailureIsHardError(t *testing.T) {
px := &fakePx{node: "n", nsErr: errors.New("proxmox down")}
c := NewCollector(px, fakeProber{status: "active"}, nil, "h", "0.3.0", quietLogger())
c := NewCollector(px, fakeProber{status: "active"}, nil, nil, nil, "h", "0.3.0", quietLogger())
if _, err := c.Collect(context.Background()); err == nil {
t.Fatal("NodeStatus failure must be a hard error (no useful report)")
}
@@ -133,7 +133,7 @@ func TestCollect_NodeStatusFailureIsHardError(t *testing.T) {
func TestCollect_CloudflaredProbeErrorIsUnknown(t *testing.T) {
px := &fakePx{node: "n", ns: newTestNodeStatus()}
c := NewCollector(px, fakeProber{err: errors.New("no systemctl")}, nil, "h", "0.3.0", quietLogger())
c := NewCollector(px, fakeProber{err: errors.New("no systemctl")}, nil, nil, nil, "h", "0.3.0", quietLogger())
r, err := c.Collect(context.Background())
if err != nil {
t.Fatalf("cloudflared failure must not be fatal: %v", err)