v0.29.0: OS/Docker-data storage split — golden + provision (Phase 1)

build-golden.sh bakes a small OS rootfs + a dedicated /var/lib/docker volume
(mp0, backup=1) carrying the baked images, plus Docker log rotation. bringup.go
grows the golden's data volume to the per-customer target (DataVolGrowGB) and
emits backup=1 on data mounts (GuestMount.Backup) — closing the spike-B3 silent
DB-loss trap. CLI gains -rootfs-grow/-datavol-grow/-datavol-mount. New
RUNBOOK-provisioning-storage.md. Phase 2 = felhom-controller v0.58.0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-13 15:38:26 +02:00
parent 5ab159521d
commit d7d68fdd83
6 changed files with 275 additions and 11 deletions
+44 -2
View File
@@ -40,6 +40,9 @@ const (
const bringUpKind = "bring_up"
// DefaultDataVolMount is the mpN slot the golden bakes the Docker-data volume (/var/lib/docker) at.
const DefaultDataVolMount = "mp0"
// configLockMaxAttempts bounds the F4 config-lock retry. configLockBackoff is a package var so
// tests can shrink it (the production value gives PVE time to release its async config lock).
const configLockMaxAttempts = 5
@@ -52,6 +55,12 @@ type GuestMount struct {
Storage string // PVE storage id (e.g. "local-lvm")
SizeGB int // new-volume size in GiB
MountPoint string // in-guest path (e.g. "/mnt/data")
// Backup includes this mountpoint in vzdump/PBS. MANDATORY for any data-bearing mount (DB
// volumes), because extra LXC mountpoints default to backup=0 = EXCLUDED from the snapshot
// (storage-split finding B3). The Docker-data volume normally rides in from the golden archive
// (already backup=1) and is grown via DataVolGrowGB rather than attached here, but any data
// mount attached through spec.Mounts MUST set this or its contents silently fall out of PBS.
Backup bool
}
// BringUpSpec is the input to one bring-up. The caller resolves it (the selftest, or slice-10
@@ -65,7 +74,14 @@ type BringUpSpec struct {
Cores int // 0 = leave as restored
MemoryMB int // 0 = leave as restored
RootfsGrowGB int // optional grow-only rootfs resize (0 = skip)
Mounts []GuestMount // additive mpN mounts (slice 7 may pass empty/test)
// DataVolGrowGB grows the golden-carried Docker-data volume (DataVolMount, default mp0) to the
// per-customer target. The golden ships a small data volume with the baked images; provision
// grows it online (grow-only, storage-split B4) rather than attaching a fresh empty volume that
// would shadow the baked images. 0 = skip (keep the golden's size).
DataVolGrowGB int
// DataVolMount is the mpN slot of the golden's Docker-data volume to grow; "" → DefaultDataVolMount ("mp0").
DataVolMount string
Mounts []GuestMount // additive mpN mounts (slice 7 may pass empty/test)
KeepMAC bool // DR knob: keep the archived MAC (true) unless a source may be live
BootTimeout time.Duration // 0 → DefaultBootTimeout; bounds the link-up liveness wait
}
@@ -213,6 +229,26 @@ func (e *Engine) runBringUp(ctx context.Context, spec BringUpSpec, res *BringUpR
}
}
// 4b. Grow the golden-carried Docker-data volume (mp0) to the per-customer target. Grow-only,
// online (storage-split B4); its OWN call like the rootfs resize. The volume + baked images
// came in with the restore, so we grow it rather than attach a fresh one that would shadow
// the baked images.
if spec.DataVolGrowGB > 0 {
mount := spec.DataVolMount
if mount == "" {
mount = DefaultDataVolMount
}
dupid, err := e.api.ResizeLXC(ctx, spec.VMID, mount, fmt.Sprintf("+%dG", spec.DataVolGrowGB))
if err != nil {
res.Err = fmt.Errorf("reconcile: bring-up data-volume resize (%s): %w", mount, err)
return
}
if _, err := e.waitTask(ctx, dupid, proxmox.WaitOptions{}); err != nil {
res.Err = fmt.Errorf("reconcile: bring-up data-volume resize task (%s): %w", mount, err)
return
}
}
// Capture the post-reset MAC for the result (fresh for provision; archived for DR keep).
if cfg2, err := e.api.GuestConfig(ctx, spec.VMID); err == nil {
res.AssignedMAC = net0MAC(cfg2)
@@ -310,7 +346,13 @@ func buildBringUpConfig(spec BringUpSpec, cfg proxmox.GuestConfig) map[string]st
params["memory"] = strconv.Itoa(spec.MemoryMB)
}
for i, m := range spec.Mounts {
params[fmt.Sprintf("mp%d", i)] = fmt.Sprintf("%s:%d,mp=%s", m.Storage, m.SizeGB, m.MountPoint)
// backup=1 for data-bearing mounts: extra LXC mountpoints default to backup=0 = EXCLUDED
// from vzdump/PBS (storage-split B3), which would silently drop their DBs from the snapshot.
spec := fmt.Sprintf("%s:%d,mp=%s", m.Storage, m.SizeGB, m.MountPoint)
if m.Backup {
spec += ",backup=1"
}
params[fmt.Sprintf("mp%d", i)] = spec
}
return params
}
+52
View File
@@ -74,6 +74,58 @@ func TestRunBringUp_ProvisionHappyPath(t *testing.T) {
}
}
// A data-bearing additive mount must carry backup=1 (so its DBs stay in PBS — storage-split B3);
// a non-backup mount must NOT. Pure-function check on buildBringUpConfig.
func TestBuildBringUpConfig_BackupFlagOnDataMount(t *testing.T) {
params := buildBringUpConfig(BringUpSpec{
Mode: ModeProvision,
Mounts: []GuestMount{
{Storage: "local-lvm", SizeGB: 2, MountPoint: "/mnt/data", Backup: true},
{Storage: "local-lvm", SizeGB: 1, MountPoint: "/mnt/scratch"}, // no backup
},
}, scratchCfg())
if params["mp0"] != "local-lvm:2,mp=/mnt/data,backup=1" {
t.Errorf("data mount must carry backup=1: mp0=%q", params["mp0"])
}
if params["mp1"] != "local-lvm:1,mp=/mnt/scratch" {
t.Errorf("non-backup mount must NOT carry backup=1: mp1=%q", params["mp1"])
}
}
// The golden-carried Docker-data volume is grown via a SEPARATE resize on its mpN slot (B4),
// alongside (but distinct from) the rootfs grow.
func TestRunBringUp_StorageSplit_DataVolGrow(t *testing.T) {
const vmid = 8050
api := &fakeAPI{cfg: map[int]proxmox.GuestConfig{vmid: scratchCfg()}}
e, _, q := newEngine(t, api, EmptyProvider{})
defer q.Close()
res := e.RunBringUp(context.Background(), BringUpSpec{
Mode: ModeProvision, Archive: "local:backup/golden.tar.zst", VMID: vmid,
RestoreStorage: "local-lvm", Hostname: "felhom-prov-8050",
RootfsGrowGB: 8, DataVolGrowGB: 240, // grows mp0 (DefaultDataVolMount)
})
if res.Err != nil || !res.Pass {
t.Fatalf("provision must pass, got %+v", res)
}
// TWO resizes: rootfs +8G and the Docker-data volume mp0 +240G.
if len(api.resizes) != 2 {
t.Fatalf("expected rootfs + data-volume resizes, got %+v", api.resizes)
}
var sawRootfs, sawData bool
for _, r := range api.resizes {
if r.disk == "rootfs" && r.size == "+8G" {
sawRootfs = true
}
if r.disk == "mp0" && r.size == "+240G" {
sawData = true
}
}
if !sawRootfs || !sawData {
t.Errorf("want rootfs +8G AND mp0 +240G, got %+v", api.resizes)
}
}
func TestRunBringUp_CompensatingRollback(t *testing.T) {
const vmid = 8000
lockBackoffFast(t)