Files
felhom-controller/controller/internal/appbackup/dbservices_test.go
T
admin 78ff991f1c v0.153.0 — R-47: the DB replay no longer races the app, on BOTH restore paths
Closes R-47. No new agent coupling — MinAgent stays 0.90.0.

The replay needs a running DB container, so both restore paths started the
WHOLE stack first, giving the application a window to rebuild the very schema
objects the dump was about to create. Measured live on 2026-07-19 (H4,
DIAG-immich-restore-round2): immich-server rebuilt clip_index two seconds
before the dump's CREATE INDEX, the replay aborted "already exists" under
ON_ERROR_STOP=1, and immich reported schema drift. The data survived only
because pg_dump emits COPY before CREATE INDEX.

Both paths now open a DB-ONLY window: only the stack's database service(s)
come up, the dump is replayed with the app still down, and the full start
runs only after the replay exits 0. Fail-closed: a dump with no identifiable
DB service refuses BEFORE the first mutation. Every exit from the window
still does a best-effort full start, so a failed restore never leaves a box
with a database and no application.

New: appbackup.DBServiceNames (yaml.v3 services-map parse — never a line
scan; immich's top-level volume keys are the decoy) sharing dbTypeForImage
with DiscoverDatabases; stacks.Manager.StartStackServices (refuses an empty
list — argument-less `up -d` is a full start); RedeployFromEnv split into
PersistUnitRedeployConfig + its unchanged tail. StackDataProvider's
RecreateStackFromUnit becomes RecreateStackDefinitionFromUnit — the hidden
`up -d` inside the old name is what carried the defect on the local path.

19 new tests (ordering plus state-at-replay-time, zero-mutation fail-closed
effects, replay-failure bring-up, parser decoys, empty-list refusal); three
companion red-proofs run and reverted. 23/23 packages green.

Not yet live-validated: STOP-1 supervised reconstitute, golden 0.153.0.
2026-07-20 17:01:52 +02:00

196 lines
7.3 KiB
Go

package appbackup
import (
"os"
"path/filepath"
"reflect"
"strings"
"testing"
)
// R-47 (v0.153.0) — the DB-service resolver.
//
// These exist because a dump replay that starts the WHOLE stack races the application's own schema
// management: proven live on 2026-07-19 (DIAG-immich-restore-round2-2026-07-19, H4) when
// immich-server rebuilt `clip_index` two seconds before the dump's CREATE INDEX and the replay
// aborted `already exists`. Closing that window means bringing up ONLY the database service, which
// means naming it correctly — every case below is a way of naming it wrongly.
// writeCompose drops a compose file in a temp dir and returns its path.
func writeCompose(t *testing.T, body string) string {
t.Helper()
p := filepath.Join(t.TempDir(), "docker-compose.yml")
if err := os.WriteFile(p, []byte(body), 0o644); err != nil {
t.Fatal(err)
}
return p
}
// TestDBTypeForImage pins the shared heuristic. It is the SAME predicate DiscoverDatabases applies to
// a running container's image, which is what makes "a dump exists ⇒ a service can be named" hold:
// the compose `image:` value IS the container's image string. The table reproduces the inline form
// this function replaced, byte for byte, including the redis/valkey negatives that must never be
// started in the DB-only window.
func TestDBTypeForImage(t *testing.T) {
cases := []struct {
image string
want DBType
ok bool
}{
{"docker.io/library/postgres:16-alpine", DBTypePostgres, true},
// immich's real pin — a vector-extended postgres whose REPO segment carries the substring.
{"ghcr.io/immich-app/postgres:16-vectorchord0.4.3-pgvectors0.2.0", DBTypePostgres, true},
{"postgres", DBTypePostgres, true},
{"POSTGRES:16", DBTypePostgres, true}, // the discovery path lowercases; so does this
{"mariadb:11", DBTypeMariaDB, true},
{"mysql:8.4", DBTypeMariaDB, true},
{"docker.io/library/MySQL:8", DBTypeMariaDB, true},
{"redis:7-alpine", "", false},
{"valkey/valkey:8", "", false},
{"ghcr.io/immich-app/immich-server:v1.119.0", "", false},
{"", "", false},
}
for _, c := range cases {
got, ok := dbTypeForImage(c.image)
if ok != c.ok || (ok && got != c.want) {
t.Errorf("dbTypeForImage(%q) = (%q, %v), want (%q, %v)", c.image, got, ok, c.want, c.ok)
}
}
}
func TestDBServiceNames(t *testing.T) {
cases := []struct {
name string
body string
want []string
}{
{
name: "postgres service is named",
body: "services:\n app:\n image: ghcr.io/x/app:1\n database:\n image: postgres:16\n",
want: []string{"database"},
},
{
name: "mariadb service is named",
body: "services:\n db:\n image: mariadb:11\n web:\n image: nextcloud:30\n",
want: []string{"db"},
},
{
name: "mysql service is named",
body: "services:\n mysql:\n image: mysql:8.4\n",
want: []string{"mysql"},
},
{
name: "redis-only app has no database service",
body: "services:\n app:\n image: ghcr.io/x/app:1\n redis:\n image: redis:7-alpine\n",
want: nil,
},
{
name: "multiple databases are returned SORTED (one up -d carries them all)",
body: "services:\n zdb:\n image: postgres:16\n adb:\n image: mariadb:11\n app:\n image: x:1\n",
want: []string{"adb", "zdb"},
},
{
name: "no services key at all",
body: "volumes:\n data:\n",
want: nil,
},
{
name: "empty services map",
body: "services:\n",
want: nil,
},
{
name: "an interpolated image is not guessed at",
body: "services:\n db:\n image: ${DB_IMAGE}\n",
want: nil,
},
}
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
got, err := DBServiceNames(writeCompose(t, c.body))
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if !reflect.DeepEqual(got, c.want) {
t.Errorf("DBServiceNames = %v, want %v", got, c.want)
}
})
}
}
// TestDBServiceNames_TopLevelKeysAreNotServices is the decoy test, and the reason this is a YAML
// parse rather than a line scan. immich's real compose carries a top-level `volumes:` block whose
// entry (`immich_ml_cache:`) sits at exactly the indentation a service name does, and a top-level
// `networks:` block does the same. A scanner that collected "indented keys followed by image-ish
// lines" would either invent a service that `docker compose up -d` cannot start, or — worse — match
// the wrong one and leave the real database down while the app came up around the replay.
func TestDBServiceNames_TopLevelKeysAreNotServices(t *testing.T) {
// The service/volume/network names and the image pins are the catalog's real immich template.
// `immich_postgres_data` is the trap made concrete: a top-level VOLUME key whose name contains
// "postgres" and which no `up -d` could ever start.
body := `services:
immich-server:
image: ghcr.io/immich-app/immich-server:v3.0.3
immich-machine-learning:
image: ghcr.io/immich-app/immich-machine-learning:v3.0.3
immich-postgres:
image: ghcr.io/immich-app/postgres:16-vectorchord0.4.3-pgvectors0.2.0
immich-redis:
image: redis:7-alpine
volumes:
immich_ml_cache:
immich_postgres_data:
immich_redis_data:
networks:
traefik-public:
external: true
immich-internal:
`
got, err := DBServiceNames(writeCompose(t, body))
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if !reflect.DeepEqual(got, []string{"immich-postgres"}) {
t.Fatalf("DBServiceNames = %v, want [immich-postgres] — a top-level volume/network key was mistaken for a service", got)
}
}
// TestDBServiceNames_UnreadableAndUnparseableError proves the fail-closed direction: "cannot tell"
// must surface as an ERROR, never as the empty (= "this app has no database") answer. The callers
// turn an empty result into a refusal only when a dump exists; if a read failure silently produced
// the same empty slice for an app with no dump, a genuinely broken compose would flow on unnoticed.
func TestDBServiceNames_UnreadableAndUnparseableError(t *testing.T) {
if _, err := DBServiceNames(filepath.Join(t.TempDir(), "nope.yml")); err == nil {
t.Fatal("a missing compose file must be an error, not an empty service list")
}
// Valid YAML scalar where a map is required, plus outright broken YAML.
if _, err := DBServiceNames(writeCompose(t, "services: [1, 2, 3\n broken")); err == nil {
t.Fatal("an unparseable compose file must be an error, not an empty service list")
}
}
// TestDiscoverAndComposeAgreeOnTheSameImages is the SYMMETRY guard: whatever image string makes
// DiscoverDatabases produce a dump must also make DBServiceNames name a service. They now share one
// predicate; this asserts the property that sharing is FOR, so a future edit to either side that
// breaks it fails here rather than in a customer's restore.
func TestDiscoverAndComposeAgreeOnTheSameImages(t *testing.T) {
images := []string{"postgres:16", "mariadb:11", "mysql:8.4", "redis:7", "ghcr.io/x/app:1"}
var body strings.Builder
body.WriteString("services:\n")
var wantDB []string
for i, img := range images {
svc := string(rune('a' + i))
body.WriteString(" " + svc + ":\n image: " + img + "\n")
if _, ok := dbTypeForImage(img); ok {
wantDB = append(wantDB, svc)
}
}
got, err := DBServiceNames(writeCompose(t, body.String()))
if err != nil {
t.Fatal(err)
}
if !reflect.DeepEqual(got, wantDB) {
t.Fatalf("compose resolver named %v but the discovery predicate says %v — the two sides have drifted", got, wantDB)
}
}