Files
felhom-controller/controller/internal/appbackup/dbdump_sniff_test.go
T
admin 062357f778 v0.148.0 — coherent snapshot pairs + an offsite restore that actually restores (R-43 + R-44)
Closes the two findings from DIAG-immich-restore-2026-07-19. Viktor deleted 11
immich photos to test offsite restore; both runs flashed success and the photos
stayed gone. Two independent defects.

R-43 — no offsite path could restore a database. All three buttons were
file-only: the two "visszaállítás" actions staged to a scratch folder and never
touched postgres, and place-to-live merged only MISSING files. For a DB-indexed
app the bytes returned and the app still could not see them. The dump was
carried INTO every snapshot and could never be replayed OUT of one.

New ReconstituteFromOffsite (/backup/offbox/reconstitute): safety dump → stop →
files overwritten to the snapshot version → start → the snapshot's own dump
replayed → health wait. Two invariants:
  - nothing is ever deleted (-a, no --ignore-existing, no --delete): a file
    created after the snapshot survives as an extra;
  - the undo exists before the act — the pre-restore- dump is verified ON DISK
    before anything is stopped, overwritten or replayed; if it cannot be taken
    the operation refuses with zero changes.
The replay reads the SCRATCH unit: the live unit is never overwritten, so
replaying from it would replay the current DB over itself and restore nothing.

R-44 — a manual push shipped an unrefreshed dump (up to ~24h old). That day's
predated the customer's account by four hours and probed to asset:0/user:0/
album:0 inside 52MB whose bulk was immich's shipped geodata. Every run, manual
AND nightly, now refreshes dumps + units BEFORE capturing. Order is the
mechanism: the gap can only ADD files the DB does not reference yet, never
remove one it does. Manifests carry offsite_run_id + dumps_at, so coherence is
verifiable at restore time rather than assumed; the periodic refresh carries a
prior stamp forward and never invents one.

Honesty surfaces, all warn-level and none a gate: unstamped (pre-v0.148) pairs
report their skew, ValidateDump gained an EXACT-match accounts-table sniff for
customer-empty dumps, the completion flash states an outcome instead of a
mechanism, and the missing-only button now says what it does NOT do.

11 tests; 5 red-proofs run and reverted. Two of those found real test weaknesses
rather than confirming strength — the first undo mutation was caught by a second
guard, and the first table-matching test did not discriminate between the two
matchers at all. Both tests were rewritten to the cases that separate them.

NOT in scope: R-41's catalog invariant check, nightly cadence, retention, quota
math, tier-2, and v0.147.x progress semantics beyond one added phase line.

Live acceptance (§9) has NOT run: no capability-map flip, customer-restore row
stays MISSING, R-3 stays DRAFT.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P9Nn14TWGzKoqAJAiVwC2s
2026-07-19 12:21:16 +02:00

142 lines
5.9 KiB
Go

package appbackup
import (
"os"
"path/filepath"
"strings"
"testing"
)
// R-44 content-sniff tests.
//
// The dump that triggered this work (DIAG-immich-restore-2026-07-19) was 52MB, had a valid
// PostgreSQL header and 60+ CREATE TABLE statements, and contained zero users and zero assets —
// its entire bulk was immich's shipped geodata reference tables. Both of the signals the product
// already had (file size, table count) called it healthy. These tests pin the one signal that
// would have caught it, and the boundaries that keep it from crying wolf.
func writeDump(t *testing.T, body string) string {
t.Helper()
p := filepath.Join(t.TempDir(), "d.sql")
if err := os.WriteFile(p, []byte(body), 0o644); err != nil {
t.Fatal(err)
}
return p
}
const pgHead = `-- PostgreSQL database dump
-- Dumped from database version 16.10
SET statement_timeout = 0;
SET client_encoding = 'UTF8';
CREATE TABLE public.asset (id uuid NOT NULL);
CREATE TABLE public."user" (id uuid NOT NULL, email text);
`
// TestSniffFlagsEmptyAccountsTable is the 2026-07-19 shape: structurally perfect, no customer.
func TestSniffFlagsEmptyAccountsTable(t *testing.T) {
body := pgHead + "COPY public.\"user\" (id, email) FROM stdin;\n\\.\n" +
"COPY public.asset (id) FROM stdin;\n\\.\n"
v := ValidateDump(writeDump(t, body), DBTypePostgres)
if !v.Valid {
t.Fatalf("the dump is structurally valid; sniff must not change that: %s", v.Error)
}
if !v.UserTableFound {
t.Fatal("the accounts table COPY block was not recognised")
}
if v.UserRows != 0 {
t.Fatalf("UserRows = %d, want 0", v.UserRows)
}
if !v.LooksEmpty {
t.Fatal("a valid dump with zero account rows MUST raise the warn signal — this is the whole point of R-44")
}
}
// TestSniffQuietOnPopulatedDump — the common case must stay silent, or the warning becomes noise
// and gets ignored precisely when it matters.
func TestSniffQuietOnPopulatedDump(t *testing.T) {
body := pgHead + "COPY public.\"user\" (id, email) FROM stdin;\n" +
"a\tone@example.invalid\nb\ttwo@example.invalid\n\\.\n"
v := ValidateDump(writeDump(t, body), DBTypePostgres)
if v.UserRows != 2 {
t.Fatalf("UserRows = %d, want 2", v.UserRows)
}
if v.LooksEmpty {
t.Fatal("a dump with account rows must not be flagged")
}
}
// TestSniffInconclusiveWithoutAccountsTable — plenty of legitimate apps have no users table. No
// table, no claim: a false positive here would warn on every restore of such an app forever.
func TestSniffInconclusiveWithoutAccountsTable(t *testing.T) {
body := "-- PostgreSQL database dump\nCREATE TABLE public.thing (id int);\n" +
"COPY public.thing (id) FROM stdin;\n\\.\n" + strings.Repeat("-- pad\n", 20)
v := ValidateDump(writeDump(t, body), DBTypePostgres)
if v.UserTableFound {
t.Fatal("no accounts table exists — none must be reported")
}
if v.LooksEmpty {
t.Fatal("an app without an accounts table must be INCONCLUSIVE, never flagged empty")
}
}
// TestSniffIgnoresJoinAndAuditTables is the false-alarm guard that shaped the name list, and it is
// written as the case that DISCRIMINATES: an app with NO accounts table but with `user_metadata` /
// `album_user` / `user_audit` — all legitimately empty on a healthy box. Exact-matching leaves this
// inconclusive (silent, correct). A substring match on "user" would treat a join table as the
// accounts table, find zero rows, and shout "your backup looks empty" on every single restore of a
// perfectly healthy app — which is how a warning signal becomes noise and then gets ignored.
func TestSniffIgnoresJoinAndAuditTables(t *testing.T) {
body := "-- PostgreSQL database dump\nCREATE TABLE public.album (id int);\n" +
"COPY public.user_metadata (id) FROM stdin;\n\\.\n" +
"COPY public.album_user (id) FROM stdin;\n\\.\n" +
"COPY public.user_audit (id) FROM stdin;\n\\.\n" +
"COPY public.album (id) FROM stdin;\n1\n\\.\n"
v := ValidateDump(writeDump(t, body), DBTypePostgres)
if v.UserTableFound {
t.Fatal("a join/audit table must never be mistaken for the accounts table")
}
if v.LooksEmpty {
t.Fatal("empty join/audit tables must not trigger the warning — this app has no accounts table at all")
}
}
// TestSniffCountsOnlyTheAccountsTable pins the counting boundary separately: with a real accounts
// table present, rows from neighbouring user-ish tables must not inflate it.
func TestSniffCountsOnlyTheAccountsTable(t *testing.T) {
body := pgHead +
"COPY public.user_metadata (id) FROM stdin;\nm1\nm2\nm3\n\\.\n" +
"COPY public.\"user\" (id, email) FROM stdin;\na\tone@example.invalid\n\\.\n"
v := ValidateDump(writeDump(t, body), DBTypePostgres)
if v.UserRows != 1 {
t.Fatalf("only the real accounts table may be counted; UserRows = %d, want 1", v.UserRows)
}
}
// TestSniffCountsWideRows — a row wider than the read buffer is skipped by the structural scan, but
// it is still a row. Counting it wrong would flag a populated table as empty (immich asset rows are
// genuinely long, which is what makes this reachable).
func TestSniffCountsWideRows(t *testing.T) {
wide := strings.Repeat("x", 300*1024)
body := pgHead + "COPY public.\"user\" (id, email) FROM stdin;\n" + wide + "\n\\.\n"
v := ValidateDump(writeDump(t, body), DBTypePostgres)
if v.UserRows != 1 {
t.Fatalf("a buffer-exceeding row must still count; UserRows = %d, want 1", v.UserRows)
}
if v.LooksEmpty {
t.Fatal("a table whose single row is very wide must not sniff as empty")
}
}
// TestSniffMariaDBInsertForm — mysqldump writes multi-row INSERTs, not COPY blocks.
func TestSniffMariaDBInsertForm(t *testing.T) {
head := "-- MariaDB dump 10.19\nCREATE TABLE `users` (id int);\n" + strings.Repeat("-- pad\n", 20)
empty := ValidateDump(writeDump(t, head), DBTypeMariaDB)
if empty.UserTableFound {
t.Fatal("a CREATE TABLE alone is not an accounts-table row source")
}
full := ValidateDump(writeDump(t, head+"INSERT INTO `users` VALUES (1),(2);\n"), DBTypeMariaDB)
if !full.UserTableFound || full.LooksEmpty {
t.Fatalf("a populated mariadb dump must not be flagged: %+v", full)
}
}