package backup import ( "context" "errors" "fmt" "os" "os/exec" "path/filepath" "strings" "time" ) // Tier-2 in-place file restore (TASK C2, closes drill finding F2): the customer-facing recovery for // class-C data — HDD bind-mount user files under appdata/. Restores MISSING files from the // recorded Tier-2 copy back into the live appdata dir, and touches NOTHING else: // // - a file that exists live is NEVER overwritten (a customer edit after the last Tier-2 run wins); // - a live file absent from the backup is NEVER deleted (that is what rsyncMirror's --delete would // do in this direction — the catastrophic trap this helper exists to avoid); // - only files present in the copy and missing live are copied back (attrs preserved). // // This exactly serves the "I deleted my files" scenario. Corruption / point-in-time rollback stays // with the offbox restore-to-verify + operator paths — deliberately out of scope. // Refusal reasons (customer-readable — they surface verbatim in the flash message). var ( errNoTier2Copy = errors.New("nincs másodlagos fájlmásolat ehhez az alkalmazáshoz") errTier2DriveGone = errors.New("a másodlagos meghajtó nincs csatlakoztatva") errLiveDriveGone = errors.New("az alkalmazás meghajtója nincs csatlakoztatva") errLiveDriveDecommed = errors.New("az alkalmazás meghajtója le van szerelve") // errTier2OldLayout (3b, §7-G2): the recorded copy predates the v2 relpath-mirroring layout (no // marker). Refuse rather than read a flat layout we no longer understand — safe, because tier-2 // restore is missing-file recovery and the live data still exists in that scenario. errTier2OldLayout = errors.New("A 2. mentés régi formátumú — futtass előbb egy új másodlagos mentést.") // ErrTier2NoRestorableData (C9-F1) — this app HAS a Tier-2 copy, but that copy contains no subtree // this restore can read: its data lives entirely in Docker named volumes, which are captured into // recovery-unit/ (db-dumps + volume-dumps) and NEVER read by this path. 43 of the 53 catalog apps // are in this class. Exported so the handler can refuse BEFORE stopping the app and name the action // that does work, instead of taking an outage and reporting "no missing files". ErrTier2NoRestorableData = errors.New("ennek az alkalmazásnak az adatai nem ebből a másolatból állíthatók vissza") ) // Tier2Coverage says what a Tier-2 restore can and cannot return for one app — the asymmetry C9-F1 // is about. Computed from the RECORDED copy on disk, never guessed from the catalog, so an app whose // template changed is judged by what its actual copy holds. // // The distinction that matters: Legs are the subtrees RestoreTier2Files reads (hdd/, userdata/); // HasUnit means the copy ALSO holds a full recovery unit — the app's database dumps and named-volume // tarballs — which this restore path never opens. An app can have HasUnit && no Legs (43 of 53), in // which case the restore is a guaranteed no-op no matter how much data was lost. type Tier2Coverage struct { Legs []string // subtrees this restore reads and that exist in the copy: "hdd", "userdata" HasUnit bool // recovery-unit/ present — captured, but NOT restorable by this path } // CanRestore reports whether the restore has any subtree to read at all. func (c Tier2Coverage) CanRestore() bool { return len(c.Legs) > 0 } // tier2CoverageAt inspects a resolved copy directory. Pure filesystem stat — no side effects. func tier2CoverageAt(destBase string) Tier2Coverage { var c Tier2Coverage for _, leg := range []string{"hdd", "userdata"} { if fi, err := os.Stat(filepath.Join(destBase, leg)); err == nil && fi.IsDir() { c.Legs = append(c.Legs, leg) } } if fi, err := os.Stat(filepath.Join(destBase, "recovery-unit")); err == nil && fi.IsDir() { c.HasUnit = true } return c } // Tier2RestoreCoverage resolves the app's RECORDED Tier-2 copy and reports what a restore could // return from it. Errors are the same refusals RestoreTier2Files itself would raise, so the caller // can surface them before starting anything — this is what lets the handler refuse without an outage. func (m *Manager) Tier2RestoreCoverage(stackName string) (Tier2Coverage, error) { destBase, err := m.tier2RecordedCopyDir(stackName) if err != nil { return Tier2Coverage{}, err } return tier2CoverageAt(destBase), nil } // tier2RecordedCopyDir resolves the RECORDED Tier-2 copy dir for a stack, applying every // source-side refusal in one place so the pre-flight check and the restore itself cannot drift. func (m *Manager) tier2RecordedCopyDir(stackName string) (string, error) { var destBase string if m.settings != nil { if cfg := m.settings.GetCrossDriveConfig(stackName); cfg != nil && cfg.LastRun != "" && cfg.DestinationPath != "" { if m.settings.IsDisconnected(cfg.DestinationPath) { return "", errTier2DriveGone } destBase = filepath.Join(cfg.DestinationPath, "backups", "secondary", stackName) } } if destBase == "" { return "", errNoTier2Copy } if _, statErr := os.Stat(destBase); statErr != nil { return "", errNoTier2Copy // recorded but the copy dir is gone — same honest refusal } // §7-G2 marker gate: a pre-v2 (flat) copy has no marker → refuse rather than read a layout we no // longer understand (live data still exists for missing-file recovery). if _, mErr := os.Stat(filepath.Join(destBase, tier2LayoutMarker)); mErr != nil { return "", errTier2OldLayout } return destBase, nil } // RestoreTier2Files restores the app's MISSING user files in place from its recorded Tier-2 copy // (additive-only; see the package comment above). Returns how many regular files were copied back. // // The source is the RECORDED Tier-2 destination (settings.CrossDriveBackup.DestinationPath) — never // a fresh selectTier2Target, which could re-pick a different (empty) drive and "restore" nothing. // All refusals happen BEFORE the app is stopped. Stop-first is the locked consistency policy: the // app must not be reorganizing its data dir mid-copy. func (m *Manager) RestoreTier2Files(stackName string) (filesRestored int, err error) { if m.stackProvider == nil { return 0, fmt.Errorf("stack provider not configured") } if err := m.acquireRunning(); err != nil { return 0, err // shares the backup/restore single-flight — must not race a running backup } defer m.releaseRunning() // Live side: the app's drive must be present and in service. drive := m.GetAppDrivePath(stackName) if drive == "" || !filepath.IsAbs(drive) { return 0, fmt.Errorf("cannot determine drive path for %s", stackName) } if m.settings != nil { if m.settings.IsDisconnected(drive) { return 0, fmt.Errorf("%w (%s)", errLiveDriveGone, drive) } if m.settings.IsDecommissioned(drive) { return 0, fmt.Errorf("%w (%s)", errLiveDriveDecommed, drive) } } // v2 relpath-mirroring: liveNsRoot == the app's HDD_PATH (Model A). The dest hdd/ and userdata/ // subtrees mirror the live relpath structure exactly, so restore is two whole-subtree merges (N>1 // dirs + nested binds handled natively — no per-appdata-dir resolution, no N>1 refusal). liveNsRoot := m.namespaceRoot(drive) // Source side: the RECORDED Tier-2 copy must exist, its drive connected, and it must be v2. destBase, err := m.tier2RecordedCopyDir(stackName) if err != nil { return 0, err } // C9-F1: refuse BEFORE the app is stopped if this copy holds nothing this path can read. Without // this the app was stopped, zero files were copied, it was restarted, and the customer was told // "Nincs hiányzó fájl — minden fájl megvan a helyén." — an outage plus a claim about data the // restore never looked at. Placed with the other source-side refusals, all of which precede the // stop, so the promise "all refusals happen BEFORE the app is stopped" stays true. cov := tier2CoverageAt(destBase) if !cov.CanRestore() { m.logger.Printf("[WARN] [backup] Tier-2 file restore refused for %s: the recorded copy has no restorable subtree (unit_present=%v) — the app was NOT stopped", stackName, cov.HasUnit) return 0, ErrTier2NoRestorableData } copier := m.restoreFilesCopier if copier == nil { copier = rsyncRestoreMissing } // The two v2 subtree merges: destBase/hdd/ ↔ liveNsRoot/; // destBase/userdata/ ↔ liveNsRoot/userdata/. Each missing-only, additive. merges := []struct{ src, dst string }{ {filepath.Join(destBase, "hdd"), liveNsRoot}, {filepath.Join(destBase, "userdata"), filepath.Join(liveNsRoot, "userdata")}, } m.logger.Printf("[INFO] [backup] Tier-2 file restore for %s: %s (v2) → %s (additive-only)", stackName, destBase, liveNsRoot) // Stop → copy → start → health (the standard restore shape; F17: errors surface, never swallowed). if stopErr := m.stackProvider.StopStack(stackName); stopErr != nil { m.logger.Printf("[WARN] [backup] could not stop %s before Tier-2 file restore: %v (continuing)", stackName, stopErr) } start := time.Now() var copyErr error for _, mg := range merges { if _, err := os.Stat(mg.src); err != nil { continue // that subtree is absent in this copy (e.g. no userdata legs) — skip } n, err := copier(mg.src, mg.dst) filesRestored += n if err != nil { copyErr = err break } } startErr := m.stackProvider.StartStack(stackName) if startErr != nil { m.logger.Printf("[ERROR] [backup] failed to restart %s after Tier-2 file restore: %v", stackName, startErr) } if healthErr := m.waitForHealthy(stackName, 90*time.Second); healthErr != nil { m.logger.Printf("[WARN] [backup] %s Tier-2 file restore done but health check failed: %v", stackName, healthErr) } if copyErr != nil { return filesRestored, fmt.Errorf("fájlmásolás sikertelen: %w", copyErr) } if startErr != nil { return filesRestored, fmt.Errorf("%d fájl visszaállítva, de az alkalmazás újraindítása sikertelen: %w", filesRestored, startErr) } // Privacy: count + duration only — customer file names never at INFO. m.logger.Printf("[INFO] [backup] Tier-2 file restore completed for %s: %d file(s) restored (%s)", stackName, filesRestored, time.Since(start).Round(time.Second)) return filesRestored, nil } // rsyncRestoreMissing copies the files MISSING from dst back from src, and nothing else: // `rsync -a --ignore-existing` — existing dst files are never overwritten, and (unlike rsyncMirror, // which carries --delete for the backup direction) nothing at dst is ever deleted. Returns the // number of regular files transferred, counted from --itemize-changes output. func rsyncRestoreMissing(src, dst string) (int, error) { if err := os.MkdirAll(dst, 0755); err != nil { return 0, fmt.Errorf("mkdir %s: %w", dst, err) } ctx, cancel := context.WithTimeout(context.Background(), 60*time.Minute) defer cancel() // Trailing slashes: copy the CONTENTS of src into dst (same shape as rsyncMirror). cmd := exec.CommandContext(ctx, "rsync", "-a", "--ignore-existing", "--itemize-changes", strings.TrimRight(src, "/")+"/", strings.TrimRight(dst, "/")+"/") out, err := cmd.CombinedOutput() if err != nil { return 0, fmt.Errorf("%v: %s", err, strings.TrimSpace(string(out))) } return countRestoredFiles(string(out)), nil } // countRestoredFiles counts the itemize-changes lines that mark a TRANSFERRED regular file (">f…"). // Created dirs ("cd…") and symlinks ("cL…") are not counted — the flash reports files. Pure // (unit-tested without rsync). func countRestoredFiles(itemizedOut string) int { n := 0 for _, line := range strings.Split(itemizedOut, "\n") { if strings.HasPrefix(line, ">f") { n++ } } return n }