fix: streaming tar verification for large cluster archives (100GB+)

- Increase timeout from 60 to 180 minutes for very large archives
- Use streaming pipes instead of buffering entire tar listing
- Only mark as corrupted for clear corruption signals (unexpected EOF, invalid gzip)
- Prevents false CORRUPTED errors on valid large archives

PITR.md

@@ -584,6 +584,100 @@ Document your recovery procedure:
 9. Create new base backup
 ```
 
+## Large Database Support (600+ GB)
+
+For databases larger than 600 GB, PITR is the **recommended approach** over full dump/restore.
+
+### Why PITR Works Better for Large DBs
+
+| Approach | 600 GB Database | Recovery Time (RTO) |
+|----------|-----------------|---------------------|
+| Full pg_dump/restore | Hours to dump, hours to restore | 4-12+ hours |
+| PITR (base + WAL) | Incremental WAL only | 30 min - 2 hours |
+
+### Setup for Large Databases
+
+**1. Enable WAL archiving with compression:**
+```bash
+dbbackup pitr enable --archive-dir /backups/wal_archive --compress
+```
+
+**2. Take ONE base backup weekly/monthly (use pg_basebackup):**
+```bash
+# For 600+ GB, use fast checkpoint to minimize impact
+pg_basebackup -D /backups/base_$(date +%Y%m%d).tar.gz \
+  -Ft -z -P --checkpoint=fast --wal-method=none
+
+# Duration: 2-6 hours for 600 GB, but only needed weekly/monthly
+```
+
+**3. WAL files archive continuously** (~1-5 GB/hour typical), capturing every change.
+
+**4. Recover to any point in time:**
+```bash
+dbbackup restore pitr \
+  --base-backup /backups/base_20260101.tar.gz \
+  --wal-archive /backups/wal_archive \
+  --target-time "2026-01-13 14:30:00" \
+  --target-dir /var/lib/postgresql/16/restored
+```
+
+### PostgreSQL Optimizations for 600+ GB
+
+| Setting | Value | Purpose |
+|---------|-------|---------|
+| `wal_compression = on` | postgresql.conf | 70-80% smaller WAL files |
+| `max_wal_size = 4GB` | postgresql.conf | Reduce checkpoint frequency |
+| `checkpoint_timeout = 30min` | postgresql.conf | Less frequent checkpoints |
+| `archive_timeout = 300` | postgresql.conf | Force archive every 5 min |
+
+### Recovery Optimizations
+
+| Optimization | How | Benefit |
+|--------------|-----|---------|
+| Parallel recovery | PostgreSQL 15+ automatic | 2-4x faster WAL replay |
+| NVMe/SSD for WAL | Hardware | 3-10x faster recovery |
+| Separate WAL disk | Dedicated mount | Avoid I/O contention |
+| `recovery_prefetch = on` | PostgreSQL 15+ | Faster page reads |
+
+### Storage Planning
+
+| Component | Size Estimate | Retention |
+|-----------|---------------|-----------|
+| Base backup | ~200-400 GB compressed | 1-2 copies |
+| WAL per day | 5-50 GB (depends on writes) | 7-14 days |
+| Total archive | 100-400 GB WAL + base | - |
+
+### RTO Estimates for Large Databases
+
+| Database Size | Base Extraction | WAL Replay (1 week) | Total RTO |
+|---------------|-----------------|---------------------|-----------|
+| 200 GB | 15-30 min | 15-30 min | 30-60 min |
+| 600 GB | 45-90 min | 30-60 min | 1-2.5 hours |
+| 1 TB | 60-120 min | 45-90 min | 2-3.5 hours |
+| 2 TB | 2-4 hours | 1-2 hours | 3-6 hours |
+
+**Compare to full restore:** 600 GB pg_dump restore takes 8-12+ hours.
+
+### Best Practices for 600+ GB
+
+1. **Weekly base backups** - Monthly if storage is tight
+2. **Test recovery monthly** - Verify WAL chain integrity
+3. **Monitor WAL lag** - Alert if archive falls behind
+4. **Use streaming replication** - For HA, combine with PITR for DR
+5. **Separate archive storage** - Don't fill up the DB disk
+
+```bash
+# Quick health check for large DB PITR setup
+dbbackup pitr status --verbose
+
+# Expected output:
+# Base Backup: 2026-01-06 (7 days old) - OK
+# WAL Archive: 847 files, 52 GB
+# Recovery Window: 2026-01-06 to 2026-01-13 (7 days)
+# Estimated RTO: ~90 minutes
+```
+
 ## Performance Considerations
 
 ### WAL Archive Size

bin/README.md

@@ -4,8 +4,8 @@ This directory contains pre-compiled binaries for the DB Backup Tool across mult
 
 ## Build Information
 - **Version**: 3.42.10
-- **Build Time**: 2026-01-12_08:50:35_UTC
+- **Build Time**: 2026-01-13_07:23:20_UTC
-- **Git Commit**: b1f8c6d
+- **Git Commit**: f153e61
 
 ## Recent Updates (v1.1.0)
 - ✅ Fixed TUI progress display with line-by-line output

internal/restore/diagnose.go

@@ -414,24 +414,121 @@ func (d *Diagnoser) diagnoseSQLScript(filePath string, compressed bool, result *
 
 // diagnoseClusterArchive analyzes a cluster tar.gz archive
 func (d *Diagnoser) diagnoseClusterArchive(filePath string, result *DiagnoseResult) {
-	// First verify tar.gz integrity with timeout
+	// Calculate dynamic timeout based on file size
-	// 5 minutes for large archives (multi-GB archives need more time)
+	// Large archives (100GB+) can take significant time to list
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Minute)
+	// Minimum 5 minutes, scales with file size, max 180 minutes for very large archives
+	timeoutMinutes := 5
+	if result.FileSize > 0 {
+		// 1 minute per 2 GB, minimum 5 minutes, max 180 minutes
+		sizeGB := result.FileSize / (1024 * 1024 * 1024)
+		estimatedMinutes := int(sizeGB/2) + 5
+		if estimatedMinutes > timeoutMinutes {
+			timeoutMinutes = estimatedMinutes
+		}
+		if timeoutMinutes > 180 {
+			timeoutMinutes = 180
+		}
+	}
+
+	d.log.Info("Verifying cluster archive integrity",
+		"size", fmt.Sprintf("%.1f GB", float64(result.FileSize)/(1024*1024*1024)),
+		"timeout", fmt.Sprintf("%d min", timeoutMinutes))
+
+	ctx, cancel := context.WithTimeout(context.Background(), time.Duration(timeoutMinutes)*time.Minute)
 	defer cancel()
 
+	// Use streaming approach with pipes to avoid memory issues with large archives
 	cmd := exec.CommandContext(ctx, "tar", "-tzf", filePath)
-	output, err := cmd.Output()
+	stdout, pipeErr := cmd.StdoutPipe()
-	if err != nil {
+	if pipeErr != nil {
+		// Pipe creation failed - not a corruption issue
+		result.Warnings = append(result.Warnings,
+			fmt.Sprintf("Cannot create pipe for verification: %v", pipeErr),
+			"Archive integrity cannot be verified but may still be valid")
+		return
+	}
+
+	var stderrBuf bytes.Buffer
+	cmd.Stderr = &stderrBuf
+
+	if startErr := cmd.Start(); startErr != nil {
+		result.Warnings = append(result.Warnings,
+			fmt.Sprintf("Cannot start tar verification: %v", startErr),
+			"Archive integrity cannot be verified but may still be valid")
+		return
+	}
+
+	// Stream output line by line to avoid buffering entire listing in memory
+	scanner := bufio.NewScanner(stdout)
+	scanner.Buffer(make([]byte, 0, 64*1024), 1024*1024) // Allow long paths
+
+	var files []string
+	fileCount := 0
+	for scanner.Scan() {
+		fileCount++
+		line := scanner.Text()
+		// Only store dump/metadata files, not every file
+		if strings.HasSuffix(line, ".dump") || strings.HasSuffix(line, ".sql.gz") ||
+			strings.HasSuffix(line, ".sql") || strings.HasSuffix(line, ".json") ||
+			strings.Contains(line, "globals") || strings.Contains(line, "manifest") ||
+			strings.Contains(line, "metadata") {
+			files = append(files, line)
+		}
+	}
+
+	scanErr := scanner.Err()
+	waitErr := cmd.Wait()
+	stderrOutput := stderrBuf.String()
+
+	// Handle errors - distinguish between actual corruption and resource/timeout issues
+	if waitErr != nil || scanErr != nil {
+		// Check if it was a timeout
+		if ctx.Err() == context.DeadlineExceeded {
+			result.Warnings = append(result.Warnings,
+				fmt.Sprintf("Verification timed out after %d minutes - archive is very large", timeoutMinutes),
+				"This does not necessarily mean the archive is corrupted",
+				"Manual verification: tar -tzf "+filePath+" | wc -l")
+			// Don't mark as corrupted or invalid on timeout - archive may be fine
+			if fileCount > 0 {
+				result.Details.TableCount = len(files)
+				result.Details.TableList = files
+			}
+			return
+		}
+
+		// Check for specific gzip/tar corruption indicators
+		if strings.Contains(stderrOutput, "unexpected end of file") ||
+			strings.Contains(stderrOutput, "Unexpected EOF") ||
+			strings.Contains(stderrOutput, "gzip: stdin: unexpected end of file") ||
+			strings.Contains(stderrOutput, "not in gzip format") ||
+			strings.Contains(stderrOutput, "invalid compressed data") {
+			// These indicate actual corruption
 			result.IsValid = false
 			result.IsCorrupted = true
 			result.Errors = append(result.Errors,
-			fmt.Sprintf("Tar archive is invalid or corrupted: %v", err),
+				"Tar archive appears truncated or corrupted",
+				fmt.Sprintf("Error: %s", truncateString(stderrOutput, 200)),
 				"Run: tar -tzf "+filePath+" 2>&1 | tail -20")
 			return
 		}
 
-	// Parse tar listing
+		// Other errors (signal killed, memory, etc.) - not necessarily corruption
-	files := strings.Split(strings.TrimSpace(string(output)), "\n")
+		// If we read some files successfully, the archive structure is likely OK
+		if fileCount > 0 {
+			result.Warnings = append(result.Warnings,
+				fmt.Sprintf("Verification incomplete (read %d files before error)", fileCount),
+				"Archive may still be valid - error could be due to system resources")
+			// Proceed with what we got
+		} else {
+			// Couldn't read anything - but don't mark as corrupted without clear evidence
+			result.Warnings = append(result.Warnings,
+				fmt.Sprintf("Cannot verify archive: %v", waitErr),
+				"Archive integrity is uncertain - proceed with caution or verify manually")
+			return
+		}
+	}
+
+	// Parse the collected file list
 	var dumpFiles []string
 	hasGlobals := false
 	hasMetadata := false
@@ -497,9 +594,22 @@ func (d *Diagnoser) diagnoseUnknown(filePath string, result *DiagnoseResult) {
 
 // verifyWithPgRestore uses pg_restore --list to verify dump integrity
 func (d *Diagnoser) verifyWithPgRestore(filePath string, result *DiagnoseResult) {
-	// Use timeout to prevent blocking on very large dump files
+	// Calculate dynamic timeout based on file size
-	// 5 minutes for large dumps (multi-GB dumps with many tables)
+	// pg_restore --list is usually faster than tar -tzf for same size
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Minute)
+	timeoutMinutes := 5
+	if result.FileSize > 0 {
+		// 1 minute per 5 GB, minimum 5 minutes, max 30 minutes
+		sizeGB := result.FileSize / (1024 * 1024 * 1024)
+		estimatedMinutes := int(sizeGB/5) + 5
+		if estimatedMinutes > timeoutMinutes {
+			timeoutMinutes = estimatedMinutes
+		}
+		if timeoutMinutes > 30 {
+			timeoutMinutes = 30
+		}
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), time.Duration(timeoutMinutes)*time.Minute)
 	defer cancel()
 
 	cmd := exec.CommandContext(ctx, "pg_restore", "--list", filePath)
@@ -554,14 +664,72 @@ func (d *Diagnoser) verifyWithPgRestore(filePath string, result *DiagnoseResult)
 
 // DiagnoseClusterDumps extracts and diagnoses all dumps in a cluster archive
 func (d *Diagnoser) DiagnoseClusterDumps(archivePath, tempDir string) ([]*DiagnoseResult, error) {
-	// First, try to list archive contents without extracting (fast check)
+	// Get archive size for dynamic timeout calculation
-	// 10 minutes for very large archives
+	archiveInfo, err := os.Stat(archivePath)
-	listCtx, listCancel := context.WithTimeout(context.Background(), 10*time.Minute)
+	if err != nil {
+		return nil, fmt.Errorf("cannot stat archive: %w", err)
+	}
+
+	// Dynamic timeout based on archive size: base 10 min + 1 min per 3 GB
+	// Large archives like 100+ GB need more time for tar -tzf
+	timeoutMinutes := 10
+	if archiveInfo.Size() > 0 {
+		sizeGB := archiveInfo.Size() / (1024 * 1024 * 1024)
+		estimatedMinutes := int(sizeGB/3) + 10
+		if estimatedMinutes > timeoutMinutes {
+			timeoutMinutes = estimatedMinutes
+		}
+		if timeoutMinutes > 120 { // Max 2 hours
+			timeoutMinutes = 120
+		}
+	}
+
+	d.log.Info("Listing cluster archive contents",
+		"size", fmt.Sprintf("%.1f GB", float64(archiveInfo.Size())/(1024*1024*1024)),
+		"timeout", fmt.Sprintf("%d min", timeoutMinutes))
+
+	listCtx, listCancel := context.WithTimeout(context.Background(), time.Duration(timeoutMinutes)*time.Minute)
 	defer listCancel()
 
 	listCmd := exec.CommandContext(listCtx, "tar", "-tzf", archivePath)
-	listOutput, listErr := listCmd.CombinedOutput()
+
-	if listErr != nil {
+	// Use pipes for streaming to avoid buffering entire output in memory
+	// This prevents OOM kills on large archives (100GB+) with millions of files
+	stdout, err := listCmd.StdoutPipe()
+	if err != nil {
+		return nil, fmt.Errorf("failed to create stdout pipe: %w", err)
+	}
+
+	var stderrBuf bytes.Buffer
+	listCmd.Stderr = &stderrBuf
+
+	if err := listCmd.Start(); err != nil {
+		return nil, fmt.Errorf("failed to start tar listing: %w", err)
+	}
+
+	// Stream the output line by line, only keeping relevant files
+	var files []string
+	scanner := bufio.NewScanner(stdout)
+	// Set a reasonable max line length (file paths shouldn't exceed this)
+	scanner.Buffer(make([]byte, 0, 4096), 1024*1024)
+
+	fileCount := 0
+	for scanner.Scan() {
+		fileCount++
+		line := scanner.Text()
+		// Only store dump files and important files, not every single file
+		if strings.HasSuffix(line, ".dump") || strings.HasSuffix(line, ".sql") ||
+			strings.HasSuffix(line, ".sql.gz") || strings.HasSuffix(line, ".json") ||
+			strings.Contains(line, "globals") || strings.Contains(line, "manifest") ||
+			strings.Contains(line, "metadata") || strings.HasSuffix(line, "/") {
+			files = append(files, line)
+		}
+	}
+
+	scanErr := scanner.Err()
+	listErr := listCmd.Wait()
+
+	if listErr != nil || scanErr != nil {
 		// Archive listing failed - likely corrupted
 		errResult := &DiagnoseResult{
 			FilePath:       archivePath,
@@ -573,7 +741,12 @@ func (d *Diagnoser) DiagnoseClusterDumps(archivePath, tempDir string) ([]*Diagno
 			Details:        &DiagnoseDetails{},
 		}
 
-		errOutput := string(listOutput)
+		errOutput := stderrBuf.String()
+		actualErr := listErr
+		if scanErr != nil {
+			actualErr = scanErr
+		}
+
 		if strings.Contains(errOutput, "unexpected end of file") ||
 			strings.Contains(errOutput, "Unexpected EOF") ||
 			strings.Contains(errOutput, "truncated") {
@@ -585,7 +758,7 @@ func (d *Diagnoser) DiagnoseClusterDumps(archivePath, tempDir string) ([]*Diagno
 				"Solution: Re-create the backup from source database")
 		} else {
 			errResult.Errors = append(errResult.Errors,
-				fmt.Sprintf("Cannot list archive contents: %v", listErr),
+				fmt.Sprintf("Cannot list archive contents: %v", actualErr),
 				fmt.Sprintf("tar error: %s", truncateString(errOutput, 300)),
 				"Run manually: tar -tzf "+archivePath+" 2>&1 | tail -50")
 		}
@@ -593,11 +766,10 @@ func (d *Diagnoser) DiagnoseClusterDumps(archivePath, tempDir string) ([]*Diagno
 		return []*DiagnoseResult{errResult}, nil
 	}
 
-	// Archive is listable - now check disk space before extraction
+	d.log.Debug("Archive listing streamed successfully", "total_files", fileCount, "relevant_files", len(files))
-	files := strings.Split(strings.TrimSpace(string(listOutput)), "\n")
 
 	// Check if we have enough disk space (estimate 4x archive size needed)
-	archiveInfo, _ := os.Stat(archivePath)
+	// archiveInfo already obtained at function start
 	requiredSpace := archiveInfo.Size() * 4
 
 	// Check temp directory space - try to extract metadata first

internal/restore/safety.go

@@ -229,8 +229,14 @@ func containsSQLKeywords(content string) bool {
 }
 
 // CheckDiskSpace verifies sufficient disk space for restore
+// Uses the effective work directory (WorkDir if set, otherwise BackupDir) since
+// that's where extraction actually happens for large databases
 func (s *Safety) CheckDiskSpace(archivePath string, multiplier float64) error {
-	return s.CheckDiskSpaceAt(archivePath, s.cfg.BackupDir, multiplier)
+	checkDir := s.cfg.GetEffectiveWorkDir()
+	if checkDir == "" {
+		checkDir = s.cfg.BackupDir
+	}
+	return s.CheckDiskSpaceAt(archivePath, checkDir, multiplier)
 }
 
 // CheckDiskSpaceAt verifies sufficient disk space at a specific directory

internal/tui/restore_preview.go

@@ -106,9 +106,23 @@ type safetyCheckCompleteMsg struct {
 
 func runSafetyChecks(cfg *config.Config, log logger.Logger, archive ArchiveInfo, targetDB string) tea.Cmd {
 	return func() tea.Msg {
-		// 10 minutes for safety checks - large archives can take a long time to diagnose
+		// Dynamic timeout based on archive size for large database support
-		ctx, cancel := context.WithTimeout(context.Background(), 10*time.Minute)
+		// Base: 10 minutes + 1 minute per 5 GB, max 120 minutes
+		timeoutMinutes := 10
+		if archive.Size > 0 {
+			sizeGB := archive.Size / (1024 * 1024 * 1024)
+			estimatedMinutes := int(sizeGB/5) + 10
+			if estimatedMinutes > timeoutMinutes {
+				timeoutMinutes = estimatedMinutes
+			}
+			if timeoutMinutes > 120 {
+				timeoutMinutes = 120
+			}
+		}
+
+		ctx, cancel := context.WithTimeout(context.Background(), time.Duration(timeoutMinutes)*time.Minute)
 		defer cancel()
+		_ = ctx // Used by database checks below
 
 		safety := restore.NewSafety(cfg, log)
 		checks := []SafetyCheck{}