fix(grafana): update dashboard queries and thresholds

- Fix Last Backup Status panel to use bool modifier for proper 1/0 values
- Change RPO threshold from 24h to 7 days (604800s) for status check
- Clean up table transformations to exclude duplicate fields
- Update variable refresh to trigger on time range change

bin/README.md

@@ -4,8 +4,8 @@ This directory contains pre-compiled binaries for the DB Backup Tool across mult
 
 ## Build Information
 - **Version**: 3.42.50
-- **Build Time**: 2026-01-16_18:37:32_UTC
+- **Build Time**: 2026-01-17_06:48:35_UTC
-- **Git Commit**: 9200024
+- **Git Commit**: dd1db84
 
 ## Recent Updates (v1.1.0)
 - ✅ Fixed TUI progress display with line-by-line output

grafana/dbbackup-dashboard.json

@@ -94,7 +94,7 @@
             "uid": "${DS_PROMETHEUS}"
           },
           "editorMode": "code",
-          "expr": "dbbackup_rpo_seconds{instance=~\"$instance\"} < 86400",
+          "expr": "dbbackup_rpo_seconds{instance=~\"$instance\"} < bool 604800",
           "legendFormat": "{{database}}",
           "range": true,
           "refId": "A"
@@ -711,19 +711,6 @@
       },
       "pluginVersion": "10.2.0",
       "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "editorMode": "code",
-          "expr": "dbbackup_rpo_seconds{instance=~\"$instance\"} < 86400",
-          "format": "table",
-          "instant": true,
-          "legendFormat": "__auto",
-          "range": false,
-          "refId": "Status"
-        },
         {
           "datasource": {
             "type": "prometheus",
@@ -769,26 +756,30 @@
               "Time": true,
               "Time 1": true,
               "Time 2": true,
-              "Time 3": true,
               "__name__": true,
               "__name__ 1": true,
               "__name__ 2": true,
-              "__name__ 3": true,
               "instance 1": true,
               "instance 2": true,
-              "instance 3": true,
               "job": true,
               "job 1": true,
               "job 2": true,
-              "job 3": true
+              "engine 1": true,
+              "engine 2": true
+            },
+            "indexByName": {
+              "Database": 0,
+              "Instance": 1,
+              "Engine": 2,
+              "RPO": 3,
+              "Size": 4
             },
-            "indexByName": {},
             "renameByName": {
               "Value #RPO": "RPO",
               "Value #Size": "Size",
-              "Value #Status": "Status",
               "database": "Database",
-              "instance": "Instance"
+              "instance": "Instance",
+              "engine": "Engine"
             }
           }
         }
@@ -1275,7 +1266,7 @@
           "query": "label_values(dbbackup_rpo_seconds, instance)",
           "refId": "StandardVariableQuery"
         },
-        "refresh": 1,
+        "refresh": 2,
         "regex": "",
         "skipUrlSync": false,
         "sort": 1,

internal/checks/error_hints.go

@@ -68,8 +68,8 @@ func ClassifyError(errorMsg string) *ErrorClassification {
 			Type:     "critical",
 			Category: "locks",
 			Message:  errorMsg,
-			Hint:     "Lock table exhausted - typically caused by large objects (BLOBs) during restore",
+			Hint:     "Lock table exhausted. Total capacity = max_locks_per_transaction × (max_connections + max_prepared_transactions). If you reduced VM size or max_connections, you need higher max_locks_per_transaction to compensate.",
-			Action:   "Option 1: Increase max_locks_per_transaction to 1024+ in postgresql.conf (requires restart). Option 2: Update dbbackup and retry - phased restore now auto-enabled for BLOB databases",
+			Action:   "Fix: ALTER SYSTEM SET max_locks_per_transaction = 4096; then RESTART PostgreSQL. For smaller VMs with fewer connections, you need higher max_locks_per_transaction values.",
 			Severity: 2,
 		}
 	case "permission_denied":
@@ -142,8 +142,8 @@ func ClassifyError(errorMsg string) *ErrorClassification {
 			Type:     "critical",
 			Category: "locks",
 			Message:  errorMsg,
-			Hint:     "Lock table exhausted - typically caused by large objects (BLOBs) during restore",
+			Hint:     "Lock table exhausted. Total capacity = max_locks_per_transaction × (max_connections + max_prepared_transactions). If you reduced VM size or max_connections, you need higher max_locks_per_transaction to compensate.",
-			Action:   "Option 1: Increase max_locks_per_transaction to 1024+ in postgresql.conf (requires restart). Option 2: Update dbbackup and retry - phased restore now auto-enabled for BLOB databases",
+			Action:   "Fix: ALTER SYSTEM SET max_locks_per_transaction = 4096; then RESTART PostgreSQL. For smaller VMs with fewer connections, you need higher max_locks_per_transaction values.",
 			Severity: 2,
 		}
 	}

internal/restore/engine.go

@@ -2125,9 +2125,10 @@ func (e *Engine) quickValidateSQLDump(archivePath string, compressed bool) error
 	return nil
 }
 
-// boostLockCapacity temporarily increases max_locks_per_transaction to prevent OOM
+// boostLockCapacity checks and reports on max_locks_per_transaction capacity.
-// during large restores with many BLOBs. Returns the original value for later reset.
+// IMPORTANT: max_locks_per_transaction requires a PostgreSQL RESTART to change!
-// Uses ALTER SYSTEM + pg_reload_conf() so no restart is needed.
+// This function now calculates total lock capacity based on max_connections and
+// warns the user if capacity is insufficient for the restore.
 func (e *Engine) boostLockCapacity(ctx context.Context) (int, error) {
 	// Connect to PostgreSQL to run system commands
 	connStr := fmt.Sprintf("host=%s port=%d user=%s password=%s dbname=postgres sslmode=disable",
@@ -2145,7 +2146,7 @@ func (e *Engine) boostLockCapacity(ctx context.Context) (int, error) {
 	}
 	defer db.Close()
 
-	// Get current value
+	// Get current max_locks_per_transaction
 	var currentValue int
 	err = db.QueryRowContext(ctx, "SHOW max_locks_per_transaction").Scan(&currentValue)
 	if err != nil {
@@ -2158,22 +2159,56 @@ func (e *Engine) boostLockCapacity(ctx context.Context) (int, error) {
 		fmt.Sscanf(currentValueStr, "%d", &currentValue)
 	}
 
-	// Skip if already high enough
+	// Get max_connections to calculate total lock capacity
-	if currentValue >= 2048 {
+	var maxConns int
-		e.log.Info("max_locks_per_transaction already sufficient", "value", currentValue)
+	if err := db.QueryRowContext(ctx, "SHOW max_connections").Scan(&maxConns); err != nil {
-		return currentValue, nil
+		maxConns = 100 // default
 	}
 
-	// Boost to 2048 (enough for most BLOB-heavy databases)
+	// Get max_prepared_transactions
-	_, err = db.ExecContext(ctx, "ALTER SYSTEM SET max_locks_per_transaction = 2048")
+	var maxPreparedTxns int
-	if err != nil {
+	if err := db.QueryRowContext(ctx, "SHOW max_prepared_transactions").Scan(&maxPreparedTxns); err != nil {
-		return currentValue, fmt.Errorf("failed to set max_locks_per_transaction: %w", err)
+		maxPreparedTxns = 0
 	}
 
-	// Reload config without restart
+	// Calculate total lock table capacity:
-	_, err = db.ExecContext(ctx, "SELECT pg_reload_conf()")
+	// Total locks = max_locks_per_transaction × (max_connections + max_prepared_transactions)
-	if err != nil {
+	totalLockCapacity := currentValue * (maxConns + maxPreparedTxns)
-		return currentValue, fmt.Errorf("failed to reload config: %w", err)
+
+	e.log.Info("PostgreSQL lock table capacity",
+		"max_locks_per_transaction", currentValue,
+		"max_connections", maxConns,
+		"max_prepared_transactions", maxPreparedTxns,
+		"total_lock_capacity", totalLockCapacity)
+
+	// Minimum recommended total capacity for BLOB-heavy restores: 200,000 locks
+	minRecommendedCapacity := 200000
+	if totalLockCapacity < minRecommendedCapacity {
+		recommendedMaxLocks := minRecommendedCapacity / (maxConns + maxPreparedTxns)
+		if recommendedMaxLocks < 4096 {
+			recommendedMaxLocks = 4096
+		}
+
+		e.log.Warn("Lock table capacity may be insufficient for BLOB-heavy restores",
+			"current_total_capacity", totalLockCapacity,
+			"recommended_capacity", minRecommendedCapacity,
+			"current_max_locks", currentValue,
+			"recommended_max_locks", recommendedMaxLocks,
+			"note", "max_locks_per_transaction requires PostgreSQL RESTART to change")
+
+		// Write suggested fix to ALTER SYSTEM but warn about restart
+		_, err = db.ExecContext(ctx, fmt.Sprintf("ALTER SYSTEM SET max_locks_per_transaction = %d", recommendedMaxLocks))
+		if err != nil {
+			e.log.Warn("Could not set recommended max_locks_per_transaction (needs superuser)", "error", err)
+		} else {
+			e.log.Warn("Wrote recommended max_locks_per_transaction to postgresql.auto.conf",
+				"value", recommendedMaxLocks,
+				"action", "RESTART PostgreSQL to apply: sudo systemctl restart postgresql")
+		}
+	} else {
+		e.log.Info("Lock table capacity is sufficient",
+			"total_capacity", totalLockCapacity,
+			"max_locks_per_transaction", currentValue)
 	}
 
 	return currentValue, nil

internal/restore/preflight.go

@@ -48,12 +48,14 @@ type LinuxChecks struct {
 
 // PostgreSQLChecks contains PostgreSQL configuration checks
 type PostgreSQLChecks struct {
-	MaxLocksPerTransaction int    // Current setting
+	MaxLocksPerTransaction  int    // Current setting
-	MaintenanceWorkMem     string // Current setting
+	MaxPreparedTransactions int    // Current setting (affects lock capacity)
-	SharedBuffers          string // Current setting (info only)
+	TotalLockCapacity       int    // Calculated: max_locks × (max_connections + max_prepared)
-	MaxConnections         int    // Current setting
+	MaintenanceWorkMem      string // Current setting
-	Version                string // PostgreSQL version
+	SharedBuffers           string // Current setting (info only)
-	IsSuperuser            bool   // Can we modify settings?
+	MaxConnections          int    // Current setting
+	Version                 string // PostgreSQL version
+	IsSuperuser             bool   // Can we modify settings?
 }
 
 // ArchiveChecks contains analysis of the backup archive
@@ -201,6 +203,29 @@ func (e *Engine) checkPostgreSQL(ctx context.Context, result *PreflightResult) {
 		result.PostgreSQL.IsSuperuser = isSuperuser
 	}
 
+	// Check max_prepared_transactions for lock capacity calculation
+	var maxPreparedTxns string
+	if err := db.QueryRowContext(ctx, "SHOW max_prepared_transactions").Scan(&maxPreparedTxns); err == nil {
+		result.PostgreSQL.MaxPreparedTransactions, _ = strconv.Atoi(maxPreparedTxns)
+	}
+
+	// CRITICAL: Calculate TOTAL lock table capacity
+	// Formula: max_locks_per_transaction × (max_connections + max_prepared_transactions)
+	// This is THE key capacity metric for BLOB-heavy restores
+	maxConns := result.PostgreSQL.MaxConnections
+	if maxConns == 0 {
+		maxConns = 100 // default
+	}
+	maxPrepared := result.PostgreSQL.MaxPreparedTransactions
+	totalLockCapacity := result.PostgreSQL.MaxLocksPerTransaction * (maxConns + maxPrepared)
+	result.PostgreSQL.TotalLockCapacity = totalLockCapacity
+
+	e.log.Info("PostgreSQL lock table capacity",
+		"max_locks_per_transaction", result.PostgreSQL.MaxLocksPerTransaction,
+		"max_connections", maxConns,
+		"max_prepared_transactions", maxPrepared,
+		"total_lock_capacity", totalLockCapacity)
+
 	// CRITICAL: max_locks_per_transaction requires PostgreSQL RESTART to change!
 	// Warn users loudly about this - it's the #1 cause of "out of shared memory" errors
 	if result.PostgreSQL.MaxLocksPerTransaction < 256 {
@@ -217,6 +242,33 @@ func (e *Engine) checkPostgreSQL(ctx context.Context, result *PreflightResult) {
 				result.PostgreSQL.MaxLocksPerTransaction))
 	}
 
+	// NEW: Check total lock capacity is sufficient for typical BLOB operations
+	// Minimum recommended: 200,000 for moderate BLOB databases
+	minRecommendedCapacity := 200000
+	if totalLockCapacity < minRecommendedCapacity {
+		recommendedMaxLocks := minRecommendedCapacity / (maxConns + maxPrepared)
+		if recommendedMaxLocks < 4096 {
+			recommendedMaxLocks = 4096
+		}
+
+		e.log.Warn("Total lock table capacity is LOW for BLOB-heavy restores",
+			"current_capacity", totalLockCapacity,
+			"recommended", minRecommendedCapacity,
+			"current_max_locks", result.PostgreSQL.MaxLocksPerTransaction,
+			"current_max_connections", maxConns,
+			"recommended_max_locks", recommendedMaxLocks,
+			"note", "VMs with fewer connections need higher max_locks_per_transaction")
+
+		result.Warnings = append(result.Warnings,
+			fmt.Sprintf("Total lock capacity=%d is low (recommend %d+). "+
+				"Capacity = max_locks_per_transaction(%d) × max_connections(%d). "+
+				"If you reduced VM size/connections, increase max_locks_per_transaction to %d. "+
+				"Fix: ALTER SYSTEM SET max_locks_per_transaction = %d; then RESTART PostgreSQL.",
+				totalLockCapacity, minRecommendedCapacity,
+				result.PostgreSQL.MaxLocksPerTransaction, maxConns,
+				recommendedMaxLocks, recommendedMaxLocks))
+	}
+
 	// Parse shared_buffers and warn if very low
 	sharedBuffersMB := parseMemoryToMB(result.PostgreSQL.SharedBuffers)
 	if sharedBuffersMB > 0 && sharedBuffersMB < 256 {
@@ -409,6 +461,13 @@ func (e *Engine) printPreflightSummary(result *PreflightResult) {
 		humanize.Comma(int64(result.PostgreSQL.MaxLocksPerTransaction)),
 		humanize.Comma(int64(result.Archive.RecommendedLockBoost))),
 		true)
+	printCheck("max_connections", humanize.Comma(int64(result.PostgreSQL.MaxConnections)), true)
+	// Show total lock capacity with warning if low
+	totalCapacityOK := result.PostgreSQL.TotalLockCapacity >= 200000
+	printCheck("Total Lock Capacity",
+		fmt.Sprintf("%s (max_locks × max_conns)",
+			humanize.Comma(int64(result.PostgreSQL.TotalLockCapacity))),
+		totalCapacityOK)
 	printCheck("maintenance_work_mem", fmt.Sprintf("%s → 2GB (auto-boost)",
 		result.PostgreSQL.MaintenanceWorkMem), true)
 	printInfo("shared_buffers", result.PostgreSQL.SharedBuffers)