Compare commits

..

4 Commits

Author SHA1 Message Date
e363e1937f fix: cluster restore database detection and TUI error display
All checks were successful
CI/CD / Test (push) Successful in 1m14s
CI/CD / Lint (push) Successful in 1m25s
CI/CD / Build & Release (push) Successful in 3m16s
- Fixed psql connection for database detection (always use -h flag)
- Use CombinedOutput() to capture stderr for better diagnostics
- Added existingDBError tracking in restore preview
- Show 'Unable to detect' instead of misleading 'None' when listing fails
- Disable cleanup toggle when database detection failed
2026-01-17 16:44:44 +01:00
df1ab2f55b feat: TUI improvements and consistency fixes
All checks were successful
CI/CD / Test (push) Successful in 1m14s
CI/CD / Lint (push) Successful in 1m23s
CI/CD / Build & Release (push) Successful in 3m10s
- Add product branding header to main menu (version + tagline)
- Fix backup success/error report formatting consistency
- Remove extra newline before error box in backup_exec
- Align backup and restore completion screens
2026-01-17 16:26:00 +01:00
0e050b2def fix: cluster backup TUI success report formatting consistency
All checks were successful
CI/CD / Test (push) Successful in 1m15s
CI/CD / Lint (push) Successful in 1m24s
CI/CD / Build & Release (push) Successful in 3m10s
- Aligned box width and indentation with restore success screen
- Removed inconsistent 2-space prefix from success/error boxes
- Standardized content indentation to 4 spaces
- Moved timing section outside else block (always shown)
- Updated footer style to match restore screen
2026-01-17 16:15:16 +01:00
62d58c77af feat(restore): add --parallel-dbs=-1 auto-detection based on CPU/RAM
All checks were successful
CI/CD / Test (push) Successful in 1m16s
CI/CD / Lint (push) Successful in 1m25s
CI/CD / Build & Release (push) Successful in 3m14s
- Add CalculateOptimalParallel() function to preflight.go
- Calculates optimal workers: min(RAM/3GB, CPU cores), capped at 16
- Reduces parallelism by 50% if memory pressure >80%
- Add -1 flag value for auto-detection mode
- Preflight summary now shows CPU cores and recommended parallel
2026-01-17 13:41:28 +01:00
7 changed files with 207 additions and 65 deletions

View File

@@ -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**: 2026-01-17_06:48:35_UTC
- **Git Commit**: dd1db84
- **Build Time**: 2026-01-17_15:26:14_UTC
- **Git Commit**: df1ab2f
## Recent Updates (v1.1.0)
- ✅ Fixed TUI progress display with line-by-line output

View File

@@ -290,7 +290,7 @@ func init() {
restoreClusterCmd.Flags().BoolVar(&restoreForce, "force", false, "Skip safety checks and confirmations")
restoreClusterCmd.Flags().BoolVar(&restoreCleanCluster, "clean-cluster", false, "Drop all existing user databases before restore (disaster recovery)")
restoreClusterCmd.Flags().IntVar(&restoreJobs, "jobs", 0, "Number of parallel decompression jobs (0 = auto)")
restoreClusterCmd.Flags().IntVar(&restoreParallelDBs, "parallel-dbs", 0, "Number of databases to restore in parallel (0 = use config default, 1 = sequential)")
restoreClusterCmd.Flags().IntVar(&restoreParallelDBs, "parallel-dbs", 0, "Number of databases to restore in parallel (0 = use config default, 1 = sequential, -1 = auto-detect based on CPU/RAM)")
restoreClusterCmd.Flags().StringVar(&restoreWorkdir, "workdir", "", "Working directory for extraction (use when system disk is small, e.g. /mnt/storage/restore_tmp)")
restoreClusterCmd.Flags().BoolVar(&restoreVerbose, "verbose", false, "Show detailed restore progress")
restoreClusterCmd.Flags().BoolVar(&restoreNoProgress, "no-progress", false, "Disable progress indicators")
@@ -786,7 +786,12 @@ func runRestoreCluster(cmd *cobra.Command, args []string) error {
}
// Override cluster parallelism if --parallel-dbs is specified
if restoreParallelDBs > 0 {
if restoreParallelDBs == -1 {
// Auto-detect optimal parallelism based on system resources
autoParallel := restore.CalculateOptimalParallel()
cfg.ClusterParallelism = autoParallel
log.Info("Auto-detected optimal parallelism for database restores", "parallel_dbs", autoParallel, "mode", "auto")
} else if restoreParallelDBs > 0 {
cfg.ClusterParallelism = restoreParallelDBs
log.Info("Using custom parallelism for database restores", "parallel_dbs", restoreParallelDBs)
}

View File

@@ -16,6 +16,57 @@ import (
"github.com/shirou/gopsutil/v3/mem"
)
// CalculateOptimalParallel returns the recommended number of parallel workers
// based on available system resources (CPU cores and RAM).
// This is a standalone function that can be called from anywhere.
// Returns 0 if resources cannot be detected.
func CalculateOptimalParallel() int {
cpuCores := runtime.NumCPU()
vmem, err := mem.VirtualMemory()
if err != nil {
// Fallback: use half of CPU cores if memory detection fails
if cpuCores > 1 {
return cpuCores / 2
}
return 1
}
memAvailableGB := float64(vmem.Available) / (1024 * 1024 * 1024)
// Each pg_restore worker needs approximately 2-4GB of RAM
// Use conservative 3GB per worker to avoid OOM
const memPerWorkerGB = 3.0
// Calculate limits
maxByMem := int(memAvailableGB / memPerWorkerGB)
maxByCPU := cpuCores
// Use the minimum of memory and CPU limits
recommended := maxByMem
if maxByCPU < recommended {
recommended = maxByCPU
}
// Apply sensible bounds
if recommended < 1 {
recommended = 1
}
if recommended > 16 {
recommended = 16 // Cap at 16 to avoid diminishing returns
}
// If memory pressure is high (>80%), reduce parallelism
if vmem.UsedPercent > 80 && recommended > 1 {
recommended = recommended / 2
if recommended < 1 {
recommended = 1
}
}
return recommended
}
// PreflightResult contains all preflight check results
type PreflightResult struct {
// Linux system checks
@@ -35,15 +86,17 @@ type PreflightResult struct {
// LinuxChecks contains Linux kernel/system checks
type LinuxChecks struct {
ShmMax int64 // /proc/sys/kernel/shmmax
ShmAll int64 // /proc/sys/kernel/shmall
MemTotal uint64 // Total RAM in bytes
MemAvailable uint64 // Available RAM in bytes
MemUsedPercent float64 // Memory usage percentage
ShmMaxOK bool // Is shmmax sufficient?
ShmAllOK bool // Is shmall sufficient?
MemAvailableOK bool // Is available RAM sufficient?
IsLinux bool // Are we running on Linux?
ShmMax int64 // /proc/sys/kernel/shmmax
ShmAll int64 // /proc/sys/kernel/shmall
MemTotal uint64 // Total RAM in bytes
MemAvailable uint64 // Available RAM in bytes
MemUsedPercent float64 // Memory usage percentage
CPUCores int // Number of CPU cores
RecommendedParallel int // Auto-calculated optimal parallel count
ShmMaxOK bool // Is shmmax sufficient?
ShmAllOK bool // Is shmall sufficient?
MemAvailableOK bool // Is available RAM sufficient?
IsLinux bool // Are we running on Linux?
}
// PostgreSQLChecks contains PostgreSQL configuration checks
@@ -100,6 +153,7 @@ func (e *Engine) RunPreflightChecks(ctx context.Context, dumpsDir string, entrie
// checkSystemResources uses gopsutil for cross-platform system checks
func (e *Engine) checkSystemResources(result *PreflightResult) {
result.Linux.IsLinux = runtime.GOOS == "linux"
result.Linux.CPUCores = runtime.NumCPU()
// Get memory info (works on Linux, macOS, Windows, BSD)
if vmem, err := mem.VirtualMemory(); err == nil {
@@ -118,6 +172,9 @@ func (e *Engine) checkSystemResources(result *PreflightResult) {
e.log.Warn("Could not detect system memory", "error", err)
}
// Calculate recommended parallel based on resources
result.Linux.RecommendedParallel = e.calculateRecommendedParallel(result)
// Linux-specific kernel checks (shmmax, shmall)
if result.Linux.IsLinux {
e.checkLinuxKernel(result)
@@ -434,6 +491,56 @@ func (e *Engine) calculateRecommendations(result *PreflightResult) {
"recommended_locks", lockBoost)
}
// calculateRecommendedParallel determines optimal parallelism based on system resources
// Returns the recommended number of parallel workers for pg_restore
func (e *Engine) calculateRecommendedParallel(result *PreflightResult) int {
cpuCores := result.Linux.CPUCores
if cpuCores == 0 {
cpuCores = runtime.NumCPU()
}
memAvailableGB := float64(result.Linux.MemAvailable) / (1024 * 1024 * 1024)
// Each pg_restore worker needs approximately 2-4GB of RAM
// Use conservative 3GB per worker to avoid OOM
const memPerWorkerGB = 3.0
// Calculate limits
maxByMem := int(memAvailableGB / memPerWorkerGB)
maxByCPU := cpuCores
// Use the minimum of memory and CPU limits
recommended := maxByMem
if maxByCPU < recommended {
recommended = maxByCPU
}
// Apply sensible bounds
if recommended < 1 {
recommended = 1
}
if recommended > 16 {
recommended = 16 // Cap at 16 to avoid diminishing returns
}
// If memory pressure is high (>80%), reduce parallelism
if result.Linux.MemUsedPercent > 80 && recommended > 1 {
recommended = recommended / 2
if recommended < 1 {
recommended = 1
}
}
e.log.Info("Calculated recommended parallel",
"cpu_cores", cpuCores,
"mem_available_gb", fmt.Sprintf("%.1f", memAvailableGB),
"max_by_mem", maxByMem,
"max_by_cpu", maxByCPU,
"recommended", recommended)
return recommended
}
// printPreflightSummary prints a nice summary of all checks
func (e *Engine) printPreflightSummary(result *PreflightResult) {
fmt.Println()
@@ -446,6 +553,8 @@ func (e *Engine) printPreflightSummary(result *PreflightResult) {
printCheck("Total RAM", humanize.Bytes(result.Linux.MemTotal), true)
printCheck("Available RAM", humanize.Bytes(result.Linux.MemAvailable), result.Linux.MemAvailableOK || result.Linux.MemAvailable == 0)
printCheck("Memory Usage", fmt.Sprintf("%.1f%%", result.Linux.MemUsedPercent), result.Linux.MemUsedPercent < 85)
printCheck("CPU Cores", fmt.Sprintf("%d", result.Linux.CPUCores), true)
printCheck("Recommended Parallel", fmt.Sprintf("%d (auto-calculated)", result.Linux.RecommendedParallel), true)
// Linux-specific kernel checks
if result.Linux.IsLinux && result.Linux.ShmMax > 0 {

View File

@@ -334,10 +334,12 @@ func (s *Safety) checkPostgresDatabaseExists(ctx context.Context, dbName string)
"-tAc", fmt.Sprintf("SELECT 1 FROM pg_database WHERE datname='%s'", dbName),
}
// Only add -h flag if host is not localhost (to use Unix socket for peer auth)
if s.cfg.Host != "localhost" && s.cfg.Host != "127.0.0.1" && s.cfg.Host != "" {
args = append([]string{"-h", s.cfg.Host}, args...)
// Always add -h flag for explicit host connection (required for password auth)
host := s.cfg.Host
if host == "" {
host = "localhost"
}
args = append([]string{"-h", host}, args...)
cmd := exec.CommandContext(ctx, "psql", args...)
@@ -346,9 +348,9 @@ func (s *Safety) checkPostgresDatabaseExists(ctx context.Context, dbName string)
cmd.Env = append(os.Environ(), fmt.Sprintf("PGPASSWORD=%s", s.cfg.Password))
}
output, err := cmd.Output()
output, err := cmd.CombinedOutput()
if err != nil {
return false, fmt.Errorf("failed to check database existence: %w", err)
return false, fmt.Errorf("failed to check database existence: %w (output: %s)", err, strings.TrimSpace(string(output)))
}
return strings.TrimSpace(string(output)) == "1", nil
@@ -405,10 +407,13 @@ func (s *Safety) listPostgresUserDatabases(ctx context.Context) ([]string, error
"-c", query,
}
// Only add -h flag if host is not localhost (to use Unix socket for peer auth)
if s.cfg.Host != "localhost" && s.cfg.Host != "127.0.0.1" && s.cfg.Host != "" {
args = append([]string{"-h", s.cfg.Host}, args...)
// Always add -h flag for explicit host connection (required for password auth)
// Empty or unset host defaults to localhost
host := s.cfg.Host
if host == "" {
host = "localhost"
}
args = append([]string{"-h", host}, args...)
cmd := exec.CommandContext(ctx, "psql", args...)
@@ -417,9 +422,10 @@ func (s *Safety) listPostgresUserDatabases(ctx context.Context) ([]string, error
cmd.Env = append(os.Environ(), fmt.Sprintf("PGPASSWORD=%s", s.cfg.Password))
}
output, err := cmd.Output()
output, err := cmd.CombinedOutput()
if err != nil {
return nil, fmt.Errorf("failed to list databases: %w", err)
// Include psql output in error for debugging
return nil, fmt.Errorf("failed to list databases: %w (output: %s)", err, strings.TrimSpace(string(output)))
}
// Parse output

View File

@@ -454,65 +454,61 @@ func (m BackupExecutionModel) View() string {
} else {
// Show completion summary with detailed stats
if m.err != nil {
s.WriteString(errorStyle.Render("╔══════════════════════════════════════════════════════════════╗"))
s.WriteString("\n")
s.WriteString(errorStyle.Render(" ╔══════════════════════════════════════════════════════════╗"))
s.WriteString(errorStyle.Render(" [FAIL] BACKUP FAILED ║"))
s.WriteString("\n")
s.WriteString(errorStyle.Render(" ║ [FAIL] BACKUP FAILED ║"))
s.WriteString("\n")
s.WriteString(errorStyle.Render(" ╚══════════════════════════════════════════════════════════╝"))
s.WriteString(errorStyle.Render("╚══════════════════════════════════════════════════════════════╝"))
s.WriteString("\n\n")
s.WriteString(errorStyle.Render(fmt.Sprintf(" Error: %v", m.err)))
s.WriteString(errorStyle.Render(fmt.Sprintf(" Error: %v", m.err)))
s.WriteString("\n")
} else {
s.WriteString(successStyle.Render("╔══════════════════════════════════════════════════════════════╗"))
s.WriteString("\n")
s.WriteString(successStyle.Render(" ╔══════════════════════════════════════════════════════════╗"))
s.WriteString(successStyle.Render(" [OK] BACKUP COMPLETED SUCCESSFULLY ║"))
s.WriteString("\n")
s.WriteString(successStyle.Render(" ║ [OK] BACKUP COMPLETED SUCCESSFULLY ║"))
s.WriteString("\n")
s.WriteString(successStyle.Render(" ╚══════════════════════════════════════════════════════════╝"))
s.WriteString(successStyle.Render("╚══════════════════════════════════════════════════════════════╝"))
s.WriteString("\n\n")
// Summary section
s.WriteString(infoStyle.Render(" ─── Summary ─────────────────────────────────────────────"))
s.WriteString(infoStyle.Render(" ─── Summary ───────────────────────────────────────────────"))
s.WriteString("\n\n")
// Backup type specific info
switch m.backupType {
case "cluster":
s.WriteString(" Type: Cluster Backup\n")
s.WriteString(" Type: Cluster Backup\n")
if m.dbTotal > 0 {
s.WriteString(fmt.Sprintf(" Databases: %d backed up\n", m.dbTotal))
s.WriteString(fmt.Sprintf(" Databases: %d backed up\n", m.dbTotal))
}
case "single":
s.WriteString(" Type: Single Database Backup\n")
s.WriteString(fmt.Sprintf(" Database: %s\n", m.databaseName))
s.WriteString(" Type: Single Database Backup\n")
s.WriteString(fmt.Sprintf(" Database: %s\n", m.databaseName))
case "sample":
s.WriteString(" Type: Sample Backup\n")
s.WriteString(fmt.Sprintf(" Database: %s\n", m.databaseName))
s.WriteString(fmt.Sprintf(" Sample Ratio: %d\n", m.ratio))
s.WriteString(" Type: Sample Backup\n")
s.WriteString(fmt.Sprintf(" Database: %s\n", m.databaseName))
s.WriteString(fmt.Sprintf(" Sample Ratio: %d\n", m.ratio))
}
s.WriteString("\n")
// Timing section
s.WriteString(infoStyle.Render(" ─── Timing ──────────────────────────────────────────────"))
s.WriteString("\n\n")
elapsed := time.Since(m.startTime)
s.WriteString(fmt.Sprintf(" Total Time: %s\n", formatBackupDuration(elapsed)))
if m.backupType == "cluster" && m.dbTotal > 0 {
avgPerDB := elapsed / time.Duration(m.dbTotal)
s.WriteString(fmt.Sprintf(" Avg per DB: %s\n", formatBackupDuration(avgPerDB)))
}
s.WriteString("\n")
s.WriteString(infoStyle.Render(" ─────────────────────────────────────────────────────────"))
s.WriteString("\n")
}
// Timing section (always shown, consistent with restore)
s.WriteString(infoStyle.Render(" ─── Timing ────────────────────────────────────────────────"))
s.WriteString("\n\n")
elapsed := time.Since(m.startTime)
s.WriteString(fmt.Sprintf(" Total Time: %s\n", formatBackupDuration(elapsed)))
if m.backupType == "cluster" && m.dbTotal > 0 && m.err == nil {
avgPerDB := elapsed / time.Duration(m.dbTotal)
s.WriteString(fmt.Sprintf(" Avg per DB: %s\n", formatBackupDuration(avgPerDB)))
}
s.WriteString("\n")
s.WriteString(" [KEY] Press Enter or ESC to return to menu\n")
s.WriteString(infoStyle.Render(" ───────────────────────────────────────────────────────────"))
s.WriteString("\n\n")
s.WriteString(infoStyle.Render(" [KEYS] Press Enter to continue"))
}
return s.String()

View File

@@ -299,9 +299,13 @@ func (m *MenuModel) View() string {
var s string
// Product branding header
brandLine := fmt.Sprintf("dbbackup v%s • Enterprise Database Backup & Recovery", m.config.Version)
s += "\n" + infoStyle.Render(brandLine) + "\n"
// Header
header := titleStyle.Render("Database Backup Tool - Interactive Menu")
s += fmt.Sprintf("\n%s\n\n", header)
header := titleStyle.Render("Interactive Menu")
s += fmt.Sprintf("%s\n\n", header)
if len(m.dbTypes) > 0 {
options := make([]string, len(m.dbTypes))

View File

@@ -55,6 +55,7 @@ type RestorePreviewModel struct {
cleanClusterFirst bool // For cluster restore: drop all user databases first
existingDBCount int // Number of existing user databases
existingDBs []string // List of existing user databases
existingDBError string // Error message if database listing failed
safetyChecks []SafetyCheck
checking bool
canProceed bool
@@ -102,6 +103,7 @@ type safetyCheckCompleteMsg struct {
canProceed bool
existingDBCount int
existingDBs []string
existingDBError string
}
func runSafetyChecks(cfg *config.Config, log logger.Logger, archive ArchiveInfo, targetDB string) tea.Cmd {
@@ -221,10 +223,12 @@ func runSafetyChecks(cfg *config.Config, log logger.Logger, archive ArchiveInfo,
check = SafetyCheck{Name: "Existing databases", Status: "checking", Critical: false}
// Get list of existing user databases (exclude templates and system DBs)
var existingDBError string
dbList, err := safety.ListUserDatabases(ctx)
if err != nil {
check.Status = "warning"
check.Message = fmt.Sprintf("Cannot list databases: %v", err)
existingDBError = err.Error()
} else {
existingDBCount = len(dbList)
existingDBs = dbList
@@ -238,6 +242,14 @@ func runSafetyChecks(cfg *config.Config, log logger.Logger, archive ArchiveInfo,
}
}
checks = append(checks, check)
return safetyCheckCompleteMsg{
checks: checks,
canProceed: canProceed,
existingDBCount: existingDBCount,
existingDBs: existingDBs,
existingDBError: existingDBError,
}
}
return safetyCheckCompleteMsg{
@@ -257,6 +269,7 @@ func (m RestorePreviewModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
m.canProceed = msg.canProceed
m.existingDBCount = msg.existingDBCount
m.existingDBs = msg.existingDBs
m.existingDBError = msg.existingDBError
// Auto-forward in auto-confirm mode
if m.config.TUIAutoConfirm {
return m.parent, tea.Quit
@@ -275,12 +288,17 @@ func (m RestorePreviewModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
case "c":
if m.mode == "restore-cluster" {
// Toggle cluster cleanup
m.cleanClusterFirst = !m.cleanClusterFirst
if m.cleanClusterFirst {
m.message = checkWarningStyle.Render(fmt.Sprintf("[WARN] Will drop %d existing database(s) before restore", m.existingDBCount))
// Prevent toggle if we couldn't detect existing databases
if m.existingDBError != "" {
m.message = checkWarningStyle.Render("[WARN] Cannot enable cleanup - database detection failed")
} else {
m.message = fmt.Sprintf("Clean cluster first: disabled")
// Toggle cluster cleanup
m.cleanClusterFirst = !m.cleanClusterFirst
if m.cleanClusterFirst {
m.message = checkWarningStyle.Render(fmt.Sprintf("[WARN] Will drop %d existing database(s) before restore", m.existingDBCount))
} else {
m.message = fmt.Sprintf("Clean cluster first: disabled")
}
}
} else {
// Toggle create if missing
@@ -382,7 +400,11 @@ func (m RestorePreviewModel) View() string {
s.WriteString("\n")
s.WriteString(fmt.Sprintf(" Host: %s:%d\n", m.config.Host, m.config.Port))
if m.existingDBCount > 0 {
if m.existingDBError != "" {
// Show error when database listing failed
s.WriteString(checkWarningStyle.Render(fmt.Sprintf(" Existing Databases: Unable to detect (%s)\n", m.existingDBError)))
s.WriteString(infoStyle.Render(" (Cleanup option disabled - cannot verify database status)\n"))
} else if m.existingDBCount > 0 {
s.WriteString(fmt.Sprintf(" Existing Databases: %d found\n", m.existingDBCount))
// Show first few database names