v3.42.9: Fix all timeout bugs and deadlocks
All checks were successful
CI/CD / Test (push) Successful in 1m14s
CI/CD / Lint (push) Successful in 1m21s
CI/CD / Build & Release (push) Successful in 3m12s

CRITICAL FIXES:
- Encryption detection false positive (IsBackupEncrypted returned true for ALL files)
- 12 cmd.Wait() deadlocks fixed with channel-based context handling
- TUI timeout bugs: 60s->10min for safety checks, 15s->60s for DB listing
- diagnose.go timeouts: 60s->5min for tar/pg_restore operations
- Panic recovery added to parallel backup/restore goroutines
- Variable shadowing fix in restore/engine.go

These bugs caused pg_dump backups to fail through TUI for months.
This commit is contained in:
2026-01-08 05:56:31 +01:00
parent 627061cdbb
commit 9c65821250
22 changed files with 1099 additions and 304 deletions

View File

@@ -217,8 +217,8 @@ func New() *Config {
SingleDBName: getEnvString("SINGLE_DB_NAME", ""),
RestoreDBName: getEnvString("RESTORE_DB_NAME", ""),
// Timeouts
ClusterTimeoutMinutes: getEnvInt("CLUSTER_TIMEOUT_MIN", 240),
// Timeouts - default 24 hours (1440 min) to handle very large databases with large objects
ClusterTimeoutMinutes: getEnvInt("CLUSTER_TIMEOUT_MIN", 1440),
// Cluster parallelism (default: 2 concurrent operations for faster cluster backup/restore)
ClusterParallelism: getEnvInt("CLUSTER_PARALLELISM", 2),
@@ -227,7 +227,7 @@ func New() *Config {
WorkDir: getEnvString("WORK_DIR", ""),
// Swap file management
SwapFilePath: "", // Will be set after WorkDir is initialized
SwapFilePath: "", // Will be set after WorkDir is initialized
SwapFileSizeGB: getEnvInt("SWAP_FILE_SIZE_GB", 0), // 0 = disabled by default
AutoSwap: getEnvBool("AUTO_SWAP", false),

View File

@@ -28,8 +28,9 @@ type LocalConfig struct {
DumpJobs int
// Performance settings
CPUWorkload string
MaxCores int
CPUWorkload string
MaxCores int
ClusterTimeout int // Cluster operation timeout in minutes (default: 1440 = 24 hours)
// Security settings
RetentionDays int
@@ -121,6 +122,10 @@ func LoadLocalConfig() (*LocalConfig, error) {
if mc, err := strconv.Atoi(value); err == nil {
cfg.MaxCores = mc
}
case "cluster_timeout":
if ct, err := strconv.Atoi(value); err == nil {
cfg.ClusterTimeout = ct
}
}
case "security":
switch key {
@@ -199,6 +204,9 @@ func SaveLocalConfig(cfg *LocalConfig) error {
if cfg.MaxCores != 0 {
sb.WriteString(fmt.Sprintf("max_cores = %d\n", cfg.MaxCores))
}
if cfg.ClusterTimeout != 0 {
sb.WriteString(fmt.Sprintf("cluster_timeout = %d\n", cfg.ClusterTimeout))
}
sb.WriteString("\n")
// Security section
@@ -268,6 +276,10 @@ func ApplyLocalConfig(cfg *Config, local *LocalConfig) {
if local.MaxCores != 0 {
cfg.MaxCores = local.MaxCores
}
// Apply cluster timeout from config file (overrides default)
if local.ClusterTimeout != 0 {
cfg.ClusterTimeoutMinutes = local.ClusterTimeout
}
if cfg.RetentionDays == 30 && local.RetentionDays != 0 {
cfg.RetentionDays = local.RetentionDays
}
@@ -282,21 +294,22 @@ func ApplyLocalConfig(cfg *Config, local *LocalConfig) {
// ConfigFromConfig creates a LocalConfig from a Config
func ConfigFromConfig(cfg *Config) *LocalConfig {
return &LocalConfig{
DBType: cfg.DatabaseType,
Host: cfg.Host,
Port: cfg.Port,
User: cfg.User,
Database: cfg.Database,
SSLMode: cfg.SSLMode,
BackupDir: cfg.BackupDir,
WorkDir: cfg.WorkDir,
Compression: cfg.CompressionLevel,
Jobs: cfg.Jobs,
DumpJobs: cfg.DumpJobs,
CPUWorkload: cfg.CPUWorkloadType,
MaxCores: cfg.MaxCores,
RetentionDays: cfg.RetentionDays,
MinBackups: cfg.MinBackups,
MaxRetries: cfg.MaxRetries,
DBType: cfg.DatabaseType,
Host: cfg.Host,
Port: cfg.Port,
User: cfg.User,
Database: cfg.Database,
SSLMode: cfg.SSLMode,
BackupDir: cfg.BackupDir,
WorkDir: cfg.WorkDir,
Compression: cfg.CompressionLevel,
Jobs: cfg.Jobs,
DumpJobs: cfg.DumpJobs,
CPUWorkload: cfg.CPUWorkloadType,
MaxCores: cfg.MaxCores,
ClusterTimeout: cfg.ClusterTimeoutMinutes,
RetentionDays: cfg.RetentionDays,
MinBackups: cfg.MinBackups,
MaxRetries: cfg.MaxRetries,
}
}