mirror of
https://github.com/Awuqing/BackupX.git
synced 2026-09-05 23:47:33 +08:00
feat(backup): 新增 CDC 内容寻址仓库模式
使用内容定义分块、不可变 pack 与快照索引实现跨文件和跨快照去重。 接入多目标上传、软配额、恢复、下载、校验、保留和安全垃圾回收,并补充前端入口、中英文文档及端到端测试。 Closes #94
This commit is contained in:
@@ -2,11 +2,13 @@ package retention
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"backupx/server/internal/backup"
|
||||
"backupx/server/internal/model"
|
||||
"backupx/server/internal/repository"
|
||||
"backupx/server/internal/storage"
|
||||
@@ -40,16 +42,48 @@ type CleanupResult struct {
|
||||
Warnings []string
|
||||
}
|
||||
|
||||
type Service struct {
|
||||
records repository.BackupRecordRepository
|
||||
now func() time.Time
|
||||
type cleanupObject struct {
|
||||
targetID uint
|
||||
path string
|
||||
}
|
||||
|
||||
func NewService(records repository.BackupRecordRepository) *Service {
|
||||
return &Service{records: records, now: func() time.Time { return time.Now().UTC() }}
|
||||
type storedUploadResult struct {
|
||||
StorageTargetID uint `json:"storageTargetId"`
|
||||
Status string `json:"status"`
|
||||
StoragePath string `json:"storagePath"`
|
||||
}
|
||||
|
||||
type Service struct {
|
||||
records repository.BackupRecordRepository
|
||||
repositoryKey []byte
|
||||
now func() time.Time
|
||||
}
|
||||
|
||||
func NewService(records repository.BackupRecordRepository, repositoryKey ...[]byte) *Service {
|
||||
var key []byte
|
||||
if len(repositoryKey) > 0 {
|
||||
key = append([]byte(nil), repositoryKey[0]...)
|
||||
}
|
||||
return &Service{records: records, repositoryKey: key, now: func() time.Time { return time.Now().UTC() }}
|
||||
}
|
||||
|
||||
func (s *Service) Cleanup(ctx context.Context, task *model.BackupTask, provider storage.StorageProvider) (*CleanupResult, error) {
|
||||
return s.cleanup(ctx, task, func(uint) (storage.StorageProvider, bool) {
|
||||
return provider, provider != nil
|
||||
})
|
||||
}
|
||||
|
||||
// CleanupProviders applies one retention decision to every successful copy of
|
||||
// a record before deleting its database row. This prevents multi-target tasks
|
||||
// from leaving stale objects after the first target removes the shared record.
|
||||
func (s *Service) CleanupProviders(ctx context.Context, task *model.BackupTask, providers map[uint]storage.StorageProvider) (*CleanupResult, error) {
|
||||
return s.cleanup(ctx, task, func(targetID uint) (storage.StorageProvider, bool) {
|
||||
provider, ok := providers[targetID]
|
||||
return provider, ok && provider != nil
|
||||
})
|
||||
}
|
||||
|
||||
func (s *Service) cleanup(ctx context.Context, task *model.BackupTask, resolveProvider func(uint) (storage.StorageProvider, bool)) (*CleanupResult, error) {
|
||||
if task == nil {
|
||||
return nil, fmt.Errorf("backup task is required")
|
||||
}
|
||||
@@ -67,17 +101,35 @@ func (s *Service) Cleanup(ctx context.Context, task *model.BackupTask, provider
|
||||
// 差异链保护:保留仍被存活差异依赖的全量,避免删除基线后差异无法恢复。
|
||||
candidates = protectDifferentialBases(records, candidates)
|
||||
result := &CleanupResult{}
|
||||
repositoryProviders := make(map[uint]storage.StorageProvider)
|
||||
touchedProviders := make(map[uint]storage.StorageProvider)
|
||||
for _, record := range candidates {
|
||||
if strings.TrimSpace(record.StoragePath) != "" {
|
||||
if provider == nil {
|
||||
result.Warnings = append(result.Warnings, fmt.Sprintf("record %d missing storage provider for cleanup", record.ID))
|
||||
objects, objectErr := cleanupObjectsForRecord(record)
|
||||
if objectErr != nil {
|
||||
result.Warnings = append(result.Warnings, fmt.Sprintf("decode storage copies for record %d failed: %v", record.ID, objectErr))
|
||||
continue
|
||||
}
|
||||
allObjectsDeleted := true
|
||||
for _, object := range objects {
|
||||
provider, ok := resolveProvider(object.targetID)
|
||||
if !ok {
|
||||
result.Warnings = append(result.Warnings, fmt.Sprintf("record %d missing storage provider %d for cleanup", record.ID, object.targetID))
|
||||
allObjectsDeleted = false
|
||||
continue
|
||||
}
|
||||
if err := provider.Delete(ctx, record.StoragePath); err != nil {
|
||||
result.Warnings = append(result.Warnings, fmt.Sprintf("delete storage object %s failed: %v", record.StoragePath, err))
|
||||
if err := provider.Delete(ctx, object.path); err != nil {
|
||||
result.Warnings = append(result.Warnings, fmt.Sprintf("delete storage object %s from target %d failed: %v", object.path, object.targetID, err))
|
||||
allObjectsDeleted = false
|
||||
continue
|
||||
}
|
||||
result.DeletedObjects++
|
||||
touchedProviders[object.targetID] = provider
|
||||
if record.BackupKind == model.BackupKindRepository {
|
||||
repositoryProviders[object.targetID] = provider
|
||||
}
|
||||
}
|
||||
if !allObjectsDeleted {
|
||||
continue
|
||||
}
|
||||
if err := s.records.Delete(ctx, record.ID); err != nil {
|
||||
result.Warnings = append(result.Warnings, fmt.Sprintf("delete backup record %d failed: %v", record.ID, err))
|
||||
@@ -85,13 +137,25 @@ func (s *Service) Cleanup(ctx context.Context, task *model.BackupTask, provider
|
||||
}
|
||||
result.DeletedRecords++
|
||||
}
|
||||
for targetID, provider := range repositoryProviders {
|
||||
pruned, pruneErr := backup.NewRepositoryStore(s.repositoryKey).Prune(ctx, provider)
|
||||
if pruneErr != nil {
|
||||
result.Warnings = append(result.Warnings, fmt.Sprintf("prune CDC repository on target %d failed: %v", targetID, pruneErr))
|
||||
} else {
|
||||
result.DeletedObjects += pruned.DeletedPacks + pruned.DeletedIndexes
|
||||
}
|
||||
}
|
||||
|
||||
// 清理空目录:收集被删除文件的父目录,尝试移除空目录
|
||||
if dirCleaner, ok := provider.(storage.StorageDirCleaner); ok && result.DeletedObjects > 0 {
|
||||
for targetID, provider := range touchedProviders {
|
||||
dirCleaner, ok := provider.(storage.StorageDirCleaner)
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
prefixes := collectDirPrefixes(candidates)
|
||||
for _, prefix := range prefixes {
|
||||
if err := dirCleaner.RemoveEmptyDirs(ctx, prefix); err != nil {
|
||||
result.Warnings = append(result.Warnings, fmt.Sprintf("cleanup empty dirs for %s: %v", prefix, err))
|
||||
result.Warnings = append(result.Warnings, fmt.Sprintf("cleanup empty dirs for %s on target %d: %v", prefix, targetID, err))
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -99,6 +163,43 @@ func (s *Service) Cleanup(ctx context.Context, task *model.BackupTask, provider
|
||||
return result, nil
|
||||
}
|
||||
|
||||
func cleanupObjectsForRecord(record model.BackupRecord) ([]cleanupObject, error) {
|
||||
defaultPath := strings.TrimSpace(record.StoragePath)
|
||||
if strings.TrimSpace(record.StorageUploadResults) == "" {
|
||||
if defaultPath == "" {
|
||||
return nil, nil
|
||||
}
|
||||
return []cleanupObject{{targetID: record.StorageTargetID, path: defaultPath}}, nil
|
||||
}
|
||||
var results []storedUploadResult
|
||||
if err := json.Unmarshal([]byte(record.StorageUploadResults), &results); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
objects := make([]cleanupObject, 0, len(results))
|
||||
seen := make(map[uint]struct{}, len(results))
|
||||
for _, result := range results {
|
||||
if !strings.EqualFold(strings.TrimSpace(result.Status), model.BackupRecordStatusSuccess) {
|
||||
continue
|
||||
}
|
||||
objectPath := strings.TrimSpace(result.StoragePath)
|
||||
if objectPath == "" {
|
||||
objectPath = defaultPath
|
||||
}
|
||||
if objectPath == "" {
|
||||
continue
|
||||
}
|
||||
if _, exists := seen[result.StorageTargetID]; exists {
|
||||
continue
|
||||
}
|
||||
seen[result.StorageTargetID] = struct{}{}
|
||||
objects = append(objects, cleanupObject{targetID: result.StorageTargetID, path: objectPath})
|
||||
}
|
||||
if len(objects) == 0 && defaultPath != "" {
|
||||
return nil, fmt.Errorf("successful record has no successful storage copy")
|
||||
}
|
||||
return objects, nil
|
||||
}
|
||||
|
||||
// protectDifferentialBases 从删除候选中剔除「仍被存活差异依赖的全量」,
|
||||
// 避免删除基线后其差异备份失去依据、无法恢复。全量仅当其全部差异都已过期/删除时才会被清理。
|
||||
func protectDifferentialBases(all []model.BackupRecord, candidates []model.BackupRecord) []model.BackupRecord {
|
||||
|
||||
@@ -221,3 +221,66 @@ func TestCleanupDeletesExpiredRecords(t *testing.T) {
|
||||
t.Fatalf("unexpected deleted objects: %#v", provider.deleted)
|
||||
}
|
||||
}
|
||||
|
||||
func TestCleanupProvidersDeletesEverySuccessfulCopyBeforeRecord(t *testing.T) {
|
||||
now := time.Date(2026, 3, 7, 16, 0, 0, 0, time.UTC)
|
||||
completedNew := now.Add(-time.Hour)
|
||||
completedOld := now.Add(-24 * time.Hour)
|
||||
repo := &fakeRecordRepository{records: []model.BackupRecord{
|
||||
{ID: 2, TaskID: 1, StoragePath: "records/2", Status: model.BackupRecordStatusSuccess, CompletedAt: &completedNew},
|
||||
{
|
||||
ID: 1, TaskID: 1, StoragePath: "records/1", Status: model.BackupRecordStatusSuccess, CompletedAt: &completedOld,
|
||||
StorageUploadResults: `[{"storageTargetId":11,"status":"success","storagePath":"first/1"},{"storageTargetId":12,"status":"success","storagePath":"second/1"},{"storageTargetId":13,"status":"failed"}]`,
|
||||
},
|
||||
}}
|
||||
first := &fakeProvider{}
|
||||
second := &fakeProvider{}
|
||||
service := NewService(repo)
|
||||
service.now = func() time.Time { return now }
|
||||
|
||||
result, err := service.CleanupProviders(context.Background(), &model.BackupTask{ID: 1, MaxBackups: 1}, map[uint]storage.StorageProvider{
|
||||
11: first,
|
||||
12: second,
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("CleanupProviders returned error: %v", err)
|
||||
}
|
||||
if result.DeletedRecords != 1 || result.DeletedObjects != 2 || len(result.Warnings) != 0 {
|
||||
t.Fatalf("unexpected cleanup result: %#v", result)
|
||||
}
|
||||
if len(repo.deleted) != 1 || repo.deleted[0] != 1 {
|
||||
t.Fatalf("unexpected deleted records: %#v", repo.deleted)
|
||||
}
|
||||
if len(first.deleted) != 1 || first.deleted[0] != "first/1" {
|
||||
t.Fatalf("unexpected first-target deletes: %#v", first.deleted)
|
||||
}
|
||||
if len(second.deleted) != 1 || second.deleted[0] != "second/1" {
|
||||
t.Fatalf("unexpected second-target deletes: %#v", second.deleted)
|
||||
}
|
||||
}
|
||||
|
||||
func TestCleanupProvidersKeepsRecordWhenCopyProviderIsUnavailable(t *testing.T) {
|
||||
now := time.Date(2026, 3, 7, 16, 0, 0, 0, time.UTC)
|
||||
completedNew := now.Add(-time.Hour)
|
||||
completedOld := now.Add(-24 * time.Hour)
|
||||
repo := &fakeRecordRepository{records: []model.BackupRecord{
|
||||
{ID: 2, TaskID: 1, StoragePath: "records/2", Status: model.BackupRecordStatusSuccess, CompletedAt: &completedNew},
|
||||
{
|
||||
ID: 1, TaskID: 1, StoragePath: "records/1", Status: model.BackupRecordStatusSuccess, CompletedAt: &completedOld,
|
||||
StorageUploadResults: `[{"storageTargetId":11,"status":"success","storagePath":"first/1"},{"storageTargetId":12,"status":"success","storagePath":"second/1"}]`,
|
||||
},
|
||||
}}
|
||||
first := &fakeProvider{}
|
||||
service := NewService(repo)
|
||||
|
||||
result, err := service.CleanupProviders(context.Background(), &model.BackupTask{ID: 1, MaxBackups: 1}, map[uint]storage.StorageProvider{11: first})
|
||||
if err != nil {
|
||||
t.Fatalf("CleanupProviders returned error: %v", err)
|
||||
}
|
||||
if result.DeletedRecords != 0 || result.DeletedObjects != 1 || len(result.Warnings) != 1 {
|
||||
t.Fatalf("unexpected safe partial-cleanup result: %#v", result)
|
||||
}
|
||||
if len(repo.deleted) != 0 {
|
||||
t.Fatalf("record must remain until all copies are deleted: %#v", repo.deleted)
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user