feat(cluster): 支持远程源服务器集中备份

为 Master 本地磁盘增加可选流式中转,远程 Agent 可直接把产物写入中央存储并通过反向通道恢复。

持久化并校验传输模式,兼容既有 Agent 本机磁盘目标,补齐鉴权、完整性、配额、访问保护、前端配置及双向链路测试。

Closes #101
This commit is contained in:
Awuqing
2026-08-07 05:54:34 +08:00
parent 05dd1baa61
commit cc50637b4b
28 changed files with 1012 additions and 180 deletions
+62 -4
View File
@@ -5,6 +5,7 @@ import (
"context"
"crypto/tls"
"encoding/json"
"errors"
"fmt"
"io"
"net/http"
@@ -125,10 +126,11 @@ type TaskSpec struct {
// StorageTargetConfig 与 service.AgentStorageTargetConfig 对齐
type StorageTargetConfig struct {
ID uint `json:"id"`
Type string `json:"type"`
Name string `json:"name"`
Config json.RawMessage `json:"config"`
ID uint `json:"id"`
Type string `json:"type"`
Name string `json:"name"`
Config json.RawMessage `json:"config"`
TransferMode string `json:"transferMode"`
}
// GetTaskSpec 拉取任务规格
@@ -149,6 +151,7 @@ type RecordUpdate struct {
Checksum string `json:"checksum,omitempty"`
StoragePath string `json:"storagePath,omitempty"`
StorageTargetID uint `json:"storageTargetId,omitempty"`
StorageTransferMode string `json:"storageTransferMode,omitempty"`
StorageUploadResults []StorageResultItem `json:"storageUploadResults,omitempty"`
ErrorMessage string `json:"errorMessage,omitempty"`
LogAppend string `json:"logAppend,omitempty"`
@@ -160,6 +163,7 @@ type StorageResultItem struct {
Status string `json:"status"`
StoragePath string `json:"storagePath,omitempty"`
FileSize int64 `json:"fileSize,omitempty"`
TransferMode string `json:"transferMode,omitempty"`
Error string `json:"error,omitempty"`
}
@@ -169,6 +173,39 @@ func (c *MasterClient) UpdateRecord(ctx context.Context, recordID uint, update R
return c.do(ctx, http.MethodPost, path, update, nil)
}
// UploadArtifact streams an artifact through the Master for storage targets
// that are not directly reachable from the Agent.
func (c *MasterClient) UploadArtifact(ctx context.Context, recordID, targetID uint, objectKey string, size int64, checksum string, reader io.Reader) error {
path := fmt.Sprintf("/api/agent/records/%d/artifacts/%d", recordID, targetID)
req, err := http.NewRequestWithContext(ctx, http.MethodPut, c.baseURL+path, reader)
if err != nil {
return err
}
// The executor owns and closes the artifact file. Prevent net/http from
// closing that underlying reader when it finishes the request body.
req.Body = io.NopCloser(reader)
req.ContentLength = size
req.Header.Set("Content-Type", "application/octet-stream")
req.Header.Set("X-Agent-Token", c.token)
req.Header.Set("X-BackupX-Object-Key", objectKey)
req.Header.Set("X-BackupX-SHA256", checksum)
client := *c.httpClient
client.Timeout = 0
resp, err := client.Do(req)
if err != nil {
return fmt.Errorf("relay artifact to Master: %w", err)
}
data, readErr := io.ReadAll(io.LimitReader(resp.Body, 1<<20))
closeErr := resp.Body.Close()
if readErr != nil || closeErr != nil {
return errors.Join(readErr, closeErr)
}
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
return fmt.Errorf("relay artifact to Master: http %d: %s", resp.StatusCode, string(data))
}
return nil
}
// RestoreSpec 与 service.AgentRestoreSpec 对齐
type RestoreSpec struct {
RestoreRecordID uint `json:"restoreRecordId"`
@@ -210,6 +247,27 @@ func (c *MasterClient) GetRestoreSpec(ctx context.Context, restoreRecordID uint)
return &spec, nil
}
func (c *MasterClient) DownloadRestoreArtifact(ctx context.Context, restoreRecordID uint) (io.ReadCloser, error) {
path := fmt.Sprintf("/api/agent/restores/%d/artifact", restoreRecordID)
req, err := http.NewRequestWithContext(ctx, http.MethodGet, c.baseURL+path, nil)
if err != nil {
return nil, err
}
req.Header.Set("X-Agent-Token", c.token)
client := *c.httpClient
client.Timeout = 0
resp, err := client.Do(req)
if err != nil {
return nil, fmt.Errorf("download relayed artifact from Master: %w", err)
}
if resp.StatusCode >= 200 && resp.StatusCode < 300 {
return resp.Body, nil
}
data, readErr := io.ReadAll(io.LimitReader(resp.Body, 1<<20))
closeErr := resp.Body.Close()
return nil, errors.Join(fmt.Errorf("download relayed artifact from Master: http %d: %s", resp.StatusCode, string(data)), readErr, closeErr)
}
// 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)
+52 -37
View File
@@ -5,6 +5,7 @@ import (
"crypto/sha256"
"encoding/hex"
"encoding/json"
"errors"
"fmt"
"io"
"os"
@@ -137,13 +138,15 @@ func (e *Executor) ExecuteRunTask(ctx context.Context, taskID, recordID uint) er
}
uploadResults := make([]StorageResultItem, 0, len(spec.StorageTargets))
selectedStorageTargetID := uint(0)
selectedStorageTransferMode := ""
var uploadErrors []string
for _, target := range spec.StorageTargets {
if err := e.uploadToTarget(ctx, recordID, target, finalPath, storagePath, fileSize, spec.TaskID); err != nil {
if err := e.uploadToTarget(ctx, recordID, target, finalPath, storagePath, fileSize, checksum, spec.TaskID); err != nil {
uploadResults = append(uploadResults, StorageResultItem{
StorageTargetID: target.ID,
StorageTargetName: target.Name,
Status: "failed",
TransferMode: target.TransferMode,
Error: err.Error(),
})
uploadErrors = append(uploadErrors, fmt.Sprintf("%s: %v", target.Name, err))
@@ -152,6 +155,7 @@ func (e *Executor) ExecuteRunTask(ctx context.Context, taskID, recordID uint) er
}
if selectedStorageTargetID == 0 {
selectedStorageTargetID = target.ID
selectedStorageTransferMode = target.TransferMode
}
uploadResults = append(uploadResults, StorageResultItem{
StorageTargetID: target.ID,
@@ -159,6 +163,7 @@ func (e *Executor) ExecuteRunTask(ctx context.Context, taskID, recordID uint) er
Status: "success",
StoragePath: storagePath,
FileSize: fileSize,
TransferMode: target.TransferMode,
})
e.appendLog(ctx, recordID, fmt.Sprintf("[agent] 已上传到存储目标 %s\n", target.Name))
}
@@ -179,34 +184,40 @@ func (e *Executor) ExecuteRunTask(ctx context.Context, taskID, recordID uint) er
Checksum: checksum,
StoragePath: storagePath,
StorageTargetID: selectedStorageTargetID,
StorageTransferMode: selectedStorageTransferMode,
StorageUploadResults: uploadResults,
LogAppend: fmt.Sprintf("[agent] 任务完成,总计 %d 字节\n", fileSize),
})
}
// uploadToTarget 上传单个目标。为保持简化不做上传级重试(rclone 本身已有 low-level 重试)。
func (e *Executor) uploadToTarget(ctx context.Context, recordID uint, target StorageTargetConfig, filePath, objectKey string, fileSize int64, taskID uint) error {
var rawConfig map[string]any
if len(target.Config) > 0 {
// DecodeRawConfig 通过 json 解析
if err := jsonUnmarshalMap(target.Config, &rawConfig); err != nil {
return fmt.Errorf("parse storage config: %w", err)
}
}
provider, err := e.storageRegistry.Create(ctx, target.Type, rawConfig)
if err != nil {
return fmt.Errorf("create provider: %w", err)
}
func (e *Executor) uploadToTarget(ctx context.Context, recordID uint, target StorageTargetConfig, filePath, objectKey string, fileSize int64, checksum string, taskID uint) error {
f, err := os.Open(filePath)
if err != nil {
return fmt.Errorf("open artifact: %w", err)
}
defer f.Close()
if target.TransferMode == storage.TransferModeMasterRelay {
uploadErr := e.client.UploadArtifact(ctx, recordID, target.ID, objectKey, fileSize, checksum, f)
return errors.Join(uploadErr, f.Close())
}
var rawConfig map[string]any
if len(target.Config) > 0 {
// DecodeRawConfig 通过 json 解析
if err := jsonUnmarshalMap(target.Config, &rawConfig); err != nil {
return errors.Join(fmt.Errorf("parse storage config: %w", err), f.Close())
}
}
provider, err := e.storageRegistry.Create(ctx, target.Type, rawConfig)
if err != nil {
closeErr := f.Close()
return errors.Join(fmt.Errorf("create provider: %w", err), closeErr)
}
meta := map[string]string{
"taskId": fmt.Sprintf("%d", taskID),
"recordId": fmt.Sprintf("%d", recordID),
}
return provider.Upload(ctx, objectKey, f, fileSize, meta)
uploadErr := provider.Upload(ctx, objectKey, f, fileSize, meta)
return errors.Join(uploadErr, f.Close())
}
// appendLog 追加日志到 Master 记录(尽力而为,失败不中断主流程)
@@ -328,7 +339,7 @@ func (e *Executor) DeleteStorageObject(ctx context.Context, targetType string, t
// 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)
// - 下载:直连共享存储,或通过 Master 中转其本地磁盘对象
// - 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 UpdateRestorestatus/logAppend
@@ -357,28 +368,31 @@ func (e *Executor) ExecuteRestore(ctx context.Context, restoreRecordID uint) 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
// 1) 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)
var reader io.ReadCloser
if spec.Storage.TransferMode == storage.TransferModeMasterRelay {
reader, err = e.client.DownloadRestoreArtifact(ctx, restoreRecordID)
} else {
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, providerErr := e.storageRegistry.Create(ctx, spec.Storage.Type, rawConfig)
if providerErr != nil {
e.reportRestoreFailure(ctx, restoreRecordID, fmt.Sprintf("创建存储客户端失败: %v", providerErr))
return providerErr
}
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
@@ -489,8 +503,10 @@ func buildRestoreBackupTaskSpec(spec *RestoreSpec, startedAt time.Time, 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()
func writeReaderToLocal(targetPath string, reader io.ReadCloser) (err error) {
defer func() {
err = errors.Join(err, reader.Close())
}()
if err := os.MkdirAll(filepath.Dir(targetPath), 0o755); err != nil {
return err
}
@@ -498,9 +514,8 @@ func writeReaderToLocal(targetPath string, reader io.ReadCloser) error {
if err != nil {
return err
}
defer file.Close()
_, err = io.Copy(file, reader)
return err
_, copyErr := io.Copy(file, reader)
return errors.Join(copyErr, file.Close())
}
// 辅助函数
+146
View File
@@ -1,7 +1,10 @@
package agent
import (
"archive/tar"
"bytes"
"context"
"crypto/sha256"
"encoding/json"
"fmt"
"io"
@@ -109,6 +112,149 @@ func TestExecuteRunTaskRecordsPerTargetUploadResults(t *testing.T) {
}
}
func TestExecuteRunTaskRelaysMasterLocalDiskTarget(t *testing.T) {
sourceDir := t.TempDir()
if err := os.WriteFile(filepath.Join(sourceDir, "index.html"), []byte("centralize me"), 0o644); err != nil {
t.Fatalf("WriteFile returned error: %v", err)
}
var relayed []byte
var finalUpdate RecordUpdate
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
switch {
case r.Method == http.MethodGet && r.URL.Path == "/api/agent/tasks/1":
writeAgentEnvelope(t, w, TaskSpec{
TaskID: 1,
Name: "remote-source",
Type: "file",
SourcePath: sourceDir,
Compression: "gzip",
StorageTargets: []StorageTargetConfig{{
ID: 11, Name: "master-disk", Type: storage.TypeLocalDisk, TransferMode: storage.TransferModeMasterRelay,
}},
})
case r.Method == http.MethodPut && r.URL.Path == "/api/agent/records/99/artifacts/11":
body, err := io.ReadAll(r.Body)
if err != nil {
t.Fatalf("ReadAll relayed body: %v", err)
}
digest := sha256.Sum256(body)
if got := r.Header.Get("X-BackupX-SHA256"); got != fmt.Sprintf("%x", digest[:]) {
t.Fatalf("relay checksum header = %q", got)
}
if r.Header.Get("X-BackupX-Object-Key") == "" || r.ContentLength != int64(len(body)) {
t.Fatalf("invalid relay metadata: key=%q length=%d body=%d", r.Header.Get("X-BackupX-Object-Key"), r.ContentLength, len(body))
}
relayed = append([]byte(nil), body...)
writeAgentEnvelope(t, w, map[string]string{"status": "ok"})
case r.Method == http.MethodPost && r.URL.Path == "/api/agent/records/99":
var update RecordUpdate
if err := json.NewDecoder(r.Body).Decode(&update); err != nil {
t.Fatalf("Decode update returned error: %v", err)
}
if update.Status != "" {
finalUpdate = update
}
writeAgentEnvelope(t, w, map[string]string{"status": "ok"})
default:
http.NotFound(w, r)
}
}))
defer server.Close()
executor := NewExecutor(NewMasterClient(server.URL, "token", false), filepath.Join(t.TempDir(), "tmp"))
if err := executor.ExecuteRunTask(context.Background(), 1, 99); err != nil {
t.Fatalf("ExecuteRunTask returned error: %v", err)
}
if len(relayed) == 0 {
t.Fatal("expected artifact bytes to be streamed through Master")
}
if finalUpdate.Status != "success" || finalUpdate.StorageTransferMode != storage.TransferModeMasterRelay {
t.Fatalf("unexpected final relay update: %#v", finalUpdate)
}
if len(finalUpdate.StorageUploadResults) != 1 || finalUpdate.StorageUploadResults[0].TransferMode != storage.TransferModeMasterRelay {
t.Fatalf("unexpected relay target result: %#v", finalUpdate.StorageUploadResults)
}
}
func TestExecuteRestoreDownloadsMasterRelayedArtifact(t *testing.T) {
var archive bytes.Buffer
tarWriter := tar.NewWriter(&archive)
content := []byte("restored through Master")
header := &tar.Header{Name: "site/index.html", Mode: 0o644, Size: int64(len(content)), Typeflag: tar.TypeReg}
if err := tarWriter.WriteHeader(header); err != nil {
t.Fatalf("WriteHeader returned error: %v", err)
}
if _, err := tarWriter.Write(content); err != nil {
t.Fatalf("Write returned error: %v", err)
}
if err := tarWriter.Close(); err != nil {
t.Fatalf("Close returned error: %v", err)
}
artifact := append([]byte(nil), archive.Bytes()...)
digest := sha256.Sum256(artifact)
restoreRoot := t.TempDir()
restoreSource := filepath.Join(restoreRoot, "site")
artifactRequests := 0
var finalUpdate RestoreUpdate
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
switch {
case r.Method == http.MethodGet && r.URL.Path == "/api/agent/restores/77/spec":
writeAgentEnvelope(t, w, RestoreSpec{
RestoreRecordID: 77,
BackupRecordID: 99,
TaskID: 1,
TaskName: "remote-source",
Type: "file",
SourcePath: restoreSource,
Storage: StorageTargetConfig{
ID: 11, Name: "master-disk", Type: storage.TypeLocalDisk, TransferMode: storage.TransferModeMasterRelay,
},
StoragePath: "BackupX/file/site.tar",
FileName: "site.tar",
Checksum: fmt.Sprintf("%x", digest[:]),
})
case r.Method == http.MethodGet && r.URL.Path == "/api/agent/restores/77/artifact":
artifactRequests++
if r.Header.Get("X-Agent-Token") != "token" {
t.Fatalf("missing Agent token on relay download")
}
w.Header().Set("Content-Length", fmt.Sprintf("%d", len(artifact)))
_, _ = w.Write(artifact)
case r.Method == http.MethodPost && r.URL.Path == "/api/agent/restores/77":
var update RestoreUpdate
if err := json.NewDecoder(r.Body).Decode(&update); err != nil {
t.Fatalf("Decode update returned error: %v", err)
}
if update.Status != "" {
finalUpdate = update
}
writeAgentEnvelope(t, w, map[string]string{"status": "ok"})
default:
http.NotFound(w, r)
}
}))
defer server.Close()
executor := NewExecutor(NewMasterClient(server.URL, "token", false), filepath.Join(t.TempDir(), "tmp"))
if err := executor.ExecuteRestore(context.Background(), 77); err != nil {
t.Fatalf("ExecuteRestore returned error: %v", err)
}
if artifactRequests != 1 {
t.Fatalf("expected one relay artifact request, got %d", artifactRequests)
}
restored, err := os.ReadFile(filepath.Join(restoreRoot, "site", "index.html"))
if err != nil {
t.Fatalf("ReadFile returned error: %v", err)
}
if string(restored) != string(content) {
t.Fatalf("restored content = %q, want %q", restored, content)
}
if finalUpdate.Status != "success" {
t.Fatalf("unexpected final restore update: %#v", finalUpdate)
}
}
func TestExecuteRunTaskReportsPerTargetUploadResultsWhenAllTargetsFail(t *testing.T) {
sourceDir := t.TempDir()
if err := os.WriteFile(filepath.Join(sourceDir, "index.html"), []byte("hello"), 0o644); err != nil {