Files
break c64f3d8b80
All checks were successful
构建并部署到测试环境(无 SSH) / build-and-deploy (push) Successful in 8m31s
全局审计完成
2026-08-07 11:02:52 +08:00

581 lines
22 KiB
Go
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package auditarchive
import (
"context"
"crypto/sha256"
"fmt"
"io"
"os"
"strconv"
"strings"
"time"
"github.com/bytedance/sonic"
"gorm.io/gorm"
"github.com/break/junhong_cmp_fiber/internal/model"
"github.com/break/junhong_cmp_fiber/pkg/constants"
)
const maxManifestBytes = 1024 * 1024
// RetentionAudit 描述月度物理清理的统一审计事实。
type RetentionAudit struct {
EventID string
Month string
Summary string
Result string
ErrorSummary string
RangeStart time.Time
RangeEnd time.Time
EventCount int64
ResourceCount int64
IntegrationCount int64
ManifestKeys []string
DurationMS int64
}
// RetentionResult 是月度留存清理的结构化执行结果。
type RetentionResult struct {
Month string
EventCount int64
ResourceCount int64
IntegrationCount int64
EstimatedBatches int64
ManifestKeys []string
Duration time.Duration
}
type retentionRuns struct {
audit []*model.LogArchiveRun
integration []*model.LogArchiveRun
}
// CleanupPreviousMonth 校验并物理清理上一个完整自然月的在线审计日志。
func (s *Service) CleanupPreviousMonth(ctx context.Context) (RetentionResult, error) {
now := time.Now().In(s.location)
return s.CleanupMonth(ctx, now.AddDate(0, -1, 0))
}
// ValidatePreviousMonth 只读校验上一个完整自然月的归档与清理门禁。
func (s *Service) ValidatePreviousMonth(ctx context.Context) (RetentionResult, error) {
now := time.Now().In(s.location)
return s.ValidateMonth(ctx, now.AddDate(0, -1, 0))
}
// ValidateMonth 只读校验指定完整自然月,不写清理断点且不删除在线数据。
func (s *Service) ValidateMonth(ctx context.Context, month time.Time) (result RetentionResult, err error) {
if s.db == nil || s.store == nil {
return result, fmt.Errorf("日志留存演练数据库或对象存储未配置")
}
start, end, err := s.retentionMonthRange(month)
if err != nil {
return result, err
}
startedAt := time.Now()
result.Month = start.Format("2006-01")
runs, err := s.loadRetentionRuns(ctx, start, end)
if err != nil {
return result, err
}
if err := s.validateRetentionRuns(ctx, start, end, runs); err != nil {
return result, err
}
summarizeRetentionRuns(runs, &result)
result.EstimatedBatches = estimatedRetentionBatches(result)
result.Duration = time.Since(startedAt)
return result, nil
}
// CleanupMonth 校验归档硬门禁后按固定顺序物理清理指定完整自然月。
func (s *Service) CleanupMonth(ctx context.Context, month time.Time) (result RetentionResult, cleanupErr error) {
if s.db == nil || s.store == nil || s.audit == nil {
return result, fmt.Errorf("日志留存清理数据库、对象存储或审计 Writer 未配置")
}
start, end, err := s.retentionMonthRange(month)
if err != nil {
return result, err
}
startedAt := time.Now()
result.Month = start.Format("2006-01")
cleanupErr = s.executeRetention(ctx, start, end, &result)
result.Duration = time.Since(startedAt)
if auditErr := s.recordRetentionAudit(ctx, start, end, result, cleanupErr); auditErr != nil {
if cleanupErr != nil {
return result, fmt.Errorf("%w记录留存清理失败审计失败: %v", cleanupErr, auditErr)
}
return result, fmt.Errorf("记录留存清理成功审计失败: %w", auditErr)
}
return result, cleanupErr
}
func (s *Service) retentionMonthRange(month time.Time) (time.Time, time.Time, error) {
start := time.Date(month.In(s.location).Year(), month.In(s.location).Month(), 1, 0, 0, 0, 0, s.location)
end := start.AddDate(0, 1, 0)
now := time.Now().In(s.location)
currentMonth := time.Date(now.Year(), now.Month(), 1, 0, 0, 0, 0, s.location)
if !end.Before(currentMonth) && !end.Equal(currentMonth) {
return time.Time{}, time.Time{}, fmt.Errorf("只能清理已经结束的完整自然月")
}
return start, end, nil
}
func (s *Service) executeRetention(ctx context.Context, start, end time.Time, result *RetentionResult) error {
started, err := s.retentionCleanupStarted(ctx, start, end)
if err != nil {
return err
}
if !started {
lastDay := end.AddDate(0, 0, -1)
if err := s.ArchiveDate(ctx, lastDay); err != nil {
return fmt.Errorf("完成上月最后一天 Audit 归档失败: %w", err)
}
if err := s.ArchiveIntegrationDate(ctx, lastDay); err != nil {
return fmt.Errorf("完成上月最后一天 Integration Log 归档失败: %w", err)
}
if err := s.FinalizeIntegrationMonth(ctx, start); err != nil {
return err
}
}
runs, err := s.loadRetentionRuns(ctx, start, end)
if err != nil {
return err
}
if err := s.validateRetentionRuns(ctx, start, end, runs); err != nil {
return err
}
summarizeRetentionRuns(runs, result)
if err := s.cleanupAuditMonth(ctx, start, end, runs.audit); err != nil {
return err
}
return s.cleanupIntegrationMonth(ctx, start, end, runs.integration)
}
func (s *Service) retentionCleanupStarted(ctx context.Context, start, end time.Time) (bool, error) {
var count int64
err := s.db.WithContext(ctx).Model(&model.LogArchiveRun{}).
Where("archive_date >= ? AND archive_date < ? AND instance_id = ? AND cleanup_started_at IS NOT NULL",
start.Format(time.DateOnly), end.Format(time.DateOnly), s.instanceID).
Count(&count).Error
if err != nil {
return false, fmt.Errorf("读取月度清理断点失败: %w", err)
}
return count > 0, nil
}
func (s *Service) loadRetentionRuns(ctx context.Context, start, end time.Time) (retentionRuns, error) {
var rows []model.LogArchiveRun
err := s.db.WithContext(ctx).Where(
"source IN ? AND archive_date >= ? AND archive_date < ? AND instance_id = ?",
[]string{constants.AuditArchiveSource, constants.IntegrationArchiveSource}, start.Format(time.DateOnly), end.Format(time.DateOnly), s.instanceID,
).Order("archive_date ASC, source ASC").Find(&rows).Error
if err != nil {
return retentionRuns{}, fmt.Errorf("读取月度归档账本失败: %w", err)
}
days := int(end.Sub(start).Hours() / 24)
if len(rows) != days*2 {
return retentionRuns{}, fmt.Errorf("月度归档账本缺日:期望 %d 条,实际 %d 条", days*2, len(rows))
}
runs := retentionRuns{audit: make([]*model.LogArchiveRun, 0, days), integration: make([]*model.LogArchiveRun, 0, days)}
for index := range rows {
run := &rows[index]
switch run.Source {
case constants.AuditArchiveSource:
runs.audit = append(runs.audit, run)
case constants.IntegrationArchiveSource:
runs.integration = append(runs.integration, run)
}
}
if len(runs.audit) != days || len(runs.integration) != days {
return retentionRuns{}, fmt.Errorf("月度 Audit 或 Integration 归档账本不完整")
}
return runs, nil
}
func (s *Service) validateRetentionRuns(ctx context.Context, start, end time.Time, runs retentionRuns) error {
if err := validateCleanupLedgerState(runs.audit); err != nil {
return fmt.Errorf("Audit 清理断点非法: %w", err)
}
if err := validateCleanupLedgerState(runs.integration); err != nil {
return fmt.Errorf("Integration 清理断点非法: %w", err)
}
for index := range runs.audit {
date := start.AddDate(0, 0, index)
if err := s.validateAuditRetentionDay(ctx, date, runs.audit[index]); err != nil {
return fmt.Errorf("%s Audit 清理门禁失败: %w", date.Format(time.DateOnly), err)
}
if err := s.validateIntegrationRetentionDay(ctx, date, runs.integration[index]); err != nil {
return fmt.Errorf("%s Integration 清理门禁失败: %w", date.Format(time.DateOnly), err)
}
}
return nil
}
func validateCleanupLedgerState(runs []*model.LogArchiveRun) error {
started, cleaned := 0, 0
for _, run := range runs {
if run.CleanupStartedAt != nil {
started++
}
if run.CleanedAt != nil {
cleaned++
}
}
if started != 0 && started != len(runs) {
return fmt.Errorf("清理开始断点不是整月原子状态")
}
if cleaned != 0 && cleaned != len(runs) {
return fmt.Errorf("清理完成断点不是整月原子状态")
}
if cleaned > 0 && started == 0 {
return fmt.Errorf("清理完成但缺少开始断点")
}
return nil
}
func (s *Service) validateAuditRetentionDay(ctx context.Context, date time.Time, run *model.LogArchiveRun) error {
if err := validateRunBase(run, date, constants.AuditArchiveSchemaVersion, false); err != nil {
return err
}
if err := s.validateAuditManifest(ctx, run); err != nil {
return err
}
events, resources, err := s.databaseCounts(ctx, run.RangeStart, run.RangeEnd)
if err != nil {
return err
}
return validateRemainingCounts(run, events, resources)
}
func (s *Service) validateIntegrationRetentionDay(ctx context.Context, date time.Time, run *model.LogArchiveRun) error {
if err := validateRunBase(run, date, constants.IntegrationArchiveSchemaVersion, true); err != nil {
return err
}
if err := s.validateIntegrationManifest(ctx, run); err != nil {
return err
}
count, err := s.integrationRecordCount(ctx, run.RangeStart, run.RangeEnd)
if err != nil {
return err
}
if run.CleanedAt != nil {
if count != 0 {
return fmt.Errorf("已标记清理完成但数据库仍有 %d 条记录", count)
}
return nil
}
if run.CleanupStartedAt != nil {
if count > run.RecordCount {
return fmt.Errorf("续跑窗口记录数超过最终归档数量")
}
return nil
}
file, err := s.buildIntegrationArchiveFile(ctx, run.RangeStart, run.RangeEnd)
if err != nil {
return err
}
defer os.Remove(file.path)
if file.recordCount != run.RecordCount || file.sha256 != run.SHA256 {
return fmt.Errorf("数据库当前 Integration 内容与最终 revision 不一致")
}
return nil
}
func validateRunBase(run *model.LogArchiveRun, date time.Time, schema string, final bool) error {
if run.Status != constants.ArchiveStatusSuccess || run.SchemaVersion != schema {
return fmt.Errorf("归档状态或 schema version 不符合清理要求")
}
if run.ArchiveDate.Format(time.DateOnly) != date.Format(time.DateOnly) ||
!run.RangeStart.Equal(date) || !run.RangeEnd.Equal(date.AddDate(0, 0, 1)) {
return fmt.Errorf("归档日期或半开时间范围不一致")
}
if final && !run.IsFinal {
return fmt.Errorf("Integration 最终 revision 尚未形成")
}
if run.ObjectKey == "" || run.ManifestKey == "" || run.SHA256 == "" {
return fmt.Errorf("归档对象、manifest 或 SHA-256 缺失")
}
return nil
}
func validateRemainingCounts(run *model.LogArchiveRun, events, resources int64) error {
if run.CleanedAt != nil {
if events != 0 || resources != 0 {
return fmt.Errorf("已标记清理完成但数据库仍有事件或资源")
}
return nil
}
if run.CleanupStartedAt != nil {
if events > run.EventCount || resources > run.ResourceCount {
return fmt.Errorf("续跑窗口数量超过已归档数量")
}
return nil
}
if events != run.EventCount || resources != run.ResourceCount {
return fmt.Errorf("数据库事件或资源数量与 manifest 不一致")
}
return nil
}
func (s *Service) validateAuditManifest(ctx context.Context, run *model.LogArchiveRun) error {
var manifest Manifest
if err := s.readManifest(ctx, run.ManifestKey, &manifest); err != nil {
return err
}
if manifest.Source != run.Source || manifest.SchemaVersion != run.SchemaVersion || manifest.Status != constants.ArchiveStatusSuccess ||
manifest.ArchiveDate != run.ArchiveDate.Format(time.DateOnly) || manifest.Timezone != constants.AuditArchiveTimezone ||
manifest.InstanceID != run.InstanceID || !manifest.RangeStart.Equal(run.RangeStart) || !manifest.RangeEnd.Equal(run.RangeEnd) ||
manifest.EventCount != run.EventCount || manifest.ResourceCount != run.ResourceCount ||
manifest.CompressedBytes != run.CompressedBytes || manifest.ObjectKey != run.ObjectKey ||
manifest.SHA256 != run.SHA256 || manifest.Revision != run.Revision {
return fmt.Errorf("Audit manifest 与 ledger 不一致")
}
if err := s.verifyObject(ctx, run.ManifestKey, -1, map[string]string{
"source": constants.AuditArchiveSource, "data-sha256": run.SHA256, "revision": strconv.Itoa(run.Revision),
}); err != nil {
return err
}
return s.verifyRetentionObject(ctx, run, false)
}
func (s *Service) validateIntegrationManifest(ctx context.Context, run *model.LogArchiveRun) error {
var manifest integrationArchiveManifest
if err := s.readManifest(ctx, run.ManifestKey, &manifest); err != nil {
return err
}
if manifest.Source != run.Source || manifest.SchemaVersion != run.SchemaVersion || manifest.Status != constants.ArchiveStatusSuccess || !manifest.Final ||
manifest.ArchiveDate != run.ArchiveDate.Format(time.DateOnly) || manifest.Timezone != constants.AuditArchiveTimezone ||
manifest.InstanceID != run.InstanceID || !manifest.RangeStart.Equal(run.RangeStart) || !manifest.RangeEnd.Equal(run.RangeEnd) ||
manifest.RecordCount != run.RecordCount || manifest.CompressedBytes != run.CompressedBytes ||
manifest.ObjectKey != run.ObjectKey || manifest.SHA256 != run.SHA256 || manifest.Revision != run.Revision {
return fmt.Errorf("Integration manifest 与最终 ledger 不一致")
}
if err := s.verifyObject(ctx, run.ManifestKey, -1, map[string]string{
"source": constants.IntegrationArchiveSource, "data-sha256": run.SHA256,
"revision": strconv.Itoa(run.Revision), "final": "true",
}); err != nil {
return err
}
return s.verifyRetentionObject(ctx, run, true)
}
func (s *Service) readManifest(ctx context.Context, key string, target any) error {
object, err := s.store.Stat(ctx, key)
if err != nil {
return fmt.Errorf("读取 manifest metadata 失败: %w", err)
}
reader, err := s.store.Download(ctx, key)
if err != nil {
return fmt.Errorf("下载 manifest 失败: %w", err)
}
data, readErr := io.ReadAll(io.LimitReader(reader, maxManifestBytes+1))
closeErr := reader.Close()
if readErr != nil {
return fmt.Errorf("读取 manifest 失败: %w", readErr)
}
if closeErr != nil {
return fmt.Errorf("关闭 manifest 对象失败: %w", closeErr)
}
if len(data) > maxManifestBytes || int64(len(data)) != object.Size {
return fmt.Errorf("manifest 大小非法或不完整")
}
if err := sonic.Unmarshal(data, target); err != nil {
return fmt.Errorf("解析 manifest 失败: %w", err)
}
return nil
}
func (s *Service) verifyRetentionObject(ctx context.Context, run *model.LogArchiveRun, final bool) error {
metadata := map[string]string{
"schema-version": run.SchemaVersion, "source": run.Source,
"archive-date": run.RangeStart.Format(time.DateOnly), "timezone": constants.AuditArchiveTimezone,
"sha256": run.SHA256, "revision": strconv.Itoa(run.Revision),
}
if run.Source == constants.AuditArchiveSource {
metadata["event-count"] = strconv.FormatInt(run.EventCount, 10)
metadata["resource-count"] = strconv.FormatInt(run.ResourceCount, 10)
} else {
metadata["record-count"] = strconv.FormatInt(run.RecordCount, 10)
metadata["final"] = strconv.FormatBool(final)
}
if err := s.verifyObject(ctx, run.ObjectKey, run.CompressedBytes, metadata); err != nil {
return err
}
reader, err := s.store.Download(ctx, run.ObjectKey)
if err != nil {
return fmt.Errorf("下载归档对象复核 SHA-256 失败: %w", err)
}
hasher := sha256.New()
written, copyErr := io.Copy(hasher, reader)
closeErr := reader.Close()
if copyErr != nil {
return fmt.Errorf("读取归档对象复核 SHA-256 失败: %w", copyErr)
}
if closeErr != nil {
return fmt.Errorf("关闭归档对象失败: %w", closeErr)
}
if written != run.CompressedBytes || fmt.Sprintf("%x", hasher.Sum(nil)) != run.SHA256 {
return fmt.Errorf("归档对象大小或 SHA-256 复核失败")
}
return nil
}
func summarizeRetentionRuns(runs retentionRuns, result *RetentionResult) {
result.ManifestKeys = make([]string, 0, len(runs.audit)+len(runs.integration))
for _, run := range runs.audit {
result.EventCount += run.EventCount
result.ResourceCount += run.ResourceCount
result.ManifestKeys = append(result.ManifestKeys, run.ManifestKey)
}
for _, run := range runs.integration {
result.IntegrationCount += run.RecordCount
result.ManifestKeys = append(result.ManifestKeys, run.ManifestKey)
}
}
func estimatedRetentionBatches(result RetentionResult) int64 {
batchSize := int64(constants.AuditRetentionDeleteBatchSize)
return (result.EventCount+batchSize-1)/batchSize +
(result.ResourceCount+batchSize-1)/batchSize +
(result.IntegrationCount+batchSize-1)/batchSize
}
func (s *Service) cleanupAuditMonth(ctx context.Context, start, end time.Time, runs []*model.LogArchiveRun) error {
if allRunsCleaned(runs) {
return nil
}
if err := s.markCleanupStarted(ctx, constants.AuditArchiveSource, start, end); err != nil {
return err
}
if err := s.deleteAuditResources(ctx, start, end); err != nil {
return err
}
if err := s.deleteAuditEvents(ctx, start, end); err != nil {
return err
}
return s.markCleaned(ctx, constants.AuditArchiveSource, start, end)
}
func (s *Service) cleanupIntegrationMonth(ctx context.Context, start, end time.Time, runs []*model.LogArchiveRun) error {
if allRunsCleaned(runs) {
return nil
}
if err := s.markCleanupStarted(ctx, constants.IntegrationArchiveSource, start, end); err != nil {
return err
}
for {
subquery := s.db.Model(&model.IntegrationLog{}).Select("id").
Where("created_at >= ? AND created_at < ?", start, end).Order("id ASC").Limit(constants.AuditRetentionDeleteBatchSize)
deleted := s.db.WithContext(ctx).Where("id IN (?)", subquery).Delete(&model.IntegrationLog{})
if deleted.Error != nil {
return fmt.Errorf("分批物理删除 Integration Log 失败: %w", deleted.Error)
}
if deleted.RowsAffected == 0 {
break
}
}
return s.markCleaned(ctx, constants.IntegrationArchiveSource, start, end)
}
func (s *Service) deleteAuditResources(ctx context.Context, start, end time.Time) error {
for {
subquery := s.db.Model(&model.AuditEventResource{}).Select("tb_audit_event_resource.id").
Joins("JOIN tb_audit_event ON tb_audit_event.id = tb_audit_event_resource.audit_event_id").
Where("tb_audit_event.created_at >= ? AND tb_audit_event.created_at < ?", start, end).
Order("tb_audit_event_resource.id ASC").Limit(constants.AuditRetentionDeleteBatchSize)
deleted := s.db.WithContext(ctx).Where("id IN (?)", subquery).Delete(&model.AuditEventResource{})
if deleted.Error != nil {
return fmt.Errorf("分批物理删除 Audit Event Resource 失败: %w", deleted.Error)
}
if deleted.RowsAffected == 0 {
return nil
}
}
}
func (s *Service) deleteAuditEvents(ctx context.Context, start, end time.Time) error {
for {
subquery := s.db.Model(&model.AuditEvent{}).Select("id").
Where("created_at >= ? AND created_at < ?", start, end).Order("id ASC").Limit(constants.AuditRetentionDeleteBatchSize)
deleted := s.db.WithContext(ctx).Where("id IN (?)", subquery).Delete(&model.AuditEvent{})
if deleted.Error != nil {
return fmt.Errorf("分批物理删除 Audit Event 失败: %w", deleted.Error)
}
if deleted.RowsAffected == 0 {
return nil
}
}
}
func (s *Service) markCleanupStarted(ctx context.Context, source string, start, end time.Time) error {
now := time.Now()
result := s.db.WithContext(ctx).Model(&model.LogArchiveRun{}).
Where("source = ? AND archive_date >= ? AND archive_date < ? AND instance_id = ? AND cleanup_started_at IS NULL",
source, start.Format(time.DateOnly), end.Format(time.DateOnly), s.instanceID).
Updates(map[string]any{"cleanup_started_at": now, "updated_at": now})
if result.Error != nil {
return fmt.Errorf("记录月度清理开始断点失败: %w", result.Error)
}
return s.validateCleanupMarkerCount(ctx, source, start, end, "cleanup_started_at IS NOT NULL", "开始")
}
func (s *Service) markCleaned(ctx context.Context, source string, start, end time.Time) error {
now := time.Now()
result := s.db.WithContext(ctx).Model(&model.LogArchiveRun{}).
Where("source = ? AND archive_date >= ? AND archive_date < ? AND instance_id = ? AND cleanup_started_at IS NOT NULL",
source, start.Format(time.DateOnly), end.Format(time.DateOnly), s.instanceID).
Updates(map[string]any{"cleaned_at": now, "updated_at": now})
if result.Error != nil {
return fmt.Errorf("记录月度清理完成断点失败: %w", result.Error)
}
return s.validateCleanupMarkerCount(ctx, source, start, end, "cleaned_at IS NOT NULL", "完成")
}
func (s *Service) validateCleanupMarkerCount(ctx context.Context, source string, start, end time.Time, marker, label string) error {
var count int64
err := s.db.WithContext(ctx).Model(&model.LogArchiveRun{}).
Where("source = ? AND archive_date >= ? AND archive_date < ? AND instance_id = ? AND "+marker,
source, start.Format(time.DateOnly), end.Format(time.DateOnly), s.instanceID).
Count(&count).Error
if err != nil {
return fmt.Errorf("复核月度清理%s断点失败: %w", label, err)
}
expected := int64(end.Sub(start).Hours() / 24)
if count != expected {
return fmt.Errorf("月度清理%s断点不完整期望 %d 条,实际 %d 条", label, expected, count)
}
return nil
}
func allRunsCleaned(runs []*model.LogArchiveRun) bool {
return len(runs) > 0 && runs[0].CleanedAt != nil
}
func (s *Service) recordRetentionAudit(ctx context.Context, start, end time.Time, result RetentionResult, cleanupErr error) error {
audit := RetentionAudit{
Month: result.Month, RangeStart: start, RangeEnd: end,
EventCount: result.EventCount, ResourceCount: result.ResourceCount,
IntegrationCount: result.IntegrationCount, ManifestKeys: result.ManifestKeys,
DurationMS: result.Duration.Milliseconds(), Result: constants.AuditResultSuccess,
Summary: "完成已归档在线日志月度物理清理",
EventID: "evt_retention_" + strings.ReplaceAll(result.Month, "-", "_"),
}
if cleanupErr != nil {
audit.EventID = ""
audit.Result = constants.AuditResultFailed
audit.Summary = "已归档在线日志月度物理清理失败"
audit.ErrorSummary = truncateRetentionError(cleanupErr)
}
return s.db.WithContext(ctx).Transaction(func(tx *gorm.DB) error {
return s.audit.WriteRetentionCleanup(ctx, tx, audit)
})
}
func truncateRetentionError(err error) string {
value := []rune(err.Error())
if len(value) > 500 {
value = value[:500]
}
return string(value)
}