fix(tasks): 任务队列 - 限制缓存回源并修复并发租约与过期写入

This commit is contained in:
ddCat
2026-09-06 00:28:45 +08:00
parent 1ff5e5cada
commit bf0c4454fa
23 changed files with 1098 additions and 59 deletions

View File

@@ -1,6 +1,7 @@
package repository
import (
"context"
"errors"
"fmt"
"slices"
@@ -54,6 +55,10 @@ func New(db *gorm.DB) *Repository {
return &Repository{db: db}
}
func (r *Repository) WithContext(ctx context.Context) *Repository {
return &Repository{db: r.db.WithContext(ctx)}
}
func (r *Repository) Dialect() string {
return r.db.Dialector.Name()
}
@@ -428,7 +433,7 @@ func (r *Repository) ClaimNextTask(owner string, leaseDuration time.Duration) (*
func (r *Repository) RenewTaskLease(id string, owner string, leaseDuration time.Duration) error {
result := r.db.Model(&model.Task{}).
Where("id = ? AND status = ? AND lease_owner = ?", id, model.TaskStatusRunning, owner).
Where("id = ? AND status = ? AND lease_owner = ? AND lease_expires_at > ?", id, model.TaskStatusRunning, owner, time.Now()).
Updates(map[string]any{"lease_expires_at": time.Now().Add(leaseDuration), "updated_at": time.Now()})
if result.Error != nil {
return result.Error
@@ -449,8 +454,8 @@ func (r *Repository) UpdateTaskProviderState(id string, providerRequestID string
func (r *Repository) DeferRunningTaskForProviderPoll(id string, owner string, stage string, delay time.Duration) error {
now := time.Now()
result := r.db.Model(&model.Task{}).
Where("id = ? AND status = ? AND lease_owner = ?", id, model.TaskStatusRunning, owner).
result := taskLeaseWriter(r.db.Model(&model.Task{}), owner).
Where("id = ? AND status = ?", id, model.TaskStatusRunning).
Updates(map[string]any{
"stage": stage, "error": "", "completed_at": nil, "next_poll_at": now.Add(delay),
"lease_owner": "", "lease_expires_at": nil, "updated_at": now,
@@ -500,6 +505,27 @@ func (r *Repository) UpdateTaskProgress(id string, stage string, progress int) e
}).Error
}
func (r *Repository) UpdateTaskProgressForLease(id string, owner string, stage string, progress int) error {
result := taskLeaseWriter(r.db.Model(&model.Task{}), owner).
Where("id = ? AND status = ?", id, model.TaskStatusRunning).
Updates(map[string]any{"stage": stage, "progress": progress, "updated_at": time.Now()})
if result.Error != nil {
return result.Error
}
if result.RowsAffected != 1 {
return ErrTaskStateConflict
}
return nil
}
// 无租约任务仅能写无租约记录;有租约的执行者必须仍持有本次领取的有效 owner。
func taskLeaseWriter(db *gorm.DB, owner string) *gorm.DB {
if owner == "" {
return db.Where("(lease_owner = '' OR lease_owner IS NULL)")
}
return db.Where("lease_owner = ? AND lease_expires_at > ?", owner, time.Now())
}
// UpdateTaskProviderProgress records upstream-reported progress without allowing
// a delayed or out-of-order poll response to move the public percentage backwards.
func (r *Repository) UpdateTaskProviderProgress(id string, progress int) error {
@@ -513,7 +539,7 @@ func (r *Repository) UpdateTaskProviderProgress(id string, progress int) error {
func (r *Repository) SaveTaskCompletion(task *model.Task, expected model.TaskStatus, session *model.Session, message *model.Message, results []model.Result) error {
return r.db.Transaction(func(tx *gorm.DB) error {
updated := tx.Model(&model.Task{}).
updated := taskLeaseWriter(tx.Model(&model.Task{}), task.LeaseOwner).
Where("id = ? AND status = ?", task.ID, expected).
Select("*").Omit("id", "created_at").Updates(task)
if updated.Error != nil {
@@ -541,8 +567,8 @@ func (r *Repository) SaveTaskCompletion(task *model.Task, expected model.TaskSta
})
}
func (r *Repository) UpdateTaskTerminalState(id string, expected model.TaskStatus, status model.TaskStatus, stage string, errorText string, completedAt time.Time) (bool, error) {
result := r.db.Model(&model.Task{}).
func (r *Repository) UpdateTaskTerminalState(id string, owner string, expected model.TaskStatus, status model.TaskStatus, stage string, errorText string, completedAt time.Time) (bool, error) {
result := taskLeaseWriter(r.db.Model(&model.Task{}), owner).
Where("id = ? AND status = ?", id, expected).
Updates(map[string]any{
"status": status, "stage": stage, "error": errorText, "completed_at": &completedAt,

View File

@@ -0,0 +1,75 @@
package repository
import (
"errors"
"testing"
"time"
"gorm.io/driver/sqlite"
"gorm.io/gorm"
"infinite-canvas/backend/internal/model"
)
func TestTaskLeaseFencesExpiredAndReclaimedWriters(t *testing.T) {
db, err := gorm.Open(sqlite.Open(":memory:"), &gorm.Config{})
if err != nil {
t.Fatal(err)
}
if err := db.AutoMigrate(&model.Task{}, &model.Result{}, &model.Message{}, &model.Session{}); err != nil {
t.Fatal(err)
}
if err := db.Create(&model.Task{ID: "task", UserID: "user", Status: model.TaskStatusQueued}).Error; err != nil {
t.Fatal(err)
}
repo := New(db)
old, err := repo.ClaimNextTask("worker:attempt-a", time.Minute)
if err != nil || old == nil {
t.Fatalf("claim: %v %v", old, err)
}
if err := db.Model(&model.Task{}).Where("id = ?", old.ID).Update("lease_expires_at", time.Now().Add(-time.Second)).Error; err != nil {
t.Fatal(err)
}
if err := repo.RenewTaskLease(old.ID, old.LeaseOwner, time.Minute); err == nil {
t.Fatal("expired owner resurrected")
}
if err := repo.DeferRunningTaskForProviderPoll(old.ID, old.LeaseOwner, "poll", time.Minute); !errors.Is(err, ErrTaskStateConflict) {
t.Fatalf("expired owner deferred task: %v", err)
}
current, err := repo.ClaimNextTask("worker:attempt-b", time.Minute)
if err != nil || current == nil {
t.Fatalf("reclaim: %v %v", current, err)
}
for _, owner := range []string{old.LeaseOwner, ""} {
if err := repo.UpdateTaskProgressForLease(old.ID, owner, "stale", 90); !errors.Is(err, ErrTaskStateConflict) {
t.Fatalf("stale progress: %v", err)
}
updated, err := repo.UpdateTaskTerminalState(old.ID, owner, model.TaskStatusRunning, model.TaskStatusFailed, "stale", "", time.Now())
if err != nil || updated {
t.Fatalf("stale terminal: %v %v", updated, err)
}
}
old.Status = model.TaskStatusSucceeded
if err := repo.SaveTaskCompletion(old, model.TaskStatusRunning, nil, &model.Message{ID: "stale"}, []model.Result{{ID: "stale"}}); !errors.Is(err, ErrTaskStateConflict) {
t.Fatalf("stale completion: %v", err)
}
var count int64
for _, table := range []any{&model.Result{}, &model.Message{}} {
if err := db.Model(table).Count(&count).Error; err != nil || count != 0 {
t.Fatalf("stale related row persisted: %d %v", count, err)
}
}
if err := repo.RenewTaskLease(current.ID, current.LeaseOwner, time.Minute); err != nil {
t.Fatal(err)
}
if err := repo.UpdateTaskProgressForLease(current.ID, current.LeaseOwner, "current", 60); err != nil {
t.Fatal(err)
}
current.Status = model.TaskStatusSucceeded
if err := repo.SaveTaskCompletion(current, model.TaskStatusRunning, nil, nil, []model.Result{{ID: "valid", TaskID: current.ID}}); err != nil {
t.Fatal(err)
}
stored, err := repo.Task(current.ID)
if err != nil || stored.Status != model.TaskStatusSucceeded || stored.LeaseOwner != current.LeaseOwner {
t.Fatalf("current completion: %v %v", stored, err)
}
}