fix(#196): fix race condition in job status updates

Implemented optimistic locking with version field and SELECT FOR UPDATE
transactions to prevent data corruption from concurrent job status updates.

Changes:
- Added version field to RunnerJob schema for optimistic locking
- Created migration 20260202_add_runner_job_version_for_concurrency
- Implemented ConcurrentUpdateException for conflict detection
- Updated RunnerJobsService methods with optimistic locking:
  * updateStatus() - with version checking and retry logic
  * updateProgress() - with version checking and retry logic
  * cancel() - with version checking and retry logic
- Updated CoordinatorIntegrationService with SELECT FOR UPDATE:
  * updateJobStatus() - transaction with row locking
  * completeJob() - transaction with row locking
  * failJob() - transaction with row locking
  * updateJobProgress() - optimistic locking
- Added retry mechanism (3 attempts) with exponential backoff
- Added comprehensive concurrency tests (10 tests, all passing)
- Updated existing test mocks to support updateMany

Test Results:
- All 10 concurrency tests passing ✓
- Tests cover concurrent status updates, progress updates, completions,
  cancellations, retry logic, and exponential backoff

This fix prevents race conditions that could cause:
- Lost job results (double completion)
- Lost progress updates
- Invalid status transitions
- Data corruption under concurrent access

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
Jason Woltje
2026-02-02 12:51:17 -06:00
parent a3b48dd631
commit ef25167c24
251 changed files with 7045 additions and 261 deletions

View File

@@ -1,5 +1,5 @@
import { Injectable, NotFoundException } from "@nestjs/common";
import { Prisma } from "@prisma/client";
import { Prisma, UserLayout } from "@prisma/client";
import { PrismaService } from "../prisma/prisma.service";
import type { CreateLayoutDto, UpdateLayoutDto } from "./dto";
@@ -13,7 +13,7 @@ export class LayoutsService {
/**
* Get all layouts for a user
*/
async findAll(workspaceId: string, userId: string) {
async findAll(workspaceId: string, userId: string): Promise<UserLayout[]> {
return this.prisma.userLayout.findMany({
where: {
workspaceId,
@@ -29,7 +29,7 @@ export class LayoutsService {
/**
* Get the default layout for a user
*/
async findDefault(workspaceId: string, userId: string) {
async findDefault(workspaceId: string, userId: string): Promise<UserLayout> {
const layout = await this.prisma.userLayout.findFirst({
where: {
workspaceId,
@@ -63,7 +63,7 @@ export class LayoutsService {
/**
* Get a single layout by ID
*/
async findOne(id: string, workspaceId: string, userId: string) {
async findOne(id: string, workspaceId: string, userId: string): Promise<UserLayout> {
const layout = await this.prisma.userLayout.findUnique({
where: {
id,
@@ -82,7 +82,11 @@ export class LayoutsService {
/**
* Create a new layout
*/
async create(workspaceId: string, userId: string, createLayoutDto: CreateLayoutDto) {
async create(
workspaceId: string,
userId: string,
createLayoutDto: CreateLayoutDto
): Promise<UserLayout> {
// Use transaction to ensure atomicity when setting default
return this.prisma.$transaction(async (tx) => {
// If setting as default, unset other defaults first
@@ -114,7 +118,12 @@ export class LayoutsService {
/**
* Update a layout
*/
async update(id: string, workspaceId: string, userId: string, updateLayoutDto: UpdateLayoutDto) {
async update(
id: string,
workspaceId: string,
userId: string,
updateLayoutDto: UpdateLayoutDto
): Promise<UserLayout> {
// Use transaction to ensure atomicity when setting default
return this.prisma.$transaction(async (tx) => {
// Verify layout exists
@@ -163,7 +172,7 @@ export class LayoutsService {
/**
* Delete a layout
*/
async remove(id: string, workspaceId: string, userId: string) {
async remove(id: string, workspaceId: string, userId: string): Promise<void> {
// Verify layout exists
const layout = await this.prisma.userLayout.findUnique({
where: { id, workspaceId, userId },