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

@@ -1,9 +1,14 @@
import { Injectable, NotFoundException } from "@nestjs/common";
import { Prisma } from "@prisma/client";
import { Prisma, Event } from "@prisma/client";
import { PrismaService } from "../prisma/prisma.service";
import { ActivityService } from "../activity/activity.service";
import type { CreateEventDto, UpdateEventDto, QueryEventsDto } from "./dto";
type EventWithRelations = Event & {
creator: { id: string; name: string; email: string };
project: { id: string; name: string; color: string | null } | null;
};
/**
* Service for managing events
*/
@@ -17,7 +22,11 @@ export class EventsService {
/**
* Create a new event
*/
async create(workspaceId: string, userId: string, createEventDto: CreateEventDto) {
async create(
workspaceId: string,
userId: string,
createEventDto: CreateEventDto
): Promise<EventWithRelations> {
const projectConnection = createEventDto.projectId
? { connect: { id: createEventDto.projectId } }
: undefined;
@@ -60,7 +69,15 @@ export class EventsService {
/**
* Get paginated events with filters
*/
async findAll(query: QueryEventsDto) {
async findAll(query: QueryEventsDto): Promise<{
data: EventWithRelations[];
meta: {
total: number;
page: number;
limit: number;
totalPages: number;
};
}> {
const page = query.page ?? 1;
const limit = query.limit ?? 50;
const skip = (page - 1) * limit;
@@ -125,7 +142,7 @@ export class EventsService {
/**
* Get a single event by ID
*/
async findOne(id: string, workspaceId: string) {
async findOne(id: string, workspaceId: string): Promise<EventWithRelations> {
const event = await this.prisma.event.findUnique({
where: {
id,
@@ -151,7 +168,12 @@ export class EventsService {
/**
* Update an event
*/
async update(id: string, workspaceId: string, userId: string, updateEventDto: UpdateEventDto) {
async update(
id: string,
workspaceId: string,
userId: string,
updateEventDto: UpdateEventDto
): Promise<EventWithRelations> {
// Verify event exists
const existingEvent = await this.prisma.event.findUnique({
where: { id, workspaceId },
@@ -208,7 +230,7 @@ export class EventsService {
/**
* Delete an event
*/
async remove(id: string, workspaceId: string, userId: string) {
async remove(id: string, workspaceId: string, userId: string): Promise<void> {
// Verify event exists
const event = await this.prisma.event.findUnique({
where: { id, workspaceId },