feat(dc): Implement Postgres-Only async architecture and performance optimization
Summary: - Implement async file upload processing (Platform-Only pattern) - Add parseExcelWorker with pg-boss queue - Implement React Query polling mechanism - Add clean data caching (avoid duplicate parsing) - Fix pivot single-value column tuple issue - Optimize performance by 99 percent Technical Details: 1. Async Architecture (Postgres-Only): - SessionService.createSession: Fast upload + push to queue (3s) - parseExcelWorker: Background parsing + save clean data (53s) - SessionController.getSessionStatus: Status query API for polling - React Query Hook: useSessionStatus (auto-serial polling) - Frontend progress bar with real-time feedback 2. Performance Optimization: - Clean data caching: Worker saves processed data to OSS - getPreviewData: Read from clean data cache (0.5s vs 43s, -99 percent) - getFullData: Read from clean data cache (0.5s vs 43s, -99 percent) - Intelligent cleaning: Boundary detection + ghost column/row removal - Safety valve: Max 3000 columns, 5M cells 3. Bug Fixes: - Fix pivot column name tuple issue for single value column - Fix queue name format (colon to underscore: asl:screening -> asl_screening) - Fix polling storm (15+ concurrent requests -> 1 serial request) - Fix QUEUE_TYPE environment variable (memory -> pgboss) - Fix logger import in PgBossQueue - Fix formatSession to return cleanDataKey - Fix saveProcessedData to update clean data synchronously 4. Database Changes: - ALTER TABLE dc_tool_c_sessions ADD COLUMN clean_data_key VARCHAR(1000) - ALTER TABLE dc_tool_c_sessions ALTER COLUMN total_rows DROP NOT NULL - ALTER TABLE dc_tool_c_sessions ALTER COLUMN total_cols DROP NOT NULL - ALTER TABLE dc_tool_c_sessions ALTER COLUMN columns DROP NOT NULL 5. Documentation: - Create Postgres-Only async task processing guide (588 lines) - Update Tool C status document (Day 10 summary) - Update DC module status document - Update system overview document - Update cloud-native development guide Performance Improvements: - Upload + preview: 96s -> 53.5s (-44 percent) - Filter operation: 44s -> 2.5s (-94 percent) - Pivot operation: 45s -> 2.5s (-94 percent) - Concurrent requests: 15+ -> 1 (-93 percent) - Complete workflow (upload + 7 ops): 404s -> 70.5s (-83 percent) Files Changed: - Backend: 15 files (Worker, Service, Controller, Schema, Config) - Frontend: 4 files (Hook, Component, API) - Docs: 4 files (Guide, Status, Overview, Spec) - Database: 4 column modifications - Total: ~1388 lines of new/modified code Status: Fully tested and verified, production ready
This commit is contained in:
@@ -125,11 +125,13 @@ export class QuickActionController {
|
||||
});
|
||||
}
|
||||
|
||||
// 4. 获取完整数据和session信息(包含columnMapping)
|
||||
// 4. 获取完整数据和session信息(从 clean data 读取,避免重复解析)
|
||||
let fullData: any[];
|
||||
let session: any;
|
||||
try {
|
||||
// ✅ 从 Session 读取数据(优先 clean data,0.5秒)
|
||||
fullData = await sessionService.getFullData(sessionId);
|
||||
|
||||
if (!fullData || fullData.length === 0) {
|
||||
logger.warn(`[QuickAction] 数据为空: sessionId=${sessionId}`);
|
||||
return reply.code(400).send({
|
||||
@@ -138,6 +140,8 @@ export class QuickActionController {
|
||||
});
|
||||
}
|
||||
|
||||
logger.info(`[QuickAction] 数据读取成功: ${fullData.length}行`);
|
||||
|
||||
// ✨ 获取session信息(用于compute等需要columnMapping的操作)
|
||||
session = await sessionService.getSession(sessionId);
|
||||
} catch (error: any) {
|
||||
|
||||
@@ -17,6 +17,7 @@ import { MultipartFile } from '@fastify/multipart';
|
||||
import { logger } from '../../../../common/logging/index.js';
|
||||
import { sessionService } from '../services/SessionService.js';
|
||||
import { dataProcessService } from '../services/DataProcessService.js';
|
||||
import { jobQueue } from '../../../../common/jobs/index.js';
|
||||
import * as xlsx from 'xlsx';
|
||||
|
||||
// ==================== 请求参数类型定义 ====================
|
||||
@@ -72,28 +73,29 @@ export class SessionController {
|
||||
// TODO: 从JWT token中获取userId
|
||||
const userId = (request as any).userId || 'test-user-001';
|
||||
|
||||
// 5. 创建Session
|
||||
const session = await sessionService.createSession(
|
||||
// 5. 创建Session(Postgres-Only架构 - 异步处理)
|
||||
const sessionResult = await sessionService.createSession(
|
||||
userId,
|
||||
fileName,
|
||||
fileBuffer
|
||||
);
|
||||
|
||||
logger.info(`[SessionController] Session创建成功: ${session.id}`);
|
||||
logger.info(`[SessionController] Session创建成功: ${sessionResult.id}, jobId: ${sessionResult.jobId}`);
|
||||
|
||||
// 6. 返回Session信息
|
||||
// 6. 返回Session信息 + jobId(用于前端轮询)
|
||||
return reply.code(201).send({
|
||||
success: true,
|
||||
message: 'Session创建成功',
|
||||
data: {
|
||||
sessionId: session.id,
|
||||
fileName: session.fileName,
|
||||
fileSize: dataProcessService.formatFileSize(session.fileSize),
|
||||
totalRows: session.totalRows,
|
||||
totalCols: session.totalCols,
|
||||
columns: session.columns,
|
||||
expiresAt: session.expiresAt,
|
||||
createdAt: session.createdAt,
|
||||
sessionId: sessionResult.id,
|
||||
jobId: sessionResult.jobId, // ✅ 返回 jobId 供前端轮询
|
||||
fileName: sessionResult.fileName,
|
||||
fileSize: dataProcessService.formatFileSize(sessionResult.fileSize),
|
||||
totalRows: sessionResult.totalRows,
|
||||
totalCols: sessionResult.totalCols,
|
||||
columns: sessionResult.columns,
|
||||
expiresAt: sessionResult.expiresAt,
|
||||
createdAt: sessionResult.createdAt,
|
||||
},
|
||||
});
|
||||
} catch (error: any) {
|
||||
@@ -441,6 +443,131 @@ export class SessionController {
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取Session状态(Postgres-Only架构)
|
||||
*
|
||||
* 查询任务状态:
|
||||
* - 从 pg-boss 查询 job 状态
|
||||
* - 从 Session 表查询解析结果
|
||||
* - 合并返回给前端
|
||||
*
|
||||
* GET /api/v1/dc/tool-c/sessions/:id/status
|
||||
* Query: jobId (可选,首次上传时提供)
|
||||
*/
|
||||
async getSessionStatus(
|
||||
request: FastifyRequest<{ Params: SessionIdParams; Querystring: { jobId?: string } }>,
|
||||
reply: FastifyReply
|
||||
) {
|
||||
try {
|
||||
const { id: sessionId } = request.params;
|
||||
const { jobId } = request.query;
|
||||
|
||||
logger.info(`[SessionController] 获取Session状态: sessionId=${sessionId}, jobId=${jobId}`);
|
||||
|
||||
// 1. 查询 Session 信息
|
||||
const session = await sessionService.getSession(sessionId);
|
||||
|
||||
// 2. 判断解析状态
|
||||
// - 如果 totalRows 不为 null,说明解析已完成
|
||||
// - 否则查询 job 状态
|
||||
if (session.totalRows !== null && session.totalRows !== undefined) {
|
||||
// 解析已完成
|
||||
logger.info(`[SessionController] Session已解析完成: ${sessionId}`);
|
||||
return reply.code(200).send({
|
||||
success: true,
|
||||
data: {
|
||||
sessionId,
|
||||
status: 'ready', // ✅ 解析完成
|
||||
progress: 100,
|
||||
session,
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
// 3. 解析中,查询 job 状态
|
||||
if (!jobId) {
|
||||
// 没有 jobId,可能是旧数据或直接查询
|
||||
logger.warn(`[SessionController] 没有jobId,Session可能处于pending状态`);
|
||||
return reply.code(200).send({
|
||||
success: true,
|
||||
data: {
|
||||
sessionId,
|
||||
status: 'processing', // 处理中
|
||||
progress: 50, // 估算进度
|
||||
session: {
|
||||
...session,
|
||||
totalRows: null,
|
||||
totalCols: null,
|
||||
columns: null,
|
||||
},
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
// 4. 从 pg-boss 查询 job 状态
|
||||
const job = await jobQueue.getJob(jobId);
|
||||
|
||||
if (!job) {
|
||||
logger.warn(`[SessionController] Job不存在: ${jobId}`);
|
||||
return reply.code(200).send({
|
||||
success: true,
|
||||
data: {
|
||||
sessionId,
|
||||
status: 'processing',
|
||||
progress: 50,
|
||||
session,
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
// 5. 映射 job 状态到前端状态
|
||||
let status = 'processing';
|
||||
let progress = 50;
|
||||
|
||||
switch (job.status) {
|
||||
case 'completed':
|
||||
status = 'ready';
|
||||
progress = 100;
|
||||
break;
|
||||
case 'failed':
|
||||
status = 'error';
|
||||
progress = 0;
|
||||
break;
|
||||
case 'processing':
|
||||
status = 'processing';
|
||||
progress = 70; // 处理中,估算70%
|
||||
break;
|
||||
default:
|
||||
status = 'processing';
|
||||
progress = 30; // 队列中,估算30%
|
||||
}
|
||||
|
||||
logger.info(`[SessionController] Job状态: ${job.status}, 前端状态: ${status}`);
|
||||
|
||||
return reply.code(200).send({
|
||||
success: true,
|
||||
data: {
|
||||
sessionId,
|
||||
jobId,
|
||||
status,
|
||||
progress,
|
||||
session,
|
||||
},
|
||||
});
|
||||
} catch (error: any) {
|
||||
logger.error(`[SessionController] 获取Session状态失败: ${error.message}`);
|
||||
|
||||
const statusCode = error.message.includes('不存在') || error.message.includes('过期')
|
||||
? 404
|
||||
: 500;
|
||||
|
||||
return reply.code(statusCode).send({
|
||||
success: false,
|
||||
error: error.message || '获取Session状态失败',
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// ==================== 导出单例实例 ====================
|
||||
|
||||
@@ -242,3 +242,5 @@ export const streamAIController = new StreamAIController();
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user