xuyueandClaude Opus 5.5
37e971b6b4
原来的 JudgeServer 按核数起 gunicorn worker、每份提交再按核数开进程池，空闲内存跟着核数走
（2 核 52MB、16 核 305MB）。换成 go-judge 后空闲 16MB，同一批提交判题中 80–100MB（原来约 370MB）。
go-judge 只管在沙箱里跑命令，编译、逐点运行、比对输出、定状态码搬到 judge/sandbox.ts，
口径逐条照搬 JudgeServer，出参形状不变。拿生产库真实提交新旧逐点对比：C 2000 份 1989 一致、
C++ 891 份 890 一致、Python 2000 份全一致；不一致的是 system("pause")（现在不再判运行时错误）、
未定义行为、endl 死循环打印（运行时错误变运行超时），见 docker/judge/README.md。
- 判题容器改成 privileged（go-judge 要自己建 cgroup），镜像 oj2-judge-3
- 心跳改由 worker 每 5 秒问判题机 /version 代记，删掉 /api/judge-server/heartbeat
- 前端统一用 stripJudgePath 去掉判题机工作目录（新的 /w/ 和旧的 /judger/run/）
- 提交前编译检查只编译不运行
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
286 lines
8.4 KiB
TypeScript
286 lines
8.4 KiB
TypeScript
/**
|
||
* 判题沙箱冒烟测试 —— **换镜像之后跑这个**（项目不写测试，验证一律实跑）。
|
||
*
|
||
* bun docker/judge/smoke.ts # 打 .env 里的 JUDGE_SERVER_URL
|
||
* JUDGE_SERVER_URL=http://localhost:8082 bun docker/judge/smoke.ts
|
||
*
|
||
* 走的是线上那份判题代码（apps/api/src/judge/sandbox.ts 的 judge()），不经过 api / worker /
|
||
* 队列，所以不需要起后端，也不需要库里有题 —— 测试点内联传进去。
|
||
*
|
||
* 它核的是四件事：
|
||
* 1. 三种语言都能编译、运行、判对（languageConfigs 就是线上那份，不是另抄的）
|
||
* 2. 六种结果状态的**整数值**没变（落库的值，见 packages/contract/src/judge-status.ts）
|
||
* 3. gcc 的宽松度没变 —— 忘了 #include 的老代码照样能过（gcc-14 默认会把它判 CE）
|
||
* 4. 从 JudgeServer 照搬过来的几条口径：stderr 算进输出、死循环打印判运行时错误（信号 25）
|
||
*/
|
||
import { JudgeStatus } from '@oj2/contract'
|
||
|
||
import { judge, sandboxVersion, type JudgeCase } from '../../apps/api/src/judge/sandbox'
|
||
|
||
const url = process.env.JUDGE_SERVER_URL ?? 'http://localhost:8081'
|
||
if (!process.env.JUDGE_SERVER_TOKEN) {
|
||
console.error('JUDGE_SERVER_TOKEN 没设 —— 在 OJ2 根目录跑，bun 会自己读 .env')
|
||
process.exit(2)
|
||
}
|
||
|
||
interface Case {
|
||
language: string
|
||
name: string
|
||
code: string
|
||
expect: number
|
||
/** 默认 3000ms / 128MB，跑得慢或要撑爆内存的用例自己改 */
|
||
cpu?: number
|
||
memory?: number
|
||
/** 再核一下第一个测试点的信号 */
|
||
signal?: number
|
||
}
|
||
|
||
const sumTestCase = [{ input: '1 2\n', output: '3\n' }]
|
||
|
||
const cases: Case[] = [
|
||
// ---------------------------------------------------------------- C
|
||
{
|
||
language: 'C',
|
||
name: 'C 正常通过',
|
||
expect: JudgeStatus.ACCEPTED,
|
||
code: `#include <stdio.h>
|
||
int main(void) {
|
||
int a, b;
|
||
scanf("%d %d", &a, &b);
|
||
printf("%d\\n", a + b);
|
||
return 0;
|
||
}`,
|
||
},
|
||
{
|
||
// 这条是升 gcc 的主要风险点：gcc-14 起 implicit-function-declaration 是
|
||
// error，languages.ts 里的几个 -Wno-error 就是为它加的。这条挂了说明那些
|
||
// 开关没生效 —— 后果是一批历史题解和 20 篇 C 教程的示例突然全 CE。
|
||
language: 'C',
|
||
name: 'C 忘了 #include 仍能过（gcc 宽松度）',
|
||
expect: JudgeStatus.ACCEPTED,
|
||
code: `int main(void) {
|
||
int a, b;
|
||
scanf("%d %d", &a, &b);
|
||
printf("%d\\n", a + b);
|
||
return 0;
|
||
}`,
|
||
},
|
||
{
|
||
// gcc-14 把 int 函数里不带值的 return;（-Wreturn-mismatch）、省略 int 的
|
||
// main()（-Wimplicit-int）也提成了 error
|
||
language: 'C',
|
||
name: 'C 不带值的 return;、省略 int 的 main() 仍能过（gcc 宽松度）',
|
||
expect: JudgeStatus.ACCEPTED,
|
||
code: `#include <stdio.h>
|
||
int check(int a) {
|
||
if (a < 0) return;
|
||
return a;
|
||
}
|
||
main(void) {
|
||
int a, b;
|
||
scanf("%d %d", &a, &b);
|
||
printf("%d\\n", check(a) + b);
|
||
return 0;
|
||
}`,
|
||
},
|
||
{
|
||
language: 'C',
|
||
name: 'C 答案错误',
|
||
expect: JudgeStatus.WRONG_ANSWER,
|
||
code: `#include <stdio.h>
|
||
int main(void) {
|
||
int a, b;
|
||
scanf("%d %d", &a, &b);
|
||
printf("%d\\n", a + b + 1);
|
||
return 0;
|
||
}`,
|
||
},
|
||
{
|
||
language: 'C',
|
||
name: 'C 编译错误',
|
||
expect: JudgeStatus.COMPILE_ERROR,
|
||
code: `int main(void) { return }`,
|
||
},
|
||
{
|
||
language: 'C',
|
||
name: 'C 运行超时',
|
||
expect: JudgeStatus.CPU_TIME_LIMIT_EXCEEDED,
|
||
cpu: 1000,
|
||
code: `int main(void) {
|
||
volatile long x = 0;
|
||
while (1) x++;
|
||
return 0;
|
||
}`,
|
||
},
|
||
{
|
||
// 地址空间限在内存限制的两倍，所以 malloc 会先成功一阵子再失败，
|
||
// 退出时峰值已经超过内存限制 → 判 MLE 而不是 RE（sandbox.ts 的 verdict）。
|
||
language: 'C',
|
||
name: 'C 内存超限',
|
||
expect: JudgeStatus.MEMORY_LIMIT_EXCEEDED,
|
||
memory: 64,
|
||
code: `#include <stdlib.h>
|
||
#include <string.h>
|
||
int main(void) {
|
||
for (;;) {
|
||
char *p = malloc(8 * 1024 * 1024);
|
||
if (!p) return 1;
|
||
memset(p, 1, 8 * 1024 * 1024);
|
||
}
|
||
}`,
|
||
},
|
||
{
|
||
language: 'C',
|
||
name: 'C 运行时错误',
|
||
expect: JudgeStatus.RUNTIME_ERROR,
|
||
signal: 11,
|
||
code: `int main(void) {
|
||
int *p = 0;
|
||
*p = 1;
|
||
return 0;
|
||
}`,
|
||
},
|
||
{
|
||
// 写满 16MB 吃 SIGXFSZ。前端按信号 25 给「循环停不下来」的说明
|
||
language: 'C',
|
||
name: 'C 死循环打印判运行时错误',
|
||
expect: JudgeStatus.RUNTIME_ERROR,
|
||
signal: 25,
|
||
code: `#include <stdio.h>
|
||
int main(void) {
|
||
for (;;) printf("hello world\\n");
|
||
}`,
|
||
},
|
||
{
|
||
// JudgeServer 把 stdout 和 stderr 写进同一个文件再比，往 stderr 打东西就是答案错误
|
||
language: 'C',
|
||
name: 'C 往 stderr 打的也算输出',
|
||
expect: JudgeStatus.WRONG_ANSWER,
|
||
code: `#include <stdio.h>
|
||
int main(void) {
|
||
int a, b;
|
||
scanf("%d %d", &a, &b);
|
||
fprintf(stderr, "debug\\n");
|
||
printf("%d\\n", a + b);
|
||
return 0;
|
||
}`,
|
||
},
|
||
// ---------------------------------------------------------------- Python
|
||
{
|
||
language: 'Python',
|
||
name: 'Python 正常通过',
|
||
expect: JudgeStatus.ACCEPTED,
|
||
code: `a, b = map(int, input().split())
|
||
print(a + b)`,
|
||
},
|
||
{
|
||
language: 'Python',
|
||
name: 'Python 编译错误',
|
||
expect: JudgeStatus.COMPILE_ERROR,
|
||
code: `def (:`,
|
||
},
|
||
{
|
||
language: 'Python',
|
||
name: 'Python 运行超时',
|
||
expect: JudgeStatus.CPU_TIME_LIMIT_EXCEEDED,
|
||
cpu: 1000,
|
||
code: `while True:
|
||
pass`,
|
||
},
|
||
{
|
||
language: 'Python',
|
||
name: 'Python 运行时错误',
|
||
expect: JudgeStatus.RUNTIME_ERROR,
|
||
code: `print(1 / 0)`,
|
||
},
|
||
{
|
||
// 学生程序开不了进程（procLimit 1），subprocess 抛 OSError
|
||
language: 'Python',
|
||
name: 'Python 开不了子进程',
|
||
expect: JudgeStatus.RUNTIME_ERROR,
|
||
code: `import subprocess
|
||
subprocess.run(['true'])`,
|
||
},
|
||
// ---------------------------------------------------------------- C++
|
||
{
|
||
language: 'C++',
|
||
name: 'C++ 正常通过',
|
||
expect: JudgeStatus.ACCEPTED,
|
||
code: `#include <iostream>
|
||
int main() {
|
||
int a, b;
|
||
std::cin >> a >> b;
|
||
std::cout << a + b << std::endl;
|
||
return 0;
|
||
}`,
|
||
},
|
||
{
|
||
language: 'C++',
|
||
name: 'C++ 编译错误',
|
||
expect: JudgeStatus.COMPILE_ERROR,
|
||
code: `int main() { return }`,
|
||
},
|
||
]
|
||
|
||
const names: Record<number, string> = {
|
||
[JudgeStatus.COMPILE_ERROR]: 'CE',
|
||
[JudgeStatus.WRONG_ANSWER]: 'WA',
|
||
[JudgeStatus.ACCEPTED]: 'AC',
|
||
[JudgeStatus.CPU_TIME_LIMIT_EXCEEDED]: 'TLE(cpu)',
|
||
[JudgeStatus.REAL_TIME_LIMIT_EXCEEDED]: 'TLE(real)',
|
||
[JudgeStatus.MEMORY_LIMIT_EXCEEDED]: 'MLE',
|
||
[JudgeStatus.RUNTIME_ERROR]: 'RE',
|
||
[JudgeStatus.SYSTEM_ERROR]: 'SE',
|
||
}
|
||
const label = (code: number) => `${names[code] ?? '?'}(${code})`
|
||
|
||
async function runCase(item: Case) {
|
||
const body = await judge(item.language, item.code, item.cpu ?? 3000, item.memory ?? 128, sumTestCase)
|
||
// 编译失败走 err 通道，不会有逐测试点的结果
|
||
if (body.err === 'CompileError') return { result: JudgeStatus.COMPILE_ERROR }
|
||
if (body.err) throw new Error(`${body.err}: ${JSON.stringify(body.data)}`)
|
||
|
||
const results = body.data as JudgeCase[]
|
||
// 多个测试点取最坏的那个，和 run.ts 的口径一致
|
||
const failed = results.find((r) => r.result !== JudgeStatus.ACCEPTED)
|
||
return failed ?? results[0]!
|
||
}
|
||
|
||
/** 判题机刚重建时还没起来，先等它 —— 否则整屏都是连接被拒。 */
|
||
async function waitReady() {
|
||
for (let i = 0; i < 60; i++) {
|
||
try {
|
||
return await sandboxVersion()
|
||
} catch {
|
||
// 还没起来，接着等
|
||
}
|
||
await Bun.sleep(500)
|
||
}
|
||
console.error(`连不上判题机 ${url}（等了 30 秒）`)
|
||
process.exit(2)
|
||
}
|
||
|
||
const version = await waitReady()
|
||
|
||
let failures = 0
|
||
console.log(`判题机 ${url}（go-judge ${version}）\n`)
|
||
for (const item of cases) {
|
||
try {
|
||
const got = await runCase(item)
|
||
const pass = got.result === item.expect && (item.signal === undefined || ('signal' in got && got.signal === item.signal))
|
||
if (!pass) failures++
|
||
const time = 'cpu_time' in got ? ` ${got.cpu_time}ms` : ''
|
||
const signal = item.signal !== undefined && 'signal' in got ? ` 信号 ${got.signal}` : ''
|
||
console.log(
|
||
`${pass ? '\x1b[32m✓\x1b[0m' : '\x1b[31m✗\x1b[0m'} ${item.name.padEnd(32)}` +
|
||
` 期望 ${label(item.expect).padEnd(10)} 实得 ${label(got.result)}${signal}${time}`,
|
||
)
|
||
} catch (error) {
|
||
failures++
|
||
console.log(`\x1b[31m✗\x1b[0m ${item.name.padEnd(32)} ${error}`)
|
||
}
|
||
}
|
||
|
||
console.log(failures === 0 ? `\n\x1b[32m全部 ${cases.length} 条通过\x1b[0m` : `\n\x1b[31m${failures} / ${cases.length} 条不对\x1b[0m`)
|
||
process.exit(failures === 0 ? 0 : 1)
|