refactor(判题机): 换成 go-judge，空闲内存从几百 MB 降到 16 MB
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>
This commit is contained in:
xuyueandClaude Opus 5.5 committed
1 parent
8427475337
commit
37e971b6b4
30 files changed
+881
-592
No files matched your search
+55
-49
@@ -4,27 +4,24 @@
|
||||
* bun docker/judge/smoke.ts # 打 .env 里的 JUDGE_SERVER_URL
|
||||
* JUDGE_SERVER_URL=http://localhost:8082 bun docker/judge/smoke.ts
|
||||
*
|
||||
* 直接打判题机的 /judge，不经过 api / worker / 队列，所以不需要起后端，也不需要
|
||||
* 库里有题 —— 测试点用 `test_case` 内联传进去，判题机会当场写进临时目录。
|
||||
* 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。
|
||||
*
|
||||
* 它核的是三件事：
|
||||
* 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 { createHash } from 'node:crypto'
|
||||
|
||||
import { JudgeStatus } from '@oj2/contract'
|
||||
|
||||
import { languageConfigs } from '../../apps/api/src/judge/languages'
|
||||
import { judge, sandboxVersion, type JudgeCase } from '../../apps/api/src/judge/sandbox'
|
||||
|
||||
const url = process.env.JUDGE_SERVER_URL ?? 'http://localhost:8081'
|
||||
const rawToken = process.env.JUDGE_SERVER_TOKEN
|
||||
if (!rawToken) {
|
||||
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)
|
||||
}
|
||||
const token = createHash('sha256').update(rawToken).digest('hex')
|
||||
|
||||
interface Case {
|
||||
language: string
|
||||
@@ -34,6 +31,8 @@ interface Case {
|
||||
/** 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' }]
|
||||
@@ -114,12 +113,12 @@ int main(void) {
|
||||
}`,
|
||||
},
|
||||
{
|
||||
// RLIMIT_AS 是 max_memory 的两倍，所以 malloc 会先成功一阵子再失败，
|
||||
// 退出时 ru_maxrss 已经超过 max_memory → judger 判 MLE 而不是 RE。
|
||||
// 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 * 1024 * 1024,
|
||||
memory: 64,
|
||||
code: `#include <stdlib.h>
|
||||
#include <string.h>
|
||||
int main(void) {
|
||||
@@ -134,10 +133,36 @@ int main(void) {
|
||||
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
|
||||
@@ -168,6 +193,14 @@ print(a + b)`,
|
||||
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++',
|
||||
@@ -202,51 +235,22 @@ const names: Record<number, string> = {
|
||||
const label = (code: number) => `${names[code] ?? '?'}(${code})`
|
||||
|
||||
async function runCase(item: Case) {
|
||||
const response = await fetch(new URL('/judge', url), {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'content-type': 'application/json',
|
||||
'X-Judge-Server-Token': token,
|
||||
},
|
||||
body: JSON.stringify({
|
||||
language_config: languageConfigs[item.language],
|
||||
src: item.code,
|
||||
max_cpu_time: item.cpu ?? 3000,
|
||||
max_memory: item.memory ?? 128 * 1024 * 1024,
|
||||
test_case: sumTestCase,
|
||||
output: false,
|
||||
io_mode: {
|
||||
io_mode: 'Standard IO',
|
||||
input: 'input.txt',
|
||||
output: 'output.txt',
|
||||
},
|
||||
}),
|
||||
})
|
||||
if (!response.ok) throw new Error(`HTTP ${response.status}`)
|
||||
|
||||
const body = (await response.json()) as {
|
||||
err: string | null
|
||||
data: unknown
|
||||
}
|
||||
const body = await judge(item.language, item.code, item.cpu ?? 3000, item.memory ?? 128, sumTestCase)
|
||||
// 编译失败走 err 通道，不会有逐测试点的结果
|
||||
if (body.err === 'CompileError') return { result: JudgeStatus.COMPILE_ERROR }
|
||||
if (body.err) throw new Error(`${body.err}: ${JSON.stringify(body.data)}`)
|
||||
|
||||
const results = body.data as { result: number; cpu_time: number }[]
|
||||
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 gunicorn 还没起来，先等它 —— 否则整屏都是连接被关。 */
|
||||
/** 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 {
|
||||
const response = await fetch(new URL('/ping', url), {
|
||||
method: 'POST',
|
||||
headers: { 'X-Judge-Server-Token': token },
|
||||
})
|
||||
if (response.ok) return
|
||||
return await sandboxVersion()
|
||||
} catch {
|
||||
// 还没起来，接着等
|
||||
}
|
||||
@@ -256,18 +260,20 @@ async function waitReady() {
|
||||
process.exit(2)
|
||||
}
|
||||
|
||||
await waitReady()
|
||||
const version = await waitReady()
|
||||
|
||||
let failures = 0
|
||||
console.log(`判题机 ${url}\n`)
|
||||
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
|
||||
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 ${label(got.result)}${time}`,
|
||||
`${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++
|
||||
|
||||
Reference in new issue
Block a user