code-to10 v6 A5: admin CLI wiring for stale-worker reap
- New production caller cloud/worker_sweep.py (python -m cloud.worker_sweep): AuthStore.authenticate + CODEX_GLOBAL_ADMINS global-admin check (same fail-closed semantics as handler_admin._is_global_admin) before any reap call; denied authenticated non-admins get an admin_worker_sweep_denied audit row; authorized runs reuse reap_stale_workers (classify, re-verify, pre-kill audit fail-closed, per-pid SIGKILL only, post-kill verification) plus an admin_worker_sweep summary audit; --dry-run lists classifications only. - No new HTTP route, no container enumeration, no name/prefix matching, no workers-row deletion; workers.py docstring only notes the new caller. - Tests: cloud/tests/test_worker_sweep_admin.py, 6 cases (bad key, non-admin, unconfigured admin list fail-closed, authorized full chain, dry-run, CLI main authorized/refused). (cherry picked from commit c7d217549c5ccedf61dcc924b8998fffeddc76c6)
This commit is contained in:
1 parent
19b9767478
commit
ee8d1e1e28
3 files changed
+378
No files matched your search
@@ -0,0 +1,174 @@
|
||||
"""管理员 CLI:失联 worker 清扫(workers kill 接线,A5)。
|
||||
|
||||
用法:python3 -m cloud.worker_sweep --db <控制面库路径> [--dry-run]
|
||||
[--stale-seconds N] [--host <本机主机名>]
|
||||
API key 走环境变量 CLOUD_WORKER_SWEEP_API_KEY,或 --api-key
|
||||
显式给(命令行会进进程表,生产优先用环境变量)。
|
||||
|
||||
这是 reap_stale_workers 的第一个生产调用方(此前除 workers.py
|
||||
本体与测试外全仓库零生产调用方):
|
||||
|
||||
- 鉴权:先经 AuthStore.authenticate 验 key,再认
|
||||
CODEX_GLOBAL_ADMINS(与 handler_admin._is_global_admin 同款
|
||||
口径:逗号分隔的用户 id 清单,未配置或为空时一律 fail-closed,
|
||||
绝不回落到项目角色推导)。任一步失败都抛 PermissionError,
|
||||
且在调 reap 之前就拒掉——未授权调用绝不走到判定/杀。
|
||||
被拒的已认证非管理员用户记一条 admin_worker_sweep_denied
|
||||
审计(审计写失败不挡拒绝本身);key 本身验不过时没有可
|
||||
归属的用户,不记这条。
|
||||
- 杀前审计 + 执行后复核:授权后直接调 reap_stale_workers,
|
||||
复用 classify_stale_workers 的判定,不另造判定函数;每行
|
||||
kill 档在 reap 内先再验 pid 已死、杀前写审计(审计失败则
|
||||
不杀,fail-closed)、只给该 pid 本人发信号、杀后用同一
|
||||
checker 复核并写杀后审计;本 CLI 另写一条
|
||||
admin_worker_sweep 汇总审计(killed / listed / 失败计数,
|
||||
写失败只记 audit_summary=False,不改已执行结果)。
|
||||
- 不新增 HTTP 路由(v1.1 契约确认 B8 未定前不扩 API 面);
|
||||
不枚举容器、不按名/前缀匹配、不碰基础设施容器、不删
|
||||
workers 注册行:杀的是判定为 kill 的行对应的 pid 本人,
|
||||
注册行的去留是另一条决策,本 CLI 不擅自删。
|
||||
- --dry-run 只调 classify_stale_workers 列判定,不调 reap、
|
||||
不杀、不写杀审计,供运维先看再动手。
|
||||
|
||||
本模块只 import cloud.auth 与 cloud.workers,不 import
|
||||
cloud.server / handler_*,避免循环 import;PG 库路径同样经
|
||||
cloud.db 的 connect 适配(与 workers 本体同款)。
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
|
||||
from cloud.auth import AuthStore
|
||||
from cloud.workers import classify_stale_workers
|
||||
from cloud.workers import reap_stale_workers
|
||||
|
||||
|
||||
def global_admin_ids(admin_ids=None):
|
||||
"""全局管理员清单:显式传入优先,否则读 CODEX_GLOBAL_ADMINS。
|
||||
|
||||
未配置或为空时返回空集——调用方一律 fail-closed。
|
||||
"""
|
||||
if admin_ids is not None:
|
||||
return {str(item).strip() for item in admin_ids if str(item).strip()}
|
||||
raw = os.environ.get("CODEX_GLOBAL_ADMINS") or ""
|
||||
return {part.strip() for part in raw.split(",") if part.strip()}
|
||||
|
||||
|
||||
def sweep_stale_workers_admin(db_path, api_key, stale_seconds=None,
|
||||
local_host=None, pid_is_dead_fn=None,
|
||||
kill_fn=None, audit_fn=None, dry_run=False,
|
||||
admin_ids=None, now=None):
|
||||
"""管理员清扫入口:鉴权通过后才调 reap(或 dry-run 只列判定)。
|
||||
|
||||
返回 dict:user_id、dry_run、results(每行判定 + 执行字段,
|
||||
与 reap/classify 的返回同款)、killed / listed / failed
|
||||
三个 worker_id 清单、audit_summary(汇总审计是否写成功,
|
||||
dry-run 时为 None)。未授权时抛 PermissionError 且绝不调
|
||||
reap、不调 kill_fn。kill_fn / audit_fn / pid_is_dead_fn 仅
|
||||
供测试注入;生产调用一律走默认(真 SIGKILL + 统一审计口)。
|
||||
"""
|
||||
store = AuthStore(db_path)
|
||||
try:
|
||||
user_id = store.authenticate(api_key) if api_key else None
|
||||
if user_id is None:
|
||||
raise PermissionError(
|
||||
"worker sweep requires a valid admin API key")
|
||||
if user_id not in global_admin_ids(admin_ids):
|
||||
try:
|
||||
store.audit(user_id, "", "admin_worker_sweep_denied",
|
||||
"worker sweep forbidden: not a global admin")
|
||||
except Exception:
|
||||
pass
|
||||
raise PermissionError(
|
||||
"worker sweep forbidden: not a global admin")
|
||||
if dry_run:
|
||||
results = classify_stale_workers(
|
||||
db_path, stale_seconds=stale_seconds,
|
||||
local_host=local_host, pid_is_dead_fn=pid_is_dead_fn,
|
||||
now=now)
|
||||
return {
|
||||
"user_id": user_id,
|
||||
"dry_run": True,
|
||||
"results": results,
|
||||
"killed": [],
|
||||
"listed": [row["worker_id"] for row in results],
|
||||
"failed": [],
|
||||
"audit_summary": None,
|
||||
}
|
||||
results = reap_stale_workers(
|
||||
db_path, stale_seconds=stale_seconds, local_host=local_host,
|
||||
pid_is_dead_fn=pid_is_dead_fn, kill_fn=kill_fn,
|
||||
audit_fn=audit_fn, now=now)
|
||||
killed = [row["worker_id"] for row in results
|
||||
if row.get("outcome") == "killed"]
|
||||
listed = [row["worker_id"] for row in results
|
||||
if row.get("outcome") == "listed"]
|
||||
failed = [row["worker_id"] for row in results
|
||||
if row.get("outcome") in (
|
||||
"kill_failed_pid_alive", "audit_failed")]
|
||||
detail = ("killed=%d listed=%d failed=%d killed_ids=%s"
|
||||
% (len(killed), len(listed), len(failed),
|
||||
",".join(killed)))
|
||||
try:
|
||||
store.audit(user_id, "", "admin_worker_sweep", detail)
|
||||
audit_summary = True
|
||||
except Exception:
|
||||
audit_summary = False
|
||||
return {
|
||||
"user_id": user_id,
|
||||
"dry_run": False,
|
||||
"results": results,
|
||||
"killed": killed,
|
||||
"listed": listed,
|
||||
"failed": failed,
|
||||
"audit_summary": audit_summary,
|
||||
}
|
||||
finally:
|
||||
try:
|
||||
store.conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def main(argv=None):
|
||||
"""CLI 入口:鉴权失败 exit 1,参数缺失 exit 2,成功 exit 0。
|
||||
|
||||
成功时 stdout 只打 JSON 汇总(worker_id 与 outcome,不含
|
||||
任何密钥);失败原因打 stderr,不回 JSON。
|
||||
"""
|
||||
parser = argparse.ArgumentParser(
|
||||
description="管理员清扫失联 worker(只杀 pid 已死验证过的本机行)")
|
||||
parser.add_argument("--db", required=True, help="控制面数据库路径")
|
||||
parser.add_argument("--api-key", default=None,
|
||||
help="管理员 API key;不给时读环境变量 "
|
||||
"CLOUD_WORKER_SWEEP_API_KEY")
|
||||
parser.add_argument("--stale-seconds", type=float, default=None,
|
||||
help="失联阈值秒数;不给时复用 alive 阈值语义")
|
||||
parser.add_argument("--host", default=None,
|
||||
help="本机主机名;不给时取 socket.gethostname()")
|
||||
parser.add_argument("--dry-run", action="store_true",
|
||||
help="只列判定,不杀")
|
||||
args = parser.parse_args(argv)
|
||||
api_key = args.api_key or os.environ.get("CLOUD_WORKER_SWEEP_API_KEY")
|
||||
try:
|
||||
summary = sweep_stale_workers_admin(
|
||||
args.db, api_key, stale_seconds=args.stale_seconds,
|
||||
local_host=args.host, dry_run=args.dry_run)
|
||||
except PermissionError as exc:
|
||||
print("worker sweep refused: %s" % exc, file=sys.stderr)
|
||||
raise SystemExit(1)
|
||||
print(json.dumps({
|
||||
"user_id": summary["user_id"],
|
||||
"dry_run": summary["dry_run"],
|
||||
"killed": summary["killed"],
|
||||
"listed": summary["listed"],
|
||||
"failed": summary["failed"],
|
||||
"audit_summary": summary["audit_summary"],
|
||||
}, ensure_ascii=False))
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in new issue
Block a user