Files
PolyGateway/tools/telemetry_retention.py
T
iomgaa 503c06327e feat: let the retention script be told which table it may delete from
Until now the target came from whatever search_path resolved to. The
script printed what it found, but that print and the DELETE happen in
the same run with nobody in between, so it only ever helped the person
who ran a dry-run first. Swap the role that runs it and "$user" can
resolve somewhere else entirely.

--table takes the whole qualified name and resolves it directly. The
table half has to be llm_calls: a version that accepts any name turns
one typo into a general purpose row deleter, and any table with a
created_at and a tenant_id would go through the same batched DELETE
without complaint.

The tests that run it now run as a role that owns its own scratch table
and holds nothing on the shared one, so the row-count snapshot could
go. What replaced it is a case that lets the script fall through to the
shared table on purpose and asserts it exits 2 having deleted nothing.
That one has no red-first path, since making it red means running it as
the superuser, which is the thing being prevented; the finding's probe
covers it instead.

Five of the new usage tests passed before the flag existed, because
argparse rejects an unknown --table with exit 1 and the word --table in
stderr, which is exactly what they asserted. They now also assert the
error is not "unrecognized", which is the difference between testing
the validation and testing argparse.
2026-08-26 10:38:21 -04:00

422 lines
18 KiB
Python

#!/usr/bin/env python3
"""遥测表 `llm_calls` 的保留期清理脚本(issue #12;独立运维工具,库本体不 import 它)。
**为什么是脚本而不是库能力**: 库对下游数据库只做 SELECT/INSERT 加可选建表,一切
改结构与删数据的操作交给下游(ARCHITECTURE D15)。库若持有 DELETE 权限,就与生产
部署模板推荐的 `REVOKE UPDATE, DELETE ON llm_calls FROM app` 直接冲突。
**默认 dry-run**: 本脚本会永久删除审计数据,故不带 `--apply` 时只统计不删,并把
行数、`created_at` 窗口、`tenant_id` 分布三样一并打出——运维据此判断"删掉的是不是
我想删的",判断不了就不该按下 `--apply`。
**失败方向与库相反**: 这是运维工具,缺依赖/连不上/表不存在一律明确报错退出,绝不
静默降级成"删了 0 行"——静默的 0 行会被当成"已清理干净"。
用法见 `--help`。
"""
from __future__ import annotations
import argparse
import asyncio
import sqlite3
import sys
from datetime import UTC, datetime, timedelta
from pathlib import Path
from typing import TYPE_CHECKING, Any, NoReturn
if TYPE_CHECKING:
from collections.abc import Sequence
TABLE = "llm_calls"
# 退出码是本脚本对调度器(cron/systemd)的公共契约,改动即破坏下游告警规则
EXIT_OK = 0
EXIT_USAGE = 1
EXIT_BACKEND = 2
EXIT_PARTITIONED = 3
# 库写 SQLite 的 created_at 是 UTC 文本(DEFAULT (datetime('now'))),故截止时刻
# 也必须是同格式文本——该格式定长且高位在前,字符串比较与时间序等价。
# PG 的 created_at 是 TIMESTAMPTZ,直接传 aware datetime,两端口径不可互换。
_SQLITE_TIME_FORMAT = "%Y-%m-%d %H:%M:%S"
_EPILOG = """\
退出码:
0 正常完成(含 dry-run)
1 参数错误
2 连接/权限/目标表不可用(含缺少 asyncpg)
3 目标是 PostgreSQL 分区表 —— 请改用 DETACH/DROP PARTITION,脚本不会 DELETE
权限: 请用**维护角色**(表属主)跑本脚本,不要用应用账号 —— 生产部署模板已对应用
账号 REVOKE UPDATE, DELETE ON llm_calls(遥测表按不可变审计表对待)。
推荐路径(本脚本是存量兜底,不是首选):
PostgreSQL 把 llm_calls 建成按 created_at 的 RANGE 分区表,过期靠
ALTER TABLE ... DETACH PARTITION + DROP TABLE 做 O(1) 清理。
SQLite 按天/按实验轮转库文件(如 runs/<date>.db),到期直接删文件。
时间口径: 截止时刻 = 当前 UTC 时刻 - N 天,删除 created_at < 截止时刻 的行;
--older-than-days 0 即"删除此刻之前的全部行"。
--table: 本脚本只清理表 llm_calls,故 --table 只有 schema 一段可变(写成
--table <schema>.llm_calls)。给了它,目标就由参数精确解析、不再经
search_path 推断。含点或引号的复杂标识符不支持,此时请不给 --table,
退回 search_path 解析那条路径。
示例:
python tools/telemetry_retention.py --backend sqlite --path runs/telemetry.db \\
--older-than-days 90 # dry-run,只看会删什么
python tools/telemetry_retention.py --backend postgres --dsn "$DSN" \\
--older-than-days 90 --apply --batch-size 1000
"""
class _Parser(argparse.ArgumentParser):
"""把 argparse 的参数错误退出码从 2 改成 1。
2 在本脚本的契约里留给"连接/权限失败",两者混用会让调度器分不清"我写错了参数"
与"数据库连不上"——后者要告警重试,前者不该重试。
"""
def error(self, message: str) -> NoReturn:
self.print_usage(sys.stderr)
print(f"{self.prog}: 参数错误: {message}", file=sys.stderr)
raise SystemExit(EXIT_USAGE)
def _build_parser() -> _Parser:
"""构造 CLI 解析器(参数契约见设计 §6.2)。"""
parser = _Parser(
prog="telemetry_retention.py",
description="按 created_at 清理 PolyGateway 遥测表 llm_calls 的过期行(默认 dry-run)。",
epilog=_EPILOG,
formatter_class=argparse.RawDescriptionHelpFormatter,
)
parser.add_argument("--backend", required=True, choices=("sqlite", "postgres"))
parser.add_argument("--path", help="SQLite 库文件路径(--backend sqlite 必填)")
parser.add_argument("--dsn", help="PostgreSQL DSN(--backend postgres 必填)")
parser.add_argument(
"--older-than-days",
type=int,
required=True,
metavar="N",
help="删除 created_at 早于 N 天前的行;N >= 0",
)
parser.add_argument(
"--apply",
action="store_true",
help="真正执行删除;不给则只统计不删(默认)",
)
parser.add_argument(
"--batch-size",
type=int,
metavar="N",
help="仅 postgres: 每批删除的行数,每批一个事务(默认 1000)",
)
parser.add_argument(
"--vacuum",
action="store_true",
help="仅 sqlite: 删除后执行 VACUUM 回收文件空间;须与 --apply 同时给",
)
parser.add_argument(
"--table",
metavar="SCHEMA.NAME",
help=f"仅 postgres: 把目标钉死为 <schema>.{TABLE},绕开 search_path 推断",
)
return parser
def _validate(parser: _Parser, args: argparse.Namespace) -> None:
"""校验参数组合;任何不合法组合以退出码 1 结束(P5: 不给默认值掩盖错误)。
**校验链的顺序就是错误消息的优先级**: 先两端通用,再按 backend 分支——同时给出
多个错误参数时,报出的是链上最先命中的那条。
"""
_validate_shared(parser, args)
if args.backend == "sqlite":
_validate_sqlite(parser, args)
return
_validate_postgres(parser, args)
def _validate_shared(parser: _Parser, args: argparse.Namespace) -> None:
"""两端通用的校验。
`--vacuum` 与 `--apply` 的联动归在这里(而不是 SQLite 分支): 它是"别在只想看看的
时候重写整个库"这条安全约束,先于"这个参数属于哪个 backend"成立。
"""
if args.older_than_days < 0:
parser.error("--older-than-days 必须 >= 0")
if args.vacuum and not args.apply:
parser.error("--vacuum 会重写整个库文件,必须与 --apply 同时给")
def _validate_sqlite(parser: _Parser, args: argparse.Namespace) -> None:
"""SQLite 分支: 必须有 --path,且拒绝一切 postgres 专属参数(不静默忽略)。"""
if args.path is None:
parser.error("--backend sqlite 需要 --path")
if args.dsn is not None:
parser.error("--backend sqlite 不接受 --dsn")
if args.batch_size is not None:
parser.error("--batch-size 仅用于 --backend postgres")
if args.table is not None:
parser.error("--table 仅用于 --backend postgres:SQLite 的库文件即目标,无 schema 可消歧")
def _validate_postgres(parser: _Parser, args: argparse.Namespace) -> None:
"""Postgres 分支: 必须有 --dsn,拒绝 sqlite 专属参数,并在此落 --batch-size 缺省值。
`--table` 在此解析成 `args.table_schema`(未给则 None): 校验与解析放在同一处,
后面的执行路径就只面对一个已经合法的 schema 名,不必再重复判断。
"""
if args.dsn is None:
parser.error("--backend postgres 需要 --dsn")
if args.path is not None:
parser.error("--backend postgres 不接受 --path")
if args.vacuum:
parser.error("--vacuum 仅用于 --backend sqlite")
if args.batch_size is None:
args.batch_size = 1000
elif args.batch_size < 1:
parser.error("--batch-size 必须 >= 1")
args.table_schema = None if args.table is None else _parse_table(parser, args.table)
def _parse_table(parser: _Parser, value: str) -> str:
"""校验 `--table SCHEMA.NAME` 并返回 schema 段;任何不合法形态退出 1。
**表名段为什么不可变**: 只校验"两段、非空"的话,一次手误 `--table audit.events`
就会让本脚本对一张恰好也有 `created_at` / `tenant_id` 的业务表跑同一套分批 DELETE。
脚本的名字、退出码 3 的分区提示、README 的定位全都围绕遥测表写,它从未声称自己
是通用清理器;把这条校验去掉等于在一个拿 DELETE 权限跑的脚本上开静默的口子。
"""
segments = value.split(".")
if len(segments) != 2:
parser.error(f"--table 必须是 <schema>.{TABLE} 这样的两段限定名,当前: {value!r}")
schema, name = segments
# 段内不可能再含 "." (上面按 "." 切成恰好两段),故此处只需查引号
if not schema or not name:
parser.error(f"--table 的 schema 段与表名段都不得为空,当前: {value!r}")
if '"' in schema or '"' in name:
parser.error(
f"--table 不支持含引号的复杂标识符,当前: {value!r};"
"这种情形请不给 --table,退回 search_path 解析那条路径。"
)
if name != TABLE:
parser.error(
f"--table 的表名段必须逐字等于 {TABLE}:本脚本只清理遥测表 {TABLE},"
f"不是通用清理器,当前: {value!r}"
)
return schema
def _print_stats(total: int, low: object, high: object, tenants: Sequence[tuple[str, int]]) -> None:
"""打印将删除行数、created_at 窗口与按 tenant_id 的分布。
tenant_id 用 repr 打: 空串是"未归属"的哨兵(不是 NULL),裸打会与缺失混淆。
"""
print(f"将删除行数: {total}")
print(f"created_at 范围: {low} ~ {high}" if total else "created_at 范围: (无匹配行)")
print("按 tenant_id 分布:")
if not tenants:
print(" (无匹配行)")
for tenant, count in tenants:
print(f" {tenant!r}: {count}")
# --------------------------------------------------------------------------- SQLite
def _run_sqlite(path: str, cutoff: str, apply_: bool, vacuum: bool) -> int:
"""SQLite 分支: 单条 DELETE(本地文件无长事务与锁膨胀问题),VACUUM 须显式要。"""
file = Path(path)
if not file.is_file():
print(f"SQLite 库文件不存在: {file}", file=sys.stderr)
return EXIT_BACKEND
try:
conn = sqlite3.connect(f"file:{file}?mode=rw", uri=True)
except sqlite3.Error as exc:
print(f"打开 SQLite 库失败: {file}: {exc}", file=sys.stderr)
return EXIT_BACKEND
try:
exists = conn.execute(
"SELECT 1 FROM sqlite_master WHERE type = 'table' AND name = ?", (TABLE,)
).fetchone()
if exists is None:
print(f"目标库里没有表 {TABLE}: {file}", file=sys.stderr)
return EXIT_BACKEND
print(f"目标表: {file}::{TABLE}")
total, low, high = conn.execute(
f"SELECT COUNT(*), MIN(created_at), MAX(created_at) FROM {TABLE} WHERE created_at < ?",
(cutoff,),
).fetchone()
tenants = conn.execute(
f"SELECT tenant_id, COUNT(*) FROM {TABLE} WHERE created_at < ? "
"GROUP BY tenant_id ORDER BY COUNT(*) DESC, tenant_id",
(cutoff,),
).fetchall()
_print_stats(total, low, high, tenants)
if not apply_:
print("模式 dry-run: 未删除任何行。确认无误后加 --apply 才会真正删除。")
return EXIT_OK
cursor = conn.execute(f"DELETE FROM {TABLE} WHERE created_at < ?", (cutoff,))
conn.commit()
print(f"已删除 {cursor.rowcount} 行。")
if vacuum:
print("执行 VACUUM(重写整个库文件,需要与库等量的空闲磁盘)…")
conn.execute("VACUUM")
conn.commit()
print("VACUUM 完成。")
except sqlite3.Error as exc:
print(f"SQLite 操作失败: {exc}", file=sys.stderr)
return EXIT_BACKEND
finally:
conn.close()
return EXIT_OK
# --------------------------------------------------------------------------- PostgreSQL
def _quote(identifier: str) -> str:
"""把 catalog 取回的 schema/表名包成合法标识符(库名含大写或特殊字符时必需)。"""
escaped = identifier.replace('"', '""')
return f'"{escaped}"'
async def _run_postgres(
dsn: str, cutoff: datetime, apply_: bool, batch_size: int, table_schema: str | None
) -> int:
"""PostgreSQL 分支: 分区表让路,普通表分批 DELETE(每批一个事务)。"""
try:
import asyncpg
except ImportError as exc:
print(
f"--backend postgres 需要 asyncpg,当前不可用({exc});"
"请 pip install 'polygateway[postgres]' 或 pip install asyncpg 后重试。",
file=sys.stderr,
)
return EXIT_BACKEND
try:
conn = await asyncpg.connect(dsn, timeout=10)
except (OSError, asyncpg.PostgresError) as exc:
print(f"连接 PostgreSQL 失败: {exc}", file=sys.stderr)
return EXIT_BACKEND
try:
return await _purge_postgres(conn, cutoff, apply_, batch_size, table_schema)
except asyncpg.PostgresError as exc:
print(f"PostgreSQL 操作失败: {exc}", file=sys.stderr)
return EXIT_BACKEND
finally:
await conn.close()
async def _purge_postgres(
conn: Any, cutoff: datetime, apply_: bool, batch_size: int, table_schema: str | None
) -> int:
"""已连上后的清理主体(conn 是 asyncpg.Connection,不 import 类型以免脚本硬依赖)。"""
# 给了 --table 就用引号限定名精确解析(绕开 search_path),否则维持裸表名解析——
# 后者走连接自己的 search_path,故无论哪条路都必须把解析结果打出来:"我删的到底是
# 哪张表"是这个脚本唯一不能猜的事(共享库里另有同名表的场景常见)。
lookup = TABLE if table_schema is None else f"{_quote(table_schema)}.{_quote(TABLE)}"
target = await conn.fetchrow(
"SELECT n.nspname AS schema, c.relname AS name, "
"EXISTS (SELECT 1 FROM pg_partitioned_table p WHERE p.partrelid = c.oid) AS partitioned "
"FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace "
"WHERE c.oid = to_regclass($1)",
lookup,
)
if target is None:
# 两条路的诊断方向不同,消息分开写: 显式指定找不到多半是名字/大小写写错了,
# search_path 找不到则是连接配置的事。
if table_schema is None:
print(f"目标库的 search_path 下找不到表 {TABLE}", file=sys.stderr)
else:
print(
f"显式指定的表 {table_schema}.{TABLE} 不存在或当前角色不可见。"
"注意: PG 中未加引号建的标识符在 catalog 里是小写。",
file=sys.stderr,
)
return EXIT_BACKEND
schema, name = target["schema"], target["name"]
qualified = f"{_quote(schema)}.{_quote(name)}"
print(f"目标表: {schema}.{name}")
if apply_ and table_schema is None:
# 只在 --apply 时提示: dry-run 不可逆性为零,且它本就以"看清楚再决定"为用途。
print(
"注意: 目标表由连接的 search_path 推断得到。要把目标钉死,请加 --table <schema>.<表名>。"
)
if target["partitioned"]:
print(
f"{schema}.{name} 是分区表: 本脚本拒绝对分区表执行 DELETE。\n"
"请改用 DETACH/DROP PARTITION —— ALTER TABLE ... DETACH PARTITION <子表> 后 "
"DROP TABLE <子表>(或交给 pg_partman 的 retention)。\n"
"那是 O(1) 的,而 DELETE 会全表扫描并留下等量膨胀。"
)
return EXIT_PARTITIONED
stats = await conn.fetchrow(
f"SELECT COUNT(*) AS total, MIN(created_at) AS low, MAX(created_at) AS high "
f"FROM {qualified} WHERE created_at < $1",
cutoff,
)
tenants = await conn.fetch(
f"SELECT tenant_id, COUNT(*) AS total FROM {qualified} WHERE created_at < $1 "
"GROUP BY tenant_id ORDER BY COUNT(*) DESC, tenant_id",
cutoff,
)
_print_stats(
stats["total"], stats["low"], stats["high"], [(r["tenant_id"], r["total"]) for r in tenants]
)
if not apply_:
print("模式 dry-run: 未删除任何行。确认无误后加 --apply 才会真正删除。")
return EXIT_OK
# 分批: 一条大 DELETE 会撑出长事务(阻塞 autovacuum、堆积 WAL、锁膨胀),
# 中断后还得整批回滚重来。每批独立提交,中断只影响未删批次。
deleted = 0
batches = 0
statement = (
f"DELETE FROM {qualified} WHERE ctid IN "
f"(SELECT ctid FROM {qualified} WHERE created_at < $1 ORDER BY created_at LIMIT $2)"
)
while True:
async with conn.transaction():
status = await conn.execute(statement, cutoff, batch_size)
count = int(status.rsplit(" ", 1)[-1])
if count == 0:
break
deleted += count
batches += 1
print(f" 批次 {batches}: 删除 {count} 行(已提交)")
print(f"已删除 {deleted} 行,共 {batches} 批。")
return EXIT_OK
# --------------------------------------------------------------------------- 入口
def main(argv: Sequence[str] | None = None) -> int:
"""解析参数并分派到对应后端;返回值即进程退出码。"""
parser = _build_parser()
args = parser.parse_args(argv)
_validate(parser, args)
cutoff = datetime.now(UTC) - timedelta(days=args.older_than_days)
print(f"后端: {args.backend}")
print(
f"截止时间(UTC): {cutoff.strftime(_SQLITE_TIME_FORMAT)}"
f"(--older-than-days {args.older_than_days};删除 created_at 早于该时刻的行)"
)
print(f"模式: {'apply(将真正删除)' if args.apply else 'dry-run(只统计,不删除)'}")
if args.backend == "sqlite":
return _run_sqlite(args.path, cutoff.strftime(_SQLITE_TIME_FORMAT), args.apply, args.vacuum)
return asyncio.run(
_run_postgres(args.dsn, cutoff, args.apply, args.batch_size, args.table_schema)
)
if __name__ == "__main__":
sys.exit(main())