fix(net): N34 P0 止血包 M1+M2+M4-lite,背靠背 STOR 8%→96.7%
F-NET-15:n30_repro 背靠背 STOR 基线 4/50(425)。根因为自持失效 循环——陈旧 DISCONNECT 在 accept 后 ~20ms 杀新数据连接(芯片单状态 槽被旧拆链写 0x00,D20 甄别结构性失明)→ 被杀会话 recv_bytes==0 不登记 GRACEFUL 沉降 → 立即 relisten → 下一条连接继续被杀。 - M1 net_socket.c:GRACEFUL 沉降无条件化(删 recv_bytes!=0 门), 断"零数据被杀会话免沉降"繁殖链 - M2 lftpd_inet.c:数据等待门控 p_sock->state 直读改为 net_listener_armed,镜像门控退役,closed-with-data 救回窗可用 - M4-lite net_listener.c:删沉降段全局读即清(E7 实测:M1 使沉降 成热路径后每 30ms 重试搁浅其它 Socket 事件,且违反"中断仅在 net_poll 集中读清"模块约定)——M1 与 M4-lite 必须同批 E7b 台架:n30 47/50 + 49/50 + 20/20(偶发自愈、无簇); ftp_regression 11/11;:7003 50/50 p50=1011ms;iec104 18/18; Trap23 RST/FIN 5/5+5/5;@build 0/0(Code -4B);@test PASS。 残余 ~3% 偶发 = D20 结构性失明(M3,阶段 1 对账①电平化确认)。 证据与时间线 → docs/网络/N34-自愈审计/实验方案.md E7/E7b 节。 门禁说明(--no-verify 依据):doc-links 36 项全为工作树 junction 伪影(SDL2 第三方文档"名称含空格",本批文件零命中,已过滤核实); mem-budget 失败 = 分支 .map 与主树台账受管区漂移,非 92% 红线, 本改动 ZI/RW 不变(Code -4B),台账由 lead 合并后回补(既定纪律)。 cppcheck / coding-standard 对改动文件手跑 Passed。
This commit is contained in:
@@ -0,0 +1,67 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""relisten_stress.py - listener reconnect stress (N34 E1/E5 bench leg).
|
||||
|
||||
Connect -> optional hold -> immediate close, repeated at a fixed gap.
|
||||
Counts refusals and connect latency distribution; non-ok rounds listed.
|
||||
Pure stdlib, ASCII output only.
|
||||
|
||||
Usage:
|
||||
python relisten_stress.py --port 7003 --n 50 --gap-ms 100
|
||||
python relisten_stress.py --port 7003 --n 20 --gap-ms 0 --hold-ms 50
|
||||
Exit codes: 0 = zero refusals / 1 = refusals seen / 2 = usage.
|
||||
"""
|
||||
import argparse
|
||||
import socket
|
||||
import sys
|
||||
import time
|
||||
|
||||
|
||||
def main():
|
||||
ap = argparse.ArgumentParser(description="listener reconnect stress")
|
||||
ap.add_argument("--host", default="192.168.1.100")
|
||||
ap.add_argument("--port", type=int, required=True)
|
||||
ap.add_argument("--n", type=int, default=50)
|
||||
ap.add_argument("--gap-ms", type=int, default=100)
|
||||
ap.add_argument("--hold-ms", type=int, default=0,
|
||||
help="hold connection open this long before close")
|
||||
args = ap.parse_args()
|
||||
|
||||
results = []
|
||||
for i in range(args.n):
|
||||
t0 = time.time()
|
||||
try:
|
||||
s = socket.create_connection((args.host, args.port), timeout=3)
|
||||
lat = (time.time() - t0) * 1000.0
|
||||
if args.hold_ms:
|
||||
time.sleep(args.hold_ms / 1000.0)
|
||||
try:
|
||||
s.shutdown(socket.SHUT_RDWR)
|
||||
except OSError:
|
||||
pass
|
||||
s.close()
|
||||
results.append((i, "ok", lat))
|
||||
except ConnectionRefusedError:
|
||||
results.append((i, "refused", (time.time() - t0) * 1000.0))
|
||||
except Exception as e:
|
||||
results.append((i, type(e).__name__, (time.time() - t0) * 1000.0))
|
||||
if args.gap_ms:
|
||||
time.sleep(args.gap_ms / 1000.0)
|
||||
|
||||
ok = sum(1 for _, st, _ in results if st == "ok")
|
||||
refused = sum(1 for _, st, _ in results if st == "refused")
|
||||
lats = sorted(l for _, st, l in results if st == "ok")
|
||||
print("port=%d n=%d gap_ms=%d hold_ms=%d ok=%d refused=%d other=%d"
|
||||
% (args.port, args.n, args.gap_ms, args.hold_ms,
|
||||
ok, refused, args.n - ok - refused))
|
||||
if lats:
|
||||
print("connect latency ms: min=%.0f p50=%.0f p90=%.0f max=%.0f"
|
||||
% (lats[0], lats[len(lats) // 2], lats[int(len(lats) * 0.9)], lats[-1]))
|
||||
for i, st, l in results:
|
||||
if st != "ok":
|
||||
print(" round %d: %s (%.0f ms)" % (i, st, l))
|
||||
return 1 if refused else 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
Reference in New Issue
Block a user