Nagle 算法减少 TCP 小报文：当前面数据尚未确认时，它会暂缓额外的小块数据，除非已经积累到足以构成完整段。延迟确认则是接收端的另一种行为，可以短暂推迟 ACK。当应用把一个请求拆成多个很小的写入，而对端必须取得后续字节才能生成响应时，两者的相互作用就会影响延迟。需要明确是哪一部分数据已经发出、哪一部分仍在等待。
坏掉的样子 单独一个小请求，不会自动被 Nagle 延迟。如果没有更早的未确认数据，第一个小段可以直接发送。问题场景是第一部分已在途中，第二个短小部分排在后面等待。如果接收端延迟确认，同时应用又在等完整请求，进展可能暂停，直到确认计时器到期。不能把所有“小请求慢”都归到这个机制，也不能省略前面存在未确认数据这一条件。
这属于有边界的延迟，不是协议无限死锁。ACK 可以释放排队数据，积累足够多数据也可能改变发送决策。观察到的等待既不统一等于额外一个 RTT，也不固定为四十毫秒。接收策略、已有确认状态、请求分帧和网络条件，共同决定真正的报文顺序与时间。把一次实验数值当成所有系统的常数，会误导后续故障判断。
TCP_NODELAY 关闭指定套接字上的 Nagle，却不会关闭所有缓冲、拥塞控制、接收窗口流控或调度延迟。Linux TCP_QUICKACK 请求改变确认模式，但这种模式不是永久设置。把任意一个选项当作万能延迟开关，可能掩盖应用缓冲或其他传输限制；这些问题本来就不在该选项职责内，需要通过对应层次的证据定位。
快速验证 将脚本保存为 check-nagle.py，准备 Docker 后运行 python3 check-nagle.py。一次性环境使用 Python 3.11.16、iproute2 6.1.0 和 tcpdump 4.99.3，在 Linux 6.12.76 上验证。NET_ADMIN 与 SYS_ADMIN 支持嵌套命名空间。客户端和目标通过新建 veth 通信，所有参数都留在实验范围内，不修改宿主正在使用的网络配置：
from pathlib import Path from tempfile import TemporaryDirectory import json,subprocess,uuid recipe='FROM python@sha256:528257d48c1da0dcecc2e725d1ae34498d60c965f1241e39cd6a85a8859bdf84\nRUN apt-get update && apt-get install -y --no-install-recommends iproute2=6.1.0-3 iputils-ping=3:20221126-1+deb12u1 nftables=1.0.6-2+deb12u2 tcpdump=4.99.3-1 traceroute=1:2.1.2-1 procps=2:4.0.2-3 && rm -rf /var/lib/apt/lists/*\nCMD ["python3"]\n' program=r""" from contextlib import ExitStack,contextmanager from pathlib import Path from tempfile import TemporaryDirectory import json,os,select,signal,subprocess,time def run(*args,check=True,input=None,timeout=8): result=subprocess.run(args,input=input,capture_output=True,text=True,timeout=timeout) if check:assert result.returncode==0,(args,result.returncode,result.stdout,result.stderr) return result def ns(name,*args,**kwargs):return run('ip','netns','exec',name,*args,**kwargs) def ip(name,*args,**kwargs):return ns(name,'ip',*args,**kwargs) def stop(process): if process.poll() is None: process.terminate() try:process.wait(timeout=2) except subprocess.TimeoutExpired:process.kill();process.wait(timeout=2) def line(process,timeout=3): assert select.select([process.stdout],[],[],timeout)[0],'child response deadline exceeded' value=process.stdout.readline();assert value,('child exited without a response',process.stderr.read()) return value def spawn(stack,command): process=subprocess.Popen(command,stdin=subprocess.PIPE,stdout=subprocess.PIPE,stderr=subprocess.PIPE,text=True) stack.callback(stop,process);return process @contextmanager def lab(names): with TemporaryDirectory(prefix='net-path-') as directory,ExitStack() as stack: root=Path(directory);proc=root/'proc';proc.mkdir();run('mount','-t','proc','proc',str(proc)) stack.callback(run,'umount',str(proc)) for name in names: run('ip','netns','add',name);stack.callback(run,'ip','netns','delete',name,check=False) ip(name,'link','set','lo','up') def setting(name,key,value): assert name in names path=proc/'sys'/key.replace('.','/') return ns(name,'python3','-c',f'from pathlib import Path; p=Path({str(path)!r}); p.write_text({str(value)!r}); print(p.read_text().strip())').stdout.strip() yield root,stack,setting def wire(left,left_if,right,right_if,left_addresses,right_addresses): run('ip','link','add',left_if,'type','veth','peer','name',right_if) for name,interface,addresses in [(left,left_if,left_addresses),(right,right_if,right_addresses)]: run('ip','link','set',interface,'netns',name) for address in addresses:ip(name,'address','add',address,'dev',interface,*(['nodad'] if ':' in address else [])) ip(name,'link','set',interface,'up') def nft(name,script):return ns(name,'nft','-f','-',input=script) def counters(name): data=json.loads(ns(name,'nft','-j','list','ruleset').stdout);found={} for entry in data['nftables']: rule=entry.get('rule',{}) if 'comment' in rule: for expression in rule['expr']: if 'counter' in expression:found[rule['comment']]=expression['counter']['packets'] return found def capture(stack,root,name,interface,expression,label): path=root/(label+'.pcap') process=subprocess.Popen(['ip','netns','exec',name,'tcpdump','--immediate-mode','-Z','root','-U','-n','-i',interface,'-w',str(path),expression], stdout=subprocess.DEVNULL,stderr=subprocess.PIPE,text=True) stack.callback(stop,process) deadline=time.monotonic()+3 while time.monotonic()<deadline: assert process.poll() is None,'tcpdump exited before listening' if select.select([process.stderr],[],[],.1)[0] and 'listening on' in process.stderr.readline():return process,path raise AssertionError('tcpdump did not become ready') def packets(process,path): import struct,socket process.send_signal(signal.SIGINT);_,diagnostic=process.communicate(timeout=3) assert process.returncode==0,diagnostic raw=path.read_bytes();assert raw[:4]==bytes.fromhex('d4c3b2a1') and struct.unpack_from('<I',raw,20)[0]==1 offset=24;result=[] while offset<len(raw): seconds,micros,size,original=struct.unpack_from('<IIII',raw,offset);offset+=16 frame=raw[offset:offset+size];offset+=size if frame[12:14]!=b'\x08\x00' or frame[23]!=6:continue ihl=(frame[14]&15)*4;length=struct.unpack_from('!H',frame,16)[0];tcp=14+ihl sport,dport,seq,ack=struct.unpack_from('!HHII',frame,tcp);header=(frame[tcp+12]>>4)*4 opts={};cursor=tcp+20 while cursor<tcp+header: kind=frame[cursor] if kind==0:break if kind==1:cursor+=1;continue option_length=frame[cursor+1];data=frame[cursor+2:cursor+option_length];assert option_length>=2 if kind==2:opts['mss']=struct.unpack('!H',data)[0] elif kind==3:opts['wscale']=data[0] elif kind==4:opts['sack_ok']=True elif kind==5:opts['sack']=[list(pair) for pair in struct.iter_unpack('!II',data)] cursor+=option_length body=frame[tcp+header:14+length] result.append({'t':seconds+micros/1e6,'src':socket.inet_ntoa(frame[26:30]),'dst':socket.inet_ntoa(frame[30:34]), 'sport':sport,'dport':dport,'seq':seq,'ack':ack,'flags':frame[tcp+13],'window':struct.unpack_from('!H',frame,tcp+14)[0], 'length':len(body),'options':opts,'preview':body[:24].hex()}) return result with lab(['client','target']) as (root,stack,setting): wire('client','c0','target','t0',['192.0.2.1/30'],['192.0.2.2/30']) setting('client','net.ipv4.tcp_autocorking',0) server_code=r''' import socket,json def read_exact(stream,length): data=b'' while len(data)<length: chunk=stream.recv(length-len(data));assert chunk,'premature EOF';data+=chunk return data listener=socket.socket();listener.setsockopt(socket.SOL_SOCKET,socket.SO_REUSEADDR,1) listener.bind(('192.0.2.2',18080));listener.listen();print('listening',flush=True) for trial in range(2): with listener.accept()[0] as connection: connection.settimeout(3);connection.setsockopt(socket.IPPROTO_TCP,socket.TCP_QUICKACK,0) print('configured',flush=True) request=read_exact(connection,2);assert request==b'ab',request connection.sendall(b'OK');print(json.dumps({'request':request.decode()}),flush=True) ''' service=spawn(stack,['ip','netns','exec','target','python3','-u','-c',server_code]);assert line(service).strip()=='listening' tap,path=capture(stack,root,'client','c0','tcp port 18080','nagle') client_code=r''' import json,socket,sys,time def read_exact(stream,length): data=b'' while len(data)<length: chunk=stream.recv(length-len(data));assert chunk,'premature EOF';data+=chunk return data nodelay=int(sys.argv[1]);s=socket.socket();s.settimeout(3) s.setsockopt(socket.IPPROTO_TCP,socket.TCP_NODELAY,nodelay);s.bind(('192.0.2.1',40300+nodelay));s.connect(('192.0.2.2',18080)) print('connected',flush=True);assert sys.stdin.readline().strip()=='go' start=time.monotonic();s.sendall(b'a');time.sleep(.002);s.sendall(b'b');reply=read_exact(s,2) assert reply==b'OK';print(json.dumps({'nodelay':nodelay,'reply':reply.decode(),'elapsed_ms':(time.monotonic()-start)*1000}),flush=True);s.close() ''' outcomes=[] for nodelay in [0,1]: client=spawn(stack,['ip','netns','exec','client','python3','-u','-c',client_code,str(nodelay)]) assert line(client).strip()=='connected' and line(service).strip()=='configured' client.stdin.write('go\n');client.stdin.flush();outcomes.append(json.loads(line(client))) assert json.loads(line(service))['request']=='ab';client.wait(timeout=2);assert client.returncode==0 observed=packets(tap,path);timelines={} for nodelay in [0,1]: port=40300+nodelay;flow=[p for p in observed if port in (p['sport'],p['dport'])] first=next(p for p in flow if p['sport']==port and p['preview']=='61') second=next(p for p in flow if p['sport']==port and p['preview']=='62') assert (second['seq']-first['seq'])%2**32==1 acks=[p for p in flow if p['dport']==port and p['flags']&0x10 and 0<(p['ack']-first['seq'])%2**32<=2] assert acks if not nodelay: intermediate=next(p for p in acks if (p['ack']-first['seq'])%2**32==1) assert first['t']<intermediate['t']<=second['t'] and second['t']-first['t']>.01 else:assert second['t']<=acks[0]['t'] timelines[nodelay]={'first_byte':first,'second_byte':second,'first_ack_covering_data':acks[0], 'data_segment_gap_ms':(second['t']-first['t'])*1000} print(json.dumps({'trials':outcomes,'packet_timelines':timelines,'receiver_quickack_requested':0,'client_autocorking':0})) """ name='xbcatm-tcpflow-'+uuid.uuid4().hex[:10] def docker(*args,**kwargs):return subprocess.run(['docker',*args],capture_output=True,text=True,timeout=300,**kwargs) try: with TemporaryDirectory(prefix=name+'-') as directory: root=Path(directory);(root/'Dockerfile').write_text(recipe) build=docker('build','-t',name,str(root));assert build.returncode==0,build.stderr result=docker('run','--rm','-i','--name',name,'--network','none','--cap-add','NET_ADMIN','--cap-add','SYS_ADMIN', '--memory','256m','--pids-limit','128',name,'python3','-',input=program) assert result.returncode==0,result.stderr print(json.dumps(json.loads(result.stdout),sort_keys=True)) finally: docker('rm','-f',name);docker('image','rm',name) 服务器等待完整请求 ab 才回复 OK。每次试验之前，它在已接受连接上请求非快速确认模式。客户端关闭本命名空间自动 corking，以排除另一种合并机制对比较的影响。父子进程通过明确消息同步，确保接收端先完成套接字设置，再让客户端开始发送应用字节，避免把配置时序竞争误认为算法差异。
...
