拥塞

慢启动在 TCP 发送端探索路径可承受的未确认数据量时，逐步扩大拥塞窗口。数据充足且确认模式合适时，经典行为是在多个往返间近似指数增长。“每个 RTT 翻倍”是有用的简化模式，不是无条件计时器规则。窗口变化依赖传输反馈和实现的增长条件，不能只根据连接已经打开多久，就推断它获得了多少发送预算。 坏掉的样子 connect 之后等待，不会自动把拥塞窗口预热。应用没有发送数据时，就没有支持这种增长的数据确认。很小的交换，也可能在用满已有发送预算之前便结束。期待每个短请求都出现大幅翻倍序列，是把受应用数据量限制的传输误认成持续积压的发送端。缺少明显增长，并不自动说明慢启动没有工作或连接存在故障。 现代系统初始窗口也不统一为一到两个段。RFC 6928 描述了允许更大初始窗口的实验性扩展，本次 Linux 发送端起步为十个段。单位同样重要：Linux TCP_INFO 的 snd_cwnd 以段为单位，许多协议说明则用字节描述拥塞窗口。推算未确认数据量之前，应同时查看发送 MSS，避免将段数直接当成字节数或当前实际在途段数。 慢启动并非总要持续到第一次丢失，之后统一彻底缩回起点。慢启动阈值帮助决定启动增长与拥塞避免，具体实现还可能采用额外启动检测；重传超时恢复也不同于快速恢复。把同一条示意曲线套到所有算法、丢失信号和工作负载，即使读到了真实指标，也可能作出错误诊断。首先需要确认当前连接处于哪个阶段。 快速验证 将脚本保存为 check-slow-start.py，准备 Docker 后运行 python3 check-slow-start.py。一次性环境使用 Python 3.11.16 和 iproute2 6.1.0，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 相连，netem 在两个方向的出口各添加十毫秒延迟，全部变更仅作用于虚拟端点： 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 info_code=r''' import struct def tcp_info(stream): raw=stream.getsockopt(socket.IPPROTO_TCP,socket.TCP_INFO,104);assert len(raw)==104 offsets={'snd_mss':16,'unacked':24,'rtt_us':68,'snd_ssthresh':76,'snd_cwnd':80,'total_retrans':100} return {'ca_state':raw[1],**{key:struct.unpack_from('=I',raw,offset)[0] for key,offset in offsets.items()}} ''' with lab(['client','target']) as (root,stack,setting): wire('client','c0','target','t0',['192.0.2.1/30'],['192.0.2.2/30']) for name,interface in [('client','c0'),('target','t0')]: ns(name,'tc','qdisc','add','dev',interface,'root','netem','delay','10ms','limit','10000') server_code=r''' import socket,json,hashlib,sys size=int(sys.argv[1]);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) with listener.accept()[0] as connection: connection.settimeout(6);remaining=size;digest=hashlib.sha256() while remaining: chunk=connection.recv(min(65536,remaining));assert chunk;remaining-=len(chunk);digest.update(chunk) assert digest.hexdigest()==hashlib.sha256(b'x'*size).hexdigest() connection.sendall((digest.hexdigest()+'\n').encode()) ''' client_code=info_code+r''' import socket,json,time,threading,sys,hashlib size=int(sys.argv[1]);stream=socket.socket();stream.settimeout(6) stream.setsockopt(socket.IPPROTO_TCP,socket.TCP_CONGESTION,b'reno');stream.connect(('192.0.2.2',18080)) initial=tcp_info(stream);time.sleep(.06);idle=tcp_info(stream);assert idle['snd_cwnd']==initial['snd_cwnd'] done=threading.Event();errors=[];samples=[initial,idle];reply=[] def transfer(): try: stream.sendall(b'x'*size) with stream.makefile('rb') as incoming:reply.append(incoming.readline().decode().strip()) except BaseException as error:errors.append(repr(error)) finally:done.set() worker=threading.Thread(target=transfer);worker.start();deadline=time.monotonic()+7 while not done.wait(.005): assert time.monotonic()<deadline,'transfer deadline exceeded' snapshot=tcp_info(stream) if snapshot!=samples[-1]:samples.append(snapshot) worker.join(timeout=1);assert not worker.is_alive() and not errors,errors samples.append(tcp_info(stream));assert reply==[hashlib.sha256(b'x'*size).hexdigest()] assert all(row['total_retrans']==0 for row in samples),samples if size>1:assert max(row['snd_cwnd'] for row in samples)>initial['snd_cwnd']*2,samples else:assert max(row['snd_cwnd'] for row in samples)==initial['snd_cwnd'],samples print(json.dumps({'bytes':size,'algorithm':stream.getsockopt(socket.IPPROTO_TCP,socket.TCP_CONGESTION,16).split(b'\0')[0].decode(), 'before_data':initial,'after_idle_without_data':idle,'samples':samples,'sha256':reply[0]}));stream.close() ''' results={} for label,size in [('short',1),('bulk',1048576)]: service=spawn(stack,['ip','netns','exec','target','python3','-u','-c',server_code,str(size)]);assert line(service).strip()=='listening' results[label]=json.loads(ns('client','python3','-c',client_code,str(size),timeout=10).stdout) service.wait(timeout=2);assert service.returncode==0 print(json.dumps({'egress_delay_each_direction_ms':10,'transfers':results})) """ 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) 客户端明确选择 Reno，避免实验悄悄受不同默认拥塞控制器影响。发送之前记录 TCP_INFO，在没有数据的情况下等待六十毫秒，然后再次记录。两次观察窗口均为十个段。这直接检验“新连接只要保持打开，拥塞预算就会按时间增长”的错误预期。增加等待时间与提供可确认的数据，属于不同输入，不能互相替代。 ...