默认路由匹配最宽范围,不会挽救所有失败路径
IPv4 默认路由是前缀 0.0.0.0/0,匹配所有 IPv4 目的地,但具体程度最低。在已经选择的路由表中,更长的匹配前缀通常优先。默认路由不是一个“其他具体路径失败后再重试”的过程。路由策略决定相关表,最终路由描述怎样转发,而不保证完整往返一定成功。匹配范围与路径健康是两类不同属性。 坏掉的样子 没有默认路由的机器,仍能访问直连或明确路由覆盖的目的地;反过来,添加默认路由也不证明能够访问互联网。下一跳需要可达,转发与过滤要允许流量,回复还需要返回路径。显示一个网关,只满足契约的一部分。真正配置是否共同工作,应由实际应用通信证明,而不是从路由文件中有一行 default 就推导全部能力。 更具体的拒绝路由会胜过可工作的默认路由。Linux 的 unreachable 等路由类型,会有意停止匹配目的地的转发。选定网关的邻居查询失败,也不意味着内核自动寻找更健康、却更宽泛的路径。静态路由优先级和 metric 不是服务健康监控或自动故障转移机制,不能把配置顺序当成逐个尝试可用出口的流程。 返回路径错误尤其容易误导。客户端选中预期网关并把流量送往监听中的服务器,服务器却可能无法把回复路由回客户端。反复修改客户端默认路由,可能破坏其他正常目的地,却没有修复缺失的反向路径。将所有连接超时归因于发送方网关之前,应查看两个方向和真实源地址。请求能到与响应能回,需要分别成立。 快速验证 将脚本保存为 check-default-route.py,准备 Docker 后运行 python3 check-default-route.py。Python 3.11.16 和 iproute2 6.1.0 在一次性 Linux 容器内建立客户端、路由器、目标拓扑。NET_ADMIN 与 SYS_ADMIN 支持嵌套命名空间和临时 proc 挂载。接口全是新建 veth,不向宿主发布端口或路由,也不修改现有网络设备: 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' 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 server(stack,name,address,port=18080,label='server'): code=r''' from http.server import BaseHTTPRequestHandler,ThreadingHTTPServer import json,socket,sys address,port,label=sys.argv[1],int(sys.argv[2]),sys.argv[3] class Handler(BaseHTTPRequestHandler): def do_GET(self): body=json.dumps({'server':label,'peer':self.client_address,'path':self.path}).encode() self.send_response(200);self.send_header('Content-Length',str(len(body)));self.end_headers();self.wfile.write(body) def log_message(self,*args):pass class Server(ThreadingHTTPServer): address_family=socket.AF_INET6 if ':' in address else socket.AF_INET def server_bind(self): if self.address_family==socket.AF_INET6:self.socket.setsockopt(socket.IPPROTO_IPV6,socket.IPV6_V6ONLY,1) super().server_bind() service=Server((address,port),Handler);print('ready',flush=True);service.serve_forever() ''' process=spawn(stack,['ip','netns','exec',name,'python3','-u','-c',code,address,str(port),label]) assert line(process).strip()=='ready';return process def request(name,address,port=18080): code=r''' import http.client,json,sys client=http.client.HTTPConnection(sys.argv[1],int(sys.argv[2]),timeout=.7) try: client.request('GET','/lab-visible-message');response=client.getresponse();body=json.loads(response.read()) assert response.status==200;print(json.dumps({'ok':True,'status':response.status,'body':body})) except OSError as error:print(json.dumps({'ok':False,'type':type(error).__name__,'errno':error.errno})) finally:client.close() ''' return json.loads(ns(name,'python3','-c',code,address,str(port)).stdout) def routed(setting): wire('client','c0','router','r0',['10.201.1.2/30'],['10.201.1.1/30']) wire('router','r1','target','t0',['10.201.2.1/30'],['10.201.2.2/30']) setting('router','net.ipv4.ip_forward',1) ip('client','route','add','default','via','10.201.1.1') ip('target','route','add','default','via','10.201.2.1') with lab(['client','router','target']) as (root,stack,setting): routed(setting);ip('client','route','delete','default') ip('target','addr','add','198.51.100.9/32','dev','lo');ip('router','route','add','198.51.100.9/32','via','10.201.2.2') daemon=server(stack,'target','198.51.100.9') connected=ns('client','ping','-n','-c','1','-W','1','10.201.1.1');assert connected.returncode==0 missing=request('client','198.51.100.9');assert not missing['ok'] and missing['errno']==101 ip('client','route','add','default','via','10.201.1.1') chosen=json.loads(ip('client','-j','route','get','198.51.100.9').stdout)[0];assert chosen['gateway']=='10.201.1.1' healthy=request('client','198.51.100.9');assert healthy['ok'] ip('client','route','add','unreachable','198.51.100.9/32') specific=request('client','198.51.100.9');assert not specific['ok'] and specific['errno']==113 ip('client','route','delete','unreachable','198.51.100.9/32') recovered=request('client','198.51.100.9');assert recovered['ok'] ip('target','route','delete','default') bad_return=request('client','198.51.100.9');assert not bad_return['ok'] and bad_return['type']=='TimeoutError' assert json.loads(ip('client','-j','route','get','198.51.100.9').stdout)[0]['gateway']=='10.201.1.1' ip('target','route','add','default','via','10.201.2.1') final=request('client','198.51.100.9');assert final['ok'] print(json.dumps({'connected_ping_without_default':0,'no_default':missing,'chosen_route':chosen,'with_default':healthy, 'specific_unreachable_route':specific,'specific_removed':recovered,'missing_return_route':bad_return,'return_route_restored':final})) """ name='xbcatm-netpath-'+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) 客户端使用 10.201.1.2,路由邻居为 10.201.1.1。目标位于路由器后的另一条链路,在回环接口拥有服务地址 198.51.100.9。路由器有到该服务的具体路由,目标起初具有返回默认路由。文档保留地址仅用于隔离拓扑,没有联系公网服务器。每项地址和下一跳都在脚本中明确配置,避免依赖宿主偶然存在的路由。 ...