转发条目可以过期或被清除,本地配置记录仍可以持续提供。

dnsmasq 区分转发缓存与本地配置名称

dnsmasq 可以向上游转发 DNS 查询,在有界缓存中保留支持的回答,也可以提供本地配置的名称。这些是不同的数据来源。重复得到相同回答,可能来自缓存命中,也可能来自本地配置。主机名与权威数据不一致、或者清缓存后仍然解析到原地址时,先确认来源十分重要;否则容易把有效配置误认为没有清干净的缓存。 坏掉的样子 启动 dnsmasq,不会自动让所有应用使用它。客户端必须把 DNS 查询交给预期监听,有的应用还会使用其他解析服务。同样,本地监听正常,也可能转发到错误上游或者读取了意外 hosts 配置。在增加缓存容量或重启服务前,应先确认真实查询路径。如果失败查询根本没到达这个进程,对它反复操作不会改变调用方看到的结果。 本地名称可以有意覆盖上游数据。清理转发缓存不会删除这个配置名称,因此反复清空也不能让上游地址获胜。应把本地记录当作有负责人、有用途的配置管理。即使回答的本地 TTL 为零,dnsmasq 仍可持续返回该值,因为它来自配置生成,不是靠保留某份转发回答维持。零 TTL 与删除本地配置并不是同一件事。 缓存容量和新鲜度解决不同问题。更大缓存可以保留更多合适条目,却不会延长条目的有效 TTL,也不会让上游故障期间所有名称都能查询成功。新名称与过期条目仍需要合适的解析路径。缓存大小也不直接代表可同时发送多少上游查询,更不能单独保证应用可用。应分别观察容量、寿命、并发与上游健康,而不是用一个参数代替所有约束。 快速验证 将脚本保存为 check-dnsmasq.py,准备 Docker 后执行 python3 check-dnsmasq.py。固定环境使用 dnsmasq 2.90 和 BIND 9.18.49。实验转发器忽略环境中的 resolv 和 hosts 文件,明确绑定回环监听,并只转发到自己的临时权威服务器。它不发布宿主端口,没有 DHCP 配置,结束后清理自己的实例,不影响现有服务: 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 bind9=1:9.18.49-1~deb12u2 bind9-dnsutils=1:9.18.49-1~deb12u2 dnsmasq-base=2.90-4~deb12u2 python3-dnspython=2.3.0-1 && rm -rf /var/lib/apt/lists/*\nCMD ["/usr/bin/python3"]\n' program=r""" from contextlib import ExitStack,contextmanager from pathlib import Path from tempfile import TemporaryDirectory import json,re,signal,subprocess,time import dns.exception,dns.message,dns.query,dns.rcode,dns.rdatatype def run(*args,check=True): result=subprocess.run(args,capture_output=True,text=True,timeout=15) if check:assert result.returncode==0,(args,result.returncode,result.stdout,result.stderr) return result def query(name,kind='A',port=1053): return dns.query.udp(dns.message.make_query(name,kind),'127.0.0.1',port=port,timeout=1) def values(response,kind='A'): wanted=dns.rdatatype.from_text(kind) return [item.to_text() for rrset in response.answer if rrset.rdtype==wanted for item in rrset] def show(response): def section(records):return [{'name':str(rr.name),'type':dns.rdatatype.to_text(rr.rdtype),'ttl':rr.ttl,'data':[item.to_text() for item in rr]} for rr in records] return {'rcode':dns.rcode.to_text(response.rcode()),'answer':section(response.answer),'authority':section(response.authority)} def wait(predicate,timeout=15): deadline=time.monotonic()+timeout while time.monotonic()<deadline: try: if predicate():return except (OSError,dns.exception.Timeout):pass time.sleep(.05) raise AssertionError('DNS fixture condition did not become true') def stop(process): if process.poll() is None: process.terminate() try:process.wait(timeout=5) except subprocess.TimeoutExpired:process.kill();process.wait(timeout=5) @contextmanager def lab(records,soa_ttl=8,minimum=4,extra=''): with TemporaryDirectory(prefix='xbcatm-dns-') as directory,ExitStack() as stack: root=Path(directory);zone=root/'zone';conf=root/'named.conf';log=root/'named.log';serial=1 def save(body): zone.write_text(f'$ORIGIN lab.test.\n$TTL 30\n@ {soa_ttl} IN SOA ns.lab.test. hostmaster.lab.test. ({serial} 60 60 3600 {minimum})\n@ IN NS ns.lab.test.\nns IN A 127.0.0.1\n'+body+'\n') run('named-checkzone','lab.test',str(zone)) save(records) conf.write_text(f'''options {{ directory "{root}"; listen-on port 1053 {{127.0.0.1;}}; listen-on-v6 {{none;}}; recursion no; dnssec-validation no; notify no; querylog yes; max-cache-size 8m; pid-file "{root}/named.pid"; session-keyfile none; {extra} }}; controls {{}}; zone "lab.test" {{ type primary; file "{zone}"; }}; ''') run('named-checkconf',str(conf)) output=stack.enter_context(log.open('w')) authority=subprocess.Popen(['named','-g','-c',str(conf),'-n','1','-U','1'],stdout=output,stderr=subprocess.STDOUT) stack.callback(stop,authority) def ready(): assert authority.poll() is None,log.read_text() response=query('lab.test.','SOA');return response.rcode()==0 and response.answer[0][0].serial==serial wait(ready) def update(body): nonlocal serial serial+=1;save(body);authority.send_signal(signal.SIGHUP);wait(ready) def cache(port=1054,upstream=1053,size=150,options=()): logfile=root/('cache-'+str(port)+'.log');stream=stack.enter_context(logfile.open('w')) command=['dnsmasq','--no-daemon','--conf-file=/dev/null','--no-resolv','--no-hosts','--bind-interfaces', '--listen-address=127.0.0.1','--port='+str(port),'--server=127.0.0.1#'+str(upstream), '--cache-size='+str(size),'--log-queries','--log-facility=-',*options] process=subprocess.Popen(command,stdout=stream,stderr=subprocess.STDOUT);stack.callback(stop,process) def cache_ready(): assert process.poll() is None,logfile.read_text() return query('lab.test.','SOA',port).rcode()==0 wait(cache_ready);return process,logfile def queries(name,kind='A'): return sum(bool(re.search(r'query: '+re.escape(name.rstrip('.'))+r' IN '+kind+r'\b',line)) for line in log.read_text().splitlines()) yield root,update,cache,queries with lab('cached 20 IN A 127.0.0.2\nuncached 20 IN A 127.0.0.3\nlocal 20 IN A 127.0.0.4') as (_,update,cache,queries): daemon,log=cache(options=('--host-record=local.lab.test,127.0.0.9',)) for _ in range(3):assert values(query('cached.lab.test.',port=1054))==['127.0.0.2'] wait(lambda: queries('cached.lab.test')==1) cache(port=1055,size=0) for _ in range(3):assert values(query('uncached.lab.test.',port=1055))==['127.0.0.3'] wait(lambda: queries('uncached.lab.test')==3) local=query('local.lab.test.',port=1054);assert values(local)==['127.0.0.9'] and local.answer[0].ttl==0 assert queries('local.lab.test')==0 authoritative=query('local.lab.test.');assert values(authoritative)==['127.0.0.4'] wait(lambda: queries('local.lab.test')==1) update('cached 20 IN A 127.0.0.8\nuncached 20 IN A 127.0.0.3\nlocal 20 IN A 127.0.0.4') stale=query('cached.lab.test.',port=1054);assert values(stale)==['127.0.0.2'] and queries('cached.lab.test')==1 previous=log.read_text().count('cleared cache');daemon.send_signal(signal.SIGHUP) wait(lambda: log.read_text().count('cleared cache')>previous) refreshed=query('cached.lab.test.',port=1054);assert values(refreshed)==['127.0.0.8'] wait(lambda: queries('cached.lab.test')==2) retained=query('local.lab.test.',port=1054);assert values(retained)==['127.0.0.9'] print(json.dumps({'three_lookups_upstream_counts':{'cache_enabled':1,'cache_disabled':3},'local_record':show(local), 'same_name_authority':show(authoritative),'before_SIGHUP':show(stale),'after_SIGHUP':show(refreshed), 'configured_local_record_retained':show(retained)},sort_keys=True)) """ name='xbcatm-dns-'+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) built=docker('build','-t',name,str(root));assert built.returncode==0,built.stderr result=docker('run','--rm','-i','--name',name,'--network','none','--memory','384m','--pids-limit','128',name, '/usr/bin/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) 通过启用缓存的监听查询 cached.lab.test 三次,都返回 127.0.0.2,权威日志却只记录一次。第二个监听使用 cache-size=0,经它对另一个名称查询三次,就产生三次上游请求。这个对照直接验证缓存对转发工作量的影响,不用响应速度猜测是否命中,也不声称测得某个固定延迟改善。回环网络的快慢本身不足以证明数据来源。 ...

四月 15, 2028 · 2 分钟 · XB Field Notes