按 nginx 均衡方法实际做出的决定来选择策略
upstream 组列出候选后端端点，均衡方法从符合条件的节点中选择目标。轮询按权重分配选择，最少连接考虑活动连接与权重，哈希方法则根据指定 key 建立亲和性。这些决定描述路由策略，不会自动测量 CPU 利用率，不保证响应时间相等，也不会在节点消失时让本地会话状态自动获得持久性。选择方法之前，应先明确希望它依据什么信号决策。 坏掉的样子 常见测量错误是看错地址。curl 的 remote IP 标识 curl 实际连接的服务器，在这种架构里通常就是代理。访问日志里的客户端地址字段，同样不是后端分布报告。要评估节点选择，应查看真正的上游地址或受控后端身份；如果重试可能访问多个节点，还要保留各次尝试信息。不能把入口连接信息当成后端选择结果。 请求数均匀不代表工作量均匀。长报表和很小的缓存响应都算一个请求，却可能占用完全不同的资源。配置权重表达预期相对份额，不是自动测得的机器容量。把权重翻倍，不能证明不同后端的每核负载或延迟已经相等。权重是否合理，需要代表性请求成本和节点能力支持，而不是只依据某个硬件参数作推断。 亲和性有另一组失败方式。很多用户可能共享同一源地址，所以 IP 哈希可能集中流量，而不是按个人均匀分布。节点失败或成员变化会改变落点，本地会话状态不会仅因为请求换了机器就一起移动。ip_hash 也不应被描述成 nginx 可配置的一致性哈希环；显式 hash ... consistent 是另一种独立方法，不能把两种策略的性质混用。 快速验证 下文集成实验的结果保留自历史运行记录；本次修订没有重新执行该实验，不能将这些记录当成本次环境的新实测。 将脚本保存为 check-balancing.py，准备 Python、Docker 和固定镜像后执行。记录环境使用单个 nginx 1.28.0 worker，以及一个可丢弃后端容器中不同端口上的两个可识别 HTTP 节点。共享机器是有意安排：实验测量选择结果，不比较硬件容量。客户端只通过宿主回环访问，结束后清理自己的资源： from contextlib import contextmanager from pathlib import Path from tempfile import TemporaryDirectory import http.client,json,socket,subprocess,time,uuid NGINX='nginx@sha256:552e7481ca93ffccd046aa658dbbed22caefbc09c66fa7cd247cbb90b8a5c609' PYTHON='python@sha256:528257d48c1da0dcecc2e725d1ae34498d60c965f1241e39cd6a85a8859bdf84' def docker(*args,check=True): result=subprocess.run(['docker',*args],capture_output=True,text=True,timeout=120) if check:assert result.returncode==0,result.stderr return result def wait(predicate): deadline=time.monotonic()+15 while time.monotonic()<deadline: try: if predicate():return except OSError:pass time.sleep(.1) raise AssertionError('fixture did not become ready') @contextmanager def lab(configuration,files=None,backend=None,extra_ports=()): name='xbcatm-nginx-'+uuid.uuid4().hex[:10];tags=[name+':proxy',name+':backend'];containers=[name+'-proxy',name+'-backend'] try: with TemporaryDirectory(prefix=name+'-') as directory: root=Path(directory);(root/'files').mkdir();(root/'nginx.conf').write_text(configuration) for path,content in (files or {}).items(): target=root/'files'/path;target.parent.mkdir(parents=True,exist_ok=True) target.write_bytes(content if isinstance(content,bytes) else content.encode()) docker('network','create',name) if backend is not None: (root/'backend.py').write_text(backend) (root/'backend.Dockerfile').write_text(f'FROM {PYTHON}\nCOPY backend.py /backend.py\nCMD ["python", "/backend.py"]\n') docker('build','--network','none','-f',str(root/'backend.Dockerfile'),'-t',tags[1],str(root)) docker('run','-d','--name',containers[1],'--network',name,'--network-alias','backend',tags[1]) wait(lambda:docker('exec',containers[1],'python','-c','import socket;s=socket.create_connection(("127.0.0.1",8081),timeout=.5);s.close()',check=False).returncode==0) (root/'Dockerfile').write_text(f'FROM {NGINX}\nCOPY nginx.conf /etc/nginx/nginx.conf\nCOPY files /srv\n') docker('build','--network','none','-t',tags[0],str(root)) docker('run','--rm','--network',name,tags[0],'nginx','-t') published=[arg for value in (8080,*extra_ports) for arg in ('-p','127.0.0.1::'+str(value))] docker('run','-d','--name',containers[0],'--network',name,*published,tags[0]) details=json.loads(docker('inspect',containers[0]).stdout)[0] binding=details['NetworkSettings']['Ports']['8080/tcp'][0];assert binding['HostIp']=='127.0.0.1';port=int(binding['HostPort']) def ready(): connection=socket.create_connection(('127.0.0.1',port),timeout=.5);connection.close();return True wait(ready) def request(path,method='GET',headers=None,body=None): connection=http.client.HTTPConnection('127.0.0.1',port,timeout=5) try: connection.request(method,path,body=body,headers=headers or {}) response=connection.getresponse();return response.status,{k.lower():v for k,v in response.getheaders()},response.read() finally:connection.close() request.port=port;request.network=name request.ports={int(key.split('/')[0]):int(value[0]['HostPort']) for key,value in details['NetworkSettings']['Ports'].items() if value} yield containers[0],request finally: docker('rm','-f',*containers,check=False);docker('image','rm',*tags,check=False);docker('network','rm',name,check=False) def config(locations,extra=''): return 'worker_processes 1;\nerror_log /tmp/error.log notice;\nevents {}\nhttp {\naccess_log off;\n'+extra+'\nserver { listen 8080; root /srv;\n'+locations+'\n}\n}\n' backend=r''' from http.server import BaseHTTPRequestHandler,ThreadingHTTPServer from urllib.parse import urlsplit,parse_qs import itertools,json,threading lock=threading.Lock();ids=itertools.count(1);counts={'A':0,'B':0};active={'A':0,'B':0};faults={'A':200,'B':200};gates={} class Handler(BaseHTTPRequestHandler): protocol_version='HTTP/1.1' def setup(self):super().setup();self.ident=next(ids) def log_message(self,*args):pass def do_GET(self): parsed=urlsplit(self.path);label=self.server.label;code=200 if label=='control': query=parse_qs(parsed.query) with lock: if parsed.path=='/fail':faults[query['peer'][0]]=int(query['status'][0]) if parsed.path=='/release':gates[query['path'][0]].set() data={'counts':dict(counts),'active':dict(active),'faults':dict(faults),'held':list(gates)} else: with lock: counts[label]+=1;active[label]+=1;code=faults[label] if parsed.path.startswith('/hold/'):gates[parsed.path]=threading.Event() if parsed.path.startswith('/hold/'):assert gates[parsed.path].wait(20) data={'peer':label,'path':self.path,'connection':self.ident} body=json.dumps(data,sort_keys=True).encode();self.send_response(code) self.send_header('Content-Type','application/json');self.send_header('Content-Length',str(len(body))) self.end_headers();self.wfile.write(body) if label!='control': with lock:active[label]-=1 for port,label in [(8081,'A'),(8082,'B'),(8083,'control')]: server=ThreadingHTTPServer(('0.0.0.0',port),Handler);server.label=label threading.Thread(target=server.serve_forever,daemon=True).start() threading.Event().wait() ''' from collections import Counter extra=''' upstream round { server backend:8081; server backend:8082; } upstream weighted { server backend:8081 weight=2; server backend:8082; } upstream by_ip { ip_hash; server backend:8081; server backend:8082; } upstream by_key { hash $arg_key consistent; server backend:8081; server backend:8082; } add_header X-Upstream $upstream_addr always; add_header X-Peer $remote_addr always; ''' locations='\n'.join(f'location /{path}/ {{ proxy_pass http://{group}/; }}' for path,group in [('round','round'),('weighted','weighted'),('sticky','by_ip'),('key','by_key')]) with lab(config(locations,extra),backend=backend) as (_,request): def get(path,headers=None): status,h,b=request(path,headers=headers);assert status==200;data=json.loads(b) assert h['x-upstream'].endswith(':8081' if data['peer']=='A' else ':8082') return data['peer'],h results={} for mode,expected in [('round',{'A':6,'B':6}),('weighted',{'A':8,'B':4})]: chosen=[get('/'+mode+'/item')[0] for _ in range(12)] assert dict(Counter(chosen))==expected,chosen;results[mode]={'sequence':chosen,'counts':dict(Counter(chosen))} sticky=[get('/sticky/item',{'X-Forwarded-For':'192.0.2.'+str(i)}) for i in range(1,9)] assert len({r[0] for r in sticky})==len({r[1]['x-peer'] for r in sticky})==1 results['ip_hash']={'peers':[r[0] for r in sticky],'socket_peer':sticky[0][1]['x-peer']} groups={} for key in ['alpha','beta','gamma','delta','epsilon','zeta']: pair=[get('/key/item?key='+key)[0] for _ in range(2)];assert pair[0]==pair[1];groups[key]=pair[0] assert set(groups.values())=={'A','B'},groups;results['consistent_key_hash']=groups print(json.dumps(results,sort_keys=True)) 对同权轮询组顺序发送十二次请求，A、B 各返回六次，本次受控运行中两者交替出现。每个响应的后端标记都会与 nginx 上游地址头中的端口对应检查，因此观察的是实际选中节点，而不是从客户端连接 nginx 的地址推测分布。即使所有请求都经过同一入口，也能明确区分最终由哪个后端回答。 ...
