【发布时间】：2018-01-14 03:15:57
【问题描述】：
所以我正在研究跨多个进程运行 socket.io。
这里的指南：https://socket.io/docs/using-multiple-nodes/ 给我留下了一些问题。
上面提到了使用配置 nginx 在 socket.io 进程之间进行负载平衡，但也提到了使用下面 Node.js 中的内置集群模块。
我应该为此使用 nginx 和 Node.js 中的集群模块吗？
另外我如何判断负载平衡是否有效？
我使用 nginx 选项对它进行了测试，其中两个 socket.io 进程使用 redis 适配器和集群模块运行。
这是我的 nginx 配置中的内容：
http {
upstream io_nodes {
ip_hash;
server 127.0.0.1:6001;
server 127.0.0.1:6002;
}
server {
listen 3000;
server_name example.com;
location / {
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header Host $host;
proxy_http_version 1.1;
proxy_pass http://io_nodes;
}
}
这是我的 socket.io 代码示例（大部分来自这里：https://github.com/elad/node-cluster-socket.io）：
var express = require('express'),
cluster = require('cluster'),
net = require('net'),
redis = require('redis'),
sio = require('socket.io'),
sio_redis = require('socket.io-redis');
var port = 6001,
num_processes = require('os').cpus().length;
if (cluster.isMaster) {
console.log('is master 6001');
// This stores our workers. We need to keep them to be able to reference
// them based on source IP address. It's also useful for auto-restart,
// for example.
var workers = [];
// Helper function for spawning worker at index 'i'.
var spawn = function(i) {
workers[i] = cluster.fork();
// Optional: Restart worker on exit
workers[i].on('exit', function(code, signal) {
console.log('respawning worker', i);
spawn(i);
});
};
// Spawn workers.
for (var i = 0; i < num_processes; i++) {
spawn(i);
}
// Helper function for getting a worker index based on IP address.
// This is a hot path so it should be really fast. The way it works
// is by converting the IP address to a number by removing non numeric
// characters, then compressing it to the number of slots we have.
//
// Compared against "real" hashing (from the sticky-session code) and
// "real" IP number conversion, this function is on par in terms of
// worker index distribution only much faster.
var worker_index = function(ip, len) {
var s = '';
for (var i = 0, _len = ip.length; i < _len; i++) {
if (!isNaN(ip[i])) {
s += ip[i];
}
}
return Number(s) % len;
};
// Create the outside facing server listening on our port.
var server = net.createServer({ pauseOnConnect: true }, function(connection) {
// We received a connection and need to pass it to the appropriate
// worker. Get the worker for this connection's source IP and pass
// it the connection.
var worker = workers[worker_index(connection.remoteAddress, num_processes)];
worker.send('sticky-session:connection', connection);
}).listen(port);
} else {
// Note we don't use a port here because the master listens on it for us.
var app = new express();
// Here you might use middleware, attach routes, etc.
// Don't expose our internal server to the outside.
var server = app.listen(0, 'localhost'),
io = sio(server);
// Tell Socket.IO to use the redis adapter. By default, the redis
// server is assumed to be on localhost:6379. You don't have to
// specify them explicitly unless you want to change them.
io.adapter(sio_redis({ host: 'localhost', port: 6379 }));
// Here you might use Socket.IO middleware for authorization etc.
io.on('connection', function(socket) {
console.log('port 6001');
console.log(socket.id);
});
// Listen to messages sent from the master. Ignore everything else.
process.on('message', function(message, connection) {
if (message !== 'sticky-session:connection') {
return;
}
// Emulate a connection event on the server by emitting the
// event with the connection the master sent us.
server.emit('connection', connection);
connection.resume();
});
}
连接工作得很好，虽然我在本地测试它..
我如何知道它是否正常工作？每次客户端连接时，似乎都连接到端口6001上的socket.io进程。
客户端连接代码连接到端口3000。
【问题讨论】：
-
如果你所有的服务器进程都在一台电脑上，你可以不用NGINX使用集群模块。如果您使用多台计算机，那么您需要一个像 NGINX 这样的网络基础设施来在不同服务器之间进行负载平衡。并且，您可以同时使用两者（通过 NGINX 之类的方式对多台服务器进行负载平衡，并且每台服务器在每台服务器上运行集群）。这里的关键是 node.js 集群只在同一主机上的不同进程之间分散负载。
-
有道理，谢谢。我只是被这一切弄糊涂了。