Node.js的集群功能以及在Express的配置

Node.js在v0.6.0版本下内置了集群功能,作为cluster模块，用于nodejs的多核处理,也比较容易通过脚本实现一个负载均衡的集群。

脚本参考了其他人的材料，建立一个server.js（因为虚拟机只有1核，为模拟多线程，所以采用numCPUs+4)

var cluster = require('cluster');
var http = require('http');
var numCPUs = require('os').cpus().length;

if (cluster.isMaster) {
    console.log('[master] ' + "start master...");

    for (var i = 0; i < numCPUs+4; i++) {
         cluster.fork();
    }

    cluster.on('listening', function (worker, address) {
        console.log('[master] ' + 'listening: worker' + worker.id + ',pid:'
 + worker.process.pid + ', Address:' + address.address + ":" + address.port);
    });

} else if (cluster.isWorker) {
    console.log('[worker] ' + "start worker ..." + cluster.worker.id);
    http.createServer(function (req, res) {
        console.log('worker'+cluster.worker.id);
        res.end('worker'+cluster.worker.id+',PID:'+process.pid);
    }).listen(3000);
}

启动服务器可以看到日志

$ node server.js
[master] start master...
[worker] start worker ...1
[master] listening: worker1,pid:2925, Address:0.0.0.0:3000
[worker] start worker ...3
[master] listening: worker3,pid:2931, Address:0.0.0.0:3000
[worker] start worker ...4
[master] listening: worker4,pid:2932, Address:0.0.0.0:3000
[worker] start worker ...2
[master] listening: worker2,pid:2930, Address:0.0.0.0:3000
worker4
worker2
worker1
worker3
worker4
worker2
worker1

通过curl访问可以看到route到不同的进程

curl 192.168.1.20:3000
worker4,PID:2932
curl 192.168.1.20:3000
worker2,PID:2930

但如何和我们的Express框架结合起来呢,通过npm start实际上是启动了package.json上的script脚本
node ./bin/www

具体打开www文件，发现详细的创建Server的命令，所以需要直接修改这个文件.修改如下:

#!/usr/bin/env node

/**
* Module dependencies.
*/

var cluster = require('cluster');
var numCPUs = require('os').cpus().length;
var app = require('../app');
var debug = require('debug')('myapp-express:server');
var http = require('http');

if (cluster.isMaster) {
console.log('[master] ' + "start master...");

for (var i = 0; i < numCPUs+4; i++) {
cluster.fork();
}

cluster.on('listening', function (worker, address) {
console.log('[master] ' + 'listening: worker' + worker.id + ',pid:' + worker.process.pid + ', Address:' + address.address + ":" + address.port);
});

} else if (cluster.isWorker) {
console.log('[worker] ' + "start worker ..." + cluster.worker.id);
http.createServer(app).listen(3000);
/*
http.createServer(app) {
console.log('worker'+cluster.worker.id);
res.end('worker'+cluster.worker.id+',PID:'+process.pid);

}).listen(3000);*/
}

启动后能正常访问网页

但在后台的日志中无法显示调用的process的信息所以我们不知道是否真的作到负载均衡了.

研究了一下，页面还是走到routes目录下的index.js模块，所以在index.js下加入console.log信息,这样基本上访问的时候就知道是走到哪个进程实现调用

router.get('/about',function(req,res) {
console.log(process.pid);
res.render('about',{titile:"Introduction"});
});

经过实践，同一个firefox的请求会路由到同一个进程pid,关闭在重新打开会路由到另一个pid.