使用 Map-Reduce 统计Web 服务器 access.log 日志文件

首先将web服务器access.log倒入到mongodb,参考 http://netkiller.github.io/article/log.html。 格式如下：

{
	"_id" : ObjectId("51553efcd8616be7e5395c0d"),
	"remote_addr" : "192.168.2.76",
	"remote_user" : "-",
	"time_local" : "29/Mar/2013:09:20:31 +0800",
	"request" : "GET /tw/ad.jpg HTTP/1.1",
	"status" : "200",
	"body_bytes_sent" : "5557",
	"http_referer" : "http://www.example.com/tw/",
	"http_user_agent" : "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.57 Safari/537.17",
	"http_x_forwarded_for" : "-"
}
		

创建map方法

var mapFunction1 = function() {
    emit(this.remote_addr, {count:1});
};
		

创建reduce方法

		
var reduceFunction1 = function(key, values) {
	var total = 0;
	values.forEach(function (value) {total += value.count;});
    return {ipaddr: key, count:total};
};
		
		

分析数据

db.access.mapReduce(mapFunction1, reduceFunction1, {out : "resultCollection"});
		

输出结果

db.resultCollection.find();
		

Demo 数据库

		
> db.resultCollection.find();
{ "_id" : "192.168.2.109", "value" : { "count" : 554 } }
{ "_id" : "192.168.2.38", "value" : { "count" : 26 } }
{ "_id" : "192.168.2.39", "value" : { "count" : 72 } }
{ "_id" : "192.168.2.40", "value" : { "count" : 3564 } }
{ "_id" : "192.168.2.49", "value" : { "count" : 955 } }
{ "_id" : "192.168.2.5", "value" : { "count" : 2 } }
{ "_id" : "192.168.2.76", "value" : { "count" : 60537 } }
{ "_id" : "192.168.3.12", "value" : { "count" : 9577 } }
{ "_id" : "192.168.3.14", "value" : { "count" : 343 } }
{ "_id" : "192.168.3.18", "value" : { "count" : 1006 } }
{ "_id" : "192.168.3.26", "value" : { "count" : 2714 } }
{ "_id" : "192.168.6.19", "value" : { "count" : 668 } }
{ "_id" : "192.168.6.2", "value" : { "count" : 123760 } }
{ "_id" : "192.168.6.30", "value" : { "count" : 1196 } }
{ "_id" : "192.168.6.35", "value" : { "count" : 1050 } }