参考资料
- https://github.com/aws/aws-xray-sdk-python
- python api reference,https://docs.aws.amazon.com/xray-sdk-for-python/latest/reference/
- node api reference,https://docs.aws.amazon.com/xray-sdk-for-nodejs/latest/reference/
初始化环境
npm init -y
npm install aws-xray-sdk
npm intall aws-sdk
npm install express
使用nodejs结合express的server来测试此配置,代码如下
// app.js
var AWSXRay = require('aws-xray-sdk');
// xray将aws sdk包装
var AWS = AWSXRay.captureAWS(require('aws-sdk'));
// var AWS = require('aws-sdk');// AWSXRay.config([AWSXRay.plugins.EC2Plugin, AWSXRay.plugins.ElasticBeanstalkPlugin]);
AWS.config.update({ region: 'cn-north-1' });// 指定xray守护进程监听地址
AWSXRay.setDaemonAddress('127.0.0.1:2000');const express = require('express')
const app = express()
const port = 3000app.use(AWSXRay.express.openSegment('TestPathApp'));app.get('/', (req, res) => {var document = AWSXRay.getSegment();// 添加注释和元数据document.addAnnotation("mykey", "my value");document.addMetadata("my key", "my value", "my namespace");res.send('Hello World!')var s3 = new AWS.S3();var params = {};s3.listBuckets(params, function (err, data) {if (err) console.log(err, err.stack);else console.log(data);});
})app.get('/testpath', (req, res) => {res.send('test path!')
})app.use(AWSXRay.express.closeSegment());app.listen(port, () => {console.log(`Example app listening on port ${port}`)
})
运行服务器
node main.js
配置采样规则的参考文档
https://docs.aws.amazon.com/zh_cn/xray/latest/devguide/xray-console-sampling.html
适用于 Node.js 的 X-Ray 配置
采样规则的配置方式
xray在ec2平台上配置xray采样规则,可以控制使用xray-sdk的服务器行为
在service侧设置采样规则的目的在于,不修改或重新部署代码的情况下修改采样行为,控制记录的数据量。
默认的采样规则
- 每秒记录首次请求
- 任何其他请求的5%
采样规则的配置方式
-
在sdk中配置从json中读取采样规则(存在的问题有,每个实例使用单独的采样规则可能导致请求数量变高,更新采样规则需要重新运行代码)
本地定义规则的缺点,固定目标由记录器的每个实例独立应用,而不是由 X-Ray 服务管理。随着部署更多主机,固定速率会成倍增加,这使得控制记录的数据量变得更加困难
-
在控制台创建采样规则,并在sdk中配置读取xray服务中定义好的采样规则(不需要重新部署代码,请求数量不会额外升高)
X-Ray SDK 需要额外配置才能使用您在控制台中配置的采样规则。
如果 SDK 无法访问 X-Ray 获取采样规则,它将恢复为每秒第一个请求的默认本地规则(1,5%)
采样规则的内容
默认的规则如下
- 每秒采样1个,固定比率为5%
- 匹配所有的满足要求的规则*
设置采样名称和优先级
设置采样限制
- reservoir,每秒钟请求的采样数量
- fixed rate,超出reservoir之后,对额外请求的百分比
- 举例,存储器容量为50,百分比为10%,如果总体请求为100,则每秒钟的采样数量为50+(100-50)*10%=55
设置采样标准
选择面向服务的条件,以确定要匹配的请求。值可以包括多字符匹配通配符(*)或单字符匹配通配符(?)
我们创建的服务器接受请求后,向xray发送的数据的原始raw data(先将ec2的插件关闭)如下
{"Id": "1-645b3731-14c36c71cafd66c95e9ce301","Duration": 0.001,"LimitExceeded": false,"Segments": [{"Id": "36cdc1612a565cbf","Document": {"id": "36cdc1612a565cbf","name": "TestPathApp","start_time": 1683699504.526,"trace_id": "1-645b3731-14c36c71cafd66c95e9ce301","end_time": 1683699504.527,"http": {"request": {"url": "http://127.0.0.1:3000/testpath","method": "GET","user_agent": "curl/7.88.1","client_ip": "::ffff:127.0.0.1"},"response": {"status": 200}},"aws": {"xray": {"package": "aws-xray-sdk","rule_name": "Default","sdk_version": "3.5.0","sdk": "X-Ray for Node.js"}},"service": {"name": "unknown","version": "unknown","runtime": "node","runtime_version": "v16.15.0"}}}]
}
在控制台配置采样规则
其中代码中的TestPathApp
就是服务名称
app.use(AWSXRay.express.openSegment('TestPathApp'));
在sdk配置采样规则
创建规则json文件
cat sampling-rules.json
{"version": 2,"rules": [{"description": "Player moves.","host": "*","http_method": "*","url_path": "/api/move/*","fixed_target": 1,"rate": 0.05}],"default": {"fixed_target": 1,"rate": 0.1}
}
在sdk中引用即可
// AWSXRay.middleware.setSamplingRules('sampling-rules.json');
AWSXRay.setDaemonAddress('127.0.0.1:2000');
var rules = {"rules": [{"description": "Player moves.","service_name": "*","http_method": "*","url_path": "/api/move/*","fixed_target": 1,"rate": 0.05}],"default": {"fixed_target": 0,"rate": 0.1},"version": 1
}
我们重新启动server,并监控xray守护进程的日志
var logger = {error: (message, meta) => { console.log(message, meta); },warn: (message, meta) => { console.log(message, meta); },info: (message, meta) => { console.log(message, meta); },debug: (message, meta) => { console.log(message, meta); }
}AWSXRay.setLogger(logger);
当请求/testpath
时,日志如下
- 由于没有匹配的
centralized sampling rule
,因此使用了本地采样方法 - segment的元数据
No effective centralized sampling rule match. Fallback to local rules. undefined
Local sampling rule match found for { http_method: GET, host: 127.0.0.1:3000, url_path: /testpath }. Matched { http_method: *, host: *, url_path: /testpath }. Using fixed_target: 1 and rate: 0.05. undefinedStarting middleware segment: { url: /testpath, name: TestPathApp, trace_id: 1-645b4739-390fcc9ee953490557b0b920, id: dac471632ef967d6, sampled: true } undefined
Closed middleware segment successfully: { url: /testpath, name: TestPathApp, trace_id: 1-645b4739-390fcc9ee953490557b0b920, id: dac471632ef967d6, sampled: true } undefinedSegment sent: {"trace_id:"1-645b4739-390fcc9ee953490557b0b920","id":"dac471632ef967d6"} undefined
UDP message sent: {"trace_id":"1-645b4739-390fcc9ee953490557b0b920","id":"dac471632ef967d6","start_time":1683703609.304,"name":"TestPathApp","service":{"runtime":"node","runtime_version":"v16.15.0","version":"unknown","name":"unknown"},"aws":{"xray":{"sdk":"X-Ray for Node.js","sdk_version":"3.5.0","package":"aws-xray-sdk"}},"http":{"request":{"method":"GET","user_agent":"curl/7.88.1","client_ip":"::ffff:127.0.0.1","url":"http://127.0.0.1:3000/testpath"},"response":{"status":200}},"end_time":1683703609.328} undefined
Successfully refreshed centralized sampling rule cache. undefined
但请求/
时,日志如下
Rule Default is matched. undefinedStarting middleware segment: { url: /, name: TestPathApp, trace_id: 1-645b477b-ba767934aabd33cbda7c5455, id: a54f43f3efcd4f89, sampled: false } undefined
Closed middleware segment successfully: { url: /, name: TestPathApp, trace_id: 1-645b477b-ba767934aabd33cbda7c5455, id: a54f43f3efcd4f89, sampled: false } undefinedSuccessfully reported rule statistics to get new sampling quota. undefined
可见,由于采样规则的设置,我们成功控制了数据收集量,避免额外的开销(例如lb健康检查的请求)