Docker部署
# 安装prometheus
docker run -d -p 9090:9090 --name prometheus --restart=always -v /opt/prometheus/data/:/data -v /opt/prometheus/prometheus.yml:/opt/prometheus/prometheus.yml -v /opt/prometheus/rule.yml:/opt/prometheus/rule.yml prom/prometheus --config.file=/opt/prometheus/prometheus.yml --web.enable-lifecycle --storage.tsdb.retention=90d
# 安装grafana
docker run -d --name=grafana -p 3000:3000 grafana/grafana
其中prometheus挂载了一些配置文件进去
prometheus.yml
# my global config
global:
scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
# scrape_timeout is set to the global default (10s).
# Alertmanager configuration
alerting:
alertmanagers:
- static_configs:
- targets:
# - alertmanager:9093
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
- "/opt/prometheus/rule.yml"
# - "second_rules.yml"
# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
# The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
- job_name: "prometheus"
# metrics_path defaults to '/metrics'
# scheme defaults to 'http'.
static_configs:
- targets: ["192.168.217.134:9090"]
- job_name: 'node-exporter'
static_configs:
- targets: ['192.168.217.134:9100']
- job_name: 'casesys'
metrics_path: '/rycem/api/casesys/actuator/prometheus'
static_configs:
- targets: ['192.168.217.134:9102']
rule.yml
groups:
- name: Hosts.rules
rules:
- alert: HostDown
expr: up{job=~"node-exporter|prometheus|grafana|alertmanager|casesys"} == 0
for: 0m
labels:
severity: ERROR
annotations:
title: 'Instance down'
summary: "{{$labels.instance}}"
description: "主机: 【{{ $labels.instance }}】has been down for more than 1 minute"
微服务改造
自定义Prometheus注解模块
Pom.xml
<dependencies>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-actuator</artifactId>
</dependency>
<dependency>
<groupId>io.micrometer</groupId>
<artifactId>micrometer-registry-prometheus</artifactId>
</dependency>
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-web</artifactId>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-aop</artifactId>
</dependency>
注解类
package com.rycem.common.prometheus.annotation;
import java.lang.annotation.Retention;
import java.lang.annotation.RetentionPolicy;
import java.lang.annotation.Target;
import static java.lang.annotation.ElementType.METHOD;
/**
* @ClassName PrometheusMetrics
* @Description 普罗米修斯自定义注释
* @Author 陈铭
* @Date 21:42 2023/4/3
* @Version 1.0
**/
@Target(METHOD)
@Retention(RetentionPolicy.RUNTIME)
public @interface PrometheusMetrics {
String value() default "";
}
切面类
切面直接切至上述的注解，那么所有被注解的接口都会被切面到
package com.rycem.common.prometheus.aop;
import com.rycem.common.prometheus.exception.MetricException;
import com.rycem.common.prometheus.monitor.PrometheusMonitor;
import io.prometheus.client.Histogram;
import org.aspectj.lang.ProceedingJoinPoint;
import org.aspectj.lang.annotation.Around;
import org.aspectj.lang.annotation.Aspect;
import org.aspectj.lang.annotation.Pointcut;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Component;
import org.springframework.web.context.request.RequestContextHolder;
import org.springframework.web.context.request.ServletRequestAttributes;
import javax.servlet.http.HttpServletRequest;
import java.util.Objects;
/**
* @ClassName PrometheusAspect
* @Description 普罗米修斯切面
* @Author 陈铭
* @Date 21:42 2023/4/3
* @Version 1.0
**/
@Aspect
@Component
public class PrometheusAspect {
@Autowired
private PrometheusMonitor prometheusMonitor;
@Pointcut("@annotation(com.rycem.common.prometheus.annotation.PrometheusMetrics)")
public void point() {
}
@Around("point()")
public Object around(ProceedingJoinPoint joinPoint) throws MetricException {
Histogram.Timer requestTimer = null;
String[] labels = null;
Object result;
try {
// 获取request信息
HttpServletRequest request = ((ServletRequestAttributes) Objects.requireNonNull(
RequestContextHolder.getRequestAttributes())
).getRequest();
labels = prometheusMonitor.buildLabels(request, joinPoint);
// 请求开始
requestTimer = prometheusMonitor.getRequestConsuming().labels(labels).startTimer();
// 请求总次数加1
prometheusMonitor.getTotalCount().labels(labels).inc();
result = joinPoint.proceed();
// 请求成功次数加1
prometheusMonitor.getSuccessCount().labels(labels).inc();
} catch (Throwable e) {
// 请求失败次数加1
prometheusMonitor.getFailureCount().labels(labels).inc();
throw new MetricException("【普罗米修斯监控AOP异常】==>"
.concat("接口URL: ").concat(Objects.requireNonNull(labels)[0])); // 抛出自定义异常
} finally {
// 请求结束
assert requestTimer != null;
requestTimer.observeDuration();
}
return result;
}
}
监控类
监控类封装了Prometheus的各类计数器
package com.rycem.common.prometheus.monitor;
import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper;
import io.micrometer.prometheus.PrometheusMeterRegistry;
import io.prometheus.client.Counter;
import io.prometheus.client.Histogram;
import lombok.Getter;
import lombok.Setter;
import org.aspectj.lang.ProceedingJoinPoint;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Component;
import javax.annotation.PostConstruct;
import javax.servlet.http.HttpServletRequest;
/**
* @ClassName PrometheusMonitor
* @Description 普罗米修斯监控类，包装了各类计数器
* @Author 陈铭
* @Date 22:15 2023/4/3
* @Version 1.0
**/
@Component
@Getter
@Setter
public class PrometheusMonitor {
public static final String SUCCESS_COUNTER_NAME="success_count";
public static final String FAILURE_COUNTER_NAME="failure_count";
public static final String TOTAL_COUNTER_NAME="total_count";
public static final String HISTOGRAM_NAME="request_consuming";
public static final String[] LABEL_NAMES={"uri","method","params","body"};
@Autowired
private ObjectMapper objectMapper;
@Autowired
private PrometheusMeterRegistry registry;
private Counter successCount;
private Counter failureCount;
private Counter totalCount;
private Histogram requestConsuming;
@PostConstruct
public void init() {
successCount = Counter.build().name(SUCCESS_COUNTER_NAME)
.labelNames(LABEL_NAMES)
.help("request error counter of api")
.register(registry.getPrometheusRegistry());
failureCount = Counter.build().name(FAILURE_COUNTER_NAME)
.labelNames(LABEL_NAMES)
.help("request error counter of api")
.register(registry.getPrometheusRegistry());
totalCount = Counter.build().name(TOTAL_COUNTER_NAME)
.labelNames(LABEL_NAMES)
.help("total request counter of api")
.register(registry.getPrometheusRegistry());
requestConsuming = Histogram.build().name(HISTOGRAM_NAME)
.labelNames(LABEL_NAMES)
.help("request consuming of api")
.register(registry.getPrometheusRegistry());
}
public String[] buildLabels(HttpServletRequest request, ProceedingJoinPoint joinPoint) throws JsonProcessingException {
String uri = request.getServletPath();
String restMethod = request.getMethod();
String params = "";
String body = "";
if ("GET".equals(restMethod)) {
params = objectMapper.writeValueAsString(request.getParameterMap());
} else {
body = objectMapper.writeValueAsString(joinPoint.getArgs());
}
return new String[]{uri, restMethod, params, body};
}
}
使用注解模块
- pom中引入该模块的依赖
- 对接口方法上方注解@PrometheusMetrics
测试
本地启动微服务，从Swagger执行一下接口，访问 http://127.0.0.1:9102/rycem/api/casesys/actuator/prometheus
Prometheus查看数据
将微服务打包成docker镜像并运行，之前启动的grafana和prometheus都在的
上述的prometheus.yml配置中已经就配好了监听该微服务，随便访问几次微服务接口，查询Prometheus控制台
Grafana查看数据
以case/list接口为例，查询成功和失败的数量
评论区