java 业务指标监控
2020-04-21 本文已影响0人
天草二十六_简村人
1、总体设计
image.png
业务方使用Slf4jReporter生成指标数据到日志文件里，后面就交由服务端来接收和处理并展示了。
2、引入jar包
<dependency>
<groupId>io.dropwizard.metrics</groupId>
<artifactId>metrics-core</artifactId>
</dependency>
<dependency>
<groupId>io.dropwizard.metrics</groupId>
<artifactId>metrics-annotation</artifactId>
</dependency>
<dependency>
<groupId>com.github.davidb</groupId>
<artifactId>metrics-influxdb</artifactId>
<version>0.9.3</version>
</dependency>
3、logback-spring.xml增加日志输入
<appender name="metricsFILE" class="ch.qos.logback.core.rolling.RollingFileAppender">
<rollingPolicy class="ch.qos.logback.core.rolling.TimeBasedRollingPolicy">
<FileNamePattern>${LOG_HOME}/metrics_%d{yyyyMMdd}.log</FileNamePattern>
<!--日志文件保留天数-->
<MaxHistory>7</MaxHistory>
</rollingPolicy>
<encoder class="ch.qos.logback.classic.encoder.PatternLayoutEncoder">
<pattern>%d{HH:mm:ss} %-5p %c:%L - %m%n</pattern>
</encoder>
<!--日志文件最大的大小-->
<triggeringPolicy class="ch.qos.logback.core.rolling.SizeBasedTriggeringPolicy">
<MaxFileSize>${FILE_SIZE}MB</MaxFileSize>
</triggeringPolicy>
</appender>
<logger name="metrics" level="INFO" additivity="false">
<appender-ref ref="metricsFILE" />
</logger>
4、指标配置类MetricConfig
import com.codahale.metrics.*;
import metrics_influxdb.HttpInfluxdbProtocol;
import metrics_influxdb.InfluxdbReporter;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import java.util.concurrent.TimeUnit;
@Configuration
public class MetricConfig {
@Bean
public MetricRegistry registry() {
return new MetricRegistry();
}
@Bean
public Slf4jReporter slf4jReporter(MetricRegistry registry) {
Slf4jReporter reporter = Slf4jReporter.forRegistry(registry)
.convertRatesTo(TimeUnit.SECONDS)
.convertDurationsTo(TimeUnit.MILLISECONDS)
.build();
reporter.start(10, TimeUnit.SECONDS);
return reporter;
}
/**
* TPS 计算器
*
* @param registry
* @return
*/
@Bean
public Meter requestMeter(MetricRegistry registry) {
return registry.meter("request");
}
/**
* 直方图
*
* @param registry
* @return
*/
@Bean
public Histogram responseSizes(MetricRegistry registry) {
return registry.histogram("response-sizes");
}
/**
* 计数器
*
* @param registry
* @return
*/
@Bean
public Counter pendingJobs(MetricRegistry registry) {
return registry.counter("requestCount");
}
/**
* 计时器
*
* @param registry
* @return
*/
@Bean
public Timer responses(MetricRegistry registry) {
return registry.timer("executeTime");
}
@Bean(name = "influxdbReporter")
public ScheduledReporter influxdbReporter(MetricRegistry registry) {
ScheduledReporter reporter = InfluxdbReporter.forRegistry(registry)
.protocol(new HttpInfluxdbProtocol("http",
"localhost",
8086, "", "", "metrics"))
.convertRatesTo(TimeUnit.SECONDS)
.convertDurationsTo(TimeUnit.MILLISECONDS)
.filter(MetricFilter.ALL)
.skipIdleMetrics(false)
.build();
reporter.start(10, TimeUnit.SECONDS);
return reporter;
}
}
5、使用示例：
@Resource
private Meter requestMeter;
@Resource
private Histogram responseSizes;
@Resource
private Counter pendingJobs;
@Resource
private Timer responses;
@RequestMapping("/test/sign")
@ResponseBody
public String getSign(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
requestMeter.mark();
pendingJobs.inc();
responseSizes.update(new Random().nextInt(10));
final Timer.Context context = responses.time();
try {
return "success";
} finally {
context.stop();
}
}
效果见下图：
image.png
每隔10秒打印出指标数据的日志。
19:11:37 INFO metrics:373 - type=COUNTER, name=requestCount, count=0
19:11:37 INFO metrics:373 - type=HISTOGRAM, name=response-sizes, count=0, min=0, max=0, mean=0.0, stddev=0.0, median=0.0, p75=0.0, p95=0.0, p98=0.0, p99=0.0, p999=0.0
19:11:37 INFO metrics:373 - type=METER, name=request, count=0, mean_rate=0.0, m1=0.0, m5=0.0, m15=0.0, rate_unit=events/second
19:11:37 INFO metrics:373 - type=TIMER, name=executeTime, count=0, min=0.0, max=0.0, mean=0.0, stddev=0.0, median=0.0, p75=0.0, p95=0.0, p98=0.0, p99=0.0, p999=0.0, mean_rate=0.0, m1=0.0, m5=0.0, m15=0.0, rate_unit=events/second, duration_unit=milliseconds
19:11:47 INFO metrics:373 - type=COUNTER, name=requestCount, count=1
19:11:47 INFO metrics:373 - type=HISTOGRAM, name=response-sizes, count=1, min=5, max=5, mean=5.0, stddev=0.0, median=5.0, p75=5.0, p95=5.0, p98=5.0, p99=5.0, p999=5.0
19:11:47 INFO metrics:373 - type=METER, name=request, count=1, mean_rate=0.04772524178633343, m1=0.014712537947741825, m5=0.0032510706679223173, m15=0.0011018917421948848, rate_unit=events/second
19:11:47 INFO metrics:373 - type=TIMER, name=executeTime, count=0, min=0.0, max=0.0, mean=0.0, stddev=0.0, median=0.0, p75=0.0, p95=0.0, p98=0.0, p99=0.0, p999=0.0, mean_rate=0.0, m1=0.0, m5=0.0, m15=0.0, rate_unit=events/second, duration_unit=milliseconds
19:11:57 INFO metrics:373 - type=COUNTER, name=requestCount, count=1
19:11:57 INFO metrics:373 - type=HISTOGRAM, name=response-sizes, count=1, min=5, max=5, mean=5.0, stddev=0.0, median=5.0, p75=5.0, p95=5.0, p98=5.0, p99=5.0, p999=5.0
19:11:57 INFO metrics:373 - type=METER, name=request, count=1, mean_rate=0.032306681295300385, m1=0.012453894499523116, m5=0.003144487893819254, m15=0.0010897162674033895, rate_unit=events/second
19:11:57 INFO metrics:373 - type=TIMER, name=executeTime, count=0, min=0.0, max=0.0, mean=0.0, stddev=0.0, median=0.0, p75=0.0, p95=0.0, p98=0.0, p99=0.0, p999=0.0, mean_rate=0.0, m1=0.0, m5=0.0, m15=0.0, rate_unit=events/second, duration_unit=milliseconds
19:12:07 INFO metrics:373 - type=COUNTER, name=requestCount, count=2
19:12:07 INFO metrics:373 - type=HISTOGRAM, name=response-sizes, count=2, min=5, max=7, mean=6.156210465768618, stddev=0.987723792557591, median=7.0, p75=7.0, p95=7.0, p98=7.0, p99=7.0, p999=7.0
19:12:07 INFO metrics:373 - type=METER, name=request, count=2, mean_rate=0.04883621909301433, m1=0.025254532045303885, m5=0.0062924699865950515, m15=0.002179567069063387, rate_unit=events/second
19:12:07 INFO metrics:373 - type=TIMER, name=executeTime, count=0, min=0.0, max=0.0, mean=0.0, stddev=0.0, median=0.0, p75=0.0, p95=0.0, p98=0.0, p99=0.0, p999=0.0, mean_rate=0.0, m1=0.0, m5=0.0, m15=0.0, rate_unit=events/second, duration_unit=milliseconds
19:12:17 INFO metrics:373 - type=COUNTER, name=requestCount, count=2
19:12:17 INFO metrics:373 - type=HISTOGRAM, name=response-sizes, count=2, min=5, max=7, mean=6.156210465768618, stddev=0.987723792557591, median=7.0, p75=7.0, p95=7.0, p98=7.0, p99=7.0, p999=7.0
19:12:17 INFO metrics:373 - type=METER, name=request, count=2, mean_rate=0.03925160662498755, m1=0.02137749984701412, m5=0.006086178282834525, m15=0.0021554837014424494, rate_unit=events/second
19:12:17 INFO metrics:373 - type=TIMER, name=executeTime, count=0, min=0.0, max=0.0, mean=0.0, stddev=0.0, median=0.0, p75=0.0, p95=0.0, p98=0.0, p99=0.0, p999=0.0, mean_rate=0.0, m1=0.0, m5=0.0, m15=0.0, rate_unit=events/second, duration_unit=milliseconds
19:12:27 INFO metrics:373 - type=COUNTER, name=requestCount, count=2
19:12:27 INFO metrics:373 - type=HISTOGRAM, name=response-sizes, count=2, min=5, max=7, mean=6.156210465768618, stddev=0.987723792557591, median=7.0, p75=7.0, p95=7.0, p98=7.0, p99=7.0, p999=7.0
19:12:27 INFO metrics:373 - type=METER, name=request, count=2, mean_rate=0.032810010401197694, m1=0.018095662944349354, m5=0.00588664962556148, m15=0.0021316664456582147, rate_unit=events/second
19:12:27 INFO metrics:373 - type=TIMER, name=executeTime, count=0, min=0.0, max=0.0, mean=0.0, stddev=0.0, median=0.0, p75=0.0, p95=0.0, p98=0.0, p99=0.0, p999=0.0, mean_rate=0.0, m1=0.0, m5=0.0, m15=0.0, rate_unit=events/second, duration_unit=milliseconds
19:12:37 INFO metrics:373 - type=COUNTER, name=requestCount, count=2
19:12:37 INFO metrics:373 - type=HISTOGRAM, name=response-sizes, count=2, min=5, max=7, mean=6.156210465768618, stddev=0.987723792557591, median=7.0, p75=7.0, p95=7.0, p98=7.0, p99=7.0, p999=7.0
19:12:37 INFO metrics:373 - type=METER, name=request, count=2, mean_rate=0.028187596113694386, m1=0.01531764798217201, m5=0.005693662295739435, m15=0.0021081123612784834, rate_unit=events/second
19:12:37 INFO metrics:373 - type=TIMER, name=executeTime, count=0, min=0.0, max=0.0, mean=0.0, stddev=0.0, median=0.0, p75=0.0, p95=0.0, p98=0.0, p99=0.0, p999=0.0, mean_rate=0.0, m1=0.0, m5=0.0, m15=0.0, rate_unit=events/second, duration_unit=milliseconds
19:12:47 INFO metrics:373 - type=COUNTER, name=requestCount, count=2
19:12:47 INFO metrics:373 - type=HISTOGRAM, name=response-sizes, count=2, min=5, max=7, mean=6.156210465768618, stddev=0.987723792557591, median=7.0, p75=7.0, p95=7.0, p98=7.0, p99=7.0, p999=7.0
19:12:47 INFO metrics:373 - type=METER, name=request, count=2, mean_rate=0.024705614814530406, m1=0.012966109085216199, m5=0.005507001843146522, m15=0.0020848185403616864, rate_unit=events/second
19:12:47 INFO metrics:373 - type=TIMER, name=executeTime, count=0, min=0.0, max=0.0, mean=0.0, stddev=0.0, median=0.0, p75=0.0, p95=0.0, p98=0.0, p99=0.0, p999=0.0, mean_rate=0.0, m1=0.0, m5=0.0, m15=0.0, rate_unit=events/second, duration_unit=milliseconds
19:12:57 INFO metrics:373 - type=COUNTER, name=requestCount, count=4
19:12:57 INFO metrics:373 - type=HISTOGRAM, name=response-sizes, count=4, min=0, max=7, mean=2.0488679402655547, stddev=2.6066574932478366, median=1.0, p75=5.0, p95=7.0, p98=7.0, p99=7.0, p999=7.0
19:12:57 INFO metrics:373 - type=METER, name=request, count=4, mean_rate=0.04397865428643308, m1=0.01097557438357367, m5=0.005326460848075398, m15=0.0020617821070978764, rate_unit=events/second
19:12:57 INFO metrics:373 - type=TIMER, name=executeTime, count=0, min=0.0, max=0.0, mean=0.0, stddev=0.0, median=0.0, p75=0.0, p95=0.0, p98=0.0, p99=0.0, p999=0.0, mean_rate=0.0, m1=0.0, m5=0.0, m15=0.0, rate_unit=events/second, duration_unit=milliseconds
19:13:07 INFO metrics:373 - type=COUNTER, name=requestCount, count=4
19:13:07 INFO metrics:373 - type=HISTOGRAM, name=response-sizes, count=4, min=0, max=7, mean=2.0488679402655547, stddev=2.6066574932478366, median=1.0, p75=5.0, p95=7.0, p98=7.0, p99=7.0, p999=7.0
19:13:07 INFO metrics:373 - type=METER, name=request, count=4, mean_rate=0.03962227676951814, m1=0.03871569903135633, m5=0.011653980026690198, m15=0.0042427837018434575, rate_unit=events/second
19:13:07 INFO metrics:373 - type=TIMER, name=executeTime, count=0, min=0.0, max=0.0, mean=0.0, stddev=0.0, median=0.0, p75=0.0, p95=0.0, p98=0.0, p99=0.0, p999=0.0, mean_rate=0.0, m1=0.0, m5=0.0, m15=0.0, rate_unit=events/second, duration_unit=milliseconds
后期补充下后面几个技术栈。
