Prometheus와 Grafana를 사용한 모니터링 구성

# prometheus.yml

global:
    scrape_interval: 15s
    evaluation_interval: 15s

rule_files:
    # - "first.rules"
    # - "second.rules"

scrape_configs:
    - job_name: 'collect_spring_job'
      metrics_path: '/actuator/prometheus'
      static_configs:
      - targets: ['host.docker.internal:8080']

docker run -d \
-p 9090:9090 \
-v /Users/song/git/prometheus-settings/prometheus.yml:/etc/prometheus/prometheus.yml \
--add-host host.docker.internal:host-gateway \
--name prometheus prom/prometheus

// build.gradle
dependencies {
  implementation 'org.springframework.boot:spring-boot-starter-actuator'
  runtimeOnly 'io.micrometer:micrometer-registry-prometheus'
}

# application.yml
management:
  endpoints:
    web:
      exposure:
        include: "prometheus"

# HELP jvm_gc_overhead_percent An approximation of the percent of CPU time used by GC activities over the last lookback period or since monitoring began, whichever is shorter, in the range [0..1]
# TYPE jvm_gc_overhead_percent gauge
jvm_gc_overhead_percent 0.0
# HELP application_started_time_seconds Time taken (ms) to start the application
# TYPE application_started_time_seconds gauge
application_started_time_seconds{main_application_class="com.example.springmonitoring.SpringMonitoringApplication",} 2.893
# HELP executor_pool_max_threads The maximum allowed number of threads in the pool
# TYPE executor_pool_max_threads gauge
executor_pool_max_threads{name="applicationTaskExecutor",} 2.147483647E9
# HELP tomcat_sessions_rejected_sessions_total  
# TYPE tomcat_sessions_rejected_sessions_total counter
tomcat_sessions_rejected_sessions_total 0.0
# HELP jvm_buffer_memory_used_bytes An estimate of the memory that the Java virtual machine is using for this buffer pool
# TYPE jvm_buffer_memory_used_bytes gauge
...

@Slf4j
@RestController
@RequiredArgsConstructor
public class CounterController {
    private final Counter requestCounter = Metrics.counter("request_count");

    @GetMapping("/counter")
    public String counter() {
        requestCounter.increment();
      
        return "hello prometheus!";
    }
}

@Slf4j
@RestController
@RequiredArgsConstructor
public class GaugeController {
    private final Executor executorForGauge;

    @GetMapping("/gauge")
    public String gauge() {
        for (int i = 0 ; i < 10 ; i++) {
            executorForGauge.execute(() -> {
                try {
                    log.info("sleep!");
                    Thread.sleep(1000L);
                } catch (InterruptedException e) {
                    throw new RuntimeException(e);
                }
            });
        }

        return "hello prometheus!";
    }
}

@Configuration
public class GaugeWorkerConfig {
	@Bean
	public Executor executorForGauge() {
		ThreadPoolTaskExecutor executor = new ThreadPoolTaskExecutor();

		executor.setCorePoolSize(5);
		executor.setMaxPoolSize(10);
		executor.setDaemon(true);
		executor.setThreadNamePrefix("gauge");
		executor.initialize();

		Metrics.gauge(
			"thread_gauge",
			executor,
			ThreadPoolTaskExecutor::getActiveCount
		);

		return executor;
	}
}

@Slf4j
@RestController
public class SummaryController {
	private static final DistributionSummary requestLatency = Metrics.summary("request_latency_1");

	private static final RandomGenerator randomGenerator = RandomGenerator.getDefault();

	@Timed(value = "request_latency_2")
	@GetMapping("/summary")
	public String summary() {
		Long startTime = System.currentTimeMillis();
		long sleep = randomGenerator.nextLong(3000);
		try {
			Thread.sleep(sleep);
		} catch (Exception e) {
			log.error("exception is occurred.", e);
		} finally {
			Long endTime = System.currentTimeMillis();
			requestLatency.record(endTime - startTime);
		}

		return "hello prometheus!";
	}
}

@Configuration
public class TimedConfig {
	// @Timed 사용을 위함
  @Bean
	public TimedAspect timedAspect(MeterRegistry registry) {
		return new TimedAspect(registry);
	}
}

docker run -d \
-p 3000:3000 \
--add-host host.docker.internal:host-gateway \
--name grafana grafana/grafana-oss