What are these metrics? What tools will we use to write these metrics?

Metrics are quantitative indicators that allow monitoring the state and performance of an application or system. In the context of Golang and service development, metrics such as response time, request count, errors, memory, and CPU usage are typically collected.

Tools and libraries often used for collecting and exporting metrics include:

• Prometheus — a monitoring and metrics collection system supporting a pull model.
• OpenTelemetry — a standard for collecting telemetry data (metrics, logs, traces).
• Go client libraries — for example, prometheus/client_golang for integration with Prometheus.

Example of using Prometheus in Go:

import (
    "github.com/prometheus/client_golang/prometheus"
    "github.com/prometheus/client_golang/prometheus/promhttp"
    "net/http"
)

var (
    requestCount = prometheus.NewCounterVec(
        prometheus.CounterOpts{
            Name: "http_requests_total",
            Help: "Total number of HTTP requests",
        },
        []string{"path"},
    )
)

func init() {
    prometheus.MustRegister(requestCount)
}

func handler(w http.ResponseWriter, r *http.Request) {
    requestCount.WithLabelValues(r.URL.Path).Inc()
    w.Write([]byte("Hello, metrics!"))
}

func main() {
    http.HandleFunc("/", handler)
    http.Handle("/metrics", promhttp.Handler())
    http.ListenAndServe(":8080", nil)
}

Thus, metrics help monitor the application's state and respond promptly to issues.