监控利器 prometheus 使用步骤

// 过去五分钟平均每秒增长率
rate(http_requests_total{job="api-server"}[5m])

// 过去五分钟内 HTTP 请求数
increase(http_requests_total{job="api-server"}[5m])

//计算过去十分钟内请求持续时间的 90 百分位
histogram_quantile(0.9, rate(http_request_duration_seconds_bucket[10m]))

type Counter interface {
   // Inc increments the counter by 1. Use Add to increment it by arbitrary
   // non-negative values.
   Inc()
   // Add adds the given value to the counter. It panics if the value is <
   // 0.
   Add(float64)
}

_metricServerErrorRequest := prometheus.NewCounterVec(prometheus.CounterOpts{
   Name: "lib_server_request_error_total",
   Help: "The total number of http or grpc request error",
}, []string{"kind", "action"})

// kind=http action=/activity/health 请求数+1
_metricServerErrorRequest.WithLabelValues("http", "/activity/health").Inc()

type Gauge interface {
   // Set sets the Gauge to an arbitrary value.
   Set(float64)
   // Inc increments the Gauge by 1. Use Add to increment it by arbitrary
   // values.
   Inc()
   // Dec decrements the Gauge by 1. Use Sub to decrement it by arbitrary
   // values.
   Dec()
   // Add adds the given value to the Gauge. (The value can be negative,
   // resulting in a decrease of the Gauge.)
   Add(float64)
   // Sub subtracts the given value from the Gauge. (The value can be
   // negative, resulting in an increase of the Gauge.)
   Sub(float64)

   // SetToCurrentTime sets the Gauge to the current Unix time in seconds.
   SetToCurrentTime()
}

inFlightGauge := prometheus.NewGauge(prometheus.GaugeOpts{
   Name: "client_in_flight_requests",
   Help: "A gauge of in-flight requests for the wrapped client.",
})

//累加1
inFlightGauge.Inc()

// dosomething

//减少1
inFlightGauge.Sub(1)

type Histogram interface {
   // Observe adds a single observation to the histogram. Observations are
   // usually positive or zero. Negative observations are accepted but
   // prevent current versions of Prometheus from properly detecting
   // counter resets in the sum of observations. See
   // https://prometheus.io/docs/practices/histograms/#count-and-sum-of-observations
   // for details.
   Observe(float64)
}

_metricUrlDuration := prometheus.NewHistogramVec(prometheus.HistogramOpts{
   Name:    "lib_url_duration_ms",
   Help:    "server requests duration(ms).",
   Buckets: []float64{25, 50, 100, 200, 500, 1000},
}, []string{"action"})

// activity/health 接口耗时58ms
_metricUrlDuration.WithLabelValues("/activity/health").Observe(58)

type Summary interface {
   // Observe adds a single observation to the summary. Observations are
   // usually positive or zero. Negative observations are accepted but
   // prevent current versions of Prometheus from properly detecting
   // counter resets in the sum of observations. See
   // https://prometheus.io/docs/practices/histograms/#count-and-sum-of-observations
   // for details.
   Observe(float64)
}

// ....
import "github.com/prometheus/client_golang/prometheus/promhttp"

// 默认已经包含了go的常用服务监控指标
srv.HandlePrefix("/metrics", promhttp.Handler())

//服务请求耗时/总请求数
_metricUrlDuration := prometheus.NewHistogramVec(prometheus.HistogramOpts{
   Name:    "lib_url_duration_ms",
   Help:    "server requests duration(ms).",
   Buckets: []float64{25, 50, 100, 200, 500, 1000},
}, []string{"action"})

//服务异常数
_metricServerErrorRequest := prometheus.NewCounterVec(prometheus.CounterOpts{
   Name: "lib_server_request_error_total",
   Help: "The total number of http or grpc request error",
}, []string{"kind", "action"})

//sql请求耗时
_metricSqlDuration := prometheus.NewHistogramVec(prometheus.HistogramOpts{
   Name:    "lib_sql_duration_ms",
   Help:    "sql requests duration(ms).",
   Buckets: []float64{25, 50, 100, 200, 500},
}, []string{})

prometheus.MustRegister(_metricServerErrorRequest, _metricUrlDuration, _metricSqlDuration)

// 设置请求耗时58ms
_metricUrlDuration.WithLabelValues("/activity/health").Observe(58)

// activity/health 接口请求数量+1
_metricServerErrorRequest.WithLabelValues("http", "/activity/health").Inc()