OCaml client library for Prometheus monitoring

To run services reliably, it is useful if they can report various metrics (for example, heap size, queue lengths, number of warnings logged, etc).

A monitoring service can be configured to collect this data regularly. The data can be graphed to help understand the performance of the service over time, or to help debug problems quickly. It can also be used to send alerts if a service is down or behaving poorly.

This repository contains code to report metrics to a Prometheus monitoring server.

Use by libraries

Library authors should define a set of metrics that may be useful. For example, the DataKitCI cache module defines several metrics like this:

module Metrics = struct
  open Prometheus

  let namespace = "DataKitCI"
  let subsystem = "cache"

  let builds_started_total =
    let help = "Total number of builds started" in
    Counter.v_label ~help ~label_name:"name" ~namespace ~subsystem "builds_started_total"

  let builds_succeeded_total =
    let help = "Total number of builds that succeeded" in
    Counter.v_label ~help ~label_name:"name" ~namespace ~subsystem "builds_succeeded_total"

  let builds_failed_total =
    let help = "Total number of builds that failed" in
    Counter.v_label ~help ~label_name:"name" ~namespace ~subsystem "builds_failed_total"

  [...]
end

Each of these metrics has a name label, which allows the reports to be further broken down by the type of thing being built.

When (for example) a build succeeds, the CI does:

Prometheus.Counter.inc_one (Metrics.builds_succeeded_total build_type)

Use by applications

Applications can enable metric reporting using the prometheus-app opam package. This depends on cohttp and can serve the metrics collected above over HTTP.

The prometheus-app.unix ocamlfind library provides the Prometheus_unix module, which includes a cmdliner option and pre-configured web-server. See the examples/example.ml program for an example, which can be run as:

$ dune exec -- examples/example.exe --listen-prometheus=9090
If run with the option --listen-prometheus=9090, this program serves metrics at
http://localhost:9090/metrics
Tick!
Tick!
...

Unikernels can use Prometheus_app instead of Prometheus_unix to avoid the Unix dependency.

Lwt collectors

The prometheus-lwt opam package provides Prometheus_lwt with collectors that may suspend before producing their samples, and also Lwt versions of the timing helpers.

A future release will remove Lwt from the prometheus core. Existing code using the core's Lwt-typed functions should migrate to Prometheus_lwt, or to the synchronous variants such as Gauge.set_time now. Code will then keep working unchanged when the core switch happens.

API docs

Generated API documentation is available at https://mirage.github.io/prometheus/.

Licensing

This code is licensed under the Apache License, Version 2.0. See LICENSE for the full license text.