feat: add prometheus endpoint

cmd/config/config_env.go

@@ -171,11 +171,20 @@ func envToOtelConfig() (*otel.Config, error) {
 	cfg := &otel.Config{}
 
 	metricsEndpoint := viper.GetString("PGSTREAM_METRICS_ENDPOINT")
-	if metricsEndpoint != "" {
-		cfg.Metrics = &otel.MetricsConfig{
-			Endpoint:           metricsEndpoint,
-			CollectionInterval: viper.GetDuration("PGSTREAM_METRICS_COLLECTION_INTERVAL"),
+	prometheusEnabled := viper.GetBool("PGSTREAM_METRICS_PROMETHEUS_ENABLED")
+	if metricsEndpoint != "" || prometheusEnabled {
+		metricsCfg := &otel.MetricsConfig{}
+		if metricsEndpoint != "" {
+			metricsCfg.Endpoint = metricsEndpoint
+			metricsCfg.CollectionInterval = viper.GetDuration("PGSTREAM_METRICS_COLLECTION_INTERVAL")
 		}
+		if prometheusEnabled {
+			metricsCfg.Prometheus = &otel.PrometheusConfig{
+				Enabled:  prometheusEnabled,
+				Endpoint: viper.GetString("PGSTREAM_METRICS_PROMETHEUS_ENDPOINT"),
+			}
+		}
+		cfg.Metrics = metricsCfg
 	}
 
 	tracesEndpoint := viper.GetString("PGSTREAM_TRACES_ENDPOINT")

cmd/config/config_yaml.go

@@ -43,8 +43,14 @@ type HealthConfig struct {
 }
 
 type MetricsConfig struct {
-	Endpoint           string `mapstructure:"endpoint" yaml:"endpoint"`
-	CollectionInterval int    `mapstructure:"collection_interval" yaml:"collection_interval"`
+	Prometheus         *PrometheusConfig `mapstructure:"prometheus" yaml:"prometheus"`
+	Endpoint           string            `mapstructure:"endpoint" yaml:"endpoint"`
+	CollectionInterval int               `mapstructure:"collection_interval" yaml:"collection_interval"`
+}
+
+type PrometheusConfig struct {
+	Enabled  bool   `mapstructure:"enabled" yaml:"enabled"`
+	Endpoint string `mapstructure:"endpoint" yaml:"endpoint"`
 }
 
 type TracesConfig struct {
@@ -400,10 +406,18 @@ func (c *InstrumentationConfig) toHealthConfig() *health.Config {
 func (c *InstrumentationConfig) toOtelConfig() (*otel.Config, error) {
 	cfg := &otel.Config{}
 	if c.Metrics != nil {
-		cfg.Metrics = &otel.MetricsConfig{
+		metricsCfg := &otel.MetricsConfig{
 			Endpoint:           c.Metrics.Endpoint,
 			CollectionInterval: time.Duration(c.Metrics.CollectionInterval) * time.Second,
+			Prometheus:         nil,
+		}
+		if c.Metrics.Prometheus != nil {
+			metricsCfg.Prometheus = &otel.PrometheusConfig{
+				Enabled:  c.Metrics.Prometheus.Enabled,
+				Endpoint: c.Metrics.Prometheus.Endpoint,
+			}
 		}
+		cfg.Metrics = metricsCfg
 	}
 
 	if c.Traces != nil {

cmd/health_cmd.go

@@ -12,6 +12,7 @@ import (
 	"github.com/xataio/pgstream/internal/phase"
 	pglib "github.com/xataio/pgstream/internal/postgres"
 	loglib "github.com/xataio/pgstream/pkg/log"
+	"github.com/xataio/pgstream/pkg/otel"
 )
 
 const (
@@ -40,6 +41,11 @@ func startHealthServer(ctx context.Context, logger loglib.Logger, sourcePostgres
 		return func() {}, nil
 	}
 
+	instrumentationCfg, err := config.ParseInstrumentationConfig()
+	if err != nil {
+		return nil, fmt.Errorf("parsing instrumentation config: %w", err)
+	}
+
 	opts := []health.Option{
 		health.WithLogger(logger),
 		health.WithVersion(version()),
@@ -60,7 +66,11 @@ func startHealthServer(ctx context.Context, logger loglib.Logger, sourcePostgres
 		opts = append(opts, health.WithReadinessCheck(pool.Ping))
 	}
 
-	srv := health.NewServer(*cfg, opts...)
+	var metricsCfg *otel.MetricsConfig
+	if instrumentationCfg.Metrics != nil {
+		metricsCfg = instrumentationCfg.Metrics
+	}
+	srv := health.NewServer(*cfg, metricsCfg, opts...)
 	if err := srv.Listen(); err != nil {
 		if pool != nil {
 			pool.Close(context.Background())

docs/Observability.md

@@ -219,6 +219,32 @@ PGSTREAM_TRACES_ENDPOINT="http://localhost:4317"
 PGSTREAM_TRACES_SAMPLE_RATIO=0.5
 ```
 
+### Prometheus Scraping (Pull-based)
+
+If you'd rather scrape metrics directly than deploy an OTel collector, enable the Prometheus exporter. It's served from the existing [health endpoint](configuration.md#instrumentation) server, so no separate port or process is needed:
+
+```yaml
+instrumentation:
+  health:
+    enabled: true
+    address: "0.0.0.0:9910" # defaults to localhost:9910
+  metrics:
+    prometheus:
+      enabled: true
+      endpoint: "/metrics" # defaults to /metrics
+```
+
+Or using environment variables:
+
+```sh
+PGSTREAM_HEALTH_CHECK_ENABLED=true
+PGSTREAM_HEALTH_CHECK_ADDRESS="0.0.0.0:9910"
+PGSTREAM_METRICS_PROMETHEUS_ENABLED=true
+PGSTREAM_METRICS_PROMETHEUS_ENDPOINT="/metrics"
+```
+
+This works standalone — `metrics.endpoint` is not required, so you get pgstream's metrics (including the [Go runtime metrics](#go-runtime-metrics)) without an OTLP collector in the loop. It can also be combined with `metrics.endpoint` to export to both a Prometheus scraper and an OTLP collector at the same time.
+
 ## Monitoring Dashboards
 
 ### Pre-built pgstream Dashboard

docs/configuration.md

@@ -11,6 +11,9 @@ instrumentation:
   metrics:
     endpoint: "0.0.0.0:4317"
     collection_interval: 60 # collection interval for metrics in seconds. Defaults to 60s
+    prometheus:
+      enabled: true # exposes a Prometheus scrape endpoint on the health server. Defaults to false
+      endpoint: "/metrics" # path the Prometheus endpoint is served on. Defaults to /metrics
   traces:
     endpoint: "0.0.0.0:4317"
     sample_ratio: 0.5 # ratio of traces that will be sampled. Must be between 0.0-1.0, where 0 is no traces sampled, and 1 is all traces sampled.
@@ -420,10 +423,12 @@ One of exponential/constant/disable retries retry policies can be provided for t
 <details>
   <summary>Metrics</summary>
 
-| Environment Variable                 | Default | Required | Description                                                            |
-| ------------------------------------ | ------- | -------- | ---------------------------------------------------------------------- |
-| PGSTREAM_METRICS_ENDPOINT            | N/A     | No       | Endpoint where the pgstream metrics will be exported to.               |
-| PGSTREAM_METRICS_COLLECTION_INTERVAL | 60s     | No       | Interval at which the pgstream metrics will be collected and exported. |
+| Environment Variable                   | Default   | Required | Description                                                                                     |
+| --------------------------------------- | --------- | -------- | ------------------------------------------------------------------------------------------------ |
+| PGSTREAM_METRICS_ENDPOINT               | N/A       | No       | Endpoint where the pgstream metrics will be pushed to via OTLP. Not required to use Prometheus.  |
+| PGSTREAM_METRICS_COLLECTION_INTERVAL    | 60s       | No       | Interval at which the pgstream metrics will be collected and exported via OTLP.                  |
+| PGSTREAM_METRICS_PROMETHEUS_ENABLED     | False     | No       | Exposes a Prometheus scrape endpoint on the health server. Requires the health endpoint enabled. |
+| PGSTREAM_METRICS_PROMETHEUS_ENDPOINT    | /metrics  | No       | Path the Prometheus endpoint is served on.                                                       |
 
 </details>
 
@@ -442,6 +447,8 @@ One of exponential/constant/disable retries retry policies can be provided for t
 
 Exposes `/health` (liveness, always 200), `/ready` (readiness, pings the source postgres database when configured), and `/status` (current pipeline phase: `snapshot` or `replication`). Only the `run` and `snapshot` commands start the server. Responses are JSON.
 
+When `instrumentation.metrics.prometheus.enabled` (`PGSTREAM_METRICS_PROMETHEUS_ENABLED`) is true, the server also exposes a Prometheus scrape endpoint (default path `/metrics`, configurable via `instrumentation.metrics.prometheus.endpoint` / `PGSTREAM_METRICS_PROMETHEUS_ENDPOINT`). The endpoint returns `404` when Prometheus is disabled. This lets you scrape pgstream's metrics directly, without deploying an OTel collector.
+
 | Environment Variable           | Default          | Required | Description                                                                                                  |
 | ------------------------------ | ---------------- | -------- | ------------------------------------------------------------------------------------------------------------ |
 | PGSTREAM_HEALTH_CHECK_ENABLED  | False            | No       | Enable the health endpoint server.                                                                           |

go.mod

@@ -26,6 +26,7 @@ require (
 	github.com/opensearch-project/opensearch-go v1.1.0
 	github.com/pgvector/pgvector-go v0.4.0
 	github.com/pgvector/pgvector-go/pgx v0.4.0
+	github.com/prometheus/client_golang v1.23.2
 	github.com/pterm/pterm v0.12.83
 	github.com/rs/xid v1.6.0
 	github.com/rs/zerolog v1.35.1
@@ -47,6 +48,7 @@ require (
 	go.opentelemetry.io/otel v1.44.0
 	go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc v1.44.0
 	go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.44.0
+	go.opentelemetry.io/otel/exporters/prometheus v0.66.0
 	go.opentelemetry.io/otel/metric v1.44.0
 	go.opentelemetry.io/otel/sdk v1.44.0
 	go.opentelemetry.io/otel/sdk/metric v1.44.0
@@ -71,6 +73,7 @@ require (
 	github.com/Masterminds/semver/v3 v3.3.1 // indirect
 	github.com/Microsoft/go-winio v0.6.2 // indirect
 	github.com/OneOfOne/xxhash v1.2.8 // indirect
+	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/bytedance/gopkg v0.1.3 // indirect
 	github.com/bytedance/sonic/loader v0.5.1 // indirect
 	github.com/cenkalti/backoff/v5 v5.0.3 // indirect
@@ -132,6 +135,7 @@ require (
 	github.com/moby/sys/user v0.4.0 // indirect
 	github.com/moby/sys/userns v0.1.0 // indirect
 	github.com/moby/term v0.5.2 // indirect
+	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/nexus-rpc/sdk-go v0.3.0 // indirect
 	github.com/opencontainers/go-digest v1.0.0 // indirect
 	github.com/opencontainers/image-spec v1.1.1 // indirect
@@ -140,6 +144,10 @@ require (
 	github.com/pierrec/lz4/v4 v4.1.22 // indirect
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 // indirect
+	github.com/prometheus/client_model v0.6.2 // indirect
+	github.com/prometheus/common v0.67.5 // indirect
+	github.com/prometheus/otlptranslator v1.0.0 // indirect
+	github.com/prometheus/procfs v0.20.1 // indirect
 	github.com/redpanda-data/benthos/v4 v4.45.1 // indirect
 	github.com/rivo/uniseg v0.4.7 // indirect
 	github.com/robfig/cron v1.2.0 // indirect
@@ -174,6 +182,7 @@ require (
 	go.opentelemetry.io/proto/otlp v1.10.0 // indirect
 	go.temporal.io/api v1.45.0 // indirect
 	go.temporal.io/sdk v1.33.0 // indirect
+	go.yaml.in/yaml/v2 v2.4.4 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
 	golang.org/x/arch v0.0.0-20210923205945-b76863e36670 // indirect
 	golang.org/x/crypto v0.53.0 // indirect

go.sum

@@ -50,6 +50,8 @@ github.com/OneOfOne/xxhash v1.2.8/go.mod h1:eZbhyaAYD41SGSSsnmcpxVoRiQ/MPUTjUdII
 github.com/atomicgo/cursor v0.0.1/go.mod h1:cBON2QmmrysudxNBFthvMtN32r3jxVRIvzkUiF/RuIk=
 github.com/aws/aws-sdk-go v1.42.27/go.mod h1:OGr6lGMAKGlG9CVrYnWYDKIyb829c6EVBRjxqjmPepc=
 github.com/benbjohnson/clock v1.1.0/go.mod h1:J11/hYXuz8f4ySSvYwY0FKfm+ezbsZBKZxNJlLklBHA=
+github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
+github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
 github.com/bytedance/gopkg v0.1.3 h1:TPBSwH8RsouGCBcMBktLt1AymVo2TVsBVCY4b6TnZ/M=
 github.com/bytedance/gopkg v0.1.3/go.mod h1:576VvJ+eJgyCzdjS+c4+77QF3p7ubbtiKARP3TxducM=
 github.com/bytedance/sonic v1.15.1 h1:nJD5PmM0vY7J8CT6MxoqbVAAMhkSmV2HgRAUrrpLoOw=
@@ -165,8 +167,8 @@ github.com/gofrs/uuid/v5 v5.3.1 h1:aPx49MwJbekCzOyhZDjJVb0hx3A0KLjlbLx6p2gY0p0=
 github.com/gofrs/uuid/v5 v5.3.1/go.mod h1:CDOjlDMVAtN56jqyRUZh58JT31Tiw7/oQyEXZV+9bD8=
 github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
 github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
-github.com/golang-jwt/jwt/v5 v5.2.2 h1:Rl4B7itRWVtYIHFrSNd7vhTiz9UpLdi6gZhZ3wEeDy8=
-github.com/golang-jwt/jwt/v5 v5.2.2/go.mod h1:pqrtFR0X4osieyHYxtmOUWsAWrfe1Q5UVIyoH402zdk=
+github.com/golang-jwt/jwt/v5 v5.3.0 h1:pv4AsKCKKZuqlgs5sUmn4x8UlGa0kEVt/puTpKx9vvo=
+github.com/golang-jwt/jwt/v5 v5.3.0/go.mod h1:fxCRLWMO43lRc8nhHWY6LGqRcf+1gQWArsqaEUEa5bE=
 github.com/golang-migrate/migrate/v4 v4.19.1 h1:OCyb44lFuQfYXYLx1SCxPZQGU7mcaZ7gH9yH4jSFbBA=
 github.com/golang-migrate/migrate/v4 v4.19.1/go.mod h1:CTcgfjxhaUtsLipnLoQRWCrjYXycRz/g5+RWDuYgPrE=
 github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
@@ -271,6 +273,8 @@ github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
+github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
+github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
 github.com/labstack/echo/v4 v4.15.4 h1:DL45vVYa+BWE+XuW+zZNd9H0YEdZ80UAWJGcTVW4EVs=
 github.com/labstack/echo/v4 v4.15.4/go.mod h1:CuMetKIRwsuO/qlAgMq+KTAalwGoB/h4tC+yPdrTj1g=
 github.com/labstack/gommon v0.5.0 h1:6VSQ2NOzsnEJ5W6+84E0RbcaDDmgB6NIAzWCczTEe6c=
@@ -322,6 +326,8 @@ github.com/moby/term v0.5.2 h1:6qk3FJAFDs6i/q3W/pQ97SX192qKfZgGjCQqfCJkgzQ=
 github.com/moby/term v0.5.2/go.mod h1:d3djjFCrjnB+fl8NJux+EJzu0msscUP+f8it8hPkFLc=
 github.com/morikuni/aec v1.0.0 h1:nP9CBfwrvYnBRgY6qfDQkygYDmYwOilePFkwzv4dU8A=
 github.com/morikuni/aec v1.0.0/go.mod h1:BbKIizmSmc5MMPqRYbxO4ZU0S0+P200+tUnFx7PXmsc=
+github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
+github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
 github.com/nexus-rpc/sdk-go v0.3.0 h1:Y3B0kLYbMhd4C2u00kcYajvmOrfozEtTV/nHSnV57jA=
 github.com/nexus-rpc/sdk-go v0.3.0/go.mod h1:TpfkM2Cw0Rlk9drGkoiSMpFqflKTiQLWUNyKJjF8mKQ=
 github.com/nsf/jsondiff v0.0.0-20230430225905-43f6cf3098c1 h1:dOYG7LS/WK00RWZc8XGgcUTlTxpp3mKhdR2Q9z9HbXM=
@@ -353,7 +359,17 @@ github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRI
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 h1:o4JXh1EVt9k/+g42oCprj/FisM4qX9L3sZB3upGN2ZU=
 github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55/go.mod h1:OmDBASR4679mdNQnz2pUhc2G8CO2JrUAVFDRBDP/hJE=
+github.com/prometheus/client_golang v1.23.2 h1:Je96obch5RDVy3FDMndoUsjAhG5Edi49h0RJWRi/o0o=
+github.com/prometheus/client_golang v1.23.2/go.mod h1:Tb1a6LWHB3/SPIzCoaDXI4I8UHKeFTEQ1YCr+0Gyqmg=
 github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
+github.com/prometheus/client_model v0.6.2 h1:oBsgwpGs7iVziMvrGhE53c/GrLUsZdHnqNwqPLxwZyk=
+github.com/prometheus/client_model v0.6.2/go.mod h1:y3m2F6Gdpfy6Ut/GBsUqTWZqCUvMVzSfMLjcu6wAwpE=
+github.com/prometheus/common v0.67.5 h1:pIgK94WWlQt1WLwAC5j2ynLaBRDiinoAb86HZHTUGI4=
+github.com/prometheus/common v0.67.5/go.mod h1:SjE/0MzDEEAyrdr5Gqc6G+sXI67maCxzaT3A2+HqjUw=
+github.com/prometheus/otlptranslator v1.0.0 h1:s0LJW/iN9dkIH+EnhiD3BlkkP5QVIUVEoIwkU+A6qos=
+github.com/prometheus/otlptranslator v1.0.0/go.mod h1:vRYWnXvI6aWGpsdY/mOT/cbeVRBlPWtBNDb7kGR3uKM=
+github.com/prometheus/procfs v0.20.1 h1:XwbrGOIplXW/AU3YhIhLODXMJYyC1isLFfYCsTEycfc=
+github.com/prometheus/procfs v0.20.1/go.mod h1:o9EMBZGRyvDrSPH1RqdxhojkuXstoe4UlK79eF5TGGo=
 github.com/pterm/pterm v0.12.27/go.mod h1:PhQ89w4i95rhgE+xedAoqous6K9X+r6aSOI2eFF7DZI=
 github.com/pterm/pterm v0.12.29/go.mod h1:WI3qxgvoQFFGKGjGnJR849gU0TsEOvKn5Q8LlY1U7lg=
 github.com/pterm/pterm v0.12.30/go.mod h1:MOqLIyMOgmTDz9yorcYbcw+HsgoZo3BQfg2wtl3HEFE=
@@ -521,6 +537,8 @@ go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.44.0 h1:4YsVu3B8+3qtWYYrsUY
 go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.44.0/go.mod h1:+wnlSn0mD1ADVMe3v9Z/WIaiz6q6gL2J/ejaAmdmv80=
 go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.44.0 h1:qazEJlUOQzhCpzQpFETGby7EdqjI1wsd0W+6Gg1SCTU=
 go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.44.0/go.mod h1:fOD2Yefuxixkx3ahVNf0O/PERb6r4OlbxfATVnYvzCo=
+go.opentelemetry.io/otel/exporters/prometheus v0.66.0 h1:vkrK8PAznv2NKt2r+kdu252ccGzkEqLc2aSXbQIALYQ=
+go.opentelemetry.io/otel/exporters/prometheus v0.66.0/go.mod h1:V/UB6D3vMF/UBOL5igAsAYnk1nG/bzYYTzvsB16cy7o=
 go.opentelemetry.io/otel/metric v1.44.0 h1:1w0gILTcHdr3YI+ixLyjemwrVnsMURbTZFrSYCdDdmc=
 go.opentelemetry.io/otel/metric v1.44.0/go.mod h1:8O7hanEPBNgEMmybD3s2VBKcgWOCsA6tzHBPODAiquo=
 go.opentelemetry.io/otel/metric/x v0.66.0 h1:YkCrx1zLOChi9ZcZ6euupOcsgzbVlec7D/xoEU1+cTA=
@@ -543,6 +561,8 @@ go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
 go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
 go.uber.org/multierr v1.6.0/go.mod h1:cdWPpRnG4AhwMwsgIHip0KRBQjJy5kYEpYjJxpXp9iU=
 go.uber.org/zap v1.18.1/go.mod h1:xg/QME4nWcxGxrpdeYfq7UvYrLh66cuVKdrbD1XF/NI=
+go.yaml.in/yaml/v2 v2.4.4 h1:tuyd0P+2Ont/d6e2rl3be67goVK4R6deVxCUX5vyPaQ=
+go.yaml.in/yaml/v2 v2.4.4/go.mod h1:gMZqIpDtDqOfM0uNfy0SkpRhvUryYH0Z6wdMYcacYXQ=
 go.yaml.in/yaml/v3 v3.0.4 h1:tfq32ie2Jv2UxXFdLJdh3jXuOzWiL1fo0bu/FbuKpbc=
 go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg=
 golang.org/x/arch v0.0.0-20210923205945-b76863e36670 h1:18EFjUmQOcUvxNYSkA6jO9VAiXCnxFY6NyDX0bHDmkU=

internal/health/health.go

@@ -12,12 +12,15 @@
 	"net/http"
 	"time"
 
+	"github.com/prometheus/client_golang/prometheus/promhttp"
 	"github.com/xataio/pgstream/internal/json"
 	loglib "github.com/xataio/pgstream/pkg/log"
+	"github.com/xataio/pgstream/pkg/otel"
 )
 
 const (
-	DefaultAddress = "localhost:9910"
+	DefaultAddress            = "localhost:9910"
+	DefaultPrometheusEndpoint = "/metrics"
 
 	readinessCheckTimeout = 2 * time.Second
 	readHeaderTimeout     = 5 * time.Second
@@ -38,6 +41,7 @@
 	phaseProvider  func() string
 	listener       net.Listener
 	httpServer     *http.Server
+	metricsConfig  *otel.MetricsConfig
 }
 
 var errNotListening = errors.New("health server not initialised: call Listen first")
@@ -46,14 +50,15 @@
 
 // NewServer builds a health server from the given config. The server is not
 // started until Start() is called.
-func NewServer(cfg Config, opts ...Option) *Server {
+func NewServer(cfg Config, metricsCfg *otel.MetricsConfig, opts ...Option) *Server {
 	address := cfg.Address
 	if address == "" {
 		address = DefaultAddress
 	}
 	s := &Server{
-		logger:  loglib.NewNoopLogger(),
-		address: address,
+		logger:        loglib.NewNoopLogger(),
+		address:       address,
+		metricsConfig: metricsCfg,
 	}
 	for _, opt := range opts {
 		opt(s)
@@ -114,6 +119,14 @@
 	mux.HandleFunc("/ready", s.handleReady)
 	mux.HandleFunc("/status", s.handleStatus)
 
+	if s.isPrometheusEnabled() {
+		endpoint := DefaultPrometheusEndpoint
+		if promEndpoint := s.metricsConfig.Prometheus.Endpoint; promEndpoint != "" {
+			endpoint = promEndpoint
+		}
+		mux.HandleFunc(endpoint, s.handlePrometheus)
+	}
+
 	s.listener = ln
 	s.httpServer = &http.Server{
 		Handler:           mux,
@@ -200,3 +213,16 @@
 		s.logger.Warn(err, "health server: writing response")
 	}
 }
+
+func (s *Server) isPrometheusEnabled() bool {
+	return s.metricsConfig != nil && s.metricsConfig.Prometheus != nil && s.metricsConfig.Prometheus.Enabled
+
+}
+
+func (s *Server) handlePrometheus(w http.ResponseWriter, req *http.Request) {
+	if s.isPrometheusEnabled() {
+		promhttp.Handler().ServeHTTP(w, req)
+	} else {
+		s.writeJSON(w, http.StatusNotFound, map[string]any{})
+	}
+}