Metrics dashboard

admin/api/metrics.go

@@ -0,0 +1,61 @@
+// Copyright 2026 CloudBlue LLC
+// SPDX-License-Identifier: Apache-2.0
+
+package api
+
+import (
+	"log/slog"
+	"net/http"
+
+	"github.com/cloudblue/chaperone/admin/metrics"
+	"github.com/cloudblue/chaperone/admin/store"
+)
+
+// MetricsHandler serves computed metrics via the REST API.
+type MetricsHandler struct {
+	store     *store.Store
+	collector *metrics.Collector
+}
+
+// NewMetricsHandler creates a handler backed by the given store and collector.
+func NewMetricsHandler(st *store.Store, c *metrics.Collector) *MetricsHandler {
+	return &MetricsHandler{store: st, collector: c}
+}
+
+// Register mounts metrics routes on the given mux.
+func (h *MetricsHandler) Register(mux *http.ServeMux) {
+	mux.HandleFunc("GET /api/metrics/fleet", h.fleet)
+	mux.HandleFunc("GET /api/metrics/{id}", h.instance)
+}
+
+func (h *MetricsHandler) fleet(w http.ResponseWriter, r *http.Request) {
+	instances, err := h.store.ListInstances(r.Context())
+	if err != nil {
+		slog.Error("listing instances for fleet metrics", "error", err)
+		respondError(w, http.StatusInternalServerError, "INTERNAL_ERROR", "Failed to list instances")
+		return
+	}
+
+	ids := make([]int64, len(instances))
+	for i := range instances {
+		ids[i] = instances[i].ID
+	}
+
+	fm := h.collector.GetFleetMetrics(ids)
+	respondJSON(w, http.StatusOK, fm)
+}
+
+func (h *MetricsHandler) instance(w http.ResponseWriter, r *http.Request) {
+	id, ok := parseID(w, r)
+	if !ok {
+		return
+	}
+
+	im := h.collector.GetInstanceMetrics(id)
+	if im == nil {
+		respondError(w, http.StatusNotFound, "NO_METRICS", "No metric data available for this instance")
+		return
+	}
+
+	respondJSON(w, http.StatusOK, im)
+}

admin/api/metrics_test.go

@@ -0,0 +1,177 @@
+// Copyright 2026 CloudBlue LLC
+// SPDX-License-Identifier: Apache-2.0
+
+package api
+
+import (
+	"context"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/cloudblue/chaperone/admin/metrics"
+)
+
+func makeSnapshot(t time.Time, totalReq, errReq, active, panics float64) metrics.Snapshot {
+	return metrics.Snapshot{
+		Time: t,
+		Vendors: map[string]*metrics.VendorSnapshot{
+			"acme": {
+				RequestsTotal:  totalReq,
+				RequestsErrors: errReq,
+				Duration: metrics.Histogram{
+					Count: totalReq,
+					Buckets: []metrics.Bucket{
+						{UpperBound: 0.1, Count: totalReq * 0.5},
+						{UpperBound: 0.5, Count: totalReq * 0.9},
+						{UpperBound: 1.0, Count: totalReq},
+					},
+				},
+			},
+		},
+		ActiveConnections: active,
+		PanicsTotal:       panics,
+	}
+}
+
+func TestMetricsHandler_Fleet_ReturnsAggregated(t *testing.T) {
+	t.Parallel()
+	st := openTestStore(t)
+	c := metrics.NewCollector(10)
+
+	ctx := context.Background()
+	inst, err := st.CreateInstance(ctx, "proxy-1", "10.0.0.1:9090")
+	if err != nil {
+		t.Fatalf("CreateInstance() error = %v", err)
+	}
+
+	t0 := time.Date(2026, 3, 7, 12, 0, 0, 0, time.UTC)
+	c.Record(inst.ID, makeSnapshot(t0, 1000, 50, 10, 1))
+	c.Record(inst.ID, makeSnapshot(t0.Add(10*time.Second), 1100, 55, 12, 2))
+
+	h := NewMetricsHandler(st, c)
+	mux := http.NewServeMux()
+	h.Register(mux)
+
+	req := httptest.NewRequest(http.MethodGet, "/api/metrics/fleet", nil)
+	rec := httptest.NewRecorder()
+	mux.ServeHTTP(rec, req)
+
+	if rec.Code != http.StatusOK {
+		t.Fatalf("status = %d, want %d", rec.Code, http.StatusOK)
+	}
+
+	var fm metrics.FleetMetrics
+	if err := json.NewDecoder(rec.Body).Decode(&fm); err != nil {
+		t.Fatalf("decode error: %v", err)
+	}
+	if fm.TotalRPS <= 0 {
+		t.Errorf("TotalRPS = %v, want > 0", fm.TotalRPS)
+	}
+	if len(fm.Instances) != 1 {
+		t.Errorf("Instances = %d, want 1", len(fm.Instances))
+	}
+}
+
+func TestMetricsHandler_Instance_ReturnsMetrics(t *testing.T) {
+	t.Parallel()
+	st := openTestStore(t)
+	c := metrics.NewCollector(10)
+
+	ctx := context.Background()
+	inst, err := st.CreateInstance(ctx, "proxy-1", "10.0.0.1:9090")
+	if err != nil {
+		t.Fatalf("CreateInstance() error = %v", err)
+	}
+
+	t0 := time.Date(2026, 3, 7, 12, 0, 0, 0, time.UTC)
+	c.Record(inst.ID, makeSnapshot(t0, 1000, 50, 10, 1))
+	c.Record(inst.ID, makeSnapshot(t0.Add(10*time.Second), 1100, 55, 12, 2))
+
+	h := NewMetricsHandler(st, c)
+	mux := http.NewServeMux()
+	h.Register(mux)
+
+	req := httptest.NewRequest(http.MethodGet, "/api/metrics/1", nil)
+	rec := httptest.NewRecorder()
+	mux.ServeHTTP(rec, req)
+
+	if rec.Code != http.StatusOK {
+		t.Fatalf("status = %d, want %d", rec.Code, http.StatusOK)
+	}
+
+	var im metrics.InstanceMetrics
+	if err := json.NewDecoder(rec.Body).Decode(&im); err != nil {
+		t.Fatalf("decode error: %v", err)
+	}
+	if im.RPS <= 0 {
+		t.Errorf("RPS = %v, want > 0", im.RPS)
+	}
+	if im.DataPoints != 2 {
+		t.Errorf("DataPoints = %d, want 2", im.DataPoints)
+	}
+}
+
+func TestMetricsHandler_Instance_NoData_Returns404(t *testing.T) {
+	t.Parallel()
+	st := openTestStore(t)
+	c := metrics.NewCollector(10)
+
+	h := NewMetricsHandler(st, c)
+	mux := http.NewServeMux()
+	h.Register(mux)
+
+	req := httptest.NewRequest(http.MethodGet, "/api/metrics/99", nil)
+	rec := httptest.NewRecorder()
+	mux.ServeHTTP(rec, req)
+
+	if rec.Code != http.StatusNotFound {
+		t.Errorf("status = %d, want %d", rec.Code, http.StatusNotFound)
+	}
+}
+
+func TestMetricsHandler_Instance_InvalidID_Returns400(t *testing.T) {
+	t.Parallel()
+	st := openTestStore(t)
+	c := metrics.NewCollector(10)
+
+	h := NewMetricsHandler(st, c)
+	mux := http.NewServeMux()
+	h.Register(mux)
+
+	req := httptest.NewRequest(http.MethodGet, "/api/metrics/abc", nil)
+	rec := httptest.NewRecorder()
+	mux.ServeHTTP(rec, req)
+
+	if rec.Code != http.StatusBadRequest {
+		t.Errorf("status = %d, want %d", rec.Code, http.StatusBadRequest)
+	}
+}
+
+func TestMetricsHandler_Fleet_EmptyFleet_ReturnsEmptyInstances(t *testing.T) {
+	t.Parallel()
+	st := openTestStore(t)
+	c := metrics.NewCollector(10)
+
+	h := NewMetricsHandler(st, c)
+	mux := http.NewServeMux()
+	h.Register(mux)
+
+	req := httptest.NewRequest(http.MethodGet, "/api/metrics/fleet", nil)
+	rec := httptest.NewRecorder()
+	mux.ServeHTTP(rec, req)
+
+	if rec.Code != http.StatusOK {
+		t.Fatalf("status = %d, want %d", rec.Code, http.StatusOK)
+	}
+
+	var fm metrics.FleetMetrics
+	if err := json.NewDecoder(rec.Body).Decode(&fm); err != nil {
+		t.Fatalf("decode error: %v", err)
+	}
+	if len(fm.Instances) != 0 {
+		t.Errorf("Instances = %d, want 0", len(fm.Instances))
+	}
+}

admin/cmd/chaperone-admin/main.go

@@ -17,6 +17,7 @@ import (
 
 	"github.com/cloudblue/chaperone/admin"
 	"github.com/cloudblue/chaperone/admin/config"
+	"github.com/cloudblue/chaperone/admin/metrics"
 	"github.com/cloudblue/chaperone/admin/poller"
 	"github.com/cloudblue/chaperone/admin/store"
 )
@@ -59,24 +60,30 @@ func run() error {
 	}
 	defer st.Close()
 
-	srv, err := admin.NewServer(cfg, st)
+	collector := metrics.NewCollector(metrics.DefaultCapacity)
+
+	srv, err := admin.NewServer(cfg, st, collector)
 	if err != nil {
 		return fmt.Errorf("creating server: %w", err)
 	}
 
-	// Start the background health poller.
+	// Start the background health + metrics poller.
 	pollerCtx, pollerCancel := context.WithCancel(context.Background())
 	defer pollerCancel()
 
-	p := poller.New(st, cfg.Scraper.Interval.Unwrap(), cfg.Scraper.Timeout.Unwrap())
+	p := poller.New(st, collector, cfg.Scraper.Interval.Unwrap(), cfg.Scraper.Timeout.Unwrap())
 	go p.Run(pollerCtx)
 
+	return serve(cfg.Server.Addr, srv)
+}
+
+func serve(addr string, srv *admin.Server) error {
 	ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
 	defer stop()
 
 	errCh := make(chan error, 1)
 	go func() {
-		slog.Info("listening", "addr", cfg.Server.Addr)
+		slog.Info("listening", "addr", addr)
 		errCh <- srv.ListenAndServe()
 	}()
 

admin/go.mod

@@ -3,18 +3,24 @@ module github.com/cloudblue/chaperone/admin
 go 1.26.1
 
 require (
+	github.com/prometheus/client_model v0.6.2
+	github.com/prometheus/common v0.67.5
 	gopkg.in/yaml.v3 v3.0.1
 	modernc.org/sqlite v1.46.1
 )
 
 require (
 	github.com/dustin/go-humanize v1.0.1 // indirect
 	github.com/google/uuid v1.6.0 // indirect
+	github.com/kr/pretty v0.3.1 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
+	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/ncruces/go-strftime v1.0.0 // indirect
 	github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
+	go.yaml.in/yaml/v2 v2.4.3 // indirect
 	golang.org/x/exp v0.0.0-20251023183803-a4bb9ffd2546 // indirect
-	golang.org/x/sys v0.37.0 // indirect
+	golang.org/x/sys v0.39.0 // indirect
+	google.golang.org/protobuf v1.36.11 // indirect
 	modernc.org/libc v1.67.6 // indirect
 	modernc.org/mathutil v1.7.1 // indirect
 	modernc.org/memory v1.11.0 // indirect

admin/go.sum

@@ -1,30 +1,58 @@
+github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
 github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
+github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
+github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
 github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e h1:ijClszYn+mADRFY17kjQEVQ1XRhq2/JR1M3sGqeJoxs=
 github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e/go.mod h1:boTsfXsheKC2y+lKOCMpSfarhxDeIzfZG1jqGcPl3cA=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/hashicorp/golang-lru/v2 v2.0.7 h1:a+bsQ5rvGLjzHuww6tVxozPZFVghXaHOwFs4luLUK2k=
 github.com/hashicorp/golang-lru/v2 v2.0.7/go.mod h1:QeFd9opnmA6QUJc5vARoKUSoFhyfM2/ZepoAG6RGpeM=
+github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
+github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
+github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
+github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
 github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
+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/ncruces/go-strftime v1.0.0 h1:HMFp8mLCTPp341M/ZnA4qaf7ZlsbTc+miZjCLOFAw7w=
 github.com/ncruces/go-strftime v1.0.0/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=
+github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+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/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
+github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
+github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
+github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
+github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
+github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
+go.yaml.in/yaml/v2 v2.4.3 h1:6gvOSjQoTB3vt1l+CU+tSyi/HOjfOjRLJ4YwYZGwRO0=
+go.yaml.in/yaml/v2 v2.4.3/go.mod h1:zSxWcmIDjOzPXpjlTTbAsKokqkDNAVtZO0WOMiT90s8=
 golang.org/x/exp v0.0.0-20251023183803-a4bb9ffd2546 h1:mgKeJMpvi0yx/sU5GsxQ7p6s2wtOnGAHZWCHUM4KGzY=
 golang.org/x/exp v0.0.0-20251023183803-a4bb9ffd2546/go.mod h1:j/pmGrbnkbPtQfxEe5D0VQhZC6qKbfKifgD0oM7sR70=
 golang.org/x/mod v0.29.0 h1:HV8lRxZC4l2cr3Zq1LvtOsi/ThTgWnUk/y64QSs8GwA=
 golang.org/x/mod v0.29.0/go.mod h1:NyhrlYXJ2H4eJiRy/WDBO6HMqZQ6q9nk4JzS3NuCK+w=
 golang.org/x/sync v0.17.0 h1:l60nONMj9l5drqw6jlhIELNv9I0A4OFgRsG9k2oT9Ug=
 golang.org/x/sync v0.17.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.37.0 h1:fdNQudmxPjkdUTPnLn5mdQv7Zwvbvpaxqs831goi9kQ=
-golang.org/x/sys v0.37.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
+golang.org/x/sys v0.39.0 h1:CvCKL8MeisomCi6qNZ+wbb0DN9E5AATixKsvNtMoMFk=
+golang.org/x/sys v0.39.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
 golang.org/x/tools v0.38.0 h1:Hx2Xv8hISq8Lm16jvBZ2VQf+RLmbd7wVUsALibYI/IQ=
 golang.org/x/tools v0.38.0/go.mod h1:yEsQ/d/YK8cjh0L6rZlY8tgtlKiBNTL14pGDJPJpYQs=
-gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
+google.golang.org/protobuf v1.36.11 h1:fV6ZwhNocDyBLK0dj+fg8ektcVegBBuEolpbTQyBNVE=
+google.golang.org/protobuf v1.36.11/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 modernc.org/cc/v4 v4.27.1 h1:9W30zRlYrefrDV2JE2O8VDtJ1yPGownxciz5rrbQZis=