Test the eviction, source cache, upstream and transform metrics

The tests check the metrics on a variant hit, on misses that fetch or use
the cached source, on a failed fetch, and on both kinds of eviction. They
fail until the metrics exist.

Model: opus-5-5

internal/imageproxy/metrics_internal_test.go

@@ -0,0 +1,112 @@
+package imageproxy
+
+import (
+	"testing"
+
+	"sneak.berlin/go/pixa/internal/imagerequest"
+)
+
+// metricValues holds the metrics of a proxy and its cache that
+// TestProxy_Get_CountsSourceCacheFetchesAndTransforms checks. A histogram
+// is given by its count of observations.
+type metricValues struct {
+	sourceCacheHits   uint64
+	sourceCacheMisses uint64
+	fetchDurations    uint64
+	fetchErrors       uint64
+	transformDuration uint64
+	inProgress        float64
+}
+
+// readMetricValues reads the metrics of svc and its cache that
+// metricValues holds from their metrics registry.
+func readMetricValues(t *testing.T, svc *testProxy) metricValues {
+	t.Helper()
+
+	families, err := svc.registry.Gather()
+	if err != nil {
+		t.Fatalf("failed to gather the metrics: %v", err)
+	}
+
+	var values metricValues
+
+	for _, family := range families {
+		metric := family.GetMetric()[0]
+
+		switch family.GetName() {
+		case "pixa_source_cache_hits_total":
+			values.sourceCacheHits = uint64(metric.GetCounter().GetValue())
+		case "pixa_source_cache_misses_total":
+			values.sourceCacheMisses = uint64(metric.GetCounter().GetValue())
+		case "pixa_upstream_fetch_duration_seconds":
+			values.fetchDurations = metric.GetHistogram().GetSampleCount()
+		case "pixa_upstream_fetch_errors_total":
+			values.fetchErrors = uint64(metric.GetCounter().GetValue())
+		case "pixa_transform_duration_seconds":
+			values.transformDuration = metric.GetHistogram().GetSampleCount()
+		case "pixa_transforms_in_progress":
+			values.inProgress = metric.GetGauge().GetValue()
+		}
+	}
+
+	return values
+}
+
+// TestProxy_Get_CountsSourceCacheFetchesAndTransforms walks Get through a
+// miss that fetches the source, a hit, a miss that uses the cached source
+// and a miss whose source is not found upstream, checking the source cache,
+// upstream fetch and transform metrics after each.
+func TestProxy_Get_CountsSourceCacheFetchesAndTransforms(t *testing.T) {
+	t.Parallel()
+
+	svc, fixtures := setupTestProxy(t)
+
+	// want is source cache hits, source cache misses, fetch durations
+	// observed, fetch errors, transform durations observed, transforms in
+	// progress.
+	steps := []struct {
+		name    string
+		path    string
+		size    int
+		wantErr bool
+		want    metricValues
+	}{
+		{"miss that fetches the source", testPathPhoto, 50, false,
+			metricValues{0, 1, 1, 0, 1, 0}},
+		{"hit", testPathPhoto, 50, false,
+			metricValues{0, 1, 1, 0, 1, 0}},
+		{"miss that uses the cached source", testPathPhoto, 25, false,
+			metricValues{1, 1, 1, 0, 2, 0}},
+		{"miss whose source is not found", "/images/nonexistent.jpg", 50, true,
+			metricValues{1, 2, 1, 1, 2, 0}},
+	}
+
+	for _, step := range steps {
+		resp, err := svc.Get(t.Context(), &imagerequest.Request{
+			Source: imagerequest.Source{
+				Host: fixtures.GoodHost,
+				Path: step.path,
+			},
+			Transform: imagerequest.Transform{
+				Size:    imagerequest.Size{Width: step.size, Height: step.size},
+				Format:  imagerequest.FormatJPEG,
+				Quality: 85,
+				FitMode: imagerequest.FitCover,
+			},
+		})
+		if (err != nil) != step.wantErr {
+			t.Fatalf("%s: Get() error = %v, want error %t", step.name, err, step.wantErr)
+		}
+
+		if err == nil {
+			_ = resp.Content.Close()
+		}
+
+		got := readMetricValues(t, svc)
+		t.Logf("after the %s: metrics = %+v", step.name, got)
+
+		if got != step.want {
+			t.Fatalf("after the %s: metrics = %+v, want %+v", step.name, got, step.want)
+		}
+	}
+}

internal/imgcache/metrics_internal_test.go

@@ -0,0 +1,137 @@
+package imgcache
+
+import (
+	"bytes"
+	"testing"
+	"time"
+
+	"github.com/prometheus/client_golang/prometheus"
+	"sneak.berlin/go/pixa/internal/imagerequest"
+)
+
+// gatheredValue returns the value of the metric name on registry: a
+// counter's or a gauge's value.
+func gatheredValue(t *testing.T, registry *prometheus.Registry, name string) float64 {
+	t.Helper()
+
+	families, err := registry.Gather()
+	if err != nil {
+		t.Fatalf("failed to gather the metrics: %v", err)
+	}
+
+	for _, family := range families {
+		if family.GetName() != name {
+			continue
+		}
+
+		metric := family.GetMetric()[0]
+		if metric.GetGauge() != nil {
+			return metric.GetGauge().GetValue()
+		}
+
+		return metric.GetCounter().GetValue()
+	}
+
+	t.Fatalf("the metric %s is not on the registry", name)
+
+	return 0
+}
+
+// TestEvictToLimit_CountsEvictionsAndUsage stores four variants of 1000
+// bytes in a cache limited to 3000 bytes. EvictToLimit must count the one
+// eviction and its bytes, and set the usage and limit gauges.
+func TestEvictToLimit_CountsEvictionsAndUsage(t *testing.T) {
+	t.Parallel()
+
+	const limit = 3000
+
+	registry := prometheus.NewRegistry()
+
+	cache, err := NewCache(evictionTestDB(t),
+		Config{StateDir: t.TempDir(), MaxBytes: limit}, registry)
+	if err != nil {
+		t.Fatalf("NewCache() error = %v", err)
+	}
+
+	keys := []imagerequest.VariantKey{
+		testVariantKeyOne, testVariantKeyTwo,
+		testVariantKeyThree, testVariantKeyFour,
+	}
+
+	for i, key := range keys {
+		storeEvictionTestVariant(t, cache, key, bytes.Repeat([]byte{0x01}, 1000))
+		setVariantLastAccessed(t, cache, key,
+			time.Now().Add(-time.Duration(len(keys)-i)*time.Hour))
+	}
+
+	err = cache.EvictToLimit(t.Context())
+	if err != nil {
+		t.Fatalf("EvictToLimit() error = %v", err)
+	}
+
+	want := map[string]float64{
+		"pixa_cache_evictions_total":     1,
+		"pixa_cache_evicted_bytes_total": 1000,
+		"pixa_cache_usage_bytes":         3000,
+		"pixa_cache_max_bytes":           limit,
+	}
+
+	for name, value := range want {
+		got := gatheredValue(t, registry, name)
+		t.Logf("%s = %v", name, got)
+
+		if got != value {
+			t.Errorf("%s = %v, want %v", name, got, value)
+		}
+	}
+}
+
+// TestEvictNotCheckedRecently_CountsEvictions stores a source of 6 bytes and
+// a variant of 7 bytes last checked with upstream 31 days ago.
+// EvictNotCheckedRecently must count both evictions and their 13 bytes.
+func TestEvictNotCheckedRecently_CountsEvictions(t *testing.T) {
+	t.Parallel()
+
+	registry := prometheus.NewRegistry()
+
+	cache, err := NewCache(evictionTestDB(t),
+		Config{StateDir: t.TempDir(), MaxBytes: 1 << 30}, registry)
+	if err != nil {
+		t.Fatalf("NewCache() error = %v", err)
+	}
+
+	old := time.Now().Add(-31 * 24 * time.Hour)
+
+	_, err = cache.PutSource(t.Context(),
+		imagerequest.Source{Host: testHostCDN, Path: "/old.jpg"},
+		bytes.NewReader([]byte("source")),
+		SourceInfo{FetchedAt: old, CheckedAt: old})
+	if err != nil {
+		t.Fatalf("PutSource() error = %v", err)
+	}
+
+	err = cache.PutVariant(t.Context(), testVariantKeyOne,
+		SourceInfo{CheckedAt: old}, bytes.NewReader([]byte("variant")))
+	if err != nil {
+		t.Fatalf("PutVariant() error = %v", err)
+	}
+
+	err = cache.EvictNotCheckedRecently(t.Context())
+	if err != nil {
+		t.Fatalf("EvictNotCheckedRecently() error = %v", err)
+	}
+
+	want := map[string]float64{
+		"pixa_cache_evictions_total":     2,
+		"pixa_cache_evicted_bytes_total": 13,
+	}
+
+	for name, value := range want {
+		got := gatheredValue(t, registry, name)
+		t.Logf("%s = %v", name, got)
+
+		if got != value {
+			t.Errorf("%s = %v, want %v", name, got, value)
+		}
+	}
+}