feat: phase 8 serviceadapter crd rollout (32/33 tasks)

internal/observability/metrics.go

@@ -0,0 +1,165 @@
+package observability
+
+import (
+	"fmt"
+	"sync"
+	"time"
+)
+
+// Metrics holds all Prometheus metrics for the gateway.
+type Metrics struct {
+	mu sync.RWMutex
+
+	// Request counters: request_total{route, upstream, status}
+	requestTotal map[string]int64
+
+	// Request latencies: request_duration_seconds (histogram)
+	// Stored as cumulative buckets for Prometheus text format
+	requestDuration map[string]int64 // stores duration samples in milliseconds
+	requestDurationBuckets map[string]map[float64]int64 // histogram buckets
+
+	// Bytes counters: gateway_bytes{direction, route, upstream}
+	bytesIn  map[string]int64
+	bytesOut map[string]int64
+
+	// Upstream health: upstream_health{upstream} = 1 or 0
+	upstreamHealth map[string]int
+
+	// Streaming metrics
+	streamingResponsesTotal map[string]int64
+	streamingByteCount      map[string]int64
+}
+
+// NewMetrics creates a new Metrics instance.
+func NewMetrics() *Metrics {
+	return &Metrics{
+		requestTotal:           make(map[string]int64),
+		requestDuration:        make(map[string]int64),
+		requestDurationBuckets: make(map[string]map[float64]int64),
+		bytesIn:                make(map[string]int64),
+		bytesOut:               make(map[string]int64),
+		upstreamHealth:         make(map[string]int),
+		streamingResponsesTotal: make(map[string]int64),
+		streamingByteCount:     make(map[string]int64),
+	}
+}
+
+// RecordRequest records a request with its route, upstream, status, and duration.
+func (m *Metrics) RecordRequest(route, upstream string, statusCode int, duration time.Duration) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	key := fmt.Sprintf("%s:%s:%d", route, upstream, statusCode)
+	m.requestTotal[key]++
+
+	// Record duration in milliseconds
+	durationKey := fmt.Sprintf("%s:%s", route, upstream)
+	m.requestDuration[durationKey] += int64(duration.Milliseconds())
+
+	// Record in histogram buckets
+	if _, ok := m.requestDurationBuckets[durationKey]; !ok {
+		m.requestDurationBuckets[durationKey] = make(map[float64]int64)
+	}
+
+	// Prometheus histogram buckets: .005, .01, .025, .05, .1, .25, .5, 1, 2.5, 5, 10
+	buckets := []float64{0.005, 0.01, 0.025, 0.05, 0.1, 0.25, 0.5, 1, 2.5, 5, 10}
+	durationSeconds := duration.Seconds()
+
+	for _, bucket := range buckets {
+		if durationSeconds <= bucket {
+			m.requestDurationBuckets[durationKey][bucket]++
+		}
+	}
+}
+
+// RecordBytesIn records incoming bytes.
+func (m *Metrics) RecordBytesIn(route, upstream string, bytes int64) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	key := fmt.Sprintf("%s:%s", route, upstream)
+	m.bytesIn[key] += bytes
+}
+
+// RecordBytesOut records outgoing bytes.
+func (m *Metrics) RecordBytesOut(route, upstream string, bytes int64) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	key := fmt.Sprintf("%s:%s", route, upstream)
+	m.bytesOut[key] += bytes
+}
+
+// SetUpstreamHealth sets the health status of an upstream (1 = healthy, 0 = unhealthy).
+func (m *Metrics) SetUpstreamHealth(upstream string, healthy bool) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	if healthy {
+		m.upstreamHealth[upstream] = 1
+	} else {
+		m.upstreamHealth[upstream] = 0
+	}
+}
+
+// RecordStreamingResponse records a streaming response with its total byte count and duration.
+func (m *Metrics) RecordStreamingResponse(route, upstream string, totalBytes int64, duration time.Duration) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	key := fmt.Sprintf("%s:%s", route, upstream)
+	m.streamingResponsesTotal[key]++
+	m.streamingByteCount[key] += totalBytes
+
+	// Also record as request duration
+	m.recordDuration(key, duration)
+}
+
+func (m *Metrics) recordDuration(key string, duration time.Duration) {
+	m.requestDuration[key] += int64(duration.Milliseconds())
+	
+	if _, ok := m.requestDurationBuckets[key]; !ok {
+		m.requestDurationBuckets[key] = make(map[float64]int64)
+	}
+
+	buckets := []float64{0.005, 0.01, 0.025, 0.05, 0.1, 0.25, 0.5, 1, 2.5, 5, 10}
+	durationSeconds := duration.Seconds()
+
+	for _, bucket := range buckets {
+		if durationSeconds <= bucket {
+			m.requestDurationBuckets[key][bucket]++
+		}
+	}
+}
+
+// GetMetrics returns a copy of current metrics (for testing/export).
+func (m *Metrics) GetMetrics() map[string]interface{} {
+	m.mu.RLock()
+	defer m.mu.RUnlock()
+
+	return map[string]interface{}{
+		"request_total":             m.requestTotal,
+		"request_duration":          m.requestDuration,
+		"request_duration_buckets":  m.requestDurationBuckets,
+		"bytes_in":                  m.bytesIn,
+		"bytes_out":                 m.bytesOut,
+		"upstream_health":           m.upstreamHealth,
+		"streaming_responses_total": m.streamingResponsesTotal,
+		"streaming_byte_count":      m.streamingByteCount,
+	}
+}
+
+// Reset clears all metrics (for testing).
+func (m *Metrics) Reset() {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	m.requestTotal = make(map[string]int64)
+	m.requestDuration = make(map[string]int64)
+	m.requestDurationBuckets = make(map[string]map[float64]int64)
+	m.bytesIn = make(map[string]int64)
+	m.bytesOut = make(map[string]int64)
+	m.upstreamHealth = make(map[string]int)
+	m.streamingResponsesTotal = make(map[string]int64)
+	m.streamingByteCount = make(map[string]int64)
+}