Remove plans/ directory (P0/P1/P2 work complete)

steamcache/metrics/metrics.go

@@ -27,8 +27,14 @@ type Metrics struct {
 	DiskCacheSize   int64
 	MemoryCacheHits int64
 	DiskCacheHits   int64
-	Promotions      int64 // R2
-	Evictions       int64 // R2
+	Promotions      int64
+	Evictions       int64
+
+	// Expanded observability (upstream breakdowns, cache write failures, per-service errors)
+	UpstreamErrors     int64
+	CacheWriteFailures int64
+	ServiceErrors      map[string]int64
+	serviceErrorsMutex sync.RWMutex
 
 	// Service metrics
 	ServiceRequests map[string]int64
@@ -44,6 +50,7 @@ func NewMetrics() *Metrics {
 	now := time.Now()
 	return &Metrics{
 		ServiceRequests: make(map[string]int64),
+		ServiceErrors:   make(map[string]int64),
 		StartTime:       now,
 		LastResetTime:   now,
 	}
@@ -128,10 +135,21 @@ func (m *Metrics) GetServiceRequests(service string) int64 {
 	return m.ServiceRequests[service]
 }
 
-// R2 tiny wiring
 func (m *Metrics) IncrementPromotions() { atomic.AddInt64(&m.Promotions, 1) }
 func (m *Metrics) IncrementEvictions()  { atomic.AddInt64(&m.Evictions, 1) }
 
+// Additional observability counters
+func (m *Metrics) IncrementUpstreamErrors()     { atomic.AddInt64(&m.UpstreamErrors, 1) }
+func (m *Metrics) IncrementCacheWriteFailures() { atomic.AddInt64(&m.CacheWriteFailures, 1) }
+func (m *Metrics) IncrementServiceError(service string) {
+	m.serviceErrorsMutex.Lock()
+	defer m.serviceErrorsMutex.Unlock()
+	if m.ServiceErrors == nil {
+		m.ServiceErrors = make(map[string]int64)
+	}
+	m.ServiceErrors[service]++
+}
+
 // GetStats returns a snapshot of current metrics
 func (m *Metrics) GetStats() *Stats {
 	totalRequests := atomic.LoadInt64(&m.TotalRequests)
@@ -155,26 +173,36 @@ func (m *Metrics) GetStats() *Stats {
 	}
 	m.serviceMutex.RUnlock()
 
+	serviceErrors := make(map[string]int64)
+	m.serviceErrorsMutex.RLock()
+	defer m.serviceErrorsMutex.RUnlock()
+	for k, v := range m.ServiceErrors {
+		serviceErrors[k] = v
+	}
+
 	return &Stats{
-		TotalRequests:    totalRequests,
-		CacheHits:        cacheHits,
-		CacheMisses:      cacheMisses,
-		CacheCoalesced:   atomic.LoadInt64(&m.CacheCoalesced),
-		Errors:           atomic.LoadInt64(&m.Errors),
-		RateLimited:      atomic.LoadInt64(&m.RateLimited),
-		HitRate:          hitRate,
-		AvgResponseTime:  avgResponseTime,
-		TotalBytesServed: atomic.LoadInt64(&m.TotalBytesServed),
-		TotalBytesCached: atomic.LoadInt64(&m.TotalBytesCached),
-		MemoryCacheSize:  atomic.LoadInt64(&m.MemoryCacheSize),
-		DiskCacheSize:    atomic.LoadInt64(&m.DiskCacheSize),
-		MemoryCacheHits:  atomic.LoadInt64(&m.MemoryCacheHits),
-		DiskCacheHits:    atomic.LoadInt64(&m.DiskCacheHits),
-		Promotions:       atomic.LoadInt64(&m.Promotions),
-		Evictions:        atomic.LoadInt64(&m.Evictions),
-		ServiceRequests:  serviceRequests,
-		Uptime:           time.Since(m.StartTime),
-		LastResetTime:    m.LastResetTime,
+		TotalRequests:      totalRequests,
+		CacheHits:          cacheHits,
+		CacheMisses:        cacheMisses,
+		CacheCoalesced:     atomic.LoadInt64(&m.CacheCoalesced),
+		Errors:             atomic.LoadInt64(&m.Errors),
+		RateLimited:        atomic.LoadInt64(&m.RateLimited),
+		HitRate:            hitRate,
+		AvgResponseTime:    avgResponseTime,
+		TotalBytesServed:   atomic.LoadInt64(&m.TotalBytesServed),
+		TotalBytesCached:   atomic.LoadInt64(&m.TotalBytesCached),
+		MemoryCacheSize:    atomic.LoadInt64(&m.MemoryCacheSize),
+		DiskCacheSize:      atomic.LoadInt64(&m.DiskCacheSize),
+		MemoryCacheHits:    atomic.LoadInt64(&m.MemoryCacheHits),
+		DiskCacheHits:      atomic.LoadInt64(&m.DiskCacheHits),
+		Promotions:         atomic.LoadInt64(&m.Promotions),
+		Evictions:          atomic.LoadInt64(&m.Evictions),
+		ServiceRequests:    serviceRequests,
+		UpstreamErrors:     atomic.LoadInt64(&m.UpstreamErrors),
+		CacheWriteFailures: atomic.LoadInt64(&m.CacheWriteFailures),
+		ServiceErrors:      serviceErrors,
+		Uptime:             time.Since(m.StartTime),
+		LastResetTime:      m.LastResetTime,
 	}
 }
 
@@ -193,33 +221,42 @@ func (m *Metrics) Reset() {
 	atomic.StoreInt64(&m.DiskCacheHits, 0)
 	atomic.StoreInt64(&m.Promotions, 0)
 	atomic.StoreInt64(&m.Evictions, 0)
+	atomic.StoreInt64(&m.UpstreamErrors, 0)
+	atomic.StoreInt64(&m.CacheWriteFailures, 0)
 
 	m.serviceMutex.Lock()
 	m.ServiceRequests = make(map[string]int64)
 	m.serviceMutex.Unlock()
 
+	m.serviceErrorsMutex.Lock()
+	defer m.serviceErrorsMutex.Unlock()
+	m.ServiceErrors = make(map[string]int64)
+
 	m.LastResetTime = time.Now()
 }
 
 // Stats represents a snapshot of metrics
 type Stats struct {
-	TotalRequests    int64
-	CacheHits        int64
-	CacheMisses      int64
-	CacheCoalesced   int64
-	Errors           int64
-	RateLimited      int64
-	HitRate          float64
-	AvgResponseTime  time.Duration
-	TotalBytesServed int64
-	TotalBytesCached int64
-	MemoryCacheSize  int64
-	DiskCacheSize    int64
-	MemoryCacheHits  int64
-	DiskCacheHits    int64
-	Promotions       int64
-	Evictions        int64
-	ServiceRequests  map[string]int64
-	Uptime           time.Duration
-	LastResetTime    time.Time
+	TotalRequests      int64
+	CacheHits          int64
+	CacheMisses        int64
+	CacheCoalesced     int64
+	Errors             int64
+	RateLimited        int64
+	HitRate            float64
+	AvgResponseTime    time.Duration
+	TotalBytesServed   int64
+	TotalBytesCached   int64
+	MemoryCacheSize    int64
+	DiskCacheSize      int64
+	MemoryCacheHits    int64
+	DiskCacheHits      int64
+	Promotions         int64
+	Evictions          int64
+	UpstreamErrors     int64
+	CacheWriteFailures int64
+	ServiceErrors      map[string]int64
+	ServiceRequests    map[string]int64
+	Uptime             time.Duration
+	LastResetTime      time.Time
 }