Files
steamcache2/steamcache/metrics/metrics.go
T
s1d3sw1ped 4bb8947ecf Harden production gaps + improve build usability (from 2026 review)
- C4: Propagate request context through semaphores and upstream calls
- C5: Make client rate limiter cleanup goroutine idempotent via sync.Once
- P1: Streaming response path using io.Copy instead of full materialization
- P2: Gate promotion goroutines to files >= 64KiB
- P3: Reduce global lock contention during eviction
- P4: Demote hot-path logging and compact metrics output
- R1: Add upstream URL scheme/host validation
- R4: Add cache file format version + tolerant deserialization
- Makefile: Make build-snapshot-single practical by using -short tests
- Config: Add GetDefaultConfig + Validate for better testability and R1 coverage

All changes follow the "smallest safe diff" principle from the review.
Safe test suite now builds and runs cleanly via make build-snapshot-single.

Ref: docs/reviews/steamcache2-production-hardening-review-2026-05-26.md
2026-05-26 22:39:12 -05:00

226 lines
6.2 KiB
Go

// steamcache/metrics/metrics.go
package metrics
import (
"sync"
"sync/atomic"
"time"
)
// Metrics tracks various performance and operational metrics
type Metrics struct {
// Request metrics
TotalRequests int64
CacheHits int64
CacheMisses int64
CacheCoalesced int64
Errors int64
RateLimited int64
// Performance metrics
TotalResponseTime int64 // in nanoseconds
TotalBytesServed int64
TotalBytesCached int64
// Cache metrics
MemoryCacheSize int64
DiskCacheSize int64
MemoryCacheHits int64
DiskCacheHits int64
Promotions int64 // R2
Evictions int64 // R2
// Service metrics
ServiceRequests map[string]int64
serviceMutex sync.RWMutex
// Time tracking
StartTime time.Time
LastResetTime time.Time
}
// NewMetrics creates a new metrics instance
func NewMetrics() *Metrics {
now := time.Now()
return &Metrics{
ServiceRequests: make(map[string]int64),
StartTime: now,
LastResetTime: now,
}
}
// IncrementTotalRequests increments the total request counter
func (m *Metrics) IncrementTotalRequests() {
atomic.AddInt64(&m.TotalRequests, 1)
}
// IncrementCacheHits increments the cache hit counter
func (m *Metrics) IncrementCacheHits() {
atomic.AddInt64(&m.CacheHits, 1)
}
// IncrementCacheMisses increments the cache miss counter
func (m *Metrics) IncrementCacheMisses() {
atomic.AddInt64(&m.CacheMisses, 1)
}
// IncrementCacheCoalesced increments the coalesced request counter
func (m *Metrics) IncrementCacheCoalesced() {
atomic.AddInt64(&m.CacheCoalesced, 1)
}
// IncrementErrors increments the error counter
func (m *Metrics) IncrementErrors() {
atomic.AddInt64(&m.Errors, 1)
}
// IncrementRateLimited increments the rate limited counter
func (m *Metrics) IncrementRateLimited() {
atomic.AddInt64(&m.RateLimited, 1)
}
// AddResponseTime adds response time to the total
func (m *Metrics) AddResponseTime(duration time.Duration) {
atomic.AddInt64(&m.TotalResponseTime, int64(duration))
}
// AddBytesServed adds bytes served to the total
func (m *Metrics) AddBytesServed(bytes int64) {
atomic.AddInt64(&m.TotalBytesServed, bytes)
}
// AddBytesCached adds bytes cached to the total
func (m *Metrics) AddBytesCached(bytes int64) {
atomic.AddInt64(&m.TotalBytesCached, bytes)
}
// SetMemoryCacheSize sets the current memory cache size
func (m *Metrics) SetMemoryCacheSize(size int64) {
atomic.StoreInt64(&m.MemoryCacheSize, size)
}
// SetDiskCacheSize sets the current disk cache size
func (m *Metrics) SetDiskCacheSize(size int64) {
atomic.StoreInt64(&m.DiskCacheSize, size)
}
// IncrementMemoryCacheHits increments memory cache hits
func (m *Metrics) IncrementMemoryCacheHits() {
atomic.AddInt64(&m.MemoryCacheHits, 1)
}
// IncrementDiskCacheHits increments disk cache hits
func (m *Metrics) IncrementDiskCacheHits() {
atomic.AddInt64(&m.DiskCacheHits, 1)
}
// IncrementServiceRequests increments requests for a specific service
func (m *Metrics) IncrementServiceRequests(service string) {
m.serviceMutex.Lock()
defer m.serviceMutex.Unlock()
m.ServiceRequests[service]++
}
// GetServiceRequests returns the number of requests for a service
func (m *Metrics) GetServiceRequests(service string) int64 {
m.serviceMutex.RLock()
defer m.serviceMutex.RUnlock()
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) }
// GetStats returns a snapshot of current metrics
func (m *Metrics) GetStats() *Stats {
totalRequests := atomic.LoadInt64(&m.TotalRequests)
cacheHits := atomic.LoadInt64(&m.CacheHits)
cacheMisses := atomic.LoadInt64(&m.CacheMisses)
var hitRate float64
if totalRequests > 0 {
hitRate = float64(cacheHits) / float64(totalRequests)
}
var avgResponseTime time.Duration
if totalRequests > 0 {
avgResponseTime = time.Duration(atomic.LoadInt64(&m.TotalResponseTime) / totalRequests)
}
m.serviceMutex.RLock()
serviceRequests := make(map[string]int64)
for k, v := range m.ServiceRequests {
serviceRequests[k] = v
}
m.serviceMutex.RUnlock()
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,
}
}
// Reset resets all metrics to zero
func (m *Metrics) Reset() {
atomic.StoreInt64(&m.TotalRequests, 0)
atomic.StoreInt64(&m.CacheHits, 0)
atomic.StoreInt64(&m.CacheMisses, 0)
atomic.StoreInt64(&m.CacheCoalesced, 0)
atomic.StoreInt64(&m.Errors, 0)
atomic.StoreInt64(&m.RateLimited, 0)
atomic.StoreInt64(&m.TotalResponseTime, 0)
atomic.StoreInt64(&m.TotalBytesServed, 0)
atomic.StoreInt64(&m.TotalBytesCached, 0)
atomic.StoreInt64(&m.MemoryCacheHits, 0)
atomic.StoreInt64(&m.DiskCacheHits, 0)
atomic.StoreInt64(&m.Promotions, 0)
atomic.StoreInt64(&m.Evictions, 0)
m.serviceMutex.Lock()
m.ServiceRequests = make(map[string]int64)
m.serviceMutex.Unlock()
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
}