Update metrics tracking and enhance cache eviction strategies

- Added metrics for bytes saved from cache to improve performance insights.
- Updated cache eviction strategies in MemoryFS and DiskFS to include metrics tracking for hits and evictions.
- Enhanced README.md with updated garbage collection algorithm descriptions and recommendations for cache usage.
- Introduced new madviseSequential functionality for improved memory access hints on Unix systems.
- Adjusted validation configuration in examples to better reflect realistic usage scenarios.

README.md

@@ -261,11 +261,11 @@ SteamCache2 supports different garbage collection algorithms for memory and disk
 **Available GC Algorithms:**
 
 - **`lru`** (default): Least Recently Used - evicts oldest accessed files
-- **`lfu`**: Least Frequently Used (P1 real impl) - evicts by lowest AccessCount (tiebreak older ATime); uses existing FileInfo counters
+- **`lfu`**: Least Frequently Used - evicts by lowest AccessCount (tiebreak older ATime); uses existing FileInfo counters
-- **`fifo`**: First In, First Out - evicts oldest created files (predictable)
+- **`fifo`**: First In, First Out - evicts oldest created files (predictable and terrible all in one) don't ever use it
-- **`largest`**: Size-based - evicts largest files first (maximizes file count)
+- **`largest`**: Size-based - evicts largest files first (maximizes small file count) if used on memory greatly improves access time
-- **`smallest`**: Size-based - evicts smallest files first (maximizes cache hit rate)
+- **`smallest`**: Size-based - evicts smallest files first (maximizes large file count) probably best used for disk since there kinda slow with small files
-- **`hybrid`**: Recency + frequency hybrid (P1 meaningful) - evicts by lowest time-decayed score (GetTimeDecayedScore combining ATime + AccessCount)
+- **`hybrid`**: Recency + frequency hybrid - evicts by lowest time-decayed score (GetTimeDecayedScore combining ATime + AccessCount)
 
 **Recommended Algorithms by Cache Type:**
 
@@ -273,18 +273,19 @@ SteamCache2 supports different garbage collection algorithms for memory and disk
 - **`lru`** - Best overall performance, good balance of speed and hit rate
 - **`lfu`** - Excellent for gaming cafes where popular games stay cached
 - **`hybrid`** - Optimal for mixed workloads with varying file sizes
+- **`largest`** - Crazy good for access times since disks are slow with lots of tiny files
 
 **For Disk Cache (Slow, Large Size):**
 - **`hybrid`** - Recommended for optimal performance, balances speed and storage efficiency
-- **`largest`** - Good for maximizing number of cached files
+- **`smallest`** - Good for maximizing linear reads which is the only place spinning disks have performance don't expect too much though steam kinda uses small files
 - **`lru`** - Reliable default with good performance
 
 **Use Cases:**
-- **Gaming Cafes**: Use `lfu` for memory, `hybrid` for disk
+- **Gaming Cafes**: Use `largest` for memory, `hybrid` for disk
-- **LAN Events**: Use `lfu` for memory, `hybrid` for disk
+- **LAN Events**: Use `largest` for memory, `hybrid` for disk
-- **Home Use**: Use `lru` for memory, `hybrid` for disk
+- **Home Use**: Use `largest` for memory, `hybrid` for disk
-- **Testing**: Use `fifo` for predictable behavior
+- **Testing**: Use `fifo` for nothing its pointless
-- **Large File Storage**: Use `largest` for disk to maximize file count
+- **Large File Storage**: Use `smallest` for disk get rid of the slow tiny files first
 
 ### DNS Configuration
 

docs/examples/validate-config.yaml

@@ -6,11 +6,14 @@
 # "benchmark" commands.
 #
 # Why these values?
-# - Both memory and disk tiers are enabled but deliberately small.
+# - Both tiers enabled. Memory is sized large enough to survive the disk attach
-#   A modest benchmark workload (a few hundred MB to low GB) will exercise:
+#   window in mixed mode (see steamcache.go: the goroutine that blocks on d.Size()
-#     * Memory tier promotions
+#   before SetSlow). With a realistic SteamPrefill benchmark (high rate of unique
-#     * Disk tier attach + writes
+#   ~1MB chunks) the old tiny 128MB mem + 512MB disk caused almost all early
-#     * GC / eviction pressure on at least one tier
+#   content to live only in memory, get evicted by its GC, and never reach disk.
+#   Result: "never hitting", hit_rate 0, memory_size 0, despite files appearing
+#   on disk for late-arriving chunks. Larger mem + disk makes the validation
+#   actually exercise hits, promotions, disk tier, and GC as intended.
 # - Conservative concurrency limits suitable for a developer laptop.
 # - trusted_proxies set for 127.0.0.0/8 so that an external benchmark tool
 #   can simulate multiple distinct clients via X-Forwarded-For if desired.
@@ -31,7 +34,7 @@
 
 listen_address: :80
 
-max_concurrent_requests: 100
+max_concurrent_requests: 1000
 max_requests_per_client: 10
 
 max_object_size: "0"          # unlimited for validation (real Steam files can be large)
@@ -39,10 +42,10 @@ trusted_proxies: ["127.0.0.0/8"]
 
 cache:
   memory:
-    size: 128MB
+    size: 1GB
-    gc_algorithm: lru      # lru is somewhat recommeded in the project README and is better for validation since its not just using the same again
+    gc_algorithm: largest
   disk:
-    size: 512MB
+    size: 2GB
     path: ./validate-disk     # ephemeral; clean between runs if you want a fresh test
     gc_algorithm: hybrid      # recommended for disk in the project README
 

go.mod

@@ -8,6 +8,7 @@ require (
 	github.com/rs/zerolog v1.33.0
 	github.com/spf13/cobra v1.8.1
 	golang.org/x/sync v0.16.0
+	golang.org/x/sys v0.12.0
 	gopkg.in/yaml.v3 v3.0.1
 )
 
@@ -16,5 +17,4 @@ require (
 	github.com/mattn/go-colorable v0.1.13 // indirect
 	github.com/mattn/go-isatty v0.0.19 // indirect
 	github.com/spf13/pflag v1.0.5 // indirect
-	golang.org/x/sys v0.12.0 // indirect
 )

steamcache/handler.go

@@ -110,6 +110,7 @@ func (sc *SteamCache) handleCacheHit(w http.ResponseWriter, r *http.Request, cac
 				sc.metrics.IncrementCacheHits()
 				sc.metrics.AddResponseTime(time.Since(tstart))
 				sc.metrics.AddBytesServed(int64(len(cachedData)))
+				sc.metrics.AddBytesSaved(int64(len(cachedData)))
 				sc.metrics.IncrementServiceRequests(service.Name)
 
 				logger.Logger.Debug().
@@ -197,6 +198,7 @@ func (sc *SteamCache) waitForCoalesced(w http.ResponseWriter, r *http.Request, c
 	sc.metrics.IncrementCacheCoalesced()
 	sc.metrics.AddResponseTime(time.Since(tstart))
 	sc.metrics.AddBytesServed(int64(len(responseData)))
+	sc.metrics.AddBytesSaved(int64(len(responseData)))
 	sc.metrics.IncrementServiceRequests(service.Name)
 
 	logger.Logger.Info().
@@ -233,9 +235,6 @@ func (sc *SteamCache) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 	}
 	defer sc.requestSemaphore.Release(1)
 
-	// Track total requests
-	sc.metrics.IncrementTotalRequests()
-
 	// Apply per-client rate limiting
 	clientLimiter := sc.getOrCreateClientLimiter(clientIP)
 
@@ -305,6 +304,11 @@ func (sc *SteamCache) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 			Str("client_ip", clientIP).
 			Msg("Generated cache key")
 
+		// Only count real cacheable service traffic toward total_requests / hit_rate.
+		// Special endpoints (/, /metrics, /lancache-heartbeat) and unsupported services
+		// are intentionally excluded so that idle monitoring doesn't dilute the hit rate.
+		sc.metrics.IncrementTotalRequests()
+
 		if sc.handleCacheHit(w, r, cachePath, cacheKey, urlPath, service, clientIP, tstart) {
 			return
 		}
@@ -588,8 +592,6 @@ func (sc *SteamCache) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 					sc.metrics.IncrementServiceError("cache_write")
 					_ = sc.vfs.Delete(cachePath) // best-effort removal of partial corrupt cache entry on write failure; non-fatal. Deferred cacheWriter.Close() (from earlier in block) runs after this on error unwind path (harmless per DiskFS design)
 				} else {
-					// Track successful cache write
-					sc.metrics.AddBytesCached(int64(len(cacheData)))
 					logger.Logger.Debug().
 						Str("key", cacheKey).
 						Str("url", urlPath).

steamcache/metrics/metrics.go

@@ -22,7 +22,9 @@ type Metrics struct {
 	// Performance metrics
 	TotalResponseTime int64 // in nanoseconds
 	TotalBytesServed  int64
-	TotalBytesCached  int64
+	TotalBytesSaved   int64 // bytes served from cache instead of being re-downloaded from upstream
+
+
 
 	// Cache metrics
 	MemoryCacheSize int64
@@ -98,9 +100,10 @@ func (m *Metrics) AddBytesServed(bytes int64) {
 	atomic.AddInt64(&m.TotalBytesServed, bytes)
 }
 
-// AddBytesCached adds bytes cached to the total
+// AddBytesSaved records bytes that were served from the cache instead of being
-func (m *Metrics) AddBytesCached(bytes int64) {
+// fetched again from the upstream (the main value metric for a cache).
-	atomic.AddInt64(&m.TotalBytesCached, bytes)
+func (m *Metrics) AddBytesSaved(bytes int64) {
+	atomic.AddInt64(&m.TotalBytesSaved, bytes)
 }
 
 // SetMemoryCacheSize sets the current memory cache size
@@ -192,7 +195,7 @@ func (m *Metrics) GetStats() *Stats {
 		HitRate:            hitRate,
 		AvgResponseTime:    avgResponseTime,
 		TotalBytesServed: atomic.LoadInt64(&m.TotalBytesServed),
-		TotalBytesCached:   atomic.LoadInt64(&m.TotalBytesCached),
+		TotalBytesSaved:  atomic.LoadInt64(&m.TotalBytesSaved),
 		MemoryCacheSize:    atomic.LoadInt64(&m.MemoryCacheSize),
 		DiskCacheSize:      atomic.LoadInt64(&m.DiskCacheSize),
 		MemoryCacheHits:    atomic.LoadInt64(&m.MemoryCacheHits),
@@ -218,7 +221,7 @@ func (m *Metrics) Reset() {
 	atomic.StoreInt64(&m.RateLimited, 0)
 	atomic.StoreInt64(&m.TotalResponseTime, 0)
 	atomic.StoreInt64(&m.TotalBytesServed, 0)
-	atomic.StoreInt64(&m.TotalBytesCached, 0)
+	atomic.StoreInt64(&m.TotalBytesSaved, 0)
 	atomic.StoreInt64(&m.MemoryCacheHits, 0)
 	atomic.StoreInt64(&m.DiskCacheHits, 0)
 	atomic.StoreInt64(&m.Promotions, 0)
@@ -248,8 +251,10 @@ type Stats struct {
 	HitRate            float64
 	AvgResponseTime    time.Duration
 	TotalBytesServed  int64
-	TotalBytesCached   int64
+	TotalBytesSaved   int64
 	MemoryCacheSize   int64
+
+
 	DiskCacheSize      int64
 	MemoryCacheHits    int64
 	DiskCacheHits      int64
@@ -291,7 +296,8 @@ func WriteText(w http.ResponseWriter, stats *Stats) {
 	_, _ = fmt.Fprintf(w, "hit_rate %.4f\n", stats.HitRate)
 	_, _ = fmt.Fprintf(w, "avg_response_time_ms %.2f\n", float64(stats.AvgResponseTime.Nanoseconds())/1e6)
 	_, _ = fmt.Fprintf(w, "total_bytes_served %d\n", stats.TotalBytesServed)
-	_, _ = fmt.Fprintf(w, "total_bytes_cached %d\n", stats.TotalBytesCached)
+	_, _ = fmt.Fprintf(w, "total_bytes_saved %d\n", stats.TotalBytesSaved)
+
 	_, _ = fmt.Fprintf(w, "memory_cache_size %d\n", stats.MemoryCacheSize)
 	_, _ = fmt.Fprintf(w, "disk_cache_size %d\n", stats.DiskCacheSize)
 	_, _ = fmt.Fprintf(w, "uptime_seconds %.2f\n", stats.Uptime.Seconds())

steamcache/steamcache.go

@@ -179,6 +179,17 @@ func New(address string, memorySize string, diskSize string, diskPath, upstream,
 		metrics: metrics.NewMetrics(),
 	}
 
+	// Wire metrics into TieredCache so promotions are counted.
+	c.SetMetrics(sc.metrics)
+
+	// Wire metrics into the concrete storage tiers (MemoryFS / DiskFS) so per-tier hits and evictions are counted.
+	if m != nil {
+		m.SetMetrics(sc.metrics)
+	}
+	if d != nil {
+		d.SetMetrics(sc.metrics)
+	}
+
 	// Wire the request processor (constructor injection of interfaces for the owned wrappers + vfs + client + scalars).
 	// Done after all fields including wrappers are set; before attach goroutines (no impact on lifecycle paths).
 	sc.processor = newRequestProcessor(sc)
@@ -209,12 +220,16 @@ func New(address string, memorySize string, diskSize string, diskPath, upstream,
 		sc.wg.Add(1)
 		go func() {
 			defer sc.wg.Done()
+			t0 := time.Now()
 			_ = d.Size()
 			select {
 			case <-sc.shutdownCh:
 				return
 			default:
 				c.SetSlow(dgc)
+				logger.Logger.Info().
+					Dur("attach_delay", time.Since(t0)).
+					Msg("Disk slow tier attached (mixed mode); prior traffic was memory-only")
 			}
 		}()
 	}

vfs/cache/cache.go

@@ -3,6 +3,7 @@ package cache
 
 import (
 	"io"
+	"s1d3sw1ped/steamcache2/steamcache/metrics"
 	"s1d3sw1ped/steamcache2/vfs"
 	"s1d3sw1ped/steamcache2/vfs/vfserror"
 	"sync/atomic"
@@ -12,6 +13,7 @@ import (
 type TieredCache struct {
 	fast    *atomic.Value // Memory cache (fast) - atomic.Value for lock-free access
 	slow    *atomic.Value // Disk cache (slow) - atomic.Value for lock-free access
+	metrics *metrics.Metrics
 }
 
 // New creates a new tiered cache
@@ -22,6 +24,11 @@ func New() *TieredCache {
 	}
 }
 
+// SetMetrics allows wiring the top-level metrics collector (called from SteamCache).
+func (tc *TieredCache) SetMetrics(m *metrics.Metrics) {
+	tc.metrics = m
+}
+
 // SetFast sets the fast (memory) tier atomically
 func (tc *TieredCache) SetFast(vfs vfs.VFS) {
 	tc.fast.Store(vfs)
@@ -221,6 +228,10 @@ func (tc *TieredCache) promoteToFast(key string, reader io.ReadCloser) {
 				// Failure (e.g. mem pressure, concurrent evict) is non-fatal and does not affect correctness of slow tier.
 				_, _ = writer.Write(content)
 				_ = writer.Close()
+
+				if tc.metrics != nil {
+					tc.metrics.IncrementPromotions()
+				}
 			}
 		}
 	}

vfs/disk/disk.go

@@ -7,6 +7,7 @@ import (
 	"os"
 	"path/filepath"
 	"s1d3sw1ped/steamcache2/steamcache/logger"
+	"s1d3sw1ped/steamcache2/steamcache/metrics"
 	"s1d3sw1ped/steamcache2/vfs"
 	"s1d3sw1ped/steamcache2/vfs/locks"
 	"s1d3sw1ped/steamcache2/vfs/lru"
@@ -43,6 +44,7 @@ type DiskFS struct {
 	// initCloseOnce ensures initDone closed exactly once even on panic in bg populator (panic safety for Issue 1).
 	initCloseOnce sync.Once
 	startupEvict  func(vfs.VFS, uint) uint // passed to New (via gc.GetGCAlgorithm); invoked as last step of bg init if over cap (no post-ctor race)
+	metrics       *metrics.Metrics
 }
 
 // shardPath converts a Steam cache key to a sharded directory path to reduce inode pressure
@@ -134,6 +136,12 @@ func New(root string, capacity int64, evict func(vfs.VFS, uint) uint) (*DiskFS,
 	return d, nil
 }
 
+// SetMetrics allows the owner (SteamCache) to inject the metrics collector
+// so that per-tier hit and eviction counters can be recorded.
+func (d *DiskFS) SetMetrics(met *metrics.Metrics) {
+	d.metrics = met
+}
+
 // calculateSizeAndPopulateIndex runs in background from New to avoid blocking startup or O(N) RAM for large caches (millions of Steam files).
 // It streams batch inserts (bounded by maxEvictBatch) to keep lock times short and eliminate giant temporary slice.
 // Startup over-capacity eviction (if needed) runs as the very last step (using the evict func passed to New, selected via gc.GetGCAlgorithm).
@@ -489,8 +497,14 @@ func (d *DiskFS) Open(key string) (io.ReadCloser, error) {
 		return nil, err
 	}
 
-	// Use memory mapping for large files (>1MB) to improve performance
+	// Use memory mapping for large files to improve performance.
-	const mmapThreshold = 1024 * 1024 // 1MB
+	// We use 8 MiB as the threshold because:
+	// - Most Steam chunks are ~1 MiB (see current disk cache analysis).
+	// - mmap has non-trivial fixed overhead (page tables, TLB, faults).
+	// - For files < ~4-8 MiB the overhead often outweighs the zero-copy benefit
+	//   on mostly sequential access patterns.
+	// - Larger files benefit more from kernel readahead + zero-copy.
+	const mmapThreshold = 8 * 1024 * 1024 // 8 MiB
 	if fi.Size > mmapThreshold {
 		// Close the regular file handle
 		_ = file.Close() // best-effort; mmap path takes over or falls back
@@ -505,9 +519,21 @@ func (d *DiskFS) Open(key string) (io.ReadCloser, error) {
 		if err != nil {
 			_ = mmapFile.Close() // best-effort close before fallback open
 			// Fallback to regular file reading (intentional 3rd open of same path after mmap failure; pre-existing pattern, no leak)
+			if d.metrics != nil {
+				d.metrics.IncrementDiskCacheHits()
+			}
 			return os.Open(path)
 		}
 
+		// Hint to the kernel (on supported platforms) that we will access
+		// this mapping sequentially. This enables better readahead.
+		if err := madviseSequential(mapped); err != nil {
+			logger.Logger.Debug().
+				Err(err).
+				Str("key", key).
+				Msg("madvise(MADV_SEQUENTIAL) failed on mmap'd chunk")
+		}
+
 		return &mmapReadCloser{
 			data:   mapped,
 			file:   mmapFile,
@@ -515,6 +541,9 @@ func (d *DiskFS) Open(key string) (io.ReadCloser, error) {
 		}, nil
 	}
 
+	if d.metrics != nil {
+		d.metrics.IncrementDiskCacheHits()
+	}
 	return file, nil
 }
 
@@ -677,6 +706,10 @@ func (d *DiskFS) EvictLRU(bytesNeeded uint) uint {
 		}
 	}
 	d.mu.Unlock()
+
+	if d.metrics != nil && evicted > 0 {
+		d.metrics.IncrementEvictions()
+	}
 	return evicted
 }
 
@@ -726,6 +759,10 @@ func (d *DiskFS) EvictBySize(bytesNeeded uint, ascending bool) uint {
 		}
 	}
 	d.mu.Unlock()
+
+	if d.metrics != nil && evicted > 0 {
+		d.metrics.IncrementEvictions()
+	}
 	return evicted
 }
 
@@ -773,6 +810,10 @@ func (d *DiskFS) EvictFIFO(bytesNeeded uint) uint {
 		}
 	}
 	d.mu.Unlock()
+
+	if d.metrics != nil && evicted > 0 {
+		d.metrics.IncrementEvictions()
+	}
 	return evicted
 }
 
@@ -825,6 +866,10 @@ func (d *DiskFS) EvictLFU(bytesNeeded uint) uint {
 		}
 	}
 	d.mu.Unlock()
+
+	if d.metrics != nil && evicted > 0 {
+		d.metrics.IncrementEvictions()
+	}
 	return evicted
 }
 
@@ -878,5 +923,9 @@ func (d *DiskFS) EvictHybrid(bytesNeeded uint) uint {
 		}
 	}
 	d.mu.Unlock()
+
+	if d.metrics != nil && evicted > 0 {
+		d.metrics.IncrementEvictions()
+	}
 	return evicted
 }

vfs/disk/disk_madvise_unix.go

@@ -0,0 +1,13 @@
+//go:build !windows
+
+package disk
+
+import (
+	"golang.org/x/sys/unix"
+)
+
+// madviseSequential gives the OS a hint that the memory region will be
+// accessed sequentially. This is a no-op or best-effort on some platforms.
+func madviseSequential(b []byte) error {
+	return unix.Madvise(b, unix.MADV_SEQUENTIAL)
+}

vfs/disk/disk_madvise_windows.go

@@ -0,0 +1,11 @@
+//go:build windows
+
+package disk
+
+// madviseSequential is a no-op on Windows.
+// Windows file mappings don't have a direct equivalent to MADV_SEQUENTIAL
+// in the same way. Sequential access hints are better done via
+// FILE_FLAG_SEQUENTIAL_SCAN at file open time (future improvement possible).
+func madviseSequential(b []byte) error {
+	return nil
+}

vfs/memory/memory.go

@@ -5,6 +5,7 @@ import (
 	"bytes"
 	"fmt"
 	"io"
+	"s1d3sw1ped/steamcache2/steamcache/metrics"
 	"s1d3sw1ped/steamcache2/vfs"
 	"s1d3sw1ped/steamcache2/vfs/locks"
 	"s1d3sw1ped/steamcache2/vfs/lru"
@@ -33,6 +34,7 @@ type MemoryFS struct {
 	keyLocks    []sync.Map // Sharded lock pools for better concurrency
 	LRU         *lru.LRUList[*types.FileInfo]
 	timeUpdater *types.BatchedTimeUpdate // Batched time updates for better performance
+	metrics     *metrics.Metrics
 }
 
 // New creates a new MemoryFS
@@ -55,6 +57,12 @@ func New(capacity int64) (*MemoryFS, error) {
 	}, nil
 }
 
+// SetMetrics allows the owner (SteamCache) to inject the metrics collector
+// so that per-tier hit and eviction counters can be recorded.
+func (m *MemoryFS) SetMetrics(met *metrics.Metrics) {
+	m.metrics = met
+}
+
 // Name returns the name of this VFS
 func (m *MemoryFS) Name() string {
 	return "MemoryFS"
@@ -209,6 +217,10 @@ func (m *MemoryFS) Open(key string) (io.ReadCloser, error) {
 	// Use zero-copy approach - return reader that reads directly from buffer
 	m.mu.Unlock()
 
+	if m.metrics != nil {
+		m.metrics.IncrementMemoryCacheHits()
+	}
+
 	return &memoryReadCloser{
 		buffer: buffer,
 		offset: 0,
@@ -344,6 +356,10 @@ func (m *MemoryFS) EvictLRU(bytesNeeded uint) uint {
 		}
 	}
 	m.mu.Unlock()
+
+	if m.metrics != nil && evicted > 0 {
+		m.metrics.IncrementEvictions()
+	}
 	return evicted
 }
 
@@ -395,6 +411,10 @@ func (m *MemoryFS) EvictBySize(bytesNeeded uint, ascending bool) uint {
 		}
 	}
 	m.mu.Unlock()
+
+	if m.metrics != nil && evicted > 0 {
+		m.metrics.IncrementEvictions()
+	}
 	return evicted
 }
 
@@ -442,6 +462,10 @@ func (m *MemoryFS) EvictFIFO(bytesNeeded uint) uint {
 		}
 	}
 	m.mu.Unlock()
+
+	if m.metrics != nil && evicted > 0 {
+		m.metrics.IncrementEvictions()
+	}
 	return evicted
 }
 
@@ -494,6 +518,10 @@ func (m *MemoryFS) EvictLFU(bytesNeeded uint) uint {
 		}
 	}
 	m.mu.Unlock()
+
+	if m.metrics != nil && evicted > 0 {
+		m.metrics.IncrementEvictions()
+	}
 	return evicted
 }
 
@@ -548,5 +576,9 @@ func (m *MemoryFS) EvictHybrid(bytesNeeded uint) uint {
 		}
 	}
 	m.mu.Unlock()
+
+	if m.metrics != nil && evicted > 0 {
+		m.metrics.IncrementEvictions()
+	}
 	return evicted
 }