Keep counts not written by the request's deadline in memory (closes #224)

TestService_Get_ReturnsByItsDeadline failed on a busy host because its
request, past its deadline, still waited to write its miss count, a write
with no deadline; in pixad that write waits for the one database
connection every request shares. Each count write now keeps the request's
deadline but not its cancellation. A count not written by then is kept in
memory, where Stats includes it, and one goroutine of the cache writes
those counts one UPDATE at a time, and once more at shutdown before the
database closes. The test phase also runs go test with -parallel 4: on a
busy host, as many tests at once as there are CPUs wait so long to be
scheduled that a timed request can fail.

Model: opus-5-5

internal/imgcache/cache.go

@@ -11,6 +11,7 @@ import (
 	"io"
 	"log/slog"
 	"path/filepath"
+	"sync/atomic"
 	"time"
 
 	lru "github.com/hashicorp/golang-lru/v2"
@@ -79,6 +80,22 @@ type Cache struct {
 	evictionDone     chan struct{}
 	evictionCancel   context.CancelFunc
 
+	// The pending counts: hits, misses, upstream fetches and transforms
+	// whose write to the database missed its request's deadline, kept
+	// here until they are written by the goroutine that
+	// StartPendingCountWrites starts. As for eviction, the channels are
+	// created in NewCache: pendingCountsAdded wakes that goroutine, and
+	// pendingCountsDone is closed when it returns. pendingCountsCancel,
+	// set by StartPendingCountWrites, cancels its context.
+	pendingHits               atomic.Int64
+	pendingMisses             atomic.Int64
+	pendingUpstreamFetches    atomic.Int64
+	pendingUpstreamFetchBytes atomic.Int64
+	pendingTransforms         atomic.Int64
+	pendingCountsAdded        chan struct{}
+	pendingCountsDone         chan struct{}
+	pendingCountsCancel       context.CancelFunc
+
 	// metaCache holds the content types of the variants most recently
 	// stored or served, so a hit does not read the variant's .meta file.
 	// It never stands in for the variant file, which is always opened.
@@ -139,6 +156,9 @@ func newCache(
 		metaCache:        metaCache,
 		contentLocks:     newContentLock(),
 
+		pendingCountsAdded: make(chan struct{}, 1),
+		pendingCountsDone:  make(chan struct{}),
+
 		reconciliationPageSize: defaultReconciliationPageSize,
 	}
 
@@ -484,6 +504,10 @@ func (c *Cache) Stats(ctx context.Context) (*CacheStats, error) {
 		return nil, fmt.Errorf("failed to get cache stats: %w", err)
 	}
 
+	// Hits and misses not yet written count too (see StartPendingCountWrites)
+	stats.HitCount += c.pendingHits.Load()
+	stats.MissCount += c.pendingMisses.Load()
+
 	// Count and size the cached source images and processed variants from
 	// their tables. A disabled cache holds none, whatever rows an earlier
 	// run left.
@@ -511,19 +535,30 @@ func (c *Cache) Stats(ctx context.Context) (*CacheStats, error) {
 }
 
 // IncrementStats counts a cache hit or miss, and an upstream fetch that read
-// fetchBytes bytes, as IncrementUpstreamFetch does.
+// fetchBytes bytes, as IncrementUpstreamFetch does. Like the other Increment
+// methods, it writes to the database with ctx's deadline but not its
+// cancellation, so an ended request is still counted but does not wait for
+// the database past its deadline; a count not written by then becomes a
+// pending count (see StartPendingCountWrites).
 func (c *Cache) IncrementStats(ctx context.Context, hit bool, fetchBytes int64) {
+	countCtx, cancel := withoutCancelKeepingDeadline(ctx)
+	defer cancel()
+
 	var err error
 
+	pendingCount := &c.pendingMisses
+
 	if hit {
-		_, err = c.db.ExecContext(ctx, `
+		pendingCount = &c.pendingHits
+
+		_, err = c.db.ExecContext(countCtx, `
 			UPDATE cache_stats
 			SET hit_count = hit_count + 1,
 			    last_updated_at = CURRENT_TIMESTAMP
 			WHERE id = 1
 		`)
 	} else {
-		_, err = c.db.ExecContext(ctx, `
+		_, err = c.db.ExecContext(countCtx, `
 			UPDATE cache_stats
 			SET miss_count = miss_count + 1,
 			    last_updated_at = CURRENT_TIMESTAMP
@@ -531,7 +566,10 @@ func (c *Cache) IncrementStats(ctx context.Context, hit bool, fetchBytes int64)
 		`)
 	}
 
-	if err != nil {
+	switch {
+	case errors.Is(err, context.DeadlineExceeded):
+		c.addPendingCount(pendingCount, 1)
+	case err != nil:
 		c.log.Warn("failed to count cache hit or miss", "hit", hit, "error", err)
 	}
 
@@ -545,14 +583,22 @@ func (c *Cache) IncrementUpstreamFetch(ctx context.Context, fetchBytes int64) {
 		return
 	}
 
-	_, err := c.db.ExecContext(ctx, `
+	countCtx, cancel := withoutCancelKeepingDeadline(ctx)
+	defer cancel()
+
+	_, err := c.db.ExecContext(countCtx, `
 		UPDATE cache_stats
 		SET upstream_fetch_count = upstream_fetch_count + 1,
 		    upstream_fetch_bytes = upstream_fetch_bytes + ?,
 		    last_updated_at = CURRENT_TIMESTAMP
 		WHERE id = 1
 	`, fetchBytes)
-	if err != nil {
+
+	switch {
+	case errors.Is(err, context.DeadlineExceeded):
+		c.addPendingCount(&c.pendingUpstreamFetches, 1)
+		c.addPendingCount(&c.pendingUpstreamFetchBytes, fetchBytes)
+	case err != nil:
 		c.log.Warn("failed to count upstream fetch",
 			"fetch_bytes", fetchBytes, "error", err)
 	}
@@ -560,13 +606,20 @@ func (c *Cache) IncrementUpstreamFetch(ctx context.Context, fetchBytes int64) {
 
 // IncrementTransformCount counts one image transcoded by the image processor.
 func (c *Cache) IncrementTransformCount(ctx context.Context) {
-	_, err := c.db.ExecContext(ctx, `
+	countCtx, cancel := withoutCancelKeepingDeadline(ctx)
+	defer cancel()
+
+	_, err := c.db.ExecContext(countCtx, `
 		UPDATE cache_stats
 		SET transform_count = transform_count + 1,
 		    last_updated_at = CURRENT_TIMESTAMP
 		WHERE id = 1
 	`)
-	if err != nil {
+
+	switch {
+	case errors.Is(err, context.DeadlineExceeded):
+		c.addPendingCount(&c.pendingTransforms, 1)
+	case err != nil:
 		c.log.Warn("failed to count transform", "error", err)
 	}
 }