perf(cache): skip redundant store writes and scans on cache requests (#1222)

Every cache hit rewrote the entry's access time, costing a bolt write and fsync per restore. Completed entries accessed within the last minute are no longer rewritten, and the in-use and retention windows grow by that minute so nothing is evicted earlier. Same-second rewrites are skipped, reservations are inserted in one transaction, and prefix lookups use the repository index instead of scanning every entry.

The store is still opened per request. Keeping it open, as this commit first did, is faster under concurrency but stops a second process sharing the cache directory from starting its cache server.

The README caching section is condensed and corrected.

| Benchmark, v2 | main | store kept open | this PR |
| --- | ---: | ---: | ---: |
| Exact hit, 1 client | 16.42 | 0.15 | 0.24 |
| Exact hit, 8 clients | 13.70 | 0.08 | 1.28 |
| Exact hit, 32 clients | 16.01 | 0.07 | 4.26 |
| Prefix hit, 8 clients | 18.34 | 0.12 | 1.28 |
| Miss, 8 clients | 3.21 | 0.11 | 1.28 |
| Save and restore 1 MiB, 8 clients | 74.4 | 22.9 | 34.9 |
| Geomean, all 22 benchmarks | 14.03 | 0.31 | 2.11 |

Mean ms per request, medians of 4 rounds of 300 requests over 1,000 entries on an Apple M3 Max.

---------

Co-authored-by: silverwind <2021+silverwind@noreply.gitea.com>
Co-authored-by: silverwind <me@silverwind.io>
Reviewed-on: https://gitea.com/gitea/runner/pulls/1222
Reviewed-by: silverwind <2021+silverwind@noreply.gitea.com>

act/artifactcache/handler.go

@@ -20,7 +20,6 @@ import (
 	"net/url"
 	"os"
 	"path/filepath"
-	"regexp"
 	"slices"
 	"strconv"
 	"strings"
@@ -784,14 +783,9 @@ func findCache(db *bolthold.Store, repo string, keys []string, version string) (
 		if exact != nil {
 			return exact, nil
 		}
-		prefixPattern := "^" + regexp.QuoteMeta(prefix)
-		re, err := regexp.Compile(prefixPattern)
-		if err != nil {
-			continue
-		}
 		if err := db.FindOne(cache,
-			bolthold.Where("Repo").Eq(repo).
-				And("Key").RegExp(re).
+			bolthold.Where("Repo").Eq(repo).Index("Repo").
+				And("Key").MatchFunc(func(key string) (bool, error) { return strings.HasPrefix(key, prefix), nil }).
 				And("Version").Eq(version).
 				And("Complete").Eq(true).
 				SortBy("CreatedAt").Reverse()); err != nil {
@@ -834,14 +828,16 @@ func findExactCache(db *bolthold.Store, repo, key, version string, complete bool
 }
 
 func insertCache(db *bolthold.Store, cache *Cache) error {
-	if err := db.Insert(bolthold.NextSequence(), cache); err != nil {
-		return fmt.Errorf("insert cache: %w", err)
-	}
-	// write back id to db
-	if err := db.Update(cache.ID, cache); err != nil {
-		return fmt.Errorf("write back id to db: %w", err)
-	}
-	return nil
+	return db.Bolt().Update(func(tx *bbolt.Tx) error {
+		if err := db.TxInsert(tx, bolthold.NextSequence(), cache); err != nil {
+			return fmt.Errorf("insert cache: %w", err)
+		}
+		// write back id to db
+		if err := db.TxUpdate(tx, cache.ID, cache); err != nil {
+			return fmt.Errorf("write back id to db: %w", err)
+		}
+		return nil
+	})
 }
 
 // touchCache stamps UsedAt so gcCache does not reap an entry mid-upload. With requireIncomplete
@@ -866,6 +862,9 @@ func (h *Handler) touchCache(id uint64, requireIncomplete bool) error {
 	if requireIncomplete && cache.Complete {
 		return fmt.Errorf("cache %d: already complete", id)
 	}
+	if !touchNeeded(cache) {
+		return nil
+	}
 	cache.UsedAt = time.Now().Unix()
 	return db.Update(cache.ID, cache)
 }
@@ -875,9 +874,11 @@ const (
 
 	defaultSweepInterval = time.Hour
 
-	// inUseGrace matches artifactURLTTL so an entry outlives every signed URL still usable
-	// for it, and no sweep cuts off a download in progress.
-	inUseGrace = artifactURLTTL
+	touchStale = time.Minute // how stale a completed entry's UsedAt may get before an access rewrites it, sparing hits the fsync
+
+	// inUseGrace covers artifactURLTTL plus the touchStale lag so an entry outlives every signed URL
+	// still usable for it, and no sweep cuts off a download in progress.
+	inUseGrace = artifactURLTTL + touchStale
 
 	// uploadStallTimeout is how long a reservation may sit without a chunk before it counts
 	// as abandoned. Widening it also widens the window for findExactCache to hand a finalize
@@ -971,7 +972,7 @@ func (h *Handler) evictExpired(db *bolthold.Store) {
 		return
 	}
 	// Never below inUseGrace, or a short retention would outrun a signed URL already issued.
-	window := max(h.policy.Retention, inUseGrace)
+	window := max(h.policy.Retention+touchStale, inUseGrace)
 	h.sweep(db, bolthold.Where("UsedAt").Lt(time.Now().Add(-window).Unix()).Index("UsedAt"))
 }
 
@@ -1072,10 +1073,18 @@ func inUse(cache *Cache) bool {
 	return time.Since(time.Unix(cache.UsedAt, 0)) < inUseGrace
 }
 
+// touchNeeded skips a write that would not change the second, and completed entries fresher than touchStale.
+func touchNeeded(cache *Cache) bool {
+	return cache.UsedAt < time.Now().Unix() && (!cache.Complete || time.Since(time.Unix(cache.UsedAt, 0)) >= touchStale)
+}
+
 // touch stamps UsedAt through the caller's store, a bolt write on the read path. It cannot
 // go through touchCache, which opens its own store and would block on the exclusive lock
 // for as long as the caller holds one.
 func (h *Handler) touch(db *bolthold.Store, cache *Cache) {
+	if !touchNeeded(cache) {
+		return
+	}
 	cache.UsedAt = time.Now().Unix()
 	if err := db.Update(cache.ID, cache); err != nil {
 		h.logger.Warnf("touch cache: %v", err)

act/artifactcache/handler_test.go

@@ -771,7 +771,7 @@ func TestHandler_gcCache(t *testing.T) {
 				Key:       "test_key_3",
 				Version:   "test_version",
 				Complete:  true,
-				UsedAt:    now.Add(-(testRetention + time.Second)).Unix(),
+				UsedAt:    now.Add(-(testRetention + touchStale + time.Second)).Unix(),
 				CreatedAt: now.Add(-(testRetention + time.Hour)).Unix(),
 			},
 			Kept: false,
@@ -1046,6 +1046,26 @@ func TestHandler_gcCacheInterval(t *testing.T) {
 	assert.Empty(t, keptKeys(t, handler, []*Cache{cache}))
 }
 
+func TestHandler_touchCacheSkipsFreshCompletedEntries(t *testing.T) {
+	fresh := &Cache{Repo: testRepo, Key: "fresh", Version: "v", Complete: true, UsedAt: time.Now().Unix()}
+	pending := &Cache{Repo: testRepo, Key: "pending", Version: "v", UsedAt: time.Now().Add(-time.Second).Unix()}
+	handler := newTestHandler(t, Policy{}, fresh, pending)
+	txID := func() int {
+		db, err := handler.openDB()
+		require.NoError(t, err)
+		defer db.Close()
+		var id int
+		require.NoError(t, db.Bolt().View(func(tx *bbolt.Tx) error { id = tx.ID(); return nil }))
+		return id
+	}
+
+	before := txID()
+	require.NoError(t, handler.touchCache(fresh.ID, false))
+	assert.Equal(t, before, txID())
+	require.NoError(t, handler.touchCache(pending.ID, false))
+	assert.Greater(t, txID(), before)
+}
+
 // newTestHandler starts a handler with testToken registered, seeded with entries.
 func newTestHandler(t *testing.T, policy Policy, entries ...*Cache) *Handler {
 	t.Helper()