sync: scalable Pool
Introduce fixed-size P-local caches.
When local caches overflow/underflow a batch of items
is transferred to/from global mutex-protected cache.
benchmark old ns/op new ns/op delta
BenchmarkPool 50554 22423 -55.65%
BenchmarkPool-4 400359 5904 -98.53%
BenchmarkPool-16 403311 1598 -99.60%
BenchmarkPool-32 367310 1526 -99.58%
BenchmarkPoolOverlflow 5214 3633 -30.32%
BenchmarkPoolOverlflow-4 42663 9539 -77.64%
BenchmarkPoolOverlflow-8 46919 11385 -75.73%
BenchmarkPoolOverlflow-16 39454 13048 -66.93%
BenchmarkSprintfEmpty 84 63 -25.68%
BenchmarkSprintfEmpty-2 371 32 -91.13%
BenchmarkSprintfEmpty-4 465 22 -95.25%
BenchmarkSprintfEmpty-8 565 12 -97.77%
BenchmarkSprintfEmpty-16 498 5 -98.87%
BenchmarkSprintfEmpty-32 492 4 -99.04%
BenchmarkSprintfString 259 229 -11.58%
BenchmarkSprintfString-2 574 144 -74.91%
BenchmarkSprintfString-4 651 77 -88.05%
BenchmarkSprintfString-8 868 47 -94.48%
BenchmarkSprintfString-16 825 33 -95.96%
BenchmarkSprintfString-32 825 30 -96.28%
BenchmarkSprintfInt 213 188 -11.74%
BenchmarkSprintfInt-2 448 138 -69.20%
BenchmarkSprintfInt-4 624 52 -91.63%
BenchmarkSprintfInt-8 691 31 -95.43%
BenchmarkSprintfInt-16 724 18 -97.46%
BenchmarkSprintfInt-32 718 16 -97.70%
BenchmarkSprintfIntInt 311 282 -9.32%
BenchmarkSprintfIntInt-2 333 145 -56.46%
BenchmarkSprintfIntInt-4 642 110 -82.87%
BenchmarkSprintfIntInt-8 832 42 -94.90%
BenchmarkSprintfIntInt-16 817 24 -97.00%
BenchmarkSprintfIntInt-32 805 22 -97.17%
BenchmarkSprintfPrefixedInt 309 269 -12.94%
BenchmarkSprintfPrefixedInt-2 245 168 -31.43%
BenchmarkSprintfPrefixedInt-4 598 99 -83.36%
BenchmarkSprintfPrefixedInt-8 770 67 -91.23%
BenchmarkSprintfPrefixedInt-16 829 54 -93.49%
BenchmarkSprintfPrefixedInt-32 824 50 -93.83%
BenchmarkSprintfFloat 418 398 -4.78%
BenchmarkSprintfFloat-2 295 203 -31.19%
BenchmarkSprintfFloat-4 585 128 -78.12%
BenchmarkSprintfFloat-8 873 60 -93.13%
BenchmarkSprintfFloat-16 884 33 -96.24%
BenchmarkSprintfFloat-32 881 29 -96.62%
BenchmarkManyArgs 1097 1069 -2.55%
BenchmarkManyArgs-2 705 567 -19.57%
BenchmarkManyArgs-4 792 319 -59.72%
BenchmarkManyArgs-8 963 172 -82.14%
BenchmarkManyArgs-16 1115 103 -90.76%
BenchmarkManyArgs-32 1133 90 -92.03%
LGTM=rsc
R=golang-codereviews, bradfitz, minux.ma, gobot, rsc
CC=golang-codereviews
https://golang.org/cl/46010043
diff --git a/src/pkg/sync/pool_test.go b/src/pkg/sync/pool_test.go
index e4aeda4..3bf5131 100644
--- a/src/pkg/sync/pool_test.go
+++ b/src/pkg/sync/pool_test.go
@@ -11,7 +11,6 @@
"sync/atomic"
"testing"
"time"
- "unsafe"
)
func TestPool(t *testing.T) {
@@ -125,28 +124,41 @@
}
func BenchmarkPool(b *testing.B) {
- procs := runtime.GOMAXPROCS(-1)
- var dec func() bool
- if unsafe.Sizeof(b.N) == 8 {
- n := int64(b.N)
- dec = func() bool {
- return atomic.AddInt64(&n, -1) >= 0
- }
- } else {
- n := int32(b.N)
- dec = func() bool {
- return atomic.AddInt32(&n, -1) >= 0
- }
- }
var p Pool
var wg WaitGroup
- for i := 0; i < procs; i++ {
+ n0 := uintptr(b.N)
+ n := n0
+ for i := 0; i < runtime.GOMAXPROCS(0); i++ {
wg.Add(1)
go func() {
defer wg.Done()
- for dec() {
- p.Put(1)
- p.Get()
+ for atomic.AddUintptr(&n, ^uintptr(0)) < n0 {
+ for b := 0; b < 100; b++ {
+ p.Put(1)
+ p.Get()
+ }
+ }
+ }()
+ }
+ wg.Wait()
+}
+
+func BenchmarkPoolOverlflow(b *testing.B) {
+ var p Pool
+ var wg WaitGroup
+ n0 := uintptr(b.N)
+ n := n0
+ for i := 0; i < runtime.GOMAXPROCS(0); i++ {
+ wg.Add(1)
+ go func() {
+ defer wg.Done()
+ for atomic.AddUintptr(&n, ^uintptr(0)) < n0 {
+ for b := 0; b < 100; b++ {
+ p.Put(1)
+ }
+ for b := 0; b < 100; b++ {
+ p.Get()
+ }
}
}()
}
