device: benchmark the waitpool to compare it to the prior channels

Here is the old implementation:

    type WaitPool struct {
        c chan interface{}
    }

    func NewWaitPool(max uint32, new func() interface{}) *WaitPool {
        p := &WaitPool{c: make(chan interface{}, max)}
        for i := uint32(0); i < max; i++ {
            p.c <- new()
        }
        return p
    }

    func (p *WaitPool) Get() interface{} {
        return <- p.c
    }

    func (p *WaitPool) Put(x interface{}) {
        p.c <- x
    }

It performs worse than the new one:

    name         old time/op  new time/op  delta
    WaitPool-16  16.4µs ± 5%  15.1µs ± 3%  -7.86%  (p=0.008 n=5+5)

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

device/pools_test.go

@@ -58,3 +58,26 @@ func TestWaitPool(t *testing.T) {
 		t.Errorf("Actual maximum count (%d) != ideal maximum count (%d)", max, p.max)
 	}
 }
+
+func BenchmarkWaitPool(b *testing.B) {
+	var wg sync.WaitGroup
+	trials := int32(b.N)
+	workers := runtime.NumCPU() + 2
+	if workers-4 <= 0 {
+		b.Skip("Not enough cores")
+	}
+	p := NewWaitPool(uint32(workers-4), func() interface{} { return make([]byte, 16) })
+	wg.Add(workers)
+	b.ResetTimer()
+	for i := 0; i < workers; i++ {
+		go func() {
+			defer wg.Done()
+			for atomic.AddInt32(&trials, -1) > 0 {
+				x := p.Get()
+				time.Sleep(time.Duration(rand.Intn(100)) * time.Microsecond)
+				p.Put(x)
+			}
+		}()
+	}
+	wg.Wait()
+}