labels/cidr: Add benchmark for concurrent exection of GetCIDRLabels

Adding a LRU cache to memoize GetCIDRLabels means sharing state between
different goroutines concurrently executing GetCIDRLabels.

To measure the scalability of the LRU cache + mutex approach against the
non-cached previous version, a benchmark with increasing number of
goroutines is added.

Running the benchmark for the current version and the previous one shows
that the memoization gives a performance improvement even when up to 48
goroutines compete for the exclusive access to the LRU cache:

name                          old time/op  new time/op  delta
GetCIDRLabelsConcurrent/1-8    493µs ±31%   259µs ± 4%  -47.54%  (p=0.000 n=20+9)
GetCIDRLabelsConcurrent/2-8    889µs ±10%   474µs ± 5%  -46.69%  (p=0.000 n=19+10)
GetCIDRLabelsConcurrent/4-8   1.74ms ± 3%  0.89ms ± 4%  -49.04%  (p=0.000 n=20+10)
GetCIDRLabelsConcurrent/16-8  7.14ms ± 6%  3.77ms ± 8%  -47.20%  (p=0.000 n=18+10)
GetCIDRLabelsConcurrent/32-8  14.3ms ± 6%   7.3ms ± 2%  -48.69%  (p=0.000 n=20+9)
GetCIDRLabelsConcurrent/48-8  21.9ms ± 5%  11.1ms ± 3%  -49.24%  (p=0.000 n=19+10)

Signed-off-by: Fabio Falzoi <fabio.falzoi@isovalent.com>

pkg/labels/cidr/cidr_test.go

@@ -4,8 +4,11 @@
 package cidr
 
 import (
+	"math/rand"
 	"net/netip"
 	"runtime"
+	"strconv"
+	"sync"
 	"testing"
 
 	. "github.com/cilium/checkmate"
@@ -318,6 +321,43 @@ func BenchmarkLabels_SortedListCIDRIDs(b *testing.B) {
 	}
 }
 
+func BenchmarkGetCIDRLabelsConcurrent(b *testing.B) {
+	prefixes := make([]netip.Prefix, 0, 16)
+	octets := [4]byte{0, 0, 1, 1}
+	for i := 0; i < 16; i++ {
+		octets[0], octets[1] = byte(rand.Intn(256)), byte(rand.Intn(256))
+		prefixes = append(prefixes, netip.PrefixFrom(netip.AddrFrom4(octets), 32))
+	}
+
+	for _, goroutines := range []int{1, 2, 4, 16, 32, 48} {
+		b.Run(strconv.Itoa(goroutines), func(b *testing.B) {
+			b.ResetTimer()
+			for i := 0; i < b.N; i++ {
+				b.StopTimer()
+				start := make(chan struct{})
+				var wg sync.WaitGroup
+
+				wg.Add(goroutines)
+				for j := 0; j < goroutines; j++ {
+					go func() {
+						defer wg.Done()
+
+						<-start
+
+						for k := 0; k < 64; k++ {
+							_ = GetCIDRLabels(prefixes[rand.Intn(len(prefixes))])
+						}
+					}()
+				}
+
+				b.StartTimer()
+				close(start)
+				wg.Wait()
+			}
+		})
+	}
+}
+
 // BenchmarkCIDRLabelsCacheHeapUsageIPv4 should be run with -benchtime=1x
 func BenchmarkCIDRLabelsCacheHeapUsageIPv4(b *testing.B) {
 	b.Skip()