labels: Reduce allocated memory by Hash method in edge cases; Added tests.

Old:
/tmp/___BenchmarkLabels_Hash_in_github_com_prometheus_prometheus_pkg_labels -test.v -test.bench ^\QBenchmarkLabels_Hash\E$ -test.run ^$
goos: linux
goarch: amd64
pkg: github.com/prometheus/prometheus/pkg/labels
BenchmarkLabels_Hash
BenchmarkLabels_Hash/typical_labels_under_1KB
BenchmarkLabels_Hash/typical_labels_under_1KB-12         	 5366161	       259 ns/op	       0 B/op	       0 allocs/op
BenchmarkLabels_Hash/bigger_labels_over_1KB
BenchmarkLabels_Hash/bigger_labels_over_1KB-12           	 1700371	       767 ns/op	    2048 B/op	       1 allocs/op
BenchmarkLabels_Hash/extremely_large_label_value_10MB
BenchmarkLabels_Hash/extremely_large_label_value_10MB-12 	     356	   3743115 ns/op	10523442 B/op	       1 allocs/op
PASS

New:
/tmp/___BenchmarkLabels_Hash_in_github_com_prometheus_prometheus_pkg_labels -test.v -test.bench ^\QBenchmarkLabels_Hash\E$ -test.run ^$
goos: linux
goarch: amd64
pkg: github.com/prometheus/prometheus/pkg/labels
BenchmarkLabels_Hash
BenchmarkLabels_Hash/typical_labels_under_1KB
BenchmarkLabels_Hash/typical_labels_under_1KB-12         	 4758883	       259 ns/op	       0 B/op	       0 allocs/op
BenchmarkLabels_Hash/bigger_labels_over_1KB
BenchmarkLabels_Hash/bigger_labels_over_1KB-12           	 3324492	       357 ns/op	      80 B/op	       1 allocs/op
BenchmarkLabels_Hash/extremely_large_label_value_10MB
BenchmarkLabels_Hash/extremely_large_label_value_10MB-12 	    1087	   1083949 ns/op	    9734 B/op	       1 allocs/op
PASS

Process finished with exit code 0

Signed-off-by: Bartlomiej Plotka <bwplotka@gmail.com>

pkg/labels/labels.go

@@ -18,6 +18,7 @@ import (
 	"encoding/json"
 	"sort"
 	"strconv"
+	"unsafe"
 
 	"github.com/cespare/xxhash"
 )
@@ -33,6 +34,8 @@ const (
 	labelSep = '\xfe'
 )
 
+var seps = []byte{'\xff'}
+
 // Label is a key/value pair of strings.
 type Label struct {
 	Name, Value string
@@ -132,11 +135,44 @@ func (ls Labels) MatchLabels(on bool, names ...string) Labels {
 	return matchedLabels
 }
 
+// noescape hides a pointer from escape analysis.  noescape is
+// the identity function but escape analysis doesn't think the
+// output depends on the input. noescape is inlined and currently
+// compiles down to zero instructions.
+// USE CAREFULLY!
+// This was copied from the runtime; see issues 23382 and 7921.
+//go:nosplit
+//go:nocheckptr
+func noescape(p unsafe.Pointer) unsafe.Pointer {
+	x := uintptr(p)
+	return unsafe.Pointer(x ^ 0) //nolint:staticcheck
+}
+
+//go:nosplit
+//go:checkptr
+func noAllocBytes(buf string) []byte {
+	return *(*[]byte)(unsafe.Pointer(&buf))
+}
+
 // Hash returns a hash value for the label set.
 func (ls Labels) Hash() uint64 {
 	b := make([]byte, 0, 1024)
+	for i, v := range ls {
+		if len(b)+len(v.Name)+len(v.Value)+2 >= cap(b) {
+			// If labels entry is 1KB+ allocate do not allocate whole entry.
+			h := xxhash.New()
+			// This allows b to be still on stack and reused. This is safe as xxhash.x
+			// is never used outside of this function.
+			_, _ = h.Write(*(*[]byte)(noescape(unsafe.Pointer(&b))))
+			for _, v := range ls[i:] {
+				_, _ = h.Write(noAllocBytes(v.Name))
+				_, _ = h.Write(seps)
+				_, _ = h.Write(noAllocBytes(v.Value))
+				_, _ = h.Write(seps)
+			}
+			return h.Sum64()
+		}
 
-	for _, v := range ls {
 		b = append(b, v.Name...)
 		b = append(b, sep)
 		b = append(b, v.Value...)

pkg/labels/labels_test.go

@@ -14,6 +14,8 @@
 package labels
 
 import (
+	"fmt"
+	"strings"
 	"testing"
 
 	"github.com/prometheus/prometheus/util/testutil"
@@ -629,3 +631,68 @@ func TestBuilder_Labels(t *testing.T) {
 		}).Labels(),
 	)
 }
+
+func TestLabels_Hash(t *testing.T) {
+	lbls := Labels{
+		{Name: "foo", Value: "bar"},
+		{Name: "baz", Value: "qux"},
+	}
+	testutil.Equals(t, lbls.Hash(), lbls.Hash())
+	testutil.Assert(t, lbls.Hash() != Labels{lbls[1], lbls[0]}.Hash(), "unordered labels match.")
+	testutil.Assert(t, lbls.Hash() != Labels{lbls[0]}.Hash(), "different labels match.")
+}
+
+var benchmarkLabelsResult uint64
+
+func BenchmarkLabels_Hash(b *testing.B) {
+	for _, tcase := range []struct {
+		name string
+		lbls Labels
+	}{
+		{
+			name: "typical labels under 1KB",
+			lbls: func() Labels {
+				lbls := make(Labels, 10)
+				for i := 0; i < len(lbls); i++ {
+					// Label ~20B name, 50B value.
+					lbls[i] = Label{Name: fmt.Sprintf("abcdefghijabcdefghijabcdefghij%d", i), Value: fmt.Sprintf("abcdefghijabcdefghijabcdefghijabcdefghijabcdefghij%d", i)}
+				}
+				return lbls
+			}(),
+		},
+		{
+			name: "bigger labels over 1KB",
+			lbls: func() Labels {
+				lbls := make(Labels, 10)
+				for i := 0; i < len(lbls); i++ {
+					//Label ~50B name, 50B value.
+					lbls[i] = Label{Name: fmt.Sprintf("abcdefghijabcdefghijabcdefghijabcdefghijabcdefghij%d", i), Value: fmt.Sprintf("abcdefghijabcdefghijabcdefghijabcdefghijabcdefghij%d", i)}
+				}
+				return lbls
+			}(),
+		},
+		{
+			name: "extremely large label value 10MB",
+			lbls: func() Labels {
+				lbl := &strings.Builder{}
+				lbl.Grow(1024 * 1024 * 10) // 10MB.
+				word := "abcdefghij"
+				for i := 0; i < lbl.Cap()/len(word); i++ {
+					_, _ = lbl.WriteString(word)
+				}
+				return Labels{{Name: "__name__", Value: lbl.String()}}
+			}(),
+		},
+	} {
+		b.Run(tcase.name, func(b *testing.B) {
+			var h uint64
+
+			b.ReportAllocs()
+			b.ResetTimer()
+			for i := 0; i < b.N; i++ {
+				h = tcase.lbls.Hash()
+			}
+			benchmarkLabelsResult = h
+		})
+	}
+}