encoding/gob: speed up encoding of arrays and slices

We borrow a trick from the fmt package and avoid reflection
to walk the elements when possible. We could push further with
unsafe (and we may) but this is a good start.
Decode can benefit similarly; it will be done separately.

Use go generate (engen.go) to produce the helper functions
(enc_helpers.go).

benchmark                            old ns/op     new ns/op     delta
BenchmarkEndToEndPipe                6593          6482          -1.68%
BenchmarkEndToEndByteBuffer          3662          3684          +0.60%
BenchmarkEndToEndSliceByteBuffer     350306        351693        +0.40%
BenchmarkComplex128Slice             96347         80045         -16.92%
BenchmarkInt32Slice                  42484         26008         -38.78%
BenchmarkFloat64Slice                51143         36265         -29.09%
BenchmarkStringSlice                 53402         35077         -34.32%

LGTM=rsc
R=rsc
CC=golang-codereviews
https://golang.org/cl/156310043

src/encoding/gob/encgen.go

+// Copyright 2009 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+// +build ignore
+
+// encgen writes the helper functions for encoding. Intended to be
+// used with go generate; see the invocation in encode.go.
+
+// TODO: We could do more by being unsafe. Add a -unsafe flag?
+
+package main
+
+import (
+	"bytes"
+	"flag"
+	"fmt"
+	"go/format"
+	"log"
+	"os"
+)
+
+var output = flag.String("output", "enc_helpers.go", "file name to write")
+
+type Type struct {
+	lower   string
+	upper   string
+	zero    string
+	encoder string
+}
+
+var types = []Type{
+	{
+		"bool",
+		"Bool",
+		"false",
+		`if x {
+			state.encodeUint(1)
+		} else {
+			state.encodeUint(0)
+		}`,
+	},
+	{
+		"complex64",
+		"Complex64",
+		"0+0i",
+		`rpart := floatBits(float64(real(x)))
+		ipart := floatBits(float64(imag(x)))
+		state.encodeUint(rpart)
+		state.encodeUint(ipart)`,
+	},
+	{
+		"complex128",
+		"Complex128",
+		"0+0i",
+		`rpart := floatBits(real(x))
+		ipart := floatBits(imag(x))
+		state.encodeUint(rpart)
+		state.encodeUint(ipart)`,
+	},
+	{
+		"float32",
+		"Float32",
+		"0",
+		`bits := floatBits(float64(x))
+		state.encodeUint(bits)`,
+	},
+	{
+		"float64",
+		"Float64",
+		"0",
+		`bits := floatBits(x)
+		state.encodeUint(bits)`,
+	},
+	{
+		"int",
+		"Int",
+		"0",
+		`state.encodeInt(int64(x))`,
+	},
+	{
+		"int16",
+		"Int16",
+		"0",
+		`state.encodeInt(int64(x))`,
+	},
+	{
+		"int32",
+		"Int32",
+		"0",
+		`state.encodeInt(int64(x))`,
+	},
+	{
+		"int64",
+		"Int64",
+		"0",
+		`state.encodeInt(x)`,
+	},
+	{
+		"int8",
+		"Int8",
+		"0",
+		`state.encodeInt(int64(x))`,
+	},
+	{
+		"string",
+		"String",
+		`""`,
+		`state.encodeUint(uint64(len(x)))
+		state.b.WriteString(x)`,
+	},
+	{
+		"uint",
+		"Uint",
+		"0",
+		`state.encodeUint(uint64(x))`,
+	},
+	{
+		"uint16",
+		"Uint16",
+		"0",
+		`state.encodeUint(uint64(x))`,
+	},
+	{
+		"uint32",
+		"Uint32",
+		"0",
+		`state.encodeUint(uint64(x))`,
+	},
+	{
+		"uint64",
+		"Uint64",
+		"0",
+		`state.encodeUint(x)`,
+	},
+	{
+		"uintptr",
+		"Uintptr",
+		"0",
+		`state.encodeUint(uint64(x))`,
+	},
+	// uint8 Handled separately.
+}
+
+func main() {
+	log.SetFlags(0)
+	log.SetPrefix("helpergen: ")
+	flag.Parse()
+	if flag.NArg() != 0 {
+		log.Fatal("usage: encgen [--output filename]")
+	}
+	var b bytes.Buffer
+	fmt.Fprintf(&b, "// Created by encgen --output %s; DO NOT EDIT\n", *output)
+	fmt.Fprint(&b, header)
+	printMaps(&b, "array", "Array")
+	fmt.Fprint(&b, "\n")
+	printMaps(&b, "slice", "Slice")
+	for _, t := range types {
+		fmt.Fprintf(&b, arrayHelper, t.lower, t.upper)
+		fmt.Fprintf(&b, sliceHelper, t.lower, t.upper, t.zero, t.encoder)
+	}
+	source, err := format.Source(b.Bytes())
+	if err != nil {
+		log.Fatal("source format error:", err)
+	}
+	fd, err := os.Create(*output)
+	_, err = fd.Write(source)
+	if err != nil {
+		log.Fatal(err)
+	}
+}
+
+func printMaps(b *bytes.Buffer, lowerClass, upperClass string) {
+	fmt.Fprintf(b, "var %sHelper = map[reflect.Kind]encHelper{\n", lowerClass)
+	for _, t := range types {
+		fmt.Fprintf(b, "reflect.%s: enc%s%s,\n", t.upper, t.upper, upperClass)
+	}
+	fmt.Fprintf(b, "}\n")
+}
+
+const header = `
+// Copyright 2014 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package gob
+
+import (
+	"reflect"
+)
+
+`
+
+const arrayHelper = `
+func enc%[2]sArray(state *encoderState, v reflect.Value) bool {
+	// Can only slice if it is addressable.
+	if !v.CanAddr() {
+		return false
+	}
+	return enc%[2]sSlice(state, v.Slice(0, v.Len()))
+}
+`
+
+const sliceHelper = `
+func enc%[2]sSlice(state *encoderState, v reflect.Value) bool {
+	slice, ok := v.Interface().([]%[1]s)
+	if !ok {
+		// It is kind %[1]s but not type %[1]s. TODO: We can handle this unsafely.
+		return false
+	}
+	for _, x := range slice {
+		if x != %[3]s || state.sendZero {
+			%[4]s
+		}
+	}
+	return true
+}
+`

src/encoding/gob/encode.go

@@ -2,6 +2,8 @@
 // Use of this source code is governed by a BSD-style
 // license that can be found in the LICENSE file.
 
+//go:generate go run encgen.go -output enc_helpers.go
+
 package gob
 
 import (
@@ -13,6 +15,8 @@ import (
 
 const uint64Size = 8
 
+type encHelper func(state *encoderState, v reflect.Value) bool
+
 // encoderState is the global execution state of an instance of the encoder.
 // Field numbers are delta encoded and always increase. The field
 // number is initialized to -1 so 0 comes out as delta(1). A delta of
@@ -291,12 +295,15 @@ func (enc *Encoder) encodeStruct(b *bytes.Buffer, engine *encEngine, value refle
 }
 
 // encodeArray encodes an array.
-func (enc *Encoder) encodeArray(b *bytes.Buffer, value reflect.Value, op encOp, elemIndir int, length int) {
+func (enc *Encoder) encodeArray(b *bytes.Buffer, value reflect.Value, op encOp, elemIndir int, length int, helper encHelper) {
 	state := enc.newEncoderState(b)
 	defer enc.freeEncoderState(state)
 	state.fieldnum = -1
 	state.sendZero = true
 	state.encodeUint(uint64(length))
+	if helper != nil && helper(state, value) {
+		return
+	}
 	for i := 0; i < length; i++ {
 		elem := value.Index(i)
 		if elemIndir > 0 {
@@ -501,19 +508,21 @@ func encOpFor(rt reflect.Type, inProgress map[reflect.Type]*encOp, building map[
 			}
 			// Slices have a header; we decode it to find the underlying array.
 			elemOp, elemIndir := encOpFor(t.Elem(), inProgress, building)
+			helper := sliceHelper[t.Elem().Kind()]
 			op = func(i *encInstr, state *encoderState, slice reflect.Value) {
 				if !state.sendZero && slice.Len() == 0 {
 					return
 				}
 				state.update(i)
-				state.enc.encodeArray(state.b, slice, *elemOp, elemIndir, slice.Len())
+				state.enc.encodeArray(state.b, slice, *elemOp, elemIndir, slice.Len(), helper)
 			}
 		case reflect.Array:
 			// True arrays have size in the type.
 			elemOp, elemIndir := encOpFor(t.Elem(), inProgress, building)
+			helper := arrayHelper[t.Elem().Kind()]
 			op = func(i *encInstr, state *encoderState, array reflect.Value) {
 				state.update(i)
-				state.enc.encodeArray(state.b, array, *elemOp, elemIndir, array.Len())
+				state.enc.encodeArray(state.b, array, *elemOp, elemIndir, array.Len(), helper)
 			}
 		case reflect.Map:
 			keyOp, keyIndir := encOpFor(t.Key(), inProgress, building)

src/encoding/gob/timing_test.go

@@ -131,3 +131,67 @@ func TestCountDecodeMallocs(t *testing.T) {
 		t.Fatalf("mallocs per decode of type Bench: %v; wanted 4\n", allocs)
 	}
 }
+
+func BenchmarkComplex128Slice(b *testing.B) {
+	var buf bytes.Buffer
+	enc := NewEncoder(&buf)
+	a := make([]complex128, 1000)
+	for i := range a {
+		a[i] = 1.2 + 3.4i
+	}
+	for i := 0; i < b.N; i++ {
+		buf.Reset()
+		err := enc.Encode(a)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func BenchmarkInt32Slice(b *testing.B) {
+	var buf bytes.Buffer
+	enc := NewEncoder(&buf)
+	a := make([]int32, 1000)
+	for i := range a {
+		a[i] = 1234
+	}
+	for i := 0; i < b.N; i++ {
+		buf.Reset()
+		err := enc.Encode(a)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func BenchmarkFloat64Slice(b *testing.B) {
+	var buf bytes.Buffer
+	enc := NewEncoder(&buf)
+	a := make([]float64, 1000)
+	for i := range a {
+		a[i] = 1.23e4
+	}
+	for i := 0; i < b.N; i++ {
+		buf.Reset()
+		err := enc.Encode(a)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func BenchmarkStringSlice(b *testing.B) {
+	var buf bytes.Buffer
+	enc := NewEncoder(&buf)
+	a := make([]string, 1000)
+	for i := range a {
+		a[i] = "now is the time"
+	}
+	for i := 0; i < b.N; i++ {
+		buf.Reset()
+		err := enc.Encode(a)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}