[exporter][batching] configuration and config validation for bytes ba…

…sed batching (#12154)

<!--Ex. Fixing a bug - Describe the bug and how this fixes the issue.
Ex. Adding a feature - Explain what this achieves.-->
#### Description

This PR adds config API that will be used for serialized bytes based
batching.

We will deprecate `MinSizeConfig` and `MaxSizeConfig` in favor of:

```
type SizeConfig struct {
	Sizer string `mapstructure:"sizer"`
	MinSize int `mapstructure:"mix_size"`
	MaxSize int `mapstructure:"max_size"`
}
```

<!-- Issue number if applicable -->
#### Link to tracking issue
#3262
#12303

<!--Describe what testing was performed and which tests were added.-->
#### Testing

<!--Describe the documentation added.-->
#### Documentation

<!--Please delete paragraphs that you did not use before submitting.-->

---------

Co-authored-by: Dmitrii Anoshin <[email protected]>

.chloggen/config-for-bytes-based-batchin.yaml

@@ -0,0 +1,25 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. otlpreceiver)
+component: exporterhelper
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Adds the config API to support serialized bytes based batching
+
+# One or more tracking issues or pull requests related to the change
+issues: [3262]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:
+
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: [api]

exporter/exporterbatcher/config.go

@@ -19,10 +19,21 @@ type Config struct {
 	// FlushTimeout sets the time after which a batch will be sent regardless of its size.
 	FlushTimeout time.Duration `mapstructure:"flush_timeout"`
 
+	SizeConfig `mapstructure:",squash"`
+
+	// Deprecated. Ignored if SizeConfig is set.
 	MinSizeConfig `mapstructure:",squash"`
+	// Deprecated. Ignored if SizeConfig is set.
 	MaxSizeConfig `mapstructure:",squash"`
 }
 
+type SizeConfig struct {
+	Sizer SizerType `mapstructure:"sizer"`
+
+	MinSize int `mapstructure:"mix_size"`
+	MaxSize int `mapstructure:"max_size"`
+}
+
 // MinSizeConfig defines the configuration for the minimum number of items in a batch.
 // Experimental: This API is at the early stage of development and may change without backward compatibility
 // until https://github.com/open-telemetry/opentelemetry-collector/issues/8122 is resolved.
@@ -59,6 +70,19 @@ func (c Config) Validate() error {
 	return nil
 }
 
+func (c SizeConfig) Validate() error {
+	if c.MinSize < 0 {
+		return errors.New("min_size must be greater than or equal to zero")
+	}
+	if c.MaxSize < 0 {
+		return errors.New("max_size must be greater than or equal to zero")
+	}
+	if c.MaxSize != 0 && c.MaxSize < c.MinSize {
+		return errors.New("max_size must be greater than or equal to mix_size")
+	}
+	return nil
+}
+
 func NewDefaultConfig() Config {
 	return Config{
 		Enabled:      true,

exporter/exporterbatcher/config_test.go

@@ -8,9 +8,12 @@ import (
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
+	"gopkg.in/yaml.v2"
+
+	"go.opentelemetry.io/collector/confmap"
 )
 
-func TestConfig_Validate(t *testing.T) {
+func TestValidateConfig(t *testing.T) {
 	cfg := NewDefaultConfig()
 	require.NoError(t, cfg.Validate())
 
@@ -29,3 +32,52 @@ func TestConfig_Validate(t *testing.T) {
 	cfg.MinSizeItems = 20001
 	assert.EqualError(t, cfg.Validate(), "max_size_items must be greater than or equal to min_size_items")
 }
+
+func TestValidateSizeConfig(t *testing.T) {
+	cfg := SizeConfig{
+		Sizer:   SizerTypeItems,
+		MaxSize: -100,
+		MinSize: 100,
+	}
+	require.EqualError(t, cfg.Validate(), "max_size must be greater than or equal to zero")
+
+	cfg = SizeConfig{
+		Sizer:   SizerTypeBytes,
+		MaxSize: 100,
+		MinSize: -100,
+	}
+	require.EqualError(t, cfg.Validate(), "min_size must be greater than or equal to zero")
+
+	cfg = SizeConfig{
+		Sizer:   SizerTypeBytes,
+		MaxSize: 100,
+		MinSize: 200,
+	}
+	require.EqualError(t, cfg.Validate(), "max_size must be greater than or equal to mix_size")
+}
+
+func TestSizeUnmarshaler(t *testing.T) {
+	var rawConf map[string]any
+	cfg := NewDefaultConfig()
+
+	require.NoError(t, yaml.Unmarshal([]byte(`sizer: bytes`), &rawConf))
+	require.NoError(t, confmap.NewFromStringMap(rawConf).Unmarshal(&cfg))
+	require.NoError(t, cfg.Validate())
+
+	require.NoError(t, yaml.Unmarshal([]byte(`sizer: "bytes"`), &rawConf))
+	require.NoError(t, confmap.NewFromStringMap(rawConf).Unmarshal(&cfg))
+	require.NoError(t, cfg.Validate())
+
+	require.NoError(t, yaml.Unmarshal([]byte(`sizer: items`), &rawConf))
+	require.NoError(t, confmap.NewFromStringMap(rawConf).Unmarshal(&cfg))
+	require.NoError(t, cfg.Validate())
+
+	require.NoError(t, yaml.Unmarshal([]byte(`sizer: 'items'`), &rawConf))
+	require.NoError(t, confmap.NewFromStringMap(rawConf).Unmarshal(&cfg))
+	require.NoError(t, cfg.Validate())
+
+	require.NoError(t, yaml.Unmarshal([]byte(`sizer: invalid`), &rawConf))
+	require.EqualError(t,
+		confmap.NewFromStringMap(rawConf).Unmarshal(&cfg),
+		"decoding failed due to the following error(s):\n\nerror decoding 'sizer': invalid sizer: \"invalid\"")
+}

exporter/exporterbatcher/sizer_type.go

@@ -0,0 +1,28 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package exporterbatcher // import "go.opentelemetry.io/collector/exporter/exporterbatcher"
+
+import (
+	"fmt"
+)
+
+type SizerType string
+
+const (
+	SizerTypeItems SizerType = "items"
+	SizerTypeBytes SizerType = "bytes"
+)
+
+// UnmarshalText implements TextUnmarshaler interface.
+func (s *SizerType) UnmarshalText(text []byte) error {
+	switch str := string(text); str {
+	case string(SizerTypeItems):
+		*s = SizerTypeItems
+	case string(SizerTypeBytes):
+		*s = SizerTypeBytes
+	default:
+		return fmt.Errorf("invalid sizer: %q", str)
+	}
+	return nil
+}

exporter/exporterhelper/xexporterhelper/go.mod

@@ -102,3 +102,5 @@ replace go.opentelemetry.io/collector/extension/extensiontest => ../../../extens
 replace go.opentelemetry.io/collector/featuregate => ../../../featuregate
 
 replace go.opentelemetry.io/collector/extension/xextension => ../../../extension/xextension
+
+replace go.opentelemetry.io/collector/confmap => ../../../confmap

exporter/exportertest/go.mod

@@ -92,3 +92,5 @@ replace go.opentelemetry.io/collector/extension/extensiontest => ../../extension
 replace go.opentelemetry.io/collector/featuregate => ../../featuregate
 
 replace go.opentelemetry.io/collector/extension/xextension => ../../extension/xextension
+
+replace go.opentelemetry.io/collector/confmap => ../../confmap

exporter/go.mod

@@ -8,6 +8,7 @@ require (
 	go.opentelemetry.io/collector/component v0.120.0
 	go.opentelemetry.io/collector/component/componenttest v0.120.0
 	go.opentelemetry.io/collector/config/configretry v1.26.0
+	go.opentelemetry.io/collector/confmap v1.24.0
 	go.opentelemetry.io/collector/consumer v1.26.0
 	go.opentelemetry.io/collector/consumer/consumererror v0.120.0
 	go.opentelemetry.io/collector/consumer/consumertest v0.120.0
@@ -26,16 +27,23 @@ require (
 	go.uber.org/goleak v1.3.0
 	go.uber.org/multierr v1.11.0
 	go.uber.org/zap v1.27.0
+	gopkg.in/yaml.v2 v2.4.0
 )
 
 require (
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/go-logr/logr v1.4.2 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
+	github.com/go-viper/mapstructure/v2 v2.2.1 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/google/uuid v1.6.0 // indirect
 	github.com/hashicorp/go-version v1.7.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
+	github.com/knadh/koanf/maps v0.1.1 // indirect
+	github.com/knadh/koanf/providers/confmap v0.1.0 // indirect
+	github.com/knadh/koanf/v2 v2.1.2 // indirect
+	github.com/mitchellh/copystructure v1.2.0 // indirect
+	github.com/mitchellh/reflectwalk v1.0.2 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
@@ -97,3 +105,5 @@ replace go.opentelemetry.io/collector/extension/extensiontest => ../extension/ex
 replace go.opentelemetry.io/collector/featuregate => ../featuregate
 
 replace go.opentelemetry.io/collector/extension/xextension => ../extension/xextension
+
+replace go.opentelemetry.io/collector/confmap => ../confmap