Skip to content
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 27 additions & 0 deletions .chloggen/aws-subscription-unmarshaler.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
# 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. filelogreceiver)
component: awslogsencodingextension

# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
note: Add support for cloudwatch logs coming from subscription filters.

# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
issues: [38820]

# (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:

# If your change doesn't affect end users or the exported elements of any package,
# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
# 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: [user]

This file was deleted.

13 changes: 7 additions & 6 deletions extension/encoding/awslogsencodingextension/extension.go
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ import (
"go.opentelemetry.io/collector/pdata/plog"

"github.com/open-telemetry/opentelemetry-collector-contrib/extension/encoding"
subscriptionfilter "github.com/open-telemetry/opentelemetry-collector-contrib/extension/encoding/awslogsencodingextension/unmarshaler/subscription-filter"
)

var _ encoding.LogsUnmarshalerExtension = (*encodingExtension)(nil)
Expand All @@ -21,12 +22,12 @@ type encodingExtension struct {
format string
}

func newExtension(cfg *Config, _ extension.Settings) (*encodingExtension, error) {
func newExtension(cfg *Config, settings extension.Settings) (*encodingExtension, error) {
switch cfg.Format {
case formatCloudWatchLogsSubscriptionFilter:
return &encodingExtension{
unmarshaler: cloudWatchLogsSubscriptionFilterUnmarshaler{},
format: cfg.Format,
unmarshaler: subscriptionfilter.NewSubscriptionFilterUnmarshaler(settings.BuildInfo),
format: formatCloudWatchLogsSubscriptionFilter,
}, nil
default:
// Format will have been validated by Config.Validate,
Expand All @@ -44,10 +45,10 @@ func (*encodingExtension) Shutdown(_ context.Context) error {
return nil
}

func (e *encodingExtension) UnmarshalLogs(record []byte) (plog.Logs, error) {
logs, err := e.unmarshaler.UnmarshalLogs(record)
func (e *encodingExtension) UnmarshalLogs(buf []byte) (plog.Logs, error) {
logs, err := e.unmarshaler.UnmarshalLogs(buf)
if err != nil {
return plog.Logs{}, fmt.Errorf("failed to unmarshal logs as '%s' format: %w", e.format, err)
return plog.Logs{}, fmt.Errorf("failed to unmarshal logs as %q format: %w", e.format, err)
}
return logs, nil
}
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,9 @@ func TestNew_CloudWatchLogsSubscriptionFilter(t *testing.T) {
e, err := newExtension(&Config{Format: formatCloudWatchLogsSubscriptionFilter}, extensiontest.NewNopSettings(extensiontest.NopType))
require.NoError(t, err)
require.NotNil(t, e)

_, err = e.UnmarshalLogs([]byte("invalid"))
require.ErrorContains(t, err, `failed to unmarshal logs as "cloudwatch_logs_subscription_filter" format`)
}

func TestNew_Unimplemented(t *testing.T) {
Expand Down
14 changes: 13 additions & 1 deletion extension/encoding/awslogsencodingextension/go.mod
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,11 @@ module github.com/open-telemetry/opentelemetry-collector-contrib/extension/encod
go 1.23.0

require (
github.com/aws/aws-lambda-go v1.47.0
github.com/json-iterator/go v1.1.12
github.com/open-telemetry/opentelemetry-collector-contrib/extension/encoding v0.122.0
github.com/open-telemetry/opentelemetry-collector-contrib/pkg/golden v0.122.0
github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatatest v0.122.0
github.com/stretchr/testify v1.10.0
go.opentelemetry.io/collector/component v1.28.2-0.20250319144947-41a9ea7f7402
go.opentelemetry.io/collector/component/componenttest v0.122.2-0.20250319144947-41a9ea7f7402
Expand All @@ -12,25 +16,27 @@ require (
go.opentelemetry.io/collector/extension v1.28.2-0.20250319144947-41a9ea7f7402
go.opentelemetry.io/collector/extension/extensiontest v0.122.2-0.20250319144947-41a9ea7f7402
go.opentelemetry.io/collector/pdata v1.28.2-0.20250319144947-41a9ea7f7402
go.opentelemetry.io/collector/semconv v0.122.2-0.20250319144947-41a9ea7f7402
go.uber.org/goleak v1.3.0
)

require (
github.com/cespare/xxhash/v2 v2.3.0 // indirect
github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // 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/open-telemetry/opentelemetry-collector-contrib/pkg/pdatautil v0.122.0 // indirect
github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
go.opentelemetry.io/auto/sdk v1.1.0 // indirect
go.opentelemetry.io/collector/featuregate v1.28.2-0.20250319144947-41a9ea7f7402 // indirect
Expand All @@ -52,3 +58,9 @@ require (
)

replace github.com/open-telemetry/opentelemetry-collector-contrib/extension/encoding => ../

replace github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatautil => ../../../pkg/pdatautil

replace github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatatest => ../../../pkg/pdatatest

replace github.com/open-telemetry/opentelemetry-collector-contrib/pkg/golden => ../../../pkg/golden
6 changes: 6 additions & 0 deletions extension/encoding/awslogsencodingextension/go.sum

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Original file line number Diff line number Diff line change
@@ -0,0 +1,140 @@
// Copyright The OpenTelemetry Authors
// SPDX-License-Identifier: Apache-2.0

package subscriptionfilter // import "github.com/open-telemetry/opentelemetry-collector-contrib/extension/encoding/awslogsencodingextension/unmarshaler/subscription-filter"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

could you move this to an internal package?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The reason this is public is so other components can use the NewSubscriptionFilterUnmarshaler function directly. For example, this would enable us to remove the cwlog code in awsfirehosereceiver.

Rather than forcing users to configure an extension, there would be a special case where the receiver will instantiate the unmarshaler directly. We could also internally create an extension, but it seems a bit unnecessarily complicated.


import (
"bytes"
"compress/gzip"
"errors"
"fmt"
"io"
"sync"
"time"

"github.com/aws/aws-lambda-go/events"
jsoniter "github.com/json-iterator/go"
"go.opentelemetry.io/collector/component"
"go.opentelemetry.io/collector/pdata/pcommon"
"go.opentelemetry.io/collector/pdata/plog"
conventions "go.opentelemetry.io/collector/semconv/v1.27.0"

"github.com/open-telemetry/opentelemetry-collector-contrib/extension/encoding/awslogsencodingextension/internal/metadata"
)

var (
errEmptyOwner = errors.New("cloudwatch log with message type 'DATA_MESSAGE' has empty owner field")
errEmptyLogGroup = errors.New("cloudwatch log with message type 'DATA_MESSAGE' has empty log group field")
errEmptyLogStream = errors.New("cloudwatch log with message type 'DATA_MESSAGE' has empty log stream field")
)

func validateLog(log events.CloudwatchLogsData) error {
switch log.MessageType {
case "DATA_MESSAGE":
if log.Owner == "" {
return errEmptyOwner
}
if log.LogGroup == "" {
return errEmptyLogGroup
}
if log.LogStream == "" {
return errEmptyLogStream
}
case "CONTROL_MESSAGE":
default:
return fmt.Errorf("cloudwatch log has invalid message type %q", log.MessageType)
}
return nil
}

type subscriptionFilterUnmarshaler struct {
buildInfo component.BuildInfo

// We need to decompress the records.
// Creating a new gzip.Reader every time is expensive.
// We can keep the gzip in cache, and take advantage
// of the continuously AWS environment or the AWS
// warm starts, in case of lambda.
// See https://docs.aws.amazon.com/lambda/latest/dg/lambda-runtime-environment.html.
gzipPool sync.Pool
}

func NewSubscriptionFilterUnmarshaler(buildInfo component.BuildInfo) plog.Unmarshaler {
return &subscriptionFilterUnmarshaler{
buildInfo: buildInfo,
gzipPool: sync.Pool{},
}
}

var _ plog.Unmarshaler = (*subscriptionFilterUnmarshaler)(nil)

// UnmarshalLogs deserializes the given record as CloudWatch Logs events
// into a plog.Logs, grouping logs by owner (account ID), log group, and
// log stream. Logs are assumed to be gzip-compressed as specified at
// https://docs.aws.amazon.com/firehose/latest/dev/writing-with-cloudwatch-logs.html.
func (f *subscriptionFilterUnmarshaler) UnmarshalLogs(compressedRecord []byte) (plog.Logs, error) {
var errDecompress error
record, ok := f.gzipPool.Get().(*gzip.Reader)
if !ok {
record, errDecompress = gzip.NewReader(bytes.NewReader(compressedRecord))
} else {
errDecompress = record.Reset(bytes.NewReader(compressedRecord))
}
if errDecompress != nil {
if record != nil {
f.gzipPool.Put(record)
}
return plog.Logs{}, fmt.Errorf("failed to decompress record: %w", errDecompress)
}
defer func() {
_ = record.Close()
f.gzipPool.Put(record)
}()

decompressedRecord, errRead := io.ReadAll(record)
if errRead != nil {
return plog.Logs{}, fmt.Errorf("failed to read decompressed record: %w", errRead)
}

var cwLog events.CloudwatchLogsData
if err := jsoniter.ConfigFastest.Unmarshal(decompressedRecord, &cwLog); err != nil {
return plog.Logs{}, fmt.Errorf("error unmarshaling data: %w", err)
}

if cwLog.MessageType == "CONTROL_MESSAGE" {
return plog.Logs{}, nil
}

if err := validateLog(cwLog); err != nil {
return plog.Logs{}, fmt.Errorf("invalid cloudwatch log: %w", err)
}

return f.createLogs(cwLog), nil
}

// createLogs create plog.Logs from the cloudwatchLog
func (f *subscriptionFilterUnmarshaler) createLogs(
cwLog events.CloudwatchLogsData,
) plog.Logs {
logs := plog.NewLogs()
rl := logs.ResourceLogs().AppendEmpty()
resourceAttrs := rl.Resource().Attributes()
resourceAttrs.PutStr(conventions.AttributeCloudProvider, conventions.AttributeCloudProviderAWS)
resourceAttrs.PutStr(conventions.AttributeCloudAccountID, cwLog.Owner)
resourceAttrs.PutEmptySlice(conventions.AttributeAWSLogGroupNames).AppendEmpty().SetStr(cwLog.LogGroup)
resourceAttrs.PutEmptySlice(conventions.AttributeAWSLogStreamNames).AppendEmpty().SetStr(cwLog.LogStream)
resourceAttrs.PutStr(conventions.AttributeAWSLogGroupNames, cwLog.LogGroup)
resourceAttrs.PutStr(conventions.AttributeAWSLogStreamNames, cwLog.LogStream)

sl := rl.ScopeLogs().AppendEmpty()
sl.Scope().SetName(metadata.ScopeName)
sl.Scope().SetVersion(f.buildInfo.Version)
for _, event := range cwLog.LogEvents {
logRecord := sl.LogRecords().AppendEmpty()
// pcommon.Timestamp is a time specified as UNIX Epoch time in nanoseconds
// but timestamp in cloudwatch logs are in milliseconds.
logRecord.SetTimestamp(pcommon.Timestamp(event.Timestamp * int64(time.Millisecond)))
logRecord.Body().SetStr(event.Message)
}
return logs
}
Loading