Cherry-pick Timestamp Validation Removal commits for XRay Exporter

.chloggen/xray-exporter-allow-random-trace-id.yaml

@@ -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: awsxrayexporter
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: "add `exporter.awsxray.skiptimestampvalidation` Alpha feature gate to remove xray timestamp restriction on first 32 bits of trace id"
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [26041]
+
+# (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]

.chloggen/xray-exporter-w3c-id-beta-feature-gate.yaml

@@ -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: awsxrayexporter
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: "Change `exporter.awsxray.skiptimestampvalidation` feature gate from Alpha to Beta"
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [26553]
+
+# (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]

exporter/awsxrayexporter/README.md

@@ -18,10 +18,10 @@ propagated by them using the `X-Amzn-Trace-Id` HTTP header. However, other gener
 supported by replacing fully-random Trace IDs with X-Ray formatted Trace IDs where necessary:
 
 > AWS X-Ray IDs are the same size as W3C Trace Context IDs but differ in that the first 32 bits of a Trace ID
-> is the Unix epoch time when the trace was started. Since X-Ray only allows submission of Trace IDs from the
-> past 30 days, received Trace IDs are checked and spans without a valid timestamp are dropped.
+> is the Unix epoch time when the trace was started. Note that X-Ray only allows submission of Trace IDs from
+> the past 30 days, otherwise the trace is dropped by X-Ray. The Exporter will not validate this timestamp.
 
-This means in order for spans to appear in X-Ray, the client SDK MUST use an X-Ray ID generator. For more
+This means that until X-Ray supports Trace Ids consisting of fully random bits, in order for spans to appear in X-Ray, the client SDK MUST use an X-Ray ID generator. For more
 information, see
 [configuring the X-Ray exporter](https://aws-otel.github.io/docs/getting-started/x-ray#configuring-the-aws-x-ray-exporter).
 

exporter/awsxrayexporter/awsxray.go

@@ -120,7 +120,8 @@ func extractResourceSpans(config component.Config, logger *zap.Logger, td ptrace
 					spans.At(k), resource,
 					config.(*Config).IndexedAttributes,
 					config.(*Config).IndexAllAttributes,
-					config.(*Config).LogGroupNames)
+					config.(*Config).LogGroupNames,
+					config.(*Config).skipTimestampValidation)
 				if localErr != nil {
 					logger.Debug("Error translating span.", zap.Error(localErr))
 					continue

exporter/awsxrayexporter/awsxray_test.go

@@ -67,14 +67,13 @@ func TestXrayAndW3CSpanTraceExport(t *testing.T) {
 func TestXrayAndW3CSpanTraceResourceExtraction(t *testing.T) {
 	td := constructXrayAndW3CSpanData()
 	logger, _ := zap.NewProduction()
-	assert.Len(t, extractResourceSpans(generateConfig(t), logger, td), 2, "2 spans have xay trace id")
+	assert.Len(t, extractResourceSpans(generateConfig(t), logger, td), 4, "4 spans have xray/w3c trace id")
 }
 
 func TestW3CSpanTraceResourceExtraction(t *testing.T) {
-	t.Skip("Flaky test, see https://github.com/open-telemetry/opentelemetry-collector-contrib/issues/9255")
 	td := constructW3CSpanData()
 	logger, _ := zap.NewProduction()
-	assert.Len(t, extractResourceSpans(generateConfig(t), logger, td), 0, "0 spans have xray trace id")
+	assert.Len(t, extractResourceSpans(generateConfig(t), logger, td), 2, "2 spans have w3c trace id")
 }
 
 func TestTelemetryEnabled(t *testing.T) {
@@ -148,7 +147,6 @@ func constructSpanData() ptrace.Traces {
 	return traces
 }
 
-// nolint:unused
 func constructW3CSpanData() ptrace.Traces {
 	resource := constructResource()
 	traces := ptrace.NewTraces()

exporter/awsxrayexporter/config.go

@@ -35,4 +35,7 @@ type Config struct {
 	LogGroupNames []string `mapstructure:"aws_log_groups"`
 	// TelemetryConfig contains the options for telemetry collection.
 	TelemetryConfig telemetry.Config `mapstructure:"telemetry,omitempty"`
+
+	// skipTimestampValidation if enabled, will skip timestamp validation logic on the trace ID
+	skipTimestampValidation bool
 }

exporter/awsxrayexporter/config_test.go

@@ -55,9 +55,10 @@ func TestLoadConfig(t *testing.T) {
 					ResourceARN:           "arn:aws:ec2:us-east1:123456789:instance/i-293hiuhe0u",
 					RoleARN:               "arn:aws:iam::123456789:role/monitoring-EKS-NodeInstanceRole",
 				},
-				IndexedAttributes:  []string{"indexed_attr_0", "indexed_attr_1"},
-				IndexAllAttributes: false,
-				LogGroupNames:      []string{"group1", "group2"},
+				IndexedAttributes:       []string{"indexed_attr_0", "indexed_attr_1"},
+				IndexAllAttributes:      false,
+				LogGroupNames:           []string{"group1", "group2"},
+				skipTimestampValidation: false,
 			},
 		},
 	}

exporter/awsxrayexporter/factory.go

@@ -19,6 +19,7 @@ import (
 
 	"go.opentelemetry.io/collector/component"
 	"go.opentelemetry.io/collector/exporter"
+	"go.opentelemetry.io/collector/featuregate"
 
 	"github.com/open-telemetry/opentelemetry-collector-contrib/internal/aws/awsutil"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/internal/aws/xray/telemetry"
@@ -31,6 +32,11 @@ const (
 	stability = component.StabilityLevelBeta
 )
 
+var skipTimestampValidationFeatureGate = featuregate.GlobalRegistry().MustRegister(
+	"exporter.awsxray.skiptimestampvalidation",
+	featuregate.StageBeta,
+	featuregate.WithRegisterDescription("Remove XRay's timestamp validation on first 32 bits of trace ID"))
+
 // NewFactory creates a factory for AWS-Xray exporter.
 func NewFactory() exporter.Factory {
 	return exporter.NewFactory(
@@ -41,7 +47,8 @@ func NewFactory() exporter.Factory {
 
 func createDefaultConfig() component.Config {
 	return &Config{
-		AWSSessionSettings: awsutil.CreateDefaultSessionConfig(),
+		AWSSessionSettings:      awsutil.CreateDefaultSessionConfig(),
+		skipTimestampValidation: skipTimestampValidationFeatureGate.IsEnabled(),
 	}
 }
 

exporter/awsxrayexporter/factory_test.go

@@ -25,6 +25,7 @@ import (
 	"go.opentelemetry.io/collector/component/componenttest"
 	"go.opentelemetry.io/collector/confmap/confmaptest"
 	"go.opentelemetry.io/collector/exporter/exportertest"
+	"go.opentelemetry.io/collector/featuregate"
 
 	"github.com/open-telemetry/opentelemetry-collector-contrib/internal/aws/awsutil"
 )
@@ -45,10 +46,39 @@ func TestCreateDefaultConfig(t *testing.T) {
 			ResourceARN:           "",
 			RoleARN:               "",
 		},
+		skipTimestampValidation: true,
 	}, "failed to create default config")
 	assert.NoError(t, componenttest.CheckConfigStruct(cfg))
 }
 
+func TestCreateDefaultConfigWithSkipTimestampValidation(t *testing.T) {
+	factory := NewFactory()
+
+	err := featuregate.GlobalRegistry().Set("exporter.awsxray.skiptimestampvalidation", true)
+	assert.NoError(t, err)
+
+	cfg := factory.CreateDefaultConfig()
+	assert.Equal(t, cfg, &Config{
+		AWSSessionSettings: awsutil.AWSSessionSettings{
+			NumberOfWorkers:       8,
+			Endpoint:              "",
+			RequestTimeoutSeconds: 30,
+			MaxRetries:            2,
+			NoVerifySSL:           false,
+			ProxyAddress:          "",
+			Region:                "",
+			LocalMode:             false,
+			ResourceARN:           "",
+			RoleARN:               "",
+		},
+		skipTimestampValidation: true,
+	}, "failed to create default config")
+	assert.NoError(t, componenttest.CheckConfigStruct(cfg))
+
+	err = featuregate.GlobalRegistry().Set("exporter.awsxray.skiptimestampvalidation", false)
+	assert.NoError(t, err)
+}
+
 func TestCreateTracesExporter(t *testing.T) {
 	cm, err := confmaptest.LoadConf(filepath.Join("testdata", "config.yaml"))
 	require.NoError(t, err)

exporter/awsxrayexporter/go.mod

@@ -12,6 +12,7 @@ require (
 	go.opentelemetry.io/collector/confmap v0.77.0
 	go.opentelemetry.io/collector/consumer v0.77.0
 	go.opentelemetry.io/collector/exporter v0.77.0
+	go.opentelemetry.io/collector/featuregate v0.77.0
 	go.opentelemetry.io/collector/pdata v1.0.0-rcv0011
 	go.opentelemetry.io/collector/semconv v0.77.0
 	go.uber.org/zap v1.24.0
@@ -34,7 +35,6 @@ require (
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	go.opencensus.io v0.24.0 // indirect
 	go.opentelemetry.io/collector v0.77.0 // indirect
-	go.opentelemetry.io/collector/featuregate v0.77.0 // indirect
 	go.opentelemetry.io/collector/receiver v0.77.0 // indirect
 	go.opentelemetry.io/otel v1.15.1 // indirect
 	go.opentelemetry.io/otel/metric v0.38.1 // indirect

exporter/awsxrayexporter/internal/translator/segment.go

@@ -76,8 +76,8 @@ var (
 )
 
 // MakeSegmentDocumentString converts an OpenTelemetry Span to an X-Ray Segment and then serialzies to JSON
-func MakeSegmentDocumentString(span ptrace.Span, resource pcommon.Resource, indexedAttrs []string, indexAllAttrs bool, logGroupNames []string) (string, error) {
-	segment, err := MakeSegment(span, resource, indexedAttrs, indexAllAttrs, logGroupNames)
+func MakeSegmentDocumentString(span ptrace.Span, resource pcommon.Resource, indexedAttrs []string, indexAllAttrs bool, logGroupNames []string, skipTimestampValidation bool) (string, error) {
+	segment, err := MakeSegment(span, resource, indexedAttrs, indexAllAttrs, logGroupNames, skipTimestampValidation)
 	if err != nil {
 		return "", err
 	}
@@ -91,7 +91,7 @@ func MakeSegmentDocumentString(span ptrace.Span, resource pcommon.Resource, inde
 }
 
 // MakeSegment converts an OpenTelemetry Span to an X-Ray Segment
-func MakeSegment(span ptrace.Span, resource pcommon.Resource, indexedAttrs []string, indexAllAttrs bool, logGroupNames []string) (*awsxray.Segment, error) {
+func MakeSegment(span ptrace.Span, resource pcommon.Resource, indexedAttrs []string, indexAllAttrs bool, logGroupNames []string, skipTimestampValidation bool) (*awsxray.Segment, error) {
 	var segmentType string
 
 	storeResource := true
@@ -103,7 +103,7 @@ func MakeSegment(span ptrace.Span, resource pcommon.Resource, indexedAttrs []str
 	}
 
 	// convert trace id
-	traceID, err := convertToAmazonTraceID(span.TraceID())
+	traceID, err := convertToAmazonTraceID(span.TraceID(), skipTimestampValidation)
 	if err != nil {
 		return nil, err
 	}
@@ -121,7 +121,7 @@ func MakeSegment(span ptrace.Span, resource pcommon.Resource, indexedAttrs []str
 		sqlfiltered, sql                                   = makeSQL(span, awsfiltered)
 		additionalAttrs                                    = addSpecialAttributes(sqlfiltered, indexedAttrs, attributes)
 		user, annotations, metadata                        = makeXRayAttributes(additionalAttrs, resource, storeResource, indexedAttrs, indexAllAttrs)
-		spanLinks, makeSpanLinkErr                         = makeSpanLinks(span.Links())
+		spanLinks, makeSpanLinkErr                         = makeSpanLinks(span.Links(), skipTimestampValidation)
 		name                                               string
 		namespace                                          string
 	)
@@ -309,7 +309,7 @@ func determineAwsOrigin(resource pcommon.Resource) string {
 //   - For example, 10:00AM December 2nd, 2016 PST in epoch time is 1480615200 seconds,
 //     or 58406520 in hexadecimal.
 //   - A 96-bit identifier for the trace, globally unique, in 24 hexadecimal digits.
-func convertToAmazonTraceID(traceID pcommon.TraceID) (string, error) {
+func convertToAmazonTraceID(traceID pcommon.TraceID, skipTimestampValidation bool) (string, error) {
 	const (
 		// maxAge of 28 days.  AWS has a 30 day limit, let's be conservative rather than
 		// hit the limit
@@ -327,13 +327,16 @@ func convertToAmazonTraceID(traceID pcommon.TraceID) (string, error) {
 		b            = [4]byte{}
 	)
 
-	// If AWS traceID originally came from AWS, no problem.  However, if oc generated
-	// the traceID, then the epoch may be outside the accepted AWS range of within the
-	// past 30 days.
-	//
-	// In that case, we return invalid traceid error
-	if delta := epochNow - epoch; delta > maxAge || delta < -maxSkew {
-		return "", fmt.Errorf("invalid xray traceid: %s", traceID)
+	// If feature gate is enabled, skip the timestamp validation logic
+	if !skipTimestampValidation {
+		// If AWS traceID originally came from AWS, no problem.  However, if oc generated
+		// the traceID, then the epoch may be outside the accepted AWS range of within the
+		// past 30 days.
+		//
+		// In that case, we return invalid traceid error
+		if delta := epochNow - epoch; delta > maxAge || delta < -maxSkew {
+			return "", fmt.Errorf("invalid xray traceid: %s", traceID)
+		}
 	}
 
 	binary.BigEndian.PutUint32(b[0:4], uint32(epoch))