chore: remote write exporter retry on 429

.chloggen/prometheus-remote-write-exporter-retry-429.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: prometheusremotewriteexporter
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Add `exporter.prometheusremotewritexporter.RetryOn429` feature gate to retry on http status code 429 response.
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [ 31032 ]
+
+# (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: The feature gate is initially disabled by default.
+
+# 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: []

exporter/prometheusremotewriteexporter/README.md

@@ -100,6 +100,13 @@ Several helper files are leveraged to provide additional capabilities automatica
 - [TLS and mTLS settings](https://github.com/open-telemetry/opentelemetry-collector/blob/main/config/configtls/README.md)
 - [Retry and timeout settings](https://github.com/open-telemetry/opentelemetry-collector/blob/main/exporter/exporterhelper/README.md), note that the exporter doesn't support `sending_queue` but provides `remote_write_queue`.
 
+### Feature gates
+This exporter has feature gate: `exporter.prometheusremotewritexporter.RetryOn429`.
+When this feature gate is enable the prometheus remote write exporter will retry on 429 http status code with the provided retry configuration.
+It currently doesn't support respecting the http header `Retry-After` if provided since the retry library used doesn't support this feature.
+
+To enable it run collector with enabled feature gate `exporter.prometheusremotewritexporter.RetryOn429`. This can be done by executing it with one additional parameter - `--feature-gates=telemetry.useOtelForInternalMetrics`.
+
 ## Metric names and labels normalization
 
 OpenTelemetry metric names and attributes are normalized to be compliant with Prometheus naming rules. [Details on this normalization process are described in the Prometheus translator module](../../pkg/translator/prometheus/).

exporter/prometheusremotewriteexporter/exporter.go

@@ -66,6 +66,7 @@ type prwExporter struct {
 	clientSettings    *confighttp.ClientConfig
 	settings          component.TelemetrySettings
 	retrySettings     configretry.BackOffConfig
+	retryOnHTTP429    bool
 	wal               *prweWAL
 	exporterSettings  prometheusremotewrite.Settings
 	telemetry         prwTelemetry
@@ -124,6 +125,7 @@ func newPRWExporter(cfg *Config, set exporter.CreateSettings) (*prwExporter, err
 		clientSettings:    &cfg.ClientConfig,
 		settings:          set.TelemetrySettings,
 		retrySettings:     cfg.BackOffConfig,
+		retryOnHTTP429:    retryOn429FeatureGate.IsEnabled(),
 		exporterSettings: prometheusremotewrite.Settings{
 			Namespace:           cfg.Namespace,
 			ExternalLabels:      sanitizedLabels,
@@ -329,6 +331,13 @@ func (prwe *prwExporter) execute(ctx context.Context, writeReq *prompb.WriteRequ
 		if resp.StatusCode >= 500 && resp.StatusCode < 600 {
 			return rerr
 		}
+
+		// 429 errors are recoverable and the exporter should retry if RetryOnHTTP429 enabled
+		// Reference: https://github.com/prometheus/prometheus/pull/12677
+		if prwe.retryOnHTTP429 && resp.StatusCode == 429 {
+			return rerr
+		}
+
 		return backoff.Permanent(consumererror.NewPermanent(rerr))
 	}
 

exporter/prometheusremotewriteexporter/exporter_test.go

@@ -1051,6 +1051,7 @@ func TestRetries(t *testing.T) {
 		serverErrorCount int // number of times server should return error
 		expectedAttempts int
 		httpStatus       int
+		RetryOnHTTP429   bool
 		assertError      assert.ErrorAssertionFunc
 		assertErrorType  assert.ErrorAssertionFunc
 		ctx              context.Context
@@ -1060,15 +1061,37 @@ func TestRetries(t *testing.T) {
 			3,
 			4,
 			http.StatusInternalServerError,
+			false,
+			assert.NoError,
+			assert.NoError,
+			context.Background(),
+		},
+		{
+			"test 429 should retry",
+			3,
+			4,
+			http.StatusTooManyRequests,
+			true,
 			assert.NoError,
 			assert.NoError,
 			context.Background(),
 		},
+		{
+			"test 429 should not retry",
+			4,
+			1,
+			http.StatusTooManyRequests,
+			false,
+			assert.Error,
+			assertPermanentConsumerError,
+			context.Background(),
+		},
 		{
 			"test 4xx should not retry",
 			4,
 			1,
 			http.StatusBadRequest,
+			false,
 			assert.Error,
 			assertPermanentConsumerError,
 			context.Background(),
@@ -1078,6 +1101,7 @@ func TestRetries(t *testing.T) {
 			4,
 			0,
 			http.StatusInternalServerError,
+			false,
 			assert.Error,
 			assertPermanentConsumerError,
 			canceledContext(),
@@ -1103,8 +1127,9 @@ func TestRetries(t *testing.T) {
 
 			// Create the prwExporter
 			exporter := &prwExporter{
-				endpointURL: endpointURL,
-				client:      http.DefaultClient,
+				endpointURL:    endpointURL,
+				client:         http.DefaultClient,
+				retryOnHTTP429: tt.RetryOnHTTP429,
 				retrySettings: configretry.BackOffConfig{
 					Enabled: true,
 				},

exporter/prometheusremotewriteexporter/factory.go

@@ -14,11 +14,19 @@ import (
 	"go.opentelemetry.io/collector/config/configretry"
 	"go.opentelemetry.io/collector/exporter"
 	"go.opentelemetry.io/collector/exporter/exporterhelper"
+	"go.opentelemetry.io/collector/featuregate"
 
 	"github.com/open-telemetry/opentelemetry-collector-contrib/exporter/prometheusremotewriteexporter/internal/metadata"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/resourcetotelemetry"
 )
 
+var retryOn429FeatureGate = featuregate.GlobalRegistry().MustRegister(
+	"exporter.prometheusremotewritexporter.RetryOn429",
+	featuregate.StageAlpha,
+	featuregate.WithRegisterFromVersion("v0.101.0"),
+	featuregate.WithRegisterDescription("When enabled, the Prometheus remote write exporter will retry 429 http status code. Requires exporter.prometheusremotewritexporter.metrics.RetryOn429 to be enabled."),
+)
+
 // NewFactory creates a new Prometheus Remote Write exporter.
 func NewFactory() exporter.Factory {
 	return exporter.NewFactory(

exporter/prometheusremotewriteexporter/go.mod

@@ -22,6 +22,7 @@ require (
 	go.opentelemetry.io/collector/confmap v0.100.0
 	go.opentelemetry.io/collector/consumer v0.100.0
 	go.opentelemetry.io/collector/exporter v0.100.0
+	go.opentelemetry.io/collector/featuregate v1.7.0
 	go.opentelemetry.io/collector/pdata v1.7.0
 	go.opentelemetry.io/otel v1.26.0
 	go.opentelemetry.io/otel/metric v1.26.0
@@ -67,7 +68,6 @@ require (
 	go.opentelemetry.io/collector/config/internal v0.100.0 // indirect
 	go.opentelemetry.io/collector/extension v0.100.0 // indirect
 	go.opentelemetry.io/collector/extension/auth v0.100.0 // indirect
-	go.opentelemetry.io/collector/featuregate v1.7.0 // indirect
 	go.opentelemetry.io/collector/receiver v0.100.0 // indirect
 	go.opentelemetry.io/collector/semconv v0.100.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.51.0 // indirect