fix marshaling error on invalid label value (#9828) (#9830)

* fix marshaling error on invalid label value Signed-off-by: Mauro Stettler <[email protected]> * only return label and metric Signed-off-by: Mauro Stettler <[email protected]> * changelog Signed-off-by: Mauro Stettler <[email protected]> --------- Signed-off-by: Mauro Stettler <[email protected]> (cherry picked from commit c7ce088) Co-authored-by: Mauro Stettler <[email protected]>
grafana · Nov 4, 2024 · c72946f · c72946f
1 parent ebd284e
commit c72946f
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 9 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -53,6 +53,7 @@
 * [ENHANCEMENT] Storage: Allow HTTP client settings to be tuned for GCS and Azure backends via an `http` block or corresponding CLI flags. This was already supported by the S3 backend. #9778
 * [ENHANCEMENT] Ruler: Support `group_limit` and `group_next_token` parameters in the `<prometheus-http-prefix>/api/v1/rules` endpoint. #9563
 * [ENHANCEMENT] Ingester: improved lock contention affecting read and write latencies during TSDB head compaction. #9822
+* [ENHANCEMENT] Distributor: when a label value fails validation due to invalid UTF-8 characters, don't include the invalid characters in the returned error. #9828
 * [BUGFIX] Fix issue where functions such as `rate()` over native histograms could return incorrect values if a float stale marker was present in the selected range. #9508
 * [BUGFIX] Fix issue where negation of native histograms (eg. `-some_native_histogram_series`) did nothing. #9508
 * [BUGFIX] Fix issue where `metric might not be a counter, name does not end in _total/_sum/_count/_bucket` annotation would be emitted even if `rate` or `increase` did not have enough samples to compute a result. #9508

diff --git a/pkg/distributor/validate.go b/pkg/distributor/validate.go
@@ -72,7 +72,7 @@ var (
 		validation.MaxLabelValueLengthFlag,
 	)
 	invalidLabelMsgFormat      = globalerror.SeriesInvalidLabel.Message("received a series with an invalid label: '%.200s' series: '%.200s'")
-	invalidLabelValueMsgFormat = globalerror.SeriesInvalidLabelValue.Message("received a series with invalid value in label '%.200s': '%.200s' series: '%.200s'")
+	invalidLabelValueMsgFormat = globalerror.SeriesInvalidLabelValue.Message("received a series with invalid value in label '%.200s': '%.200s' metric: '%.200s'")
 	duplicateLabelMsgFormat    = globalerror.SeriesWithDuplicateLabelNames.Message("received a series with duplicate label name, label: '%.200s' series: '%.200s'")
 	tooManyLabelsMsgFormat     = globalerror.MaxLabelNamesPerSeries.MessageWithPerTenantLimitConfig(
 		"received a series whose number of labels exceeds the limit (actual: %d, limit: %d) series: '%.200s%s'",
@@ -404,7 +404,7 @@ func validateLabels(m *sampleValidationMetrics, cfg labelValidationConfig, userI
 			return fmt.Errorf(labelNameTooLongMsgFormat, l.Name, mimirpb.FromLabelAdaptersToString(ls))
 		} else if !skipLabelValidation && !model.LabelValue(l.Value).IsValid() {
 			m.invalidLabelValue.WithLabelValues(userID, group).Inc()
-			return fmt.Errorf(invalidLabelValueMsgFormat, l.Name, l.Value, mimirpb.FromLabelAdaptersToString(ls))
+			return fmt.Errorf(invalidLabelValueMsgFormat, l.Name, strings.ToValidUTF8(l.Value, ""), unsafeMetricName)
 		} else if len(l.Value) > maxLabelValueLength {
 			m.labelValueTooLong.WithLabelValues(userID, group).Inc()
 			return fmt.Errorf(labelValueTooLongMsgFormat, l.Name, l.Value, mimirpb.FromLabelAdaptersToString(ls))

diff --git a/pkg/distributor/validate_test.go b/pkg/distributor/validate_test.go
@@ -181,13 +181,7 @@ func TestValidateLabels(t *testing.T) {
 			skipLabelCountValidation: false,
 			err: fmt.Errorf(
 				invalidLabelValueMsgFormat,
-				"label1", "abc\xfe\xfddef",
-				mimirpb.FromLabelAdaptersToString(
-					[]mimirpb.LabelAdapter{
-						{Name: model.MetricNameLabel, Value: "foo"},
-						{Name: "label1", Value: "abc\xfe\xfddef"},
-					},
-				),
+				"label1", "abcdef", "foo",
 			),
 		},
 		{