lib/storage: improve performance for /api/v1/labels and /api/v1/label/.../values endpoints when match[] filter matches small number of time series

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2978

docs/CHANGELOG.md

@@ -16,6 +16,7 @@ The following tip changes can be tested by building VictoriaMetrics components f
 ## v1.79.x long-time support release (LTS)
 
 * BUGFIX: prevent from excess CPU usage when the storage enters [read-only mode](https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#readonly-mode).
+* BUGFIX: improve performance for requests to [/api/v1/labels](https://docs.victoriametrics.com/url-examples.html#apiv1labels) and [/api/v1/label/.../values](https://docs.victoriametrics.com/url-examples.html#apiv1labelvalues) when the filter in the `match[]` query arg matches small number of time series. The performance for this case has been reduced in [v1.78.0](https://docs.victoriametrics.com/CHANGELOG.html#v1780). See [this](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2978) and [this](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1533) issues.
 
 ## [v1.79.2](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.79.2)
 

lib/storage/index_db.go

@@ -815,9 +815,13 @@ func (is *indexSearch) searchLabelNamesWithFiltersOnDate(qt *querytracer.Tracer,
 	if err != nil {
 		return err
 	}
-	if filter != nil && filter.Len() == 0 {
+	if filter != nil && filter.Len() <= 100e3 {
-		qt.Printf("found zero label names for filter=%s", tfss)
+		// It is faster to obtain label names by metricIDs from the filter
-		return nil
+		// instead of scanning the inverted index for the matching filters.
+		// This hould help https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2978
+		metricIDs := filter.AppendTo(nil)
+		qt.Printf("sort %d metricIDs", len(metricIDs))
+		return is.getLabelNamesForMetricIDs(qt, metricIDs, lns, maxLabelNames)
 	}
 	var prevLabelName []byte
 	ts := &is.ts
@@ -877,6 +881,41 @@ func (is *indexSearch) searchLabelNamesWithFiltersOnDate(qt *querytracer.Tracer,
 	return nil
 }
 
+func (is *indexSearch) getLabelNamesForMetricIDs(qt *querytracer.Tracer, metricIDs []uint64, lns map[string]struct{}, maxLabelNames int) error {
+	lns["__name__"] = struct{}{}
+	var mn MetricName
+	foundLabelNames := 0
+	var buf []byte
+	for _, metricID := range metricIDs {
+		var err error
+		buf, err = is.searchMetricNameWithCache(buf[:0], metricID)
+		if err != nil {
+			if err == io.EOF {
+				// It is likely the metricID->metricName entry didn't propagate to inverted index yet.
+				// Skip this metricID for now.
+				continue
+			}
+			return fmt.Errorf("cannot find metricName by metricID %d: %w", metricID, err)
+		}
+		if err := mn.Unmarshal(buf); err != nil {
+			return fmt.Errorf("cannot unmarshal metricName %q: %w", buf, err)
+		}
+		for _, tag := range mn.Tags {
+			_, ok := lns[string(tag.Key)]
+			if !ok {
+				foundLabelNames++
+				lns[string(tag.Key)] = struct{}{}
+				if len(lns) >= maxLabelNames {
+					qt.Printf("hit the limit on the number of unique label names: %d", maxLabelNames)
+					return nil
+				}
+			}
+		}
+	}
+	qt.Printf("get %d distinct label names from %d metricIDs", foundLabelNames, len(metricIDs))
+	return nil
+}
+
 // SearchLabelValuesWithFiltersOnTimeRange returns label values for the given labelName, tfss and tr.
 func (db *indexDB) SearchLabelValuesWithFiltersOnTimeRange(qt *querytracer.Tracer, labelName string, tfss []*TagFilters, tr TimeRange,
 	maxLabelValues, maxMetrics int, deadline uint64) ([]string, error) {
@@ -972,9 +1011,13 @@ func (is *indexSearch) searchLabelValuesWithFiltersOnDate(qt *querytracer.Tracer
 	if err != nil {
 		return err
 	}
-	if filter != nil && filter.Len() == 0 {
+	if filter != nil && filter.Len() < 100e3 {
-		qt.Printf("found zero label values for filter=%s", tfss)
+		// It is faster to obtain label names by metricIDs from the filter
-		return nil
+		// instead of scanning the inverted index for the matching filters.
+		// This hould help https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2978
+		metricIDs := filter.AppendTo(nil)
+		qt.Printf("sort %d metricIDs", len(metricIDs))
+		return is.getLabelValuesForMetricIDs(qt, lvs, labelName, metricIDs, maxLabelValues)
 	}
 	if labelName == "__name__" {
 		// __name__ label is encoded as empty string in indexdb.
@@ -1033,6 +1076,39 @@ func (is *indexSearch) searchLabelValuesWithFiltersOnDate(qt *querytracer.Tracer
 	return nil
 }
 
+func (is *indexSearch) getLabelValuesForMetricIDs(qt *querytracer.Tracer, lvs map[string]struct{}, labelName string, metricIDs []uint64, maxLabelValues int) error {
+	var mn MetricName
+	foundLabelValues := 0
+	var buf []byte
+	for _, metricID := range metricIDs {
+		var err error
+		buf, err = is.searchMetricNameWithCache(buf[:0], metricID)
+		if err != nil {
+			if err == io.EOF {
+				// It is likely the metricID->metricName entry didn't propagate to inverted index yet.
+				// Skip this metricID for now.
+				continue
+			}
+			return fmt.Errorf("cannot find metricName by metricID %d: %w", metricID, err)
+		}
+		if err := mn.Unmarshal(buf); err != nil {
+			return fmt.Errorf("cannot unmarshal metricName %q: %w", buf, err)
+		}
+		tagValue := mn.GetTagValue(labelName)
+		_, ok := lvs[string(tagValue)]
+		if !ok {
+			foundLabelValues++
+			lvs[string(tagValue)] = struct{}{}
+			if len(lvs) >= maxLabelValues {
+				qt.Printf("hit the limit on the number of unique label values for label %q: %d", labelName, maxLabelValues)
+				return nil
+			}
+		}
+	}
+	qt.Printf("get %d distinct values for label %q from %d metricIDs", foundLabelValues, labelName, len(metricIDs))
+	return nil
+}
+
 // SearchTagValueSuffixes returns all the tag value suffixes for the given tagKey and tagValuePrefix on the given tr.
 //
 // This allows implementing https://graphite-api.readthedocs.io/en/latest/api.html#metrics-find or similar APIs.