app/vmselect: add ability to pass match[], start and end to /api/v1/labels

This makes the `/api/v1/labels` handler consistent with already existing functionality for `/api/v1/label/.../values`.

See https://github.com/prometheus/prometheus/issues/6178 for more details.

README.md

@@ -405,6 +405,18 @@ VictoriaMetrics supports the following handlers from [Prometheus querying API](h
 
 These handlers can be queried from Prometheus-compatible clients such as Grafana or curl.
 
+VictoriaMetrics accepts additional args for `/api/v1/labels` and `/api/v1/label/.../values` handlers.
+See [this feature request](https://github.com/prometheus/prometheus/issues/6178) for details:
+
+* Any number [time series selectors](https://prometheus.io/docs/prometheus/latest/querying/basics/#time-series-selectors) via `match[]` query arg.
+* Optional `start` and `end` query args for limiting the time range for the selected labels or label values.
+
+Additionally VictoriaMetrics provides the following handlers:
+
+* `/api/v1/series/count` - it returns the total number of time series in the database. Note that this handler scans all the inverted index,
+  so it can be slow if the database contains tens of millions of time series.
+* `/api/v1/labels/count` - it returns a list of `label: values_count` entries. It can be used for determining labels with the maximum number of values.
+
 
 ### How to build from sources
 

app/vmselect/netstorage/netstorage.go

@@ -432,13 +432,10 @@ func GetLabelEntries(deadline Deadline) ([]storage.TagEntry, error) {
 	// Sort labelEntries by the number of label values in each entry.
 	sort.Slice(labelEntries, func(i, j int) bool {
 		a, b := labelEntries[i].Values, labelEntries[j].Values
-		if len(a) < len(b) {
-			return true
+		if len(a) != len(b) {
+			return len(a) > len(b)
 		}
-		if len(a) > len(b) {
-			return false
-		}
-		return labelEntries[i].Key < labelEntries[j].Key
+		return labelEntries[i].Key > labelEntries[j].Key
 	})
 
 	return labelEntries, nil

app/vmselect/prometheus/prometheus.go

@@ -285,6 +285,13 @@ func labelValuesWithMatches(labelName string, matches []string, start, end int64
 	if err != nil {
 		return nil, err
 	}
+	for i, tfs := range tagFilterss {
+		// Add `labelName!=''` tag filter in order to filter out series without the labelName.
+		tagFilterss[i] = append(tfs, storage.TagFilter{
+			Key:        []byte(labelName),
+			IsNegative: true,
+		})
+	}
 	if start >= end {
 		end = start + defaultStep
 	}
@@ -346,9 +353,37 @@ var labelsCountDuration = metrics.NewSummary(`vm_request_duration_seconds{path="
 func LabelsHandler(w http.ResponseWriter, r *http.Request) error {
 	startTime := time.Now()
 	deadline := getDeadline(r)
-	labels, err := netstorage.GetLabels(deadline)
-	if err != nil {
-		return fmt.Errorf("cannot obtain labels: %s", err)
+
+	if err := r.ParseForm(); err != nil {
+		return fmt.Errorf("cannot parse form values: %s", err)
+	}
+	var labels []string
+	if len(r.Form["match[]"]) == 0 && len(r.Form["start"]) == 0 && len(r.Form["end"]) == 0 {
+		var err error
+		labels, err = netstorage.GetLabels(deadline)
+		if err != nil {
+			return fmt.Errorf("cannot obtain labels: %s", err)
+		}
+	} else {
+		// Extended functionality that allows filtering by label filters and time range
+		// i.e. /api/v1/labels?match[]=foobar{baz="abc"}&start=...&end=...
+		matches := r.Form["match[]"]
+		if len(matches) == 0 {
+			matches = []string{"{__name__!=''}"}
+		}
+		ct := currentTime()
+		end, err := getTime(r, "end", ct)
+		if err != nil {
+			return err
+		}
+		start, err := getTime(r, "start", end-defaultStep)
+		if err != nil {
+			return err
+		}
+		labels, err = labelsWithMatches(matches, start, end, deadline)
+		if err != nil {
+			return fmt.Errorf("cannot obtain labels for match[]=%q, start=%d, end=%d: %s", matches, start, end, err)
+		}
 	}
 
 	w.Header().Set("Content-Type", "application/json")
@@ -357,6 +392,51 @@ func LabelsHandler(w http.ResponseWriter, r *http.Request) error {
 	return nil
 }
 
+func labelsWithMatches(matches []string, start, end int64, deadline netstorage.Deadline) ([]string, error) {
+	if len(matches) == 0 {
+		logger.Panicf("BUG: matches must be non-empty")
+	}
+	tagFilterss, err := getTagFilterssFromMatches(matches)
+	if err != nil {
+		return nil, err
+	}
+	if start >= end {
+		end = start + defaultStep
+	}
+	sq := &storage.SearchQuery{
+		MinTimestamp: start,
+		MaxTimestamp: end,
+		TagFilterss:  tagFilterss,
+	}
+	rss, err := netstorage.ProcessSearchQuery(sq, false, deadline)
+	if err != nil {
+		return nil, fmt.Errorf("cannot fetch data for %q: %s", sq, err)
+	}
+
+	m := make(map[string]struct{})
+	var mLock sync.Mutex
+	err = rss.RunParallel(func(rs *netstorage.Result, workerID uint) {
+		mLock.Lock()
+		tags := rs.MetricName.Tags
+		for i := range tags {
+			t := &tags[i]
+			m[string(t.Key)] = struct{}{}
+		}
+		m["__name__"] = struct{}{}
+		mLock.Unlock()
+	})
+	if err != nil {
+		return nil, fmt.Errorf("error when data fetching: %s", err)
+	}
+
+	labels := make([]string, 0, len(m))
+	for label := range m {
+		labels = append(labels, label)
+	}
+	sort.Strings(labels)
+	return labels, nil
+}
+
 var labelsDuration = metrics.NewSummary(`vm_request_duration_seconds{path="/api/v1/labels"}`)
 
 // SeriesCountHandler processes /api/v1/series/count request.