From 852aed62f7db078af41ef87ce7de170c79368b02 Mon Sep 17 00:00:00 2001
From: Aliaksandr Valialkin <valyala@gmail.com>
Date: Mon, 16 Nov 2020 13:45:50 +0200
Subject: [PATCH] app/vmselect/prometheus: improve performance for
 `/api/v1/labels` and `/api/v1/label/<labelName>/values` on time ranges
 exceeding one day when `match[]` query arg is set

---
 app/vmselect/prometheus/prometheus.go | 101 +++++++++++++++++---------
 docs/CHANGELOG.md                     |   2 +-
 2 files changed, 66 insertions(+), 37 deletions(-)

diff --git a/app/vmselect/prometheus/prometheus.go b/app/vmselect/prometheus/prometheus.go
index bb49641f7..689785516 100644
--- a/app/vmselect/prometheus/prometheus.go
+++ b/app/vmselect/prometheus/prometheus.go
@@ -662,27 +662,43 @@ func labelValuesWithMatches(at *auth.Token, denyPartialResponse bool, labelName
 		MaxTimestamp: end,
 		TagFilterss:  tagFilterss,
 	}
-	rss, isPartial, err := netstorage.ProcessSearchQuery(at, denyPartialResponse, sq, false, deadline)
-	if err != nil {
-		return nil, false, fmt.Errorf("cannot fetch data for %q: %w", sq, err)
-	}
-
 	m := make(map[string]struct{})
-	var mLock sync.Mutex
-	err = rss.RunParallel(func(rs *netstorage.Result, workerID uint) error {
-		labelValue := rs.MetricName.GetTagValue(labelName)
-		if len(labelValue) == 0 {
-			return nil
+	isPartial := false
+	if end-start > 24*3600*1000 {
+		// It is cheaper to call SearchMetricNames on time ranges exceeding a day.
+		mns, isPartialResponse, err := netstorage.SearchMetricNames(at, denyPartialResponse, sq, deadline)
+		if err != nil {
+			return nil, false, fmt.Errorf("cannot fetch time series for %q: %w", sq, err)
+		}
+		isPartial = isPartialResponse
+		for _, mn := range mns {
+			labelValue := mn.GetTagValue(labelName)
+			if len(labelValue) == 0 {
+				continue
+			}
+			m[string(labelValue)] = struct{}{}
+		}
+	} else {
+		rss, isPartialResponse, err := netstorage.ProcessSearchQuery(at, denyPartialResponse, sq, false, deadline)
+		if err != nil {
+			return nil, false, fmt.Errorf("cannot fetch data for %q: %w", sq, err)
+		}
+		isPartial = isPartialResponse
+		var mLock sync.Mutex
+		err = rss.RunParallel(func(rs *netstorage.Result, workerID uint) error {
+			labelValue := rs.MetricName.GetTagValue(labelName)
+			if len(labelValue) == 0 {
+				return nil
+			}
+			mLock.Lock()
+			m[string(labelValue)] = struct{}{}
+			mLock.Unlock()
+			return nil
+		})
+		if err != nil {
+			return nil, false, fmt.Errorf("error when data fetching: %w", err)
 		}
-		mLock.Lock()
-		m[string(labelValue)] = struct{}{}
-		mLock.Unlock()
-		return nil
-	})
-	if err != nil {
-		return nil, false, fmt.Errorf("error when data fetching: %w", err)
 	}
-
 	labelValues := make([]string, 0, len(m))
 	for labelValue := range m {
 		labelValues = append(labelValues, labelValue)
@@ -856,26 +872,39 @@ func labelsWithMatches(at *auth.Token, denyPartialResponse bool, matches []strin
 		MaxTimestamp: end,
 		TagFilterss:  tagFilterss,
 	}
-	rss, isPartial, err := netstorage.ProcessSearchQuery(at, denyPartialResponse, sq, false, deadline)
-	if err != nil {
-		return nil, false, fmt.Errorf("cannot fetch data for %q: %w", sq, err)
-	}
-
 	m := make(map[string]struct{})
-	var mLock sync.Mutex
-	err = rss.RunParallel(func(rs *netstorage.Result, workerID uint) error {
-		mLock.Lock()
-		tags := rs.MetricName.Tags
-		for i := range tags {
-			t := &tags[i]
-			m[string(t.Key)] = struct{}{}
+	isPartial := false
+	if end-start > 24*3600*1000 {
+		// It is cheaper to call SearchMetricNames on time ranges exceeding a day.
+		mns, isPartialResponse, err := netstorage.SearchMetricNames(at, denyPartialResponse, sq, deadline)
+		if err != nil {
+			return nil, false, fmt.Errorf("cannot fetch time series for %q: %w", sq, err)
+		}
+		isPartial = isPartialResponse
+		for _, mn := range mns {
+			for _, tag := range mn.Tags {
+				m[string(tag.Key)] = struct{}{}
+			}
+		}
+	} else {
+		rss, isPartialResponse, err := netstorage.ProcessSearchQuery(at, denyPartialResponse, sq, false, deadline)
+		if err != nil {
+			return nil, false, fmt.Errorf("cannot fetch data for %q: %w", sq, err)
+		}
+		isPartial = isPartialResponse
+		var mLock sync.Mutex
+		err = rss.RunParallel(func(rs *netstorage.Result, workerID uint) error {
+			mLock.Lock()
+			for _, tag := range rs.MetricName.Tags {
+				m[string(tag.Key)] = struct{}{}
+			}
+			m["__name__"] = struct{}{}
+			mLock.Unlock()
+			return nil
+		})
+		if err != nil {
+			return nil, false, fmt.Errorf("error when data fetching: %w", err)
 		}
-		m["__name__"] = struct{}{}
-		mLock.Unlock()
-		return nil
-	})
-	if err != nil {
-		return nil, false, fmt.Errorf("error when data fetching: %w", err)
 	}
 
 	labels := make([]string, 0, len(m))
diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md
index 5266bb327..d30bc3c21 100644
--- a/docs/CHANGELOG.md
+++ b/docs/CHANGELOG.md
@@ -7,7 +7,7 @@
 * FEATURE: vmselect: add `"isPartial":{true|false}` field in JSON output for `/api/v1/*` functions
   from [Prometheus querying API](https://prometheus.io/docs/prometheus/latest/querying/api/). `"isPartial":true` is set if the response contains partial data
   because of a part of `vmstorage` nodes were unavailable during query processing.
-* FEATURE: improve performance for `/api/v1/series` on time ranges exceeding one day.
+* FEATURE: improve performance for `/api/v1/series`, `/api/v1/labels` and `/api/v1/label/<labelName>/values` on time ranges exceeding one day.
 * FEATURE: vmagent: reduce memory usage when service discovery detects big number of scrape targets and the set of discovered targets changes over time.
   See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/825
 * FEATURE: vmagent: add `-promscrape.dropOriginalLabels` command-line option, which can be used for reducing memory usage when scraping big number of targets.