all: update Docker image tag for VictoriaMetrics components from v1.97.1 to v1.98.0

See https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.98.0

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -60,8 +60,8 @@ body:
   
         For VictoriaMetrics health-state issues please provide full-length screenshots
         of Grafana dashboards if possible:
-          * [Grafana dashboard for single-node VictoriaMetrics](https://grafana.com/grafana/dashboards/10229-victoriametrics/)
-          * [Grafana dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176-victoriametrics-cluster/)
+          * [Grafana dashboard for single-node VictoriaMetrics](https://grafana.com/grafana/dashboards/10229/)
+          * [Grafana dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176/)
         
         See how to setup monitoring here:
           * [monitoring for single-node VictoriaMetrics](https://docs.victoriametrics.com/#monitoring)

.github/workflows/check-licenses.yml

@@ -25,7 +25,7 @@ jobs:
           cache: false
 
       - name: Cache Go artifacts
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: |
             ~/.cache/go-build

.github/workflows/codeql-analysis-js.yml

@@ -36,11 +36,11 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@v2
+        uses: github/codeql-action/init@v3
         with:
           languages: ${{ matrix.language }}
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v2
+        uses: github/codeql-action/analyze@v3
         with:
           category: "javascript"

.github/workflows/codeql-analysis.yml

@@ -63,7 +63,7 @@ jobs:
         if: ${{ matrix.language == 'go' }}
 
       - name: Cache Go artifacts
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: |
             ~/.cache/go-build
@@ -75,7 +75,7 @@ jobs:
 
       # Initializes the CodeQL tools for scanning.
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@v2
+        uses: github/codeql-action/init@v3
         with:
           languages: ${{ matrix.language }}
           # If you wish to specify custom queries, you can do so here or in a config file.
@@ -86,7 +86,7 @@ jobs:
       # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
       # If this step fails, then you should remove it and run the build manually (see below)
       - name: Autobuild
-        uses: github/codeql-action/autobuild@v2
+        uses: github/codeql-action/autobuild@v3
 
       # ℹ️ Command-line programs to run using the OS shell.
       # 📚 https://git.io/JvXDl
@@ -100,4 +100,4 @@ jobs:
       #   make release
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v2
+        uses: github/codeql-action/analyze@v3

.github/workflows/main.yml

@@ -41,7 +41,7 @@ jobs:
           cache: false
 
       - name: Cache Go artifacts
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: |
             ~/.cache/go-build
@@ -71,7 +71,7 @@ jobs:
           cache: false
 
       - name: Cache Go artifacts
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: |
             ~/.cache/go-build
@@ -102,7 +102,7 @@ jobs:
           cache: false
 
       - name: Cache Go artifacts
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: |
             ~/.cache/go-build
@@ -115,6 +115,6 @@ jobs:
         run: make ${{ matrix.scenario}}
 
       - name: Publish coverage
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v4
         with:
           file: ./coverage.txt

.gitignore

@@ -22,3 +22,4 @@ Gemfile.lock
 /_site
 _site
 *.tmp
+/docs/.jekyll-metadata

LICENSE

@@ -175,7 +175,7 @@
 
    END OF TERMS AND CONDITIONS
 
-   Copyright 2019-2023 VictoriaMetrics, Inc.
+   Copyright 2019-2024 VictoriaMetrics, Inc.
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

Makefile

@@ -1,6 +1,6 @@
 PKG_PREFIX := github.com/VictoriaMetrics/VictoriaMetrics
 
-MAKE_CONCURRENCY ?= $(shell cat /proc/cpuinfo | grep -c processor)
+MAKE_CONCURRENCY ?= $(shell getconf _NPROCESSORS_ONLN)
 MAKE_PARALLEL := $(MAKE) -j $(MAKE_CONCURRENCY)
 DATEINFO_TAG ?= $(shell date -u +'%Y%m%d-%H%M%S')
 BUILDINFO_TAG ?= $(shell echo $$(git describe --long --all | tr '/' '-')$$( \
@@ -178,7 +178,8 @@ victoria-metrics-crossbuild: \
 	victoria-metrics-darwin-amd64 \
 	victoria-metrics-darwin-arm64 \
 	victoria-metrics-freebsd-amd64 \
-	victoria-metrics-openbsd-amd64
+	victoria-metrics-openbsd-amd64 \
+	victoria-metrics-windows-amd64
 
 vmutils-crossbuild: \
 	vmutils-linux-386 \
@@ -465,7 +466,7 @@ benchmark-pure:
 vendor-update:
 	go get -u -d ./lib/...
 	go get -u -d ./app/...
-	go mod tidy -compat=1.20
+	go mod tidy -compat=1.22
 	go mod vendor
 
 app-local:

SECURITY.md

@@ -5,8 +5,8 @@
 | Version | Supported          |
 |---------|--------------------|
 | [latest release](https://docs.victoriametrics.com/CHANGELOG.html) | :white_check_mark: |
+| v1.97.x LTS release | :white_check_mark: |
 | v1.93.x LTS release | :white_check_mark: |
-| v1.87.x LTS release | :white_check_mark: |
 | other releases  | :x:                |
 
 ## Reporting a Vulnerability

app/victoria-logs/main.go

@@ -11,7 +11,6 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlselect"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vlstorage"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/buildinfo"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
@@ -22,11 +21,10 @@ import (
 )
 
 var (
-	httpListenAddr   = flag.String("httpListenAddr", ":9428", "TCP address to listen for http connections. See also -httpListenAddr.useProxyProtocol")
-	useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
+	httpListenAddrs  = flagutil.NewArrayString("httpListenAddr", "TCP address to listen for incoming http requests. See also -httpListenAddr.useProxyProtocol")
+	useProxyProtocol = flagutil.NewArrayBool("httpListenAddr.useProxyProtocol", "Whether to use proxy protocol for connections accepted at the given -httpListenAddr . "+
 		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
 		"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
-	gogc = flag.Int("gogc", 100, "GOGC to use. See https://tip.golang.org/doc/gc-guide")
 )
 
 func main() {
@@ -34,27 +32,31 @@ func main() {
 	flag.CommandLine.SetOutput(os.Stdout)
 	flag.Usage = usage
 	envflag.Parse()
-	cgroup.SetGOGC(*gogc)
 	buildinfo.Init()
 	logger.Init()
-	pushmetrics.Init()
 
-	logger.Infof("starting VictoriaLogs at %q...", *httpListenAddr)
+	listenAddrs := *httpListenAddrs
+	if len(listenAddrs) == 0 {
+		listenAddrs = []string{":9428"}
+	}
+	logger.Infof("starting VictoriaLogs at %q...", listenAddrs)
 	startTime := time.Now()
 
 	vlstorage.Init()
 	vlselect.Init()
 	vlinsert.Init()
 
-	go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
+	go httpserver.Serve(listenAddrs, useProxyProtocol, requestHandler)
 	logger.Infof("started VictoriaLogs in %.3f seconds; see https://docs.victoriametrics.com/VictoriaLogs/", time.Since(startTime).Seconds())
 
+	pushmetrics.Init()
 	sig := procutil.WaitForSigterm()
 	logger.Infof("received signal %s", sig)
+	pushmetrics.Stop()
 
-	logger.Infof("gracefully shutting down webservice at %q", *httpListenAddr)
+	logger.Infof("gracefully shutting down webservice at %q", listenAddrs)
 	startTime = time.Now()
-	if err := httpserver.Stop(*httpListenAddr); err != nil {
+	if err := httpserver.Stop(listenAddrs); err != nil {
 		logger.Fatalf("cannot stop the webservice: %s", err)
 	}
 	logger.Infof("successfully shut down the webservice in %.3f seconds", time.Since(startTime).Seconds())

app/victoria-metrics/main.go

@@ -26,8 +26,8 @@ import (
 )
 
 var (
-	httpListenAddr   = flag.String("httpListenAddr", ":8428", "TCP address to listen for http connections. See also -tls and -httpListenAddr.useProxyProtocol")
-	useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
+	httpListenAddrs  = flagutil.NewArrayString("httpListenAddr", "TCP addresses to listen for incoming http requests. See also -tls and -httpListenAddr.useProxyProtocol")
+	useProxyProtocol = flagutil.NewArrayBool("httpListenAddr.useProxyProtocol", "Whether to use proxy protocol for connections accepted at the corresponding -httpListenAddr . "+
 		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
 		"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
 	minScrapeInterval = flag.Duration("dedup.minScrapeInterval", 0, "Leave only the last sample in every time series per each discrete interval "+
@@ -48,7 +48,6 @@ func main() {
 	envflag.Parse()
 	buildinfo.Init()
 	logger.Init()
-	pushmetrics.Init()
 
 	if promscrape.IsDryRun() {
 		*dryRun = true
@@ -67,30 +66,37 @@ func main() {
 		return
 	}
 
-	logger.Infof("starting VictoriaMetrics at %q...", *httpListenAddr)
+	listenAddrs := *httpListenAddrs
+	if len(listenAddrs) == 0 {
+		listenAddrs = []string{":8428"}
+	}
+	logger.Infof("starting VictoriaMetrics at %q...", listenAddrs)
 	startTime := time.Now()
 	storage.SetDedupInterval(*minScrapeInterval)
 	storage.SetDataFlushInterval(*inmemoryDataFlushInterval)
 	vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
 	vmselect.Init()
 	vminsert.Init()
+
 	startSelfScraper()
 
-	go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
+	go httpserver.Serve(listenAddrs, useProxyProtocol, requestHandler)
 	logger.Infof("started VictoriaMetrics in %.3f seconds", time.Since(startTime).Seconds())
 
+	pushmetrics.Init()
 	sig := procutil.WaitForSigterm()
 	logger.Infof("received signal %s", sig)
+	pushmetrics.Stop()
 
 	stopSelfScraper()
 
-	logger.Infof("gracefully shutting down webservice at %q", *httpListenAddr)
+	logger.Infof("gracefully shutting down webservice at %q", listenAddrs)
 	startTime = time.Now()
-	if err := httpserver.Stop(*httpListenAddr); err != nil {
+	if err := httpserver.Stop(listenAddrs); err != nil {
 		logger.Fatalf("cannot stop the webservice: %s", err)
 	}
-	vminsert.Stop()
 	logger.Infof("successfully shut down the webservice in %.3f seconds", time.Since(startTime).Seconds())
+	vminsert.Stop()
 
 	vmstorage.Stop()
 	vmselect.Stop()
@@ -122,6 +128,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 			{"api/v1/status/tsdb", "tsdb status page"},
 			{"api/v1/status/top_queries", "top queries"},
 			{"api/v1/status/active_queries", "active queries"},
+			{"-/reload", "reload configuration"},
 		})
 		return true
 	}

app/victoria-metrics/main_test.go

@@ -7,11 +7,13 @@ import (
 	"fmt"
 	"io"
 	"log"
+	"math/rand"
 	"net"
 	"net/http"
 	"os"
 	"path/filepath"
 	"reflect"
+	"strconv"
 	"strings"
 	"testing"
 	"time"
@@ -54,15 +56,14 @@ var (
 )
 
 type test struct {
-	Name             string     `json:"name"`
-	Data             []string   `json:"data"`
-	InsertQuery      string     `json:"insert_query"`
-	Query            []string   `json:"query"`
-	ResultMetrics    []Metric   `json:"result_metrics"`
-	ResultSeries     Series     `json:"result_series"`
-	ResultQuery      Query      `json:"result_query"`
-	ResultQueryRange QueryRange `json:"result_query_range"`
-	Issue            string     `json:"issue"`
+	Name          string   `json:"name"`
+	Data          []string `json:"data"`
+	InsertQuery   string   `json:"insert_query"`
+	Query         []string `json:"query"`
+	ResultMetrics []Metric `json:"result_metrics"`
+	ResultSeries  Series   `json:"result_series"`
+	ResultQuery   Query    `json:"result_query"`
+	Issue         string   `json:"issue"`
 }
 
 type Metric struct {
@@ -80,42 +81,90 @@ type Series struct {
 	Status string              `json:"status"`
 	Data   []map[string]string `json:"data"`
 }
+
 type Query struct {
-	Status string    `json:"status"`
-	Data   QueryData `json:"data"`
-}
-type QueryData struct {
-	ResultType string            `json:"resultType"`
-	Result     []QueryDataResult `json:"result"`
+	Status string `json:"status"`
+	Data   struct {
+		ResultType string          `json:"resultType"`
+		Result     json.RawMessage `json:"result"`
+	} `json:"data"`
 }
 
-type QueryDataResult struct {
-	Metric map[string]string `json:"metric"`
-	Value  []interface{}     `json:"value"`
+const rtVector, rtMatrix = "vector", "matrix"
+
+func (q *Query) metrics() ([]Metric, error) {
+	switch q.Data.ResultType {
+	case rtVector:
+		var r QueryInstant
+		if err := json.Unmarshal(q.Data.Result, &r.Result); err != nil {
+			return nil, err
+		}
+		return r.metrics()
+	case rtMatrix:
+		var r QueryRange
+		if err := json.Unmarshal(q.Data.Result, &r.Result); err != nil {
+			return nil, err
+		}
+		return r.metrics()
+	default:
+		return nil, fmt.Errorf("unknown result type %q", q.Data.ResultType)
+	}
 }
 
-func (r *QueryDataResult) UnmarshalJSON(b []byte) error {
-	type plain QueryDataResult
-	return json.Unmarshal(testutil.PopulateTimeTpl(b, insertionTime), (*plain)(r))
+type QueryInstant struct {
+	Result []struct {
+		Labels map[string]string `json:"metric"`
+		TV     [2]interface{}    `json:"value"`
+	} `json:"result"`
+}
+
+func (q QueryInstant) metrics() ([]Metric, error) {
+	result := make([]Metric, len(q.Result))
+	for i, res := range q.Result {
+		f, err := strconv.ParseFloat(res.TV[1].(string), 64)
+		if err != nil {
+			return nil, fmt.Errorf("metric %v, unable to parse float64 from %s: %w", res, res.TV[1], err)
+		}
+		var m Metric
+		m.Metric = res.Labels
+		m.Timestamps = append(m.Timestamps, int64(res.TV[0].(float64)))
+		m.Values = append(m.Values, f)
+		result[i] = m
+	}
+	return result, nil
 }
 
 type QueryRange struct {
-	Status string         `json:"status"`
-	Data   QueryRangeData `json:"data"`
-}
-type QueryRangeData struct {
-	ResultType string                 `json:"resultType"`
-	Result     []QueryRangeDataResult `json:"result"`
+	Result []struct {
+		Metric map[string]string `json:"metric"`
+		Values [][]interface{}   `json:"values"`
+	} `json:"result"`
 }
 
-type QueryRangeDataResult struct {
-	Metric map[string]string `json:"metric"`
-	Values [][]interface{}   `json:"values"`
+func (q QueryRange) metrics() ([]Metric, error) {
+	var result []Metric
+	for i, res := range q.Result {
+		var m Metric
+		for _, tv := range res.Values {
+			f, err := strconv.ParseFloat(tv[1].(string), 64)
+			if err != nil {
+				return nil, fmt.Errorf("metric %v, unable to parse float64 from %s: %w", res, tv[1], err)
+			}
+			m.Values = append(m.Values, f)
+			m.Timestamps = append(m.Timestamps, int64(tv[0].(float64)))
+		}
+		if len(m.Values) < 1 || len(m.Timestamps) < 1 {
+			return nil, fmt.Errorf("metric %v contains no values", res)
+		}
+		m.Metric = q.Result[i].Metric
+		result = append(result, m)
+	}
+	return result, nil
 }
 
-func (r *QueryRangeDataResult) UnmarshalJSON(b []byte) error {
-	type plain QueryRangeDataResult
-	return json.Unmarshal(testutil.PopulateTimeTpl(b, insertionTime), (*plain)(r))
+func (q *Query) UnmarshalJSON(b []byte) error {
+	type plain Query
+	return json.Unmarshal(testutil.PopulateTimeTpl(b, insertionTime), (*plain)(q))
 }
 
 func TestMain(m *testing.M) {
@@ -132,7 +181,7 @@ func setUp() {
 	vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
 	vmselect.Init()
 	vminsert.Init()
-	go httpserver.Serve(*httpListenAddr, false, requestHandler)
+	go httpserver.Serve(*httpListenAddrs, useProxyProtocol, requestHandler)
 	readyStorageCheckFunc := func() bool {
 		resp, err := http.Get(testHealthHTTPPath)
 		if err != nil {
@@ -178,7 +227,7 @@ func waitFor(timeout time.Duration, f func() bool) error {
 }
 
 func tearDown() {
-	if err := httpserver.Stop(*httpListenAddr); err != nil {
+	if err := httpserver.Stop(*httpListenAddrs); err != nil {
 		log.Printf("cannot stop the webservice: %s", err)
 	}
 	vminsert.Stop()
@@ -197,6 +246,9 @@ func TestWriteRead(t *testing.T) {
 func testWrite(t *testing.T) {
 	t.Run("prometheus", func(t *testing.T) {
 		for _, test := range readIn("prometheus", t, insertionTime) {
+			if test.Data == nil {
+				continue
+			}
 			s := newSuite(t)
 			r := testutil.WriteRequest{}
 			s.noError(json.Unmarshal([]byte(strings.Join(test.Data, "\n")), &r.Timeseries))
@@ -272,17 +324,19 @@ func testRead(t *testing.T) {
 							if err := checkSeriesResult(s, test.ResultSeries); err != nil {
 								t.Fatalf("Series. %s fails with error %s.%s", q, err, test.Issue)
 							}
-						case strings.HasPrefix(q, "/api/v1/query_range"):
-							queryResult := QueryRange{}
-							httpReadStruct(t, testReadHTTPPath, q, &queryResult)
-							if err := checkQueryRangeResult(queryResult, test.ResultQueryRange); err != nil {
-								t.Fatalf("Query Range. %s fails with error %s.%s", q, err, test.Issue)
-							}
 						case strings.HasPrefix(q, "/api/v1/query"):
 							queryResult := Query{}
 							httpReadStruct(t, testReadHTTPPath, q, &queryResult)
-							if err := checkQueryResult(queryResult, test.ResultQuery); err != nil {
-								t.Fatalf("Query. %s fails with error: %s.%s", q, err, test.Issue)
+							gotMetrics, err := queryResult.metrics()
+							if err != nil {
+								t.Fatalf("failed to parse query response: %s", err)
+							}
+							expMetrics, err := test.ResultQuery.metrics()
+							if err != nil {
+								t.Fatalf("failed to parse expected response: %s", err)
+							}
+							if err := checkMetricsResult(gotMetrics, expMetrics); err != nil {
+								t.Fatalf("%q fails with error %s.%s", q, err, test.Issue)
 							}
 						default:
 							t.Fatalf("unsupported read query %s", q)
@@ -360,6 +414,7 @@ func httpReadMetrics(t *testing.T, address, query string) []Metric {
 	}
 	return rows
 }
+
 func httpReadStruct(t *testing.T, address, query string, dst interface{}) {
 	t.Helper()
 	s := newSuite(t)
@@ -417,60 +472,6 @@ func removeIfFoundSeries(r map[string]string, contains []map[string]string) []ma
 	return contains
 }
 
-func checkQueryResult(got, want Query) error {
-	if got.Status != want.Status {
-		return fmt.Errorf("status mismatch %q - %q", want.Status, got.Status)
-	}
-	if got.Data.ResultType != want.Data.ResultType {
-		return fmt.Errorf("result type mismatch %q - %q", want.Data.ResultType, got.Data.ResultType)
-	}
-	wantData := append([]QueryDataResult(nil), want.Data.Result...)
-	for _, r := range got.Data.Result {
-		wantData = removeIfFoundQueryData(r, wantData)
-	}
-	if len(wantData) > 0 {
-		return fmt.Errorf("expected query result %+v not found in %+v", wantData, got.Data.Result)
-	}
-	return nil
-}
-
-func removeIfFoundQueryData(r QueryDataResult, contains []QueryDataResult) []QueryDataResult {
-	for i, item := range contains {
-		if reflect.DeepEqual(r.Metric, item.Metric) && reflect.DeepEqual(r.Value[0], item.Value[0]) && reflect.DeepEqual(r.Value[1], item.Value[1]) {
-			contains[i] = contains[len(contains)-1]
-			return contains[:len(contains)-1]
-		}
-	}
-	return contains
-}
-
-func checkQueryRangeResult(got, want QueryRange) error {
-	if got.Status != want.Status {
-		return fmt.Errorf("status mismatch %q - %q", want.Status, got.Status)
-	}
-	if got.Data.ResultType != want.Data.ResultType {
-		return fmt.Errorf("result type mismatch %q - %q", want.Data.ResultType, got.Data.ResultType)
-	}
-	wantData := append([]QueryRangeDataResult(nil), want.Data.Result...)
-	for _, r := range got.Data.Result {
-		wantData = removeIfFoundQueryRangeData(r, wantData)
-	}
-	if len(wantData) > 0 {
-		return fmt.Errorf("expected query range result %+v not found in %+v", wantData, got.Data.Result)
-	}
-	return nil
-}
-
-func removeIfFoundQueryRangeData(r QueryRangeDataResult, contains []QueryRangeDataResult) []QueryRangeDataResult {
-	for i, item := range contains {
-		if reflect.DeepEqual(r.Metric, item.Metric) && reflect.DeepEqual(r.Values, item.Values) {
-			contains[i] = contains[len(contains)-1]
-			return contains[:len(contains)-1]
-		}
-	}
-	return contains
-}
-
 type suite struct{ t *testing.T }
 
 func newSuite(t *testing.T) *suite { return &suite{t: t} }
@@ -498,3 +499,73 @@ func (s *suite) greaterThan(a, b int) {
 		s.t.FailNow()
 	}
 }
+
+func TestImportJSONLines(t *testing.T) {
+	f := func(labelsCount, labelLen int) {
+		t.Helper()
+
+		reqURL := fmt.Sprintf("http://localhost%s/api/v1/import", testHTTPListenAddr)
+		line := generateJSONLine(labelsCount, labelLen)
+		req, err := http.NewRequest("POST", reqURL, bytes.NewBufferString(line))
+		if err != nil {
+			t.Fatalf("cannot create request: %s", err)
+		}
+		resp, err := http.DefaultClient.Do(req)
+		if err != nil {
+			t.Fatalf("cannot perform request for labelsCount=%d, labelLen=%d: %s", labelsCount, labelLen, err)
+		}
+		if resp.StatusCode != 204 {
+			t.Fatalf("unexpected statusCode for labelsCount=%d, labelLen=%d; got %d; want 204", labelsCount, labelLen, resp.StatusCode)
+		}
+	}
+
+	// labels with various lengths
+	for i := 0; i < 500; i++ {
+		f(10, i*5)
+	}
+
+	// Too many labels
+	f(1000, 100)
+
+	// Too long labels
+	f(1, 100_000)
+	f(10, 100_000)
+	f(10, 10_000)
+}
+
+func generateJSONLine(labelsCount, labelLen int) string {
+	m := make(map[string]string, labelsCount)
+	m["__name__"] = generateSizedRandomString(labelLen)
+	for j := 1; j < labelsCount; j++ {
+		labelName := generateSizedRandomString(labelLen)
+		labelValue := generateSizedRandomString(labelLen)
+		m[labelName] = labelValue
+	}
+
+	type jsonLine struct {
+		Metric     map[string]string `json:"metric"`
+		Values     []float64         `json:"values"`
+		Timestamps []int64           `json:"timestamps"`
+	}
+	line := &jsonLine{
+		Metric:     m,
+		Values:     []float64{1.34},
+		Timestamps: []int64{time.Now().UnixNano() / 1e6},
+	}
+	data, err := json.Marshal(&line)
+	if err != nil {
+		panic(fmt.Errorf("cannot marshal JSON: %w", err))
+	}
+	data = append(data, '\n')
+	return string(data)
+}
+
+const alphabetSample = `qwertyuiopasdfghjklzxcvbnm`
+
+func generateSizedRandomString(size int) string {
+	dst := make([]byte, size)
+	for i := range dst {
+		dst[i] = alphabetSample[rand.Intn(len(alphabetSample))]
+	}
+	return string(dst)
+}

app/victoria-metrics/self_scraper.go

@@ -8,6 +8,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmstorage"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/appmetrics"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus"
@@ -49,16 +50,8 @@ func selfScraper(scrapeInterval time.Duration) {
 	var mrs []storage.MetricRow
 	var labels []prompb.Label
 	t := time.NewTicker(scrapeInterval)
-	var currentTimestamp int64
-	for {
-		select {
-		case <-selfScraperStopCh:
-			t.Stop()
-			logger.Infof("stopped self-scraping `/metrics` page")
-			return
-		case currentTime := <-t.C:
-			currentTimestamp = currentTime.UnixNano() / 1e6
-		}
+	f := func(currentTime time.Time, sendStaleMarkers bool) {
+		currentTimestamp := currentTime.UnixNano() / 1e6
 		bb.Reset()
 		appmetrics.WritePrometheusMetrics(&bb)
 		s := bytesutil.ToUnsafeString(bb.B)
@@ -83,12 +76,27 @@ func selfScraper(scrapeInterval time.Duration) {
 			mr := &mrs[len(mrs)-1]
 			mr.MetricNameRaw = storage.MarshalMetricNameRaw(mr.MetricNameRaw[:0], labels)
 			mr.Timestamp = currentTimestamp
-			mr.Value = r.Value
+			if sendStaleMarkers {
+				mr.Value = decimal.StaleNaN
+			} else {
+				mr.Value = r.Value
+			}
 		}
 		if err := vmstorage.AddRows(mrs); err != nil {
 			logger.Errorf("cannot store self-scraped metrics: %s", err)
 		}
 	}
+	for {
+		select {
+		case <-selfScraperStopCh:
+			f(time.Now(), true)
+			t.Stop()
+			logger.Infof("stopped self-scraping `/metrics` page")
+			return
+		case currentTime := <-t.C:
+			f(currentTime, false)
+		}
+	}
 }
 
 func addLabel(dst []prompb.Label, key, value string) []prompb.Label {
@@ -98,7 +106,7 @@ func addLabel(dst []prompb.Label, key, value string) []prompb.Label {
 		dst = append(dst, prompb.Label{})
 	}
 	lb := &dst[len(dst)-1]
-	lb.Name = bytesutil.ToUnsafeBytes(key)
-	lb.Value = bytesutil.ToUnsafeBytes(value)
+	lb.Name = key
+	lb.Value = value
 	return dst
 }

app/victoria-metrics/testdata/graphite/comparison-not-inf-not-nan.json

@@ -7,7 +7,7 @@
     "not_nan_not_inf;item=y 3 {TIME_S-1m}",
     "not_nan_not_inf;item=y 1 {TIME_S-2m}"],
   "query": ["/api/v1/query_range?query=1/(not_nan_not_inf-1)!=inf!=nan&start={TIME_S-3m}&end={TIME_S}&step=60"],
-  "result_query_range": {
+  "result_query": {
     "status":"success",
     "data":{"resultType":"matrix",
       "result":[

app/victoria-metrics/testdata/graphite/empty-label-match.json

@@ -6,7 +6,7 @@
     "empty_label_match;foo=bar 2 {TIME_S-1m}",
     "empty_label_match;foo=baz 3 {TIME_S-1m}"],
   "query": ["/api/v1/query_range?query=empty_label_match{foo=~'bar|'}&start={TIME_S-1m}&end={TIME_S}&step=60"],
-  "result_query_range": {
+  "result_query": {
     "status":"success",
     "data":{"resultType":"matrix",
       "result":[

app/victoria-metrics/testdata/graphite/max_lookback_set.json

@@ -8,7 +8,7 @@
     "max_lookback_set 4 {TIME_S-150s}"
   ],
   "query": ["/api/v1/query_range?query=max_lookback_set&start={TIME_S-150s}&end={TIME_S}&step=10s&max_lookback=1s"],
-  "result_query_range": {
+  "result_query": {
     "status":"success",
     "data":{"resultType":"matrix",
       "result":[{"metric":{"__name__":"max_lookback_set"},"values":[

app/victoria-metrics/testdata/graphite/max_lookback_unset.json

@@ -8,7 +8,7 @@
     "max_lookback_unset 4 {TIME_S-150s}"
   ],
   "query": ["/api/v1/query_range?query=max_lookback_unset&start={TIME_S-150s}&end={TIME_S}&step=10s"],
-  "result_query_range": {
+  "result_query": {
     "status":"success",
     "data":{"resultType":"matrix",
       "result":[{"metric":{"__name__":"max_lookback_unset"},"values":[

app/victoria-metrics/testdata/graphite/not-nan-as-missing-data.json

@@ -8,7 +8,7 @@
     "not_nan_as_missing_data;item=y 3 {TIME_S-1m}"
   ],
   "query": ["/api/v1/query_range?query=not_nan_as_missing_data>1&start={TIME_S-2m}&end={TIME_S}&step=60"],
-  "result_query_range": {
+  "result_query": {
     "status":"success",
     "data":{"resultType":"matrix",
       "result":[

app/victoria-metrics/testdata/prometheus/instant-matrix.json

@@ -0,0 +1,12 @@
+{
+  "name": "instant query with look-behind window",
+  "data": ["[{\"labels\":[{\"name\":\"__name__\",\"value\":\"foo\"}],\"samples\":[{\"value\":1,\"timestamp\":\"{TIME_MS-60s}\"}]}]"],
+  "query": ["/api/v1/query?query=foo[5m]"],
+  "result_query": {
+      "status": "success",
+      "data":{
+        "resultType":"matrix",
+        "result":[{"metric":{"__name__":"foo"},"values":[["{TIME_S-60s}", "1"]]}]
+      }
+    }
+}

app/victoria-metrics/testdata/prometheus/instant-scalar.json

@@ -0,0 +1,11 @@
+{
+  "name": "instant scalar query",
+  "query": ["/api/v1/query?query=42&time={TIME_S}"],
+  "result_query": {
+      "status": "success",
+      "data":{
+        "resultType":"vector",
+        "result":[{"metric":{},"value":["{TIME_S}", "42"]}]
+      }
+    }
+}

app/victoria-metrics/testdata/prometheus/issue-5553-too-big-lookback.json

@@ -0,0 +1,13 @@
+{
+  "name": "too big look-behind window",
+  "issue": "https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5553",
+  "data": ["[{\"labels\":[{\"name\":\"__name__\",\"value\":\"foo\"},{\"name\":\"issue\",\"value\":\"5553\"}],\"samples\":[{\"value\":1,\"timestamp\":\"{TIME_MS-60s}\"}]}]"],
+  "query": ["/api/v1/query?query=foo{issue=\"5553\"}[100y]"],
+  "result_query": {
+      "status": "success",
+      "data":{
+        "resultType":"matrix",
+        "result":[{"metric":{"__name__":"foo", "issue": "5553"},"values":[["{TIME_S-60s}", "1"]]}]
+      }
+    }
+}

app/victoria-metrics/testdata/prometheus/query-range.json

@@ -0,0 +1,18 @@
+{
+  "name": "query range",
+  "issue": "https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5553",
+  "data": ["[{\"labels\":[{\"name\":\"__name__\",\"value\":\"bar\"}],\"samples\":[{\"value\":1,\"timestamp\":\"{TIME_MS-60s}\"}, {\"value\":2,\"timestamp\":\"{TIME_MS-120s}\"}, {\"value\":1,\"timestamp\":\"{TIME_MS-180s}\"}]}]"],
+  "query": ["/api/v1/query_range?query=bar&step=30s&start={TIME_MS-180s}"],
+  "result_query": {
+      "status": "success",
+      "data":{
+        "resultType":"matrix",
+        "result":[
+          {
+            "metric":{"__name__":"bar"},
+            "values":[["{TIME_S-180s}", "1"],["{TIME_S-150s}", "1"],["{TIME_S-120s}", "2"],["{TIME_S-90s}", "2"], ["{TIME_S-60s}", "1"], ["{TIME_S-30s}", "1"], ["{TIME_S}", "1"]]
+          }
+        ]
+      }
+    }
+}

app/vlselect/vmui/asset-manifest.json

@@ -1,13 +1,13 @@
 {
   "files": {
-    "main.css": "./static/css/main.d1313636.css",
-    "main.js": "./static/js/main.1919fefe.js",
+    "main.css": "./static/css/main.1e22ee10.css",
+    "main.js": "./static/js/main.92cf3903.js",
     "static/js/522.da77e7b3.chunk.js": "./static/js/522.da77e7b3.chunk.js",
-    "static/media/MetricsQL.md": "./static/media/MetricsQL.8644fd7c964802dd34a9.md",
+    "static/media/MetricsQL.md": "./static/media/MetricsQL.48b7b7105a48d7775f01.md",
     "index.html": "./index.html"
   },
   "entrypoints": [
-    "static/css/main.d1313636.css",
-    "static/js/main.1919fefe.js"
+    "static/css/main.1e22ee10.css",
+    "static/js/main.92cf3903.js"
   ]
 }

app/vlselect/vmui/index.html

@@ -1 +1 @@
-<!doctype html><html lang="en"><head><meta charset="utf-8"/><link rel="icon" href="./favicon.ico"/><meta name="viewport" content="width=device-width,initial-scale=1,maximum-scale=5"/><meta name="theme-color" content="#000000"/><meta name="description" content="UI for VictoriaMetrics"/><link rel="apple-touch-icon" href="./apple-touch-icon.png"/><link rel="icon" type="image/png" sizes="32x32" href="./favicon-32x32.png"><link rel="manifest" href="./manifest.json"/><title>VM UI</title><script src="./dashboards/index.js" type="module"></script><meta name="twitter:card" content="summary_large_image"><meta name="twitter:image" content="./preview.jpg"><meta name="twitter:title" content="UI for VictoriaMetrics"><meta name="twitter:description" content="Explore and troubleshoot your VictoriaMetrics data"><meta name="twitter:site" content="@VictoriaMetrics"><meta property="og:title" content="Metric explorer for VictoriaMetrics"><meta property="og:description" content="Explore and troubleshoot your VictoriaMetrics data"><meta property="og:image" content="./preview.jpg"><meta property="og:type" content="website"><script defer="defer" src="./static/js/main.1919fefe.js"></script><link href="./static/css/main.d1313636.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>
+<!doctype html><html lang="en"><head><meta charset="utf-8"/><link rel="icon" href="./favicon.ico"/><meta name="viewport" content="width=device-width,initial-scale=1,maximum-scale=5"/><meta name="theme-color" content="#000000"/><meta name="description" content="UI for VictoriaMetrics"/><link rel="apple-touch-icon" href="./apple-touch-icon.png"/><link rel="icon" type="image/png" sizes="32x32" href="./favicon-32x32.png"><link rel="manifest" href="./manifest.json"/><title>VM UI</title><script src="./dashboards/index.js" type="module"></script><meta name="twitter:card" content="summary_large_image"><meta name="twitter:image" content="./preview.jpg"><meta name="twitter:title" content="UI for VictoriaMetrics"><meta name="twitter:description" content="Explore and troubleshoot your VictoriaMetrics data"><meta name="twitter:site" content="@VictoriaMetrics"><meta property="og:title" content="Metric explorer for VictoriaMetrics"><meta property="og:description" content="Explore and troubleshoot your VictoriaMetrics data"><meta property="og:image" content="./preview.jpg"><meta property="og:type" content="website"><script defer="defer" src="./static/js/main.92cf3903.js"></script><link href="./static/css/main.1e22ee10.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>

app/vlselect/vmui/static/media/MetricsQL.48b7b7105a48d7775f01.md

@@ -810,7 +810,7 @@ Metric names are stripped from the resulting rollups. Add [keep_metric_names](#k
 
 #### timestamp
 
-`timestamp(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds for the last raw sample
+`timestamp(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the last raw sample
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -819,7 +819,7 @@ This function is supported by PromQL. See also [timestamp_with_name](#timestamp_
 
 #### timestamp_with_name
 
-`timestamp_with_name(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds for the last raw sample
+`timestamp_with_name(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the last raw sample
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
 
 Metric names are preserved in the resulting rollups.
@@ -828,7 +828,7 @@ See also [timestamp](#timestamp).
 
 #### tfirst_over_time
 
-`tfirst_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds for the first raw sample
+`tfirst_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the first raw sample
 on the given lookbehind window `d` per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -837,7 +837,7 @@ See also [first_over_time](#first_over_time).
 
 #### tlast_change_over_time
 
-`tlast_change_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds for the last change
+`tlast_change_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the last change
 per each time series returned from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering) on the given lookbehind window `d`.
 
 Metric names are stripped from the resulting rollups. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
@@ -852,7 +852,7 @@ See also [tlast_change_over_time](#tlast_change_over_time).
 
 #### tmax_over_time
 
-`tmax_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds for the raw sample
+`tmax_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the raw sample
 with the maximum value on the given lookbehind window `d`. It is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
 
@@ -862,7 +862,7 @@ See also [max_over_time](#max_over_time).
 
 #### tmin_over_time
 
-`tmin_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds for the raw sample
+`tmin_over_time(series_selector[d])` is a [rollup function](#rollup-functions), which returns the timestamp in seconds with millisecond precision for the raw sample
 with the minimum value on the given lookbehind window `d`. It is calculated independently per each time series returned
 from the given [series_selector](https://docs.victoriametrics.com/keyConcepts.html#filtering).
 
@@ -1029,7 +1029,7 @@ for every point of every time series returned by `q`.
 
 Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
 
-This function is supported by PromQL. This function is supported by PromQL. See also [acosh](#acosh).
+This function is supported by PromQL. See also [acosh](#acosh).
 
 #### day_of_month
 
@@ -1049,6 +1049,15 @@ Metric names are stripped from the resulting series. Add [keep_metric_names](#ke
 
 This function is supported by PromQL.
 
+#### day_of_year
+
+`day_of_year(q)` is a [transform function](#transform-functions), which returns the day of year for every point of every time series returned by `q`.
+It is expected that `q` returns unix timestamps. The returned values are in the range `[1...365]` for non-leap years, and `[1 to 366]` in leap years.
+
+Metric names are stripped from the resulting series. Add [keep_metric_names](#keep_metric_names) modifier in order to keep metric names.
+
+This function is supported by PromQL.
+
 #### days_in_month
 
 `days_in_month(q)` is a [transform function](#transform-functions), which returns the number of days in the month identified

app/vmagent/datadogsketches/request_handler.go

@@ -0,0 +1,95 @@
+package datadogsketches
+
+import (
+	"net/http"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogsketches"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogsketches/stream"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogutils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+var (
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="datadogsketches"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="datadogsketches"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="datadogsketches"}`)
+)
+
+// InsertHandlerForHTTP processes remote write for DataDog POST /api/beta/sketches request.
+func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
+	ce := req.Header.Get("Content-Encoding")
+	return stream.Parse(req.Body, ce, func(sketches []*datadogsketches.Sketch) error {
+		return insertRows(at, sketches, extraLabels)
+	})
+}
+
+func insertRows(at *auth.Token, sketches []*datadogsketches.Sketch, extraLabels []prompbmarshal.Label) error {
+	ctx := common.GetPushCtx()
+	defer common.PutPushCtx(ctx)
+
+	rowsTotal := 0
+	tssDst := ctx.WriteRequest.Timeseries[:0]
+	labels := ctx.Labels[:0]
+	samples := ctx.Samples[:0]
+	for _, sketch := range sketches {
+		ms := sketch.ToSummary()
+		for _, m := range ms {
+			labelsLen := len(labels)
+			labels = append(labels, prompbmarshal.Label{
+				Name:  "__name__",
+				Value: m.Name,
+			})
+			for _, label := range m.Labels {
+				labels = append(labels, prompbmarshal.Label{
+					Name:  label.Name,
+					Value: label.Value,
+				})
+			}
+			for _, tag := range sketch.Tags {
+				name, value := datadogutils.SplitTag(tag)
+				if name == "host" {
+					name = "exported_host"
+				}
+				labels = append(labels, prompbmarshal.Label{
+					Name:  name,
+					Value: value,
+				})
+			}
+			labels = append(labels, extraLabels...)
+			samplesLen := len(samples)
+			for _, p := range m.Points {
+				samples = append(samples, prompbmarshal.Sample{
+					Timestamp: p.Timestamp,
+					Value:     p.Value,
+				})
+			}
+			rowsTotal += len(m.Points)
+			tssDst = append(tssDst, prompbmarshal.TimeSeries{
+				Labels:  labels[labelsLen:],
+				Samples: samples[samplesLen:],
+			})
+		}
+	}
+	ctx.WriteRequest.Timeseries = tssDst
+	ctx.Labels = labels
+	ctx.Samples = samples
+	if !remotewrite.TryPush(at, &ctx.WriteRequest) {
+		return remotewrite.ErrQueueFullHTTPRetry
+	}
+	rowsInserted.Add(rowsTotal)
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(rowsTotal)
+	}
+	rowsPerInsert.Update(float64(rowsTotal))
+	return nil
+}

app/vmagent/datadogv1/request_handler.go

@@ -1,4 +1,4 @@
-package datadog
+package datadogv1
 
 import (
 	"net/http"
@@ -8,33 +8,32 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadog"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadog/stream"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogutils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv1"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv1/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="datadog"}`)
-	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="datadog"}`)
-	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="datadog"}`)
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="datadogv1"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="datadogv1"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="datadogv1"}`)
 )
 
 // InsertHandlerForHTTP processes remote write for DataDog POST /api/v1/series request.
-//
-// See https://docs.datadoghq.com/api/latest/metrics/#submit-metrics
 func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
 	extraLabels, err := parserCommon.GetExtraLabels(req)
 	if err != nil {
 		return err
 	}
 	ce := req.Header.Get("Content-Encoding")
-	return stream.Parse(req.Body, ce, func(series []datadog.Series) error {
+	return stream.Parse(req.Body, ce, func(series []datadogv1.Series) error {
 		return insertRows(at, series, extraLabels)
 	})
 }
 
-func insertRows(at *auth.Token, series []datadog.Series, extraLabels []prompbmarshal.Label) error {
+func insertRows(at *auth.Token, series []datadogv1.Series, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -63,7 +62,7 @@ func insertRows(at *auth.Token, series []datadog.Series, extraLabels []prompbmar
 			})
 		}
 		for _, tag := range ss.Tags {
-			name, value := datadog.SplitTag(tag)
+			name, value := datadogutils.SplitTag(tag)
 			if name == "host" {
 				name = "exported_host"
 			}

app/vmagent/datadogv2/request_handler.go

@@ -0,0 +1,102 @@
+package datadogv2
+
+import (
+	"net/http"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogutils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv2"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv2/stream"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+var (
+	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="datadogv2"}`)
+	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="datadogv2"}`)
+	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="datadogv2"}`)
+)
+
+// InsertHandlerForHTTP processes remote write for DataDog POST /api/v2/series request.
+//
+// See https://docs.datadoghq.com/api/latest/metrics/#submit-metrics
+func InsertHandlerForHTTP(at *auth.Token, req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
+	ct := req.Header.Get("Content-Type")
+	ce := req.Header.Get("Content-Encoding")
+	return stream.Parse(req.Body, ce, ct, func(series []datadogv2.Series) error {
+		return insertRows(at, series, extraLabels)
+	})
+}
+
+func insertRows(at *auth.Token, series []datadogv2.Series, extraLabels []prompbmarshal.Label) error {
+	ctx := common.GetPushCtx()
+	defer common.PutPushCtx(ctx)
+
+	rowsTotal := 0
+	tssDst := ctx.WriteRequest.Timeseries[:0]
+	labels := ctx.Labels[:0]
+	samples := ctx.Samples[:0]
+	for i := range series {
+		ss := &series[i]
+		rowsTotal += len(ss.Points)
+		labelsLen := len(labels)
+		labels = append(labels, prompbmarshal.Label{
+			Name:  "__name__",
+			Value: ss.Metric,
+		})
+		for _, rs := range ss.Resources {
+			labels = append(labels, prompbmarshal.Label{
+				Name:  rs.Type,
+				Value: rs.Name,
+			})
+		}
+		if ss.SourceTypeName != "" {
+			labels = append(labels, prompbmarshal.Label{
+				Name:  "source_type_name",
+				Value: ss.SourceTypeName,
+			})
+		}
+		for _, tag := range ss.Tags {
+			name, value := datadogutils.SplitTag(tag)
+			if name == "host" {
+				name = "exported_host"
+			}
+			labels = append(labels, prompbmarshal.Label{
+				Name:  name,
+				Value: value,
+			})
+		}
+		labels = append(labels, extraLabels...)
+		samplesLen := len(samples)
+		for _, pt := range ss.Points {
+			samples = append(samples, prompbmarshal.Sample{
+				Timestamp: pt.Timestamp * 1000,
+				Value:     pt.Value,
+			})
+		}
+		tssDst = append(tssDst, prompbmarshal.TimeSeries{
+			Labels:  labels[labelsLen:],
+			Samples: samples[samplesLen:],
+		})
+	}
+	ctx.WriteRequest.Timeseries = tssDst
+	ctx.Labels = labels
+	ctx.Samples = samples
+	if !remotewrite.TryPush(at, &ctx.WriteRequest) {
+		return remotewrite.ErrQueueFullHTTPRetry
+	}
+	rowsInserted.Add(rowsTotal)
+	if at != nil {
+		rowsTenantInserted.Get(at).Add(rowsTotal)
+	}
+	rowsPerInsert.Update(float64(rowsTotal))
+	return nil
+}

app/vmagent/main.go

@@ -12,7 +12,9 @@ import (
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/csvimport"
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/datadog"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/datadogsketches"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/datadogv1"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/datadogv2"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/graphite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/influx"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/native"
@@ -44,10 +46,10 @@ import (
 )
 
 var (
-	httpListenAddr = flag.String("httpListenAddr", ":8429", "TCP address to listen for http connections. "+
+	httpListenAddrs = flagutil.NewArrayString("httpListenAddr", "TCP address to listen for incoming http requests. "+
 		"Set this flag to empty value in order to disable listening on any port. This mode may be useful for running multiple vmagent instances on the same server. "+
 		"Note that /targets and /metrics pages aren't available if -httpListenAddr=''. See also -tls and -httpListenAddr.useProxyProtocol")
-	useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
+	useProxyProtocol = flagutil.NewArrayBool("httpListenAddr.useProxyProtocol", "Whether to use proxy protocol for connections accepted at the corresponding -httpListenAddr . "+
 		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
 		"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
 	influxListenAddr = flag.String("influxListenAddr", "", "TCP and UDP address to listen for InfluxDB line protocol data. Usually :8089 must be set. Doesn't work if empty. "+
@@ -68,7 +70,8 @@ var (
 		"See also -opentsdbHTTPListenAddr.useProxyProtocol")
 	opentsdbHTTPUseProxyProtocol = flag.Bool("opentsdbHTTPListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted "+
 		"at -opentsdbHTTPListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
-	configAuthKey = flag.String("configAuthKey", "", "Authorization key for accessing /config page. It must be passed via authKey query arg")
+	configAuthKey = flagutil.NewPassword("configAuthKey", "Authorization key for accessing /config page. It must be passed via authKey query arg")
+	reloadAuthKey = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed as authKey=...")
 	dryRun        = flag.Bool("dryRun", false, "Whether to check config files without running vmagent. The following files are checked: "+
 		"-promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig, -remoteWrite.streamAggr.config . "+
 		"Unknown config entries aren't allowed in -promscrape.config by default. This can be changed by passing -promscrape.config.strictParse=false command-line flag")
@@ -95,7 +98,6 @@ func main() {
 	remotewrite.InitSecretFlags()
 	buildinfo.Init()
 	logger.Init()
-	pushmetrics.Init()
 
 	if promscrape.IsDryRun() {
 		if err := promscrape.CheckConfig(); err != nil {
@@ -118,7 +120,11 @@ func main() {
 		return
 	}
 
-	logger.Infof("starting vmagent at %q...", *httpListenAddr)
+	listenAddrs := *httpListenAddrs
+	if len(listenAddrs) == 0 {
+		listenAddrs = []string{":8429"}
+	}
+	logger.Infof("starting vmagent at %q...", listenAddrs)
 	startTime := time.Now()
 	remotewrite.Init()
 	common.StartUnmarshalWorkers()
@@ -141,22 +147,20 @@ func main() {
 
 	promscrape.Init(remotewrite.PushDropSamplesOnFailure)
 
-	if len(*httpListenAddr) > 0 {
-		go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
-	}
+	go httpserver.Serve(listenAddrs, useProxyProtocol, requestHandler)
 	logger.Infof("started vmagent in %.3f seconds", time.Since(startTime).Seconds())
 
+	pushmetrics.Init()
 	sig := procutil.WaitForSigterm()
 	logger.Infof("received signal %s", sig)
+	pushmetrics.Stop()
 
 	startTime = time.Now()
-	if len(*httpListenAddr) > 0 {
-		logger.Infof("gracefully shutting down webservice at %q", *httpListenAddr)
-		if err := httpserver.Stop(*httpListenAddr); err != nil {
-			logger.Fatalf("cannot stop the webservice: %s", err)
-		}
-		logger.Infof("successfully shut down the webservice in %.3f seconds", time.Since(startTime).Seconds())
+	logger.Infof("gracefully shutting down webservice at %q", listenAddrs)
+	if err := httpserver.Stop(listenAddrs); err != nil {
+		logger.Fatalf("cannot stop the webservice: %s", err)
 	}
+	logger.Infof("successfully shut down the webservice in %.3f seconds", time.Since(startTime).Seconds())
 
 	promscrape.Stop()
 
@@ -343,9 +347,20 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		fmt.Fprintf(w, `{"status":"ok"}`)
 		return true
 	case "/datadog/api/v1/series":
-		datadogWriteRequests.Inc()
-		if err := datadog.InsertHandlerForHTTP(nil, r); err != nil {
-			datadogWriteErrors.Inc()
+		datadogv1WriteRequests.Inc()
+		if err := datadogv1.InsertHandlerForHTTP(nil, r); err != nil {
+			datadogv1WriteErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.Header().Set("Content-Type", "application/json")
+		w.WriteHeader(202)
+		fmt.Fprintf(w, `{"status":"ok"}`)
+		return true
+	case "/datadog/api/v2/series":
+		datadogv2WriteRequests.Inc()
+		if err := datadogv2.InsertHandlerForHTTP(nil, r); err != nil {
+			datadogv2WriteErrors.Inc()
 			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
@@ -354,6 +369,15 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		w.WriteHeader(202)
 		fmt.Fprintf(w, `{"status":"ok"}`)
 		return true
+	case "/datadog/api/beta/sketches":
+		datadogsketchesWriteRequests.Inc()
+		if err := datadogsketches.InsertHandlerForHTTP(nil, r); err != nil {
+			datadogsketchesWriteErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(202)
+		return true
 	case "/datadog/api/v1/validate":
 		datadogValidateRequests.Inc()
 		// See https://docs.datadoghq.com/api/latest/authentication/#validate-api-key
@@ -408,7 +432,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		}
 		return true
 	case "/prometheus/config", "/config":
-		if !httpserver.CheckAuthFlag(w, r, *configAuthKey, "configAuthKey") {
+		if !httpserver.CheckAuthFlag(w, r, configAuthKey.Get(), "configAuthKey") {
 			return true
 		}
 		promscrapeConfigRequests.Inc()
@@ -417,7 +441,7 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		return true
 	case "/prometheus/api/v1/status/config", "/api/v1/status/config":
 		// See https://prometheus.io/docs/prometheus/latest/querying/api/#config
-		if !httpserver.CheckAuthFlag(w, r, *configAuthKey, "configAuthKey") {
+		if !httpserver.CheckAuthFlag(w, r, configAuthKey.Get(), "configAuthKey") {
 			return true
 		}
 		promscrapeStatusConfigRequests.Inc()
@@ -427,6 +451,9 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		fmt.Fprintf(w, `{"status":"success","data":{"yaml":%q}}`, bb.B)
 		return true
 	case "/prometheus/-/reload", "/-/reload":
+		if !httpserver.CheckAuthFlag(w, r, reloadAuthKey.Get(), "reloadAuthKey") {
+			return true
+		}
 		promscrapeConfigReloadRequests.Inc()
 		procutil.SelfSIGHUP()
 		w.WriteHeader(http.StatusOK)
@@ -566,9 +593,19 @@ func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path stri
 		fmt.Fprintf(w, `{"status":"ok"}`)
 		return true
 	case "datadog/api/v1/series":
-		datadogWriteRequests.Inc()
-		if err := datadog.InsertHandlerForHTTP(at, r); err != nil {
-			datadogWriteErrors.Inc()
+		datadogv1WriteRequests.Inc()
+		if err := datadogv1.InsertHandlerForHTTP(at, r); err != nil {
+			datadogv1WriteErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(202)
+		fmt.Fprintf(w, `{"status":"ok"}`)
+		return true
+	case "datadog/api/v2/series":
+		datadogv2WriteRequests.Inc()
+		if err := datadogv2.InsertHandlerForHTTP(at, r); err != nil {
+			datadogv2WriteErrors.Inc()
 			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
@@ -576,6 +613,15 @@ func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path stri
 		w.WriteHeader(202)
 		fmt.Fprintf(w, `{"status":"ok"}`)
 		return true
+	case "datadog/api/beta/sketches":
+		datadogsketchesWriteRequests.Inc()
+		if err := datadogsketches.InsertHandlerForHTTP(at, r); err != nil {
+			datadogsketchesWriteErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(202)
+		return true
 	case "datadog/api/v1/validate":
 		datadogValidateRequests.Inc()
 		// See https://docs.datadoghq.com/api/latest/authentication/#validate-api-key
@@ -626,8 +672,14 @@ var (
 
 	influxQueryRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/influx/query", protocol="influx"}`)
 
-	datadogWriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/series", protocol="datadog"}`)
-	datadogWriteErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/datadog/api/v1/series", protocol="datadog"}`)
+	datadogv1WriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/series", protocol="datadog"}`)
+	datadogv1WriteErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/datadog/api/v1/series", protocol="datadog"}`)
+
+	datadogv2WriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v2/series", protocol="datadog"}`)
+	datadogv2WriteErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/datadog/api/v2/series", protocol="datadog"}`)
+
+	datadogsketchesWriteRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/beta/sketches", protocol="datadog"}`)
+	datadogsketchesWriteErrors   = metrics.NewCounter(`vmagent_http_request_errors_total{path="/datadog/api/beta/sketches", protocol="datadog"}`)
 
 	datadogValidateRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/validate", protocol="datadog"}`)
 	datadogCheckRunRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/datadog/api/v1/check_run", protocol="datadog"}`)

app/vmagent/promremotewrite/request_handler.go

@@ -6,7 +6,6 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
@@ -48,8 +47,8 @@ func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, extraLabels []pr
 		for i := range ts.Labels {
 			label := &ts.Labels[i]
 			labels = append(labels, prompbmarshal.Label{
-				Name:  bytesutil.ToUnsafeString(label.Name),
-				Value: bytesutil.ToUnsafeString(label.Value),
+				Name:  label.Name,
+				Value: label.Value,
 			})
 		}
 		labels = append(labels, extraLabels...)

app/vmagent/remotewrite/client.go

@@ -18,6 +18,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timerpool"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timeutil"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -34,6 +35,7 @@ var (
 	proxyURL    = flagutil.NewArrayString("remoteWrite.proxyURL", "Optional proxy URL for writing data to the corresponding -remoteWrite.url. "+
 		"Supported proxies: http, https, socks5. Example: -remoteWrite.proxyURL=socks5://proxy:1234")
 
+	tlsHandshakeTimeout   = flagutil.NewArrayDuration("remoteWrite.tlsHandshakeTimeout", 20*time.Second, "The timeout for estabilishing tls connections to the corresponding -remoteWrite.url")
 	tlsInsecureSkipVerify = flagutil.NewArrayBool("remoteWrite.tlsInsecureSkipVerify", "Whether to skip tls verification when connecting to the corresponding -remoteWrite.url")
 	tlsCertFile           = flagutil.NewArrayString("remoteWrite.tlsCertFile", "Optional path to client-side TLS certificate file to use when connecting "+
 		"to the corresponding -remoteWrite.url")
@@ -58,8 +60,10 @@ var (
 	oauth2ClientID         = flagutil.NewArrayString("remoteWrite.oauth2.clientID", "Optional OAuth2 clientID to use for the corresponding -remoteWrite.url")
 	oauth2ClientSecret     = flagutil.NewArrayString("remoteWrite.oauth2.clientSecret", "Optional OAuth2 clientSecret to use for the corresponding -remoteWrite.url")
 	oauth2ClientSecretFile = flagutil.NewArrayString("remoteWrite.oauth2.clientSecretFile", "Optional OAuth2 clientSecretFile to use for the corresponding -remoteWrite.url")
-	oauth2TokenURL         = flagutil.NewArrayString("remoteWrite.oauth2.tokenUrl", "Optional OAuth2 tokenURL to use for the corresponding -remoteWrite.url")
-	oauth2Scopes           = flagutil.NewArrayString("remoteWrite.oauth2.scopes", "Optional OAuth2 scopes to use for the corresponding -remoteWrite.url. Scopes must be delimited by ';'")
+	oauth2EndpointParams   = flagutil.NewArrayString("remoteWrite.oauth2.endpointParams", "Optional OAuth2 endpoint parameters to use for the corresponding -remoteWrite.url . "+
+		`The endpoint parameters must be set in JSON format: {"param1":"value1",...,"paramN":"valueN"}`)
+	oauth2TokenURL = flagutil.NewArrayString("remoteWrite.oauth2.tokenUrl", "Optional OAuth2 tokenURL to use for the corresponding -remoteWrite.url")
+	oauth2Scopes   = flagutil.NewArrayString("remoteWrite.oauth2.scopes", "Optional OAuth2 scopes to use for the corresponding -remoteWrite.url. Scopes must be delimited by ';'")
 
 	awsUseSigv4 = flagutil.NewArrayBool("remoteWrite.aws.useSigv4", "Enables SigV4 request signing for the corresponding -remoteWrite.url. "+
 		"It is expected that other -remoteWrite.aws.* command-line flags are set if sigv4 request signing is enabled")
@@ -119,7 +123,7 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
 	tr := &http.Transport{
 		DialContext:         statDial,
 		TLSClientConfig:     tlsCfg,
-		TLSHandshakeTimeout: 10 * time.Second,
+		TLSHandshakeTimeout: tlsHandshakeTimeout.GetOptionalArg(argIdx),
 		MaxConnsPerHost:     2 * concurrency,
 		MaxIdleConnsPerHost: 2 * concurrency,
 		IdleConnTimeout:     time.Minute,
@@ -234,10 +238,16 @@ func getAuthConfig(argIdx int) (*promauth.Config, error) {
 	clientSecret := oauth2ClientSecret.GetOptionalArg(argIdx)
 	clientSecretFile := oauth2ClientSecretFile.GetOptionalArg(argIdx)
 	if clientSecretFile != "" || clientSecret != "" {
+		endpointParamsJSON := oauth2EndpointParams.GetOptionalArg(argIdx)
+		endpointParams, err := flagutil.ParseJSONMap(endpointParamsJSON)
+		if err != nil {
+			return nil, fmt.Errorf("cannot parse JSON for -remoteWrite.oauth2.endpointParams=%s: %w", endpointParamsJSON, err)
+		}
 		oauth2Cfg = &promauth.OAuth2Config{
 			ClientID:         oauth2ClientID.GetOptionalArg(argIdx),
 			ClientSecret:     promauth.NewSecret(clientSecret),
 			ClientSecretFile: clientSecretFile,
+			EndpointParams:   endpointParams,
 			TokenURL:         oauth2TokenURL.GetOptionalArg(argIdx),
 			Scopes:           strings.Split(oauth2Scopes.GetOptionalArg(argIdx), ";"),
 		}
@@ -387,7 +397,8 @@ func (c *client) newRequest(url string, body []byte) (*http.Request, error) {
 // Otherwise it tries sending the block to remote storage indefinitely.
 func (c *client) sendBlockHTTP(block []byte) bool {
 	c.rl.register(len(block), c.stopCh)
-	retryDuration := time.Second
+	maxRetryDuration := timeutil.AddJitterToDuration(time.Minute)
+	retryDuration := timeutil.AddJitterToDuration(time.Second)
 	retriesCount := 0
 
 again:
@@ -397,8 +408,8 @@ again:
 	if err != nil {
 		c.errorsCount.Inc()
 		retryDuration *= 2
-		if retryDuration > time.Minute {
-			retryDuration = time.Minute
+		if retryDuration > maxRetryDuration {
+			retryDuration = maxRetryDuration
 		}
 		logger.Warnf("couldn't send a block with size %d bytes to %q: %s; re-sending the block in %.3f seconds",
 			len(block), c.sanitizedURL, err, retryDuration.Seconds())
@@ -444,8 +455,8 @@ again:
 	// Unexpected status code returned
 	retriesCount++
 	retryDuration *= 2
-	if retryDuration > time.Minute {
-		retryDuration = time.Minute
+	if retryDuration > maxRetryDuration {
+		retryDuration = maxRetryDuration
 	}
 	body, err := io.ReadAll(resp.Body)
 	_ = resp.Body.Close()

app/vmagent/remotewrite/pendingseries.go

@@ -7,6 +7,7 @@ import (
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/encoding/zstd"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
@@ -15,6 +16,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/persistentqueue"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timeutil"
 	"github.com/VictoriaMetrics/metrics"
 	"github.com/golang/snappy"
 )
@@ -69,7 +71,8 @@ func (ps *pendingSeries) periodicFlusher() {
 	if flushSeconds <= 0 {
 		flushSeconds = 1
 	}
-	ticker := time.NewTicker(*flushInterval)
+	d := timeutil.AddJitterToDuration(*flushInterval)
+	ticker := time.NewTicker(d)
 	defer ticker.Stop()
 	for {
 		select {
@@ -107,11 +110,12 @@ type writeRequest struct {
 
 	wr prompbmarshal.WriteRequest
 
-	tss []prompbmarshal.TimeSeries
-
+	tss     []prompbmarshal.TimeSeries
 	labels  []prompbmarshal.Label
 	samples []prompbmarshal.Sample
-	buf     []byte
+
+	// buf holds labels data
+	buf []byte
 }
 
 func (wr *writeRequest) reset() {
@@ -222,33 +226,45 @@ func (wr *writeRequest) copyTimeSeries(dst, src *prompbmarshal.TimeSeries) {
 	wr.buf = buf
 }
 
+// marshalConcurrency limits the maximum number of concurrent workers, which marshal and compress WriteRequest.
+var marshalConcurrencyCh = make(chan struct{}, cgroup.AvailableCPUs())
+
 func tryPushWriteRequest(wr *prompbmarshal.WriteRequest, tryPushBlock func(block []byte) bool, isVMRemoteWrite bool) bool {
 	if len(wr.Timeseries) == 0 {
 		// Nothing to push
 		return true
 	}
+
+	marshalConcurrencyCh <- struct{}{}
+
 	bb := writeRequestBufPool.Get()
-	bb.B = prompbmarshal.MarshalWriteRequest(bb.B[:0], wr)
+	bb.B = wr.MarshalProtobuf(bb.B[:0])
 	if len(bb.B) <= maxUnpackedBlockSize.IntN() {
-		zb := snappyBufPool.Get()
+		zb := compressBufPool.Get()
 		if isVMRemoteWrite {
 			zb.B = zstd.CompressLevel(zb.B[:0], bb.B, *vmProtoCompressLevel)
 		} else {
 			zb.B = snappy.Encode(zb.B[:cap(zb.B)], bb.B)
 		}
 		writeRequestBufPool.Put(bb)
+
+		<-marshalConcurrencyCh
+
 		if len(zb.B) <= persistentqueue.MaxBlockSize {
-			if !tryPushBlock(zb.B) {
-				return false
+			zbLen := len(zb.B)
+			ok := tryPushBlock(zb.B)
+			compressBufPool.Put(zb)
+			if ok {
+				blockSizeRows.Update(float64(len(wr.Timeseries)))
+				blockSizeBytes.Update(float64(zbLen))
 			}
-			blockSizeRows.Update(float64(len(wr.Timeseries)))
-			blockSizeBytes.Update(float64(len(zb.B)))
-			snappyBufPool.Put(zb)
-			return true
+			return ok
 		}
-		snappyBufPool.Put(zb)
+		compressBufPool.Put(zb)
 	} else {
 		writeRequestBufPool.Put(bb)
+
+		<-marshalConcurrencyCh
 	}
 
 	// Too big block. Recursively split it into smaller parts if possible.
@@ -294,5 +310,7 @@ var (
 	blockSizeRows  = metrics.NewHistogram(`vmagent_remotewrite_block_size_rows`)
 )
 
-var writeRequestBufPool bytesutil.ByteBufferPool
-var snappyBufPool bytesutil.ByteBufferPool
+var (
+	writeRequestBufPool bytesutil.ByteBufferPool
+	compressBufPool     bytesutil.ByteBufferPool
+)

app/vmagent/remotewrite/pendingseries_test.go

@@ -43,7 +43,7 @@ func testPushWriteRequest(t *testing.T, rowsCount, expectedBlockLenProm, expecte
 	}
 
 	// Check Prometheus remote write
-	f(false, expectedBlockLenProm, 0)
+	f(false, expectedBlockLenProm, 3)
 
 	// Check VictoriaMetrics remote write
 	f(true, expectedBlockLenVM, 15)

app/vmagent/remotewrite/pendingseries_timing_test.go

@@ -4,7 +4,6 @@ import (
 	"fmt"
 	"testing"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	"github.com/golang/snappy"
 	"github.com/klauspost/compress/s2"
 )
@@ -22,7 +21,7 @@ func benchmarkCompressWriteRequest(b *testing.B, compressFunc func(dst, src []by
 	for _, rowsCount := range []int{1, 10, 100, 1e3, 1e4} {
 		b.Run(fmt.Sprintf("rows_%d", rowsCount), func(b *testing.B) {
 			wr := newTestWriteRequest(rowsCount, 10)
-			data := prompbmarshal.MarshalWriteRequest(nil, wr)
+			data := wr.MarshalProtobuf(nil)
 			b.ReportAllocs()
 			b.SetBytes(int64(rowsCount))
 			b.RunParallel(func(pb *testing.PB) {

app/vmagent/remotewrite/remotewrite.go

@@ -276,7 +276,7 @@ func reloadRelabelConfigs() {
 var (
 	relabelConfigReloads      = metrics.NewCounter(`vmagent_relabel_config_reloads_total`)
 	relabelConfigReloadErrors = metrics.NewCounter(`vmagent_relabel_config_reloads_errors_total`)
-	relabelConfigSuccess      = metrics.NewCounter(`vmagent_relabel_config_last_reload_successful`)
+	relabelConfigSuccess      = metrics.NewGauge(`vmagent_relabel_config_last_reload_successful`, nil)
 	relabelConfigTimestamp    = metrics.NewCounter(`vmagent_relabel_config_last_reload_success_timestamp_seconds`)
 )
 

app/vmalert-tool/unittest/unittest.go

@@ -25,6 +25,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/prometheus"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/promql"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmstorage"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
@@ -184,7 +185,8 @@ func processFlags() {
 
 func setUp() {
 	vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
-	go httpserver.Serve(httpListenAddr, false, func(w http.ResponseWriter, r *http.Request) bool {
+	var ab flagutil.ArrayBool
+	go httpserver.Serve([]string{httpListenAddr}, &ab, func(w http.ResponseWriter, r *http.Request) bool {
 		switch r.URL.Path {
 		case "/prometheus/api/v1/query":
 			if err := prometheus.QueryHandler(nil, time.Now(), w, r); err != nil {
@@ -225,7 +227,7 @@ checkCheck:
 }
 
 func tearDown() {
-	if err := httpserver.Stop(httpListenAddr); err != nil {
+	if err := httpserver.Stop([]string{httpListenAddr}); err != nil {
 		logger.Errorf("cannot stop the webservice: %s", err)
 	}
 	vmstorage.Stop()

app/vmalert/Makefile

@@ -68,6 +68,7 @@ publish-vmalert:
 
 test-vmalert:
 	go test -v -race -cover ./app/vmalert -loggerLevel=ERROR
+	go test -v -race -cover ./app/vmalert/rule
 	go test -v -race -cover ./app/vmalert/templates
 	go test -v -race -cover ./app/vmalert/datasource
 	go test -v -race -cover ./app/vmalert/notifier

app/vmalert/config/testdata/rules/rules2-good.rules

@@ -22,6 +22,7 @@ groups:
               {{ . | first | value }}
             {{ end }}
           description: "It is {{ $value }} connections for {{$labels.instance}}"
+          link: http://localhost:3000/d/wNf0q_kZk?viewPanel=51&from={{($activeAt.Add (parseDurationTime "1h")).UnixMilli}}&to={{($activeAt.Add (parseDurationTime "-1h")).UnixMilli}}
       - alert: ExampleAlertAlwaysFiring
         update_entries_limit: -1
         expr: sum by(job)

app/vmalert/datasource/init.go

@@ -10,6 +10,7 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 )
 
@@ -37,11 +38,13 @@ var (
 	tlsCAFile             = flag.String("datasource.tlsCAFile", "", `Optional path to TLS CA file to use for verifying connections to -datasource.url. By default, system CA is used`)
 	tlsServerName         = flag.String("datasource.tlsServerName", "", `Optional TLS server name to use for connections to -datasource.url. By default, the server name from -datasource.url is used`)
 
-	oauth2ClientID         = flag.String("datasource.oauth2.clientID", "", "Optional OAuth2 clientID to use for -datasource.url. ")
-	oauth2ClientSecret     = flag.String("datasource.oauth2.clientSecret", "", "Optional OAuth2 clientSecret to use for -datasource.url.")
-	oauth2ClientSecretFile = flag.String("datasource.oauth2.clientSecretFile", "", "Optional OAuth2 clientSecretFile to use for -datasource.url. ")
-	oauth2TokenURL         = flag.String("datasource.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -datasource.url.")
-	oauth2Scopes           = flag.String("datasource.oauth2.scopes", "", "Optional OAuth2 scopes to use for -datasource.url. Scopes must be delimited by ';'")
+	oauth2ClientID         = flag.String("datasource.oauth2.clientID", "", "Optional OAuth2 clientID to use for -datasource.url")
+	oauth2ClientSecret     = flag.String("datasource.oauth2.clientSecret", "", "Optional OAuth2 clientSecret to use for -datasource.url")
+	oauth2ClientSecretFile = flag.String("datasource.oauth2.clientSecretFile", "", "Optional OAuth2 clientSecretFile to use for -datasource.url")
+	oauth2EndpointParams   = flag.String("datasource.oauth2.endpointParams", "", "Optional OAuth2 endpoint parameters to use for -datasource.url . "+
+		`The endpoint parameters must be set in JSON format: {"param1":"value1",...,"paramN":"valueN"}`)
+	oauth2TokenURL = flag.String("datasource.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -datasource.url")
+	oauth2Scopes   = flag.String("datasource.oauth2.scopes", "", "Optional OAuth2 scopes to use for -datasource.url. Scopes must be delimited by ';'")
 
 	lookBack = flag.Duration("datasource.lookback", 0, `Will be deprecated soon, please adjust "-search.latencyOffset"  at datasource side `+
 		`or specify "latency_offset" in rule group's params. Lookback defines how far into the past to look when evaluating queries. `+
@@ -91,7 +94,7 @@ func Init(extraParams url.Values) (QuerierBuilder, error) {
 		logger.Warnf("flag `-datasource.lookback` will be deprecated soon. Please use `-rule.evalDelay` command-line flag instead. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5155 for details.")
 	}
 
-	tr, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
+	tr, err := httputils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
 	if err != nil {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
@@ -108,10 +111,14 @@ func Init(extraParams url.Values) (QuerierBuilder, error) {
 		extraParams.Set("round_digits", fmt.Sprintf("%d", *roundDigits))
 	}
 
+	endpointParams, err := flagutil.ParseJSONMap(*oauth2EndpointParams)
+	if err != nil {
+		return nil, fmt.Errorf("cannot parse JSON for -datasource.oauth2.endpointParams=%s: %w", *oauth2EndpointParams, err)
+	}
 	authCfg, err := utils.AuthConfig(
 		utils.WithBasicAuth(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile),
 		utils.WithBearer(*bearerToken, *bearerTokenFile),
-		utils.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes),
+		utils.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes, endpointParams),
 		utils.WithHeaders(*headers))
 	if err != nil {
 		return nil, fmt.Errorf("failed to configure auth: %w", err)

app/vmalert/main.go

@@ -59,8 +59,8 @@ absolute path to all .tpl files in root.
 	configCheckInterval = flag.Duration("configCheckInterval", 0, "Interval for checking for changes in '-rule' or '-notifier.config' files. "+
 		"By default, the checking is disabled. Send SIGHUP signal in order to force config check for changes.")
 
-	httpListenAddr   = flag.String("httpListenAddr", ":8880", "Address to listen for http connections. See also -tls and -httpListenAddr.useProxyProtocol")
-	useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
+	httpListenAddrs  = flagutil.NewArrayString("httpListenAddr", "Address to listen for incoming http requests. See also -tls and -httpListenAddr.useProxyProtocol")
+	useProxyProtocol = flagutil.NewArrayBool("httpListenAddr.useProxyProtocol", "Whether to use proxy protocol for connections accepted at the corresponding -httpListenAddr . "+
 		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
 		"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
 	evaluationInterval = flag.Duration("evaluationInterval", time.Minute, "How often to evaluate the rules")
@@ -96,7 +96,6 @@ func main() {
 	notifier.InitSecretFlags()
 	buildinfo.Init()
 	logger.Init()
-	pushmetrics.Init()
 
 	if !*remoteReadIgnoreRestoreErrors {
 		logger.Warnf("flag `remoteRead.ignoreRestoreErrors` is deprecated and will be removed in next releases.")
@@ -118,9 +117,9 @@ func main() {
 		return
 	}
 
-	eu, err := getExternalURL(*externalURL, *httpListenAddr, httpserver.IsTLS())
+	eu, err := getExternalURL(*externalURL)
 	if err != nil {
-		logger.Fatalf("failed to init `external.url`: %s", err)
+		logger.Fatalf("failed to init `-external.url`: %s", err)
 	}
 
 	alertURLGeneratorFn, err = getAlertURLGenerator(eu, *externalAlertSource, *validateTemplates)
@@ -179,12 +178,19 @@ func main() {
 
 	go configReload(ctx, manager, groupsCfg, sighupCh)
 
+	listenAddrs := *httpListenAddrs
+	if len(listenAddrs) == 0 {
+		listenAddrs = []string{":8880"}
+	}
 	rh := &requestHandler{m: manager}
-	go httpserver.Serve(*httpListenAddr, *useProxyProtocol, rh.handler)
+	go httpserver.Serve(listenAddrs, useProxyProtocol, rh.handler)
 
+	pushmetrics.Init()
 	sig := procutil.WaitForSigterm()
 	logger.Infof("service received signal %s", sig)
-	if err := httpserver.Stop(*httpListenAddr); err != nil {
+	pushmetrics.Stop()
+
+	if err := httpserver.Stop(listenAddrs); err != nil {
 		logger.Fatalf("cannot stop the webservice: %s", err)
 	}
 	cancel()
@@ -194,7 +200,7 @@ func main() {
 var (
 	configReloads      = metrics.NewCounter(`vmalert_config_last_reload_total`)
 	configReloadErrors = metrics.NewCounter(`vmalert_config_last_reload_errors_total`)
-	configSuccess      = metrics.NewCounter(`vmalert_config_last_reload_successful`)
+	configSuccess      = metrics.NewGauge(`vmalert_config_last_reload_successful`, nil)
 	configTimestamp    = metrics.NewCounter(`vmalert_config_last_reload_success_timestamp_seconds`)
 )
 
@@ -243,16 +249,34 @@ func newManager(ctx context.Context) (*manager, error) {
 	return manager, nil
 }
 
-func getExternalURL(externalURL, httpListenAddr string, isSecure bool) (*url.URL, error) {
-	if externalURL != "" {
-		return url.Parse(externalURL)
+func getExternalURL(customURL string) (*url.URL, error) {
+	if customURL == "" {
+		// use local hostname as external URL
+		listenAddr := ":8880"
+		if len(*httpListenAddrs) > 0 {
+			listenAddr = (*httpListenAddrs)[0]
+		}
+		isTLS := httpserver.IsTLS(0)
+
+		return getHostnameAsExternalURL(listenAddr, isTLS)
 	}
-	hname, err := os.Hostname()
+	u, err := url.Parse(customURL)
 	if err != nil {
 		return nil, err
 	}
+	if u.Scheme != "http" && u.Scheme != "https" {
+		return nil, fmt.Errorf("invalid scheme %q in url %q, only 'http' and 'https' are supported", u.Scheme, u.String())
+	}
+	return u, nil
+}
+
+func getHostnameAsExternalURL(addr string, isSecure bool) (*url.URL, error) {
+	hname, err := os.Hostname()
+	if err != nil {
+		return nil, fmt.Errorf("failed to get hostname: %w", err)
+	}
 	port := ""
-	if ipport := strings.Split(httpListenAddr, ":"); len(ipport) > 1 {
+	if ipport := strings.Split(addr, ":"); len(ipport) > 1 {
 		port = ":" + ipport[1]
 	}
 	schema := "http://"

app/vmalert/main_test.go

@@ -22,22 +22,29 @@ func init() {
 }
 
 func TestGetExternalURL(t *testing.T) {
-	expURL := "https://vicotriametrics.com/path"
-	u, err := getExternalURL(expURL, "", false)
+	invalidURL := "victoriametrics.com/path"
+	_, err := getExternalURL(invalidURL)
+	if err == nil {
+		t.Errorf("expected error, got nil")
+	}
+
+	expURL := "https://victoriametrics.com/path"
+	u, err := getExternalURL(expURL)
 	if err != nil {
 		t.Errorf("unexpected error %s", err)
 	}
 	if u.String() != expURL {
-		t.Errorf("unexpected url want %s, got %s", expURL, u.String())
+		t.Errorf("unexpected url: want %q, got %s", expURL, u.String())
 	}
+
 	h, _ := os.Hostname()
-	expURL = fmt.Sprintf("https://%s:4242", h)
-	u, err = getExternalURL("", "0.0.0.0:4242", true)
+	expURL = fmt.Sprintf("http://%s:8880", h)
+	u, err = getExternalURL("")
 	if err != nil {
 		t.Errorf("unexpected error %s", err)
 	}
 	if u.String() != expURL {
-		t.Errorf("unexpected url want %s, got %s", expURL, u.String())
+		t.Errorf("unexpected url: want %s, got %s", expURL, u.String())
 	}
 }
 
@@ -134,7 +141,7 @@ groups:
 				t.Fatalf("expected to have config error %s; got nil instead", cErr)
 			}
 			if cfgSuc != 0 {
-				t.Fatalf("expected to have metric configSuccess to be set to 0; got %d instead", cfgSuc)
+				t.Fatalf("expected to have metric configSuccess to be set to 0; got %v instead", cfgSuc)
 			}
 			return
 		}
@@ -143,7 +150,7 @@ groups:
 			t.Fatalf("unexpected config error: %s", cErr)
 		}
 		if cfgSuc != 1 {
-			t.Fatalf("expected to have metric configSuccess to be set to 1; got %d instead", cfgSuc)
+			t.Fatalf("expected to have metric configSuccess to be set to 1; got %v instead", cfgSuc)
 		}
 	}
 

app/vmalert/manager.go

@@ -156,11 +156,14 @@ func (m *manager) update(ctx context.Context, groupsCfg []config.Group, restore
 		var wg sync.WaitGroup
 		for _, item := range toUpdate {
 			wg.Add(1)
+			// cancel evaluation so the Update will be applied as fast as possible.
+			// it is important to call InterruptEval before the update, because cancel fn
+			// can be re-assigned during the update.
+			item.old.InterruptEval()
 			go func(old *rule.Group, new *rule.Group) {
 				old.UpdateWith(new)
 				wg.Done()
 			}(item.old, item.new)
-			item.old.InterruptEval()
 		}
 		wg.Wait()
 	}

app/vmalert/notifier/alertmanager.go

@@ -11,6 +11,7 @@ import (
 	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
 )
@@ -127,7 +128,7 @@ func NewAlertManager(alertManagerURL string, fn AlertURLGenerator, authCfg proma
 	if authCfg.TLSConfig != nil {
 		tls = authCfg.TLSConfig
 	}
-	tr, err := utils.Transport(alertManagerURL, tls.CertFile, tls.KeyFile, tls.CAFile, tls.ServerName, tls.InsecureSkipVerify)
+	tr, err := httputils.Transport(alertManagerURL, tls.CertFile, tls.KeyFile, tls.CAFile, tls.ServerName, tls.InsecureSkipVerify)
 	if err != nil {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
@@ -144,7 +145,7 @@ func NewAlertManager(alertManagerURL string, fn AlertURLGenerator, authCfg proma
 	aCfg, err := utils.AuthConfig(
 		utils.WithBasicAuth(ba.Username, ba.Password.String(), ba.PasswordFile),
 		utils.WithBearer(authCfg.BearerToken.String(), authCfg.BearerTokenFile),
-		utils.WithOAuth(oauth.ClientID, oauth.ClientSecretFile, oauth.ClientSecretFile, oauth.TokenURL, strings.Join(oauth.Scopes, ";")))
+		utils.WithOAuth(oauth.ClientID, oauth.ClientSecretFile, oauth.ClientSecretFile, oauth.TokenURL, strings.Join(oauth.Scopes, ";"), oauth.EndpointParams))
 	if err != nil {
 		return nil, fmt.Errorf("failed to configure auth: %w", err)
 	}

app/vmalert/notifier/init.go

@@ -46,6 +46,8 @@ var (
 		"If multiple args are set, then they are applied independently for the corresponding -notifier.url")
 	oauth2ClientSecretFile = flagutil.NewArrayString("notifier.oauth2.clientSecretFile", "Optional OAuth2 clientSecretFile to use for -notifier.url. "+
 		"If multiple args are set, then they are applied independently for the corresponding -notifier.url")
+	oauth2EndpointParams = flagutil.NewArrayString("notifier.oauth2.endpointParams", "Optional OAuth2 endpoint parameters to use for the corresponding -notifier.url . "+
+		`The endpoint parameters must be set in JSON format: {"param1":"value1",...,"paramN":"valueN"}`)
 	oauth2TokenURL = flagutil.NewArrayString("notifier.oauth2.tokenUrl", "Optional OAuth2 tokenURL to use for -notifier.url. "+
 		"If multiple args are set, then they are applied independently for the corresponding -notifier.url")
 	oauth2Scopes = flagutil.NewArrayString("notifier.oauth2.scopes", "Optional OAuth2 scopes to use for -notifier.url. Scopes must be delimited by ';'. "+
@@ -141,6 +143,11 @@ func InitSecretFlags() {
 func notifiersFromFlags(gen AlertURLGenerator) ([]Notifier, error) {
 	var notifiers []Notifier
 	for i, addr := range *addrs {
+		endpointParamsJSON := oauth2EndpointParams.GetOptionalArg(i)
+		endpointParams, err := flagutil.ParseJSONMap(endpointParamsJSON)
+		if err != nil {
+			return nil, fmt.Errorf("cannot parse JSON for -notifier.oauth2.endpointParams=%s: %w", endpointParamsJSON, err)
+		}
 		authCfg := promauth.HTTPClientConfig{
 			TLSConfig: &promauth.TLSConfig{
 				CAFile:             tlsCAFile.GetOptionalArg(i),
@@ -160,6 +167,7 @@ func notifiersFromFlags(gen AlertURLGenerator) ([]Notifier, error) {
 				ClientID:         oauth2ClientID.GetOptionalArg(i),
 				ClientSecret:     promauth.NewSecret(oauth2ClientSecret.GetOptionalArg(i)),
 				ClientSecretFile: oauth2ClientSecretFile.GetOptionalArg(i),
+				EndpointParams:   endpointParams,
 				Scopes:           strings.Split(oauth2Scopes.GetOptionalArg(i), ";"),
 				TokenURL:         oauth2TokenURL.GetOptionalArg(i),
 			},

app/vmalert/remoteread/init.go

@@ -8,6 +8,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
 )
 
 var (
@@ -41,8 +42,10 @@ var (
 	oauth2ClientID         = flag.String("remoteRead.oauth2.clientID", "", "Optional OAuth2 clientID to use for -remoteRead.url.")
 	oauth2ClientSecret     = flag.String("remoteRead.oauth2.clientSecret", "", "Optional OAuth2 clientSecret to use for -remoteRead.url.")
 	oauth2ClientSecretFile = flag.String("remoteRead.oauth2.clientSecretFile", "", "Optional OAuth2 clientSecretFile to use for -remoteRead.url.")
-	oauth2TokenURL         = flag.String("remoteRead.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -remoteRead.url. ")
-	oauth2Scopes           = flag.String("remoteRead.oauth2.scopes", "", "Optional OAuth2 scopes to use for -remoteRead.url. Scopes must be delimited by ';'.")
+	oauth2EndpointParams   = flag.String("remoteRead.oauth2.endpointParams", "", "Optional OAuth2 endpoint parameters to use for -remoteRead.url . "+
+		`The endpoint parameters must be set in JSON format: {"param1":"value1",...,"paramN":"valueN"}`)
+	oauth2TokenURL = flag.String("remoteRead.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -remoteRead.url. ")
+	oauth2Scopes   = flag.String("remoteRead.oauth2.scopes", "", "Optional OAuth2 scopes to use for -remoteRead.url. Scopes must be delimited by ';'.")
 )
 
 // InitSecretFlags must be called after flag.Parse and before any logging
@@ -58,15 +61,19 @@ func Init() (datasource.QuerierBuilder, error) {
 	if *addr == "" {
 		return nil, nil
 	}
-	tr, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
+	tr, err := httputils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
 	if err != nil {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
 
+	endpointParams, err := flagutil.ParseJSONMap(*oauth2EndpointParams)
+	if err != nil {
+		return nil, fmt.Errorf("cannot parse JSON for -remoteRead.oauth2.endpointParams=%s: %w", *oauth2EndpointParams, err)
+	}
 	authCfg, err := utils.AuthConfig(
 		utils.WithBasicAuth(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile),
 		utils.WithBearer(*bearerToken, *bearerTokenFile),
-		utils.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes),
+		utils.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes, endpointParams),
 		utils.WithHeaders(*headers))
 	if err != nil {
 		return nil, fmt.Errorf("failed to configure auth: %w", err)

app/vmalert/remotewrite/client.go

@@ -123,14 +123,12 @@ func (c *Client) Push(s prompbmarshal.TimeSeries) error {
 	case <-c.doneCh:
 		rwErrors.Inc()
 		droppedRows.Add(len(s.Samples))
-		droppedBytes.Add(s.Size())
 		return fmt.Errorf("client is closed")
 	case c.input <- s:
 		return nil
 	default:
 		rwErrors.Inc()
 		droppedRows.Add(len(s.Samples))
-		droppedBytes.Add(s.Size())
 		return fmt.Errorf("failed to push timeseries - queue is full (%d entries). "+
 			"Queue size is controlled by -remoteWrite.maxQueueSize flag",
 			c.maxQueueSize)
@@ -195,7 +193,6 @@ var (
 	sentRows            = metrics.NewCounter(`vmalert_remotewrite_sent_rows_total`)
 	sentBytes           = metrics.NewCounter(`vmalert_remotewrite_sent_bytes_total`)
 	droppedRows         = metrics.NewCounter(`vmalert_remotewrite_dropped_rows_total`)
-	droppedBytes        = metrics.NewCounter(`vmalert_remotewrite_dropped_bytes_total`)
 	sendDuration        = metrics.NewFloatCounter(`vmalert_remotewrite_send_duration_seconds_total`)
 	bufferFlushDuration = metrics.NewHistogram(`vmalert_remotewrite_flush_duration_seconds`)
 
@@ -211,15 +208,10 @@ func (c *Client) flush(ctx context.Context, wr *prompbmarshal.WriteRequest) {
 	if len(wr.Timeseries) < 1 {
 		return
 	}
-	defer prompbmarshal.ResetWriteRequest(wr)
+	defer wr.Reset()
 	defer bufferFlushDuration.UpdateDuration(time.Now())
 
-	data, err := wr.Marshal()
-	if err != nil {
-		logger.Errorf("failed to marshal WriteRequest: %s", err)
-		return
-	}
-
+	data := wr.MarshalProtobuf(nil)
 	b := snappy.Encode(nil, data)
 
 	retryInterval, maxRetryInterval := *retryMinInterval, *retryMaxTime
@@ -276,8 +268,11 @@ L:
 	}
 
 	rwErrors.Inc()
-	droppedRows.Add(len(wr.Timeseries))
-	droppedBytes.Add(len(b))
+	rows := 0
+	for _, ts := range wr.Timeseries {
+		rows += len(ts.Samples)
+	}
+	droppedRows.Add(rows)
 	logger.Errorf("attempts to send remote-write request failed - dropping %d time series",
 		len(wr.Timeseries))
 }

app/vmalert/remotewrite/client_test.go

@@ -140,7 +140,7 @@ func (rw *rwServer) handler(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 	wr := &prompb.WriteRequest{}
-	if err := wr.Unmarshal(b); err != nil {
+	if err := wr.UnmarshalProtobuf(b); err != nil {
 		rw.err(w, fmt.Errorf("unmarhsal err: %w", err))
 		return
 	}

app/vmalert/remotewrite/debug_client.go

@@ -11,7 +11,7 @@ import (
 
 	"github.com/golang/snappy"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 )
 
@@ -30,7 +30,7 @@ func NewDebugClient() (*DebugClient, error) {
 		return nil, nil
 	}
 
-	t, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
+	t, err := httputils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
 	if err != nil {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
@@ -49,10 +49,7 @@ func (c *DebugClient) Push(s prompbmarshal.TimeSeries) error {
 	c.wg.Add(1)
 	defer c.wg.Done()
 	wr := &prompbmarshal.WriteRequest{Timeseries: []prompbmarshal.TimeSeries{s}}
-	data, err := wr.Marshal()
-	if err != nil {
-		return fmt.Errorf("failed to marshal the given time series: %w", err)
-	}
+	data := wr.MarshalProtobuf(nil)
 
 	return c.send(data)
 }

app/vmalert/remotewrite/init.go

@@ -8,6 +8,7 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
 )
 
 var (
@@ -41,11 +42,13 @@ var (
 	tlsServerName = flag.String("remoteWrite.tlsServerName", "", "Optional TLS server name to use for connections to -remoteWrite.url. "+
 		"By default, the server name from -remoteWrite.url is used")
 
-	oauth2ClientID         = flag.String("remoteWrite.oauth2.clientID", "", "Optional OAuth2 clientID to use for -remoteWrite.url.")
-	oauth2ClientSecret     = flag.String("remoteWrite.oauth2.clientSecret", "", "Optional OAuth2 clientSecret to use for -remoteWrite.url.")
-	oauth2ClientSecretFile = flag.String("remoteWrite.oauth2.clientSecretFile", "", "Optional OAuth2 clientSecretFile to use for -remoteWrite.url.")
-	oauth2TokenURL         = flag.String("remoteWrite.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -notifier.url.")
-	oauth2Scopes           = flag.String("remoteWrite.oauth2.scopes", "", "Optional OAuth2 scopes to use for -notifier.url. Scopes must be delimited by ';'.")
+	oauth2ClientID         = flag.String("remoteWrite.oauth2.clientID", "", "Optional OAuth2 clientID to use for -remoteWrite.url")
+	oauth2ClientSecret     = flag.String("remoteWrite.oauth2.clientSecret", "", "Optional OAuth2 clientSecret to use for -remoteWrite.url")
+	oauth2ClientSecretFile = flag.String("remoteWrite.oauth2.clientSecretFile", "", "Optional OAuth2 clientSecretFile to use for -remoteWrite.url")
+	oauth2EndpointParams   = flag.String("remoteWrite.oauth2.endpointParams", "", "Optional OAuth2 endpoint parameters to use for -remoteWrite.url . "+
+		`The endpoint parameters must be set in JSON format: {"param1":"value1",...,"paramN":"valueN"}`)
+	oauth2TokenURL = flag.String("remoteWrite.oauth2.tokenUrl", "", "Optional OAuth2 tokenURL to use for -notifier.url.")
+	oauth2Scopes   = flag.String("remoteWrite.oauth2.scopes", "", "Optional OAuth2 scopes to use for -notifier.url. Scopes must be delimited by ';'.")
 )
 
 // InitSecretFlags must be called after flag.Parse and before any logging
@@ -62,15 +65,19 @@ func Init(ctx context.Context) (*Client, error) {
 		return nil, nil
 	}
 
-	t, err := utils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
+	t, err := httputils.Transport(*addr, *tlsCertFile, *tlsKeyFile, *tlsCAFile, *tlsServerName, *tlsInsecureSkipVerify)
 	if err != nil {
 		return nil, fmt.Errorf("failed to create transport: %w", err)
 	}
 
+	endpointParams, err := flagutil.ParseJSONMap(*oauth2EndpointParams)
+	if err != nil {
+		return nil, fmt.Errorf("cannot parse JSON for -remoteWrite.oauth2.endpointParams=%s: %w", *oauth2EndpointParams, err)
+	}
 	authCfg, err := utils.AuthConfig(
 		utils.WithBasicAuth(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile),
 		utils.WithBearer(*bearerToken, *bearerTokenFile),
-		utils.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes),
+		utils.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes, endpointParams),
 		utils.WithHeaders(*headers))
 	if err != nil {
 		return nil, fmt.Errorf("failed to configure auth: %w", err)

app/vmalert/rule/alerting.go

@@ -237,11 +237,30 @@ type labelSet struct {
 	origin map[string]string
 	// processed labels includes origin labels
 	// plus extra labels (group labels, service labels like alertNameLabel).
-	// in case of conflicts, extra labels are preferred.
+	// in case of key conflicts, origin labels are renamed with prefix `exported_` and extra labels are preferred.
+	// see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5161
 	// used as labels attached to notifier.Alert and ALERTS series written to remote storage.
 	processed map[string]string
 }
 
+// add adds a value v with key k to origin and processed label sets.
+// On k conflicts in processed set, the passed v is preferred.
+// On k conflicts in origin set, the original value is preferred and copied
+// to processed with `exported_%k` key. The copy happens only if passed v isn't equal to origin[k] value.
+func (ls *labelSet) add(k, v string) {
+	ls.processed[k] = v
+	ov, ok := ls.origin[k]
+	if !ok {
+		ls.origin[k] = v
+		return
+	}
+	if ov != v {
+		// copy value only if v and ov are different
+		key := fmt.Sprintf("exported_%s", k)
+		ls.processed[key] = ov
+	}
+}
+
 // toLabels converts labels from given Metric
 // to labelSet which contains original and processed labels.
 func (ar *AlertingRule) toLabels(m datasource.Metric, qFn templates.QueryFn) (*labelSet, error) {
@@ -267,24 +286,14 @@ func (ar *AlertingRule) toLabels(m datasource.Metric, qFn templates.QueryFn) (*l
 		return nil, fmt.Errorf("failed to expand labels: %w", err)
 	}
 	for k, v := range extraLabels {
-		ls.processed[k] = v
-		if _, ok := ls.origin[k]; !ok {
-			ls.origin[k] = v
-		}
+		ls.add(k, v)
 	}
-
 	// set additional labels to identify group and rule name
 	if ar.Name != "" {
-		ls.processed[alertNameLabel] = ar.Name
-		if _, ok := ls.origin[alertNameLabel]; !ok {
-			ls.origin[alertNameLabel] = ar.Name
-		}
+		ls.add(alertNameLabel, ar.Name)
 	}
 	if !*disableAlertGroupLabel && ar.GroupName != "" {
-		ls.processed[alertGroupNameLabel] = ar.GroupName
-		if _, ok := ls.origin[alertGroupNameLabel]; !ok {
-			ls.origin[alertGroupNameLabel] = ar.GroupName
-		}
+		ls.add(alertGroupNameLabel, ar.GroupName)
 	}
 	return ls, nil
 }
@@ -315,16 +324,6 @@ func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]
 			return nil, fmt.Errorf("failed to create alert: %w", err)
 		}
 
-		// if alert is instant, For: 0
-		if ar.For == 0 {
-			a.State = notifier.StateFiring
-			for i := range s.Values {
-				result = append(result, ar.alertToTimeSeries(a, s.Timestamps[i])...)
-			}
-			continue
-		}
-
-		// if alert with For > 0
 		prevT := time.Time{}
 		for i := range s.Values {
 			at := time.Unix(s.Timestamps[i], 0)
@@ -345,6 +344,10 @@ func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]
 				a.Start = at
 			}
 			prevT = at
+			if ar.For == 0 {
+				// rules with `for: 0` are always firing when they have Value
+				a.State = notifier.StateFiring
+			}
 			result = append(result, ar.alertToTimeSeries(a, s.Timestamps[i])...)
 
 			// save alert's state on last iteration, so it can be used on the next execRange call
@@ -414,8 +417,7 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
 		}
 		h := hash(ls.processed)
 		if _, ok := updated[h]; ok {
-			// duplicate may be caused by extra labels
-			// conflicting with the metric labels
+			// duplicate may be caused the removal of `__name__` label
 			curState.Err = fmt.Errorf("labels %v: %w", ls.processed, errDuplicate)
 			return nil, curState.Err
 		}
@@ -438,14 +440,13 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
 			a.KeepFiringSince = time.Time{}
 			continue
 		}
-		a, err := ar.newAlert(m, ls, start, qFn)
+		a, err := ar.newAlert(m, ls, ts, qFn)
 		if err != nil {
 			curState.Err = fmt.Errorf("failed to create alert: %w", err)
 			return nil, curState.Err
 		}
 		a.ID = h
 		a.State = notifier.StatePending
-		a.ActiveAt = ts
 		ar.alerts[h] = a
 		ar.logDebugf(ts, a, "created in state PENDING")
 	}
@@ -471,7 +472,7 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
 				}
 				// alerts with ar.KeepFiringFor>0 may remain FIRING
 				// even if their expression isn't true anymore
-				if ts.Sub(a.KeepFiringSince) > ar.KeepFiringFor {
+				if ts.Sub(a.KeepFiringSince) >= ar.KeepFiringFor {
 					a.State = notifier.StateInactive
 					a.ResolvedAt = ts
 					ar.logDebugf(ts, a, "FIRING => INACTIVE: is absent in current evaluation round")
@@ -551,9 +552,9 @@ func (ar *AlertingRule) newAlert(m datasource.Metric, ls *labelSet, start time.T
 }
 
 const (
-	// alertMetricName is the metric name for synthetic alert timeseries.
+	// alertMetricName is the metric name for time series reflecting the alert state.
 	alertMetricName = "ALERTS"
-	// alertForStateMetricName is the metric name for 'for' state of alert.
+	// alertForStateMetricName is the metric name for time series reflecting the moment of time when alert became active.
 	alertForStateMetricName = "ALERTS_FOR_STATE"
 
 	// alertNameLabel is the label name indicating the name of an alert.
@@ -568,12 +569,10 @@ const (
 
 // alertToTimeSeries converts the given alert with the given timestamp to time series
 func (ar *AlertingRule) alertToTimeSeries(a *notifier.Alert, timestamp int64) []prompbmarshal.TimeSeries {
-	var tss []prompbmarshal.TimeSeries
-	tss = append(tss, alertToTimeSeries(a, timestamp))
-	if ar.For > 0 {
-		tss = append(tss, alertForToTimeSeries(a, timestamp))
+	return []prompbmarshal.TimeSeries{
+		alertToTimeSeries(a, timestamp),
+		alertForToTimeSeries(a, timestamp),
 	}
-	return tss
 }
 
 func alertToTimeSeries(a *notifier.Alert, timestamp int64) prompbmarshal.TimeSeries {

app/vmalert/rule/alerting_test.go

@@ -28,20 +28,26 @@ func TestAlertingRule_ToTimeSeries(t *testing.T) {
 	}{
 		{
 			newTestAlertingRule("instant", 0),
-			&notifier.Alert{State: notifier.StateFiring},
+			&notifier.Alert{State: notifier.StateFiring, ActiveAt: timestamp.Add(time.Second)},
 			[]prompbmarshal.TimeSeries{
 				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
 					alertStateLabel: notifier.StateFiring.String(),
 				}),
+				newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
+					[]int64{timestamp.UnixNano()},
+					map[string]string{
+						"__name__": alertForStateMetricName,
+					}),
 			},
 		},
 		{
 			newTestAlertingRule("instant extra labels", 0),
-			&notifier.Alert{State: notifier.StateFiring, Labels: map[string]string{
-				"job":      "foo",
-				"instance": "bar",
-			}},
+			&notifier.Alert{State: notifier.StateFiring, ActiveAt: timestamp.Add(time.Second),
+				Labels: map[string]string{
+					"job":      "foo",
+					"instance": "bar",
+				}},
 			[]prompbmarshal.TimeSeries{
 				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
@@ -49,19 +55,33 @@ func TestAlertingRule_ToTimeSeries(t *testing.T) {
 					"job":           "foo",
 					"instance":      "bar",
 				}),
+				newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
+					[]int64{timestamp.UnixNano()},
+					map[string]string{
+						"__name__": alertForStateMetricName,
+						"job":      "foo",
+						"instance": "bar",
+					}),
 			},
 		},
 		{
 			newTestAlertingRule("instant labels override", 0),
-			&notifier.Alert{State: notifier.StateFiring, Labels: map[string]string{
-				alertStateLabel: "foo",
-				"__name__":      "bar",
-			}},
+			&notifier.Alert{State: notifier.StateFiring, ActiveAt: timestamp.Add(time.Second),
+				Labels: map[string]string{
+					alertStateLabel: "foo",
+					"__name__":      "bar",
+				}},
 			[]prompbmarshal.TimeSeries{
 				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
 					"__name__":      alertMetricName,
 					alertStateLabel: notifier.StateFiring.String(),
 				}),
+				newTimeSeries([]float64{float64(timestamp.Add(time.Second).Unix())},
+					[]int64{timestamp.UnixNano()},
+					map[string]string{
+						"__name__":      alertForStateMetricName,
+						alertStateLabel: "foo",
+					}),
 			},
 		},
 		{
@@ -308,14 +328,17 @@ func TestAlertingRule_Exec(t *testing.T) {
 			fq := &datasource.FakeQuerier{}
 			tc.rule.q = fq
 			tc.rule.GroupID = fakeGroup.ID()
+			ts := time.Now()
 			for i, step := range tc.steps {
 				fq.Reset()
 				fq.Add(step...)
-				if _, err := tc.rule.exec(context.TODO(), time.Now(), 0); err != nil {
+				if _, err := tc.rule.exec(context.TODO(), ts, 0); err != nil {
 					t.Fatalf("unexpected err: %s", err)
 				}
-				// artificial delay between applying steps
-				time.Sleep(defaultStep)
+
+				// shift the execution timestamp before the next iteration
+				ts = ts.Add(defaultStep)
+
 				if _, ok := tc.expAlerts[i]; !ok {
 					continue
 				}
@@ -367,7 +390,7 @@ func TestAlertingRule_ExecRange(t *testing.T) {
 				{Values: []float64{1}, Timestamps: []int64{1}},
 			},
 			[]*notifier.Alert{
-				{State: notifier.StateFiring},
+				{State: notifier.StateFiring, ActiveAt: time.Unix(1, 0)},
 			},
 			nil,
 		},
@@ -378,8 +401,9 @@ func TestAlertingRule_ExecRange(t *testing.T) {
 			},
 			[]*notifier.Alert{
 				{
-					Labels: map[string]string{"name": "foo"},
-					State:  notifier.StateFiring,
+					Labels:   map[string]string{"name": "foo"},
+					State:    notifier.StateFiring,
+					ActiveAt: time.Unix(1, 0),
 				},
 			},
 			nil,
@@ -390,9 +414,9 @@ func TestAlertingRule_ExecRange(t *testing.T) {
 				{Values: []float64{1, 1, 1}, Timestamps: []int64{1e3, 2e3, 3e3}},
 			},
 			[]*notifier.Alert{
-				{State: notifier.StateFiring},
-				{State: notifier.StateFiring},
-				{State: notifier.StateFiring},
+				{State: notifier.StateFiring, ActiveAt: time.Unix(1e3, 0)},
+				{State: notifier.StateFiring, ActiveAt: time.Unix(2e3, 0)},
+				{State: notifier.StateFiring, ActiveAt: time.Unix(3e3, 0)},
 			},
 			nil,
 		},
@@ -460,6 +484,20 @@ func TestAlertingRule_ExecRange(t *testing.T) {
 				For:         time.Second,
 			}},
 		},
+		{
+			newTestAlertingRuleWithEvalInterval("firing=>inactive=>inactive=>firing=>firing", 0, time.Second),
+			[]datasource.Metric{
+				{Values: []float64{1, 1, 1, 1}, Timestamps: []int64{1, 4, 5, 6}},
+			},
+			[]*notifier.Alert{
+				{State: notifier.StateFiring, ActiveAt: time.Unix(1, 0)},
+				// It is expected for ActiveAT to remain the same while rule continues to fire in each iteration
+				{State: notifier.StateFiring, ActiveAt: time.Unix(4, 0)},
+				{State: notifier.StateFiring, ActiveAt: time.Unix(4, 0)},
+				{State: notifier.StateFiring, ActiveAt: time.Unix(4, 0)},
+			},
+			nil,
+		},
 		{
 			newTestAlertingRule("for=>pending=>firing=>pending=>firing=>pending", time.Second),
 			[]datasource.Metric{
@@ -534,21 +572,25 @@ func TestAlertingRule_ExecRange(t *testing.T) {
 				},
 			},
 			[]*notifier.Alert{
-				{State: notifier.StateFiring, Labels: map[string]string{
-					"source": "vm",
-				}},
-				{State: notifier.StateFiring, Labels: map[string]string{
-					"source": "vm",
-				}},
+				{State: notifier.StateFiring, ActiveAt: time.Unix(1, 0),
+					Labels: map[string]string{
+						"source": "vm",
+					}},
+				{State: notifier.StateFiring, ActiveAt: time.Unix(100, 0),
+					Labels: map[string]string{
+						"source": "vm",
+					}},
 				//
-				{State: notifier.StateFiring, Labels: map[string]string{
-					"foo":    "bar",
-					"source": "vm",
-				}},
-				{State: notifier.StateFiring, Labels: map[string]string{
-					"foo":    "bar",
-					"source": "vm",
-				}},
+				{State: notifier.StateFiring, ActiveAt: time.Unix(1, 0),
+					Labels: map[string]string{
+						"foo":    "bar",
+						"source": "vm",
+					}},
+				{State: notifier.StateFiring, ActiveAt: time.Unix(5, 0),
+					Labels: map[string]string{
+						"foo":    "bar",
+						"source": "vm",
+					}},
 			},
 			nil,
 		},
@@ -768,14 +810,16 @@ func TestAlertingRule_Exec_Negative(t *testing.T) {
 	ar.q = fq
 
 	// successful attempt
+	// label `job` will be overridden by rule extra label, the original value will be reserved by "exported_job"
 	fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "bar"))
+	fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "baz"))
 	_, err := ar.exec(context.TODO(), time.Now(), 0)
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	// label `job` will collide with rule extra label and will make both time series equal
-	fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "baz"))
+	// label `__name__` will be omitted and get duplicated results here
+	fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo_1", "job", "bar"))
 	_, err = ar.exec(context.TODO(), time.Now(), 0)
 	if !errors.Is(err, errDuplicate) {
 		t.Fatalf("expected to have %s error; got %s", errDuplicate, err)
@@ -899,20 +943,22 @@ func TestAlertingRule_Template(t *testing.T) {
 				metricWithValueAndLabels(t, 10, "__name__", "second", "instance", "bar", alertNameLabel, "override"),
 			},
 			map[uint64]*notifier.Alert{
-				hash(map[string]string{alertNameLabel: "override label", "instance": "foo"}): {
+				hash(map[string]string{alertNameLabel: "override label", "exported_alertname": "override", "instance": "foo"}): {
 					Labels: map[string]string{
-						alertNameLabel: "override label",
-						"instance":     "foo",
+						alertNameLabel:       "override label",
+						"exported_alertname": "override",
+						"instance":           "foo",
 					},
 					Annotations: map[string]string{
 						"summary":     `first: Too high connection number for "foo"`,
 						"description": `override: It is 2 connections for "foo"`,
 					},
 				},
-				hash(map[string]string{alertNameLabel: "override label", "instance": "bar"}): {
+				hash(map[string]string{alertNameLabel: "override label", "exported_alertname": "override", "instance": "bar"}): {
 					Labels: map[string]string{
-						alertNameLabel: "override label",
-						"instance":     "bar",
+						alertNameLabel:       "override label",
+						"exported_alertname": "override",
+						"instance":           "bar",
 					},
 					Annotations: map[string]string{
 						"summary":     `second: Too high connection number for "bar"`,
@@ -941,14 +987,18 @@ func TestAlertingRule_Template(t *testing.T) {
 			},
 			map[uint64]*notifier.Alert{
 				hash(map[string]string{
-					alertNameLabel:      "OriginLabels",
-					alertGroupNameLabel: "Testing",
-					"instance":          "foo",
+					alertNameLabel:        "OriginLabels",
+					"exported_alertname":  "originAlertname",
+					alertGroupNameLabel:   "Testing",
+					"exported_alertgroup": "originGroupname",
+					"instance":            "foo",
 				}): {
 					Labels: map[string]string{
-						alertNameLabel:      "OriginLabels",
-						alertGroupNameLabel: "Testing",
-						"instance":          "foo",
+						alertNameLabel:        "OriginLabels",
+						"exported_alertname":  "originAlertname",
+						alertGroupNameLabel:   "Testing",
+						"exported_alertgroup": "originGroupname",
+						"instance":            "foo",
 					},
 					Annotations: map[string]string{
 						"summary": `Alert "originAlertname(originGroupname)" for instance foo`,
@@ -1087,8 +1137,65 @@ func newTestAlertingRule(name string, waitFor time.Duration) *AlertingRule {
 	return &rule
 }
 
+func newTestAlertingRuleWithEvalInterval(name string, waitFor, evalInterval time.Duration) *AlertingRule {
+	rule := newTestAlertingRule(name, waitFor)
+	rule.EvalInterval = evalInterval
+	return rule
+}
+
 func newTestAlertingRuleWithKeepFiring(name string, waitFor, keepFiringFor time.Duration) *AlertingRule {
 	rule := newTestAlertingRule(name, waitFor)
 	rule.KeepFiringFor = keepFiringFor
 	return rule
 }
+
+func TestAlertingRule_ToLabels(t *testing.T) {
+	metric := datasource.Metric{
+		Labels: []datasource.Label{
+			{Name: "instance", Value: "0.0.0.0:8800"},
+			{Name: "group", Value: "vmalert"},
+			{Name: "alertname", Value: "ConfigurationReloadFailure"},
+		},
+		Values:     []float64{1},
+		Timestamps: []int64{time.Now().UnixNano()},
+	}
+
+	ar := &AlertingRule{
+		Labels: map[string]string{
+			"instance": "override", // this should override instance with new value
+			"group":    "vmalert",  // this shouldn't have effect since value in metric is equal
+		},
+		Expr:      "sum(vmalert_alerting_rules_error) by(instance, group, alertname) > 0",
+		Name:      "AlertingRulesError",
+		GroupName: "vmalert",
+	}
+
+	expectedOriginLabels := map[string]string{
+		"instance":   "0.0.0.0:8800",
+		"group":      "vmalert",
+		"alertname":  "ConfigurationReloadFailure",
+		"alertgroup": "vmalert",
+	}
+
+	expectedProcessedLabels := map[string]string{
+		"instance":           "override",
+		"exported_instance":  "0.0.0.0:8800",
+		"alertname":          "AlertingRulesError",
+		"exported_alertname": "ConfigurationReloadFailure",
+		"group":              "vmalert",
+		"alertgroup":         "vmalert",
+	}
+
+	ls, err := ar.toLabels(metric, nil)
+	if err != nil {
+		t.Fatalf("unexpected error: %s", err)
+	}
+
+	if !reflect.DeepEqual(ls.origin, expectedOriginLabels) {
+		t.Errorf("origin labels mismatch, got: %v, want: %v", ls.origin, expectedOriginLabels)
+	}
+
+	if !reflect.DeepEqual(ls.processed, expectedProcessedLabels) {
+		t.Errorf("processed labels mismatch, got: %v, want: %v", ls.processed, expectedProcessedLabels)
+	}
+}

app/vmalert/rule/recording.go

@@ -194,6 +194,9 @@ func (rr *RecordingRule) toTimeSeries(m datasource.Metric) prompbmarshal.TimeSer
 	labels["__name__"] = rr.Name
 	// override existing labels with configured ones
 	for k, v := range rr.Labels {
+		if _, ok := labels[k]; ok && labels[k] != v {
+			labels[fmt.Sprintf("exported_%s", k)] = labels[k]
+		}
 		labels[k] = v
 	}
 	return newTimeSeries(m.Values, m.Timestamps, labels)
@@ -203,7 +206,7 @@ func (rr *RecordingRule) toTimeSeries(m datasource.Metric) prompbmarshal.TimeSer
 func (rr *RecordingRule) updateWith(r Rule) error {
 	nr, ok := r.(*RecordingRule)
 	if !ok {
-		return fmt.Errorf("BUG: attempt to update recroding rule with wrong type %#v", r)
+		return fmt.Errorf("BUG: attempt to update recording rule with wrong type %#v", r)
 	}
 	rr.Expr = nr.Expr
 	rr.Labels = nr.Labels

app/vmalert/rule/recording_test.go

@@ -61,7 +61,7 @@ func TestRecordingRule_Exec(t *testing.T) {
 			},
 			[]datasource.Metric{
 				metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "foo"),
-				metricWithValueAndLabels(t, 1, "__name__", "bar", "job", "bar"),
+				metricWithValueAndLabels(t, 1, "__name__", "bar", "job", "bar", "source", "origin"),
 			},
 			[]prompbmarshal.TimeSeries{
 				newTimeSeries([]float64{2}, []int64{timestamp.UnixNano()}, map[string]string{
@@ -70,9 +70,10 @@ func TestRecordingRule_Exec(t *testing.T) {
 					"source":   "test",
 				}),
 				newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
-					"__name__": "job:foo",
-					"job":      "bar",
-					"source":   "test",
+					"__name__":        "job:foo",
+					"job":             "bar",
+					"source":          "test",
+					"exported_source": "origin",
 				}),
 			},
 		},
@@ -254,10 +255,7 @@ func TestRecordingRule_ExecNegative(t *testing.T) {
 	fq.Add(metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "bar"))
 
 	_, err = rr.exec(context.TODO(), time.Now(), 0)
-	if err == nil {
-		t.Fatalf("expected to get err; got nil")
-	}
-	if !strings.Contains(err.Error(), errDuplicate.Error()) {
-		t.Fatalf("expected to get err %q; got %q insterad", errDuplicate, err)
+	if err != nil {
+		t.Fatal(err)
 	}
 }

app/vmalert/utils/auth.go

@@ -45,13 +45,14 @@ func WithBearer(token, tokenFile string) AuthConfigOptions {
 }
 
 // WithOAuth returns AuthConfigOptions and set OAuth params based on given params
-func WithOAuth(clientID, clientSecret, clientSecretFile, tokenURL, scopes string) AuthConfigOptions {
+func WithOAuth(clientID, clientSecret, clientSecretFile, tokenURL, scopes string, endpointParams map[string]string) AuthConfigOptions {
 	return func(config *promauth.HTTPClientConfig) {
 		if clientSecretFile != "" || clientSecret != "" {
 			config.OAuth2 = &promauth.OAuth2Config{
 				ClientID:         clientID,
 				ClientSecret:     promauth.NewSecret(clientSecret),
 				ClientSecretFile: clientSecretFile,
+				EndpointParams:   endpointParams,
 				TokenURL:         tokenURL,
 				Scopes:           strings.Split(scopes, ";"),
 			}

app/vmalert/web.go

@@ -12,11 +12,15 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/rule"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/tpl"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 )
 
+var reloadAuthKey = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed as authKey=...")
+
 var (
 	apiLinks = [][2]string{
 		// api links are relative since they can be used by external clients,
@@ -84,7 +88,10 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
 		WriteRuleDetails(w, r, rule)
 		return true
 	case "/vmalert/groups":
-		WriteListGroups(w, r, rh.groups())
+		var data []apiGroup
+		rf := extractRulesFilter(r)
+		data = rh.groups(rf)
+		WriteListGroups(w, r, data)
 		return true
 	case "/vmalert/notifiers":
 		WriteListTargets(w, r, notifier.GetTargets())
@@ -95,12 +102,20 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
 	case "/rules":
 		// Grafana makes an extra request to `/rules`
 		// handler in addition to `/api/v1/rules` calls in alerts UI,
-		WriteListGroups(w, r, rh.groups())
+		var data []apiGroup
+		rf := extractRulesFilter(r)
+		data = rh.groups(rf)
+		WriteListGroups(w, r, data)
 		return true
 
 	case "/vmalert/api/v1/rules", "/api/v1/rules":
 		// path used by Grafana for ng alerting
-		data, err := rh.listGroups()
+		var data []byte
+		var err error
+
+		rf := extractRulesFilter(r)
+		data, err = rh.listGroups(rf)
+
 		if err != nil {
 			httpserver.Errorf(w, r, "%s", err)
 			return true
@@ -108,6 +123,7 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
 		w.Header().Set("Content-Type", "application/json")
 		w.Write(data)
 		return true
+
 	case "/vmalert/api/v1/alerts", "/api/v1/alerts":
 		// path used by Grafana for ng alerting
 		data, err := rh.listAlerts()
@@ -151,6 +167,9 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
 		w.Write(data)
 		return true
 	case "/-/reload":
+		if !httpserver.CheckAuthFlag(w, r, reloadAuthKey.Get(), "reloadAuthKey") {
+			return true
+		}
 		logger.Infof("api config reload was called, sending sighup")
 		procutil.SelfSIGHUP()
 		w.WriteHeader(http.StatusOK)
@@ -201,26 +220,90 @@ type listGroupsResponse struct {
 	} `json:"data"`
 }
 
-func (rh *requestHandler) groups() []apiGroup {
+// see https://prometheus.io/docs/prometheus/latest/querying/api/#rules
+type rulesFilter struct {
+	files         []string
+	groupNames    []string
+	ruleNames     []string
+	ruleType      string
+	excludeAlerts bool
+}
+
+func extractRulesFilter(r *http.Request) rulesFilter {
+	rf := rulesFilter{}
+
+	var ruleType string
+	ruleTypeParam := r.URL.Query().Get("type")
+	// for some reason, `type` in filter doesn't match `type` in response,
+	// so we use this matching here
+	if ruleTypeParam == "alert" {
+		ruleType = ruleTypeAlerting
+	} else if ruleTypeParam == "record" {
+		ruleType = ruleTypeRecording
+	}
+	rf.ruleType = ruleType
+
+	rf.excludeAlerts = httputils.GetBool(r, "exclude_alerts")
+	rf.ruleNames = append([]string{}, r.Form["rule_name[]"]...)
+	rf.groupNames = append([]string{}, r.Form["rule_group[]"]...)
+	rf.files = append([]string{}, r.Form["file[]"]...)
+	return rf
+}
+
+func (rh *requestHandler) groups(rf rulesFilter) []apiGroup {
 	rh.m.groupsMu.RLock()
 	defer rh.m.groupsMu.RUnlock()
 
-	groups := make([]apiGroup, 0)
-	for _, g := range rh.m.groups {
-		groups = append(groups, groupToAPI(g))
+	isInList := func(list []string, needle string) bool {
+		if len(list) < 1 {
+			return true
+		}
+		for _, i := range list {
+			if i == needle {
+				return true
+			}
+		}
+		return false
 	}
 
-	// sort list of alerts for deterministic output
+	groups := make([]apiGroup, 0)
+	for _, group := range rh.m.groups {
+		if !isInList(rf.groupNames, group.Name) {
+			continue
+		}
+		if !isInList(rf.files, group.File) {
+			continue
+		}
+
+		g := groupToAPI(group)
+		// the returned list should always be non-nil
+		// https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4221
+		filteredRules := make([]apiRule, 0)
+		for _, r := range g.Rules {
+			if rf.ruleType != "" && rf.ruleType != r.Type {
+				continue
+			}
+			if !isInList(rf.ruleNames, r.Name) {
+				continue
+			}
+			if rf.excludeAlerts {
+				r.Alerts = nil
+			}
+			filteredRules = append(filteredRules, r)
+		}
+		g.Rules = filteredRules
+		groups = append(groups, g)
+	}
+	// sort list of groups for deterministic output
 	sort.Slice(groups, func(i, j int) bool {
 		return groups[i].Name < groups[j].Name
 	})
-
 	return groups
 }
 
-func (rh *requestHandler) listGroups() ([]byte, error) {
+func (rh *requestHandler) listGroups(rf rulesFilter) ([]byte, error) {
 	lr := listGroupsResponse{Status: "success"}
-	lr.Data.Groups = rh.groups()
+	lr.Data.Groups = rh.groups(rf)
 	b, err := json.Marshal(lr)
 	if err != nil {
 		return nil, &httpserver.ErrorWithStatusCode{

app/vmalert/web_test.go

@@ -23,6 +23,7 @@ func TestHandler(t *testing.T) {
 	})
 	g := &rule.Group{
 		Name:        "group",
+		File:        "rules.yaml",
 		Concurrency: 1,
 	}
 	ar := rule.NewAlertingRule(fq, g, config.Rule{ID: 0, Alert: "alert"})
@@ -165,6 +166,74 @@ func TestHandler(t *testing.T) {
 			t.Fatalf("expected %+v to have state updates field not empty", gotRuleWithUpdates.StateUpdates)
 		}
 	})
+
+	t.Run("/api/v1/rules&filters", func(t *testing.T) {
+		check := func(url string, expGroups, expRules int) {
+			t.Helper()
+			lr := listGroupsResponse{}
+			getResp(ts.URL+url, &lr, 200)
+			if length := len(lr.Data.Groups); length != expGroups {
+				t.Errorf("expected %d groups got %d", expGroups, length)
+			}
+			if len(lr.Data.Groups) < 1 {
+				return
+			}
+			var rulesN int
+			for _, gr := range lr.Data.Groups {
+				rulesN += len(gr.Rules)
+			}
+			if rulesN != expRules {
+				t.Errorf("expected %d rules got %d", expRules, rulesN)
+			}
+		}
+
+		check("/api/v1/rules?type=alert", 1, 1)
+		check("/api/v1/rules?type=record", 1, 1)
+
+		check("/vmalert/api/v1/rules?type=alert", 1, 1)
+		check("/vmalert/api/v1/rules?type=record", 1, 1)
+
+		// no filtering expected due to bad params
+		check("/api/v1/rules?type=badParam", 1, 2)
+		check("/api/v1/rules?foo=bar", 1, 2)
+
+		check("/api/v1/rules?rule_group[]=foo&rule_group[]=bar", 0, 0)
+		check("/api/v1/rules?rule_group[]=foo&rule_group[]=group&rule_group[]=bar", 1, 2)
+
+		check("/api/v1/rules?rule_group[]=group&file[]=foo", 0, 0)
+		check("/api/v1/rules?rule_group[]=group&file[]=rules.yaml", 1, 2)
+
+		check("/api/v1/rules?rule_group[]=group&file[]=rules.yaml&rule_name[]=foo", 1, 0)
+		check("/api/v1/rules?rule_group[]=group&file[]=rules.yaml&rule_name[]=alert", 1, 1)
+		check("/api/v1/rules?rule_group[]=group&file[]=rules.yaml&rule_name[]=alert&rule_name[]=record", 1, 2)
+	})
+	t.Run("/api/v1/rules&exclude_alerts=true", func(t *testing.T) {
+		// check if response returns active alerts by default
+		lr := listGroupsResponse{}
+		getResp(ts.URL+"/api/v1/rules?rule_group[]=group&file[]=rules.yaml", &lr, 200)
+		activeAlerts := 0
+		for _, gr := range lr.Data.Groups {
+			for _, r := range gr.Rules {
+				activeAlerts += len(r.Alerts)
+			}
+		}
+		if activeAlerts == 0 {
+			t.Fatalf("expected at least 1 active alert in response; got 0")
+		}
+
+		// disable returning alerts via param
+		lr = listGroupsResponse{}
+		getResp(ts.URL+"/api/v1/rules?rule_group[]=group&file[]=rules.yaml&exclude_alerts=true", &lr, 200)
+		activeAlerts = 0
+		for _, gr := range lr.Data.Groups {
+			for _, r := range gr.Rules {
+				activeAlerts += len(r.Alerts)
+			}
+		}
+		if activeAlerts != 0 {
+			t.Fatalf("expected to get 0 active alert in response; got %d", activeAlerts)
+		}
+	})
 }
 
 func TestEmptyResponse(t *testing.T) {

app/vmalert/web_types.go

@@ -193,10 +193,15 @@ func ruleToAPI(r interface{}) apiRule {
 	return apiRule{}
 }
 
+const (
+	ruleTypeRecording = "recording"
+	ruleTypeAlerting  = "alerting"
+)
+
 func recordingToAPI(rr *rule.RecordingRule) apiRule {
 	lastState := rule.GetLastEntry(rr)
 	r := apiRule{
-		Type:              "recording",
+		Type:              ruleTypeRecording,
 		DatasourceType:    rr.Type.String(),
 		Name:              rr.Name,
 		Query:             rr.Expr,
@@ -224,7 +229,7 @@ func recordingToAPI(rr *rule.RecordingRule) apiRule {
 func alertingToAPI(ar *rule.AlertingRule) apiRule {
 	lastState := rule.GetLastEntry(ar)
 	r := apiRule{
-		Type:              "alerting",
+		Type:              ruleTypeAlerting,
 		DatasourceType:    ar.Type.String(),
 		Name:              ar.Name,
 		Query:             ar.Expr,

app/vmauth/auth_config.go

@@ -9,6 +9,7 @@ import (
 	"net/url"
 	"os"
 	"regexp"
+	"sort"
 	"strconv"
 	"strings"
 	"sync"
@@ -16,12 +17,13 @@ import (
 	"time"
 
 	"github.com/VictoriaMetrics/metrics"
+	"github.com/cespare/xxhash/v2"
 	"gopkg.in/yaml.v2"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envtemplate"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs/fscore"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 )
@@ -41,6 +43,9 @@ var (
 type AuthConfig struct {
 	Users            []UserInfo `yaml:"users,omitempty"`
 	UnauthorizedUser *UserInfo  `yaml:"unauthorized_user,omitempty"`
+
+	// ms holds all the metrics for the given AuthConfig
+	ms *metrics.Set
 }
 
 // UserInfo is user information read from authConfigPath
@@ -56,16 +61,19 @@ type UserInfo struct {
 	DefaultURL             *URLPrefix  `yaml:"default_url,omitempty"`
 	RetryStatusCodes       []int       `yaml:"retry_status_codes,omitempty"`
 	LoadBalancingPolicy    string      `yaml:"load_balancing_policy,omitempty"`
-	DropSrcPathPrefixParts int         `yaml:"drop_src_path_prefix_parts,omitempty"`
+	DropSrcPathPrefixParts *int        `yaml:"drop_src_path_prefix_parts,omitempty"`
 	TLSInsecureSkipVerify  *bool       `yaml:"tls_insecure_skip_verify,omitempty"`
 	TLSCAFile              string      `yaml:"tls_ca_file,omitempty"`
 
+	MetricLabels map[string]string `yaml:"metric_labels,omitempty"`
+
 	concurrencyLimitCh      chan struct{}
 	concurrencyLimitReached *metrics.Counter
 
 	httpTransport *http.Transport
 
 	requests         *metrics.Counter
+	backendErrors    *metrics.Counter
 	requestsDuration *metrics.Summary
 }
 
@@ -126,16 +134,30 @@ func (h *Header) MarshalYAML() (interface{}, error) {
 
 // URLMap is a mapping from source paths to target urls.
 type URLMap struct {
-	SrcPaths               []*SrcPath  `yaml:"src_paths,omitempty"`
-	URLPrefix              *URLPrefix  `yaml:"url_prefix,omitempty"`
-	HeadersConf            HeadersConf `yaml:",inline"`
-	RetryStatusCodes       []int       `yaml:"retry_status_codes,omitempty"`
-	LoadBalancingPolicy    string      `yaml:"load_balancing_policy,omitempty"`
-	DropSrcPathPrefixParts int         `yaml:"drop_src_path_prefix_parts,omitempty"`
+	// SrcHosts is the list of regular expressions, which match the request hostname.
+	SrcHosts []*Regex `yaml:"src_hosts,omitempty"`
+
+	// SrcPaths is the list of regular expressions, which match the request path.
+	SrcPaths []*Regex `yaml:"src_paths,omitempty"`
+
+	// UrlPrefix contains backend url prefixes for the proxied request url.
+	URLPrefix *URLPrefix `yaml:"url_prefix,omitempty"`
+
+	// HeadersConf is the config for augumenting request and response headers.
+	HeadersConf HeadersConf `yaml:",inline"`
+
+	// RetryStatusCodes is the list of response status codes used for retrying requests.
+	RetryStatusCodes []int `yaml:"retry_status_codes,omitempty"`
+
+	// LoadBalancingPolicy is load balancing policy among UrlPrefix backends.
+	LoadBalancingPolicy string `yaml:"load_balancing_policy,omitempty"`
+
+	// DropSrcPathPrefixParts is the number of `/`-delimited request path prefix parts to drop before proxying the request to backend.
+	DropSrcPathPrefixParts *int `yaml:"drop_src_path_prefix_parts,omitempty"`
 }
 
-// SrcPath represents an src path
-type SrcPath struct {
+// Regex represents a regex
+type Regex struct {
 	sOriginal string
 	re        *regexp.Regexp
 }
@@ -152,6 +174,9 @@ type URLPrefix struct {
 
 	// load balancing policy used
 	loadBalancingPolicy string
+
+	// how many request path prefix parts to drop before routing the request to backendURL.
+	dropSrcPathPrefixParts int
 }
 
 func (up *URLPrefix) setLoadBalancingPolicy(loadBalancingPolicy string) error {
@@ -249,8 +274,10 @@ func (up *URLPrefix) getLeastLoadedBackendURL() *backendURL {
 		if bu.isBroken() {
 			continue
 		}
-		if atomic.CompareAndSwapInt32(&bu.concurrentRequests, 0, 1) {
+		if atomic.LoadInt32(&bu.concurrentRequests) == 0 {
 			// Fast path - return the backend with zero concurrently executed requests.
+			// Do not use atomic.CompareAndSwapInt32(), since it is much slower on systems with many CPU cores.
+			atomic.AddInt32(&bu.concurrentRequests, 1)
 			return bu
 		}
 	}
@@ -333,8 +360,8 @@ func (up *URLPrefix) MarshalYAML() (interface{}, error) {
 	return string(b), nil
 }
 
-func (sp *SrcPath) match(s string) bool {
-	prefix, ok := sp.re.LiteralPrefix()
+func (r *Regex) match(s string) bool {
+	prefix, ok := r.re.LiteralPrefix()
 	if ok {
 		// Fast path - literal match
 		return s == prefix
@@ -342,11 +369,11 @@ func (sp *SrcPath) match(s string) bool {
 	if !strings.HasPrefix(s, prefix) {
 		return false
 	}
-	return sp.re.MatchString(s)
+	return r.re.MatchString(s)
 }
 
 // UnmarshalYAML implements yaml.Unmarshaler
-func (sp *SrcPath) UnmarshalYAML(f func(interface{}) error) error {
+func (r *Regex) UnmarshalYAML(f func(interface{}) error) error {
 	var s string
 	if err := f(&s); err != nil {
 		return err
@@ -356,20 +383,20 @@ func (sp *SrcPath) UnmarshalYAML(f func(interface{}) error) error {
 	if err != nil {
 		return fmt.Errorf("cannot build regexp from %q: %w", s, err)
 	}
-	sp.sOriginal = s
-	sp.re = re
+	r.sOriginal = s
+	r.re = re
 	return nil
 }
 
 // MarshalYAML implements yaml.Marshaler.
-func (sp *SrcPath) MarshalYAML() (interface{}, error) {
-	return sp.sOriginal, nil
+func (r *Regex) MarshalYAML() (interface{}, error) {
+	return r.sOriginal, nil
 }
 
 var (
 	configReloads      = metrics.NewCounter(`vmauth_config_last_reload_total`)
 	configReloadErrors = metrics.NewCounter(`vmauth_config_last_reload_errors_total`)
-	configSuccess      = metrics.NewCounter(`vmauth_config_last_reload_successful`)
+	configSuccess      = metrics.NewGauge(`vmauth_config_last_reload_successful`, nil)
 	configTimestamp    = metrics.NewCounter(`vmauth_config_last_reload_success_timestamp_seconds`)
 )
 
@@ -445,17 +472,19 @@ func authConfigReloader(sighupCh <-chan os.Signal) {
 // authConfigData needs to be updated each time authConfig is updated.
 var authConfigData atomic.Pointer[[]byte]
 
-var authConfig atomic.Pointer[AuthConfig]
-var authUsers atomic.Pointer[map[string]*UserInfo]
-var authConfigWG sync.WaitGroup
-var stopCh chan struct{}
+var (
+	authConfig   atomic.Pointer[AuthConfig]
+	authUsers    atomic.Pointer[map[string]*UserInfo]
+	authConfigWG sync.WaitGroup
+	stopCh       chan struct{}
+)
 
 // loadAuthConfig loads and applies the config from *authConfigPath.
 // It returns bool value to identify if new config was applied.
 // The config can be not applied if there is a parsing error
 // or if there are no changes to the current authConfig.
 func loadAuthConfig() (bool, error) {
-	data, err := fs.ReadFileOrHTTP(*authConfigPath)
+	data, err := fscore.ReadFileOrHTTP(*authConfigPath)
 	if err != nil {
 		return false, fmt.Errorf("failed to read -auth.config=%q: %w", *authConfigPath, err)
 	}
@@ -477,6 +506,11 @@ func loadAuthConfig() (bool, error) {
 	}
 	logger.Infof("loaded information about %d users from -auth.config=%q", len(m), *authConfigPath)
 
+	prevAc := authConfig.Load()
+	if prevAc != nil {
+		metrics.UnregisterSet(prevAc.ms)
+	}
+	metrics.RegisterSet(ac.ms)
 	authConfig.Store(ac)
 	authConfigData.Store(&data)
 	authUsers.Store(&m)
@@ -489,10 +523,13 @@ func parseAuthConfig(data []byte) (*AuthConfig, error) {
 	if err != nil {
 		return nil, fmt.Errorf("cannot expand environment vars: %w", err)
 	}
-	var ac AuthConfig
-	if err = yaml.UnmarshalStrict(data, &ac); err != nil {
+	ac := &AuthConfig{
+		ms: metrics.NewSet(),
+	}
+	if err = yaml.UnmarshalStrict(data, ac); err != nil {
 		return nil, fmt.Errorf("cannot unmarshal AuthConfig data: %w", err)
 	}
+
 	ui := ac.UnauthorizedUser
 	if ui != nil {
 		if ui.Username != "" {
@@ -510,23 +547,30 @@ func parseAuthConfig(data []byte) (*AuthConfig, error) {
 		if err := ui.initURLs(); err != nil {
 			return nil, err
 		}
-		ui.requests = metrics.GetOrCreateCounter(`vmauth_unauthorized_user_requests_total`)
-		ui.requestsDuration = metrics.GetOrCreateSummary(`vmauth_unauthorized_user_request_duration_seconds`)
+
+		metricLabels, err := ui.getMetricLabels()
+		if err != nil {
+			return nil, fmt.Errorf("cannot parse metric_labels for unauthorized_user: %w", err)
+		}
+		ui.requests = ac.ms.NewCounter(`vmauth_unauthorized_user_requests_total` + metricLabels)
+		ui.backendErrors = ac.ms.NewCounter(`vmauth_unauthorized_user_request_backend_errors_total` + metricLabels)
+		ui.requestsDuration = ac.ms.NewSummary(`vmauth_unauthorized_user_request_duration_seconds` + metricLabels)
 		ui.concurrencyLimitCh = make(chan struct{}, ui.getMaxConcurrentRequests())
-		ui.concurrencyLimitReached = metrics.GetOrCreateCounter(`vmauth_unauthorized_user_concurrent_requests_limit_reached_total`)
-		_ = metrics.GetOrCreateGauge(`vmauth_unauthorized_user_concurrent_requests_capacity`, func() float64 {
+		ui.concurrencyLimitReached = ac.ms.NewCounter(`vmauth_unauthorized_user_concurrent_requests_limit_reached_total` + metricLabels)
+		_ = ac.ms.NewGauge(`vmauth_unauthorized_user_concurrent_requests_capacity`+metricLabels, func() float64 {
 			return float64(cap(ui.concurrencyLimitCh))
 		})
-		_ = metrics.GetOrCreateGauge(`vmauth_unauthorized_user_concurrent_requests_current`, func() float64 {
+		_ = ac.ms.NewGauge(`vmauth_unauthorized_user_concurrent_requests_current`+metricLabels, func() float64 {
 			return float64(len(ui.concurrencyLimitCh))
 		})
+
 		tr, err := getTransport(ui.TLSInsecureSkipVerify, ui.TLSCAFile)
 		if err != nil {
 			return nil, fmt.Errorf("cannot initialize HTTP transport: %w", err)
 		}
 		ui.httpTransport = tr
 	}
-	return &ac, nil
+	return ac, nil
 }
 
 func parseAuthConfigUsers(ac *AuthConfig) (map[string]*UserInfo, error) {
@@ -537,43 +581,47 @@ func parseAuthConfigUsers(ac *AuthConfig) (map[string]*UserInfo, error) {
 	byAuthToken := make(map[string]*UserInfo, len(uis))
 	for i := range uis {
 		ui := &uis[i]
-		if ui.BearerToken == "" && ui.Username == "" {
-			return nil, fmt.Errorf("either bearer_token or username must be set")
+		if ui.Username != "" && ui.Password == "" {
+			// Do not allow setting username without password if there are other auth configs exist.
+			// This should prevent from typical mis-configuration when access by username without password
+			// remains open if other authorization schemes are defined.
+			if ui.BearerToken != "" {
+				return nil, fmt.Errorf("bearer_token=%q and username=%q cannot be set simultaneously", ui.BearerToken, ui.Username)
+			}
 		}
-		if ui.BearerToken != "" && ui.Username != "" {
-			return nil, fmt.Errorf("bearer_token=%q and username=%q cannot be set simultaneously", ui.BearerToken, ui.Username)
+		ats := getAuthTokens(ui.BearerToken, ui.Username, ui.Password)
+		if len(ats) == 0 {
+			return nil, fmt.Errorf("one of bearer_token, username or mtls must be set")
 		}
-		at1, at2 := getAuthTokens(ui.BearerToken, ui.Username, ui.Password)
-		if byAuthToken[at1] != nil {
-			return nil, fmt.Errorf("duplicate auth token found for bearer_token=%q, username=%q: %q", ui.BearerToken, ui.Username, at1)
-		}
-		if byAuthToken[at2] != nil {
-			return nil, fmt.Errorf("duplicate auth token found for bearer_token=%q, username=%q: %q", ui.BearerToken, ui.Username, at2)
+		for _, at := range ats {
+			if uiOld := byAuthToken[at]; uiOld != nil {
+				return nil, fmt.Errorf("duplicate auth token=%q found for username=%q, name=%q; the previous one is set for username=%q, name=%q",
+					at, ui.Username, ui.Name, uiOld.Username, uiOld.Name)
+			}
 		}
 
 		if err := ui.initURLs(); err != nil {
 			return nil, err
 		}
 
-		name := ui.name()
-		if ui.BearerToken != "" {
-			if ui.Password != "" {
-				return nil, fmt.Errorf("password shouldn't be set for bearer_token %q", ui.BearerToken)
-			}
-			ui.requests = metrics.GetOrCreateCounter(fmt.Sprintf(`vmauth_user_requests_total{username=%q}`, name))
-			ui.requestsDuration = metrics.GetOrCreateSummary(fmt.Sprintf(`vmauth_user_request_duration_seconds{username=%q}`, name))
+		if ui.BearerToken != "" && ui.Password != "" {
+			return nil, fmt.Errorf("password shouldn't be set for bearer_token %q", ui.BearerToken)
 		}
-		if ui.Username != "" {
-			ui.requests = metrics.GetOrCreateCounter(fmt.Sprintf(`vmauth_user_requests_total{username=%q}`, name))
-			ui.requestsDuration = metrics.GetOrCreateSummary(fmt.Sprintf(`vmauth_user_request_duration_seconds{username=%q}`, name))
+
+		metricLabels, err := ui.getMetricLabels()
+		if err != nil {
+			return nil, fmt.Errorf("cannot parse metric_labels: %w", err)
 		}
+		ui.requests = ac.ms.GetOrCreateCounter(`vmauth_user_requests_total` + metricLabels)
+		ui.backendErrors = ac.ms.GetOrCreateCounter(`vmauth_user_request_backend_errors_total` + metricLabels)
+		ui.requestsDuration = ac.ms.GetOrCreateSummary(`vmauth_user_request_duration_seconds` + metricLabels)
 		mcr := ui.getMaxConcurrentRequests()
 		ui.concurrencyLimitCh = make(chan struct{}, mcr)
-		ui.concurrencyLimitReached = metrics.GetOrCreateCounter(fmt.Sprintf(`vmauth_user_concurrent_requests_limit_reached_total{username=%q}`, name))
-		_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmauth_user_concurrent_requests_capacity{username=%q}`, name), func() float64 {
+		ui.concurrencyLimitReached = ac.ms.GetOrCreateCounter(`vmauth_user_concurrent_requests_limit_reached_total` + metricLabels)
+		_ = ac.ms.GetOrCreateGauge(`vmauth_user_concurrent_requests_capacity`+metricLabels, func() float64 {
 			return float64(cap(ui.concurrencyLimitCh))
 		})
-		_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmauth_user_concurrent_requests_current{username=%q}`, name), func() float64 {
+		_ = ac.ms.GetOrCreateGauge(`vmauth_user_concurrent_requests_current`+metricLabels, func() float64 {
 			return float64(len(ui.concurrencyLimitCh))
 		})
 
@@ -583,26 +631,55 @@ func parseAuthConfigUsers(ac *AuthConfig) (map[string]*UserInfo, error) {
 		}
 		ui.httpTransport = tr
 
-		byAuthToken[at1] = ui
-		byAuthToken[at2] = ui
+		for _, at := range ats {
+			byAuthToken[at] = ui
+		}
 	}
 	return byAuthToken, nil
 }
 
+var labelNameRegexp = regexp.MustCompile("^[a-zA-Z_:.][a-zA-Z0-9_:.]*$")
+
+func (ui *UserInfo) getMetricLabels() (string, error) {
+	name := ui.name()
+	if len(name) == 0 && len(ui.MetricLabels) == 0 {
+		// fast path
+		return "", nil
+	}
+	labels := make([]string, 0, len(ui.MetricLabels)+1)
+	if len(name) > 0 {
+		labels = append(labels, fmt.Sprintf(`username=%q`, name))
+	}
+	for k, v := range ui.MetricLabels {
+		if !labelNameRegexp.MatchString(k) {
+			return "", fmt.Errorf("incorrect label name=%q, it must match regex=%q for user=%q", k, labelNameRegexp, name)
+		}
+		labels = append(labels, fmt.Sprintf(`%s=%q`, k, v))
+	}
+	sort.Strings(labels)
+	labelsStr := "{" + strings.Join(labels, ",") + "}"
+	return labelsStr, nil
+}
+
 func (ui *UserInfo) initURLs() error {
 	retryStatusCodes := defaultRetryStatusCodes.Values()
 	loadBalancingPolicy := *defaultLoadBalancingPolicy
+	dropSrcPathPrefixParts := 0
 	if ui.URLPrefix != nil {
 		if err := ui.URLPrefix.sanitize(); err != nil {
 			return err
 		}
-		if len(ui.RetryStatusCodes) > 0 {
+		if ui.RetryStatusCodes != nil {
 			retryStatusCodes = ui.RetryStatusCodes
 		}
 		if ui.LoadBalancingPolicy != "" {
 			loadBalancingPolicy = ui.LoadBalancingPolicy
 		}
+		if ui.DropSrcPathPrefixParts != nil {
+			dropSrcPathPrefixParts = *ui.DropSrcPathPrefixParts
+		}
 		ui.URLPrefix.retryStatusCodes = retryStatusCodes
+		ui.URLPrefix.dropSrcPathPrefixParts = dropSrcPathPrefixParts
 		if err := ui.URLPrefix.setLoadBalancingPolicy(loadBalancingPolicy); err != nil {
 			return err
 		}
@@ -613,8 +690,8 @@ func (ui *UserInfo) initURLs() error {
 		}
 	}
 	for _, e := range ui.URLMaps {
-		if len(e.SrcPaths) == 0 {
-			return fmt.Errorf("missing `src_paths` in `url_map`")
+		if len(e.SrcPaths) == 0 && len(e.SrcHosts) == 0 {
+			return fmt.Errorf("missing `src_paths` and `src_hosts` in `url_map`")
 		}
 		if e.URLPrefix == nil {
 			return fmt.Errorf("missing `url_prefix` in `url_map`")
@@ -624,16 +701,21 @@ func (ui *UserInfo) initURLs() error {
 		}
 		rscs := retryStatusCodes
 		lbp := loadBalancingPolicy
-		if len(e.RetryStatusCodes) > 0 {
+		dsp := dropSrcPathPrefixParts
+		if e.RetryStatusCodes != nil {
 			rscs = e.RetryStatusCodes
 		}
 		if e.LoadBalancingPolicy != "" {
 			lbp = e.LoadBalancingPolicy
 		}
+		if e.DropSrcPathPrefixParts != nil {
+			dsp = *e.DropSrcPathPrefixParts
+		}
 		e.URLPrefix.retryStatusCodes = rscs
 		if err := e.URLPrefix.setLoadBalancingPolicy(lbp); err != nil {
 			return err
 		}
+		e.URLPrefix.dropSrcPathPrefixParts = dsp
 	}
 	if len(ui.URLMaps) == 0 && ui.URLPrefix == nil {
 		return fmt.Errorf("missing `url_prefix`")
@@ -649,29 +731,51 @@ func (ui *UserInfo) name() string {
 		return ui.Username
 	}
 	if ui.BearerToken != "" {
-		return "bearer_token"
+		h := xxhash.Sum64([]byte(ui.BearerToken))
+		return fmt.Sprintf("bearer_token:hash:%016X", h)
 	}
 	return ""
 }
 
-func getAuthTokens(bearerToken, username, password string) (string, string) {
+func getAuthTokens(bearerToken, username, password string) []string {
+	var ats []string
 	if bearerToken != "" {
 		// Accept the bearerToken as Basic Auth username with empty password
-		at1 := getAuthToken(bearerToken, "", "")
-		at2 := getAuthToken("", bearerToken, "")
-		return at1, at2
+		at1 := getHTTPAuthBearerToken(bearerToken)
+		at2 := getHTTPAuthBasicToken(bearerToken, "")
+		ats = append(ats, at1, at2)
+	} else if username != "" {
+		at := getHTTPAuthBasicToken(username, password)
+		ats = append(ats, at)
 	}
-	at := getAuthToken("", username, password)
-	return at, at
+	return ats
 }
 
-func getAuthToken(bearerToken, username, password string) string {
-	if bearerToken != "" {
-		return "Bearer " + bearerToken
-	}
+func getHTTPAuthBearerToken(bearerToken string) string {
+	return "http_auth:Bearer " + bearerToken
+}
+
+func getHTTPAuthBasicToken(username, password string) string {
 	token := username + ":" + password
 	token64 := base64.StdEncoding.EncodeToString([]byte(token))
-	return "Basic " + token64
+	return "http_auth:Basic " + token64
+}
+
+func getAuthTokensFromRequest(r *http.Request) []string {
+	var ats []string
+
+	ah := r.Header.Get("Authorization")
+	if ah == "" {
+		return ats
+	}
+	if strings.HasPrefix(ah, "Token ") {
+		// Handle InfluxDB's proprietary token authentication scheme as a bearer token authentication
+		// See https://docs.influxdata.com/influxdb/v2.0/api/
+		ah = strings.Replace(ah, "Token", "Bearer", 1)
+	}
+	at := "http_auth:" + ah
+	ats = append(ats, at)
+	return ats
 }
 
 func (up *URLPrefix) sanitize() error {

app/vmauth/auth_config_test.go

@@ -145,6 +145,12 @@ users:
   url_map:
   - src_paths: ["/foo/bar"]
 `)
+	f(`
+users:
+- username: a
+  url_map:
+  - src_hosts: ["foobar"]
+`)
 
 	// Invalid url_prefix in url_map
 	f(`
@@ -154,6 +160,13 @@ users:
   - src_paths: ["/foo/bar"]
     url_prefix: foo.bar
 `)
+	f(`
+users:
+- username: a
+  url_map:
+  - src_hosts: ["foobar"]
+    url_prefix: foo.bar
+`)
 
 	// empty url_prefix in url_map
 	f(`
@@ -163,8 +176,15 @@ users:
   - src_paths: ['/foo/bar']
     url_prefix: []
 `)
+	f(`
+users:
+- username: a
+  url_map:
+  - src_phosts: ['foobar']
+    url_prefix: []
+`)
 
-	// Missing src_paths in url_map
+	// Missing src_paths and src_hosts in url_map
 	f(`
 users:
 - username: a
@@ -181,6 +201,15 @@ users:
     url_prefix: http://foobar
 `)
 
+	// Invalid regexp in src_hosts
+	f(`
+users:
+- username: a
+  url_map:
+  - src_hosts: ['fo[obar']
+    url_prefix: http://foobar
+`)
+
 	// Invalid headers in url_map (missing ':')
 	f(`
 users:
@@ -200,6 +229,14 @@ users:
     url_prefix: http://foobar
     headers:
       aaa: bbb
+`)
+	// Invalid metric label name
+	f(`
+users:
+- username: foo
+  url_prefix: http://foo.bar
+  metric_labels:
+    not-prometheus-compatible: value
 `)
 }
 
@@ -230,7 +267,7 @@ users:
   max_concurrent_requests: 5
   tls_insecure_skip_verify: true
 `, map[string]*UserInfo{
-		getAuthToken("", "foo", "bar"): {
+		getHTTPAuthBasicToken("foo", "bar"): {
 			Username:              "foo",
 			Password:              "bar",
 			URLPrefix:             mustParseURL("http://aaa:343/bbb"),
@@ -253,7 +290,7 @@ users:
   load_balancing_policy: first_available
   drop_src_path_prefix_parts: 1
 `, map[string]*UserInfo{
-		getAuthToken("", "foo", "bar"): {
+		getHTTPAuthBasicToken("foo", "bar"): {
 			Username: "foo",
 			Password: "bar",
 			URLPrefix: mustParseURLs([]string{
@@ -263,7 +300,7 @@ users:
 			TLSInsecureSkipVerify:  &insecureSkipVerifyFalse,
 			RetryStatusCodes:       []int{500, 501},
 			LoadBalancingPolicy:    "first_available",
-			DropSrcPathPrefixParts: 1,
+			DropSrcPathPrefixParts: intp(1),
 		},
 	})
 
@@ -275,11 +312,11 @@ users:
 - username: bar
   url_prefix: https://bar/x///
 `, map[string]*UserInfo{
-		getAuthToken("", "foo", ""): {
+		getHTTPAuthBasicToken("foo", ""): {
 			Username:  "foo",
 			URLPrefix: mustParseURL("http://foo"),
 		},
-		getAuthToken("", "bar", ""): {
+		getHTTPAuthBasicToken("bar", ""): {
 			Username:  "bar",
 			URLPrefix: mustParseURL("https://bar/x"),
 		},
@@ -293,20 +330,22 @@ users:
   - src_paths: ["/api/v1/query","/api/v1/query_range","/api/v1/label/[^./]+/.+"]
     url_prefix: http://vmselect/select/0/prometheus
   - src_paths: ["/api/v1/write"]
+    src_hosts: ["foo\\.bar", "baz:1234"]
     url_prefix: ["http://vminsert1/insert/0/prometheus","http://vminsert2/insert/0/prometheus"]
     headers:
     - "foo: bar"
     - "xxx: y"
 `, map[string]*UserInfo{
-		getAuthToken("foo", "", ""): {
+		getHTTPAuthBearerToken("foo"): {
 			BearerToken: "foo",
 			URLMaps: []URLMap{
 				{
-					SrcPaths:  getSrcPaths([]string{"/api/v1/query", "/api/v1/query_range", "/api/v1/label/[^./]+/.+"}),
+					SrcPaths:  getRegexs([]string{"/api/v1/query", "/api/v1/query_range", "/api/v1/label/[^./]+/.+"}),
 					URLPrefix: mustParseURL("http://vmselect/select/0/prometheus"),
 				},
 				{
-					SrcPaths: getSrcPaths([]string{"/api/v1/write"}),
+					SrcHosts: getRegexs([]string{"foo\\.bar", "baz:1234"}),
+					SrcPaths: getRegexs([]string{"/api/v1/write"}),
 					URLPrefix: mustParseURLs([]string{
 						"http://vminsert1/insert/0/prometheus",
 						"http://vminsert2/insert/0/prometheus",
@@ -326,15 +365,16 @@ users:
 				},
 			},
 		},
-		getAuthToken("", "foo", ""): {
+		getHTTPAuthBasicToken("foo", ""): {
 			BearerToken: "foo",
 			URLMaps: []URLMap{
 				{
-					SrcPaths:  getSrcPaths([]string{"/api/v1/query", "/api/v1/query_range", "/api/v1/label/[^./]+/.+"}),
+					SrcPaths:  getRegexs([]string{"/api/v1/query", "/api/v1/query_range", "/api/v1/label/[^./]+/.+"}),
 					URLPrefix: mustParseURL("http://vmselect/select/0/prometheus"),
 				},
 				{
-					SrcPaths: getSrcPaths([]string{"/api/v1/write"}),
+					SrcHosts: getRegexs([]string{"foo\\.bar", "baz:1234"}),
+					SrcPaths: getRegexs([]string{"/api/v1/write"}),
 					URLPrefix: mustParseURLs([]string{
 						"http://vminsert1/insert/0/prometheus",
 						"http://vminsert2/insert/0/prometheus",
@@ -355,7 +395,7 @@ users:
 			},
 		},
 	})
-	// Multiple users with the same name
+	// Multiple users with the same name - this should work, since these users have different passwords
 	f(`
 users:
 - username: foo-same
@@ -365,17 +405,18 @@ users:
   password: bar
   url_prefix: https://bar/x///
 `, map[string]*UserInfo{
-		getAuthToken("", "foo-same", "baz"): {
+		getHTTPAuthBasicToken("foo-same", "baz"): {
 			Username:  "foo-same",
 			Password:  "baz",
 			URLPrefix: mustParseURL("http://foo"),
 		},
-		getAuthToken("", "foo-same", "bar"): {
+		getHTTPAuthBasicToken("foo-same", "bar"): {
 			Username:  "foo-same",
 			Password:  "bar",
 			URLPrefix: mustParseURL("https://bar/x"),
 		},
 	})
+
 	// with default url
 	f(`
 users:
@@ -392,15 +433,15 @@ users:
   - http://default1/select/0/prometheus
   - http://default2/select/0/prometheus
 `, map[string]*UserInfo{
-		getAuthToken("foo", "", ""): {
+		getHTTPAuthBearerToken("foo"): {
 			BearerToken: "foo",
 			URLMaps: []URLMap{
 				{
-					SrcPaths:  getSrcPaths([]string{"/api/v1/query", "/api/v1/query_range", "/api/v1/label/[^./]+/.+"}),
+					SrcPaths:  getRegexs([]string{"/api/v1/query", "/api/v1/query_range", "/api/v1/label/[^./]+/.+"}),
 					URLPrefix: mustParseURL("http://vmselect/select/0/prometheus"),
 				},
 				{
-					SrcPaths: getSrcPaths([]string{"/api/v1/write"}),
+					SrcPaths: getRegexs([]string{"/api/v1/write"}),
 					URLPrefix: mustParseURLs([]string{
 						"http://vminsert1/insert/0/prometheus",
 						"http://vminsert2/insert/0/prometheus",
@@ -424,15 +465,15 @@ users:
 				"http://default2/select/0/prometheus",
 			}),
 		},
-		getAuthToken("", "foo", ""): {
+		getHTTPAuthBasicToken("foo", ""): {
 			BearerToken: "foo",
 			URLMaps: []URLMap{
 				{
-					SrcPaths:  getSrcPaths([]string{"/api/v1/query", "/api/v1/query_range", "/api/v1/label/[^./]+/.+"}),
+					SrcPaths:  getRegexs([]string{"/api/v1/query", "/api/v1/query_range", "/api/v1/label/[^./]+/.+"}),
 					URLPrefix: mustParseURL("http://vmselect/select/0/prometheus"),
 				},
 				{
-					SrcPaths: getSrcPaths([]string{"/api/v1/write"}),
+					SrcPaths: getRegexs([]string{"/api/v1/write"}),
 					URLPrefix: mustParseURLs([]string{
 						"http://vminsert1/insert/0/prometheus",
 						"http://vminsert2/insert/0/prometheus",
@@ -457,7 +498,41 @@ users:
 			}),
 		},
 	})
-
+	// With metric_labels
+	f(`
+users:
+- username: foo-same
+  password: baz
+  url_prefix: http://foo
+  metric_labels:
+    dc: eu
+    team: dev
+- username: foo-same
+  password: bar
+  url_prefix: https://bar/x///
+  metric_labels:
+    backend_env: test
+    team: accounting
+`, map[string]*UserInfo{
+		getHTTPAuthBasicToken("foo-same", "baz"): {
+			Username:  "foo-same",
+			Password:  "baz",
+			URLPrefix: mustParseURL("http://foo"),
+			MetricLabels: map[string]string{
+				"dc":   "eu",
+				"team": "dev",
+			},
+		},
+		getHTTPAuthBasicToken("foo-same", "bar"): {
+			Username:  "foo-same",
+			Password:  "bar",
+			URLPrefix: mustParseURL("https://bar/x"),
+			MetricLabels: map[string]string{
+				"backend_env": "test",
+				"team":        "accounting",
+			},
+		},
+	})
 }
 
 func TestParseAuthConfigPassesTLSVerificationConfig(t *testing.T) {
@@ -484,7 +559,7 @@ unauthorized_user:
 		t.Fatalf("unexpected error: %s", err)
 	}
 
-	ui := m[getAuthToken("", "foo", "bar")]
+	ui := m[getHTTPAuthBasicToken("foo", "bar")]
 	if !isSetBool(ui.TLSInsecureSkipVerify, true) || !ui.httpTransport.TLSClientConfig.InsecureSkipVerify {
 		t.Fatalf("unexpected TLSInsecureSkipVerify value for user foo")
 	}
@@ -494,6 +569,86 @@ unauthorized_user:
 	}
 }
 
+func TestUserInfoGetMetricLabels(t *testing.T) {
+	t.Run("empty-labels", func(t *testing.T) {
+		ui := &UserInfo{
+			Username: "user1",
+		}
+		labels, err := ui.getMetricLabels()
+		if err != nil {
+			t.Fatalf("unexpected error: %s", err)
+		}
+		labelsExpected := `{username="user1"}`
+		if labels != labelsExpected {
+			t.Fatalf("unexpected labels; got %s; want %s", labels, labelsExpected)
+		}
+	})
+	t.Run("non-empty-username", func(t *testing.T) {
+		ui := &UserInfo{
+			Username: "user1",
+			MetricLabels: map[string]string{
+				"env":        "prod",
+				"datacenter": "dc1",
+			},
+		}
+		labels, err := ui.getMetricLabels()
+		if err != nil {
+			t.Fatalf("unexpected error: %s", err)
+		}
+		labelsExpected := `{datacenter="dc1",env="prod",username="user1"}`
+		if labels != labelsExpected {
+			t.Fatalf("unexpected labels; got %s; want %s", labels, labelsExpected)
+		}
+	})
+	t.Run("non-empty-name", func(t *testing.T) {
+		ui := &UserInfo{
+			Name:        "user1",
+			BearerToken: "abc",
+			MetricLabels: map[string]string{
+				"env":        "prod",
+				"datacenter": "dc1",
+			},
+		}
+		labels, err := ui.getMetricLabels()
+		if err != nil {
+			t.Fatalf("unexpected error: %s", err)
+		}
+		labelsExpected := `{datacenter="dc1",env="prod",username="user1"}`
+		if labels != labelsExpected {
+			t.Fatalf("unexpected labels; got %s; want %s", labels, labelsExpected)
+		}
+	})
+	t.Run("non-empty-bearer-token", func(t *testing.T) {
+		ui := &UserInfo{
+			BearerToken: "abc",
+			MetricLabels: map[string]string{
+				"env":        "prod",
+				"datacenter": "dc1",
+			},
+		}
+		labels, err := ui.getMetricLabels()
+		if err != nil {
+			t.Fatalf("unexpected error: %s", err)
+		}
+		labelsExpected := `{datacenter="dc1",env="prod",username="bearer_token:hash:44BC2CF5AD770999"}`
+		if labels != labelsExpected {
+			t.Fatalf("unexpected labels; got %s; want %s", labels, labelsExpected)
+		}
+	})
+	t.Run("invalid-label", func(t *testing.T) {
+		ui := &UserInfo{
+			Username: "foo",
+			MetricLabels: map[string]string{
+				",{": "aaaa",
+			},
+		}
+		_, err := ui.getMetricLabels()
+		if err == nil {
+			t.Fatalf("expecting non-nil error")
+		}
+	})
+}
+
 func isSetBool(boolP *bool, expectedValue bool) bool {
 	if boolP == nil {
 		return false
@@ -501,10 +656,10 @@ func isSetBool(boolP *bool, expectedValue bool) bool {
 	return *boolP == expectedValue
 }
 
-func getSrcPaths(paths []string) []*SrcPath {
-	var sps []*SrcPath
+func getRegexs(paths []string) []*Regex {
+	var sps []*Regex
 	for _, path := range paths {
-		sps = append(sps, &SrcPath{
+		sps = append(sps, &Regex{
 			sOriginal: path,
 			re:        regexp.MustCompile("^(?:" + path + ")$"),
 		})
@@ -552,3 +707,7 @@ func mustParseURLs(us []string) *URLPrefix {
 		bus: bus,
 	}
 }
+
+func intp(n int) *int {
+	return &n
+}

app/vmauth/example_config.yml

@@ -10,6 +10,11 @@ users:
 - bearer_token: "XXXX"
   url_prefix: "http://localhost:8428"
 
+  # Adds labels to the exported metrics for given user section
+  # label name must be prometheus compatible and match regex: `^[a-zA-Z_:.][a-zA-Z0-9_:.]*$`
+  metric_labels:
+    backend_dc: eu
+    access_team: dev
   # Requests with the 'Authorization: Bearer YYY' header are proxied to http://localhost:8428 ,
   # The `X-Scope-OrgID: foobar` http header is added to every proxied request.
   # The `X-Server-Hostname:` http header is removed from the proxied response.
@@ -92,7 +97,7 @@ users:
   #  - to http://default1:8888/unsupported_url_handler?request_path=/non/existing/path
   #  - or http://default2:8888/unsupported_url_handler?request_path=/non/existing/path
   #
-  # Regular expressions are allowed in `src_paths` entries.
+  # Regular expressions are allowed in `src_paths` and `src_hosts` entries.
 - username: "foobar"
   url_map:
   - src_paths:

app/vmauth/main.go

@@ -24,7 +24,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/encoding"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envflag"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs/fscore"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
@@ -33,8 +33,8 @@ import (
 )
 
 var (
-	httpListenAddr   = flag.String("httpListenAddr", ":8427", "TCP address to listen for http connections. See also -tls and -httpListenAddr.useProxyProtocol")
-	useProxyProtocol = flag.Bool("httpListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted at -httpListenAddr . "+
+	httpListenAddrs  = flagutil.NewArrayString("httpListenAddr", "TCP address to listen for incoming http requests. See also -tls and -httpListenAddr.useProxyProtocol")
+	useProxyProtocol = flagutil.NewArrayBool("httpListenAddr.useProxyProtocol", "Whether to use proxy protocol for connections accepted at the corresponding -httpListenAddr . "+
 		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
 		"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
 	maxIdleConnsPerBackend = flag.Int("maxIdleConnsPerBackend", 100, "The maximum number of idle connections vmauth can open per each backend host. "+
@@ -45,7 +45,7 @@ var (
 	maxConcurrentPerUserRequests = flag.Int("maxConcurrentPerUserRequests", 300, "The maximum number of concurrent requests vmauth can process per each configured user. "+
 		"Other requests are rejected with '429 Too Many Requests' http status code. See also -maxConcurrentRequests command-line option and max_concurrent_requests option "+
 		"in per-user config")
-	reloadAuthKey        = flag.String("reloadAuthKey", "", "Auth key for /-/reload http endpoint. It must be passed as authKey=...")
+	reloadAuthKey        = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed as authKey=...")
 	logInvalidAuthTokens = flag.Bool("logInvalidAuthTokens", false, "Whether to log requests with invalid auth tokens. "+
 		`Such requests are always counted at vmauth_http_request_errors_total{reason="invalid_auth_token"} metric, which is exposed at /metrics page`)
 	failTimeout               = flag.Duration("failTimeout", 3*time.Second, "Sets a delay period for load balancing to skip a malfunctioning backend")
@@ -64,20 +64,25 @@ func main() {
 	envflag.Parse()
 	buildinfo.Init()
 	logger.Init()
-	pushmetrics.Init()
 
-	logger.Infof("starting vmauth at %q...", *httpListenAddr)
+	listenAddrs := *httpListenAddrs
+	if len(listenAddrs) == 0 {
+		listenAddrs = []string{":8427"}
+	}
+	logger.Infof("starting vmauth at %q...", listenAddrs)
 	startTime := time.Now()
 	initAuthConfig()
-	go httpserver.Serve(*httpListenAddr, *useProxyProtocol, requestHandler)
+	go httpserver.Serve(listenAddrs, useProxyProtocol, requestHandler)
 	logger.Infof("started vmauth in %.3f seconds", time.Since(startTime).Seconds())
 
+	pushmetrics.Init()
 	sig := procutil.WaitForSigterm()
 	logger.Infof("received signal %s", sig)
+	pushmetrics.Stop()
 
 	startTime = time.Now()
-	logger.Infof("gracefully shutting down webservice at %q", *httpListenAddr)
-	if err := httpserver.Stop(*httpListenAddr); err != nil {
+	logger.Infof("gracefully shutting down webservice at %q", listenAddrs)
+	if err := httpserver.Stop(listenAddrs); err != nil {
 		logger.Fatalf("cannot stop the webservice: %s", err)
 	}
 	logger.Infof("successfully shut down the webservice in %.3f seconds", time.Since(startTime).Seconds())
@@ -88,7 +93,7 @@ func main() {
 func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 	switch r.URL.Path {
 	case "/-/reload":
-		if !httpserver.CheckAuthFlag(w, r, *reloadAuthKey, "reloadAuthKey") {
+		if !httpserver.CheckAuthFlag(w, r, reloadAuthKey.Get(), "reloadAuthKey") {
 			return true
 		}
 		configReloadRequests.Inc()
@@ -96,8 +101,9 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		w.WriteHeader(http.StatusOK)
 		return true
 	}
-	authToken := r.Header.Get("Authorization")
-	if authToken == "" {
+
+	ats := getAuthTokensFromRequest(r)
+	if len(ats) == 0 {
 		// Process requests for unauthorized users
 		ui := authConfig.Load().UnauthorizedUser
 		if ui != nil {
@@ -109,18 +115,12 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		http.Error(w, "missing `Authorization` request header", http.StatusUnauthorized)
 		return true
 	}
-	if strings.HasPrefix(authToken, "Token ") {
-		// Handle InfluxDB's proprietary token authentication scheme as a bearer token authentication
-		// See https://docs.influxdata.com/influxdb/v2.0/api/
-		authToken = strings.Replace(authToken, "Token", "Bearer", 1)
-	}
 
-	ac := *authUsers.Load()
-	ui := ac[authToken]
+	ui := getUserInfoByAuthTokens(ats)
 	if ui == nil {
 		invalidAuthTokenRequests.Inc()
 		if *logInvalidAuthTokens {
-			err := fmt.Errorf("cannot find the provided auth token %q in config", authToken)
+			err := fmt.Errorf("cannot authorize request with auth tokens %q", ats)
 			err = &httpserver.ErrorWithStatusCode{
 				Err:        err,
 				StatusCode: http.StatusUnauthorized,
@@ -136,6 +136,17 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 	return true
 }
 
+func getUserInfoByAuthTokens(ats []string) *UserInfo {
+	ac := *authUsers.Load()
+	for _, at := range ats {
+		ui := ac[at]
+		if ui != nil {
+			return ui
+		}
+	}
+	return nil
+}
+
 func processUserRequest(w http.ResponseWriter, r *http.Request, ui *UserInfo) {
 	startTime := time.Now()
 	defer ui.requestsDuration.UpdateDuration(startTime)
@@ -149,12 +160,20 @@ func processUserRequest(w http.ResponseWriter, r *http.Request, ui *UserInfo) {
 		if err := ui.beginConcurrencyLimit(); err != nil {
 			handleConcurrencyLimitError(w, r, err)
 			<-concurrencyLimitCh
+
+			// Requests failed because of concurrency limit must be counted as errors,
+			// since this usually means the backend cannot keep up with the current load.
+			ui.backendErrors.Inc()
 			return
 		}
 	default:
 		concurrentRequestsLimitReached.Inc()
 		err := fmt.Errorf("cannot serve more than -maxConcurrentRequests=%d concurrent requests", cap(concurrencyLimitCh))
 		handleConcurrencyLimitError(w, r, err)
+
+		// Requests failed because of concurrency limit must be counted as errors,
+		// since this usually means the backend cannot keep up with the current load.
+		ui.backendErrors.Inc()
 		return
 	}
 	processRequest(w, r, ui)
@@ -164,7 +183,7 @@ func processUserRequest(w http.ResponseWriter, r *http.Request, ui *UserInfo) {
 
 func processRequest(w http.ResponseWriter, r *http.Request, ui *UserInfo) {
 	u := normalizeURL(r.URL)
-	up, hc, dropSrcPathPrefixParts := ui.getURLPrefixAndHeaders(u)
+	up, hc := ui.getURLPrefixAndHeaders(u)
 	isDefault := false
 	if up == nil {
 		if ui.DefaultURL == nil {
@@ -198,9 +217,9 @@ func processRequest(w http.ResponseWriter, r *http.Request, ui *UserInfo) {
 			query.Set("request_path", u.String())
 			targetURL.RawQuery = query.Encode()
 		} else { // Update path for regular routes.
-			targetURL = mergeURLs(targetURL, u, dropSrcPathPrefixParts)
+			targetURL = mergeURLs(targetURL, u, up.dropSrcPathPrefixParts)
 		}
-		ok := tryProcessingRequest(w, r, targetURL, hc, up.retryStatusCodes, ui.httpTransport)
+		ok := tryProcessingRequest(w, r, targetURL, hc, up.retryStatusCodes, ui)
 		bu.put()
 		if ok {
 			return
@@ -212,15 +231,16 @@ func processRequest(w http.ResponseWriter, r *http.Request, ui *UserInfo) {
 		StatusCode: http.StatusServiceUnavailable,
 	}
 	httpserver.Errorf(w, r, "%s", err)
+	ui.backendErrors.Inc()
 }
 
-func tryProcessingRequest(w http.ResponseWriter, r *http.Request, targetURL *url.URL, hc HeadersConf, retryStatusCodes []int, transport *http.Transport) bool {
+func tryProcessingRequest(w http.ResponseWriter, r *http.Request, targetURL *url.URL, hc HeadersConf, retryStatusCodes []int, ui *UserInfo) bool {
 	// This code has been copied from net/http/httputil/reverseproxy.go
 	req := sanitizeRequestHeaders(r)
 	req.URL = targetURL
 	req.Host = targetURL.Host
 	updateHeadersByConfig(req.Header, hc.RequestHeaders)
-	res, err := transport.RoundTrip(req)
+	res, err := ui.httpTransport.RoundTrip(req)
 	rtb, rtbOK := req.Body.(*readTrackingBody)
 	if err != nil {
 		if errors.Is(err, context.Canceled) || errors.Is(err, context.DeadlineExceeded) {
@@ -228,15 +248,20 @@ func tryProcessingRequest(w http.ResponseWriter, r *http.Request, targetURL *url
 			remoteAddr := httpserver.GetQuotedRemoteAddr(r)
 			requestURI := httpserver.GetRequestURI(r)
 			logger.Warnf("remoteAddr: %s; requestURI: %s; error when proxying response body from %s: %s", remoteAddr, requestURI, targetURL, err)
+			if errors.Is(err, context.DeadlineExceeded) {
+				// Timed out request must be counted as errors, since this usually means that the backend is slow.
+				ui.backendErrors.Inc()
+			}
 			return true
 		}
 		if !rtbOK || !rtb.canRetry() {
 			// Request body cannot be re-sent to another backend. Return the error to the client then.
 			err = &httpserver.ErrorWithStatusCode{
-				Err:        fmt.Errorf("cannot proxy the request to %q: %w", targetURL, err),
+				Err:        fmt.Errorf("cannot proxy the request to %s: %w", targetURL, err),
 				StatusCode: http.StatusServiceUnavailable,
 			}
 			httpserver.Errorf(w, r, "%s", err)
+			ui.backendErrors.Inc()
 			return true
 		}
 		// Retry the request if its body wasn't read yet. This usually means that the backend isn't reachable.
@@ -246,7 +271,20 @@ func tryProcessingRequest(w http.ResponseWriter, r *http.Request, targetURL *url
 		logger.Warnf("remoteAddr: %s; requestURI: %s; retrying the request to %s because of response error: %s", remoteAddr, req.URL, targetURL, err)
 		return false
 	}
-	if (rtbOK && rtb.canRetry()) && hasInt(retryStatusCodes, res.StatusCode) {
+	if hasInt(retryStatusCodes, res.StatusCode) {
+		_ = res.Body.Close()
+		if !rtbOK || !rtb.canRetry() {
+			// If we get an error from the retry_status_codes list, but cannot execute retry,
+			// we consider such a request an error as well.
+			err := &httpserver.ErrorWithStatusCode{
+				Err: fmt.Errorf("got response status code=%d from %s, but cannot retry the request on another backend, because the request has been already consumed",
+					res.StatusCode, targetURL),
+				StatusCode: http.StatusServiceUnavailable,
+			}
+			httpserver.Errorf(w, r, "%s", err)
+			ui.backendErrors.Inc()
+			return true
+		}
 		// Retry requests at other backends if it matches retryStatusCodes.
 		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4893
 		remoteAddr := httpserver.GetQuotedRemoteAddr(r)
@@ -265,6 +303,7 @@ func tryProcessingRequest(w http.ResponseWriter, r *http.Request, targetURL *url
 	copyBuf.B = bytesutil.ResizeNoCopyNoOverallocate(copyBuf.B, 16*1024)
 	_, err = io.CopyBuffer(w, res.Body, copyBuf.B)
 	copyBufPool.Put(copyBuf)
+	_ = res.Body.Close()
 	if err != nil && !netutil.IsTrivialNetworkError(err) {
 		remoteAddr := httpserver.GetQuotedRemoteAddr(r)
 		requestURI := httpserver.GetRequestURI(r)
@@ -392,8 +431,10 @@ func getTransport(insecureSkipVerifyP *bool, caFile string) (*http.Transport, er
 	return tr, nil
 }
 
-var transportMap = make(map[string]*http.Transport)
-var transportMapLock sync.Mutex
+var (
+	transportMap     = make(map[string]*http.Transport)
+	transportMapLock sync.Mutex
+)
 
 func appendTransportKey(dst []byte, insecureSkipVerify bool, caFile string) []byte {
 	dst = encoding.MarshalBool(dst, insecureSkipVerify)
@@ -421,7 +462,7 @@ func newTransport(insecureSkipVerify bool, caFile string) (*http.Transport, erro
 		tlsCfg.ClientSessionCache = tls.NewLRUClientSessionCache(0)
 		tlsCfg.InsecureSkipVerify = insecureSkipVerify
 		if caFile != "" {
-			data, err := fs.ReadFileOrHTTP(caFile)
+			data, err := fscore.ReadFileOrHTTP(caFile)
 			if err != nil {
 				return nil, fmt.Errorf("cannot read tls_ca_file: %w", err)
 			}

app/vmauth/target_url.go

@@ -49,18 +49,28 @@ func dropPrefixParts(path string, parts int) string {
 	return path
 }
 
-func (ui *UserInfo) getURLPrefixAndHeaders(u *url.URL) (*URLPrefix, HeadersConf, int) {
+func (ui *UserInfo) getURLPrefixAndHeaders(u *url.URL) (*URLPrefix, HeadersConf) {
 	for _, e := range ui.URLMaps {
-		for _, sp := range e.SrcPaths {
-			if sp.match(u.Path) {
-				return e.URLPrefix, e.HeadersConf, e.DropSrcPathPrefixParts
-			}
+		if matchAnyRegex(e.SrcHosts, u.Host) && matchAnyRegex(e.SrcPaths, u.Path) {
+			return e.URLPrefix, e.HeadersConf
 		}
 	}
 	if ui.URLPrefix != nil {
-		return ui.URLPrefix, ui.HeadersConf, ui.DropSrcPathPrefixParts
+		return ui.URLPrefix, ui.HeadersConf
 	}
-	return nil, HeadersConf{}, 0
+	return nil, HeadersConf{}
+}
+
+func matchAnyRegex(rs []*Regex, s string) bool {
+	if len(rs) == 0 {
+		return true
+	}
+	for _, r := range rs {
+		if r.match(s) {
+			return true
+		}
+	}
+	return false
 }
 
 func normalizeURL(uOrig *url.URL) *url.URL {

app/vmauth/target_url_test.go

@@ -89,12 +89,12 @@ func TestCreateTargetURLSuccess(t *testing.T) {
 			t.Fatalf("cannot parse %q: %s", requestURI, err)
 		}
 		u = normalizeURL(u)
-		up, hc, dropSrcPathPrefixParts := ui.getURLPrefixAndHeaders(u)
+		up, hc := ui.getURLPrefixAndHeaders(u)
 		if up == nil {
 			t.Fatalf("cannot determie backend: %s", err)
 		}
 		bu := up.getLeastLoadedBackendURL()
-		target := mergeURLs(bu.url, u, dropSrcPathPrefixParts)
+		target := mergeURLs(bu.url, u, up.dropSrcPathPrefixParts)
 		bu.put()
 		if target.String() != expectedTarget {
 			t.Fatalf("unexpected target; got %q; want %q", target, expectedTarget)
@@ -109,8 +109,8 @@ func TestCreateTargetURLSuccess(t *testing.T) {
 		if up.loadBalancingPolicy != expectedLoadBalancingPolicy {
 			t.Fatalf("unexpected loadBalancingPolicy; got %q; want %q", up.loadBalancingPolicy, expectedLoadBalancingPolicy)
 		}
-		if dropSrcPathPrefixParts != expectedDropSrcPathPrefixParts {
-			t.Fatalf("unexpected dropSrcPathPrefixParts; got %d; want %d", dropSrcPathPrefixParts, expectedDropSrcPathPrefixParts)
+		if up.dropSrcPathPrefixParts != expectedDropSrcPathPrefixParts {
+			t.Fatalf("unexpected dropSrcPathPrefixParts; got %d; want %d", up.dropSrcPathPrefixParts, expectedDropSrcPathPrefixParts)
 		}
 	}
 	// Simple routing with `url_prefix`
@@ -127,7 +127,7 @@ func TestCreateTargetURLSuccess(t *testing.T) {
 		},
 		RetryStatusCodes:       []int{503, 501},
 		LoadBalancingPolicy:    "first_available",
-		DropSrcPathPrefixParts: 2,
+		DropSrcPathPrefixParts: intp(2),
 	}, "/a/b/c", "http://foo.bar/c", `[{"bb" "aaa"}]`, `[]`, []int{503, 501}, "first_available", 2)
 	f(&UserInfo{
 		URLPrefix: mustParseURL("http://foo.bar/federate"),
@@ -149,7 +149,8 @@ func TestCreateTargetURLSuccess(t *testing.T) {
 	ui := &UserInfo{
 		URLMaps: []URLMap{
 			{
-				SrcPaths:  getSrcPaths([]string{"/vmsingle/api/v1/query"}),
+				SrcHosts:  getRegexs([]string{"host42"}),
+				SrcPaths:  getRegexs([]string{"/vmsingle/api/v1/query"}),
 				URLPrefix: mustParseURL("http://vmselect/0/prometheus"),
 				HeadersConf: HeadersConf{
 					RequestHeaders: []Header{
@@ -171,11 +172,13 @@ func TestCreateTargetURLSuccess(t *testing.T) {
 				},
 				RetryStatusCodes:       []int{503, 500, 501},
 				LoadBalancingPolicy:    "first_available",
-				DropSrcPathPrefixParts: 1,
+				DropSrcPathPrefixParts: intp(1),
 			},
 			{
-				SrcPaths:  getSrcPaths([]string{"/api/v1/write"}),
-				URLPrefix: mustParseURL("http://vminsert/0/prometheus"),
+				SrcPaths:               getRegexs([]string{"/api/v1/write"}),
+				URLPrefix:              mustParseURL("http://vminsert/0/prometheus"),
+				RetryStatusCodes:       []int{},
+				DropSrcPathPrefixParts: intp(0),
 			},
 		},
 		URLPrefix: mustParseURL("http://default-server"),
@@ -190,23 +193,30 @@ func TestCreateTargetURLSuccess(t *testing.T) {
 			}},
 		},
 		RetryStatusCodes:       []int{502},
-		DropSrcPathPrefixParts: 2,
+		DropSrcPathPrefixParts: intp(2),
 	}
-	f(ui, "/vmsingle/api/v1/query?query=up", "http://vmselect/0/prometheus/api/v1/query?query=up", `[{"xx" "aa"} {"yy" "asdf"}]`, `[{"qwe" "rty"}]`, []int{503, 500, 501}, "first_available", 1)
-	f(ui, "/api/v1/write", "http://vminsert/0/prometheus/api/v1/write", "[]", "[]", []int{502}, "least_loaded", 0)
-	f(ui, "/foo/bar/api/v1/query_range", "http://default-server/api/v1/query_range", `[{"bb" "aaa"}]`, `[{"x" "y"}]`, []int{502}, "least_loaded", 2)
+	f(ui, "http://host42/vmsingle/api/v1/query?query=up", "http://vmselect/0/prometheus/api/v1/query?query=up",
+		`[{"xx" "aa"} {"yy" "asdf"}]`, `[{"qwe" "rty"}]`, []int{503, 500, 501}, "first_available", 1)
+	f(ui, "http://host123/vmsingle/api/v1/query?query=up", "http://default-server/v1/query?query=up",
+		`[{"bb" "aaa"}]`, `[{"x" "y"}]`, []int{502}, "least_loaded", 2)
+	f(ui, "https://foo-host/api/v1/write", "http://vminsert/0/prometheus/api/v1/write", "[]", "[]", []int{}, "least_loaded", 0)
+	f(ui, "https://foo-host/foo/bar/api/v1/query_range", "http://default-server/api/v1/query_range", `[{"bb" "aaa"}]`, `[{"x" "y"}]`, []int{502}, "least_loaded", 2)
 
 	// Complex routing regexp paths in `url_map`
 	ui = &UserInfo{
 		URLMaps: []URLMap{
 			{
-				SrcPaths:  getSrcPaths([]string{"/api/v1/query(_range)?", "/api/v1/label/[^/]+/values"}),
+				SrcPaths:  getRegexs([]string{"/api/v1/query(_range)?", "/api/v1/label/[^/]+/values"}),
 				URLPrefix: mustParseURL("http://vmselect/0/prometheus"),
 			},
 			{
-				SrcPaths:  getSrcPaths([]string{"/api/v1/write"}),
+				SrcPaths:  getRegexs([]string{"/api/v1/write"}),
 				URLPrefix: mustParseURL("http://vminsert/0/prometheus"),
 			},
+			{
+				SrcHosts:  getRegexs([]string{"vmui\\..+"}),
+				URLPrefix: mustParseURL("http://vmui.host:1234/vmui/"),
+			},
 		},
 		URLPrefix: mustParseURL("http://default-server"),
 	}
@@ -215,6 +225,8 @@ func TestCreateTargetURLSuccess(t *testing.T) {
 	f(ui, "/api/v1/label/foo/values", "http://vmselect/0/prometheus/api/v1/label/foo/values", "[]", "[]", nil, "least_loaded", 0)
 	f(ui, "/api/v1/write", "http://vminsert/0/prometheus/api/v1/write", "[]", "[]", nil, "least_loaded", 0)
 	f(ui, "/api/v1/foo/bar", "http://default-server/api/v1/foo/bar", "[]", "[]", nil, "least_loaded", 0)
+	f(ui, "https://vmui.foobar.com/a/b?c=d", "http://vmui.host:1234/vmui/a/b?c=d", "[]", "[]", nil, "least_loaded", 0)
+
 	f(&UserInfo{
 		URLPrefix: mustParseURL("http://foo.bar?extra_label=team=dev"),
 	}, "/api/v1/query", "http://foo.bar/api/v1/query?extra_label=team=dev", "[]", "[]", nil, "least_loaded", 0)
@@ -231,7 +243,7 @@ func TestCreateTargetURLFailure(t *testing.T) {
 			t.Fatalf("cannot parse %q: %s", requestURI, err)
 		}
 		u = normalizeURL(u)
-		up, hc, dropSrcPathPrefixParts := ui.getURLPrefixAndHeaders(u)
+		up, hc := ui.getURLPrefixAndHeaders(u)
 		if up != nil {
 			t.Fatalf("unexpected non-empty up=%#v", up)
 		}
@@ -241,15 +253,12 @@ func TestCreateTargetURLFailure(t *testing.T) {
 		if hc.ResponseHeaders != nil {
 			t.Fatalf("unexpected non-empty response headers=%q", hc.ResponseHeaders)
 		}
-		if dropSrcPathPrefixParts != 0 {
-			t.Fatalf("unexpected non-zero dropSrcPathPrefixParts=%d", dropSrcPathPrefixParts)
-		}
 	}
 	f(&UserInfo{}, "/foo/bar")
 	f(&UserInfo{
 		URLMaps: []URLMap{
 			{
-				SrcPaths:  getSrcPaths([]string{"/api/v1/query"}),
+				SrcPaths:  getRegexs([]string{"/api/v1/query"}),
 				URLPrefix: mustParseURL("http://foobar/baz"),
 			},
 		},

app/vmbackup/main.go

@@ -20,6 +20,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/pushmetrics"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/snapshot"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/snapshot/snapshotutil"
 )
 
 var (
@@ -47,7 +48,6 @@ func main() {
 	envflag.Parse()
 	buildinfo.Init()
 	logger.Init()
-	pushmetrics.Init()
 
 	// Storing snapshot delete function to be able to call it in case
 	// of error since logger.Fatal will exit the program without
@@ -94,17 +94,20 @@ func main() {
 		}
 	}
 
-	go httpserver.Serve(*httpListenAddr, false, nil)
+	listenAddrs := []string{*httpListenAddr}
+	go httpserver.Serve(listenAddrs, nil, nil)
 
+	pushmetrics.Init()
 	err := makeBackup()
 	deleteSnapshot()
 	if err != nil {
 		logger.Fatalf("cannot create backup: %s", err)
 	}
+	pushmetrics.Stop()
 
 	startTime := time.Now()
-	logger.Infof("gracefully shutting down http server for metrics at %q", *httpListenAddr)
-	if err := httpserver.Stop(*httpListenAddr); err != nil {
+	logger.Infof("gracefully shutting down http server for metrics at %q", listenAddrs)
+	if err := httpserver.Stop(listenAddrs); err != nil {
 		logger.Fatalf("cannot stop http server for metrics: %s", err)
 	}
 	logger.Infof("successfully shut down http server for metrics in %.3f seconds", time.Since(startTime).Seconds())
@@ -167,7 +170,7 @@ See the docs at https://docs.victoriametrics.com/vmbackup.html .
 }
 
 func newSrcFS() (*fslocal.FS, error) {
-	if err := snapshot.Validate(*snapshotName); err != nil {
+	if err := snapshotutil.Validate(*snapshotName); err != nil {
 		return nil, fmt.Errorf("invalid -snapshotName=%q: %w", *snapshotName, err)
 	}
 	snapshotPath := filepath.Join(*storageDataPath, "snapshots", *snapshotName)

app/vmctl/backoff/backoff_test.go

@@ -15,7 +15,6 @@ func TestRetry_Do(t *testing.T) {
 		backoffFactor      float64
 		backoffMinDuration time.Duration
 		retryableFunc      retryableFunc
-		ctx                context.Context
 		cancelTimeout      time.Duration
 		want               uint64
 		wantErr            bool
@@ -25,7 +24,6 @@ func TestRetry_Do(t *testing.T) {
 			retryableFunc: func() error {
 				return ErrBadRequest
 			},
-			ctx:     context.Background(),
 			want:    0,
 			wantErr: true,
 		},
@@ -35,7 +33,6 @@ func TestRetry_Do(t *testing.T) {
 				time.Sleep(time.Millisecond * 100)
 				return nil
 			},
-			ctx:     context.Background(),
 			want:    0,
 			wantErr: true,
 		},
@@ -58,7 +55,6 @@ func TestRetry_Do(t *testing.T) {
 				}
 				return nil
 			},
-			ctx:     context.Background(),
 			want:    1,
 			wantErr: false,
 		},
@@ -75,7 +71,6 @@ func TestRetry_Do(t *testing.T) {
 				}
 				return nil
 			},
-			ctx:     context.Background(),
 			want:    5,
 			wantErr: true,
 		},
@@ -85,14 +80,8 @@ func TestRetry_Do(t *testing.T) {
 			backoffFactor:      1.7,
 			backoffMinDuration: time.Millisecond * 10,
 			retryableFunc: func() error {
-				t := time.NewTicker(time.Millisecond * 5)
-				defer t.Stop()
-				for range t.C {
-					return fmt.Errorf("got some error")
-				}
-				return nil
+				return fmt.Errorf("got some error")
 			},
-			ctx:           context.Background(),
 			cancelTimeout: time.Millisecond * 40,
 			want:          3,
 			wantErr:       true,
@@ -101,12 +90,13 @@ func TestRetry_Do(t *testing.T) {
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			r := &Backoff{retries: tt.backoffRetries, factor: tt.backoffFactor, minDuration: tt.backoffMinDuration}
+			ctx := context.Background()
 			if tt.cancelTimeout != 0 {
-				newCtx, cancelFn := context.WithTimeout(tt.ctx, tt.cancelTimeout)
-				tt.ctx = newCtx
+				newCtx, cancelFn := context.WithTimeout(context.Background(), tt.cancelTimeout)
+				ctx = newCtx
 				defer cancelFn()
 			}
-			got, err := r.Retry(tt.ctx, tt.retryableFunc)
+			got, err := r.Retry(ctx, tt.retryableFunc)
 			if (err != nil) != tt.wantErr {
 				t.Errorf("Retry() error = %v, wantErr %v", err, tt.wantErr)
 				return

app/vmctl/flags.go

@@ -320,26 +320,29 @@ var (
 )
 
 const (
-	vmNativeFilterMatch     = "vm-native-filter-match"
-	vmNativeFilterTimeStart = "vm-native-filter-time-start"
-	vmNativeFilterTimeEnd   = "vm-native-filter-time-end"
-	vmNativeStepInterval    = "vm-native-step-interval"
+	vmNativeFilterMatch       = "vm-native-filter-match"
+	vmNativeFilterTimeStart   = "vm-native-filter-time-start"
+	vmNativeFilterTimeEnd     = "vm-native-filter-time-end"
+	vmNativeFilterTimeReverse = "vm-native-filter-time-reverse"
+	vmNativeStepInterval      = "vm-native-step-interval"
 
-	vmNativeDisableBinaryProtocol = "vm-native-disable-binary-protocol"
-	vmNativeDisableHTTPKeepAlive  = "vm-native-disable-http-keep-alive"
-	vmNativeDisableRetries        = "vm-native-disable-retries"
+	vmNativeDisableBinaryProtocol     = "vm-native-disable-binary-protocol"
+	vmNativeDisableHTTPKeepAlive      = "vm-native-disable-http-keep-alive"
+	vmNativeDisablePerMetricMigration = "vm-native-disable-per-metric-migration"
 
-	vmNativeSrcAddr        = "vm-native-src-addr"
-	vmNativeSrcUser        = "vm-native-src-user"
-	vmNativeSrcPassword    = "vm-native-src-password"
-	vmNativeSrcHeaders     = "vm-native-src-headers"
-	vmNativeSrcBearerToken = "vm-native-src-bearer-token"
+	vmNativeSrcAddr               = "vm-native-src-addr"
+	vmNativeSrcUser               = "vm-native-src-user"
+	vmNativeSrcPassword           = "vm-native-src-password"
+	vmNativeSrcHeaders            = "vm-native-src-headers"
+	vmNativeSrcBearerToken        = "vm-native-src-bearer-token"
+	vmNativeSrcInsecureSkipVerify = "vm-native-src-insecure-skip-verify"
 
-	vmNativeDstAddr        = "vm-native-dst-addr"
-	vmNativeDstUser        = "vm-native-dst-user"
-	vmNativeDstPassword    = "vm-native-dst-password"
-	vmNativeDstHeaders     = "vm-native-dst-headers"
-	vmNativeDstBearerToken = "vm-native-dst-bearer-token"
+	vmNativeDstAddr               = "vm-native-dst-addr"
+	vmNativeDstUser               = "vm-native-dst-user"
+	vmNativeDstPassword           = "vm-native-dst-password"
+	vmNativeDstHeaders            = "vm-native-dst-headers"
+	vmNativeDstBearerToken        = "vm-native-dst-bearer-token"
+	vmNativeDstInsecureSkipVerify = "vm-native-dst-insecure-skip-verify"
 )
 
 var (
@@ -362,10 +365,15 @@ var (
 		},
 		&cli.StringFlag{
 			Name: vmNativeStepInterval,
-			Usage: fmt.Sprintf("Split export data into chunks. Requires setting --%s. Valid values are '%s','%s','%s','%s','%s'.", vmNativeFilterTimeStart,
-				stepper.StepMonth, stepper.StepWeek, stepper.StepDay, stepper.StepHour, stepper.StepMinute),
+			Usage: fmt.Sprintf("The time interval to split the migration into steps. For example, to migrate 1y of data with '--%s=month' vmctl will execute it in 12 separate requests from the beginning of the time range to its end. To reverse the order use '--%s'. Requires setting '--%s'. Valid values are '%s','%s','%s','%s','%s'.",
+				vmNativeStepInterval, vmNativeFilterTimeReverse, vmNativeFilterTimeStart, stepper.StepMonth, stepper.StepWeek, stepper.StepDay, stepper.StepHour, stepper.StepMinute),
 			Value: stepper.StepMonth,
 		},
+		&cli.BoolFlag{
+			Name:  vmNativeFilterTimeReverse,
+			Usage: fmt.Sprintf("Whether to reverse the order of time intervals split by '--%s' cmd-line flag. When set, the migration will start from the newest to the oldest data.", vmNativeStepInterval),
+			Value: false,
+		},
 		&cli.BoolFlag{
 			Name:  vmNativeDisableHTTPKeepAlive,
 			Usage: "Disable HTTP persistent connections for requests made to VictoriaMetrics components during export",
@@ -448,8 +456,8 @@ var (
 			Value: 2,
 		},
 		&cli.BoolFlag{
-			Name:  vmNativeDisableRetries,
-			Usage: "Defines whether to disable retries with backoff policy for migration process",
+			Name:  vmNativeDisablePerMetricMigration,
+			Usage: "Defines whether to disable per-metric migration and migrate all data via one connection. In this mode, vmctl makes less export/import requests, but can't provide a progress bar or retry failed requests.",
 			Value: false,
 		},
 		&cli.BoolFlag{
@@ -460,6 +468,16 @@ var (
 				"Non-binary export/import API is less efficient, but supports deduplication if it is configured on vm-native-src-addr side.",
 			Value: false,
 		},
+		&cli.BoolFlag{
+			Name:  vmNativeSrcInsecureSkipVerify,
+			Usage: "Whether to skip TLS certificate verification when connecting to the source address",
+			Value: false,
+		},
+		&cli.BoolFlag{
+			Name:  vmNativeDstInsecureSkipVerify,
+			Usage: "Whether to skip TLS certificate verification when connecting to the destination address",
+			Value: false,
+		},
 	}
 )
 
@@ -469,6 +487,7 @@ const (
 	remoteReadConcurrency        = "remote-read-concurrency"
 	remoteReadFilterTimeStart    = "remote-read-filter-time-start"
 	remoteReadFilterTimeEnd      = "remote-read-filter-time-end"
+	remoteReadFilterTimeReverse  = "remote-read-filter-time-reverse"
 	remoteReadFilterLabel        = "remote-read-filter-label"
 	remoteReadFilterLabelValue   = "remote-read-filter-label-value"
 	remoteReadStepInterval       = "remote-read-step-interval"
@@ -520,9 +539,14 @@ var (
 			Value: false,
 		},
 		&cli.StringFlag{
-			Name:     remoteReadStepInterval,
-			Usage:    fmt.Sprintf("Split export data into chunks. Requires setting --%s. Valid values are %q,%q,%q,%q.", remoteReadFilterTimeStart, stepper.StepMonth, stepper.StepDay, stepper.StepHour, stepper.StepMinute),
-			Required: true,
+			Name: remoteReadStepInterval,
+			Usage: fmt.Sprintf("The time interval to split the migration into steps. For example, to migrate 1y of data with '--%s=month' vmctl will execute it in 12 separate requests from the beginning of the time range to its end. To reverse the order use '--%s'. Requires setting '--%s'. Valid values are '%s','%s','%s','%s','%s'.",
+				remoteReadStepInterval, remoteReadFilterTimeReverse, remoteReadFilterTimeStart, stepper.StepMonth, stepper.StepWeek, stepper.StepDay, stepper.StepHour, stepper.StepMinute), Required: true,
+		},
+		&cli.BoolFlag{
+			Name:  remoteReadFilterTimeReverse,
+			Usage: fmt.Sprintf("Whether to reverse the order of time intervals split by '--%s' cmd-line flag. When set, the migration will start from the newest to the oldest data.", remoteReadStepInterval),
+			Value: false,
 		},
 		&cli.StringFlag{
 			Name:     remoteReadSrcAddr,

app/vmctl/main.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"context"
+	"crypto/tls"
 	"fmt"
 	"log"
 	"net/http"
@@ -12,11 +13,12 @@ import (
 	"syscall"
 	"time"
 
+	"github.com/urfave/cli/v2"
+
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/backoff"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/native"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/remoteread"
-	"github.com/urfave/cli/v2"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/influx"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/opentsdb"
@@ -150,9 +152,10 @@ func main() {
 						src: rr,
 						dst: importer,
 						filter: remoteReadFilter{
-							timeStart: c.Timestamp(remoteReadFilterTimeStart),
-							timeEnd:   c.Timestamp(remoteReadFilterTimeEnd),
-							chunk:     c.String(remoteReadStepInterval),
+							timeStart:   c.Timestamp(remoteReadFilterTimeStart),
+							timeEnd:     c.Timestamp(remoteReadFilterTimeEnd),
+							chunk:       c.String(remoteReadStepInterval),
+							timeReverse: c.Bool(remoteReadFilterTimeReverse),
 						},
 						cc:        c.Int(remoteReadConcurrency),
 						isSilent:  c.Bool(globalSilent),
@@ -210,6 +213,7 @@ func main() {
 
 					var srcExtraLabels []string
 					srcAddr := strings.Trim(c.String(vmNativeSrcAddr), "/")
+					srcInsecureSkipVerify := c.Bool(vmNativeSrcInsecureSkipVerify)
 					srcAuthConfig, err := auth.Generate(
 						auth.WithBasicAuth(c.String(vmNativeSrcUser), c.String(vmNativeSrcPassword)),
 						auth.WithBearer(c.String(vmNativeSrcBearerToken)),
@@ -217,10 +221,16 @@ func main() {
 					if err != nil {
 						return fmt.Errorf("error initilize auth config for source: %s", srcAddr)
 					}
-					srcHTTPClient := &http.Client{Transport: &http.Transport{DisableKeepAlives: disableKeepAlive}}
+					srcHTTPClient := &http.Client{Transport: &http.Transport{
+						DisableKeepAlives: disableKeepAlive,
+						TLSClientConfig: &tls.Config{
+							InsecureSkipVerify: srcInsecureSkipVerify,
+						},
+					}}
 
 					dstAddr := strings.Trim(c.String(vmNativeDstAddr), "/")
 					dstExtraLabels := c.StringSlice(vmExtraLabel)
+					dstInsecureSkipVerify := c.Bool(vmNativeDstInsecureSkipVerify)
 					dstAuthConfig, err := auth.Generate(
 						auth.WithBasicAuth(c.String(vmNativeDstUser), c.String(vmNativeDstPassword)),
 						auth.WithBearer(c.String(vmNativeDstBearerToken)),
@@ -228,16 +238,22 @@ func main() {
 					if err != nil {
 						return fmt.Errorf("error initilize auth config for destination: %s", dstAddr)
 					}
-					dstHTTPClient := &http.Client{Transport: &http.Transport{DisableKeepAlives: disableKeepAlive}}
+					dstHTTPClient := &http.Client{Transport: &http.Transport{
+						DisableKeepAlives: disableKeepAlive,
+						TLSClientConfig: &tls.Config{
+							InsecureSkipVerify: dstInsecureSkipVerify,
+						},
+					}}
 
 					p := vmNativeProcessor{
 						rateLimit:    c.Int64(vmRateLimit),
 						interCluster: c.Bool(vmInterCluster),
 						filter: native.Filter{
-							Match:     c.String(vmNativeFilterMatch),
-							TimeStart: c.String(vmNativeFilterTimeStart),
-							TimeEnd:   c.String(vmNativeFilterTimeEnd),
-							Chunk:     c.String(vmNativeStepInterval),
+							Match:       c.String(vmNativeFilterMatch),
+							TimeStart:   c.String(vmNativeFilterTimeStart),
+							TimeEnd:     c.String(vmNativeFilterTimeEnd),
+							Chunk:       c.String(vmNativeStepInterval),
+							TimeReverse: c.Bool(vmNativeFilterTimeReverse),
 						},
 						src: &native.Client{
 							AuthCfg:     srcAuthConfig,
@@ -251,11 +267,11 @@ func main() {
 							ExtraLabels: dstExtraLabels,
 							HTTPClient:  dstHTTPClient,
 						},
-						backoff:        backoff.New(),
-						cc:             c.Int(vmConcurrency),
-						disableRetries: c.Bool(vmNativeDisableRetries),
-						isSilent:       c.Bool(globalSilent),
-						isNative:       !c.Bool(vmNativeDisableBinaryProtocol),
+						backoff:                  backoff.New(),
+						cc:                       c.Int(vmConcurrency),
+						disablePerMetricRequests: c.Bool(vmNativeDisablePerMetricMigration),
+						isSilent:                 c.Bool(globalSilent),
+						isNative:                 !c.Bool(vmNativeDisableBinaryProtocol),
 					}
 					return p.run(ctx)
 				},

app/vmctl/native/filter.go

@@ -4,10 +4,11 @@ import "fmt"
 
 // Filter represents request filter
 type Filter struct {
-	Match     string
-	TimeStart string
-	TimeEnd   string
-	Chunk     string
+	Match       string
+	TimeStart   string
+	TimeEnd     string
+	Chunk       string
+	TimeReverse bool
 }
 
 func (f Filter) String() string {

app/vmctl/remoteread.go

@@ -7,11 +7,12 @@ import (
 	"sync"
 	"time"
 
+	"github.com/cheggaaa/pb/v3"
+
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/barpool"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/remoteread"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/stepper"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/vm"
-	"github.com/cheggaaa/pb/v3"
 )
 
 type remoteReadProcessor struct {
@@ -26,9 +27,10 @@ type remoteReadProcessor struct {
 }
 
 type remoteReadFilter struct {
-	timeStart *time.Time
-	timeEnd   *time.Time
-	chunk     string
+	timeStart   *time.Time
+	timeEnd     *time.Time
+	chunk       string
+	timeReverse bool
 }
 
 func (rrp *remoteReadProcessor) run(ctx context.Context) error {
@@ -41,7 +43,7 @@ func (rrp *remoteReadProcessor) run(ctx context.Context) error {
 		rrp.cc = 1
 	}
 
-	ranges, err := stepper.SplitDateRange(*rrp.filter.timeStart, *rrp.filter.timeEnd, rrp.filter.chunk)
+	ranges, err := stepper.SplitDateRange(*rrp.filter.timeStart, *rrp.filter.timeEnd, rrp.filter.chunk, rrp.filter.timeReverse)
 	if err != nil {
 		return fmt.Errorf("failed to create date ranges for the given time filters: %v", err)
 	}

app/vmctl/stepper/split.go

@@ -2,6 +2,7 @@ package stepper
 
 import (
 	"fmt"
+	"sort"
 	"time"
 )
 
@@ -20,7 +21,7 @@ const (
 
 // SplitDateRange splits start-end range in a subset of ranges respecting the given step
 // Ranges with granularity of StepMonth are aligned to 1st of each month in order to improve export efficiency at block transfer level
-func SplitDateRange(start, end time.Time, step string) ([][]time.Time, error) {
+func SplitDateRange(start, end time.Time, step string, timeReverse bool) ([][]time.Time, error) {
 
 	if start.After(end) {
 		return nil, fmt.Errorf("start time %q should come before end time %q", start.Format(time.RFC3339), end.Format(time.RFC3339))
@@ -71,6 +72,11 @@ func SplitDateRange(start, end time.Time, step string) ([][]time.Time, error) {
 		ranges = append(ranges, []time.Time{s, e})
 		currentStep = e
 	}
+	if timeReverse {
+		sort.SliceStable(ranges, func(i, j int) bool {
+			return ranges[i][0].After(ranges[j][0])
+		})
+	}
 
 	return ranges, nil
 }

app/vmctl/stepper/split_test.go

@@ -252,7 +252,280 @@ func Test_splitDateRange(t *testing.T) {
 			start := mustParseDatetime(tt.args.start)
 			end := mustParseDatetime(tt.args.end)
 
-			got, err := SplitDateRange(start, end, tt.args.granularity)
+			got, err := SplitDateRange(start, end, tt.args.granularity, false)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("splitDateRange() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+
+			var testExpectedResults [][]time.Time
+			if tt.want != nil {
+				testExpectedResults = make([][]time.Time, 0)
+				for _, dr := range tt.want {
+					testExpectedResults = append(testExpectedResults, []time.Time{
+						mustParseDatetime(dr[0]),
+						mustParseDatetime(dr[1]),
+					})
+				}
+			}
+
+			if !reflect.DeepEqual(got, testExpectedResults) {
+				t.Errorf("splitDateRange() got = %v, want %v", got, testExpectedResults)
+			}
+		})
+	}
+}
+
+func Test_splitDateRange_reverse(t *testing.T) {
+	type args struct {
+		start       string
+		end         string
+		granularity string
+		timeReverse bool
+	}
+	tests := []struct {
+		name    string
+		args    args
+		want    []testTimeRange
+		wantErr bool
+	}{
+		{
+			name: "validates start is before end",
+			args: args{
+				start:       "2022-02-01T00:00:00Z",
+				end:         "2022-01-01T00:00:00Z",
+				granularity: StepMonth,
+				timeReverse: true,
+			},
+			want:    nil,
+			wantErr: true,
+		},
+		{
+			name: "validates granularity value",
+			args: args{
+				start:       "2022-01-01T00:00:00Z",
+				end:         "2022-02-01T00:00:00Z",
+				granularity: "non-existent-format",
+				timeReverse: true,
+			},
+			want:    nil,
+			wantErr: true,
+		},
+		{
+			name: "month chunking",
+			args: args{
+				start:       "2022-01-03T11:11:11Z",
+				end:         "2022-03-03T12:12:12Z",
+				granularity: StepMonth,
+				timeReverse: true,
+			},
+			want: []testTimeRange{
+				{
+					"2022-03-01T00:00:00Z",
+					"2022-03-03T12:12:12Z",
+				},
+				{
+					"2022-02-01T00:00:00Z",
+					"2022-02-28T23:59:59.999999999Z",
+				},
+				{
+					"2022-01-03T11:11:11Z",
+					"2022-01-31T23:59:59.999999999Z",
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "daily chunking",
+			args: args{
+				start:       "2022-01-03T11:11:11Z",
+				end:         "2022-01-05T12:12:12Z",
+				granularity: StepDay,
+				timeReverse: true,
+			},
+			want: []testTimeRange{
+				{
+					"2022-01-05T11:11:11Z",
+					"2022-01-05T12:12:12Z",
+				},
+				{
+					"2022-01-04T11:11:11Z",
+					"2022-01-05T11:11:11Z",
+				},
+				{
+					"2022-01-03T11:11:11Z",
+					"2022-01-04T11:11:11Z",
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "hourly chunking",
+			args: args{
+				start:       "2022-01-03T11:11:11Z",
+				end:         "2022-01-03T14:14:14Z",
+				granularity: StepHour,
+				timeReverse: true,
+			},
+			want: []testTimeRange{
+				{
+					"2022-01-03T14:11:11Z",
+					"2022-01-03T14:14:14Z",
+				},
+				{
+					"2022-01-03T13:11:11Z",
+					"2022-01-03T14:11:11Z",
+				},
+				{
+					"2022-01-03T12:11:11Z",
+					"2022-01-03T13:11:11Z",
+				},
+				{
+					"2022-01-03T11:11:11Z",
+					"2022-01-03T12:11:11Z",
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "month chunking with one day time range",
+			args: args{
+				start:       "2022-01-03T11:11:11Z",
+				end:         "2022-01-04T12:12:12Z",
+				granularity: StepMonth,
+				timeReverse: true,
+			},
+			want: []testTimeRange{
+				{
+					"2022-01-03T11:11:11Z",
+					"2022-01-04T12:12:12Z",
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "month chunking with same day time range",
+			args: args{
+				start:       "2022-01-03T11:11:11Z",
+				end:         "2022-01-03T12:12:12Z",
+				granularity: StepMonth,
+				timeReverse: true,
+			},
+			want: []testTimeRange{
+				{
+					"2022-01-03T11:11:11Z",
+					"2022-01-03T12:12:12Z",
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "month chunking with one month and two days range",
+			args: args{
+				start:       "2022-01-03T11:11:11Z",
+				end:         "2022-02-03T00:00:00Z",
+				granularity: StepMonth,
+				timeReverse: true,
+			},
+			want: []testTimeRange{
+				{
+					"2022-02-01T00:00:00Z",
+					"2022-02-03T00:00:00Z",
+				},
+				{
+					"2022-01-03T11:11:11Z",
+					"2022-01-31T23:59:59.999999999Z",
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name: "week chunking with not full week",
+			args: args{
+				start:       "2023-07-30T00:00:00Z",
+				end:         "2023-08-05T23:59:59.999999999Z",
+				granularity: StepWeek,
+				timeReverse: true,
+			},
+			want: []testTimeRange{
+				{
+					"2023-07-30T00:00:00Z",
+					"2023-08-05T23:59:59.999999999Z",
+				},
+			},
+		},
+		{
+			name: "week chunking with start of the week and end of the week",
+			args: args{
+				start:       "2023-07-30T00:00:00Z",
+				end:         "2023-08-06T00:00:00Z",
+				granularity: StepWeek,
+				timeReverse: true,
+			},
+			want: []testTimeRange{
+				{
+					"2023-07-30T00:00:00Z",
+					"2023-08-06T00:00:00Z",
+				},
+			},
+		},
+		{
+			name: "week chunking with next one day week",
+			args: args{
+				start:       "2023-07-30T00:00:00Z",
+				end:         "2023-08-07T01:12:00Z",
+				granularity: StepWeek,
+				timeReverse: true,
+			},
+			want: []testTimeRange{
+				{
+					"2023-08-06T00:00:00Z",
+					"2023-08-07T01:12:00Z",
+				},
+				{
+					"2023-07-30T00:00:00Z",
+					"2023-08-06T00:00:00Z",
+				},
+			},
+		},
+		{
+			name: "week chunking with month and not full week representation",
+			args: args{
+				start:       "2023-07-30T00:00:00Z",
+				end:         "2023-09-01T01:12:00Z",
+				granularity: StepWeek,
+				timeReverse: true,
+			},
+			want: []testTimeRange{
+				{
+					"2023-08-27T00:00:00Z",
+					"2023-09-01T01:12:00Z",
+				},
+				{
+					"2023-08-20T00:00:00Z",
+					"2023-08-27T00:00:00Z",
+				},
+				{
+					"2023-08-13T00:00:00Z",
+					"2023-08-20T00:00:00Z",
+				},
+				{
+					"2023-08-06T00:00:00Z",
+					"2023-08-13T00:00:00Z",
+				},
+				{
+					"2023-07-30T00:00:00Z",
+					"2023-08-06T00:00:00Z",
+				},
+			},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			start := mustParseDatetime(tt.args.start)
+			end := mustParseDatetime(tt.args.end)
+
+			got, err := SplitDateRange(start, end, tt.args.granularity, tt.args.timeReverse)
 			if (err != nil) != tt.wantErr {
 				t.Errorf("splitDateRange() error = %v, wantErr %v", err, tt.wantErr)
 				return

app/vmctl/vm_native.go

@@ -9,6 +9,8 @@ import (
 	"sync"
 	"time"
 
+	"github.com/cheggaaa/pb/v3"
+
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/backoff"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/barpool"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/limiter"
@@ -18,7 +20,6 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/vm"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/searchutils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
-	"github.com/cheggaaa/pb/v3"
 )
 
 type vmNativeProcessor struct {
@@ -28,13 +29,14 @@ type vmNativeProcessor struct {
 	src     *native.Client
 	backoff *backoff.Backoff
 
-	s              *stats
-	rateLimit      int64
-	interCluster   bool
-	cc             int
-	disableRetries bool
-	isSilent       bool
-	isNative       bool
+	s            *stats
+	rateLimit    int64
+	interCluster bool
+	cc           int
+	isSilent     bool
+	isNative     bool
+
+	disablePerMetricRequests bool
 }
 
 const (
@@ -67,12 +69,11 @@ func (p *vmNativeProcessor) run(ctx context.Context) error {
 
 	ranges := [][]time.Time{{start, end}}
 	if p.filter.Chunk != "" {
-		ranges, err = stepper.SplitDateRange(start, end, p.filter.Chunk)
+		ranges, err = stepper.SplitDateRange(start, end, p.filter.Chunk, p.filter.TimeReverse)
 		if err != nil {
 			return fmt.Errorf("failed to create date ranges for the given time filters: %w", err)
 		}
 	}
-
 	tenants := []string{""}
 	if p.interCluster {
 		log.Printf("Discovering tenants...")
@@ -119,19 +120,16 @@ func (p *vmNativeProcessor) runSingle(ctx context.Context, f native.Filter, srcU
 		return fmt.Errorf("failed to init export pipe: %w", err)
 	}
 
-	if p.disableRetries && bar != nil {
+	if p.disablePerMetricRequests && bar != nil {
 		fmt.Printf("Continue import process with filter %s:\n", f.String())
 		reader = bar.NewProxyReader(reader)
 	}
 
 	pr, pw := io.Pipe()
-	done := make(chan struct{})
+	importCh := make(chan error)
 	go func() {
-		defer func() { close(done) }()
-		if err := p.dst.ImportPipe(ctx, dstURL, pr); err != nil {
-			logger.Errorf("error initialize import pipe: %s", err)
-			return
-		}
+		importCh <- p.dst.ImportPipe(ctx, dstURL, pr)
+		close(importCh)
 	}()
 
 	w := io.Writer(pw)
@@ -153,9 +151,8 @@ func (p *vmNativeProcessor) runSingle(ctx context.Context, f native.Filter, srcU
 	if err := pw.Close(); err != nil {
 		return err
 	}
-	<-done
 
-	return nil
+	return <-importCh
 }
 
 func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string, ranges [][]time.Time, silent bool) error {
@@ -193,7 +190,7 @@ func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string,
 	var foundSeriesMsg string
 
 	metrics := []string{p.filter.Match}
-	if !p.disableRetries {
+	if !p.disablePerMetricRequests {
 		log.Printf("Exploring metrics...")
 		metrics, err = p.src.Explore(ctx, p.filter, tenantID)
 		if err != nil {
@@ -231,7 +228,7 @@ func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string,
 	var bar *pb.ProgressBar
 	if !silent {
 		bar = barpool.NewSingleProgress(fmt.Sprintf(nativeWithBackoffTpl, barPrefix), len(metrics)*len(ranges))
-		if p.disableRetries {
+		if p.disablePerMetricRequests {
 			bar = barpool.NewSingleProgress(nativeSingleProcessTpl, 0)
 		}
 		bar.Start()
@@ -247,7 +244,7 @@ func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string,
 		go func() {
 			defer wg.Done()
 			for f := range filterCh {
-				if !p.disableRetries {
+				if !p.disablePerMetricRequests {
 					if err := p.do(ctx, f, srcURL, dstURL, nil); err != nil {
 						errCh <- err
 						return

app/vmctl/vm_native_test.go

@@ -266,10 +266,16 @@ func fillStorage(series []vm.TimeSeries) error {
 	for _, series := range series {
 		var labels []prompb.Label
 		for _, lp := range series.LabelPairs {
-			labels = append(labels, prompb.Label{Name: []byte(lp.Name), Value: []byte(lp.Value)})
+			labels = append(labels, prompb.Label{
+				Name:  lp.Name,
+				Value: lp.Value,
+			})
 		}
 		if series.Name != "" {
-			labels = append(labels, prompb.Label{Name: []byte("__name__"), Value: []byte(series.Name)})
+			labels = append(labels, prompb.Label{
+				Name:  "__name__",
+				Value: series.Name,
+			})
 		}
 		mr := storage.MetricRow{}
 		mr.MetricNameRaw = storage.MarshalMetricNameRaw(mr.MetricNameRaw[:0], labels)

app/vminsert/common/insert_ctx.go

@@ -27,12 +27,11 @@ type InsertCtx struct {
 
 // Reset resets ctx for future fill with rowsLen rows.
 func (ctx *InsertCtx) Reset(rowsLen int) {
-	for i := range ctx.Labels {
-		label := &ctx.Labels[i]
-		label.Name = nil
-		label.Value = nil
+	labels := ctx.Labels
+	for i := range labels {
+		labels[i] = prompb.Label{}
 	}
-	ctx.Labels = ctx.Labels[:0]
+	ctx.Labels = labels[:0]
 
 	mrs := ctx.mrs
 	for i := range mrs {
@@ -112,8 +111,8 @@ func (ctx *InsertCtx) AddLabelBytes(name, value []byte) {
 	ctx.Labels = append(ctx.Labels, prompb.Label{
 		// Do not copy name and value contents for performance reasons.
 		// This reduces GC overhead on the number of objects and allocations.
-		Name:  name,
-		Value: value,
+		Name:  bytesutil.ToUnsafeString(name),
+		Value: bytesutil.ToUnsafeString(value),
 	})
 }
 
@@ -130,8 +129,8 @@ func (ctx *InsertCtx) AddLabel(name, value string) {
 	ctx.Labels = append(ctx.Labels, prompb.Label{
 		// Do not copy name and value contents for performance reasons.
 		// This reduces GC overhead on the number of objects and allocations.
-		Name:  bytesutil.ToUnsafeBytes(name),
-		Value: bytesutil.ToUnsafeBytes(value),
+		Name:  name,
+		Value: value,
 	})
 }
 

app/vminsert/common/streamaggr.go

@@ -38,7 +38,7 @@ var (
 
 	saCfgReloads   = metrics.NewCounter(`vminsert_streamagg_config_reloads_total`)
 	saCfgReloadErr = metrics.NewCounter(`vminsert_streamagg_config_reloads_errors_total`)
-	saCfgSuccess   = metrics.NewCounter(`vminsert_streamagg_config_last_reload_successful`)
+	saCfgSuccess   = metrics.NewGauge(`vminsert_streamagg_config_last_reload_successful`, nil)
 	saCfgTimestamp = metrics.NewCounter(`vminsert_streamagg_config_last_reload_success_timestamp_seconds`)
 
 	sasGlobal atomic.Pointer[streamaggr.Aggregators]

app/vminsert/datadogsketches/request_handler.go

@@ -0,0 +1,85 @@
+package datadogsketches
+
+import (
+	"net/http"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/relabel"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogsketches"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogsketches/stream"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogutils"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+var (
+	rowsInserted  = metrics.NewCounter(`vm_rows_inserted_total{type="datadogsketches"}`)
+	rowsPerInsert = metrics.NewHistogram(`vm_rows_per_insert{type="datadogsketches"}`)
+)
+
+// InsertHandlerForHTTP processes remote write for DataDog POST /api/beta/sketches request.
+func InsertHandlerForHTTP(req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
+	ce := req.Header.Get("Content-Encoding")
+	return stream.Parse(req.Body, ce, func(sketches []*datadogsketches.Sketch) error {
+		return insertRows(sketches, extraLabels)
+	})
+}
+
+func insertRows(sketches []*datadogsketches.Sketch, extraLabels []prompbmarshal.Label) error {
+	ctx := common.GetInsertCtx()
+	defer common.PutInsertCtx(ctx)
+
+	rowsLen := 0
+	for _, sketch := range sketches {
+		rowsLen += sketch.RowsCount()
+	}
+	ctx.Reset(rowsLen)
+	rowsTotal := 0
+	hasRelabeling := relabel.HasRelabeling()
+	for _, sketch := range sketches {
+		ms := sketch.ToSummary()
+		for _, m := range ms {
+			ctx.Labels = ctx.Labels[:0]
+			ctx.AddLabel("", m.Name)
+			for _, label := range m.Labels {
+				ctx.AddLabel(label.Name, label.Value)
+			}
+			for _, tag := range sketch.Tags {
+				name, value := datadogutils.SplitTag(tag)
+				if name == "host" {
+					name = "exported_host"
+				}
+				ctx.AddLabel(name, value)
+			}
+			for j := range extraLabels {
+				label := &extraLabels[j]
+				ctx.AddLabel(label.Name, label.Value)
+			}
+			if hasRelabeling {
+				ctx.ApplyRelabeling()
+			}
+			if len(ctx.Labels) == 0 {
+				// Skip metric without labels.
+				continue
+			}
+			ctx.SortLabelsIfNeeded()
+			var metricNameRaw []byte
+			var err error
+			for _, p := range m.Points {
+				metricNameRaw, err = ctx.WriteDataPointExt(metricNameRaw, ctx.Labels, p.Timestamp, p.Value)
+				if err != nil {
+					return err
+				}
+			}
+			rowsTotal += len(m.Points)
+		}
+	}
+	rowsInserted.Add(rowsTotal)
+	rowsPerInsert.Update(float64(rowsTotal))
+	return ctx.FlushBufs()
+}

app/vminsert/datadogv1/request_handler.go

@@ -1,4 +1,4 @@
-package datadog
+package datadogv1
 
 import (
 	"net/http"
@@ -7,31 +7,30 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/relabel"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
 	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
-	parser "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadog"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadog/stream"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogutils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv1"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv1/stream"
 	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
-	rowsInserted  = metrics.NewCounter(`vm_rows_inserted_total{type="datadog"}`)
-	rowsPerInsert = metrics.NewHistogram(`vm_rows_per_insert{type="datadog"}`)
+	rowsInserted  = metrics.NewCounter(`vm_rows_inserted_total{type="datadogv1"}`)
+	rowsPerInsert = metrics.NewHistogram(`vm_rows_per_insert{type="datadogv1"}`)
 )
 
 // InsertHandlerForHTTP processes remote write for DataDog POST /api/v1/series request.
-//
-// See https://docs.datadoghq.com/api/latest/metrics/#submit-metrics
 func InsertHandlerForHTTP(req *http.Request) error {
 	extraLabels, err := parserCommon.GetExtraLabels(req)
 	if err != nil {
 		return err
 	}
 	ce := req.Header.Get("Content-Encoding")
-	return stream.Parse(req.Body, ce, func(series []parser.Series) error {
+	return stream.Parse(req.Body, ce, func(series []datadogv1.Series) error {
 		return insertRows(series, extraLabels)
 	})
 }
 
-func insertRows(series []parser.Series, extraLabels []prompbmarshal.Label) error {
+func insertRows(series []datadogv1.Series, extraLabels []prompbmarshal.Label) error {
 	ctx := common.GetInsertCtx()
 	defer common.PutInsertCtx(ctx)
 
@@ -54,7 +53,7 @@ func insertRows(series []parser.Series, extraLabels []prompbmarshal.Label) error
 			ctx.AddLabel("device", ss.Device)
 		}
 		for _, tag := range ss.Tags {
-			name, value := parser.SplitTag(tag)
+			name, value := datadogutils.SplitTag(tag)
 			if name == "host" {
 				name = "exported_host"
 			}

app/vminsert/datadogv2/request_handler.go

@@ -0,0 +1,91 @@
+package datadogv2
+
+import (
+	"net/http"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/relabel"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	parserCommon "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogutils"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv2"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/datadogv2/stream"
+	"github.com/VictoriaMetrics/metrics"
+)
+
+var (
+	rowsInserted  = metrics.NewCounter(`vm_rows_inserted_total{type="datadogv2"}`)
+	rowsPerInsert = metrics.NewHistogram(`vm_rows_per_insert{type="datadogv2"}`)
+)
+
+// InsertHandlerForHTTP processes remote write for DataDog POST /api/v2/series request.
+//
+// See https://docs.datadoghq.com/api/latest/metrics/#submit-metrics
+func InsertHandlerForHTTP(req *http.Request) error {
+	extraLabels, err := parserCommon.GetExtraLabels(req)
+	if err != nil {
+		return err
+	}
+	ct := req.Header.Get("Content-Type")
+	ce := req.Header.Get("Content-Encoding")
+	return stream.Parse(req.Body, ce, ct, func(series []datadogv2.Series) error {
+		return insertRows(series, extraLabels)
+	})
+}
+
+func insertRows(series []datadogv2.Series, extraLabels []prompbmarshal.Label) error {
+	ctx := common.GetInsertCtx()
+	defer common.PutInsertCtx(ctx)
+
+	rowsLen := 0
+	for i := range series {
+		rowsLen += len(series[i].Points)
+	}
+	ctx.Reset(rowsLen)
+	rowsTotal := 0
+	hasRelabeling := relabel.HasRelabeling()
+	for i := range series {
+		ss := &series[i]
+		rowsTotal += len(ss.Points)
+		ctx.Labels = ctx.Labels[:0]
+		ctx.AddLabel("", ss.Metric)
+		for _, rs := range ss.Resources {
+			ctx.AddLabel(rs.Type, rs.Name)
+		}
+		for _, tag := range ss.Tags {
+			name, value := datadogutils.SplitTag(tag)
+			if name == "host" {
+				name = "exported_host"
+			}
+			ctx.AddLabel(name, value)
+		}
+		if ss.SourceTypeName != "" {
+			ctx.AddLabel("source_type_name", ss.SourceTypeName)
+		}
+		for j := range extraLabels {
+			label := &extraLabels[j]
+			ctx.AddLabel(label.Name, label.Value)
+		}
+		if hasRelabeling {
+			ctx.ApplyRelabeling()
+		}
+		if len(ctx.Labels) == 0 {
+			// Skip metric without labels.
+			continue
+		}
+		ctx.SortLabelsIfNeeded()
+		var metricNameRaw []byte
+		var err error
+		for _, pt := range ss.Points {
+			timestamp := pt.Timestamp * 1000
+			value := pt.Value
+			metricNameRaw, err = ctx.WriteDataPointExt(metricNameRaw, ctx.Labels, timestamp, value)
+			if err != nil {
+				return err
+			}
+		}
+	}
+	rowsInserted.Add(rowsTotal)
+	rowsPerInsert.Update(float64(rowsTotal))
+	return ctx.FlushBufs()
+}

app/vminsert/influx/request_handler.go

@@ -160,11 +160,9 @@ func (ctx *pushCtx) reset() {
 
 	originLabels := ctx.originLabels
 	for i := range originLabels {
-		label := &originLabels[i]
-		label.Name = nil
-		label.Value = nil
+		originLabels[i] = prompb.Label{}
 	}
-	ctx.originLabels = ctx.originLabels[:0]
+	ctx.originLabels = originLabels[:0]
 }
 
 func getPushCtx() *pushCtx {

app/vminsert/main.go

@@ -13,7 +13,9 @@ import (
 
 	vminsertCommon "github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/common"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/csvimport"
-	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/datadog"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/datadogsketches"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/datadogv1"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/datadogv2"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/graphite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/influx"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/native"
@@ -28,6 +30,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/vmimport"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/influxutils"
 	graphiteserver "github.com/VictoriaMetrics/VictoriaMetrics/lib/ingestserver/graphite"
@@ -61,7 +64,8 @@ var (
 		"See also -opentsdbHTTPListenAddr.useProxyProtocol")
 	opentsdbHTTPUseProxyProtocol = flag.Bool("opentsdbHTTPListenAddr.useProxyProtocol", false, "Whether to use proxy protocol for connections accepted "+
 		"at -opentsdbHTTPListenAddr . See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt")
-	configAuthKey          = flag.String("configAuthKey", "", "Authorization key for accessing /config page. It must be passed via authKey query arg")
+	configAuthKey          = flagutil.NewPassword("configAuthKey", "Authorization key for accessing /config page. It must be passed via authKey query arg")
+	reloadAuthKey          = flagutil.NewPassword("reloadAuthKey", "Auth key for /-/reload http endpoint. It must be passed as authKey=...")
 	maxLabelsPerTimeseries = flag.Int("maxLabelsPerTimeseries", 30, "The maximum number of labels accepted per time series. Superfluous labels are dropped. In this case the vm_metrics_with_dropped_labels_total metric at /metrics page is incremented")
 	maxLabelValueLen       = flag.Int("maxLabelValueLen", 16*1024, "The maximum length of label values in the accepted time series. Longer label values are truncated. In this case the vm_too_long_label_values_total metric at /metrics page is incremented")
 )
@@ -246,9 +250,20 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		fmt.Fprintf(w, `{"status":"ok"}`)
 		return true
 	case "/datadog/api/v1/series":
-		datadogWriteRequests.Inc()
-		if err := datadog.InsertHandlerForHTTP(r); err != nil {
-			datadogWriteErrors.Inc()
+		datadogv1WriteRequests.Inc()
+		if err := datadogv1.InsertHandlerForHTTP(r); err != nil {
+			datadogv1WriteErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.Header().Set("Content-Type", "application/json")
+		w.WriteHeader(202)
+		fmt.Fprintf(w, `{"status":"ok"}`)
+		return true
+	case "/datadog/api/v2/series":
+		datadogv2WriteRequests.Inc()
+		if err := datadogv2.InsertHandlerForHTTP(r); err != nil {
+			datadogv2WriteErrors.Inc()
 			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
@@ -257,6 +272,15 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		w.WriteHeader(202)
 		fmt.Fprintf(w, `{"status":"ok"}`)
 		return true
+	case "/datadog/api/beta/sketches":
+		datadogsketchesWriteRequests.Inc()
+		if err := datadogsketches.InsertHandlerForHTTP(r); err != nil {
+			datadogsketchesWriteErrors.Inc()
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		w.WriteHeader(202)
+		return true
 	case "/datadog/api/v1/validate":
 		datadogValidateRequests.Inc()
 		// See https://docs.datadoghq.com/api/latest/authentication/#validate-api-key
@@ -303,7 +327,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		}
 		return true
 	case "/prometheus/config", "/config":
-		if !httpserver.CheckAuthFlag(w, r, *configAuthKey, "configAuthKey") {
+		if !httpserver.CheckAuthFlag(w, r, configAuthKey.Get(), "configAuthKey") {
 			return true
 		}
 		promscrapeConfigRequests.Inc()
@@ -312,7 +336,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		return true
 	case "/prometheus/api/v1/status/config", "/api/v1/status/config":
 		// See https://prometheus.io/docs/prometheus/latest/querying/api/#config
-		if !httpserver.CheckAuthFlag(w, r, *configAuthKey, "configAuthKey") {
+		if !httpserver.CheckAuthFlag(w, r, configAuthKey.Get(), "configAuthKey") {
 			return true
 		}
 		promscrapeStatusConfigRequests.Inc()
@@ -322,9 +346,12 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		fmt.Fprintf(w, `{"status":"success","data":{"yaml":%q}}`, bb.B)
 		return true
 	case "/prometheus/-/reload", "/-/reload":
+		if !httpserver.CheckAuthFlag(w, r, reloadAuthKey.Get(), "reloadAuthKey") {
+			return true
+		}
 		promscrapeConfigReloadRequests.Inc()
 		procutil.SelfSIGHUP()
-		w.WriteHeader(http.StatusNoContent)
+		w.WriteHeader(http.StatusOK)
 		return true
 	case "/ready":
 		if rdy := atomic.LoadInt32(&promscrape.PendingScrapeConfigs); rdy > 0 {
@@ -371,8 +398,14 @@ var (
 
 	influxQueryRequests = metrics.NewCounter(`vm_http_requests_total{path="/influx/query", protocol="influx"}`)
 
-	datadogWriteRequests = metrics.NewCounter(`vm_http_requests_total{path="/datadog/api/v1/series", protocol="datadog"}`)
-	datadogWriteErrors   = metrics.NewCounter(`vm_http_request_errors_total{path="/datadog/api/v1/series", protocol="datadog"}`)
+	datadogv1WriteRequests = metrics.NewCounter(`vm_http_requests_total{path="/datadog/api/v1/series", protocol="datadog"}`)
+	datadogv1WriteErrors   = metrics.NewCounter(`vm_http_request_errors_total{path="/datadog/api/v1/series", protocol="datadog"}`)
+
+	datadogv2WriteRequests = metrics.NewCounter(`vm_http_requests_total{path="/datadog/api/v2/series", protocol="datadog"}`)
+	datadogv2WriteErrors   = metrics.NewCounter(`vm_http_request_errors_total{path="/datadog/api/v2/series", protocol="datadog"}`)
+
+	datadogsketchesWriteRequests = metrics.NewCounter(`vm_http_requests_total{path="/datadog/api/beta/sketches", protocol="datadog"}`)
+	datadogsketchesWriteErrors   = metrics.NewCounter(`vm_http_request_errors_total{path="/datadog/api/beta/sketches", protocol="datadog"}`)
 
 	datadogValidateRequests = metrics.NewCounter(`vm_http_requests_total{path="/datadog/api/v1/validate", protocol="datadog"}`)
 	datadogCheckRunRequests = metrics.NewCounter(`vm_http_requests_total{path="/datadog/api/v1/check_run", protocol="datadog"}`)

app/vminsert/promremotewrite/request_handler.go

@@ -46,7 +46,7 @@ func insertRows(timeseries []prompb.TimeSeries, extraLabels []prompbmarshal.Labe
 		ctx.Labels = ctx.Labels[:0]
 		srcLabels := ts.Labels
 		for _, srcLabel := range srcLabels {
-			ctx.AddLabelBytes(srcLabel.Name, srcLabel.Value)
+			ctx.AddLabel(srcLabel.Name, srcLabel.Value)
 		}
 		for j := range extraLabels {
 			label := &extraLabels[j]

app/vminsert/relabel/relabel.go

@@ -5,7 +5,6 @@ import (
 	"fmt"
 	"sync/atomic"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
@@ -65,7 +64,7 @@ func Init() {
 var (
 	configReloads      = metrics.NewCounter(`vm_relabel_config_reloads_total`)
 	configReloadErrors = metrics.NewCounter(`vm_relabel_config_reloads_errors_total`)
-	configSuccess      = metrics.NewCounter(`vm_relabel_config_last_reload_successful`)
+	configSuccess      = metrics.NewGauge(`vm_relabel_config_last_reload_successful`, nil)
 	configTimestamp    = metrics.NewCounter(`vm_relabel_config_last_reload_success_timestamp_seconds`)
 )
 
@@ -118,11 +117,11 @@ func (ctx *Ctx) ApplyRelabeling(labels []prompb.Label) []prompb.Label {
 	// Convert labels to prompbmarshal.Label format suitable for relabeling.
 	tmpLabels := ctx.tmpLabels[:0]
 	for _, label := range labels {
-		name := bytesutil.ToUnsafeString(label.Name)
-		if len(name) == 0 {
+		name := label.Name
+		if name == "" {
 			name = "__name__"
 		}
-		value := bytesutil.ToUnsafeString(label.Value)
+		value := label.Value
 		tmpLabels = append(tmpLabels, prompbmarshal.Label{
 			Name:  name,
 			Value: value,
@@ -155,11 +154,11 @@ func (ctx *Ctx) ApplyRelabeling(labels []prompb.Label) []prompb.Label {
 	// Return back labels to the desired format.
 	dst := labels[:0]
 	for _, label := range tmpLabels {
-		name := bytesutil.ToUnsafeBytes(label.Name)
+		name := label.Name
 		if label.Name == "__name__" {
-			name = nil
+			name = ""
 		}
-		value := bytesutil.ToUnsafeBytes(label.Value)
+		value := label.Value
 		dst = append(dst, prompb.Label{
 			Name:  name,
 			Value: value,

app/vmrestore/main.go

@@ -36,9 +36,9 @@ func main() {
 	envflag.Parse()
 	buildinfo.Init()
 	logger.Init()
-	pushmetrics.Init()
 
-	go httpserver.Serve(*httpListenAddr, false, nil)
+	listenAddrs := []string{*httpListenAddr}
+	go httpserver.Serve(listenAddrs, nil, nil)
 
 	srcFS, err := newSrcFS()
 	if err != nil {
@@ -54,15 +54,17 @@ func main() {
 		Dst:                     dstFS,
 		SkipBackupCompleteCheck: *skipBackupCompleteCheck,
 	}
+	pushmetrics.Init()
 	if err := a.Run(); err != nil {
 		logger.Fatalf("cannot restore from backup: %s", err)
 	}
+	pushmetrics.Stop()
 	srcFS.MustStop()
 	dstFS.MustStop()
 
 	startTime := time.Now()
-	logger.Infof("gracefully shutting down http server for metrics at %q", *httpListenAddr)
-	if err := httpserver.Stop(*httpListenAddr); err != nil {
+	logger.Infof("gracefully shutting down http server for metrics at %q", listenAddrs)
+	if err := httpserver.Stop(listenAddrs); err != nil {
 		logger.Fatalf("cannot stop http server for metrics: %s", err)
 	}
 	logger.Infof("successfully shut down http server for metrics in %.3f seconds", time.Since(startTime).Seconds())

app/vmselect/graphite/tags_api.go

@@ -123,13 +123,13 @@ func registerMetrics(startTime time.Time, w http.ResponseWriter, r *http.Request
 
 		// Convert parsed metric and tags to labels.
 		labels = append(labels[:0], prompb.Label{
-			Name:  []byte("__name__"),
-			Value: []byte(row.Metric),
+			Name:  "__name__",
+			Value: row.Metric,
 		})
 		for _, tag := range row.Tags {
 			labels = append(labels, prompb.Label{
-				Name:  []byte(tag.Key),
-				Value: []byte(tag.Value),
+				Name:  tag.Key,
+				Value: tag.Value,
 			})
 		}
 

app/vmselect/graphite/transform.go

@@ -3599,6 +3599,17 @@ func groupSeriesByNodes(ss []*series, nodes []graphiteql.Expr) map[string][]*ser
 	return m
 }
 
+func getAbsoluteNodeIndex(index, size int) int {
+	// Handle the negative index case as Python does
+	if index < 0 {
+		index = size + index
+	}
+	if index < 0 || index >= size {
+		return -1
+	}
+	return index
+}
+
 func getNameFromNodes(name string, tags map[string]string, nodes []graphiteql.Expr) string {
 	if len(nodes) == 0 {
 		return ""
@@ -3609,7 +3620,7 @@ func getNameFromNodes(name string, tags map[string]string, nodes []graphiteql.Ex
 	for _, node := range nodes {
 		switch t := node.(type) {
 		case *graphiteql.NumberExpr:
-			if n := int(t.N); n >= 0 && n < len(parts) {
+			if n := getAbsoluteNodeIndex(int(t.N), len(parts)); n >= 0 {
 				dstParts = append(dstParts, parts[n])
 			}
 		case *graphiteql.StringExpr:

app/vmselect/graphite/transform_test.go

@@ -79,3 +79,31 @@ func TestGraphiteToGolangRegexpReplace(t *testing.T) {
 	f(`a\d+`, `a\d+`)
 	f(`\1f\\oo\2`, `$1f\\oo$2`)
 }
+
+func TestGetAbsoluteNodeIndex(t *testing.T) {
+	f := func(index, size, expectedIndex int) {
+		t.Helper()
+		absoluteIndex := getAbsoluteNodeIndex(index, size)
+		if absoluteIndex != expectedIndex {
+			t.Fatalf("unexpected result for getAbsoluteNodeIndex(%d, %d); got %d; want %d", index, size, expectedIndex, absoluteIndex)
+		}
+	}
+	f(1, 1, -1)
+	f(0, 1, 0)
+	f(-1, 3, 2)
+	f(-3, 1, -1)
+	f(-1, 1, 0)
+	f(-2, 1, -1)
+	f(3, 2, -1)
+	f(2, 2, -1)
+	f(1, 2, 1)
+	f(0, 2, 0)
+	f(-1, 2, 1)
+	f(-2, 2, 0)
+	f(-3, 2, -1)
+	f(-5, 2, -1)
+	f(-1, 100, 99)
+	f(-99, 100, 1)
+	f(-100, 100, 0)
+	f(-101, 100, -1)
+}

app/vmselect/main.go

@@ -18,6 +18,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/searchutils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmstorage"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputils"
@@ -29,13 +30,13 @@ import (
 )
 
 var (
-	deleteAuthKey         = flag.String("deleteAuthKey", "", "authKey for metrics' deletion via /api/v1/admin/tsdb/delete_series and /tags/delSeries")
+	deleteAuthKey         = flagutil.NewPassword("deleteAuthKey", "authKey for metrics' deletion via /api/v1/admin/tsdb/delete_series and /tags/delSeries")
 	maxConcurrentRequests = flag.Int("search.maxConcurrentRequests", getDefaultMaxConcurrentRequests(), "The maximum number of concurrent search requests. "+
 		"It shouldn't be high, since a single request can saturate all the CPU cores, while many concurrently executed requests may require high amounts of memory. "+
 		"See also -search.maxQueueDuration and -search.maxMemoryPerQuery")
 	maxQueueDuration = flag.Duration("search.maxQueueDuration", 10*time.Second, "The maximum time the request waits for execution when -search.maxConcurrentRequests "+
 		"limit is reached; see also -search.maxQueryDuration")
-	resetCacheAuthKey    = flag.String("search.resetCacheAuthKey", "", "Optional authKey for resetting rollup cache via /internal/resetRollupResultCache call")
+	resetCacheAuthKey    = flagutil.NewPassword("search.resetCacheAuthKey", "Optional authKey for resetting rollup cache via /internal/resetRollupResultCache call")
 	logSlowQueryDuration = flag.Duration("search.logSlowQueryDuration", 5*time.Second, "Log queries with execution time exceeding this value. Zero disables slow query logging. "+
 		"See also -search.logQueryMemoryUsage")
 	vmalertProxyURL = flag.String("vmalert.proxyURL", "", "Optional URL for proxying requests to vmalert. For example, if -vmalert.proxyURL=http://vmalert:8880 , then alerting API requests such as /api/v1/rules from Grafana will be proxied to http://vmalert:8880/api/v1/rules")
@@ -148,8 +149,9 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 					"are executed. Possible solutions: to reduce query load; to add more compute resources to the server; "+
 					"to increase -search.maxQueueDuration=%s; to increase -search.maxQueryDuration; to increase -search.maxConcurrentRequests",
 					d.Seconds(), *maxConcurrentRequests, maxQueueDuration),
-				StatusCode: http.StatusServiceUnavailable,
+				StatusCode: http.StatusTooManyRequests,
 			}
+			w.Header().Add("Retry-After", "10")
 			httpserver.Errorf(w, r, "%s", err)
 			return true
 		}
@@ -170,7 +172,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 	}
 
 	if path == "/internal/resetRollupResultCache" {
-		if !httpserver.CheckAuthFlag(w, r, *resetCacheAuthKey, "resetCacheAuthKey") {
+		if !httpserver.CheckAuthFlag(w, r, resetCacheAuthKey.Get(), "resetCacheAuthKey") {
 			return true
 		}
 		promql.ResetRollupResultCache()
@@ -367,7 +369,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		}
 		return true
 	case "/tags/delSeries":
-		if !httpserver.CheckAuthFlag(w, r, *deleteAuthKey, "deleteAuthKey") {
+		if !httpserver.CheckAuthFlag(w, r, deleteAuthKey.Get(), "deleteAuthKey") {
 			return true
 		}
 		graphiteTagsDelSeriesRequests.Inc()
@@ -386,7 +388,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		}
 		return true
 	case "/api/v1/admin/tsdb/delete_series":
-		if !httpserver.CheckAuthFlag(w, r, *deleteAuthKey, "deleteAuthKey") {
+		if !httpserver.CheckAuthFlag(w, r, deleteAuthKey.Get(), "deleteAuthKey") {
 			return true
 		}
 		deleteRequests.Inc()
@@ -425,6 +427,14 @@ func handleStaticAndSimpleRequests(w http.ResponseWriter, r *http.Request, path
 		}
 		return true
 	}
+	if path == "/vmui/timezone" {
+		httpserver.EnableCORS(w, r)
+		if err := handleVMUITimezone(w); err != nil {
+			httpserver.Errorf(w, r, "%s", err)
+			return true
+		}
+		return true
+	}
 	if strings.HasPrefix(path, "/vmui/") {
 		if strings.HasPrefix(path, "/vmui/static/") {
 			// Allow clients caching static contents for long period of time, since it shouldn't change over time.

app/vmselect/netstorage/netstorage.go

@@ -5,10 +5,12 @@ import (
 	"errors"
 	"flag"
 	"fmt"
+	"reflect"
 	"sort"
 	"sync"
 	"sync/atomic"
 	"time"
+	"unsafe"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/searchutils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmstorage"
@@ -88,30 +90,6 @@ type timeseriesWork struct {
 	rowsProcessed int
 }
 
-func (tsw *timeseriesWork) reset() {
-	tsw.mustStop = nil
-	tsw.rss = nil
-	tsw.pts = nil
-	tsw.f = nil
-	tsw.err = nil
-	tsw.rowsProcessed = 0
-}
-
-func getTimeseriesWork() *timeseriesWork {
-	v := tswPool.Get()
-	if v == nil {
-		v = &timeseriesWork{}
-	}
-	return v.(*timeseriesWork)
-}
-
-func putTimeseriesWork(tsw *timeseriesWork) {
-	tsw.reset()
-	tswPool.Put(tsw)
-}
-
-var tswPool sync.Pool
-
 func (tsw *timeseriesWork) do(r *Result, workerID uint) error {
 	if atomic.LoadUint32(tsw.mustStop) != 0 {
 		return nil
@@ -270,22 +248,20 @@ func (rss *Results) runParallel(qt *querytracer.Tracer, f func(rs *Result, worke
 	maxWorkers := MaxWorkers()
 	if maxWorkers == 1 || tswsLen == 1 {
 		// It is faster to process time series in the current goroutine.
-		tsw := getTimeseriesWork()
+		var tsw timeseriesWork
 		tmpResult := getTmpResult()
 		rowsProcessedTotal := 0
 		var err error
 		for i := range rss.packedTimeseries {
-			initTimeseriesWork(tsw, &rss.packedTimeseries[i])
+			initTimeseriesWork(&tsw, &rss.packedTimeseries[i])
 			err = tsw.do(&tmpResult.rs, 0)
 			rowsReadPerSeries.Update(float64(tsw.rowsProcessed))
 			rowsProcessedTotal += tsw.rowsProcessed
 			if err != nil {
 				break
 			}
-			tsw.reset()
 		}
 		putTmpResult(tmpResult)
-		putTimeseriesWork(tsw)
 
 		return rowsProcessedTotal, err
 	}
@@ -295,11 +271,9 @@ func (rss *Results) runParallel(qt *querytracer.Tracer, f func(rs *Result, worke
 	// which reduces the scalability on systems with many CPU cores.
 
 	// Prepare the work for workers.
-	tsws := make([]*timeseriesWork, len(rss.packedTimeseries))
+	tsws := make([]timeseriesWork, len(rss.packedTimeseries))
 	for i := range rss.packedTimeseries {
-		tsw := getTimeseriesWork()
-		initTimeseriesWork(tsw, &rss.packedTimeseries[i])
-		tsws[i] = tsw
+		initTimeseriesWork(&tsws[i], &rss.packedTimeseries[i])
 	}
 
 	// Prepare worker channels.
@@ -314,9 +288,9 @@ func (rss *Results) runParallel(qt *querytracer.Tracer, f func(rs *Result, worke
 	}
 
 	// Spread work among workers.
-	for i, tsw := range tsws {
+	for i := range tsws {
 		idx := i % len(workChs)
-		workChs[idx] <- tsw
+		workChs[idx] <- &tsws[i]
 	}
 	// Mark worker channels as closed.
 	for _, workCh := range workChs {
@@ -339,14 +313,14 @@ func (rss *Results) runParallel(qt *querytracer.Tracer, f func(rs *Result, worke
 	// Collect results.
 	var firstErr error
 	rowsProcessedTotal := 0
-	for _, tsw := range tsws {
+	for i := range tsws {
+		tsw := &tsws[i]
 		if tsw.err != nil && firstErr == nil {
 			// Return just the first error, since other errors are likely duplicate the first error.
 			firstErr = tsw.err
 		}
 		rowsReadPerSeries.Update(float64(tsw.rowsProcessed))
 		rowsProcessedTotal += tsw.rowsProcessed
-		putTimeseriesWork(tsw)
 	}
 	return rowsProcessedTotal, firstErr
 }
@@ -1044,7 +1018,7 @@ func ExportBlocks(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline sear
 			for xw := range workCh {
 				if err := f(&xw.mn, &xw.b, tr, workerID); err != nil {
 					errGlobalLock.Lock()
-					if errGlobal != nil {
+					if errGlobal == nil {
 						errGlobal = err
 						atomic.StoreUint32(&mustStop, 1)
 					}
@@ -1169,15 +1143,44 @@ func ProcessSearchQuery(qt *querytracer.Tracer, sq *storage.SearchQuery, deadlin
 	maxSeriesCount := sr.Init(qt, vmstorage.Storage, tfss, tr, sq.MaxMetrics, deadline.Deadline())
 	indexSearchDuration.UpdateDuration(startTime)
 	type blockRefs struct {
-		brsPrealloc [4]blockRef
-		brs         []blockRef
+		brs []blockRef
 	}
-	m := make(map[string]*blockRefs, maxSeriesCount)
-	orderedMetricNames := make([]string, 0, maxSeriesCount)
+
 	blocksRead := 0
 	samples := 0
 	tbf := getTmpBlocksFile()
 	var buf []byte
+	var metricNamePrev []byte
+
+	// metricNamesBuf is used for holding all the loaded unique metric names at m and orderedMetricNames.
+	// It should reduce pressure on Go GC by reducing the number of string allocations
+	// when constructing metricName string from byte slice.
+	metricNamesBufCap := maxSeriesCount * 100
+	if metricNamesBufCap > maxFastAllocBlockSize {
+		metricNamesBufCap = maxFastAllocBlockSize
+	}
+	metricNamesBuf := make([]byte, 0, metricNamesBufCap)
+
+	// brssPool is used for holding all the blockRefs objects across all the loaded time series.
+	// It should reduce pressure on Go GC by reducing the number of blockRefs allocations.
+	brssPool := make([]blockRefs, 0, maxSeriesCount)
+
+	// brsPool is used for holding the most of blockRefs.brs slices across all the loaded time series.
+	// It should reduce pressure on Go GC by reducing the number of allocations for blockRefs.brs slices.
+	brsPoolCap := uintptr(maxSeriesCount)
+	if brsPoolCap > maxFastAllocBlockSize/unsafe.Sizeof(blockRef{}) {
+		brsPoolCap = maxFastAllocBlockSize / unsafe.Sizeof(blockRef{})
+	}
+	brsPool := make([]blockRef, 0, brsPoolCap)
+
+	// m maps from metricName to the index of blockRefs inside brssPool
+	m := make(map[string]int, maxSeriesCount)
+
+	// orderedMetricNames contains the list of loaded unique metric names
+	// in the load order. This order is important for triggering sequential data reading.
+	orderedMetricNames := make([]string, 0, maxSeriesCount)
+
+	var brsIdx int
 	for sr.NextMetricBlock() {
 		blocksRead++
 		if deadline.Exceeded() {
@@ -1190,8 +1193,10 @@ func ProcessSearchQuery(qt *querytracer.Tracer, sq *storage.SearchQuery, deadlin
 		if *maxSamplesPerQuery > 0 && samples > *maxSamplesPerQuery {
 			putTmpBlocksFile(tbf)
 			putStorageSearch(sr)
-			return nil, fmt.Errorf("cannot select more than -search.maxSamplesPerQuery=%d samples; possible solutions: to increase the -search.maxSamplesPerQuery; to reduce time range for the query; to use more specific label filters in order to select lower number of series", *maxSamplesPerQuery)
+			return nil, fmt.Errorf("cannot select more than -search.maxSamplesPerQuery=%d samples; possible solutions: to increase the -search.maxSamplesPerQuery; "+
+				"to reduce time range for the query; to use more specific label filters in order to select lower number of series", *maxSamplesPerQuery)
 		}
+
 		buf = br.Marshal(buf[:0])
 		addr, err := tbf.WriteBlockRefData(buf)
 		if err != nil {
@@ -1199,24 +1204,59 @@ func ProcessSearchQuery(qt *querytracer.Tracer, sq *storage.SearchQuery, deadlin
 			putStorageSearch(sr)
 			return nil, fmt.Errorf("cannot write %d bytes to temporary file: %w", len(buf), err)
 		}
-		// Do not intern mb.MetricName, since it leads to increased memory usage.
-		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3692
+
 		metricName := sr.MetricBlockRef.MetricName
-		brs := m[string(metricName)]
-		if brs == nil {
-			brs = &blockRefs{}
-			brs.brs = brs.brsPrealloc[:0]
+		if metricNamePrev == nil || string(metricName) != string(metricNamePrev) {
+			idx, ok := m[string(metricName)]
+			if !ok {
+				if cap(brssPool) > len(brssPool) {
+					brssPool = brssPool[:len(brssPool)+1]
+				} else {
+					brssPool = append(brssPool, blockRefs{})
+				}
+				idx = len(brssPool) - 1
+			}
+			brsIdx = idx
+			metricNamePrev = append(metricNamePrev[:0], metricName...)
+		}
+
+		brs := &brssPool[brsIdx]
+		partRef := br.PartRef()
+		if uintptr(cap(brsPool)) >= maxFastAllocBlockSize/unsafe.Sizeof(blockRef{}) && len(brsPool) == cap(brsPool) {
+			// Allocate a new brsPool in order to avoid slow allocation of an object
+			// bigger than maxFastAllocBlockSize bytes at append() below.
+			brsPool = make([]blockRef, 0, maxFastAllocBlockSize/unsafe.Sizeof(blockRef{}))
+		}
+		if canAppendToBlockRefPool(brsPool, brs.brs) {
+			// It is safe appending blockRef to brsPool, since there are no other items added there yet.
+			brsPool = append(brsPool, blockRef{
+				partRef: partRef,
+				addr:    addr,
+			})
+			brs.brs = brsPool[len(brsPool)-len(brs.brs)-1 : len(brsPool) : len(brsPool)]
+		} else {
+			// It is unsafe appending blockRef to brsPool, since there are other items added there.
+			// So just append it to brs.brs.
+			brs.brs = append(brs.brs, blockRef{
+				partRef: partRef,
+				addr:    addr,
+			})
 		}
-		brs.brs = append(brs.brs, blockRef{
-			partRef: br.PartRef(),
-			addr:    addr,
-		})
 		if len(brs.brs) == 1 {
-			metricNameStr := string(metricName)
+			if cap(metricNamesBuf) >= maxFastAllocBlockSize && len(metricNamesBuf)+len(metricName) > cap(metricNamesBuf) {
+				// Allocate a new metricNamesBuf in order to avoid slow allocation of byte slice
+				// bigger than maxFastAllocBlockSize bytes at append() below.
+				metricNamesBuf = make([]byte, 0, maxFastAllocBlockSize)
+			}
+			metricNamesBufLen := len(metricNamesBuf)
+			metricNamesBuf = append(metricNamesBuf, metricName...)
+			metricNameStr := bytesutil.ToUnsafeString(metricNamesBuf[metricNamesBufLen:])
+
 			orderedMetricNames = append(orderedMetricNames, metricNameStr)
-			m[metricNameStr] = brs
+			m[metricNameStr] = brsIdx
 		}
 	}
+
 	if err := sr.Error(); err != nil {
 		putTmpBlocksFile(tbf)
 		putStorageSearch(sr)
@@ -1239,7 +1279,7 @@ func ProcessSearchQuery(qt *querytracer.Tracer, sq *storage.SearchQuery, deadlin
 	for i, metricName := range orderedMetricNames {
 		pts[i] = packedTimeseries{
 			metricName: metricName,
-			brs:        m[metricName].brs,
+			brs:        brssPool[m[metricName]].brs,
 		}
 	}
 	rss.packedTimeseries = pts
@@ -1255,6 +1295,25 @@ type blockRef struct {
 	addr    tmpBlockAddr
 }
 
+// canAppendToBlockRefPool returns true if a points to the pool and the last item in a is the last item in the pool.
+//
+// In this case it is safe appending an item to the pool and then updating the a, so it refers to the extended slice.
+//
+// True is also returned if a is nil, since in this case it is safe appending an item to the pool and pointing a
+// to the last item in the pool.
+func canAppendToBlockRefPool(pool, a []blockRef) bool {
+	if a == nil {
+		return true
+	}
+	if len(a) > len(pool) {
+		// a doesn't belong to pool
+		return false
+	}
+	shPool := (*reflect.SliceHeader)(unsafe.Pointer(&pool))
+	shA := (*reflect.SliceHeader)(unsafe.Pointer(&a))
+	return shPool.Data+uintptr(shPool.Len)*unsafe.Sizeof(blockRef{}) == shA.Data+uintptr(shA.Len)*unsafe.Sizeof(blockRef{})
+}
+
 func setupTfss(qt *querytracer.Tracer, tr storage.TimeRange, tagFilterss [][]storage.TagFilter, maxMetrics int, deadline searchutils.Deadline) ([]*storage.TagFilters, error) {
 	tfss := make([]*storage.TagFilters, 0, len(tagFilterss))
 	for _, tagFilters := range tagFilterss {
@@ -1300,3 +1359,8 @@ func applyGraphiteRegexpFilter(filter string, ss []string) ([]string, error) {
 	}
 	return dst, nil
 }
+
+// Go uses fast allocations for block sizes up to 32Kb.
+//
+// See https://github.com/golang/go/blob/704401ffa06c60e059c9e6e4048045b4ff42530a/src/runtime/malloc.go#L11
+const maxFastAllocBlockSize = 32 * 1024

app/vmselect/netstorage/tmp_blocks_file.go

@@ -136,21 +136,25 @@ func (tbf *tmpBlocksFile) Finalize() error {
 		return fmt.Errorf("cannot write the remaining %d bytes to %q: %w", len(tbf.buf), fname, err)
 	}
 	tbf.buf = tbf.buf[:0]
-	r := fs.MustOpenReaderAt(fname)
+	r := fs.NewReaderAt(tbf.f)
+
 	// Hint the OS that the file is read almost sequentiallly.
 	// This should reduce the number of disk seeks, which is important
 	// for HDDs.
 	r.MustFadviseSequentialRead(true)
+
 	// Collect local stats in order to improve performance on systems with big number of CPU cores.
 	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3966
 	r.SetUseLocalStats()
+
 	tbf.r = r
+	tbf.f = nil
 	return nil
 }
 
 func (tbf *tmpBlocksFile) MustReadBlockRefAt(partRef storage.PartRef, addr tmpBlockAddr) storage.BlockRef {
 	var buf []byte
-	if tbf.f == nil {
+	if tbf.r == nil {
 		buf = tbf.buf[addr.offset : addr.offset+uint64(addr.size)]
 	} else {
 		bb := tmpBufPool.Get()
@@ -169,21 +173,45 @@ func (tbf *tmpBlocksFile) MustReadBlockRefAt(partRef storage.PartRef, addr tmpBl
 var tmpBufPool bytesutil.ByteBufferPool
 
 func (tbf *tmpBlocksFile) MustClose() {
-	if tbf.f == nil {
+	if tbf.f != nil {
+		// tbf.f could be non-nil if Finalize wasn't called.
+		// In this case tbf.r must be nil.
+		if tbf.r != nil {
+			logger.Panicf("BUG: tbf.r must be nil when tbf.f!=nil")
+		}
+
+		// Try removing the file before closing it in order to prevent from flushing the in-memory data
+		// from page cache to the disk and save disk write IO. This may fail on non-posix systems such as Windows.
+		// Gracefully handle this case by attempting to remove the file after closing it.
+		fname := tbf.f.Name()
+		errRemove := os.Remove(fname)
+		if err := tbf.f.Close(); err != nil {
+			logger.Panicf("FATAL: cannot close %q: %s", fname, err)
+		}
+		if errRemove != nil {
+			if err := os.Remove(fname); err != nil {
+				logger.Panicf("FATAL: cannot remove %q: %s", fname, err)
+			}
+		}
+		tbf.f = nil
 		return
 	}
-	if tbf.r != nil {
-		// tbf.r could be nil if Finalize wasn't called.
-		tbf.r.MustClose()
-	}
-	fname := tbf.f.Name()
 
-	if err := tbf.f.Close(); err != nil {
-		logger.Panicf("FATAL: cannot close %q: %s", fname, err)
+	if tbf.r == nil {
+		// Nothing to do
+		return
 	}
-	// We cannot remove unclosed at non-posix filesystems, like windows
-	if err := os.Remove(fname); err != nil {
-		logger.Panicf("FATAL: cannot remove %q: %s", fname, err)
+
+	// Try removing the file before closing it in order to prevent from flushing the in-memory data
+	// from page cache to the disk and save disk write IO. This may fail on non-posix systems such as Windows.
+	// Gracefully handle this case by attempting to remove the file after closing it.
+	fname := tbf.r.Path()
+	errRemove := os.Remove(fname)
+	tbf.r.MustClose()
+	if errRemove != nil {
+		if err := os.Remove(fname); err != nil {
+			logger.Panicf("FATAL: cannot remove %q: %s", fname, err)
+		}
 	}
-	tbf.f = nil
+	tbf.r = nil
 }

app/vmselect/prometheus/expand-with-exprs.qtpl

@@ -82,7 +82,7 @@ textarea { margin: 1em }
 <h3>Tutorial for WITH expressions in <a href="https://docs.victoriametrics.com/MetricsQL.html">MetricsQL</a></h3>
 
 <p>
-    Let's look at the following real query from <a href="https://grafana.com/grafana/dashboards/1860-node-exporter-full/">Node Exporter Full</a> dashboard:
+    Let's look at the following real query from <a href="https://grafana.com/grafana/dashboards/1860">Node Exporter Full</a> dashboard:
 </p>
 
 <pre>
@@ -146,7 +146,7 @@ my_resource_utilization(
 </p>
 
 <p>
-    Let's take another nice query from <a href="https://grafana.com/grafana/dashboards/1860-node-exporter-full/">Node Exporter Full</a> dashboard:
+    Let's take another nice query from <a href="https://grafana.com/grafana/dashboards/1860">Node Exporter Full</a> dashboard:
 </p>
 
 <pre>

app/vmselect/prometheus/expand-with-exprs.qtpl.go

@@ -195,7 +195,7 @@ func streamwithExprsTutorial(qw422016 *qt422016.Writer) {
 <h3>Tutorial for WITH expressions in <a href="https://docs.victoriametrics.com/MetricsQL.html">MetricsQL</a></h3>
 
 <p>
-    Let's look at the following real query from <a href="https://grafana.com/grafana/dashboards/1860-node-exporter-full/">Node Exporter Full</a> dashboard:
+    Let's look at the following real query from <a href="https://grafana.com/grafana/dashboards/1860">Node Exporter Full</a> dashboard:
 </p>
 
 <pre>
@@ -259,7 +259,7 @@ my_resource_utilization(
 </p>
 
 <p>
-    Let's take another nice query from <a href="https://grafana.com/grafana/dashboards/1860-node-exporter-full/">Node Exporter Full</a> dashboard:
+    Let's take another nice query from <a href="https://grafana.com/grafana/dashboards/1860">Node Exporter Full</a> dashboard:
 </p>
 
 <pre>

app/vmselect/prometheus/prometheus.go

@@ -321,7 +321,9 @@ func exportHandler(qt *querytracer.Tracer, w http.ResponseWriter, cp *commonPara
 		firstLineSent := uint32(0)
 		writeLineFunc = func(xb *exportBlock, workerID uint) error {
 			bb := sw.getBuffer(workerID)
-			if atomic.CompareAndSwapUint32(&firstLineOnce, 0, 1) {
+			// Use atomic.LoadUint32() in front of atomic.CompareAndSwapUint32() in order to avoid slow inter-CPU synchronization
+			// in fast path after the first line has been already sent.
+			if atomic.LoadUint32(&firstLineOnce) == 0 && atomic.CompareAndSwapUint32(&firstLineOnce, 0, 1) {
 				// Send the first line to sw.bw
 				WriteExportPromAPILine(bb, xb)
 				_, err := sw.bw.Write(bb.B)
@@ -497,7 +499,10 @@ func LabelValuesHandler(qt *querytracer.Tracer, startTime time.Time, labelName s
 	if err != nil {
 		return err
 	}
-	sq := storage.NewSearchQuery(cp.start, cp.end, cp.filterss, *maxUniqueTimeseries)
+	// Do not limit the number of unique time series, which could be scanned
+	// during the search for matching label values, since users expect this API
+	// must always work.
+	sq := storage.NewSearchQuery(cp.start, cp.end, cp.filterss, -1)
 	labelValues, err := netstorage.LabelValues(qt, labelName, sq, limit, cp.deadline)
 	if err != nil {
 		return fmt.Errorf("cannot obtain values for label %q: %w", labelName, err)
@@ -594,7 +599,10 @@ func LabelsHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseW
 	if err != nil {
 		return err
 	}
-	sq := storage.NewSearchQuery(cp.start, cp.end, cp.filterss, *maxUniqueTimeseries)
+	// Do not limit the number of unique time series, which could be scanned
+	// during the search for matching label values, since users expect this API
+	// must always work.
+	sq := storage.NewSearchQuery(cp.start, cp.end, cp.filterss, -1)
 	labels, err := netstorage.LabelNames(qt, sq, limit, cp.deadline)
 	if err != nil {
 		return fmt.Errorf("cannot obtain labels: %w", err)

app/vmselect/promql/aggr.go

@@ -111,41 +111,48 @@ func aggrFuncExt(afe func(tss []*timeseries, modifier *metricsql.ModifierExpr) [
 	modifier *metricsql.ModifierExpr, maxSeries int, keepOriginal bool) ([]*timeseries, error) {
 	m := aggrPrepareSeries(argOrig, modifier, maxSeries, keepOriginal)
 	rvs := make([]*timeseries, 0, len(m))
-	for _, tss := range m {
-		rv := afe(tss, modifier)
+	for _, tssl := range m {
+		rv := afe(tssl.tss, modifier)
 		rvs = append(rvs, rv...)
 	}
 	return rvs, nil
 }
 
-func aggrPrepareSeries(argOrig []*timeseries, modifier *metricsql.ModifierExpr, maxSeries int, keepOriginal bool) map[string][]*timeseries {
+func aggrPrepareSeries(argOrig []*timeseries, modifier *metricsql.ModifierExpr, maxSeries int, keepOriginal bool) map[string]*tssList {
 	// Remove empty time series, e.g. series with all NaN samples,
 	// since such series are ignored by aggregate functions.
 	argOrig = removeEmptySeries(argOrig)
 	arg := copyTimeseriesMetricNames(argOrig, keepOriginal)
 
 	// Perform grouping.
-	m := make(map[string][]*timeseries)
+	m := make(map[string]*tssList)
 	bb := bbPool.Get()
 	for i, ts := range arg {
 		removeGroupTags(&ts.MetricName, modifier)
 		bb.B = marshalMetricNameSorted(bb.B[:0], &ts.MetricName)
-		k := string(bb.B)
+		k := bb.B
 		if keepOriginal {
 			ts = argOrig[i]
 		}
-		tss := m[k]
-		if tss == nil && maxSeries > 0 && len(m) >= maxSeries {
-			// We already reached time series limit after grouping. Skip other time series.
-			continue
+		tssl := m[string(k)]
+		if tssl == nil {
+			if maxSeries > 0 && len(m) >= maxSeries {
+				// We already reached time series limit after grouping. Skip other time series.
+				continue
+			}
+			tssl = &tssList{}
+			m[string(k)] = tssl
 		}
-		tss = append(tss, ts)
-		m[k] = tss
+		tssl.tss = append(tssl.tss, ts)
 	}
 	bbPool.Put(bb)
 	return m
 }
 
+type tssList struct {
+	tss []*timeseries
+}
+
 func aggrFuncAny(afa *aggrFuncArg) ([]*timeseries, error) {
 	tss, err := getAggrTimeseries(afa.args)
 	if err != nil {
@@ -626,8 +633,8 @@ func aggrFuncCountValues(afa *aggrFuncArg) ([]*timeseries, error) {
 
 	m := aggrPrepareSeries(args[1], &afa.ae.Modifier, afa.ae.Limit, false)
 	rvs := make([]*timeseries, 0, len(m))
-	for _, tss := range m {
-		rv, err := afe(tss, modifier)
+	for _, tssl := range m {
+		rv, err := afe(tssl.tss, modifier)
 		if err != nil {
 			return nil, err
 		}
@@ -651,13 +658,14 @@ func newAggrFuncTopK(isReverse bool) aggrFunc {
 		}
 		afe := func(tss []*timeseries, modififer *metricsql.ModifierExpr) []*timeseries {
 			for n := range tss[0].Values {
+				lessFunc := lessWithNaNs
+				if isReverse {
+					lessFunc = greaterWithNaNs
+				}
 				sort.Slice(tss, func(i, j int) bool {
 					a := tss[i].Values[n]
 					b := tss[j].Values[n]
-					if isReverse {
-						a, b = b, a
-					}
-					return lessWithNaNs(a, b)
+					return lessFunc(a, b)
 				})
 				fillNaNsAtIdx(n, ks[n], tss)
 			}
@@ -710,17 +718,19 @@ func getRangeTopKTimeseries(tss []*timeseries, modifier *metricsql.ModifierExpr,
 			value: value,
 		}
 	}
+	lessFunc := lessWithNaNs
+	if isReverse {
+		lessFunc = greaterWithNaNs
+	}
 	sort.Slice(maxs, func(i, j int) bool {
 		a := maxs[i].value
 		b := maxs[j].value
-		if isReverse {
-			a, b = b, a
-		}
-		return lessWithNaNs(a, b)
+		return lessFunc(a, b)
 	})
 	for i := range maxs {
 		tss[i] = maxs[i].ts
 	}
+
 	remainingSumTS := getRemainingSumTimeseries(tss, modifier, ks, remainingSumTagName)
 	for i, k := range ks {
 		fillNaNsAtIdx(i, k, tss)
@@ -1253,12 +1263,27 @@ func newAggrQuantileFunc(phis []float64) func(tss []*timeseries, modifier *metri
 }
 
 func lessWithNaNs(a, b float64) bool {
+	// consider NaNs are smaller than non-NaNs
 	if math.IsNaN(a) {
 		return !math.IsNaN(b)
 	}
+	if math.IsNaN(b) {
+		return false
+	}
 	return a < b
 }
 
+func greaterWithNaNs(a, b float64) bool {
+	// consider NaNs are bigger than non-NaNs
+	if math.IsNaN(a) {
+		return !math.IsNaN(b)
+	}
+	if math.IsNaN(b) {
+		return false
+	}
+	return a > b
+}
+
 func floatToIntBounded(f float64) int {
 	if f > math.MaxInt {
 		return math.MaxInt

app/vmselect/promql/aggr_incremental.go

@@ -111,8 +111,8 @@ func (iafc *incrementalAggrFuncContext) updateTimeseries(tsOrig *timeseries, wor
 	removeGroupTags(&ts.MetricName, &iafc.ae.Modifier)
 	bb := bbPool.Get()
 	bb.B = marshalMetricNameSorted(bb.B[:0], &ts.MetricName)
-	k := string(bb.B)
-	iac := m[k]
+	k := bb.B
+	iac := m[string(k)]
 	if iac == nil {
 		if iafc.ae.Limit > 0 && len(m) >= iafc.ae.Limit {
 			// Skip this time series, since the limit on the number of output time series has been already reached.
@@ -131,7 +131,7 @@ func (iafc *incrementalAggrFuncContext) updateTimeseries(tsOrig *timeseries, wor
 			ts:     tsAggr,
 			values: make([]float64, len(ts.Values)),
 		}
-		m[k] = iac
+		m[string(k)] = iac
 	}
 	bbPool.Put(bb)
 	iafc.callbacks.updateAggrFunc(iac, ts.Values)