docs/enterprise.md: add clarification for when license expires (#10956)

Many people are concerned about what happens when the license expires on
a VictoriaMetrics component. This PR aims to address those concerns.

PR https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10956

---------

Signed-off-by: Stephan Burns <34520077+Sleuth56@users.noreply.github.com>
Signed-off-by: Pablo (Tomas) Fernandez <46322567+TomFern@users.noreply.github.com>
Co-authored-by: Pablo Fernandez <46322567+TomFern@users.noreply.github.com>
Co-authored-by: Max Kotliar <mkotlyar@victoriametrics.com>

.github/workflows/build.yml

@@ -57,15 +57,17 @@ jobs:
             arch: amd64
           - os: openbsd
             arch: amd64
+          - os: netbsd
+            arch: amd64
           - os: windows
             arch: amd64
     steps:
       - name: Code checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Setup Go
         id: go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
           cache-dependency-path: |
             go.sum

.github/workflows/changelog-linter.yml

@@ -9,7 +9,7 @@ jobs:
   tip-lint:
     runs-on: 'ubuntu-latest'
     steps:
-      - uses: 'actions/checkout@v6'
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           # needed for proper diff
           fetch-depth: 0

.github/workflows/check-commit-signed.yml

@@ -8,7 +8,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           fetch-depth: 0  # we need full history for commit verification
 

.github/workflows/check-licenses.yml

@@ -15,11 +15,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@master
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Setup Go
         id: go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
           go-version-file: 'go.mod'
           cache: false
@@ -27,7 +27,7 @@ jobs:
       - run: go version
 
       - name: Cache Go artifacts
-        uses: actions/cache@v5
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
         with:
           path: |
             ~/.cache/go-build

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

@@ -29,18 +29,18 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Set up Go
         id: go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
           cache: false
           go-version-file: 'go.mod'
       - run: go version
 
       - name: Cache Go artifacts
-        uses: actions/cache@v5
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
         with:
           path: |
             ~/.cache/go-build
@@ -50,14 +50,14 @@ jobs:
           restore-keys: go-artifacts-${{ runner.os }}-codeql-analyze-${{ steps.go.outputs.go-version }}-
 
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@v4.35.1
+        uses: github/codeql-action/init@95e58e9a2cdfd71adc6e0353d5c52f41a045d225  # v4.35.2
         with:
           languages: go
 
       - name: Autobuild
-        uses: github/codeql-action/autobuild@v4.35.1
+        uses: github/codeql-action/autobuild@95e58e9a2cdfd71adc6e0353d5c52f41a045d225  # v4.35.2
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v4.35.1
+        uses: github/codeql-action/analyze@95e58e9a2cdfd71adc6e0353d5c52f41a045d225  # v4.35.2
         with:
           category: 'language:go'

.github/workflows/docs.yaml

@@ -16,19 +16,19 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           path: __vm
 
       - name: Checkout private code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           repository: VictoriaMetrics/vmdocs
           token: ${{ secrets.VM_BOT_GH_TOKEN }}
           path: __vm-docs
 
       - name: Import GPG key
-        uses: crazy-max/ghaction-import-gpg@v7
+        uses: crazy-max/ghaction-import-gpg@2dc316deee8e90f13e1a351ab510b4d5bc0c82cd  # v7.0.0
         id: import-gpg
         with:
           gpg_private_key: ${{ secrets.VM_BOT_GPG_PRIVATE_KEY }}

.github/workflows/test.yml

@@ -32,11 +32,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Setup Go
         id: go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
           cache-dependency-path: |
             go.sum
@@ -47,7 +47,7 @@ jobs:
       - run: go version
 
       - name: Cache golangci-lint
-        uses: actions/cache@v5
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
         with:
           path: |
             ~/.cache/golangci-lint
@@ -72,11 +72,11 @@ jobs:
 
     steps:
       - name: Code checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Setup Go
         id: go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
           cache-dependency-path: |
             go.sum
@@ -94,11 +94,11 @@ jobs:
 
     steps:
       - name: Code checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Setup Go
         id: go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
           cache-dependency-path: |
             go.sum

.github/workflows/vmui.yml

@@ -32,11 +32,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Cache node_modules
         id: cache
-        uses: actions/cache@v5
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
         with:
           path: app/vmui/packages/vmui/node_modules
           key: vmui-deps-${{ runner.os }}-${{ hashFiles('app/vmui/packages/vmui/package-lock.json', 'app/vmui/Dockerfile-build') }}
@@ -69,7 +69,7 @@ jobs:
           VMUI_SKIP_INSTALL: true
 
       - name: Annotate Code Linting Results
-        uses: ataylorme/eslint-annotate-action@v3
+        uses: ataylorme/eslint-annotate-action@d57a1193d4c59cbfbf3f86c271f42612f9dbd9e9  # 3.0.0
         with:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           report-json: app/vmui/packages/vmui/vmui-lint-report.json

SECURITY.md

@@ -1,42 +1,4 @@
 # Security Policy
 
-## Supported Versions
+You can find out about our security policy and VictoriaMetrics version support on the [security page](https://docs.victoriametrics.com/victoriametrics/#security) in the documentation.
 
-The following versions of VictoriaMetrics receive regular security fixes:
-
-| Version                                                                        | Supported          |
-|--------------------------------------------------------------------------------|--------------------|
-| [Latest release](https://docs.victoriametrics.com/victoriametrics/changelog/)  | :white_check_mark: |
-| [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-releases/) | :white_check_mark: |
-| other releases                                                                 | :x:                |
-
-See [this page](https://victoriametrics.com/security/) for more details.
-
-## Software Bill of Materials (SBOM)
-
-Every VictoriaMetrics container{{% available_from "#" %}} image published to
-[Docker Hub](https://hub.docker.com/u/victoriametrics)
-and [Quay.io](https://quay.io/organization/victoriametrics)
-includes an [SPDX](https://spdx.dev/) SBOM attestation
-generated automatically by BuildKit during
-`docker buildx build`.
-
-To inspect the SBOM for an image:
-
-```sh
-docker buildx imagetools inspect \
-  docker.io/victoriametrics/victoria-metrics:latest \
-  --format "{{ json .SBOM }}"
-```
-
-To scan an image using its SBOM attestation with
-[Trivy](https://github.com/aquasecurity/trivy):
-
-```sh
-trivy image --sbom-sources oci \
-  docker.io/victoriametrics/victoria-metrics:latest
-```
-
-## Reporting a Vulnerability
-
-Please report any security issues to <security@victoriametrics.com>

app/vmagent/main.go

@@ -83,6 +83,9 @@ var (
 	maxLabelsPerTimeseries = flag.Int("maxLabelsPerTimeseries", 0, "The maximum number of labels per time series to be accepted. Series with superfluous labels are ignored. In this case the vm_rows_ignored_total{reason=\"too_many_labels\"} metric at /metrics page is incremented")
 	maxLabelNameLen        = flag.Int("maxLabelNameLen", 0, "The maximum length of label names in the accepted time series. Series with longer label name are ignored. In this case the vm_rows_ignored_total{reason=\"too_long_label_name\"} metric at /metrics page is incremented")
 	maxLabelValueLen       = flag.Int("maxLabelValueLen", 0, "The maximum length of label values in the accepted time series. Series with longer label value are ignored. In this case the vm_rows_ignored_total{reason=\"too_long_label_value\"} metric at /metrics page is incremented")
+
+	enableMultitenancyViaHeaders = flag.Bool("enableMultitenancyViaHeaders", false, "Enables multitenancy via HTTP headers. "+
+		"See https://docs.victoriametrics.com/victoriametrics/vmagent/#multitenancy")
 )
 
 var (
@@ -216,7 +219,7 @@ func getOpenTSDBHTTPInsertHandler() func(req *http.Request) error {
 	}
 	return func(req *http.Request) error {
 		path := strings.ReplaceAll(req.URL.Path, "//", "/")
-		at, err := getAuthTokenFromPath(path)
+		at, err := getAuthTokenFromPath(path, req.Header)
 		if err != nil {
 			return fmt.Errorf("cannot obtain auth token from path %q: %w", path, err)
 		}
@@ -224,8 +227,15 @@ func getOpenTSDBHTTPInsertHandler() func(req *http.Request) error {
 	}
 }
 
-func getAuthTokenFromPath(path string) (*auth.Token, error) {
-	p, err := httpserver.ParsePath(path)
+func parsePath(path string, header http.Header) (*httpserver.Path, error) {
+	if *enableMultitenancyViaHeaders {
+		return httpserver.ParsePathAndHeaders(path, header)
+	}
+	return httpserver.ParsePath(path)
+}
+
+func getAuthTokenFromPath(path string, header http.Header) (*auth.Token, error) {
+	p, err := parsePath(path, header)
 	if err != nil {
 		return nil, fmt.Errorf("cannot parse multitenant path: %w", err)
 	}
@@ -559,14 +569,15 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 }
 
 func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path string) bool {
-	p, err := httpserver.ParsePath(path)
+	p, err := parsePath(path, r.Header)
 	if err != nil {
 		// Cannot parse multitenant path. Skip it - probably it will be parsed later.
 		return false
 	}
 	if p.Prefix != "insert" {
-		httpserver.Errorf(w, r, `unsupported multitenant prefix: %q; expected "insert"`, p.Prefix)
-		return true
+		// processMultitenantRequest is called for all unmatched path variants,
+		// but we should try parsing only /insert prefixed to avoid catching all possible paths.
+		return false
 	}
 	at, err := auth.NewTokenPossibleMultitenant(p.AuthToken)
 	if err != nil {

app/vmagent/remotewrite/client.go

@@ -2,6 +2,7 @@ package remotewrite
 
 import (
 	"bytes"
+	"context"
 	"errors"
 	"fmt"
 	"io"
@@ -59,6 +60,8 @@ var (
 		"Multiple headers must be delimited by '^^': -remoteWrite.headers='header1:value1^^header2:value2'")
 
 	basicAuthUsername     = flagutil.NewArrayString("remoteWrite.basicAuth.username", "Optional basic auth username to use for the corresponding -remoteWrite.url")
+	basicAuthUsernameFile = flagutil.NewArrayString("remoteWrite.basicAuth.usernameFile", "Optional path to basic auth username to use for the corresponding -remoteWrite.url. "+
+		"The file is re-read every second")
 	basicAuthPassword     = flagutil.NewArrayString("remoteWrite.basicAuth.password", "Optional basic auth password to use for the corresponding -remoteWrite.url")
 	basicAuthPasswordFile = flagutil.NewArrayString("remoteWrite.basicAuth.passwordFile", "Optional path to basic auth password to use for the corresponding -remoteWrite.url. "+
 		"The file is re-read every second")
@@ -223,12 +226,14 @@ func getAuthConfig(argIdx int) (*promauth.Config, error) {
 		hdrs = strings.Split(headersValue, "^^")
 	}
 	username := basicAuthUsername.GetOptionalArg(argIdx)
+	usernameFile := basicAuthUsernameFile.GetOptionalArg(argIdx)
 	password := basicAuthPassword.GetOptionalArg(argIdx)
 	passwordFile := basicAuthPasswordFile.GetOptionalArg(argIdx)
 	var basicAuthCfg *promauth.BasicAuthConfig
-	if username != "" || password != "" || passwordFile != "" {
+	if username != "" || usernameFile != "" || password != "" || passwordFile != "" {
 		basicAuthCfg = &promauth.BasicAuthConfig{
 			Username:     username,
+			UsernameFile: usernameFile,
 			Password:     promauth.NewSecret(password),
 			PasswordFile: passwordFile,
 		}
@@ -326,15 +331,20 @@ func (c *client) runWorker() {
 			c.fq.MustWriteBlockIgnoreDisabledPQ(block)
 			return
 		case <-c.stopCh:
-			// c must be stopped. Wait for a while in the hope the block will be sent.
-			graceDuration := 5 * time.Second
+			// c must be stopped. Wait up to 5 seconds for the in-flight request to complete.
+			// If it succeeds, drain the remaining in-memory queue before returning.
+			stopCtx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+			defer cancel()
+
 			select {
 			case ok := <-ch:
 				if !ok {
 					// Return unsent block to the queue.
 					c.fq.MustWriteBlockIgnoreDisabledPQ(block)
+				} else {
+					c.drainInMemoryQueue(stopCtx, block[:0])
 				}
-			case <-time.After(graceDuration):
+			case <-stopCtx.Done():
 				// Return unsent block to the queue.
 				c.fq.MustWriteBlockIgnoreDisabledPQ(block)
 			}
@@ -466,7 +476,7 @@ again:
 				goto again
 			}
 
-			logger.Warnf("failed to repack zstd block (%s bytes) to snappy: %s; The block will be rejected. "+
+			logger.Warnf("failed to repack zstd block (%d bytes) to snappy: %s; The block will be rejected. "+
 				"Possible cause: ungraceful shutdown leading to persisted queue corruption.",
 				zstdBlockLen, err)
 		}
@@ -504,6 +514,36 @@ again:
 	goto again
 }
 
+func (c *client) drainInMemoryQueue(stopCtx context.Context, block []byte) {
+	var ok bool
+	for {
+		select {
+		case <-stopCtx.Done():
+			return
+		default:
+		}
+
+		block, ok = c.fq.MustReadInMemoryBlock(block[:0])
+		if !ok {
+			// The in memory queue has already been drained,
+			// or persisted queue is being used.
+			// In this case it is guaranteed that fq will be empty
+			return
+		}
+		if len(block) == 0 {
+			// skip empty data blocks from sending
+			continue
+		}
+
+		// at this stage c.stopCh should be closed
+		// so sendBlock function should not perform retries
+		if ok := c.sendBlock(block); !ok {
+			c.fq.MustWriteBlockIgnoreDisabledPQ(block)
+			return
+		}
+	}
+}
+
 var remoteWriteRejectedLogger = logger.WithThrottler("remoteWriteRejected", 5*time.Second)
 var remoteWriteRetryLogger = logger.WithThrottler("remoteWriteRetry", 5*time.Second)
 

app/vmagent/remotewrite/client_test.go

@@ -9,6 +9,7 @@ import (
 	"github.com/golang/snappy"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/encoding"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 )
 
 func TestParseRetryAfterHeader(t *testing.T) {
@@ -36,6 +37,40 @@ func TestParseRetryAfterHeader(t *testing.T) {
 	f(time.Now().Add(10*time.Second).Format("Mon, 02 Jan 2006 15:04:05 FAKETZ"), 0)
 }
 
+func TestInitSecretFlags(t *testing.T) {
+	showRemoteWriteURLOrig := *showRemoteWriteURL
+	defer func() {
+		*showRemoteWriteURL = showRemoteWriteURLOrig
+		flagutil.UnregisterAllSecretFlags()
+	}()
+
+	flagutil.UnregisterAllSecretFlags()
+	*showRemoteWriteURL = false
+	InitSecretFlags()
+	if !flagutil.IsSecretFlag("remotewrite.url") {
+		t.Fatalf("expecting remoteWrite.url to be secret")
+	}
+	if !flagutil.IsSecretFlag("remotewrite.headers") {
+		t.Fatalf("expecting remoteWrite.headers to be secret")
+	}
+	if !flagutil.IsSecretFlag("remotewrite.proxyurl") {
+		t.Fatalf("expecting remoteWrite.proxyURL to be secret")
+	}
+
+	flagutil.UnregisterAllSecretFlags()
+	*showRemoteWriteURL = true
+	InitSecretFlags()
+	if flagutil.IsSecretFlag("remotewrite.url") {
+		t.Fatalf("remoteWrite.url must remain visible when -remoteWrite.showURL is set")
+	}
+	if !flagutil.IsSecretFlag("remotewrite.headers") {
+		t.Fatalf("expecting remoteWrite.headers to remain secret")
+	}
+	if !flagutil.IsSecretFlag("remotewrite.proxyurl") {
+		t.Fatalf("expecting remoteWrite.proxyURL to remain secret")
+	}
+}
+
 func TestRepackBlockFromZstdToSnappy(t *testing.T) {
 	expectedPlainBlock := []byte(`foobar`)
 

app/vmagent/remotewrite/remotewrite.go

@@ -12,7 +12,6 @@ import (
 	"sync/atomic"
 	"time"
 
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/mdx"
 	"github.com/cespare/xxhash/v2"
 
 	"github.com/VictoriaMetrics/metrics"
@@ -103,9 +102,6 @@ var (
 		"cannot be pushed into the configured -remoteWrite.url systems in a timely manner. See https://docs.victoriametrics.com/victoriametrics/vmagent/#disabling-on-disk-persistence")
 	disableMetadataPerURL = flagutil.NewArrayBool("remoteWrite.disableMetadata", "Whether to disable sending metadata to the corresponding -remoteWrite.url. "+
 		"By default, metadata sending is controlled by the global -enableMetadata flag")
-
-	enableMdx = flagutil.NewArrayBool("remoteWrite.mdx.enable", "Whether to only retain metrics from VictoriaMetrics services before sending them to the corresponding -remoteWrite.url. "+
-		"Please see https://docs.victoriametrics.com/victoriametrics/vmagent/#monitoring-data-exchange")
 )
 
 var (
@@ -155,6 +151,10 @@ func InitSecretFlags() {
 		// remoteWrite.url can contain authentication codes, so hide it at `/metrics` output.
 		flagutil.RegisterSecretFlag("remoteWrite.url")
 	}
+	// remoteWrite.proxyURL can contain authentication codes.
+	flagutil.RegisterSecretFlag("remoteWrite.proxyURL")
+	// remoteWrite.headers can contain auth headers such as Authorization and API keys.
+	flagutil.RegisterSecretFlag("remoteWrite.headers")
 }
 
 var (
@@ -171,6 +171,18 @@ func Init() {
 	if len(*remoteWriteURLs) == 0 {
 		logger.Fatalf("at least one `-remoteWrite.url` command-line flag must be set")
 	}
+	if *shardByURL && len(*disableOnDiskQueue) > 1 {
+		disableOnDiskQueues := *disableOnDiskQueue
+
+		firstValue := disableOnDiskQueues[0]
+		for _, v := range disableOnDiskQueues[1:] {
+			if firstValue != v {
+				logger.Fatalf("all -remoteWrite.url targets must have the same -remoteWrite.disableOnDiskQueue setting when -remoteWrite.shardByURL is enabled; " +
+					"either enable or disable -remoteWrite.disableOnDiskQueue for all targets")
+			}
+		}
+	}
+
 	if limit := getMaxHourlySeries(); limit > 0 {
 		hourlySeriesLimiter = bloomfilter.NewLimiter(limit, time.Hour)
 		_ = metrics.NewGauge(`vmagent_hourly_series_limit_max_series`, func() float64 {
@@ -289,6 +301,7 @@ func initRemoteWriteCtxs(urls []string) {
 		rwctxs[i] = newRemoteWriteCtx(i, remoteWriteURL, sanitizedURL)
 		rwctxIdx[i] = i
 	}
+	fs.RegisterPathFsMetrics(*tmpDataPath)
 
 	if *shardByURL {
 		consistentHashNodes := make([]string, 0, len(urls))
@@ -298,10 +311,6 @@ func initRemoteWriteCtxs(urls []string) {
 		rwctxConsistentHashGlobal = consistenthash.NewConsistentHash(consistentHashNodes, 0)
 	}
 
-	if slices.Contains(*enableMdx, true) {
-		mdx.InitGlobalVmInstanceFilter()
-	}
-
 	rwctxsGlobal = rwctxs
 	rwctxsGlobalIdx = rwctxIdx
 }
@@ -364,7 +373,6 @@ func Stop() {
 	if sl := dailySeriesLimiter; sl != nil {
 		sl.MustStop()
 	}
-	mdx.GlobalVmInstanceFilter.MustStop()
 }
 
 // PushDropSamplesOnFailure pushes wr to the configured remote storage systems set via -remoteWrite.url
@@ -507,7 +515,9 @@ func tryPush(at *auth.Token, wr *prompb.WriteRequest, forceDropSamplesOnFailure
 //
 // calculateHealthyRwctxIdx will rely on the order of rwctx to be in ascending order.
 func getEligibleRemoteWriteCtxs(tss []prompb.TimeSeries, forceDropSamplesOnFailure bool) ([]*remoteWriteCtx, bool) {
-	if !disableOnDiskQueueAny {
+	// When -remoteWrite.shardByURL=true always use all configured remote writes to preserve stable metrics distribution across shards.
+	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10507
+	if !disableOnDiskQueueAny || *shardByURL {
 		return rwctxsGlobal, true
 	}
 
@@ -522,12 +532,6 @@ func getEligibleRemoteWriteCtxs(tss []prompb.TimeSeries, forceDropSamplesOnFailu
 				return nil, false
 			}
 			rowsCount := getRowsCount(tss)
-			if *shardByURL {
-				// Todo: When shardByURL is enabled, the following metrics won't be 100% accurate. Because vmagent don't know
-				// which rwctx should data be pushed to yet. Let's consider the hashing algorithm fair and will distribute
-				// data to all rwctxs evenly.
-				rowsCount = rowsCount / len(rwctxsGlobal)
-			}
 			rwctx.rowsDroppedOnPushFailure.Add(rowsCount)
 		}
 	}
@@ -707,7 +711,7 @@ func shardAmountRemoteWriteCtx(tssBlock []prompb.TimeSeries, shards [][]prompb.T
 			}
 			tmpLabels.Labels = hashLabels
 		}
-		h := getLabelsHash(hashLabels)
+		h := getLabelsHashForShard(hashLabels)
 
 		// Get the rwctxIdx through consistent hashing and then map it to the index in shards.
 		// The rwctxIdx is not always equal to the shardIdx, for example, when some rwctx are not available.
@@ -798,11 +802,28 @@ var (
 	dailySeriesLimitRowsDropped  = metrics.NewCounter(`vmagent_daily_series_limit_rows_dropped_total`)
 )
 
+// getLabelsHashForShard is a separate function from getLabelsHash because
+// it omits the '=' separator between label name and value for backward compatibility.
+// Changing it would re-shard all series across remoteWrite targets.
+func getLabelsHashForShard(labels []prompb.Label) uint64 {
+	bb := labelsHashBufPool.Get()
+	b := bb.B[:0]
+	for _, label := range labels {
+		b = append(b, label.Name...)
+		b = append(b, label.Value...)
+	}
+	h := xxhash.Sum64(b)
+	bb.B = b
+	labelsHashBufPool.Put(bb)
+	return h
+}
+
 func getLabelsHash(labels []prompb.Label) uint64 {
 	bb := labelsHashBufPool.Get()
 	b := bb.B[:0]
 	for _, label := range labels {
 		b = append(b, label.Name...)
+		b = append(b, '=')
 		b = append(b, label.Value...)
 	}
 	h := xxhash.Sum64(b)
@@ -846,14 +867,11 @@ type remoteWriteCtx struct {
 	// otherwise by the global -enableMetadata flag.
 	enableMetadata bool
 
-	enableMdx bool
-
 	pss        []*pendingSeries
 	pssNextIdx atomic.Uint64
 
 	rowsPushedAfterRelabel *metrics.Counter
 	rowsDroppedByRelabel   *metrics.Counter
-	rowsDroppedByMdx       *metrics.Counter
 
 	pushFailures                 *metrics.Counter
 	metadataDroppedOnPushFailure *metrics.Counter
@@ -940,17 +958,16 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
 	for i := range pss {
 		pss[i] = newPendingSeries(fq, &c.useVMProto, sf, rd)
 	}
+
 	rwctx := &remoteWriteCtx{
 		idx:            argIdx,
 		fq:             fq,
 		c:              c,
 		pss:            pss,
 		enableMetadata: isMetadataEnabledForURL(argIdx),
-		enableMdx:      enableMdx.GetOptionalArg(argIdx),
 
 		rowsPushedAfterRelabel: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_rows_pushed_after_relabel_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
 		rowsDroppedByRelabel:   metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_relabel_metrics_dropped_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
-		rowsDroppedByMdx:       metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_mdx_rows_dropped_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
 
 		pushFailures:                 metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_push_failures_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
 		metadataDroppedOnPushFailure: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_metadata_dropped_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
@@ -986,7 +1003,6 @@ func (rwctx *remoteWriteCtx) MustStop() {
 
 	rwctx.rowsPushedAfterRelabel = nil
 	rwctx.rowsDroppedByRelabel = nil
-	rwctx.rowsDroppedByMdx = nil
 }
 
 // TryPushTimeSeries sends tss series to the configured remote write endpoint
@@ -1004,31 +1020,17 @@ func (rwctx *remoteWriteCtx) TryPushTimeSeries(tss []prompb.TimeSeries, forceDro
 		putRelabelCtx(rctx)
 	}()
 
-	if rwctx.enableMdx && mdx.GlobalVmInstanceFilter != nil {
-		rctx = getRelabelCtx()
-		// Make a copy of tss
-		v = tssPool.Get().(*[]prompb.TimeSeries)
-		tss = append(*v, tss...)
-		rowsCountBeforeMdx := getRowsCount(tss)
-		tss = mdx.GlobalVmInstanceFilter.ApplyMdxFilter(tss)
-		rowsCountAfterMdx := getRowsCount(tss)
-		rwctx.rowsDroppedByMdx.Add(rowsCountBeforeMdx - rowsCountAfterMdx)
-	}
-
 	// Apply relabeling
 	rcs := allRelabelConfigs.Load()
 	pcs := rcs.perURL[rwctx.idx]
 	if pcs.Len() > 0 {
-		if rctx == nil {
-			// Make a copy of tss before applying relabeling in order to prevent
-			// from affecting time series for other remoteWrite.url configs.
-			// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/467
-			// and https://github.com/VictoriaMetrics/VictoriaMetrics/issues/599
-			rctx = getRelabelCtx()
-			// Make a copy of tss before dropping aggregated series
-			v = tssPool.Get().(*[]prompb.TimeSeries)
-			tss = append(*v, tss...)
-		}
+		rctx = getRelabelCtx()
+		// Make a copy of tss before applying relabeling in order to prevent
+		// from affecting time series for other remoteWrite.url configs.
+		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/467
+		// and https://github.com/VictoriaMetrics/VictoriaMetrics/issues/599
+		v = tssPool.Get().(*[]prompb.TimeSeries)
+		tss = append(*v, tss...)
 		rowsCountBeforeRelabel := getRowsCount(tss)
 		tss = rctx.applyRelabeling(tss, pcs)
 		rowsCountAfterRelabel := getRowsCount(tss)

app/vmagent/remotewrite/remotewrite_test.go

@@ -25,7 +25,7 @@ func TestGetLabelsHash_Distribution(t *testing.T) {
 		t.Helper()
 
 		// Distribute itemsCount hashes returned by getLabelsHash() across bucketsCount buckets.
-		itemsCount := 1_000 * bucketsCount
+		itemsCount := 10_000 * bucketsCount
 		m := make([]int, bucketsCount)
 		var labels []prompb.Label
 		for i := range itemsCount {
@@ -44,10 +44,12 @@ func TestGetLabelsHash_Distribution(t *testing.T) {
 		}
 
 		// Verify that the distribution is even
-		expectedItemsPerBucket := itemsCount / bucketsCount
+		expectedItemsPerBucket := float64(itemsCount / bucketsCount)
+		allowedDeviation := math.Round(float64(expectedItemsPerBucket) * 0.04)
 		for _, n := range m {
-			if math.Abs(1-float64(n)/float64(expectedItemsPerBucket)) > 0.04 {
-				t.Fatalf("unexpected items in the bucket for %d buckets; got %d; want around %d", bucketsCount, n, expectedItemsPerBucket)
+			if math.Abs(expectedItemsPerBucket-float64(n)) > allowedDeviation {
+				t.Fatalf("unexpected items in the bucket for %d buckets; got %d; want in range [%.0f, %.0f]",
+					bucketsCount, n, expectedItemsPerBucket-allowedDeviation, expectedItemsPerBucket+allowedDeviation)
 			}
 		}
 	}

app/vmalert-tool/unittest/unittest.go

@@ -61,7 +61,7 @@ func UnitTest(files []string, disableGroupLabel bool, externalLabels []string, e
 	}
 	eu, err := url.Parse(externalURL)
 	if err != nil {
-		logger.Fatalf("failed to parse external URL: %w", err)
+		logger.Fatalf("failed to parse external URL: %s", err)
 	}
 	if err := templates.Load([]string{}, *eu); err != nil {
 		logger.Fatalf("failed to load template: %v", err)

app/vmalert/datasource/client_test.go

@@ -772,7 +772,7 @@ func TestHeaders(t *testing.T) {
 
 	// basic auth
 	f(func() *Client {
-		cfg, err := vmalertutil.AuthConfig(vmalertutil.WithBasicAuth("foo", "bar", ""))
+		cfg, err := vmalertutil.AuthConfig(vmalertutil.WithBasicAuth("foo", "", "bar", ""))
 		if err != nil {
 			t.Fatalf("Error get auth config: %s", err)
 		}
@@ -817,7 +817,7 @@ func TestHeaders(t *testing.T) {
 
 	// custom header overrides basic auth
 	f(func() *Client {
-		cfg, err := vmalertutil.AuthConfig(vmalertutil.WithBasicAuth("foo", "bar", ""))
+		cfg, err := vmalertutil.AuthConfig(vmalertutil.WithBasicAuth("foo", "", "bar", ""))
 		if err != nil {
 			t.Fatalf("Error get auth config: %s", err)
 		}

app/vmalert/datasource/init.go

@@ -27,6 +27,7 @@ var (
 		"Multiple headers must be delimited by '^^': -datasource.headers='header1:value1^^header2:value2'")
 
 	basicAuthUsername     = flag.String("datasource.basicAuth.username", "", "Optional basic auth username for -datasource.url")
+	basicAuthUsernameFile = flag.String("datasource.basicAuth.usernameFile", "", "Optional path to basic auth username to use for -datasource.url")
 	basicAuthPassword     = flag.String("datasource.basicAuth.password", "", "Optional basic auth password for -datasource.url")
 	basicAuthPasswordFile = flag.String("datasource.basicAuth.passwordFile", "", "Optional path to basic auth password to use for -datasource.url")
 
@@ -63,6 +64,7 @@ func InitSecretFlags() {
 	if !*showDatasourceURL {
 		flagutil.RegisterSecretFlag("datasource.url")
 	}
+	flagutil.RegisterSecretFlag("datasource.headers")
 }
 
 // ShowDatasourceURL whether to show -datasource.url with sensitive information
@@ -105,7 +107,7 @@ func Init(extraParams url.Values) (QuerierBuilder, error) {
 		return nil, fmt.Errorf("cannot parse JSON for -datasource.oauth2.endpointParams=%s: %w", *oauth2EndpointParams, err)
 	}
 	authCfg, err := vmalertutil.AuthConfig(
-		vmalertutil.WithBasicAuth(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile),
+		vmalertutil.WithBasicAuth(*basicAuthUsername, *basicAuthUsernameFile, *basicAuthPassword, *basicAuthPasswordFile),
 		vmalertutil.WithBearer(*bearerToken, *bearerTokenFile),
 		vmalertutil.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes, endpointParams),
 		vmalertutil.WithHeaders(*headers))

app/vmalert/notifier/alertmanager.go

@@ -191,7 +191,7 @@ func NewAlertManager(alertManagerURL string, fn AlertURLGenerator, authCfg proma
 	}
 
 	aCfg, err := vmalertutil.AuthConfig(
-		vmalertutil.WithBasicAuth(ba.Username, ba.Password.String(), ba.PasswordFile),
+		vmalertutil.WithBasicAuth(ba.Username, ba.UsernameFile, ba.Password.String(), ba.PasswordFile),
 		vmalertutil.WithBearer(authCfg.BearerToken.String(), authCfg.BearerTokenFile),
 		vmalertutil.WithOAuth(oauth.ClientID, oauth.ClientSecret.String(), oauth.ClientSecretFile, oauth.TokenURL, strings.Join(oauth.Scopes, ";"), oauth.EndpointParams),
 		vmalertutil.WithHeaders(strings.Join(authCfg.Headers, "^^")),

app/vmalert/notifier/config_watcher.go

@@ -105,7 +105,7 @@ func (cw *configWatcher) add(typeK TargetType, interval time.Duration, targetsFn
 			}
 			targetMetadata, errors := getTargetMetadata(targetsFn, cw.cfg)
 			for _, err := range errors {
-				logger.Errorf("failed to init notifier for %q: %w", typeK, err)
+				logger.Errorf("failed to init notifier for %q: %s", typeK, err)
 			}
 			cw.updateTargets(typeK, targetMetadata, cw.cfg, cw.genFn)
 		}
@@ -274,7 +274,7 @@ func (cw *configWatcher) updateTargets(key TargetType, targetMts map[string]targ
 	for addr, metadata := range targetMts {
 		am, err := NewAlertManager(addr, genFn, cfg.HTTPClientConfig, metadata.alertRelabelConfigs, cfg.Timeout.Duration())
 		if err != nil {
-			logger.Errorf("failed to init %s notifier with addr %q: %w", key, addr, err)
+			logger.Errorf("failed to init %s notifier with addr %q: %s", key, addr, err)
 			continue
 		}
 		updatedTargets = append(updatedTargets, Target{

app/vmalert/notifier/init.go

@@ -36,6 +36,7 @@ var (
 		"For example, -remoteWrite.headers='My-Auth:foobar' would send 'My-Auth: foobar' HTTP header with every request to the corresponding -notifier.url. "+
 		"Multiple headers must be delimited by '^^': -notifier.headers='header1:value1^^header2:value2,header3:value3'")
 	basicAuthUsername     = flagutil.NewArrayString("notifier.basicAuth.username", "Optional basic auth username for -notifier.url")
+	basicAuthUsernameFile = flagutil.NewArrayString("notifier.basicAuth.usernameFile", "Optional path to basic auth username file for -notifier.url")
 	basicAuthPassword     = flagutil.NewArrayString("notifier.basicAuth.password", "Optional basic auth password for -notifier.url")
 	basicAuthPasswordFile = flagutil.NewArrayString("notifier.basicAuth.passwordFile", "Optional path to basic auth password file for -notifier.url")
 
@@ -193,6 +194,7 @@ func InitSecretFlags() {
 	if !*showNotifierURL {
 		flagutil.RegisterSecretFlag("notifier.url")
 	}
+	flagutil.RegisterSecretFlag("notifier.headers")
 }
 
 func notifiersFromFlags(gen AlertURLGenerator) ([]Notifier, error) {
@@ -213,6 +215,7 @@ func notifiersFromFlags(gen AlertURLGenerator) ([]Notifier, error) {
 			},
 			BasicAuth: &promauth.BasicAuthConfig{
 				Username:     basicAuthUsername.GetOptionalArg(i),
+				UsernameFile: basicAuthUsernameFile.GetOptionalArg(i),
 				Password:     promauth.NewSecret(basicAuthPassword.GetOptionalArg(i)),
 				PasswordFile: basicAuthPasswordFile.GetOptionalArg(i),
 			},

app/vmalert/notifier/notifier.go

@@ -14,7 +14,7 @@ type Notifier interface {
 	Send(ctx context.Context, alerts []Alert, alertLabels [][]prompb.Label, notifierHeaders map[string]string) error
 	// Addr returns address where alerts are sent.
 	Addr() string
-	// LastError returns error, that occured during last attempt to send data
+	// LastError returns error, that occurred during last attempt to send data
 	LastError() string
 	// Close is a destructor for the Notifier
 	Close()

app/vmalert/remoteread/init.go

@@ -28,6 +28,7 @@ var (
 		"Multiple headers must be delimited by '^^': -remoteRead.headers='header1:value1^^header2:value2'")
 
 	basicAuthUsername     = flag.String("remoteRead.basicAuth.username", "", "Optional basic auth username for -remoteRead.url")
+	basicAuthUsernameFile = flag.String("remoteRead.basicAuth.usernameFile", "", "Optional path to basic auth username to use for -remoteRead.url")
 	basicAuthPassword     = flag.String("remoteRead.basicAuth.password", "", "Optional basic auth password for -remoteRead.url")
 	basicAuthPasswordFile = flag.String("remoteRead.basicAuth.passwordFile", "", "Optional path to basic auth password to use for -remoteRead.url")
 
@@ -58,6 +59,7 @@ func InitSecretFlags() {
 	if !*showRemoteReadURL {
 		flagutil.RegisterSecretFlag("remoteRead.url")
 	}
+	flagutil.RegisterSecretFlag("remoteRead.headers")
 }
 
 // Init creates a Querier from provided flag values.
@@ -80,7 +82,7 @@ func Init() (datasource.QuerierBuilder, error) {
 		return nil, fmt.Errorf("cannot parse JSON for -remoteRead.oauth2.endpointParams=%s: %w", *oauth2EndpointParams, err)
 	}
 	authCfg, err := vmalertutil.AuthConfig(
-		vmalertutil.WithBasicAuth(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile),
+		vmalertutil.WithBasicAuth(*basicAuthUsername, *basicAuthUsernameFile, *basicAuthPassword, *basicAuthPasswordFile),
 		vmalertutil.WithBearer(*bearerToken, *bearerTokenFile),
 		vmalertutil.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes, endpointParams),
 		vmalertutil.WithHeaders(*headers))

app/vmalert/remotewrite/client.go

@@ -11,6 +11,7 @@ import (
 	"path"
 	"strings"
 	"sync"
+	"sync/atomic"
 	"time"
 
 	"github.com/cespare/xxhash/v2"
@@ -18,6 +19,8 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/encoding"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/encoding/zstd"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
@@ -57,6 +60,11 @@ type Client struct {
 
 	wg     sync.WaitGroup
 	doneCh chan struct{}
+
+	// Whether to encode the write request with VictoriaMetrics remote write protocol.
+	// It is set to true by default, and will be switched to false if the client
+	// receives specific errors indicating that the remote storage doesn't support VictoriaMetrics remote write protocol.
+	isVMRemoteWrite atomic.Bool
 }
 
 // Config is config for remote write client.
@@ -116,6 +124,7 @@ func NewClient(ctx context.Context, cfg Config) (*Client, error) {
 		doneCh:        make(chan struct{}),
 		input:         make(chan prompb.TimeSeries, cfg.MaxQueueSize),
 	}
+	c.isVMRemoteWrite.Store(true)
 
 	for i := 0; i < cc; i++ {
 		c.wg.Go(func() {
@@ -265,8 +274,16 @@ func (c *Client) flush(ctx context.Context, wr *prompb.WriteRequest) {
 	defer wr.Reset()
 	defer bufferFlushDuration.UpdateDuration(time.Now())
 
-	data := wr.MarshalProtobuf(nil)
-	b := snappy.Encode(nil, data)
+	bb := writeRequestBufPool.Get()
+	bb.B = wr.MarshalProtobuf(bb.B[:0])
+	zb := compressBufPool.Get()
+	defer compressBufPool.Put(zb)
+	if c.isVMRemoteWrite.Load() {
+		zb.B = zstd.CompressLevel(zb.B[:0], bb.B, 0)
+	} else {
+		zb.B = snappy.Encode(zb.B[:cap(zb.B)], bb.B)
+	}
+	writeRequestBufPool.Put(bb)
 
 	maxRetryInterval := *retryMaxTime
 	bt := timeutil.NewBackoffTimer(*retryMinInterval, maxRetryInterval)
@@ -278,17 +295,17 @@ func (c *Client) flush(ctx context.Context, wr *prompb.WriteRequest) {
 	attempts := 0
 L:
 	for {
-		err := c.send(ctx, b)
+		err := c.send(ctx, zb.B)
 		if err != nil && (errors.Is(err, io.EOF) || netutil.IsTrivialNetworkError(err)) {
 			// Something in the middle between client and destination might be closing
 			// the connection. So we do a one more attempt in hope request will succeed.
-			err = c.send(ctx, b)
+			err = c.send(ctx, zb.B)
 		}
 		if err == nil {
 			sentRows.Add(len(wr.Timeseries))
-			sentBytes.Add(len(b))
+			sentBytes.Add(len(zb.B))
 			flushedRows.Update(float64(len(wr.Timeseries)))
-			flushedBytes.Update(float64(len(b)))
+			flushedBytes.Update(float64(len(zb.B)))
 			return
 		}
 
@@ -340,12 +357,16 @@ func (c *Client) send(ctx context.Context, data []byte) error {
 		return fmt.Errorf("failed to create new HTTP request: %w", err)
 	}
 
-	// RFC standard compliant headers
-	req.Header.Set("Content-Encoding", "snappy")
+	req.Header.Set("User-Agent", "vmalert")
 	req.Header.Set("Content-Type", "application/x-protobuf")
 
-	// Prometheus compliant headers
-	req.Header.Set("X-Prometheus-Remote-Write-Version", "0.1.0")
+	if encoding.IsZstd(data) {
+		req.Header.Set("Content-Encoding", "zstd")
+		req.Header.Set("X-VictoriaMetrics-Remote-Write-Version", "1")
+	} else {
+		req.Header.Set("Content-Encoding", "snappy")
+		req.Header.Set("X-Prometheus-Remote-Write-Version", "0.1.0")
+	}
 
 	if c.authCfg != nil {
 		err = c.authCfg.SetHeaders(req, true)
@@ -374,6 +395,29 @@ func (c *Client) send(ctx context.Context, data []byte) error {
 		// respond with HTTP 2xx status code when write is successful.
 		return nil
 	case 4:
+		// - Remote Write v1 specification implicitly expects a `400 Bad Request` when the encoding is not supported.
+		// - Remote Write v2 specification explicitly specifies a `415 Unsupported Media Type` for unsupported encodings.
+		// - Real-world implementations of v1 use both 400 and 415 status codes.
+		// See more in research: https://github.com/VictoriaMetrics/VictoriaMetrics/pull/8462#issuecomment-2786918054
+		if resp.StatusCode == http.StatusUnsupportedMediaType || resp.StatusCode == http.StatusBadRequest {
+			if encoding.IsZstd(data) {
+				logger.Infof("received unsupported media type or bad request from remote storage at %q. Re-packing the block to Prometheus remote write and retrying."+
+					"See https://docs.victoriametrics.com/victoriametrics/vmagent/#victoriametrics-remote-write-protocol", req.URL.Redacted())
+				zstdBlockLen := len(data)
+				data, err = repackBlockFromZstdToSnappy(data)
+				if err == nil {
+					logger.Infof("received unsupported media type or bad request from remote storage at %q. Downgrading protocol from VictoriaMetrics to Prometheus remote write for all future requests. "+
+						"See https://docs.victoriametrics.com/victoriametrics/vmagent/#victoriametrics-remote-write-protocol", req.URL.Redacted())
+					c.isVMRemoteWrite.Store(false)
+					return c.send(ctx, data)
+				}
+
+				logger.Warnf("failed to repack zstd block (%d bytes) to snappy: %s; The block will be rejected. "+
+					"Possible cause: ungraceful shutdown leading to persisted queue corruption.",
+					zstdBlockLen, err)
+			}
+		}
+
 		if resp.StatusCode != http.StatusTooManyRequests {
 			// MUST NOT retry write requests on HTTP 4xx responses other than 429
 			return &nonRetriableError{
@@ -394,3 +438,19 @@ type nonRetriableError struct {
 func (e *nonRetriableError) Error() string {
 	return e.err.Error()
 }
+
+var (
+	writeRequestBufPool bytesutil.ByteBufferPool
+	compressBufPool     bytesutil.ByteBufferPool
+)
+
+// repackBlockFromZstdToSnappy repacks the given zstd-compressed block to snappy-compressed block.
+func repackBlockFromZstdToSnappy(zstdBlock []byte) ([]byte, error) {
+	plainBlock := make([]byte, 0, len(zstdBlock)*2)
+	plainBlock, err := encoding.DecompressZSTD(plainBlock, zstdBlock)
+	if err != nil {
+		return nil, err
+	}
+
+	return snappy.Encode(nil, plainBlock), nil
+}

app/vmalert/remotewrite/client_test.go

@@ -12,8 +12,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/golang/snappy"
-
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/encoding/zstd"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
 )
 
@@ -103,7 +102,10 @@ func TestClient_run_maxBatchSizeDuringShutdown(t *testing.T) {
 
 		// push time series to the client.
 		for range pushCnt {
-			if err = rwClient.Push(prompb.TimeSeries{}); err != nil {
+			if err = rwClient.Push(prompb.TimeSeries{
+				Labels:  []prompb.Label{{Name: "__name__", Value: "m"}},
+				Samples: []prompb.Sample{{Value: 1, Timestamp: 1000}},
+			}); err != nil {
 				t.Fatalf("cannot time series to the client: %s", err)
 			}
 		}
@@ -156,8 +158,8 @@ func (rw *rwServer) handler(w http.ResponseWriter, r *http.Request) {
 	}
 
 	h := r.Header.Get("Content-Encoding")
-	if h != "snappy" {
-		rw.err(w, fmt.Errorf("header read error: Content-Encoding is not snappy (%q)", h))
+	if h != "zstd" {
+		rw.err(w, fmt.Errorf("header read error: Content-Encoding is not zstd (%q)", h))
 	}
 
 	h = r.Header.Get("Content-Type")
@@ -165,9 +167,9 @@ func (rw *rwServer) handler(w http.ResponseWriter, r *http.Request) {
 		rw.err(w, fmt.Errorf("header read error: Content-Type is not x-protobuf (%q)", h))
 	}
 
-	h = r.Header.Get("X-Prometheus-Remote-Write-Version")
-	if h != "0.1.0" {
-		rw.err(w, fmt.Errorf("header read error: X-Prometheus-Remote-Write-Version is not 0.1.0 (%q)", h))
+	h = r.Header.Get("X-VictoriaMetrics-Remote-Write-Version")
+	if h != "1" {
+		rw.err(w, fmt.Errorf("header read error: X-VictoriaMetrics-Remote-Write-Version is not 1 (%q)", h))
 	}
 
 	data, err := io.ReadAll(r.Body)
@@ -177,7 +179,7 @@ func (rw *rwServer) handler(w http.ResponseWriter, r *http.Request) {
 	}
 	defer func() { _ = r.Body.Close() }()
 
-	b, err := snappy.Decode(nil, data)
+	b, err := zstd.Decompress(nil, data)
 	if err != nil {
 		rw.err(w, fmt.Errorf("decode err: %w", err))
 		return

app/vmalert/remotewrite/debug_client.go

@@ -9,8 +9,7 @@ import (
 	"strings"
 	"sync"
 
-	"github.com/golang/snappy"
-
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/encoding/zstd"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
@@ -64,19 +63,17 @@ func (c *DebugClient) Close() error {
 }
 
 func (c *DebugClient) send(data []byte) error {
-	b := snappy.Encode(nil, data)
+	b := zstd.CompressLevel(nil, data, 0)
 	r := bytes.NewReader(b)
 	req, err := http.NewRequest(http.MethodPost, c.addr, r)
 	if err != nil {
 		return fmt.Errorf("failed to create new HTTP request: %w", err)
 	}
 
-	// RFC standard compliant headers
-	req.Header.Set("Content-Encoding", "snappy")
+	req.Header.Set("Content-Encoding", "zstd")
 	req.Header.Set("Content-Type", "application/x-protobuf")
 
-	// Prometheus compliant headers
-	req.Header.Set("X-Prometheus-Remote-Write-Version", "0.1.0")
+	req.Header.Set("X-VictoriaMetrics-Remote-Write-Version", "1")
 
 	if !*disablePathAppend {
 		req.URL.Path = path.Join(req.URL.Path, "/api/v1/write")

app/vmalert/remotewrite/init.go

@@ -13,8 +13,8 @@ import (
 )
 
 var (
-	addr = flag.String("remoteWrite.url", "", "Optional URL to VictoriaMetrics or vminsert where to persist alerts state "+
-		"and recording rules results in form of timeseries. "+
+	addr = flag.String("remoteWrite.url", "", "Optional URL to persist alerts state and recording rules results in form of timeseries. "+
+		"It must support either VictoriaMetrics remote write protocol or Prometheus remote_write protocol. "+
 		"Supports address in the form of IP address with a port (e.g., http://127.0.0.1:8428) or DNS SRV record. "+
 		"For example, if -remoteWrite.url=http://127.0.0.1:8428 is specified, "+
 		"then the alerts state will be written to http://127.0.0.1:8428/api/v1/write . See also -remoteWrite.disablePathAppend, '-remoteWrite.showURL'.")
@@ -26,6 +26,7 @@ var (
 		"Multiple headers must be delimited by '^^': -remoteWrite.headers='header1:value1^^header2:value2'")
 
 	basicAuthUsername     = flag.String("remoteWrite.basicAuth.username", "", "Optional basic auth username for -remoteWrite.url")
+	basicAuthUsernameFile = flag.String("remoteWrite.basicAuth.usernameFile", "", "Optional path to basic auth username to use for -remoteWrite.url")
 	basicAuthPassword     = flag.String("remoteWrite.basicAuth.password", "", "Optional basic auth password for -remoteWrite.url")
 	basicAuthPasswordFile = flag.String("remoteWrite.basicAuth.passwordFile", "", "Optional path to basic auth password to use for -remoteWrite.url")
 
@@ -61,6 +62,7 @@ func InitSecretFlags() {
 	if !*showRemoteWriteURL {
 		flagutil.RegisterSecretFlag("remoteWrite.url")
 	}
+	flagutil.RegisterSecretFlag("remoteWrite.headers")
 }
 
 // Init creates Client object from given flags.
@@ -83,7 +85,7 @@ func Init(ctx context.Context) (*Client, error) {
 		return nil, fmt.Errorf("cannot parse JSON for -remoteWrite.oauth2.endpointParams=%s: %w", *oauth2EndpointParams, err)
 	}
 	authCfg, err := vmalertutil.AuthConfig(
-		vmalertutil.WithBasicAuth(*basicAuthUsername, *basicAuthPassword, *basicAuthPasswordFile),
+		vmalertutil.WithBasicAuth(*basicAuthUsername, *basicAuthUsernameFile, *basicAuthPassword, *basicAuthPasswordFile),
 		vmalertutil.WithBearer(*bearerToken, *bearerTokenFile),
 		vmalertutil.WithOAuth(*oauth2ClientID, *oauth2ClientSecret, *oauth2ClientSecretFile, *oauth2TokenURL, *oauth2Scopes, endpointParams),
 		vmalertutil.WithHeaders(*headers))

app/vmalert/rule/group.go

@@ -8,6 +8,7 @@ import (
 	"hash/fnv"
 	"maps"
 	"net/url"
+	"path"
 	"sync"
 	"time"
 
@@ -42,6 +43,9 @@ var (
 		"For example, if lookback=1h then range from now() to now()-1h will be scanned.")
 	maxStartDelay = flag.Duration("group.maxStartDelay", 5*time.Minute, "Defines the max delay before starting the group evaluation. Group's start is artificially delayed for random duration on interval"+
 		" [0..min(--group.maxStartDelay, group.interval)]. This helps smoothing out the load on the configured datasource, so evaluations aren't executed too close to each other.")
+	ruleStripFilePath = flag.Bool("rule.stripFilePath", false, "Whether to strip rule file paths in logs and all API responses, including /metrics. "+
+		"For example, file path '/path/to/tenant_id/rules.yml' will be stripped to 'groupHashID/rules.yml'. "+
+		"This flag may be useful for hiding sensitive information in file paths, such as S3 bucket details.")
 )
 
 // Group is an entity for grouping rules
@@ -147,6 +151,12 @@ func NewGroup(cfg config.Group, qb datasource.QuerierBuilder, defaultInterval ti
 		g.EvalDelay = &cfg.EvalDelay.D
 	}
 	g.id = g.CreateID()
+	// strip file path from group.File after generated group ID when ruleStripFilePath is set,
+	// so it won't be exposed in logs and api responses
+	if *ruleStripFilePath {
+		_, filename := path.Split(g.File)
+		g.File = fmt.Sprintf("%d/%s", g.id, filename)
+	}
 	for _, h := range cfg.Headers {
 		g.Headers[h.Key] = h.Value
 	}

app/vmalert/rule/group_test.go

@@ -742,3 +742,64 @@ func parseTime(t *testing.T, s string) time.Time {
 	}
 	return tt
 }
+
+func TestRuleStripFilePath(t *testing.T) {
+	configG := config.Group{
+		Name:        "group",
+		File:        "/var/local/test/rules.yaml",
+		Type:        config.NewRawType("prometheus"),
+		Concurrency: 1,
+		Rules: []config.Rule{
+			{
+				ID:    0,
+				Alert: "alert",
+			},
+			{
+				ID:     1,
+				Record: "record",
+			},
+		}}
+	qb := &datasource.FakeQuerier{}
+	g := NewGroup(configG, qb, 1*time.Minute, nil)
+
+	gID := g.id
+	if g.File != "/var/local/test/rules.yaml" {
+		t.Fatalf("expected file path to be unchanged; got %q instead", g.File)
+	}
+
+	for _, r := range g.Rules {
+		if ar, ok := r.(*AlertingRule); ok {
+			if ar.File != "/var/local/test/rules.yaml" {
+				t.Fatalf("expected rule file path to be unchanged; got %q instead", ar.File)
+			}
+		}
+		if rr, ok := r.(*RecordingRule); ok {
+			if rr.File != "/var/local/test/rules.yaml" {
+				t.Fatalf("expected rule file path to be unchanged; got %q instead", rr.File)
+			}
+		}
+	}
+
+	oldRuleStripFilePath := *ruleStripFilePath
+	*ruleStripFilePath = true
+	defer func() {
+		*ruleStripFilePath = oldRuleStripFilePath
+	}()
+	g = NewGroup(configG, qb, 1*time.Minute, nil)
+
+	if g.File != fmt.Sprintf("%d/rules.yaml", gID) {
+		t.Fatalf("expected file path to be stripped to %q; got %q instead", fmt.Sprintf("%d/rules.yaml", gID), g.File)
+	}
+	for _, r := range g.Rules {
+		if ar, ok := r.(*AlertingRule); ok {
+			if ar.File != fmt.Sprintf("%d/rules.yaml", gID) {
+				t.Fatalf("expected rule file path to be unchanged; got %q instead", ar.File)
+			}
+		}
+		if rr, ok := r.(*RecordingRule); ok {
+			if rr.File != fmt.Sprintf("%d/rules.yaml", gID) {
+				t.Fatalf("expected rule file path to be unchanged; got %q instead", rr.File)
+			}
+		}
+	}
+}

app/vmalert/rule/web.go

@@ -252,6 +252,9 @@ func (r *ApiRule) ExtendState() {
 
 // ToAPI returns ApiGroup representation of g
 func (g *Group) ToAPI() *ApiGroup {
+	if g == nil {
+		return &ApiGroup{}
+	}
 	g.mu.RLock()
 	defer g.mu.RUnlock()
 	ag := ApiGroup{

app/vmalert/templates/template.go

@@ -402,6 +402,20 @@ func templateFuncs() textTpl.FuncMap {
 			return t, nil
 		},
 
+		// formatTime formats the given Unix timestamp with the provided layout.
+		// For example: {{ now | formatTime "2006-01-02T15:04:05Z07:00" }}
+		"formatTime": func(layout string, i any) (string, error) {
+			v, err := toFloat64(i)
+			if err != nil {
+				return "", fmt.Errorf("formatTime: %w", err)
+			}
+			if math.IsNaN(v) || math.IsInf(v, 0) {
+				return "", fmt.Errorf("formatTime: cannot convert %v to time", v)
+			}
+			t := timeFromUnixTimestamp(v).Time().UTC()
+			return t.Format(layout), nil
+		},
+
 		/* URLs */
 
 		// externalURL returns value of `external.url` flag

app/vmalert/templates/template_test.go

@@ -6,6 +6,7 @@ import (
 	"strings"
 	"testing"
 	textTpl "text/template"
+	"time"
 )
 
 func TestTemplateFuncs_StringConversion(t *testing.T) {
@@ -103,6 +104,26 @@ func TestTemplateFuncs_Formatting(t *testing.T) {
 	f("humanizeTimestamp", 1679055557, "2023-03-17 12:19:17 +0000 UTC")
 }
 
+func TestTemplateFuncs_FormatTime(t *testing.T) {
+	funcs := templateFuncs()
+	formatTime := funcs["formatTime"].(func(layout string, i any) (string, error))
+
+	f := func(layout string, input any, expected string) {
+		t.Helper()
+		result, err := formatTime(layout, input)
+		if err != nil {
+			t.Fatalf("unexpected error for formatTime(%q, %v): %s", layout, input, err)
+		}
+		if result != expected {
+			t.Fatalf("unexpected result for formatTime(%q, %v); got\n%s\nwant\n%s", layout, input, result, expected)
+		}
+	}
+
+	f(time.RFC3339, float64(1679055557), "2023-03-17T12:19:17Z")
+	f("2006-01-02T15:04:05", int64(1679055557), "2023-03-17T12:19:17")
+	f(time.RFC822, int(1679055557), "17 Mar 23 12:19 UTC")
+}
+
 func mkTemplate(current, replacement any) textTemplate {
 	tmpl := textTemplate{}
 	if current != nil {

app/vmalert/vmalertutil/auth.go

@@ -20,11 +20,12 @@ func AuthConfig(filterOptions ...AuthConfigOptions) (*promauth.Config, error) {
 }
 
 // WithBasicAuth returns AuthConfigOptions and initialized promauth.BasicAuthConfig based on given params
-func WithBasicAuth(username, password, passwordFile string) AuthConfigOptions {
+func WithBasicAuth(username, usernameFile, password, passwordFile string) AuthConfigOptions {
 	return func(config *promauth.HTTPClientConfig) {
-		if username != "" || password != "" || passwordFile != "" {
+		if username != "" || usernameFile != "" || password != "" || passwordFile != "" {
 			config.BasicAuth = &promauth.BasicAuthConfig{
 				Username:     username,
+				UsernameFile: usernameFile,
 				Password:     promauth.NewSecret(password),
 				PasswordFile: passwordFile,
 			}

app/vmauth/auth_config.go

@@ -610,6 +610,7 @@ func areEqualBackendURLs(a, b []*backendURL) bool {
 }
 
 // getFirstAvailableBackendURL returns the first available backendURL, which isn't broken.
+// If all backendURLs are broken, then returns the first backendURL.
 //
 // backendURL.put() must be called on the returned backendURL after the request is complete.
 func getFirstAvailableBackendURL(bus []*backendURL) *backendURL {
@@ -628,21 +629,22 @@ func getFirstAvailableBackendURL(bus []*backendURL) *backendURL {
 			return bu
 		}
 	}
-	return nil
+
+	// All backend urls are unavailable, then returning a first one, it could help increase the success rate of the requests。
+	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10837#issuecomment-4307050980.
+	bu.get()
+	return bu
 }
 
 // getLeastLoadedBackendURL returns a non-broken backendURL with the lowest number of concurrent requests.
+// If all backendURLs are broken, then returns the first backendURL.
 //
 // backendURL.put() must be called on the returned backendURL after the request is complete.
 func getLeastLoadedBackendURL(bus []*backendURL, atomicCounter *atomic.Uint32) *backendURL {
+	firstBu := bus[0]
 	if len(bus) == 1 {
-		// Fast path - return the only backend url.
-		bu := bus[0]
-		if bu.isBroken() {
-			return nil
-		}
-		bu.get()
-		return bu
+		firstBu.get()
+		return firstBu
 	}
 
 	// Slow path - select other backend urls.
@@ -680,7 +682,10 @@ func getLeastLoadedBackendURL(bus []*backendURL, atomicCounter *atomic.Uint32) *
 	}
 	buMin := bus[buMinIdx]
 	if buMin.isBroken() {
-		return nil
+		// If all backendURLs are broken, then returns the first backendURL.
+		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10837#issuecomment-4307050980.
+		firstBu.get()
+		return firstBu
 	}
 	buMin.get()
 	atomicCounter.CompareAndSwap(n+1, buMinIdx+1)

app/vmauth/auth_config_test.go

@@ -1031,6 +1031,33 @@ func TestLogRequest(t *testing.T) {
 	f("foo", 404, 10*time.Millisecond, `access_log request_host="localhost:8080" request_uri="" status_code=404 remote_addr="" user_agent="" referer="" duration_ms=10 username="foo"`)
 }
 
+func TestGetFirstAvailableBackend(t *testing.T) {
+	f := func(broken []bool, expectedIdx int) {
+		t.Helper()
+		bus := make([]*backendURL, len(broken))
+		for i := range broken {
+			bus[i] = &backendURL{
+				url: &url.URL{Host: fmt.Sprintf("server-%d", i)},
+			}
+			bus[i].broken.Store(broken[i])
+		}
+		bu := getFirstAvailableBackendURL(bus)
+		if bu == nil {
+			t.Fatalf("unexpected nil backend")
+		}
+		if bu.url.Host != fmt.Sprintf("server-%d", expectedIdx) {
+			t.Fatalf("unexpected backend, expected server-%d, got %s", expectedIdx, bu.url.Host)
+		}
+	}
+
+	f([]bool{false, false, false}, 0)
+	f([]bool{true, true, false}, 2)
+	// all backend are broken, then return the first one.
+	f([]bool{true, true, true}, 0)
+	f([]bool{true}, 0)
+
+}
+
 func getRegexs(paths []string) []*Regex {
 	var sps []*Regex
 	for _, path := range paths {

app/vmauth/main.go

@@ -51,7 +51,7 @@ var (
 		"This allows reducing the consumption of backend resources when processing requests from clients connected via slow networks. "+
 		"Set to 0 to disable request buffering. See https://docs.victoriametrics.com/victoriametrics/vmauth/#request-body-buffering")
 	maxRequestBodySizeToRetry = flagutil.NewBytes("maxRequestBodySizeToRetry", 16*1024, "The maximum request body size to buffer in memory for potential retries at other backends. "+
-		"Request bodies larger than this size cannot be retried if the backend fails. Zero or negative value disables request body buffering and retries. "+
+		"Request bodies larger than this size cannot be retried if the backend fails. Zero or negative value disables retries. "+
 		"See also -requestBufferSize")
 
 	maxConcurrentRequests = flag.Int("maxConcurrentRequests", 1000, "The maximum number of concurrent requests vmauth can process simultaneously. "+
@@ -850,14 +850,18 @@ func (bb *bufferedBody) Read(p []byte) (int, error) {
 }
 
 func (bb *bufferedBody) canRetry() bool {
-	return bb.r == nil
+	if bb.r != nil {
+		return false
+	}
+	maxRetrySize := maxRequestBodySizeToRetry.IntN()
+	return len(bb.buf) == 0 || (maxRetrySize > 0 && len(bb.buf) <= maxRetrySize)
 }
 
 // Close implements io.Closer interface.
 func (bb *bufferedBody) Close() error {
 	bb.resetReader()
+	bb.cannotRetry = !bb.canRetry()
 	if bb.r != nil {
-		bb.cannotRetry = true
 		return bb.r.Close()
 	}
 	return nil

app/vmauth/main_test.go

@@ -19,6 +19,7 @@ import (
 	"os"
 	"path/filepath"
 	"sort"
+	"strconv"
 	"strings"
 	"sync/atomic"
 	"testing"
@@ -1831,7 +1832,7 @@ func (r *mockBody) Read(p []byte) (n int, err error) {
 }
 
 func TestBufferedBody_RetrySuccess(t *testing.T) {
-	f := func(s string, maxBodySize int) {
+	f := func(s string, maxSizeToRetry, bufferSize int) {
 		t.Helper()
 
 		defaultRequestBufferSize := requestBufferSize.String()
@@ -1840,7 +1841,7 @@ func TestBufferedBody_RetrySuccess(t *testing.T) {
 				t.Fatalf("cannot reset requestBufferSize: %s", err)
 			}
 		}()
-		if err := requestBufferSize.Set(fmt.Sprintf("%d", maxBodySize)); err != nil {
+		if err := requestBufferSize.Set(strconv.Itoa(bufferSize)); err != nil {
 			t.Fatalf("cannot set requestBufferSize: %s", err)
 		}
 
@@ -1850,7 +1851,7 @@ func TestBufferedBody_RetrySuccess(t *testing.T) {
 				t.Fatalf("cannot reset maxRequestBodySizeToRetry: %s", err)
 			}
 		}()
-		if err := maxRequestBodySizeToRetry.Set("0"); err != nil {
+		if err := maxRequestBodySizeToRetry.Set(strconv.Itoa(maxSizeToRetry)); err != nil {
 			t.Fatalf("cannot set maxRequestBodySizeToRetry: %s", err)
 		}
 
@@ -1879,16 +1880,20 @@ func TestBufferedBody_RetrySuccess(t *testing.T) {
 		}
 	}
 
-	f("", 0)
-	f("", -1)
-	f("", 100)
-	f("foo", 100)
-	f("foobar", 100)
-	f(newTestString(1000), 1001)
+	f("", 0, 2000)
+	f("", 0, 0)
+	f("", -1, 2000)
+	f("", 100, 2000)
+	f("foo", 100, 2000)
+	f("foobar", 100, 2000)
+	f("foobar", 100, 0)
+	f("foobar", 100, -1)
+	f(newTestString(1000), 1001, 2000)
+	f(newTestString(1000), 1001, 500)
 }
 
 func TestBufferedBody_RetrySuccessPartialRead(t *testing.T) {
-	f := func(s string, maxBodySize int) {
+	f := func(s string, maxSizeToRetry, bufferSize int) {
 		t.Helper()
 
 		// Check the case with partial read
@@ -1898,7 +1903,7 @@ func TestBufferedBody_RetrySuccessPartialRead(t *testing.T) {
 				t.Fatalf("cannot reset requestBufferSize: %s", err)
 			}
 		}()
-		if err := requestBufferSize.Set(fmt.Sprintf("%d", maxBodySize)); err != nil {
+		if err := requestBufferSize.Set(strconv.Itoa(bufferSize)); err != nil {
 			t.Fatalf("cannot set requestBufferSize: %s", err)
 		}
 
@@ -1908,7 +1913,7 @@ func TestBufferedBody_RetrySuccessPartialRead(t *testing.T) {
 				t.Fatalf("cannot reset maxRequestBodySizeToRetry: %s", err)
 			}
 		}()
-		if err := maxRequestBodySizeToRetry.Set("0"); err != nil {
+		if err := maxRequestBodySizeToRetry.Set(strconv.Itoa(maxSizeToRetry)); err != nil {
 			t.Fatalf("cannot set maxRequestBodySizeToRetry: %s", err)
 		}
 
@@ -1952,16 +1957,20 @@ func TestBufferedBody_RetrySuccessPartialRead(t *testing.T) {
 		}
 	}
 
-	f("", 0)
-	f("", -1)
-	f("", 100)
-	f("foo", 100)
-	f("foobar", 100)
-	f(newTestString(1000), 1001)
+	f("", 0, 2000)
+	f("", 0, 0)
+	f("", -1, 2000)
+	f("", 100, 2000)
+	f("foo", 100, 2000)
+	f("foobar", 100, 2000)
+	f("foobar", 100, 0)
+	f("foobar", 100, -1)
+	f(newTestString(1000), 1001, 2000)
+	f(newTestString(1000), 1001, 500)
 }
 
 func TestBufferedBody_RetryFailureTooBigBody(t *testing.T) {
-	f := func(s string, maxBodySize int) {
+	f := func(s string, maxSizeToRetry, bufferSize int) {
 		t.Helper()
 
 		defaultRequestBufferSize := requestBufferSize.String()
@@ -1970,7 +1979,7 @@ func TestBufferedBody_RetryFailureTooBigBody(t *testing.T) {
 				t.Fatalf("cannot reset requestBufferSize: %s", err)
 			}
 		}()
-		if err := requestBufferSize.Set("0"); err != nil {
+		if err := requestBufferSize.Set(strconv.Itoa(bufferSize)); err != nil {
 			t.Fatalf("cannot set requestBufferSize: %s", err)
 		}
 
@@ -1980,7 +1989,7 @@ func TestBufferedBody_RetryFailureTooBigBody(t *testing.T) {
 				t.Fatalf("cannot reset maxRequestBodySizeToRetry: %s", err)
 			}
 		}()
-		if err := maxRequestBodySizeToRetry.Set(fmt.Sprintf("%d", maxBodySize)); err != nil {
+		if err := maxRequestBodySizeToRetry.Set(strconv.Itoa(maxSizeToRetry)); err != nil {
 			t.Fatalf("cannot set maxRequestBodySizeToRetry: %s", err)
 		}
 
@@ -2025,12 +2034,17 @@ func TestBufferedBody_RetryFailureTooBigBody(t *testing.T) {
 	}
 
 	const maxBodySize = 1000
-	f(newTestString(maxBodySize+1), maxBodySize)
-	f(newTestString(2*maxBodySize), maxBodySize)
+	f(newTestString(maxBodySize+1), 0, 2*maxBodySize)
+	f(newTestString(maxBodySize+1), -1, 2*maxBodySize)
+	f(newTestString(maxBodySize+1), maxBodySize, 0)
+	f(newTestString(maxBodySize+1), maxBodySize, -1)
+	f(newTestString(maxBodySize+1), maxBodySize, maxBodySize)
+	f(newTestString(maxBodySize+1), maxBodySize, 2*maxBodySize)
+	f(newTestString(2*maxBodySize), maxBodySize, 0)
 }
 
-func TestBufferedBody_RetryFailureZeroOrNegativeMaxBodySize(t *testing.T) {
-	f := func(s string, maxBodySize int) {
+func TestBufferedBody_RetryDisabledByMaxRequestBodySizeToRetry(t *testing.T) {
+	f := func(s string, maxSizeToRetry, bufferSize int) {
 		t.Helper()
 
 		defaultRequestBufferSize := requestBufferSize.String()
@@ -2039,10 +2053,20 @@ func TestBufferedBody_RetryFailureZeroOrNegativeMaxBodySize(t *testing.T) {
 				t.Fatalf("cannot reset requestBufferSize: %s", err)
 			}
 		}()
-		if err := requestBufferSize.Set(fmt.Sprintf("%d", maxBodySize)); err != nil {
+		if err := requestBufferSize.Set(strconv.Itoa(bufferSize)); err != nil {
 			t.Fatalf("cannot set requestBufferSize: %s", err)
 		}
 
+		defaultMaxRequestBodySizeToRetry := maxRequestBodySizeToRetry.String()
+		defer func() {
+			if err := maxRequestBodySizeToRetry.Set(defaultMaxRequestBodySizeToRetry); err != nil {
+				t.Fatalf("cannot reset maxRequestBodySizeToRetry: %s", err)
+			}
+		}()
+		if err := maxRequestBodySizeToRetry.Set(strconv.Itoa(maxSizeToRetry)); err != nil {
+			t.Fatalf("cannot set maxRequestBodySizeToRetry: %s", err)
+		}
+
 		ctx := context.Background()
 		rb, err := bufferRequestBody(ctx, io.NopCloser(bytes.NewBufferString(s)), "foo")
 		if err != nil {
@@ -2051,8 +2075,8 @@ func TestBufferedBody_RetryFailureZeroOrNegativeMaxBodySize(t *testing.T) {
 		bb, ok := rb.(*bufferedBody)
 		canRetry := !ok || bb.canRetry()
 
-		if !canRetry {
-			t.Fatalf("canRetry() must return true before reading anything")
+		if canRetry {
+			t.Fatalf("canRetry() must return false before reading anything")
 		}
 		data, err := io.ReadAll(rb)
 		if err != nil {
@@ -2066,19 +2090,19 @@ func TestBufferedBody_RetryFailureZeroOrNegativeMaxBodySize(t *testing.T) {
 		}
 
 		data, err = io.ReadAll(rb)
-		if err != nil {
-			t.Fatalf("unexpected error in io.ReadAll: %s", err)
+		if err == nil {
+			t.Fatalf("expecting non-nil error")
 		}
-		if string(data) != s {
-			t.Fatalf("unexpected data read\ngot\n%s\nwant\n%s", data, s)
+		if len(data) != 0 {
+			t.Fatalf("unexpected non-empty data read: %q", data)
 		}
 	}
 
-	f("foobar", 0)
-	f(newTestString(1000), 0)
+	f("foobar", 0, 2048)
+	f(newTestString(1000), 0, 2048)
 
-	f("foobar", -1)
-	f(newTestString(1000), -1)
+	f("foobar", -1, 2048)
+	f(newTestString(1000), -1, 2048)
 }
 
 func newTestString(sLen int) string {

app/vmselect/main.go

@@ -69,6 +69,8 @@ func Init() {
 	concurrencyLimitCh = make(chan struct{}, *maxConcurrentRequests)
 	initVMUIConfig()
 	initVMAlertProxy()
+
+	flagutil.RegisterSecretFlag("vmalert.proxyURL")
 }
 
 // Stop stops vmselect
@@ -262,6 +264,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		return true
 	case "/api/v1/export":
 		exportRequests.Inc()
+		httpserver.EnableCORS(w, r)
 		if err := prometheus.ExportHandler(startTime, w, r); err != nil {
 			exportErrors.Inc()
 			httpserver.Errorf(w, r, "%s", err)
@@ -270,6 +273,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		return true
 	case "/api/v1/export/csv":
 		exportCSVRequests.Inc()
+		httpserver.EnableCORS(w, r)
 		if err := prometheus.ExportCSVHandler(startTime, w, r); err != nil {
 			exportCSVErrors.Inc()
 			httpserver.Errorf(w, r, "%s", err)
@@ -278,6 +282,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		return true
 	case "/api/v1/export/native":
 		exportNativeRequests.Inc()
+		httpserver.EnableCORS(w, r)
 		if err := prometheus.ExportNativeHandler(startTime, w, r); err != nil {
 			exportNativeErrors.Inc()
 			httpserver.Errorf(w, r, "%s", err)

app/vmselect/searchutil/searchutil.go

@@ -132,9 +132,20 @@ func (d *Deadline) String() string {
 //
 //	{env="prod",team="devops",t1="v1",t2="v2"}
 //	{env=~"dev|staging",team!="devops",t1="v1",t2="v2"}
+//
+//	Query args from URL path have precedence over post form args.
 func GetExtraTagFilters(r *http.Request) ([][]storage.TagFilter, error) {
 	var tagFilters []storage.TagFilter
-	for _, match := range r.Form["extra_label"] {
+	urlQueryValues := r.URL.Query()
+	getRequestParam := func(key string) []string {
+		// query request param must always take precedence over form values
+		// in order to simplify security enforcement policy for extra_label and extra_filters
+		if uv, ok := urlQueryValues[key]; ok {
+			return uv
+		}
+		return r.Form[key]
+	}
+	for _, match := range getRequestParam("extra_label") {
 		tmp := strings.SplitN(match, "=", 2)
 		if len(tmp) != 2 {
 			return nil, fmt.Errorf("`extra_label` query arg must have the format `name=value`; got %q", match)
@@ -148,8 +159,8 @@ func GetExtraTagFilters(r *http.Request) ([][]storage.TagFilter, error) {
 			Value: []byte(tmp[1]),
 		})
 	}
-	extraFilters := append([]string{}, r.Form["extra_filters"]...)
-	extraFilters = append(extraFilters, r.Form["extra_filters[]"]...)
+	extraFilters := append([]string{}, getRequestParam("extra_filters")...)
+	extraFilters = append(extraFilters, getRequestParam("extra_filters[]")...)
 	if len(extraFilters) == 0 {
 		if len(tagFilters) == 0 {
 			return nil, nil

app/vmselect/searchutil/searchutil_test.go

@@ -20,6 +20,7 @@ func TestGetExtraTagFilters(t *testing.T) {
 		}
 		return &http.Request{
 			Form: q,
+			URL:  &url.URL{RawQuery: q.Encode()},
 		}
 	}
 	f := func(t *testing.T, r *http.Request, want []string, wantErr bool) {
@@ -79,6 +80,24 @@ func TestGetExtraTagFilters(t *testing.T) {
 		nil,
 		false,
 	)
+
+	formValues, err := url.ParseQuery(`extra_label=env=prod&extra_label=job=vmsingle&extra_label=tenant=prod&extra_filters[]={foo="bar"}&extra_filters[]={tenant="prod"}`)
+	if err != nil {
+		t.Fatalf("BUG: cannot parse query: %s", err)
+	}
+	urlValues, err := url.ParseQuery(`extra_label=job=vmagent&extra_label=env=dev&extra_filters[]={tenant="dev"}`)
+	if err != nil {
+		t.Fatalf("BUG: cannot parse query: %s", err)
+	}
+	httpReqWithBothFormAndURLParams := &http.Request{
+		Form: formValues,
+		URL: &url.URL{
+			RawQuery: urlValues.Encode(),
+		},
+	}
+	f(t, httpReqWithBothFormAndURLParams,
+		[]string{`{tenant="dev",job="vmagent",env="dev"}`},
+		false)
 }
 
 func TestParseMetricSelectorSuccess(t *testing.T) {

app/vmselect/vmui/index.html

@@ -37,9 +37,9 @@
   <meta property="og:title" content="UI for VictoriaMetrics">
   <meta property="og:url" content="https://victoriametrics.com/">
   <meta property="og:description" content="Explore and troubleshoot your VictoriaMetrics data">
-  <script type="module" crossorigin src="./assets/index-fsxQMWD9.js"></script>
+  <script type="module" crossorigin src="./assets/index-C7gvW_Zn.js"></script>
   <link rel="modulepreload" crossorigin href="./assets/rolldown-runtime-COnpUsM8.js">
-  <link rel="modulepreload" crossorigin href="./assets/vendor-BF3F25aG.js">
+  <link rel="modulepreload" crossorigin href="./assets/vendor-C8Kwp93_.js">
   <link rel="stylesheet" crossorigin href="./assets/vendor-CnsZ1jie.css">
   <link rel="stylesheet" crossorigin href="./assets/index-D2OEy8Ra.css">
 </head>

app/vmstorage/main.go

@@ -180,6 +180,7 @@ func Init(resetCacheIfNeeded func(mrs []storage.MetricRow)) {
 		writeStorageMetrics(w, strg)
 	})
 	metrics.RegisterSet(storageMetrics)
+	fs.RegisterPathFsMetrics(*DataPath)
 }
 
 var storageMetrics *metrics.Set

app/vmui/Dockerfile-web

@@ -1,4 +1,4 @@
-FROM golang:1.26.2 AS build-web-stage
+FROM golang:1.26.3 AS build-web-stage
 COPY build /build
 
 WORKDIR /build

app/vmui/packages/vmui/package-lock.json

@@ -11,7 +11,7 @@
         "classnames": "^2.5.1",
         "dayjs": "^1.11.20",
         "lodash.debounce": "^4.0.8",
-        "marked": "^18.0.0",
+        "marked": "^18.0.2",
         "preact": "^10.29.1",
         "qs": "^6.15.1",
         "react-input-mask": "^2.0.4",
@@ -1394,9 +1394,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -1413,9 +1410,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": [
-        "musl"
-      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -1432,9 +1426,6 @@
       "cpu": [
         "ppc64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -1451,9 +1442,6 @@
       "cpu": [
         "s390x"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -1470,9 +1458,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -1489,9 +1474,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "musl"
-      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -5153,9 +5135,9 @@
       }
     },
     "node_modules/marked": {
-      "version": "18.0.0",
-      "resolved": "https://registry.npmjs.org/marked/-/marked-18.0.0.tgz",
-      "integrity": "sha512-2e7Qiv/HJSXj8rDEpgTvGKsP8yYtI9xXHKDnrftrmnrJPaFNM7VRb2YCzWaX4BP1iCJ/XPduzDJZMFoqTCcIMA==",
+      "version": "18.0.2",
+      "resolved": "https://registry.npmjs.org/marked/-/marked-18.0.2.tgz",
+      "integrity": "sha512-NsmlUYBS/Zg57rgDWMYdnre6OTj4e+qq/JS2ot3KrYLSoHLw+sDu0Nm1ZGpRgYAq6c+b1ekaY5NzVchMCQnzcg==",
       "license": "MIT",
       "bin": {
         "marked": "bin/marked.js"
@@ -6215,7 +6197,6 @@
       "cpu": [
         "arm"
       ],
-      "libc": "glibc",
       "license": "MIT",
       "optional": true,
       "os": [
@@ -6232,7 +6213,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": "glibc",
       "license": "MIT",
       "optional": true,
       "os": [
@@ -6249,7 +6229,6 @@
       "cpu": [
         "arm"
       ],
-      "libc": "musl",
       "license": "MIT",
       "optional": true,
       "os": [
@@ -6266,7 +6245,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": "musl",
       "license": "MIT",
       "optional": true,
       "os": [
@@ -6283,7 +6261,6 @@
       "cpu": [
         "riscv64"
       ],
-      "libc": "musl",
       "license": "MIT",
       "optional": true,
       "os": [
@@ -6300,7 +6277,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": "musl",
       "license": "MIT",
       "optional": true,
       "os": [
@@ -6317,7 +6293,6 @@
       "cpu": [
         "riscv64"
       ],
-      "libc": "glibc",
       "license": "MIT",
       "optional": true,
       "os": [
@@ -6334,7 +6309,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": "glibc",
       "license": "MIT",
       "optional": true,
       "os": [

app/vmui/packages/vmui/package.json

@@ -23,7 +23,7 @@
     "classnames": "^2.5.1",
     "dayjs": "^1.11.20",
     "lodash.debounce": "^4.0.8",
-    "marked": "^18.0.0",
+    "marked": "^18.0.2",
     "preact": "^10.29.1",
     "qs": "^6.15.1",
     "react-input-mask": "^2.0.4",

app/vmui/packages/vmui/src/pages/TopQueries/TopQueryPanel/TopQueryPanel.tsx

@@ -1,4 +1,4 @@
-import { FC, useState } from "react";
+import { FC, ReactNode, useState } from "react";
 import { TopQuery } from "../../../types";
 import JsonView from "../../../components/Views/JsonView/JsonView";
 import { CodeIcon, TableIcon } from "../../../components/Main/Icons";
@@ -8,10 +8,18 @@ import "./style.scss";
 import classNames from "classnames";
 import useDeviceDetect from "../../../hooks/useDeviceDetect";
 
+export interface TopQueryColumn {
+  title?: string;
+  tooltip?: string;
+  key: keyof TopQuery;
+  sortBy?: keyof TopQuery;
+  format?: (row: TopQuery) => ReactNode;
+}
+
 export interface TopQueryPanelProps {
   rows: TopQuery[],
   title?: string,
-  columns: {title?: string, key: (keyof TopQuery), sortBy?: (keyof TopQuery)}[],
+  columns: TopQueryColumn[],
   defaultOrderBy?: keyof TopQuery,
 }
 const tabs = ["table", "JSON"].map((t, i) => ({

app/vmui/packages/vmui/src/pages/TopQueries/TopQueryTable/TopQueryTable.tsx

@@ -3,7 +3,7 @@ import { TopQuery } from "../../../types";
 import { getComparator, stableSort } from "../../../components/Table/helpers";
 import { TopQueryPanelProps } from "../TopQueryPanel/TopQueryPanel";
 import classNames from "classnames";
-import { ArrowDropDownIcon, CopyIcon, PlayCircleOutlineIcon } from "../../../components/Main/Icons";
+import { ArrowDropDownIcon, CopyIcon, InfoOutlinedIcon, PlayCircleOutlineIcon } from "../../../components/Main/Icons";
 import Button from "../../../components/Main/Button/Button";
 import Tooltip from "../../../components/Main/Tooltip/Tooltip";
 import { Link } from "react-router-dom";
@@ -35,26 +35,40 @@ const TopQueryTable:FC<TopQueryPanelProps> = ({ rows, columns, defaultOrderBy })
     <table className="vm-table">
       <thead className="vm-table-header">
         <tr className="vm-table__row vm-table__row_header">
-          {columns.map((col) => (
-            <th
-              className="vm-table-cell vm-table-cell_header vm-table-cell_sort"
-              onClick={createSortHandler(col.sortBy || col.key)}
-              key={col.key}
-            >
-              <div className="vm-table-cell__content">
-                {col.title || col.key}
-                <div
-                  className={classNames({
-                    "vm-table__sort-icon": true,
-                    "vm-table__sort-icon_active": orderBy === col.key,
-                    "vm-table__sort-icon_desc": orderDir === "desc" && orderBy === col.key
-                  })}
-                >
-                  <ArrowDropDownIcon/>
+          {columns.map((col) => {
+            const sortKey = col.sortBy || col.key;
+
+            return (
+              <th
+                className="vm-table-cell vm-table-cell_header vm-table-cell_sort"
+                onClick={createSortHandler(sortKey)}
+                key={col.key}
+              >
+                <div className="vm-table-cell__content">
+                  {col.title || col.key}
+                  {col.tooltip && (
+                    <Tooltip
+                      placement="top-center"
+                      title={col.tooltip}
+                    >
+                      <span className="vm-top-queries-table__info-icon">
+                        <InfoOutlinedIcon/>
+                      </span>
+                    </Tooltip>
+                  )}
+                  <div
+                    className={classNames({
+                      "vm-table__sort-icon": true,
+                      "vm-table__sort-icon_active": orderBy === sortKey,
+                      "vm-table__sort-icon_desc": orderDir === "desc" && orderBy === sortKey
+                    })}
+                  >
+                    <ArrowDropDownIcon/>
+                  </div>
                 </div>
-              </div>
-            </th>
-          ))}
+              </th>
+            );
+          })}
           <th className="vm-table-cell vm-table-cell_header"/> {/* empty cell for actions */}
         </tr>
       </thead>
@@ -69,7 +83,7 @@ const TopQueryTable:FC<TopQueryPanelProps> = ({ rows, columns, defaultOrderBy })
                 className="vm-table-cell"
                 key={col.key}
               >
-                {row[col.key] || "-"}
+                {col.format?.(row) ?? row[col.key] ?? "-"}
               </td>
             ))}
             <td className="vm-table-cell vm-table-cell_no-padding">

app/vmui/packages/vmui/src/pages/TopQueries/hooks/useFetchTopQueries.ts

@@ -34,7 +34,7 @@ const processResponse = (data: TopQueriesData) => {
     target.forEach(t => {
       const timeRange = getDurationFromMilliseconds(t.timeRangeSeconds*1000);
       t.url = getQueryUrl(t, timeRange);
-      t.timeRange = timeRange;
+      t.timeRange = timeRange || "instant";
     });
   });
 

app/vmui/packages/vmui/src/pages/TopQueries/hooks/useTopQueriesColumns.ts

@@ -0,0 +1,77 @@
+import { useMemo } from "react";
+import { TopQueryColumn } from "../TopQueryPanel/TopQueryPanel";
+import { humanizeSeconds } from "../../../utils/time";
+import { formatBytes } from "../../../utils/bytes";
+
+type UseTopQueriesColumns = {
+  maxLifetime: string;
+};
+
+export const useTopQueriesColumns = ({ maxLifetime }: UseTopQueriesColumns) => {
+  return useMemo(() => {
+    const queryCol: TopQueryColumn = {
+      key: "query"
+    };
+
+    const timeRangeCol: TopQueryColumn = {
+      key: "timeRange",
+      sortBy: "timeRangeSeconds",
+      title: "range",
+      tooltip: "The time range between start and end of the query request. 'instant' means the query was executed at a single point in time without a time range"
+    };
+
+    const countCol: TopQueryColumn = {
+      key: "count",
+      tooltip: `The number of times the query was executed over the last ${maxLifetime}`,
+    };
+
+    const topBySumDuration: TopQueryColumn[] = [
+      queryCol,
+      {
+        key: "sumDurationSeconds",
+        title: "duration",
+        tooltip: `Cumulative time spent executing the query across all its invocations over the last ${maxLifetime}`,
+        format: (row) => humanizeSeconds(row.sumDurationSeconds)
+      },
+      timeRangeCol,
+      countCol,
+    ];
+
+    const topByAvgDuration: TopQueryColumn[] = [
+      queryCol,
+      {
+        key: "avgDurationSeconds",
+        title: "duration",
+        tooltip: `Average time spent executing the query over the last ${maxLifetime}`,
+        format: (row) => humanizeSeconds(row.avgDurationSeconds)
+      },
+      timeRangeCol,
+      countCol,
+    ];
+
+    const topByCount: TopQueryColumn[] = [
+      queryCol,
+      timeRangeCol,
+      countCol,
+    ];
+
+    const topByAvgMemoryUsage: TopQueryColumn[] = [
+      queryCol,
+      {
+        key: "avgMemoryBytes",
+        title: "memory",
+        tooltip: `Average memory used during query execution over the last ${maxLifetime}`,
+        format: (row) => formatBytes(row.avgMemoryBytes)
+      },
+      timeRangeCol,
+      countCol,
+    ];
+
+    return {
+      topBySumDuration,
+      topByAvgDuration,
+      topByCount,
+      topByAvgMemoryUsage,
+    };
+  }, [maxLifetime]);
+};

app/vmui/packages/vmui/src/pages/TopQueries/index.tsx

@@ -15,6 +15,7 @@ import "./style.scss";
 import useDeviceDetect from "../../hooks/useDeviceDetect";
 import classNames from "classnames";
 import useStateSearchParams from "../../hooks/useStateSearchParams";
+import { useTopQueriesColumns } from "./hooks/useTopQueriesColumns";
 
 const exampleDuration = "30ms, 15s, 3d4h, 1y2w";
 
@@ -23,6 +24,7 @@ const TopQueries: FC = () => {
 
   const [topN, setTopN] = useStateSearchParams(10, "topN");
   const [maxLifetime, setMaxLifetime] = useStateSearchParams("10m", "maxLifetime");
+  const columns = useTopQueriesColumns({ maxLifetime });
 
   const { data, error, loading, fetch } = useFetchTopQueries({ topN, maxLifetime });
 
@@ -145,52 +147,33 @@ const TopQueries: FC = () => {
 
       {error && <Alert variant="error">{error}</Alert>}
 
-      {data && (<>
+      {data && (
         <div className="vm-top-queries-panels">
           <TopQueryPanel
+            title="Queries with most summary time to execute"
             rows={data.topBySumDuration}
-            title={"Queries with most summary time to execute"}
-            columns={[
-              { key: "query" },
-              { key: "sumDurationSeconds", title: "sum duration, sec" },
-              { key: "timeRange", sortBy: "timeRangeSeconds", title: "query time interval" },
-              { key: "count" }
-            ]}
-            defaultOrderBy={"sumDurationSeconds"}
+            columns={columns.topBySumDuration}
+            defaultOrderBy="sumDurationSeconds"
           />
           <TopQueryPanel
+            title="Most heavy queries"
             rows={data.topByAvgDuration}
-            title={"Most heavy queries"}
-            columns={[
-              { key: "query" },
-              { key: "avgDurationSeconds", title: "avg duration, sec" },
-              { key: "timeRange", sortBy: "timeRangeSeconds", title: "query time interval" },
-              { key: "count" }
-            ]}
-            defaultOrderBy={"avgDurationSeconds"}
+            columns={columns.topByAvgDuration}
+            defaultOrderBy="avgDurationSeconds"
           />
           <TopQueryPanel
+            title="Most frequently executed queries"
             rows={data.topByCount}
-            title={"Most frequently executed queries"}
-            columns={[
-              { key: "query" },
-              { key: "timeRange", sortBy: "timeRangeSeconds", title: "query time interval" },
-              { key: "count" }
-            ]}
+            columns={columns.topByCount}
           />
           <TopQueryPanel
+            title="Queries with most memory to execute"
             rows={data.topByAvgMemoryUsage}
-            title={"Queries with most memory to execute"}
-            columns={[
-              { key: "query" },
-              { key: "avgMemoryBytes", title: "avg memory usage, bytes" },
-              { key: "timeRange", sortBy: "timeRangeSeconds", title: "query time interval" },
-              { key: "count" }
-            ]}
-            defaultOrderBy={"avgMemoryBytes"}
+            columns={columns.topByAvgMemoryUsage}
+            defaultOrderBy="avgMemoryBytes"
           />
         </div>
-      </>)}
+      )}
     </div>
   );
 };

app/vmui/packages/vmui/src/pages/TopQueries/style.scss

@@ -1,5 +1,19 @@
 @use "src/styles/variables" as *;
 
+.vm-top-queries-table {
+  &__info-icon {
+    display: inline-flex;
+    align-items: center;
+    color: $color-text-secondary;
+    margin-left: 4px;
+
+    svg {
+      width: 14px;
+      height: 14px;
+    }
+  }
+}
+
 .vm-top-queries {
   display: grid;
   align-items: flex-start;

app/vmui/packages/vmui/src/utils/bytes.test.ts

@@ -0,0 +1,47 @@
+import { describe, expect, it } from "vitest";
+import { formatBytes } from "./bytes";
+
+describe("formatBytes", () => {
+  it("returns null for invalid values", () => {
+    expect(formatBytes(-1)).toBeNull();
+    expect(formatBytes(Number.NaN)).toBeNull();
+    expect(formatBytes(Number.POSITIVE_INFINITY)).toBeNull();
+    expect(formatBytes(Number.NEGATIVE_INFINITY)).toBeNull();
+  });
+
+  it("formats zero bytes", () => {
+    expect(formatBytes(0)).toBe("0 B");
+  });
+
+  it("formats bytes", () => {
+    expect(formatBytes(0.5)).toBe("0.5 B");
+    expect(formatBytes(1)).toBe("1 B");
+    expect(formatBytes(512)).toBe("512 B");
+    expect(formatBytes(1023)).toBe("1023 B");
+  });
+
+  it("formats kilobytes", () => {
+    expect(formatBytes(1024)).toBe("1 KB");
+    expect(formatBytes(1536)).toBe("1.5 KB");
+  });
+
+  it("formats megabytes", () => {
+    expect(formatBytes(1024 ** 2)).toBe("1 MB");
+    expect(formatBytes(2.5 * 1024 ** 2)).toBe("2.5 MB");
+  });
+
+  it("formats gigabytes, terabytes and petabytes", () => {
+    expect(formatBytes(1024 ** 3)).toBe("1 GB");
+    expect(formatBytes(1024 ** 4)).toBe("1 TB");
+    expect(formatBytes(1024 ** 5)).toBe("1 PB");
+  });
+
+  it("caps values above PB to PB unit", () => {
+    expect(formatBytes(1024 ** 6)).toBe("1024 PB");
+  });
+
+  it("rounds to two decimals", () => {
+    expect(formatBytes(1234)).toBe("1.21 KB");
+    expect(formatBytes(1234567)).toBe("1.18 MB");
+  });
+});

app/vmui/packages/vmui/src/utils/bytes.ts

@@ -0,0 +1,14 @@
+const LOG_1024 = Math.log(1024);
+const UNITS = ["B", "KB", "MB", "GB", "TB", "PB"] as const;
+
+export const formatBytes = (bytes: number): string | null => {
+  if (!Number.isFinite(bytes) || bytes < 0) return null;
+  if (bytes === 0) return "0 B";
+
+  const unitIndex = Math.min(
+    Math.max(Math.floor(Math.log(bytes) / LOG_1024), 0),
+    UNITS.length - 1
+  );
+
+  return `${parseFloat((bytes / 1024 ** unitIndex).toFixed(2))} ${UNITS[unitIndex]}`;
+};

apptest/client.go

@@ -2,6 +2,8 @@ package apptest
 
 import (
 	"bytes"
+	"encoding/json"
+	"fmt"
 	"io"
 	"net"
 	"net/http"
@@ -12,6 +14,10 @@ import (
 	"testing"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prommetadata"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
+	otlppb "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/pb"
+	"github.com/golang/snappy"
 )
 
 // Client is used for interacting with the apps over the network.
@@ -105,6 +111,35 @@ func (c *Client) Write(t *testing.T, address string, data []string) {
 	}
 }
 
+// getClusterPath returns path in cluster's URL format.
+// Based on QueryOpts, it will either put tenant ID into URL
+// or will skip it if tenant is set via HTTP headers.
+func getClusterPath(addr, prefix, suffix string, o QueryOpts) string {
+	if o.Tenant != "" {
+		// QueryOpts.Tenant has priority over headers
+		return tenantViaURL(addr, prefix, o.Tenant, suffix)
+	}
+
+	h := o.getHeaders()
+	if h.Get("AccountID") != "" || h.Get("ProjectID") != "" {
+		return tenantViaHeaders(addr, prefix, suffix)
+	}
+
+	// tenant is missing in QueryOpts and in HTTP headers. Falling back to default 0:0 tenant in URL
+	return tenantViaURL(addr, prefix, "0:0", suffix)
+}
+
+// tenantViaURL returns path in cluster's URL format with tenant specified in URL
+func tenantViaURL(addr, prefix, tenant, suffix string) string {
+	return fmt.Sprintf("http://%s/%s/%s/%s", addr, prefix, tenant, suffix)
+}
+
+// tenantViaHeaders returns path in cluster's URL format where tenant is omitted in URL
+// Only supported if -enableMultitenancyViaHeaders is specified
+func tenantViaHeaders(addr, prefix, suffix string) string {
+	return fmt.Sprintf("http://%s/%s/%s", addr, prefix, suffix)
+}
+
 // readAllAndClose reads everything from the response body and then closes it.
 func readAllAndClose(t *testing.T, responseBody io.ReadCloser) string {
 	t.Helper()
@@ -117,27 +152,34 @@ func readAllAndClose(t *testing.T, responseBody io.ReadCloser) string {
 	return string(b)
 }
 
-// ServesMetrics is used to retrieve the app's metrics.
+// metricsClient is used to retrieve the app's metrics.
 //
 // This type is expected to be embedded by the apps that serve metrics.
-type ServesMetrics struct {
-	metricsURL string
-	cli        *Client
+type metricsClient struct {
+	metricsCli *Client
+	url        string
+}
+
+func newMetricsClient(cli *Client, addr string) *metricsClient {
+	return &metricsClient{
+		metricsCli: cli,
+		url:        fmt.Sprintf("http://%s/metrics", addr),
+	}
 }
 
 // GetIntMetric retrieves the value of a metric served by an app at /metrics URL.
 // The value is then converted to int.
-func (app *ServesMetrics) GetIntMetric(t *testing.T, metricName string) int {
+func (c *metricsClient) GetIntMetric(t *testing.T, metricName string) int {
 	t.Helper()
 
-	return int(app.GetMetric(t, metricName))
+	return int(c.GetMetric(t, metricName))
 }
 
 // GetMetric retrieves the value of a metric served by an app at /metrics URL.
-func (app *ServesMetrics) GetMetric(t *testing.T, metricName string) float64 {
+func (c *metricsClient) GetMetric(t *testing.T, metricName string) float64 {
 	t.Helper()
 
-	metrics, statusCode := app.cli.Get(t, app.metricsURL, nil)
+	metrics, statusCode := c.metricsCli.Get(t, c.url, nil)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
 	}
@@ -158,12 +200,12 @@ func (app *ServesMetrics) GetMetric(t *testing.T, metricName string) float64 {
 
 // GetMetricsByPrefix retrieves the values of all metrics that start with given
 // prefix.
-func (app *ServesMetrics) GetMetricsByPrefix(t *testing.T, prefix string) []float64 {
+func (c *metricsClient) GetMetricsByPrefix(t *testing.T, prefix string) []float64 {
 	t.Helper()
 
 	values := []float64{}
 
-	metrics, statusCode := app.cli.Get(t, app.metricsURL, nil)
+	metrics, statusCode := c.metricsCli.Get(t, c.url, nil)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
 	}
@@ -187,12 +229,12 @@ func (app *ServesMetrics) GetMetricsByPrefix(t *testing.T, prefix string) []floa
 	return values
 }
 
-func (app *ServesMetrics) GetMetricsByRegexp(t *testing.T, re *regexp.Regexp) []float64 {
+func (c *metricsClient) GetMetricsByRegexp(t *testing.T, re *regexp.Regexp) []float64 {
 	t.Helper()
 
 	values := []float64{}
 
-	metrics, statusCode := app.cli.Get(t, app.metricsURL, nil)
+	metrics, statusCode := c.metricsCli.Get(t, c.url, nil)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
 	}
@@ -215,3 +257,756 @@ func (app *ServesMetrics) GetMetricsByRegexp(t *testing.T, re *regexp.Regexp) []
 	}
 	return values
 }
+
+// rpcRowsSentTotal retrieves the values of all vminsert
+// `vm_rpc_rows_sent_total` metrics (there will be one for each vmstorage) and
+// returns their integer sum.
+func (c *metricsClient) rpcRowsSentTotal(t *testing.T) int {
+	total := 0.0
+	for _, v := range c.GetMetricsByPrefix(t, "vm_rpc_rows_sent_total") {
+		total += v
+	}
+	return int(total)
+}
+
+type vmselectClient struct {
+	vmselectCli              *Client
+	url                      func(op, path string, opts QueryOpts) string
+	metricNamesStatsResetURL string
+	tenantsURL               string
+}
+
+// PrometheusAPIV1Export is a test helper function that performs the export of
+// raw samples in JSON line format by sending a request to
+// /prometheus/api/v1/export endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1export
+func (c *vmselectClient) PrometheusAPIV1Export(t *testing.T, query string, opts QueryOpts) *PrometheusAPIV1QueryResponse {
+	t.Helper()
+	url := c.url("select", "prometheus/api/v1/export", opts)
+	values := opts.asURLValues()
+	values.Add("match[]", query)
+	values.Add("format", "promapi")
+	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	return NewPrometheusAPIV1QueryResponse(t, res)
+}
+
+// PrometheusAPIV1ExportNative is a test helper function that performs the export of
+// raw samples in native binary format by sending a request to
+// /prometheus/api/v1/export/native endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1exportnative
+func (c *vmselectClient) PrometheusAPIV1ExportNative(t *testing.T, query string, opts QueryOpts) []byte {
+	t.Helper()
+	url := c.url("select", "prometheus/api/v1/export/native", opts)
+	values := opts.asURLValues()
+	values.Add("match[]", query)
+	values.Add("format", "promapi")
+	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	return []byte(res)
+}
+
+// PrometheusAPIV1Query is a test helper function that performs PromQL/MetricsQL
+// instant query by sending a request to /prometheus/api/v1/query endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1query
+func (c *vmselectClient) PrometheusAPIV1Query(t *testing.T, query string, opts QueryOpts) *PrometheusAPIV1QueryResponse {
+	t.Helper()
+	url := c.url("select", "prometheus/api/v1/query", opts)
+	values := opts.asURLValues()
+	values.Add("query", query)
+	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	return NewPrometheusAPIV1QueryResponse(t, res)
+}
+
+// PrometheusAPIV1QueryRange is a test helper function that performs
+// PromQL/MetricsQL range query by sending a request to
+// /prometheus/api/v1/query_range endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1query_range
+func (c *vmselectClient) PrometheusAPIV1QueryRange(t *testing.T, query string, opts QueryOpts) *PrometheusAPIV1QueryResponse {
+	t.Helper()
+	url := c.url("select", "prometheus/api/v1/query_range", opts)
+	values := opts.asURLValues()
+	values.Add("query", query)
+	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	return NewPrometheusAPIV1QueryResponse(t, res)
+}
+
+// PrometheusAPIV1Series retrieves list of time series that match the query by
+// sending a request to /prometheus/api/v1/series endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1series
+func (c *vmselectClient) PrometheusAPIV1Series(t *testing.T, matchQuery string, opts QueryOpts) *PrometheusAPIV1SeriesResponse {
+	t.Helper()
+	url := c.url("select", "prometheus/api/v1/series", opts)
+	values := opts.asURLValues()
+	values.Add("match[]", matchQuery)
+	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	return NewPrometheusAPIV1SeriesResponse(t, res)
+}
+
+// PrometheusAPIV1SeriesCount retrieves the total number of time series by
+// sending a request to /prometheus/api/v1/series/count endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1series
+func (c *vmselectClient) PrometheusAPIV1SeriesCount(t *testing.T, opts QueryOpts) *PrometheusAPIV1SeriesCountResponse {
+	t.Helper()
+	url := c.url("select", "prometheus/api/v1/series/count", opts)
+	values := opts.asURLValues()
+	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	return NewPrometheusAPIV1SeriesCountResponse(t, res)
+}
+
+// PrometheusAPIV1Labels retrieves the label names for time series that match a
+// query by sending a request to /prometheus/api/v1/labels endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1labels
+func (c *vmselectClient) PrometheusAPIV1Labels(t *testing.T, matchQuery string, opts QueryOpts) *PrometheusAPIV1LabelsResponse {
+	t.Helper()
+	url := c.url("select", "prometheus/api/v1/labels", opts)
+	values := opts.asURLValues()
+	values.Add("match[]", matchQuery)
+	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	return NewPrometheusAPIV1LabelsResponse(t, res)
+}
+
+// PrometheusAPIV1LabelValues retrieves the labels values for the metrics that
+// match the query by sending a request to /prometheus/api/v1/label/.../values
+// endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1labelvalues
+func (c *vmselectClient) PrometheusAPIV1LabelValues(t *testing.T, labelName, matchQuery string, opts QueryOpts) *PrometheusAPIV1LabelValuesResponse {
+	t.Helper()
+	path := fmt.Sprintf("prometheus/api/v1/label/%s/values", labelName)
+	url := c.url("select", path, opts)
+	values := opts.asURLValues()
+	values.Add("match[]", matchQuery)
+	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	return NewPrometheusAPIV1LabelValuesResponse(t, res)
+}
+
+// PrometheusAPIV1Metadata retrieves metadata for the given metric by sending a
+// request to /prometheus/api/v1/metadata endpoint.
+func (c *vmselectClient) PrometheusAPIV1Metadata(t *testing.T, metric string, limit int, opts QueryOpts) *PrometheusAPIV1Metadata {
+	t.Helper()
+	url := c.url("select", "prometheus/api/v1/metadata", opts)
+	values := opts.asURLValues()
+	values.Add("metric", metric)
+	values.Add("limit", strconv.Itoa(limit))
+	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	return NewPrometheusAPIV1Metadata(t, res)
+}
+
+// PrometheusAPIV1AdminTSDBDeleteSeries deletes the series that match the query
+// by sending a request to /prometheus/api/v1/admin/tsdb/delete_series.
+//
+// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1admintsdbdelete_series
+func (c *vmselectClient) PrometheusAPIV1AdminTSDBDeleteSeries(t *testing.T, matchQuery string, opts QueryOpts) {
+	t.Helper()
+
+	url := c.url("delete", "prometheus/api/v1/admin/tsdb/delete_series", opts)
+	values := opts.asURLValues()
+	values.Add("match[]", matchQuery)
+	res, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	if statusCode != http.StatusNoContent {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
+	}
+}
+
+// PrometheusAPIV1StatusMetricNamesStats sends a query to
+// /prometheus/api/v1/status/metric_names_stats endpoint and returns the metric
+// usage stats response for given params.
+//
+// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#track-ingested-metrics-usage
+func (c *vmselectClient) PrometheusAPIV1StatusMetricNamesStats(t *testing.T, limit, le, matchPattern string, opts QueryOpts) MetricNamesStatsResponse {
+	t.Helper()
+	url := c.url("select", "prometheus/api/v1/status/metric_names_stats", opts)
+	values := opts.asURLValues()
+	values.Add("limit", limit)
+	values.Add("le", le)
+	values.Add("match_pattern", matchPattern)
+	res, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	if statusCode != http.StatusOK {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
+	}
+	var resp MetricNamesStatsResponse
+	if err := json.Unmarshal([]byte(res), &resp); err != nil {
+		t.Fatalf("could not unmarshal metric names stats response data:\n%s\n err: %v", res, err)
+	}
+	return resp
+}
+
+// PrometheusAPIV1StatusTSDB retrieves the TSDB status for the time series that
+// match the query on the given date by sending a request to
+// /prometheus/api/v1/status/tsdb endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#tsdb-stats
+func (c *vmselectClient) PrometheusAPIV1StatusTSDB(t *testing.T, matchQuery string, date string, topN string, opts QueryOpts) TSDBStatusResponse {
+	t.Helper()
+	url := c.url("select", "prometheus/api/v1/status/tsdb", opts)
+	values := opts.asURLValues()
+	addNonEmpty := func(name, value string) {
+		if len(value) == 0 {
+			return
+		}
+		values.Add(name, value)
+	}
+	addNonEmpty("match[]", matchQuery)
+	addNonEmpty("topN", topN)
+	addNonEmpty("date", date)
+	res, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	if statusCode != http.StatusOK {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
+	}
+
+	var status TSDBStatusResponse
+	if err := json.Unmarshal([]byte(res), &status); err != nil {
+		t.Fatalf("could not unmarshal tsdb status response data:\n%s\n err: %v", res, err)
+	}
+	status.Sort()
+	return status
+}
+
+// GraphiteMetricsIndex retrieves the list of all metrics by sending a request
+// to /graphite/metrics/index.json endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#metrics-api
+func (c *vmselectClient) GraphiteMetricsIndex(t *testing.T, opts QueryOpts) GraphiteMetricsIndexResponse {
+	t.Helper()
+
+	url := c.url("select", "graphite/metrics/index.json", opts)
+	res, statusCode := c.vmselectCli.Get(t, url, opts.Headers)
+	if statusCode != http.StatusOK {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
+	}
+
+	var index GraphiteMetricsIndexResponse
+	if err := json.Unmarshal([]byte(res), &index); err != nil {
+		t.Fatalf("could not unmarshal metrics index response data:\n%s\n err: %v", res, err)
+	}
+	return index
+}
+
+// GraphiteMetricsFind finds metrics under a given path by sending a request
+// to /metrics/find endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#metrics-api
+// and https://graphite.readthedocs.io/en/latest/metrics_api.html#metrics-find
+func (c *vmselectClient) GraphiteMetricsFind(t *testing.T, query string, opts QueryOpts) GraphiteMetricsFindResponse {
+	t.Helper()
+
+	url := c.url("select", "graphite/metrics/find", opts)
+	values := opts.asURLValues()
+	values.Add("query", query)
+	resText, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	if statusCode != http.StatusOK {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, resText)
+	}
+
+	var res GraphiteMetricsFindResponse
+	if err := json.Unmarshal([]byte(resText), &res); err != nil {
+		t.Fatalf("could not unmarshal response data:\n%s\n err: %v", resText, err)
+	}
+	return res
+}
+
+// GraphiteMetricsExpand expands the given query with matching paths by sending
+// a request to /graphite/metrics/expand endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#metrics-api
+// and https://graphite.readthedocs.io/en/latest/metrics_api.html#metrics-expand
+func (c *vmselectClient) GraphiteMetricsExpand(t *testing.T, query string, opts QueryOpts) GraphiteMetricsExpandResponse {
+	t.Helper()
+
+	url := c.url("select", "graphite/metrics/expand", opts)
+	values := opts.asURLValues()
+	values.Add("query", query)
+	resText, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	if statusCode != http.StatusOK {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, resText)
+	}
+
+	var res GraphiteMetricsExpandResponse
+	if err := json.Unmarshal([]byte(resText), &res); err != nil {
+		t.Fatalf("could not unmarshal response data:\n%s\n err: %v", resText, err)
+	}
+	return res
+}
+
+// GraphiteRender retrieves the raw metric data by sending a request to
+// /graphite/render endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#render-api
+// and https://graphite-api.readthedocs.io/en/latest/api.html#the-render-api-render
+func (c *vmselectClient) GraphiteRender(t *testing.T, target string, opts QueryOpts) GraphiteRenderResponse {
+	t.Helper()
+
+	url := c.url("select", "graphite/render", opts)
+	values := opts.asURLValues()
+	values.Add("format", "json")
+	values.Add("target", target)
+	resText, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	if statusCode != http.StatusOK {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, resText)
+	}
+
+	var res GraphiteRenderResponse
+	if err := json.Unmarshal([]byte(resText), &res); err != nil {
+		t.Fatalf("could not unmarshal response data:\n%s\n err: %v", resText, err)
+	}
+	return res
+}
+
+// GraphiteTagsTagSeries is a test helper function that registers Graphite tags
+// for a single time series by sending a request to /graphite/tags/tagSeries
+// endpoint.
+func (c *vmselectClient) GraphiteTagsTagSeries(t *testing.T, record string, opts QueryOpts) {
+	t.Helper()
+
+	url := c.url("select", "graphite/tags/tagSeries", opts)
+	values := opts.asURLValues()
+	values.Add("path", record)
+	_, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	if got, want := statusCode, http.StatusNotImplemented; got != want {
+		t.Fatalf("unexpected status code: got %d, want %d", got, want)
+	}
+}
+
+// GraphiteTagsTagMultiSeries is a test helper function that registers Graphite
+// tags for a multiple time series by sending a request to
+// /graphite/tags/tagSeries endpoint.
+func (c *vmselectClient) GraphiteTagsTagMultiSeries(t *testing.T, records []string, opts QueryOpts) {
+	t.Helper()
+
+	url := c.url("select", "graphite/tags/tagMultiSeries", opts)
+	values := opts.asURLValues()
+	for _, rec := range records {
+		values.Add("path", rec)
+	}
+	_, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	if got, want := statusCode, http.StatusNotImplemented; got != want {
+		t.Fatalf("unexpected status code: got %d, want %d", got, want)
+	}
+}
+
+// PrometheusAPIV1AdminStatusMetricNamesStatsReset resets the metric name usage
+// stats by sending a request to
+// /prometheus/api/v1/admin/status/metric_names_stats/reset endpoint
+//
+// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#track-ingested-metrics-usage
+func (c *vmselectClient) PrometheusAPIV1AdminStatusMetricNamesStatsReset(t *testing.T, opts QueryOpts) {
+	t.Helper()
+	values := opts.asURLValues()
+	res, statusCode := c.vmselectCli.PostForm(t, c.metricNamesStatsResetURL, values, opts.Headers)
+	if statusCode != http.StatusNoContent {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
+	}
+}
+
+// APIV1AdminTenants retrieves the list of tenants by sending a request to
+// /admin/tenants endpoint.
+func (c *vmselectClient) APIV1AdminTenants(t *testing.T, opts QueryOpts) *AdminTenantsResponse {
+	t.Helper()
+	res, statusCode := c.vmselectCli.Get(t, c.tenantsURL, opts.Headers)
+	if statusCode != http.StatusOK {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
+	}
+
+	tenants := &AdminTenantsResponse{}
+	if err := json.Unmarshal([]byte(res), tenants); err != nil {
+		t.Fatalf("could not unmarshal tenants response data:\n%s\n err: %v", res, err)
+	}
+
+	return tenants
+}
+
+type vminsertClient struct {
+	vminsertCli        *Client
+	url                func(op, path string, opts QueryOpts) string
+	openTSDBURL        func(op, path string, opts QueryOpts) string
+	graphiteListenAddr string
+	sendBlocking       func(t *testing.T, numRecordsToSend int, send func())
+}
+
+// PrometheusAPIV1ImportCSV is a test helper function that inserts a collection
+// of records in CSV format for the given tenant by sending an HTTP POST
+// request to prometheus/api/v1/import/csv vminsert endpoint.
+//
+// See https://docs.victoriametrics.com/cluster-victoriametrics/#url-format
+func (c *vminsertClient) PrometheusAPIV1ImportCSV(t *testing.T, records []string, opts QueryOpts) {
+	t.Helper()
+
+	url := c.url("insert", "prometheus/api/v1/import/csv", opts)
+	uv := opts.asURLValues()
+	uvs := uv.Encode()
+	if len(uvs) > 0 {
+		url += "?" + uvs
+	}
+	data := []byte(strings.Join(records, "\n"))
+	headers := opts.getHeaders()
+	headers.Set("Content-Type", "text/plain")
+	c.sendBlocking(t, len(records), func() {
+		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		if statusCode != http.StatusNoContent {
+			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
+		}
+	})
+}
+
+// PrometheusAPIV1ImportNative is a test helper function that inserts a collection
+// of records in Native format for the given tenant by sending an HTTP POST
+// request to prometheus/api/v1/import/native vminsert endpoint.
+//
+// See https://docs.victoriametrics.com/cluster-victoriametrics/#url-format
+func (c *vminsertClient) PrometheusAPIV1ImportNative(t *testing.T, data []byte, opts QueryOpts) {
+	t.Helper()
+
+	url := c.url("insert", "prometheus/api/v1/import/native", opts)
+	uv := opts.asURLValues()
+	uvs := uv.Encode()
+	if len(uvs) > 0 {
+		url += "?" + uvs
+	}
+	headers := opts.getHeaders()
+	headers.Set("Content-Type", "text/plain")
+	c.sendBlocking(t, 1, func() {
+		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		if statusCode != http.StatusNoContent {
+			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
+		}
+	})
+}
+
+// PrometheusAPIV1Write is a test helper function that inserts a
+// collection of records in Prometheus remote-write format by sending a HTTP
+// POST request to /prometheus/api/v1/write vminsert endpoint.
+func (c *vminsertClient) PrometheusAPIV1Write(t *testing.T, wr prompb.WriteRequest, opts QueryOpts) {
+	t.Helper()
+
+	url := c.url("insert", "prometheus/api/v1/write", opts)
+	data := snappy.Encode(nil, wr.MarshalProtobuf(nil))
+	recordsCount := len(wr.Timeseries)
+	if prommetadata.IsEnabled() {
+		recordsCount += len(wr.Metadata)
+	}
+	headers := opts.getHeaders()
+	headers.Set("Content-Type", "application/x-protobuf")
+	c.sendBlocking(t, recordsCount, func() {
+		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		if statusCode != http.StatusNoContent {
+			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
+		}
+	})
+}
+
+// PrometheusAPIV1ImportPrometheus is a test helper function that inserts a
+// collection of records in Prometheus text exposition format for the given
+// tenant by sending a HTTP POST request to
+// /prometheus/api/v1/import/prometheus vminsert endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1importprometheus
+func (c *vminsertClient) PrometheusAPIV1ImportPrometheus(t *testing.T, records []string, opts QueryOpts) {
+	t.Helper()
+
+	url := c.url("insert", "prometheus/api/v1/import/prometheus", opts)
+	uv := opts.asURLValues()
+	uvs := uv.Encode()
+	if len(uvs) > 0 {
+		url += "?" + uvs
+	}
+	data := []byte(strings.Join(records, "\n"))
+	var recordsCount int
+	var metadataRecords int
+	uniqueMetadataMetricNames := make(map[string]struct{})
+	for _, record := range records {
+		// metric metadata has the following format:
+		//# HELP importprometheus_series
+		//# TYPE importprometheus_series
+		// it results into single metadata record
+		if strings.HasPrefix(record, "# ") {
+			metadataItems := strings.Split(record, " ")
+			if len(metadataItems) < 3 {
+				t.Fatalf("BUG: unexpected metadata format=%q", record)
+			}
+			metricName := metadataItems[2]
+			if _, ok := uniqueMetadataMetricNames[metricName]; ok {
+				continue
+			}
+			uniqueMetadataMetricNames[metricName] = struct{}{}
+			metadataRecords++
+			continue
+		}
+		recordsCount++
+	}
+	if prommetadata.IsEnabled() {
+		recordsCount += metadataRecords
+	}
+	headers := opts.getHeaders()
+	headers.Set("Content-Type", "text/plain")
+	c.sendBlocking(t, recordsCount, func() {
+		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		if statusCode != http.StatusNoContent {
+			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
+		}
+	})
+}
+
+// InfluxWrite is a test helper function that inserts a collection of records in
+// Influx line format by sending a HTTP POST request to /influx/write endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/url-examples/#influxwrite
+func (c *vminsertClient) InfluxWrite(t *testing.T, records []string, opts QueryOpts) {
+	t.Helper()
+
+	url := c.url("insert", "influx/write", opts)
+	uv := opts.asURLValues()
+	uvs := uv.Encode()
+	if len(uvs) > 0 {
+		url += "?" + uvs
+	}
+
+	data := []byte(strings.Join(records, "\n"))
+	headers := opts.getHeaders()
+	headers.Set("Content-Type", "text/plain")
+	c.sendBlocking(t, len(records), func() {
+		t.Helper()
+		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		if statusCode != http.StatusNoContent {
+			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
+		}
+	})
+}
+
+// OpentelemetryV1Metrics is a test helper function that inserts a
+// collection of records in Opentelemetry protocol format by sending a HTTP
+// POST request to /opentelemetry/v1/metrics vminsert endpoint.
+func (c *vminsertClient) OpentelemetryV1Metrics(t *testing.T, md otlppb.MetricsData, opts QueryOpts) {
+	t.Helper()
+
+	var recordsCount int
+	for _, rss := range md.ResourceMetrics {
+		for _, sm := range rss.ScopeMetrics {
+			recordsCount += len(sm.Metrics)
+			for _, m := range sm.Metrics {
+				if prommetadata.IsEnabled() {
+					recordsCount += len(m.Metadata)
+				}
+			}
+		}
+	}
+	url := c.url("insert", "opentelemetry/v1/metrics", opts)
+	uv := opts.asURLValues()
+	uvs := uv.Encode()
+	if len(uvs) > 0 {
+		url += "?" + uvs
+	}
+	data := md.MarshalProtobuf(nil)
+	headers := opts.getHeaders()
+	headers.Set("Content-Type", "application/x-protobuf")
+	c.sendBlocking(t, recordsCount, func() {
+		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		if statusCode != http.StatusOK {
+			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
+		}
+	})
+}
+
+// OpenTSDBAPIPut is a test helper function that inserts a collection of
+// records in OpenTSDB format for the given tenant by sending an HTTP POST
+// request to /opentsdb/api/put vminsert endpoint.
+//
+// See https://docs.victoriametrics.com/cluster-victoriametrics/#url-format
+func (c *vminsertClient) OpenTSDBAPIPut(t *testing.T, records []string, opts QueryOpts) {
+	t.Helper()
+
+	url := c.openTSDBURL("insert", "opentsdb/api/put", opts)
+	uv := opts.asURLValues()
+	uvs := uv.Encode()
+	if len(uvs) > 0 {
+		url += "?" + uvs
+	}
+	data := []byte("[" + strings.Join(records, ",") + "]")
+	headers := opts.getHeaders()
+	headers.Set("Content-Type", "application/json")
+	c.sendBlocking(t, len(records), func() {
+		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		if statusCode != http.StatusNoContent {
+			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
+		}
+	})
+}
+
+// ZabbixConnectorHistory is a test helper function that inserts a
+// collection of records in zabbixconnector  format by sending a HTTP
+// POST request to /zabbixconnector/api/v1/history vmsingle endpoint.
+func (c *vminsertClient) ZabbixConnectorHistory(t *testing.T, records []string, opts QueryOpts) {
+	t.Helper()
+
+	url := c.url("insert", "zabbixconnector/api/v1/history", opts)
+	uv := opts.asURLValues()
+	uvs := uv.Encode()
+	if len(uvs) > 0 {
+		url += "?" + uvs
+	}
+	data := []byte(strings.Join(records, "\n"))
+	headers := opts.getHeaders()
+	headers.Set("Content-Type", "application/json")
+	c.sendBlocking(t, len(records), func() {
+		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		if statusCode != http.StatusOK {
+			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
+		}
+	})
+
+}
+
+// GraphiteWrite is a test helper function that sends a
+// collection of records to graphiteListenAddr port.
+//
+// See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#ingesting
+func (c *vminsertClient) GraphiteWrite(t *testing.T, records []string, _ QueryOpts) {
+	t.Helper()
+	c.vminsertCli.Write(t, c.graphiteListenAddr, records)
+}
+
+type vmstorageClient struct {
+	vmstorageCli   *Client
+	httpListenAddr string
+}
+
+// ForceFlush is a test helper function that forces the flushing of inserted
+// data, so it becomes available for searching immediately.
+func (c *vmstorageClient) ForceFlush(t *testing.T) {
+	t.Helper()
+
+	url := fmt.Sprintf("http://%s/internal/force_flush", c.httpListenAddr)
+	_, statusCode := c.vmstorageCli.Get(t, url, nil)
+	if statusCode != http.StatusOK {
+		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
+	}
+}
+
+// ForceMerge is a test helper function that forces the merging of parts.
+func (c *vmstorageClient) ForceMerge(t *testing.T) {
+	t.Helper()
+
+	url := fmt.Sprintf("http://%s/internal/force_merge", c.httpListenAddr)
+	_, statusCode := c.vmstorageCli.Get(t, url, nil)
+	if statusCode != http.StatusOK {
+		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
+	}
+}
+
+// SnapshotCreate creates a database snapshot by sending a query to the
+// /snapshot/create endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots
+func (c *vmstorageClient) SnapshotCreate(t *testing.T) *SnapshotCreateResponse {
+	t.Helper()
+
+	data, statusCode := c.vmstorageCli.Post(t, c.SnapshotCreateURL(), nil, nil)
+	if got, want := statusCode, http.StatusOK; got != want {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
+	}
+
+	var res SnapshotCreateResponse
+	if err := json.Unmarshal([]byte(data), &res); err != nil {
+		t.Fatalf("could not unmarshal snapshot create response: data=%q, err: %v", data, err)
+	}
+
+	return &res
+}
+
+// SnapshotCreateURL returns the URL for creating snapshots.
+func (c *vmstorageClient) SnapshotCreateURL() string {
+	return fmt.Sprintf("http://%s/snapshot/create", c.httpListenAddr)
+}
+
+// APIV1AdminTSDBSnapshot creates a database snapshot by sending a query to the
+// /api/v1/admin/tsdb/snapshot endpoint.
+//
+// See https://prometheus.io/docs/prometheus/latest/querying/api/#snapshot.
+func (c *vmstorageClient) APIV1AdminTSDBSnapshot(t *testing.T) *APIV1AdminTSDBSnapshotResponse {
+	t.Helper()
+
+	url := fmt.Sprintf("http://%s/api/v1/admin/tsdb/snapshot", c.httpListenAddr)
+	data, statusCode := c.vmstorageCli.Post(t, url, nil, nil)
+	if got, want := statusCode, http.StatusOK; got != want {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
+	}
+
+	var res APIV1AdminTSDBSnapshotResponse
+	if err := json.Unmarshal([]byte(data), &res); err != nil {
+		t.Fatalf("could not unmarshal prometheus snapshot create response: data=%q, err: %v", data, err)
+	}
+
+	return &res
+}
+
+// SnapshotList lists existing database snapshots by sending a query to the
+// /snapshot/list endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots
+func (c *vmstorageClient) SnapshotList(t *testing.T) *SnapshotListResponse {
+	t.Helper()
+
+	url := fmt.Sprintf("http://%s/snapshot/list", c.httpListenAddr)
+	data, statusCode := c.vmstorageCli.Get(t, url, nil)
+	if got, want := statusCode, http.StatusOK; got != want {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
+	}
+
+	var res SnapshotListResponse
+	if err := json.Unmarshal([]byte(data), &res); err != nil {
+		t.Fatalf("could not unmarshal snapshot list response: data=%q, err: %v", data, err)
+	}
+
+	return &res
+}
+
+// SnapshotDelete deletes a snapshot by sending a query to the
+// /snapshot/delete endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots
+func (c *vmstorageClient) SnapshotDelete(t *testing.T, snapshotName string) *SnapshotDeleteResponse {
+	t.Helper()
+
+	url := fmt.Sprintf("http://%s/snapshot/delete?snapshot=%s", c.httpListenAddr, snapshotName)
+	data, statusCode := c.vmstorageCli.Delete(t, url)
+	wantStatusCodes := map[int]bool{
+		http.StatusOK:                  true,
+		http.StatusInternalServerError: true,
+	}
+	if !wantStatusCodes[statusCode] {
+		t.Fatalf("unexpected status code: got %d, want %v, resp text=%q", statusCode, wantStatusCodes, data)
+	}
+
+	var res SnapshotDeleteResponse
+	if err := json.Unmarshal([]byte(data), &res); err != nil {
+		t.Fatalf("could not unmarshal snapshot delete response: data=%q, err: %v", data, err)
+	}
+
+	return &res
+}
+
+// SnapshotDeleteAll deletes all snapshots by sending a query to the
+// /snapshot/delete_all endpoint.
+//
+// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots
+func (c *vmstorageClient) SnapshotDeleteAll(t *testing.T) *SnapshotDeleteAllResponse {
+	t.Helper()
+
+	url := fmt.Sprintf("http://%s/snapshot/delete_all", c.httpListenAddr)
+	data, statusCode := c.vmstorageCli.Post(t, url, nil, nil)
+	if got, want := statusCode, http.StatusOK; got != want {
+		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
+	}
+
+	var res SnapshotDeleteAllResponse
+	if err := json.Unmarshal([]byte(data), &res); err != nil {
+		t.Fatalf("could not unmarshal snapshot delete all response: data=%q, err: %v", data, err)
+	}
+
+	return &res
+}

apptest/model.go

@@ -27,13 +27,16 @@ type PrometheusQuerier interface {
 	PrometheusAPIV1LabelValues(t *testing.T, labelName, query string, opts QueryOpts) *PrometheusAPIV1LabelValuesResponse
 	PrometheusAPIV1ExportNative(t *testing.T, query string, opts QueryOpts) []byte
 	PrometheusAPIV1Metadata(t *testing.T, metric string, limit int, opts QueryOpts) *PrometheusAPIV1Metadata
-
-	APIV1AdminTSDBDeleteSeries(t *testing.T, matchQuery string, opts QueryOpts)
+	PrometheusAPIV1StatusMetricNamesStats(t *testing.T, limit, le, matchPattern string, opts QueryOpts) MetricNamesStatsResponse
+	PrometheusAPIV1AdminTSDBDeleteSeries(t *testing.T, matchQuery string, opts QueryOpts)
 
 	// TODO(@rtm0): Prometheus does not provide this API. Either move it to a
 	// separate interface or rename this interface to allow for multiple querier
 	// types.
 	GraphiteMetricsIndex(t *testing.T, opts QueryOpts) GraphiteMetricsIndexResponse
+	GraphiteMetricsFind(t *testing.T, query string, opts QueryOpts) GraphiteMetricsFindResponse
+	GraphiteMetricsExpand(t *testing.T, query string, opts QueryOpts) GraphiteMetricsExpandResponse
+	GraphiteRender(t *testing.T, target string, opts QueryOpts) GraphiteRenderResponse
 	GraphiteTagsTagSeries(t *testing.T, record string, opts QueryOpts)
 	GraphiteTagsTagMultiSeries(t *testing.T, records []string, opts QueryOpts)
 }
@@ -91,14 +94,9 @@ type QueryOpts struct {
 	Format         string
 	NoCache        string
 	Headers        http.Header
-}
-
-// getTenant returns tenant with optional default value
-func (qos *QueryOpts) getTenant() string {
-	if qos.Tenant == "" {
-		return "0"
-	}
-	return qos.Tenant
+	From           string
+	Until          string
+	StorageStep    string
 }
 
 func (qos *QueryOpts) getHeaders() http.Header {
@@ -131,6 +129,9 @@ func (qos *QueryOpts) asURLValues() url.Values {
 	addNonEmpty("latency_offset", qos.LatencyOffset)
 	addNonEmpty("format", qos.Format)
 	addNonEmpty("nocache", qos.NoCache)
+	addNonEmpty("from", qos.From)
+	addNonEmpty("until", qos.Until)
+	addNonEmpty("storage_step", qos.StorageStep)
 
 	return uv
 }
@@ -488,10 +489,6 @@ type TSDBStatusResponse struct {
 	Data      TSDBStatusResponseData
 }
 
-// GraphiteMetricsIndexResponse is an in-memory representation of the json response
-// returned by the /graphite/metrics/index.json endpoint.
-type GraphiteMetricsIndexResponse = []string
-
 // AdminTenantsResponse is an in-memory representation of the json response
 // returned by the /api/v1/admin/tenants endpoint.
 type AdminTenantsResponse struct {
@@ -541,3 +538,32 @@ func sortTSDBStatusResponseEntries(entries []TSDBStatusResponseEntry) {
 		return left.Count < right.Count
 	})
 }
+
+// GraphiteMetricsIndexResponse is an in-memory representation of the json response
+// returned by the /graphite/metrics/index.json endpoint.
+type GraphiteMetricsIndexResponse = []string
+
+type GraphiteMetric struct {
+	Id            string
+	Text          string
+	AllowChildren int
+	Expandable    int
+	Leaf          int
+}
+
+// GraphiteMetricsIndexResponse is an in-memory representation of the json response
+// returned by the /graphite/metrics/find endpoint.
+type GraphiteMetricsFindResponse = []GraphiteMetric
+
+// GraphiteMetricsExpandResponse is an in-memory representation of the json response
+// returned by the /graphite/metrics/expand endpoint.
+type GraphiteMetricsExpandResponse = []string
+
+type GraphiteRenderedTarget struct {
+	Target     string
+	Datapoints [][2]float64
+}
+
+// GraphiteRenderResponse is an in-memory representation of the json response
+// returned by the /graphite/render endpoint.
+type GraphiteRenderResponse = []GraphiteRenderedTarget

apptest/testcase.go

@@ -6,6 +6,7 @@ import (
 	"os"
 	"path"
 	"path/filepath"
+	"slices"
 	"sync"
 	"testing"
 	"time"
@@ -169,6 +170,18 @@ func (tc *TestCase) MustStartVmagent(instance string, flags []string, promScrape
 	return app
 }
 
+// MustStartDefaultRWVmagent is a test helper function that starts an instance of
+// vmagent with defaults suitable for remote-write tests.
+func (tc *TestCase) MustStartDefaultRWVmagent(instance string, flags []string) *Vmagent {
+	tc.t.Helper()
+
+	defaultFlags := []string{
+		"-remoteWrite.flushInterval=50ms",
+	}
+	defaultFlags = slices.Concat(defaultFlags, flags)
+	return tc.MustStartVmagent(instance, defaultFlags, ``)
+}
+
 // Vmcluster represents a typical cluster setup: several vmstorage replicas, one
 // vminsert, and one vmselect.
 //

apptest/tests/ingestprotocols_test.go

@@ -11,6 +11,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/apptest"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
+	otlppb "github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/pb"
 )
 
 func TestSingleIngestionProtocols(t *testing.T) {
@@ -297,6 +298,231 @@ func TestSingleIngestionProtocols(t *testing.T) {
 		},
 	})
 
+	// opentelemetry metrics protocol
+	tsNano := uint64(1707123456700 * 1e6) // 2024-02-05T08:57:36.700Z
+	otlpData := otlppb.MetricsData{
+		ResourceMetrics: []*otlppb.ResourceMetrics{
+			{
+				Resource: &otlppb.Resource{
+					Attributes: []*otlppb.KeyValue{
+						{
+							Key:   "foo",
+							Value: &otlppb.AnyValue{StringValue: new("bar")},
+						},
+					},
+				},
+				ScopeMetrics: []*otlppb.ScopeMetrics{
+					{
+						Scope: &otlppb.InstrumentationScope{
+							Name:    new("otlp"),
+							Version: new("v1"),
+							Attributes: []*otlppb.KeyValue{
+								{
+									Key:   "scope_attribute",
+									Value: &otlppb.AnyValue{IntValue: new(int64(100))},
+								},
+							},
+						},
+						Metrics: []*otlppb.Metric{
+							{
+								Name: "otlp_series_gauge",
+								Gauge: &otlppb.Gauge{
+									DataPoints: []*otlppb.NumberDataPoint{
+										{IntValue: new(int64(10)), TimeUnixNano: tsNano},
+										{IntValue: new(int64(5)), TimeUnixNano: tsNano, Attributes: []*otlppb.KeyValue{{Key: "bar", Value: &otlppb.AnyValue{StringValue: new("foo")}}}},
+									},
+								},
+							},
+							{
+								Name: "otlp_series_counter",
+								Sum: &otlppb.Sum{
+									DataPoints: []*otlppb.NumberDataPoint{
+										{IntValue: new(int64(30)), TimeUnixNano: tsNano, Attributes: []*otlppb.KeyValue{{Key: "bar", Value: &otlppb.AnyValue{StringValue: new("foo")}}}},
+									},
+								},
+							},
+						},
+					},
+					{
+						Scope: &otlppb.InstrumentationScope{
+							Name:    new("otlp2"),
+							Version: new("v2"),
+						},
+						Metrics: []*otlppb.Metric{
+							{
+								Name: "otlp_series_histogram",
+								Histogram: &otlppb.Histogram{
+									DataPoints: []*otlppb.HistogramDataPoint{
+										{
+											Count:          15,
+											Sum:            new(float64(100)),
+											ExplicitBounds: []float64{0.1, 0.5, 1.0, 5.0},
+											BucketCounts:   []uint64{0, 5, 10, 0, 0},
+											TimeUnixNano:   tsNano,
+											Attributes: []*otlppb.KeyValue{
+												{Key: "baz", Value: &otlppb.AnyValue{ArrayValue: &otlppb.ArrayValue{Values: []*otlppb.AnyValue{
+													{StringValue: new("foo")},
+													{IntValue: new(int64(100))},
+												}}}},
+											},
+										},
+									},
+								},
+							},
+						},
+					},
+				},
+			},
+			{
+				ScopeMetrics: []*otlppb.ScopeMetrics{
+					{
+						Metrics: []*otlppb.Metric{
+							{
+								Name: "otlp_series_summary",
+								Summary: &otlppb.Summary{
+									DataPoints: []*otlppb.SummaryDataPoint{
+										{
+											Attributes:   []*otlppb.KeyValue{},
+											TimeUnixNano: tsNano,
+											Sum:          17.5,
+											Count:        2,
+											QuantileValues: []*otlppb.ValueAtQuantile{
+												{
+													Quantile: 0.1,
+													Value:    7.5,
+												},
+												{
+													Quantile: 0.5,
+													Value:    10.0,
+												},
+											},
+										},
+									},
+								},
+							},
+						},
+					},
+				},
+			},
+		},
+	}
+	sut.OpentelemetryV1Metrics(t, otlpData, apptest.QueryOpts{})
+	sut.ForceFlush(t)
+	f(sut, &opts{
+		query: `{__name__=~"otlp.+"}`,
+		wantMetrics: []map[string]string{
+			{
+				"__name__":                         "otlp_series_counter",
+				"foo":                              "bar",
+				"bar":                              "foo",
+				"scope.attributes.scope_attribute": "100",
+				"scope.name":                       "otlp",
+				"scope.version":                    "v1",
+			},
+			{
+				"__name__":                         "otlp_series_gauge",
+				"foo":                              "bar",
+				"bar":                              "foo",
+				"scope.attributes.scope_attribute": "100",
+				"scope.name":                       "otlp",
+				"scope.version":                    "v1",
+			},
+			{
+				"__name__":                         "otlp_series_gauge",
+				"foo":                              "bar",
+				"scope.attributes.scope_attribute": "100",
+				"scope.name":                       "otlp",
+				"scope.version":                    "v1",
+			},
+
+			{
+				"__name__":      "otlp_series_histogram_bucket",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+				"le":            "+Inf",
+			},
+			{
+				"__name__":      "otlp_series_histogram_bucket",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+				"le":            "0.1",
+			},
+			{
+				"__name__":      "otlp_series_histogram_bucket",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+				"le":            "0.5",
+			},
+			{
+				"__name__":      "otlp_series_histogram_bucket",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+				"le":            "1",
+			},
+			{
+				"__name__":      "otlp_series_histogram_bucket",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+				"le":            "5",
+			},
+			{
+				"__name__":      "otlp_series_histogram_count",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+			},
+			{
+				"__name__":      "otlp_series_histogram_sum",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+			},
+			{
+				"__name__": "otlp_series_summary",
+				"quantile": "0.1",
+			},
+			{
+				"__name__": "otlp_series_summary",
+				"quantile": "0.5",
+			},
+			{
+				"__name__": "otlp_series_summary_count",
+			},
+			{
+				"__name__": "otlp_series_summary_sum",
+			},
+		},
+		wantSamples: []*apptest.Sample{
+			{Timestamp: 1707123456700, Value: 30},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 5},    // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 10},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 15},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 0},    // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 5},    // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 15},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 15},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 15},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 100},  // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 7.5},  // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 10},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 2},    // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 17.5}, // 2024-02-05T08:57:36.700Z
+
+		},
+	})
+
 }
 
 func TestSingleCardinalityLimiter(t *testing.T) {
@@ -718,6 +944,231 @@ func TestClusterIngestionProtocols(t *testing.T) {
 		},
 	})
 
+	// opentelemetry metrics protocol
+	tsNano := uint64(1707123456700 * 1e6) // 2024-02-05T08:57:36.700Z
+	otlpData := otlppb.MetricsData{
+		ResourceMetrics: []*otlppb.ResourceMetrics{
+			{
+				Resource: &otlppb.Resource{
+					Attributes: []*otlppb.KeyValue{
+						{
+							Key:   "foo",
+							Value: &otlppb.AnyValue{StringValue: new("bar")},
+						},
+					},
+				},
+				ScopeMetrics: []*otlppb.ScopeMetrics{
+					{
+						Scope: &otlppb.InstrumentationScope{
+							Name:    new("otlp"),
+							Version: new("v1"),
+							Attributes: []*otlppb.KeyValue{
+								{
+									Key:   "scope_attribute",
+									Value: &otlppb.AnyValue{IntValue: new(int64(100))},
+								},
+							},
+						},
+						Metrics: []*otlppb.Metric{
+							{
+								Name: "otlp_series_gauge",
+								Gauge: &otlppb.Gauge{
+									DataPoints: []*otlppb.NumberDataPoint{
+										{IntValue: new(int64(10)), TimeUnixNano: tsNano},
+										{IntValue: new(int64(5)), TimeUnixNano: tsNano, Attributes: []*otlppb.KeyValue{{Key: "bar", Value: &otlppb.AnyValue{StringValue: new("foo")}}}},
+									},
+								},
+							},
+							{
+								Name: "otlp_series_counter",
+								Sum: &otlppb.Sum{
+									DataPoints: []*otlppb.NumberDataPoint{
+										{IntValue: new(int64(30)), TimeUnixNano: tsNano, Attributes: []*otlppb.KeyValue{{Key: "bar", Value: &otlppb.AnyValue{StringValue: new("foo")}}}},
+									},
+								},
+							},
+						},
+					},
+					{
+						Scope: &otlppb.InstrumentationScope{
+							Name:    new("otlp2"),
+							Version: new("v2"),
+						},
+						Metrics: []*otlppb.Metric{
+							{
+								Name: "otlp_series_histogram",
+								Histogram: &otlppb.Histogram{
+									DataPoints: []*otlppb.HistogramDataPoint{
+										{
+											Count:          15,
+											Sum:            new(float64(100)),
+											ExplicitBounds: []float64{0.1, 0.5, 1.0, 5.0},
+											BucketCounts:   []uint64{0, 5, 10, 0, 0},
+											TimeUnixNano:   tsNano,
+											Attributes: []*otlppb.KeyValue{
+												{Key: "baz", Value: &otlppb.AnyValue{ArrayValue: &otlppb.ArrayValue{Values: []*otlppb.AnyValue{
+													{StringValue: new("foo")},
+													{IntValue: new(int64(100))},
+												}}}},
+											},
+										},
+									},
+								},
+							},
+						},
+					},
+				},
+			},
+			{
+				ScopeMetrics: []*otlppb.ScopeMetrics{
+					{
+						Metrics: []*otlppb.Metric{
+							{
+								Name: "otlp_series_summary",
+								Summary: &otlppb.Summary{
+									DataPoints: []*otlppb.SummaryDataPoint{
+										{
+											Attributes:   []*otlppb.KeyValue{},
+											TimeUnixNano: tsNano,
+											Sum:          17.5,
+											Count:        2,
+											QuantileValues: []*otlppb.ValueAtQuantile{
+												{
+													Quantile: 0.1,
+													Value:    7.5,
+												},
+												{
+													Quantile: 0.5,
+													Value:    10.0,
+												},
+											},
+										},
+									},
+								},
+							},
+						},
+					},
+				},
+			},
+		},
+	}
+	vminsert.OpentelemetryV1Metrics(t, otlpData, apptest.QueryOpts{})
+	vmstorage.ForceFlush(t)
+	f(&opts{
+		query: `{__name__=~"otlp.+"}`,
+		wantMetrics: []map[string]string{
+			{
+				"__name__":                         "otlp_series_counter",
+				"foo":                              "bar",
+				"bar":                              "foo",
+				"scope.attributes.scope_attribute": "100",
+				"scope.name":                       "otlp",
+				"scope.version":                    "v1",
+			},
+			{
+				"__name__":                         "otlp_series_gauge",
+				"foo":                              "bar",
+				"bar":                              "foo",
+				"scope.attributes.scope_attribute": "100",
+				"scope.name":                       "otlp",
+				"scope.version":                    "v1",
+			},
+			{
+				"__name__":                         "otlp_series_gauge",
+				"foo":                              "bar",
+				"scope.attributes.scope_attribute": "100",
+				"scope.name":                       "otlp",
+				"scope.version":                    "v1",
+			},
+
+			{
+				"__name__":      "otlp_series_histogram_bucket",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+				"le":            "+Inf",
+			},
+			{
+				"__name__":      "otlp_series_histogram_bucket",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+				"le":            "0.1",
+			},
+			{
+				"__name__":      "otlp_series_histogram_bucket",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+				"le":            "0.5",
+			},
+			{
+				"__name__":      "otlp_series_histogram_bucket",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+				"le":            "1",
+			},
+			{
+				"__name__":      "otlp_series_histogram_bucket",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+				"le":            "5",
+			},
+			{
+				"__name__":      "otlp_series_histogram_count",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+			},
+			{
+				"__name__":      "otlp_series_histogram_sum",
+				"baz":           `["foo",100]`,
+				"foo":           "bar",
+				"scope.name":    "otlp2",
+				"scope.version": "v2",
+			},
+			{
+				"__name__": "otlp_series_summary",
+				"quantile": "0.1",
+			},
+			{
+				"__name__": "otlp_series_summary",
+				"quantile": "0.5",
+			},
+			{
+				"__name__": "otlp_series_summary_count",
+			},
+			{
+				"__name__": "otlp_series_summary_sum",
+			},
+		},
+		wantSamples: []*apptest.Sample{
+			{Timestamp: 1707123456700, Value: 30},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 5},    // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 10},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 15},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 0},    // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 5},    // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 15},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 15},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 15},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 100},  // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 7.5},  // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 10},   // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 2},    // 2024-02-05T08:57:36.700Z
+			{Timestamp: 1707123456700, Value: 17.5}, // 2024-02-05T08:57:36.700Z
+
+		},
+	})
+
 }
 
 func TestClusterCardinalityLimiter(t *testing.T) {

apptest/tests/legacy_indexdb_test.go

@@ -214,7 +214,7 @@ func testLegacyDeleteSeries(tc *at.TestCase, opts testLegacyDeleteSeriesOpts) {
 	newSUT := opts.startNewSUT()
 	assertSearchResults(newSUT, `{__name__=~".*"}`, start1, end1, "1d", want1)
 
-	newSUT.APIV1AdminTSDBDeleteSeries(t, `{__name__=~".*"}`, at.QueryOpts{})
+	newSUT.PrometheusAPIV1AdminTSDBDeleteSeries(t, `{__name__=~".*"}`, at.QueryOpts{})
 	wantNoResults := &want{
 		series:       []map[string]string{},
 		queryResults: []*at.QueryResult{},
@@ -877,7 +877,7 @@ func testLegacyDowngrade(tc *at.TestCase, opts testLegacyDowngradeOpts) {
 	// Ingest legacy2 records, ensure the queries return only legacy2.
 	legacySUT = opts.startLegacySUT()
 	assertQueries(legacySUT, `{__name__=~".*"}`, wantLegacy1, numMetrics)
-	legacySUT.APIV1AdminTSDBDeleteSeries(t, `{__name__=~".*"}`, at.QueryOpts{})
+	legacySUT.PrometheusAPIV1AdminTSDBDeleteSeries(t, `{__name__=~".*"}`, at.QueryOpts{})
 	assertQueries(legacySUT, `{__name__=~".*"}`, wantEmpty, numMetrics)
 	legacySUT.PrometheusAPIV1ImportPrometheus(t, legacy2Data, at.QueryOpts{})
 	legacySUT.ForceFlush(t)
@@ -891,7 +891,7 @@ func testLegacyDowngrade(tc *at.TestCase, opts testLegacyDowngradeOpts) {
 	newSUT = opts.startNewSUT()
 	// series count includes deleted metrics
 	assertQueries(newSUT, `{__name__=~".*"}`, wantLegacy2New1, 3*numMetrics)
-	newSUT.APIV1AdminTSDBDeleteSeries(t, `{__name__=~".*"}`, at.QueryOpts{})
+	newSUT.PrometheusAPIV1AdminTSDBDeleteSeries(t, `{__name__=~".*"}`, at.QueryOpts{})
 	// series count includes deleted metrics
 	assertQueries(newSUT, `{__name__=~".*"}`, wantEmpty, 3*numMetrics)
 	opts.stopNewSUT()

apptest/tests/metric_names_stats_test.go

@@ -48,7 +48,7 @@ func TestSingleMetricNamesStats(t *testing.T) {
 			{MetricName: "metric_name_3"},
 		},
 	}
-	got := sut.APIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{})
+	got := sut.PrometheusAPIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{})
 	if diff := cmp.Diff(expected, got); diff != "" {
 		t.Errorf("unexpected response (-want, +got):\n%s", diff)
 	}
@@ -63,7 +63,7 @@ func TestSingleMetricNamesStats(t *testing.T) {
 			{MetricName: "metric_name_3", QueryRequestsCount: 1},
 		},
 	}
-	got = sut.APIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{})
+	got = sut.PrometheusAPIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{})
 	if diff := cmp.Diff(expected, got); diff != "" {
 		t.Errorf("unexpected response (-want, +got):\n%s", diff)
 	}
@@ -90,7 +90,7 @@ func TestSingleMetricNamesStats(t *testing.T) {
 		},
 	}
 	expectedStatsResponse.Sort()
-	gotStatus := sut.APIV1StatusTSDB(t, "", date, "", apptest.QueryOpts{})
+	gotStatus := sut.PrometheusAPIV1StatusTSDB(t, "", date, "", apptest.QueryOpts{})
 	if diff := cmp.Diff(expectedStatsResponse, gotStatus, tsdbMetricNameEntryCmpOpts); diff != "" {
 		t.Errorf("unexpected APIV1StatusTSDB response (-want, +got):\n%s", diff)
 	}
@@ -105,7 +105,7 @@ func TestSingleMetricNamesStats(t *testing.T) {
 			{MetricName: "metric_name_3", QueryRequestsCount: 1},
 		},
 	}
-	got = sut.APIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{})
+	got = sut.PrometheusAPIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{})
 	if diff := cmp.Diff(expected, got); diff != "" {
 		t.Errorf("unexpected response (-want, +got):\n%s", diff)
 	}
@@ -118,17 +118,17 @@ func TestSingleMetricNamesStats(t *testing.T) {
 			{MetricName: "metric_name_3", QueryRequestsCount: 1},
 		},
 	}
-	got = sut.APIV1StatusMetricNamesStats(t, "", "2", "", apptest.QueryOpts{})
+	got = sut.PrometheusAPIV1StatusMetricNamesStats(t, "", "2", "", apptest.QueryOpts{})
 	if diff := cmp.Diff(expected, got); diff != "" {
 		t.Errorf("unexpected response (-want, +got):\n%s", diff)
 	}
 
 	// reset state and check empty request response
-	sut.APIV1AdminStatusMetricNamesStatsReset(t, apptest.QueryOpts{})
+	sut.PrometheusAPIV1AdminStatusMetricNamesStatsReset(t, apptest.QueryOpts{})
 	expected = apptest.MetricNamesStatsResponse{
 		Records: []apptest.MetricNamesStatsRecord{},
 	}
-	got = sut.APIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{})
+	got = sut.PrometheusAPIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{})
 	if diff := cmp.Diff(expected, got); diff != "" {
 		t.Errorf("unexpected response (-want, +got):\n%s", diff)
 	}
@@ -158,7 +158,7 @@ func TestClusterMetricNamesStats(t *testing.T) {
 		fmt.Sprintf("-storageNode=%s,%s", vmstorage1.VmselectAddr(), vmstorage2.VmselectAddr()),
 	})
 	// verify empty stats
-	resp := vmselect.MetricNamesStats(t, "", "", "", apptest.QueryOpts{Tenant: "0:0"})
+	resp := vmselect.PrometheusAPIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{Tenant: "0:0"})
 	if len(resp.Records) != 0 {
 		t.Fatalf("unexpected resp Records: %d, want: %d", len(resp.Records), 0)
 	}
@@ -198,7 +198,7 @@ func TestClusterMetricNamesStats(t *testing.T) {
 				{MetricName: "metric_name_3"},
 			},
 		}
-		gotStats := vmselect.MetricNamesStats(t, "", "", "", apptest.QueryOpts{Tenant: tenantID})
+		gotStats := vmselect.PrometheusAPIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{Tenant: tenantID})
 		if diff := cmp.Diff(expected, gotStats); diff != "" {
 			t.Errorf("unexpected response (-want, +got):\n%s", diff)
 		}
@@ -216,7 +216,7 @@ func TestClusterMetricNamesStats(t *testing.T) {
 				{MetricName: "metric_name_1", QueryRequestsCount: 3},
 			},
 		}
-		gotStats = vmselect.MetricNamesStats(t, "", "", "", apptest.QueryOpts{Tenant: tenantID})
+		gotStats = vmselect.PrometheusAPIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{Tenant: tenantID})
 		if diff := cmp.Diff(expected, gotStats); diff != "" {
 			t.Errorf("unexpected response tenant: %s (-want, +got):\n%s", tenantID, diff)
 		}
@@ -243,9 +243,9 @@ func TestClusterMetricNamesStats(t *testing.T) {
 			},
 		}
 		expectedStatsResponse.Sort()
-		gotStatus := vmselect.APIV1StatusTSDB(t, "", date, "", apptest.QueryOpts{Tenant: tenantID})
+		gotStatus := vmselect.PrometheusAPIV1StatusTSDB(t, "", date, "", apptest.QueryOpts{Tenant: tenantID})
 		if diff := cmp.Diff(expectedStatsResponse, gotStatus, tsdbMetricNameEntryCmpOpts); diff != "" {
-			t.Errorf("unexpected APIV1StatusTSDB response tenant: %s (-want, +got):\n%s", tenantID, diff)
+			t.Errorf("unexpected TSDB status for tenant %s (-want, +got):\n%s", tenantID, diff)
 		}
 	}
 
@@ -258,14 +258,14 @@ func TestClusterMetricNamesStats(t *testing.T) {
 			{MetricName: "metric_name_1", QueryRequestsCount: 9},
 		},
 	}
-	gotStats := vmselect.MetricNamesStats(t, "", "", "", apptest.QueryOpts{Tenant: "multitenant"})
+	gotStats := vmselect.PrometheusAPIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{Tenant: "multitenant"})
 	if diff := cmp.Diff(expected, gotStats); diff != "" {
 		t.Errorf("unexpected response (-want, +got):\n%s", diff)
 	}
 
 	// reset cache and check empty state
-	vmselect.MetricNamesStatsReset(t, apptest.QueryOpts{})
-	resp = vmselect.MetricNamesStats(t, "", "", "", apptest.QueryOpts{Tenant: "multitenant"})
+	vmselect.PrometheusAPIV1AdminStatusMetricNamesStatsReset(t, apptest.QueryOpts{})
+	resp = vmselect.PrometheusAPIV1StatusMetricNamesStats(t, "", "", "", apptest.QueryOpts{Tenant: "multitenant"})
 	if len(resp.Records) != 0 {
 		t.Fatalf("want 0 records, got: %d", len(resp.Records))
 	}

apptest/tests/multitenancy_via_headers_test.go

@@ -0,0 +1,313 @@
+package tests
+
+import (
+	"net/http"
+	"testing"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/apptest"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
+)
+
+func TestClusterMultiTenantSelectViaHeaders(t *testing.T) {
+	fs.MustRemoveDir(t.Name())
+
+	cmpOpt := cmpopts.IgnoreFields(apptest.PrometheusAPIV1QueryResponse{}, "Status", "Data.ResultType")
+	cmpSROpt := cmpopts.IgnoreFields(apptest.PrometheusAPIV1SeriesResponse{}, "Status", "IsPartial")
+
+	tc := apptest.NewTestCase(t)
+	defer tc.Stop()
+	vmstorage := tc.MustStartVmstorage("vmstorage", []string{
+		"-storageDataPath=" + tc.Dir() + "/vmstorage",
+		"-retentionPeriod=100y",
+	})
+	vminsert := tc.MustStartVminsert("vminsert", []string{
+		"-storageNode=" + vmstorage.VminsertAddr(),
+		"-enableMultitenancyViaHeaders",
+	})
+	vmselect := tc.MustStartVmselect("vmselect", []string{
+		"-storageNode=" + vmstorage.VmselectAddr(),
+		"-search.tenantCacheExpireDuration=0",
+		"-enableMultitenancyViaHeaders",
+	})
+
+	multitenant := make(http.Header)
+	multitenant.Set("AccountID", "multitenant")
+
+	// test for empty tenants request
+	got := vmselect.PrometheusAPIV1Query(t, "foo_bar", apptest.QueryOpts{
+		Headers: multitenant,
+		Step:    "5m",
+		Time:    "2022-05-10T08:03:00.000Z",
+	})
+	want := apptest.NewPrometheusAPIV1QueryResponse(t, `{"data":{"result":[]}}`)
+	if diff := cmp.Diff(want, got, cmpOpt); diff != "" {
+		t.Errorf("unexpected response (-want, +got):\n%s", diff)
+	}
+
+	// ingest per tenant data and verify it with search
+	samples := []string{
+		`foo_bar 1.00 1652169600000`, // 2022-05-10T08:00:00Z
+		`foo_bar 2.00 1652169660000`, // 2022-05-10T08:01:00Z
+		`foo_bar 3.00 1652169720000`, // 2022-05-10T08:02:00Z
+	}
+	tenantHeaders := []map[string]string{
+		{"AccountID": "1", "ProjectID": "1"},
+		{"AccountID": "1", "ProjectID": "15"},
+		{"AccountID": "2"},
+		{"ProjectID": "3"},
+	}
+	instantCT := "2022-05-10T08:05:00.000Z" // 1652169900 Unix seconds
+	for _, headers := range tenantHeaders {
+		h := make(http.Header)
+		for k, v := range headers {
+			h.Set(k, v)
+		}
+		vminsert.PrometheusAPIV1ImportPrometheus(t, samples, apptest.QueryOpts{Headers: h})
+		vmstorage.ForceFlush(t)
+
+		// verify tenants are searchable via tenantID in headers
+		got := vmselect.PrometheusAPIV1Query(t, "foo_bar", apptest.QueryOpts{
+			Headers: h, Time: instantCT,
+		})
+		want := apptest.NewPrometheusAPIV1QueryResponse(t, `{"data":{"result":[{"metric":{"__name__":"foo_bar"},"value":[1652169900,"3"]}]}}`)
+		if diff := cmp.Diff(want, got, cmpOpt); diff != "" {
+			t.Errorf("unexpected response (-want, +got):\n%s", diff)
+		}
+	}
+
+	// verify all tenants searchable with multitenant header
+
+	//  /api/v1/query
+	want = apptest.NewPrometheusAPIV1QueryResponse(t,
+		`{"data":
+       {"result":[
+          {"metric":{"__name__":"foo_bar","vm_account_id":"0","vm_project_id":"3"},"value":[1652169900,"3"]},
+          {"metric":{"__name__":"foo_bar","vm_account_id":"1","vm_project_id": "1"},"value":[1652169900,"3"]},
+          {"metric":{"__name__":"foo_bar","vm_account_id":"1","vm_project_id":"15"},"value":[1652169900,"3"]},
+          {"metric":{"__name__":"foo_bar","vm_account_id":"2","vm_project_id":"0"},"value":[1652169900,"3"]}
+                 ]
+       }
+     }`,
+	)
+
+	got = vmselect.PrometheusAPIV1Query(t, "foo_bar", apptest.QueryOpts{
+		Headers: multitenant,
+		Time:    instantCT,
+	})
+	if diff := cmp.Diff(want, got, cmpOpt); diff != "" {
+		t.Errorf("unexpected response (-want, +got):\n%s", diff)
+	}
+
+	// /api/v1/query_range aggregated by tenant labels
+	query := "sum(foo_bar) by(vm_account_id,vm_project_id)"
+	got = vmselect.PrometheusAPIV1QueryRange(t, query, apptest.QueryOpts{
+		Headers: multitenant,
+		Start:   "2022-05-10T07:59:00.000Z",
+		End:     "2022-05-10T08:05:00.000Z",
+		Step:    "1m",
+	})
+
+	want = apptest.NewPrometheusAPIV1QueryResponse(t,
+		`{"data": 
+        {"result": [
+          {"metric": {"vm_account_id": "0","vm_project_id":"3"}, "values": [[1652169600,"1"],[1652169660,"2"],[1652169720,"3"],[1652169780,"3"]]},
+          {"metric": {"vm_account_id": "1","vm_project_id":"1"}, "values": [[1652169600,"1"],[1652169660,"2"],[1652169720,"3"],[1652169780,"3"]]},
+          {"metric": {"vm_account_id": "1","vm_project_id":"15"}, "values": [[1652169600,"1"],[1652169660,"2"],[1652169720,"3"],[1652169780,"3"]]},
+          {"metric": {"vm_account_id": "2","vm_project_id":"0"}, "values": [[1652169600,"1"],[1652169660,"2"],[1652169720,"3"],[1652169780,"3"]]}
+                   ]
+        }
+     }`)
+	if diff := cmp.Diff(want, got, cmpOpt); diff != "" {
+		t.Errorf("unexpected response (-want, +got):\n%s", diff)
+	}
+
+	// verify /api/v1/series response
+
+	wantSR := apptest.NewPrometheusAPIV1SeriesResponse(t,
+		`{"data": [
+        {"__name__":"foo_bar", "vm_account_id":"1", "vm_project_id":"1"},
+        {"__name__":"foo_bar", "vm_account_id":"1", "vm_project_id":"15"},
+        {"__name__":"foo_bar", "vm_account_id":"2", "vm_project_id":"0"},
+        {"__name__":"foo_bar", "vm_account_id":"0", "vm_project_id":"3"}
+              ]
+     }`)
+	wantSR.Sort()
+
+	gotSR := vmselect.PrometheusAPIV1Series(t, "foo_bar", apptest.QueryOpts{
+		Headers: multitenant,
+		Start:   "2022-05-10T08:03:00.000Z",
+	})
+	gotSR.Sort()
+	if diff := cmp.Diff(wantSR, gotSR, cmpSROpt); diff != "" {
+		t.Errorf("unexpected response (-want, +got):\n%s", diff)
+	}
+
+	// test ingestion with multitenant header, tenants must be populated from labels
+	//
+	var tenantLabelsSamples = []string{
+		`foo_bar{vm_account_id="5"} 1.00 1652169720000`,                    // 2022-05-10T08:02:00Z'
+		`foo_bar{vm_project_id="10"} 2.00 1652169660000`,                   // 2022-05-10T08:01:00Z
+		`foo_bar{vm_account_id="5",vm_project_id="15"} 3.00 1652169720000`, // 2022-05-10T08:02:00Z
+	}
+
+	vminsert.PrometheusAPIV1ImportPrometheus(t, tenantLabelsSamples, apptest.QueryOpts{Headers: multitenant})
+	vmstorage.ForceFlush(t)
+
+	//  /api/v1/query with query filters
+	want = apptest.NewPrometheusAPIV1QueryResponse(t,
+		`{"data":
+        {"result":[
+	         {"metric":{"__name__":"foo_bar","vm_account_id":"5","vm_project_id": "0"},"value":[1652169900,"1"]},
+	         {"metric":{"__name__":"foo_bar","vm_account_id":"5","vm_project_id":"15"},"value":[1652169900,"3"]}
+	                ]
+        }
+    }`,
+	)
+	got = vmselect.PrometheusAPIV1Query(t, `foo_bar{vm_account_id="5"}`, apptest.QueryOpts{
+		Time:    instantCT,
+		Headers: multitenant,
+	})
+	if diff := cmp.Diff(want, got, cmpOpt); diff != "" {
+		t.Errorf("unexpected response (-want, +got):\n%s", diff)
+	}
+
+	// /api/v1/series with extra_filters
+
+	wantSR = apptest.NewPrometheusAPIV1SeriesResponse(t,
+		`{"data": [
+	       {"__name__":"foo_bar", "vm_account_id":"5", "vm_project_id":"15"},
+	       {"__name__":"foo_bar", "vm_account_id":"1", "vm_project_id":"15"}
+	             ]
+	   }`)
+	wantSR.Sort()
+	gotSR = vmselect.PrometheusAPIV1Series(t, "foo_bar", apptest.QueryOpts{
+		Start:        "2022-05-10T08:00:00.000Z",
+		End:          "2022-05-10T08:30:00.000Z",
+		ExtraFilters: []string{`{vm_project_id="15"}`},
+		Headers:      multitenant,
+	})
+	gotSR.Sort()
+
+	if diff := cmp.Diff(wantSR, gotSR, cmpSROpt); diff != "" {
+		t.Errorf("unexpected response (-want, +got):\n%s", diff)
+	}
+
+	// /api/v1/label/../value with extra_filters
+
+	wantVR := apptest.NewPrometheusAPIV1LabelValuesResponse(t,
+		`{"data": [
+	       "5"
+	             ]
+	   }`)
+	// matchQuery is ignored for /api/v1/label/<labelName>/values lookups with multitenant token
+	gotVR := vmselect.PrometheusAPIV1LabelValues(t, "vm_account_id", "xxx", apptest.QueryOpts{
+		Start:        "2022-05-10T08:00:00.000Z",
+		End:          "2022-05-10T08:30:00.000Z",
+		ExtraFilters: []string{`{vm_account_id="5"}`},
+		Headers:      multitenant,
+	})
+	gotSR.Sort()
+
+	if diff := cmp.Diff(wantVR, gotVR, cmpopts.IgnoreFields(apptest.PrometheusAPIV1LabelValuesResponse{}, "Status", "IsPartial")); diff != "" {
+		t.Errorf("unexpected response (-want, +got):\n%s", diff)
+	}
+
+	// Delete series from specific tenant
+	tenantID := make(http.Header)
+	tenantID.Set("AccountID", "5")
+	tenantID.Set("ProjectID", "15")
+	vmselect.PrometheusAPIV1AdminTSDBDeleteSeries(t, "foo_bar", apptest.QueryOpts{
+		Headers: tenantID,
+	})
+	wantSR = apptest.NewPrometheusAPIV1SeriesResponse(t,
+		`{"data": [
+        {"__name__":"foo_bar", "vm_account_id":"0", "vm_project_id":"3"},
+        {"__name__":"foo_bar", "vm_account_id":"0", "vm_project_id":"10"},
+        {"__name__":"foo_bar", "vm_account_id":"1", "vm_project_id":"1"},
+        {"__name__":"foo_bar", "vm_account_id":"1", "vm_project_id":"15"},
+        {"__name__":"foo_bar", "vm_account_id":"2", "vm_project_id":"0"},
+        {"__name__":"foo_bar", "vm_account_id":"5", "vm_project_id":"0"}
+              ]
+     }`)
+	wantSR.Sort()
+
+	gotSR = vmselect.PrometheusAPIV1Series(t, "foo_bar", apptest.QueryOpts{
+		Headers: multitenant,
+		Start:   "2022-05-10T08:03:00.000Z",
+	})
+	gotSR.Sort()
+	if diff := cmp.Diff(wantSR, gotSR, cmpSROpt); diff != "" {
+		t.Errorf("unexpected response (-want, +got):\n%s", diff)
+	}
+
+	// Delete series for multitenant with tenant filter
+	vmselect.PrometheusAPIV1AdminTSDBDeleteSeries(t, `foo_bar{vm_account_id="1"}`, apptest.QueryOpts{
+		Headers: multitenant,
+	})
+
+	wantSR = apptest.NewPrometheusAPIV1SeriesResponse(t,
+		`{"data": [
+        {"__name__":"foo_bar", "vm_account_id":"0", "vm_project_id":"3"},
+        {"__name__":"foo_bar", "vm_account_id":"0", "vm_project_id":"10"},
+        {"__name__":"foo_bar", "vm_account_id":"2", "vm_project_id":"0"},
+        {"__name__":"foo_bar", "vm_account_id":"5", "vm_project_id":"0"}
+              ]
+     }`)
+	wantSR.Sort()
+
+	gotSR = vmselect.PrometheusAPIV1Series(t, `foo_bar`, apptest.QueryOpts{
+		Headers: multitenant,
+		Start:   "2022-05-10T08:03:00.000Z",
+	})
+	gotSR.Sort()
+	if diff := cmp.Diff(wantSR, gotSR, cmpSROpt); diff != "" {
+		t.Errorf("unexpected response (-want, +got):\n%s", diff)
+	}
+
+	if got := vmselect.GetIntMetric(t, `vm_cache_requests_total{type="multitenancy/tenants"}`); got != 0 {
+		t.Errorf("unexpected multitenancy tenants cache requests; got %d; want 0", got)
+	}
+
+	if got := vmselect.GetIntMetric(t, `vm_cache_misses_total{type="multitenancy/tenants"}`); got != 0 {
+		t.Errorf("unexpected multitenancy tenants cache misses; got %d; want 0", got)
+	}
+
+	if got := vmselect.GetIntMetric(t, `vm_cache_entries{type="multitenancy/tenants"}`); got != 0 {
+		t.Errorf("unexpected multitenancy tenants cache entries; got %d; want 0", got)
+	}
+
+	// verify that tenant in path has priority over tenant specified in headers
+
+	// /api/v1/import/prometheus
+
+	tenantInHeader := make(http.Header)
+	tenantInHeader.Set("AccountID", "42")
+	tenantInPath := "112"
+	vminsert.PrometheusAPIV1ImportPrometheus(t, samples, apptest.QueryOpts{
+		// tenants in header and path clash - path should have higher priority on ingestion
+		Headers: tenantInHeader,
+		Tenant:  "112",
+	})
+	vmstorage.ForceFlush(t)
+
+	want = apptest.NewPrometheusAPIV1QueryResponse(t,
+		`{"data":
+       {"result":[
+          {"metric":{"__name__":"foo_bar"},"value":[1652169900,"3"]}
+                 ]
+       }
+     }`,
+	)
+	got = vmselect.PrometheusAPIV1Query(t, "foo_bar", apptest.QueryOpts{
+		// tenants in header and path clash - path should have higher priority on ingestion
+		Headers: multitenant,
+		Tenant:  tenantInPath,
+		Time:    instantCT,
+	})
+	if diff := cmp.Diff(want, got, cmpOpt); diff != "" {
+		t.Errorf("unexpected response (-want, +got):\n%s", diff)
+	}
+}

apptest/tests/multitenant_test.go

@@ -192,7 +192,7 @@ func TestClusterMultiTenantSelect(t *testing.T) {
 	}
 
 	// Delete series from specific tenant
-	vmselect.APIV1AdminTSDBDeleteSeries(t, "foo_bar", apptest.QueryOpts{
+	vmselect.PrometheusAPIV1AdminTSDBDeleteSeries(t, "foo_bar", apptest.QueryOpts{
 		Tenant: "5:15",
 	})
 	wantSR = apptest.NewPrometheusAPIV1SeriesResponse(t,
@@ -215,7 +215,7 @@ func TestClusterMultiTenantSelect(t *testing.T) {
 	}
 
 	// Delete series for multitenant with tenant filter
-	vmselect.APIV1AdminTSDBDeleteSeries(t, `foo_bar{vm_account_id="1"}`, apptest.QueryOpts{
+	vmselect.PrometheusAPIV1AdminTSDBDeleteSeries(t, `foo_bar{vm_account_id="1"}`, apptest.QueryOpts{
 		Tenant: "multitenant",
 	})
 

apptest/tests/vmagent_remotewrite_test.go

@@ -30,13 +30,12 @@ func TestSingleVMAgentReloadConfigs(t *testing.T) {
 	relabelFilePath := fmt.Sprintf("%s/%s", t.TempDir(), "relabel_config.yaml")
 	fs.MustWriteSync(relabelFilePath, []byte(relabelingRules))
 
-	vmagent := tc.MustStartVmagent("vmagent", []string{
-		`-remoteWrite.flushInterval=50ms`,
+	vmagent := tc.MustStartDefaultRWVmagent("vmagent", []string{
 		`-remoteWrite.forcePromProto=true`,
 		"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent",
 		fmt.Sprintf(`-remoteWrite.url=http://%s/api/v1/write`, vmsingle.HTTPAddr()),
 		fmt.Sprintf(`-remoteWrite.urlRelabelConfig=%s`, relabelFilePath),
-	}, ``)
+	})
 
 	checkResponse := func(query, expResponse string) {
 		t.Helper()
@@ -132,12 +131,11 @@ func testSingleVMAgentRemoteWrite(t *testing.T, forcePromProto bool) {
 
 	vmsingle := tc.MustStartDefaultVmsingle()
 
-	vmagent := tc.MustStartVmagent("vmagent", []string{
-		`-remoteWrite.flushInterval=50ms`,
+	vmagent := tc.MustStartDefaultRWVmagent("vmagent", []string{
 		fmt.Sprintf(`-remoteWrite.forcePromProto=%v`, forcePromProto),
 		fmt.Sprintf(`-remoteWrite.url=http://%s/api/v1/write`, vmsingle.HTTPAddr()),
 		"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent",
-	}, ``)
+	})
 
 	vmagent.APIV1ImportPrometheus(t, []string{
 		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
@@ -181,12 +179,11 @@ func TestSingleVMAgentUnsupportedMediaTypeDropIfSnappy(t *testing.T) {
 	}))
 	defer remoteWriteSrv.Close()
 
-	vmagent := tc.MustStartVmagent("vmagent", []string{
-		`-remoteWrite.flushInterval=50ms`,
+	vmagent := tc.MustStartDefaultRWVmagent("vmagent", []string{
 		`-remoteWrite.forcePromProto=true`,
 		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv.URL),
 		"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent",
-	}, ``)
+	})
 
 	vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
 		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
@@ -245,11 +242,10 @@ func TestSingleVMAgentDowngradeRemoteWriteProtocol(t *testing.T) {
 	}))
 	defer remoteWriteSrv.Close()
 
-	vmagent := tc.MustStartVmagent("vmagent", []string{
-		`-remoteWrite.flushInterval=50ms`,
+	vmagent := tc.MustStartDefaultRWVmagent("vmagent", []string{
 		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv.URL),
 		"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent",
-	}, ``)
+	})
 
 	// Send request encoded with `zstd`; it fails, gets repacked as `snappy`, and retries successfully.
 	vmagent.APIV1ImportPrometheus(t, []string{
@@ -294,8 +290,7 @@ func TestSingleVMAgentDropOnOverload(t *testing.T) {
 	}))
 	defer remoteWriteSrv2.Close()
 
-	vmagent := tc.MustStartVmagent("vmagent", []string{
-		`-remoteWrite.flushInterval=50ms`,
+	vmagent := tc.MustStartDefaultRWVmagent("vmagent", []string{
 		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv.URL),
 		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv2.URL),
 		"-remoteWrite.disableOnDiskQueue=true",
@@ -311,7 +306,7 @@ func TestSingleVMAgentDropOnOverload(t *testing.T) {
 		// It improves the test stability on resource-constrained runners.
 		// Should be bigger than retries * period
 		"-remoteWrite.retryMinInterval=3s",
-	}, ``)
+	})
 
 	const (
 		retries = 20
@@ -397,13 +392,12 @@ func TestSingleVMAgentCardinalityLimiter(t *testing.T) {
 	defer remoteWriteSrv.Close()
 
 	// Verify hourly limit is applied
-	vmagent := tc.MustStartVmagent("vmagent-hourly", []string{
-		`-remoteWrite.flushInterval=50ms`,
+	vmagent := tc.MustStartDefaultRWVmagent("vmagent-hourly", []string{
 		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv.URL),
 		"-remoteWrite.maxRowsPerBlock=1",
 		"-remoteWrite.maxHourlySeries=1",
 		"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent-hourly",
-	}, ``)
+	})
 
 	vmagent.APIV1ImportPrometheus(t, []string{
 		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
@@ -432,13 +426,12 @@ func TestSingleVMAgentCardinalityLimiter(t *testing.T) {
 	)
 
 	// Daily limits
-	vmagent2 := tc.MustStartVmagent("vmagent-daily", []string{
-		`-remoteWrite.flushInterval=50ms`,
+	vmagent2 := tc.MustStartDefaultRWVmagent("vmagent-daily", []string{
 		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv.URL),
 		"-remoteWrite.maxRowsPerBlock=1",
 		"-remoteWrite.maxDailySeries=1",
 		"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent-daily",
-	}, ``)
+	})
 
 	vmagent2.APIV1ImportPrometheus(t, []string{
 		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
@@ -467,14 +460,13 @@ func TestSingleVMAgentCardinalityLimiter(t *testing.T) {
 	)
 
 	// test running with unlimited tracker
-	vmagent3 := tc.MustStartVmagent("vmagent-unlimited", []string{
-		`-remoteWrite.flushInterval=50ms`,
+	vmagent3 := tc.MustStartDefaultRWVmagent("vmagent-unlimited", []string{
 		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv.URL),
 		"-remoteWrite.maxRowsPerBlock=10",
 		"-remoteWrite.maxDailySeries=-1",
 		"-remoteWrite.maxHourlySeries=-1",
 		"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent-unlimited",
-	}, ``)
+	})
 
 	metrics := make([]string, 0, 100)
 	for i := range 100 {
@@ -520,13 +512,12 @@ func TestClusterVMAgentForwardMetricsMetadata(t *testing.T) {
 
 	sut := tc.MustStartDefaultCluster()
 
-	vmagent := tc.MustStartVmagent("vmagent", []string{
-		`-remoteWrite.flushInterval=50ms`,
+	vmagent := tc.MustStartDefaultRWVmagent("vmagent", []string{
 		`-remoteWrite.forcePromProto=true`,
 		`-enableMultitenantHandlers=true`,
 		"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent",
 		fmt.Sprintf(`-remoteWrite.url=http://%s/insert/multitenant/prometheus/api/v1/write`, sut.Vminsert.HTTPAddr()),
-	}, ``)
+	})
 
 	prometheusRemoteWriteDataSet := prompb.WriteRequest{
 		Metadata: []prompb.MetricMetadata{
@@ -584,3 +575,69 @@ func TestClusterVMAgentForwardMetricsMetadata(t *testing.T) {
 	})
 
 }
+
+// See https://docs.victoriametrics.com/victoriametrics/vmagent/#multitenancy
+func TestSingleVMAgentMultitenancy(t *testing.T) {
+	tc := apptest.NewTestCase(t)
+	defer tc.Stop()
+
+	remoteWriteSrv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(http.StatusNoContent)
+	}))
+	defer remoteWriteSrv.Close()
+
+	vmagent := tc.MustStartDefaultRWVmagent("vmagent-multitenancy", []string{
+		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv.URL),
+		"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent-multitenancy",
+		"-enableMultitenantHandlers",
+		"-enableMultitenancyViaHeaders",
+	})
+
+	vmagent.APIV1ImportPrometheus(t, []string{
+		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
+	}, apptest.QueryOpts{Tenant: "2"})
+	v := vmagent.GetIntMetric(t, `vmagent_tenant_inserted_rows_total{type="prometheus",accountID="2",projectID="0"}`)
+	if v != 1 {
+		t.Fatalf("expected vmagent_tenant_inserted_rows_total to have value 1 for accountID=2")
+	}
+
+	vmagent.APIV1ImportPrometheus(t, []string{
+		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
+	}, apptest.QueryOpts{Tenant: "2:2"})
+	v = vmagent.GetIntMetric(t, `vmagent_tenant_inserted_rows_total{type="prometheus",accountID="2",projectID="2"}`)
+	if v != 1 {
+		t.Fatalf("expected vmagent_tenant_inserted_rows_total to have value 1 for accountID=2, projectID=2")
+	}
+
+	headers := make(http.Header)
+	headers.Set("AccountID", "3")
+	vmagent.APIV1ImportPrometheus(t, []string{
+		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
+	}, apptest.QueryOpts{Headers: headers})
+	v = vmagent.GetIntMetric(t, `vmagent_tenant_inserted_rows_total{type="prometheus",accountID="3",projectID="0"}`)
+	if v != 1 {
+		t.Fatalf("expected vmagent_tenant_inserted_rows_total to have value 1 for accountID=3, projectID=0")
+	}
+
+	headers.Set("AccountID", "3")
+	headers.Set("ProjectID", "3")
+	vmagent.APIV1ImportPrometheus(t, []string{
+		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
+	}, apptest.QueryOpts{Headers: headers})
+	v = vmagent.GetIntMetric(t, `vmagent_tenant_inserted_rows_total{type="prometheus",accountID="3",projectID="3"}`)
+	if v != 1 {
+		t.Fatalf("expected vmagent_tenant_inserted_rows_total to have value 1 for accountID=3, projectID=3")
+	}
+
+	// tenants in header and path clash - path should have higher priority on ingestion
+	opts := apptest.QueryOpts{Headers: make(http.Header)}
+	opts.Headers.Set("AccountID", "4")
+	opts.Tenant = "5"
+	vmagent.APIV1ImportPrometheus(t, []string{
+		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
+	}, opts)
+	v = vmagent.GetIntMetric(t, `vmagent_tenant_inserted_rows_total{type="prometheus",accountID="5",projectID="0"}`)
+	if v != 1 {
+		t.Fatalf("expected vmagent_tenant_inserted_rows_total to have value 1 for accountID=5, projectID=0")
+	}
+}

apptest/vmagent.go

@@ -19,10 +19,11 @@ import (
 // Vmagent holds the state of a vmagent app and provides vmagent-specific functions
 type Vmagent struct {
 	*app
-	*ServesMetrics
+	*metricsClient
 
-	httpListenAddr           string
-	apiV1ImportPrometheusURL string
+	httpListenAddr string
+
+	cli *Client
 }
 
 // StartVmagent starts an instance of vmagent with the given flags. It also
@@ -47,13 +48,10 @@ func StartVmagent(instance string, flags []string, cli *Client, promScrapeConfig
 	}
 
 	return &Vmagent{
-		app: app,
-		ServesMetrics: &ServesMetrics{
-			metricsURL: fmt.Sprintf("http://%s/metrics", stderrExtracts[0]),
-			cli:        cli,
-		},
-		httpListenAddr:           stderrExtracts[0],
-		apiV1ImportPrometheusURL: fmt.Sprintf("http://%s/api/v1/import/prometheus", stderrExtracts[0]),
+		app:            app,
+		metricsClient:  newMetricsClient(cli, stderrExtracts[0]),
+		httpListenAddr: stderrExtracts[0],
+		cli:            cli,
 	}, nil
 }
 
@@ -86,12 +84,33 @@ func (app *Vmagent) APIV1ImportPrometheusNoWaitFlush(t *testing.T, records []str
 	data := []byte(strings.Join(records, "\n"))
 	headers := opts.getHeaders()
 	headers.Set("Content-Type", "text/plain")
-	_, statusCode := app.cli.Post(t, app.apiV1ImportPrometheusURL, data, headers)
+	url := getVMAgentInsertPath(app.httpListenAddr, "prometheus/api/v1/import/prometheus", opts)
+	_, statusCode := app.cli.Post(t, url, data, headers)
 	if statusCode != http.StatusNoContent {
 		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
 	}
 }
 
+// getVMAgentInsertPath returns URL path for writes.
+// If tenant is set in QueryOpts, it will return cluster-like path for ingestion.
+// If tenant is empty, it will return single-node (no tenants) path.
+func getVMAgentInsertPath(addr, suffix string, o QueryOpts) string {
+	if o.Tenant != "" {
+		// QueryOpts.Tenant has priority over headers
+		return fmt.Sprintf("http://%s/insert/%s/%s", addr, o.Tenant, suffix)
+	}
+
+	h := o.getHeaders()
+	if h.Get("AccountID") != "" || h.Get("ProjectID") != "" {
+		// vmagent supports tenantID in HTTP headers only if -enableMultitenantHandlers and -enableMultitenancyViaHeaders are set
+		// see https://docs.victoriametrics.com/victoriametrics/vmagent/#multitenancy
+		return fmt.Sprintf("http://%s/insert/%s", addr, suffix)
+	}
+
+	// tenant is missing in QueryOpts and in HTTP headers. Use single-node (no tenants) path
+	return fmt.Sprintf("http://%s/%s", addr, suffix)
+}
+
 // RemoteWriteRequestsRetriesCountTotal sums up the total retries for remote write requests.
 func (app *Vmagent) RemoteWriteRequestsRetriesCountTotal(t *testing.T) int {
 	total := 0.0
@@ -168,10 +187,7 @@ func (app *Vmagent) ReloadRelabelConfigs(t *testing.T) {
 func (app *Vmagent) PrometheusAPIV1Write(t *testing.T, wr prompb.WriteRequest, opts QueryOpts) {
 	t.Helper()
 
-	url := fmt.Sprintf("http://%s/prometheus/api/v1/write", app.httpListenAddr)
-	if opts.Tenant != "" {
-		url = fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/write", app.httpListenAddr, opts.Tenant)
-	}
+	url := getVMAgentInsertPath(app.httpListenAddr, "prometheus/api/v1/write", opts)
 	data := snappy.Encode(nil, wr.MarshalProtobuf(nil))
 	recordsCount := len(wr.Timeseries)
 	if prommetadata.IsEnabled() {

apptest/vmauth.go

@@ -1,7 +1,6 @@
 package apptest
 
 import (
-	"fmt"
 	"io"
 	"regexp"
 	"syscall"
@@ -17,7 +16,7 @@ var httpBuilitinListenAddrRE = regexp.MustCompile(`pprof handlers are exposed at
 // functions.
 type Vmauth struct {
 	*app
-	*ServesMetrics
+	*metricsClient
 
 	httpListenAddr string
 	configFilePath string
@@ -45,11 +44,8 @@ func StartVmauth(instance string, flags []string, cli *Client, configFilePath st
 	}
 
 	return &Vmauth{
-		app: app,
-		ServesMetrics: &ServesMetrics{
-			metricsURL: fmt.Sprintf("http://%s/metrics", stderrExtracts[0]),
-			cli:        cli,
-		},
+		app:            app,
+		metricsClient:  newMetricsClient(cli, stderrExtracts[0]),
 		httpListenAddr: stderrExtracts[0],
 		configFilePath: configFilePath,
 		cli:            cli,

apptest/vminsert.go

@@ -3,30 +3,21 @@ package apptest
 import (
 	"fmt"
 	"io"
-	"net/http"
 	"regexp"
 	"strings"
 	"testing"
 	"time"
-
-	"github.com/golang/snappy"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prommetadata"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
 )
 
 // Vminsert holds the state of a vminsert app and provides vminsert-specific
 // functions.
 type Vminsert struct {
 	*app
-	*ServesMetrics
+	*metricsClient
+	*vminsertClient
 
 	httpListenAddr          string
 	clusternativeListenAddr string
-	graphiteListenAddr      string
-	openTSDBListenAddr      string
-
-	cli *Client
 }
 
 // storageNodes returns the storage node addresses passed to vminsert via
@@ -72,17 +63,26 @@ func StartVminsert(instance string, flags []string, cli *Client, output io.Write
 		return nil, err
 	}
 
+	metricsClient := newMetricsClient(cli, stderrExtracts[0])
 	return &Vminsert{
-		app: app,
-		ServesMetrics: &ServesMetrics{
-			metricsURL: fmt.Sprintf("http://%s/metrics", stderrExtracts[0]),
-			cli:        cli,
+		app:           app,
+		metricsClient: metricsClient,
+		vminsertClient: &vminsertClient{
+			vminsertCli: cli,
+			url: func(op, path string, opts QueryOpts) string {
+				return getClusterPath(stderrExtracts[0], op, path, opts)
+			},
+			openTSDBURL: func(op, path string, opts QueryOpts) string {
+				return getClusterPath(stderrExtracts[3], op, path, opts)
+			},
+			graphiteListenAddr: stderrExtracts[2],
+			sendBlocking: func(t *testing.T, numRecordsToSend int, send func()) {
+				t.Helper()
+				sendBlocking(t, metricsClient, numRecordsToSend, send)
+			},
 		},
 		httpListenAddr:          stderrExtracts[0],
 		clusternativeListenAddr: stderrExtracts[1],
-		graphiteListenAddr:      stderrExtracts[2],
-		openTSDBListenAddr:      stderrExtracts[3],
-		cli:                     cli,
 	}, nil
 }
 
@@ -98,213 +98,6 @@ func (app *Vminsert) HTTPAddr() string {
 	return app.httpListenAddr
 }
 
-// InfluxWrite is a test helper function that inserts a
-// collection of records in Influx line format by sending a HTTP
-// POST request to /influx/write vmsingle endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#influxwrite
-func (app *Vminsert) InfluxWrite(t *testing.T, records []string, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/insert/%s/influx/write", app.httpListenAddr, opts.getTenant())
-	uv := opts.asURLValues()
-	uvs := uv.Encode()
-	if len(uvs) > 0 {
-		url += "?" + uvs
-	}
-
-	data := []byte(strings.Join(records, "\n"))
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "text/plain")
-	app.sendBlocking(t, len(records), func() {
-		_, statusCode := app.cli.Post(t, url, data, headers)
-		if statusCode != http.StatusNoContent {
-			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
-		}
-	})
-}
-
-// GraphiteWrite is a test helper function that sends a
-// collection of records to graphiteListenAddr port.
-//
-// See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#ingesting
-func (app *Vminsert) GraphiteWrite(t *testing.T, records []string, _ QueryOpts) {
-	t.Helper()
-	app.cli.Write(t, app.graphiteListenAddr, records)
-}
-
-// PrometheusAPIV1ImportCSV is a test helper function that inserts a collection
-// of records in CSV format for the given tenant by sending an HTTP POST
-// request to prometheus/api/v1/import/csv vminsert endpoint.
-//
-// See https://docs.victoriametrics.com/cluster-victoriametrics/#url-format
-func (app *Vminsert) PrometheusAPIV1ImportCSV(t *testing.T, records []string, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/import/csv", app.httpListenAddr, opts.getTenant())
-	uv := opts.asURLValues()
-	uvs := uv.Encode()
-	if len(uvs) > 0 {
-		url += "?" + uvs
-	}
-	data := []byte(strings.Join(records, "\n"))
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "text/plain")
-	app.sendBlocking(t, len(records), func() {
-		_, statusCode := app.cli.Post(t, url, data, headers)
-		if statusCode != http.StatusNoContent {
-			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
-		}
-	})
-}
-
-// PrometheusAPIV1ImportNative is a test helper function that inserts a collection
-// of records in Native format for the given tenant by sending an HTTP POST
-// request to prometheus/api/v1/import/native vminsert endpoint.
-//
-// See https://docs.victoriametrics.com/cluster-victoriametrics/#url-format
-func (app *Vminsert) PrometheusAPIV1ImportNative(t *testing.T, data []byte, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/import/native", app.httpListenAddr, opts.getTenant())
-	uv := opts.asURLValues()
-	uvs := uv.Encode()
-	if len(uvs) > 0 {
-		url += "?" + uvs
-	}
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "text/plain")
-	app.sendBlocking(t, 1, func() {
-		_, statusCode := app.cli.Post(t, url, data, headers)
-		if statusCode != http.StatusNoContent {
-			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
-		}
-	})
-}
-
-// OpenTSDBAPIPut is a test helper function that inserts a collection of
-// records in OpenTSDB format for the given tenant by sending an HTTP POST
-// request to /opentsdb/api/put vminsert endpoint.
-//
-// See https://docs.victoriametrics.com/cluster-victoriametrics/#url-format
-func (app *Vminsert) OpenTSDBAPIPut(t *testing.T, records []string, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/insert/%s/opentsdb/api/put", app.openTSDBListenAddr, opts.getTenant())
-	uv := opts.asURLValues()
-	uvs := uv.Encode()
-	if len(uvs) > 0 {
-		url += "?" + uvs
-	}
-	data := []byte("[" + strings.Join(records, ",") + "]")
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "application/json")
-	app.sendBlocking(t, len(records), func() {
-		_, statusCode := app.cli.Post(t, url, data, headers)
-		if statusCode != http.StatusNoContent {
-			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
-		}
-	})
-}
-
-// PrometheusAPIV1Write is a test helper function that inserts a
-// collection of records in Prometheus remote-write format by sending a HTTP
-// POST request to /prometheus/api/v1/write vminsert endpoint.
-func (app *Vminsert) PrometheusAPIV1Write(t *testing.T, wr prompb.WriteRequest, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/write", app.httpListenAddr, opts.getTenant())
-	data := snappy.Encode(nil, wr.MarshalProtobuf(nil))
-	recordsCount := len(wr.Timeseries)
-	if prommetadata.IsEnabled() {
-		recordsCount += len(wr.Metadata)
-	}
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "application/x-protobuf")
-	app.sendBlocking(t, recordsCount, func() {
-		_, statusCode := app.cli.Post(t, url, data, headers)
-		if statusCode != http.StatusNoContent {
-			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
-		}
-	})
-}
-
-// PrometheusAPIV1ImportPrometheus is a test helper function that inserts a
-// collection of records in Prometheus text exposition format for the given
-// tenant by sending a HTTP POST request to
-// /prometheus/api/v1/import/prometheus vminsert endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1importprometheus
-func (app *Vminsert) PrometheusAPIV1ImportPrometheus(t *testing.T, records []string, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/import/prometheus", app.httpListenAddr, opts.getTenant())
-	uv := opts.asURLValues()
-	uvs := uv.Encode()
-	if len(uvs) > 0 {
-		url += "?" + uvs
-	}
-	data := []byte(strings.Join(records, "\n"))
-	var recordsCount int
-	var metadataRecords int
-	uniqueMetadataMetricNames := make(map[string]struct{})
-	for _, record := range records {
-		// metric metadata has the following format:
-		//# HELP importprometheus_series
-		//# TYPE importprometheus_series
-		// it results into single metadata record
-		if strings.HasPrefix(record, "# ") {
-			metadataItems := strings.Split(record, " ")
-			if len(metadataItems) < 2 {
-				t.Fatalf("BUG: unexpected metadata format=%q", record)
-			}
-			metricName := metadataItems[2]
-			if _, ok := uniqueMetadataMetricNames[metricName]; ok {
-				continue
-			}
-			uniqueMetadataMetricNames[metricName] = struct{}{}
-			metadataRecords++
-			continue
-		}
-		recordsCount++
-	}
-	if prommetadata.IsEnabled() {
-		recordsCount += metadataRecords
-	}
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "text/plain")
-	app.sendBlocking(t, recordsCount, func() {
-		_, statusCode := app.cli.Post(t, url, data, headers)
-		if statusCode != http.StatusNoContent {
-			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
-		}
-	})
-}
-
-// ZabbixConnectorHistory is a test helper function that inserts a
-// collection of records in zabbixconnector  format by sending a HTTP
-// POST request to /zabbixconnector/api/v1/history vmsingle endpoint.
-func (app *Vminsert) ZabbixConnectorHistory(t *testing.T, records []string, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/insert/%s/zabbixconnector/api/v1/history", app.httpListenAddr, opts.getTenant())
-	uv := opts.asURLValues()
-	uvs := uv.Encode()
-	if len(uvs) > 0 {
-		url += "?" + uvs
-	}
-	data := []byte(strings.Join(records, "\n"))
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "application/json")
-	app.sendBlocking(t, len(records), func() {
-		_, statusCode := app.cli.Post(t, url, data, headers)
-		if statusCode != http.StatusOK {
-			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
-		}
-	})
-
-}
-
 // String returns the string representation of the vminsert app state.
 func (app *Vminsert) String() string {
 	return fmt.Sprintf("{app: %s httpListenAddr: %q}", app.app, app.httpListenAddr)
@@ -320,13 +113,10 @@ func (app *Vminsert) String() string {
 // Waiting is implemented a retrieving the value of `vm_rpc_rows_sent_total`
 // metric and checking whether it is equal or greater than the wanted value.
 // If it is, then the data has been sent to vmstorage.
-//
-// Unreliable if the records are inserted concurrently.
-// TODO(rtm0): Put sending and waiting into a critical section to make reliable?
-func (app *Vminsert) sendBlocking(t *testing.T, numRecordsToSend int, send func()) {
+func sendBlocking(t *testing.T, c *metricsClient, numRecordsToSend int, send func()) {
 	t.Helper()
 
-	wantRowsSentCount := app.rpcRowsSentTotal(t) + numRecordsToSend
+	wantRowsSentCount := c.rpcRowsSentTotal(t) + numRecordsToSend
 
 	send()
 
@@ -335,7 +125,7 @@ func (app *Vminsert) sendBlocking(t *testing.T, numRecordsToSend int, send func(
 		period  = 100 * time.Millisecond
 	)
 	for range retries {
-		d := app.rpcRowsSentTotal(t)
+		d := c.rpcRowsSentTotal(t)
 		if d >= wantRowsSentCount {
 			return
 		}
@@ -343,14 +133,3 @@ func (app *Vminsert) sendBlocking(t *testing.T, numRecordsToSend int, send func(
 	}
 	t.Fatalf("timed out while waiting for inserted rows to be sent to vmstorage")
 }
-
-// rpcRowsSentTotal retrieves the values of all vminsert
-// `vm_rpc_rows_sent_total` metrics (there will be one for each vmstorage) and
-// returns their integer sum.
-func (app *Vminsert) rpcRowsSentTotal(t *testing.T) int {
-	total := 0.0
-	for _, v := range app.GetMetricsByPrefix(t, "vm_rpc_rows_sent_total") {
-		total += v
-	}
-	return int(total)
-}

apptest/vmselect.go

@@ -1,20 +1,17 @@
 package apptest
 
 import (
-	"encoding/json"
 	"fmt"
 	"io"
-	"net/http"
 	"regexp"
-	"strconv"
-	"testing"
 )
 
 // Vmselect holds the state of a vmselect app and provides vmselect-specific
 // functions.
 type Vmselect struct {
 	*app
-	*ServesMetrics
+	*metricsClient
+	*vmselectClient
 
 	httpListenAddr          string
 	clusternativeListenAddr string
@@ -41,10 +38,15 @@ func StartVmselect(instance string, flags []string, cli *Client, output io.Write
 	}
 
 	return &Vmselect{
-		app: app,
-		ServesMetrics: &ServesMetrics{
-			metricsURL: fmt.Sprintf("http://%s/metrics", stderrExtracts[0]),
-			cli:        cli,
+		app:           app,
+		metricsClient: newMetricsClient(cli, stderrExtracts[0]),
+		vmselectClient: &vmselectClient{
+			vmselectCli: cli,
+			url: func(op, path string, opts QueryOpts) string {
+				return getClusterPath(stderrExtracts[0], op, path, opts)
+			},
+			metricNamesStatsResetURL: fmt.Sprintf("http://%s/admin/api/v1/admin/status/metric_names_stats/reset", stderrExtracts[0]),
+			tenantsURL:               fmt.Sprintf("http://%s/admin/tenants", stderrExtracts[0]),
 		},
 		httpListenAddr:          stderrExtracts[0],
 		clusternativeListenAddr: stderrExtracts[1],
@@ -64,298 +66,6 @@ func (app *Vmselect) HTTPAddr() string {
 	return app.httpListenAddr
 }
 
-// PrometheusAPIV1Export is a test helper function that performs the export of
-// raw samples in JSON line format by sending a HTTP POST request to
-// /prometheus/api/v1/export vmselect endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1export
-func (app *Vmselect) PrometheusAPIV1Export(t *testing.T, query string, opts QueryOpts) *PrometheusAPIV1QueryResponse {
-	t.Helper()
-
-	exportURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/export", app.httpListenAddr, opts.getTenant())
-	values := opts.asURLValues()
-	values.Add("match[]", query)
-	values.Add("format", "promapi")
-	res, _ := app.cli.PostForm(t, exportURL, values, opts.Headers)
-	return NewPrometheusAPIV1QueryResponse(t, res)
-}
-
-// PrometheusAPIV1ExportNative is a test helper function that performs the export of
-// raw samples in native binary format by sending an HTTP POST request to
-// /prometheus/api/v1/export/native vmselect endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1exportnative
-func (app *Vmselect) PrometheusAPIV1ExportNative(t *testing.T, query string, opts QueryOpts) []byte {
-	t.Helper()
-
-	exportURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/export/native", app.httpListenAddr, opts.getTenant())
-	values := opts.asURLValues()
-	values.Add("match[]", query)
-	values.Add("format", "promapi")
-	res, _ := app.cli.PostForm(t, exportURL, values, opts.Headers)
-	return []byte(res)
-}
-
-// PrometheusAPIV1Query is a test helper function that performs PromQL/MetricsQL
-// instant query by sending a HTTP POST request to /prometheus/api/v1/query
-// vmselect endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1query
-func (app *Vmselect) PrometheusAPIV1Query(t *testing.T, query string, opts QueryOpts) *PrometheusAPIV1QueryResponse {
-	t.Helper()
-
-	queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/query", app.httpListenAddr, opts.getTenant())
-	values := opts.asURLValues()
-	values.Add("query", query)
-
-	res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	return NewPrometheusAPIV1QueryResponse(t, res)
-}
-
-// PrometheusAPIV1QueryRange is a test helper function that performs
-// PromQL/MetricsQL range query by sending a HTTP POST request to
-// /prometheus/api/v1/query_range vmselect endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1query_range
-func (app *Vmselect) PrometheusAPIV1QueryRange(t *testing.T, query string, opts QueryOpts) *PrometheusAPIV1QueryResponse {
-	t.Helper()
-
-	queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/query_range", app.httpListenAddr, opts.getTenant())
-	values := opts.asURLValues()
-	values.Add("query", query)
-
-	res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	return NewPrometheusAPIV1QueryResponse(t, res)
-}
-
-// PrometheusAPIV1Series sends a query to a /prometheus/api/v1/series endpoint
-// and returns the list of time series that match the query.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1series
-func (app *Vmselect) PrometheusAPIV1Series(t *testing.T, matchQuery string, opts QueryOpts) *PrometheusAPIV1SeriesResponse {
-	t.Helper()
-
-	seriesURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/series", app.httpListenAddr, opts.getTenant())
-	values := opts.asURLValues()
-	values.Add("match[]", matchQuery)
-
-	res, _ := app.cli.PostForm(t, seriesURL, values, opts.Headers)
-	return NewPrometheusAPIV1SeriesResponse(t, res)
-}
-
-// PrometheusAPIV1SeriesCount sends a query to a /prometheus/api/v1/series/count endpoint
-// and returns the total number of time series.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1series
-func (app *Vmselect) PrometheusAPIV1SeriesCount(t *testing.T, opts QueryOpts) *PrometheusAPIV1SeriesCountResponse {
-	t.Helper()
-
-	seriesURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/series/count", app.httpListenAddr, opts.getTenant())
-	values := opts.asURLValues()
-
-	res, _ := app.cli.PostForm(t, seriesURL, values, opts.Headers)
-	return NewPrometheusAPIV1SeriesCountResponse(t, res)
-}
-
-// PrometheusAPIV1Labels sends a query to a /prometheus/api/v1/labels endpoint
-// and returns the label names list of time series that match the query.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1labels
-func (app *Vmselect) PrometheusAPIV1Labels(t *testing.T, matchQuery string, opts QueryOpts) *PrometheusAPIV1LabelsResponse {
-	t.Helper()
-
-	values := opts.asURLValues()
-	values.Add("match[]", matchQuery)
-
-	queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/labels", app.httpListenAddr, opts.getTenant())
-	res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	return NewPrometheusAPIV1LabelsResponse(t, res)
-}
-
-// PrometheusAPIV1LabelValues sends a query to a /prometheus/api/v1/label/.../values endpoint
-// and returns the label names list of time series that match the query.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1labelvalues
-func (app *Vmselect) PrometheusAPIV1LabelValues(t *testing.T, labelName, matchQuery string, opts QueryOpts) *PrometheusAPIV1LabelValuesResponse {
-	t.Helper()
-
-	values := opts.asURLValues()
-	values.Add("match[]", matchQuery)
-	queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/label/%s/values", app.httpListenAddr, opts.getTenant(), labelName)
-
-	res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	return NewPrometheusAPIV1LabelValuesResponse(t, res)
-}
-
-// PrometheusAPIV1Metadata sends a query to a /prometheus/api/v1/metadata endpoint
-// and returns the results.
-func (app *Vmselect) PrometheusAPIV1Metadata(t *testing.T, metric string, limit int, opts QueryOpts) *PrometheusAPIV1Metadata {
-	t.Helper()
-
-	values := opts.asURLValues()
-	values.Add("metric", metric)
-	values.Add("limit", strconv.Itoa(limit))
-	queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/metadata", app.httpListenAddr, opts.getTenant())
-
-	res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	return NewPrometheusAPIV1Metadata(t, res)
-}
-
-// APIV1AdminTSDBDeleteSeries deletes the series that match the query by sending
-// a request to /api/v1/admin/tsdb/delete_series.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1admintsdbdelete_series
-func (app *Vmselect) APIV1AdminTSDBDeleteSeries(t *testing.T, matchQuery string, opts QueryOpts) {
-	t.Helper()
-
-	queryURL := fmt.Sprintf("http://%s/delete/%s/prometheus/api/v1/admin/tsdb/delete_series", app.httpListenAddr, opts.getTenant())
-	values := opts.asURLValues()
-	values.Add("match[]", matchQuery)
-
-	res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	if statusCode != http.StatusNoContent {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
-	}
-}
-
-// MetricNamesStats sends a query to a /select/tenant/prometheus/api/v1/status/metric_names_stats endpoint
-// and returns the statistics response for given params.
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#track-ingested-metrics-usage
-func (app *Vmselect) MetricNamesStats(t *testing.T, limit, le, matchPattern string, opts QueryOpts) MetricNamesStatsResponse {
-	t.Helper()
-
-	values := opts.asURLValues()
-	values.Add("limit", limit)
-	values.Add("le", le)
-	values.Add("match_pattern", matchPattern)
-	queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/status/metric_names_stats", app.httpListenAddr, opts.getTenant())
-
-	res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	if statusCode != http.StatusOK {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
-	}
-	var resp MetricNamesStatsResponse
-	if err := json.Unmarshal([]byte(res), &resp); err != nil {
-		t.Fatalf("could not unmarshal series response data:\n%s\n err: %v", res, err)
-	}
-	return resp
-}
-
-// MetricNamesStatsReset sends a query to a /admin/api/v1/status/metric_names_stats/reset endpoint
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#track-ingested-metrics-usage
-func (app *Vmselect) MetricNamesStatsReset(t *testing.T, opts QueryOpts) {
-	t.Helper()
-
-	values := opts.asURLValues()
-	queryURL := fmt.Sprintf("http://%s/admin/api/v1/admin/status/metric_names_stats/reset", app.httpListenAddr)
-
-	res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	if statusCode != http.StatusNoContent {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
-	}
-}
-
-// APIV1StatusTSDB sends a query to a /prometheus/api/v1/status/tsdb
-// //
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#tsdb-stats
-func (app *Vmselect) APIV1StatusTSDB(t *testing.T, matchQuery string, date string, topN string, opts QueryOpts) TSDBStatusResponse {
-	t.Helper()
-
-	seriesURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/status/tsdb", app.httpListenAddr, opts.getTenant())
-	values := opts.asURLValues()
-	addNonEmpty := func(name, value string) {
-		if len(value) == 0 {
-			return
-		}
-		values.Add(name, value)
-	}
-	addNonEmpty("match[]", matchQuery)
-	addNonEmpty("topN", topN)
-	addNonEmpty("date", date)
-
-	res, statusCode := app.cli.PostForm(t, seriesURL, values, opts.Headers)
-	if statusCode != http.StatusOK {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
-	}
-
-	var status TSDBStatusResponse
-	if err := json.Unmarshal([]byte(res), &status); err != nil {
-		t.Fatalf("could not unmarshal tsdb status response data:\n%s\n err: %v", res, err)
-	}
-	status.Sort()
-	return status
-}
-
-// GraphiteMetricsIndex sends a query to a /graphite/metrics/index.json
-//
-// See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#metrics-api
-func (app *Vmselect) GraphiteMetricsIndex(t *testing.T, opts QueryOpts) GraphiteMetricsIndexResponse {
-	t.Helper()
-
-	seriesURL := fmt.Sprintf("http://%s/select/%s/graphite/metrics/index.json", app.httpListenAddr, opts.getTenant())
-	res, statusCode := app.cli.Get(t, seriesURL, opts.Headers)
-	if statusCode != http.StatusOK {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
-	}
-
-	var index GraphiteMetricsIndexResponse
-	if err := json.Unmarshal([]byte(res), &index); err != nil {
-		t.Fatalf("could not unmarshal metrics index response data:\n%s\n err: %v", res, err)
-	}
-	return index
-}
-
-// GraphiteTagsTagSeries is a test helper function that registers Graphite tags
-// for a single time series by sending a HTTP POST request to
-// /graphite/tags/tagSeries vmsingle endpoint.
-func (app *Vmselect) GraphiteTagsTagSeries(t *testing.T, record string, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/select/%s/graphite/tags/tagSeries", app.httpListenAddr, opts.getTenant())
-	values := opts.asURLValues()
-	values.Add("path", record)
-
-	_, statusCode := app.cli.PostForm(t, url, values, opts.Headers)
-	if got, want := statusCode, http.StatusNotImplemented; got != want {
-		t.Fatalf("unexpected status code: got %d, want %d", got, want)
-	}
-}
-
-func (app *Vmselect) GraphiteTagsTagMultiSeries(t *testing.T, records []string, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/select/%s/graphite/tags/tagMultiSeries", app.httpListenAddr, opts.getTenant())
-	values := opts.asURLValues()
-	for _, rec := range records {
-		values.Add("path", rec)
-	}
-
-	_, statusCode := app.cli.PostForm(t, url, values, opts.Headers)
-	if got, want := statusCode, http.StatusNotImplemented; got != want {
-		t.Fatalf("unexpected status code: got %d, want %d", got, want)
-	}
-}
-
-// APIV1AdminTenants sends a query to a /admin/tenants endpoint
-func (app *Vmselect) APIV1AdminTenants(t *testing.T) *AdminTenantsResponse {
-	t.Helper()
-
-	tenantsURL := fmt.Sprintf("http://%s/admin/tenants", app.httpListenAddr)
-	res, statusCode := app.cli.Get(t, tenantsURL, nil)
-	if statusCode != http.StatusOK {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
-	}
-
-	var tenants *AdminTenantsResponse
-	if err := json.Unmarshal([]byte(res), tenants); err != nil {
-		t.Fatalf("could not unmarshal tenants response data:\n%s\n err: %v", res, err)
-	}
-
-	return tenants
-}
-
 // String returns the string representation of the vmselect app state.
 func (app *Vmselect) String() string {
 	return fmt.Sprintf("{app: %s httpListenAddr: %q}", app.app, app.httpListenAddr)

apptest/vmsingle.go

@@ -1,48 +1,25 @@
 package apptest
 
 import (
-	"encoding/json"
 	"fmt"
 	"io"
-	"net/http"
 	"os"
 	"regexp"
-	"strconv"
-	"strings"
 	"testing"
 	"time"
-
-	"github.com/golang/snappy"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
 )
 
 // Vmsingle holds the state of a vmsingle app and provides vmsingle-specific
 // functions.
 type Vmsingle struct {
 	*app
-	*ServesMetrics
+	*metricsClient
+	*vmstorageClient
+	*vmselectClient
+	*vminsertClient
 
 	storageDataPath string
 	httpListenAddr  string
-
-	// vmstorage URLs.
-	forceFlushURL string
-	forceMergeURL string
-
-	// vminsert URLs.
-	influxLineWriteURL                 string
-	graphiteWriteAddr                  string
-	openTSDBHTTPURL                    string
-	prometheusAPIV1ImportPrometheusURL string
-	prometheusAPIV1WriteURL            string
-
-	// vmselect URLs.
-	prometheusAPIV1ExportURL       string
-	prometheusAPIV1ExportNativeURL string
-	prometheusAPIV1QueryURL        string
-	prometheusAPIV1QueryRangeURL   string
-	prometheusAPIV1SeriesURL       string
 }
 
 // StartVmsingleAt starts an instance of vmsingle with the given flags. It also
@@ -69,596 +46,39 @@ func StartVmsingleAt(instance, binary string, flags []string, cli *Client, outpu
 	}
 
 	return &Vmsingle{
-		app: app,
-		ServesMetrics: &ServesMetrics{
-			metricsURL: fmt.Sprintf("http://%s/metrics", stderrExtracts[1]),
-			cli:        cli,
+		app:           app,
+		metricsClient: newMetricsClient(cli, stderrExtracts[1]),
+		vmstorageClient: &vmstorageClient{
+			vmstorageCli:   cli,
+			httpListenAddr: stderrExtracts[1],
+		},
+		vmselectClient: &vmselectClient{
+			vmselectCli: cli,
+			url: func(op, path string, opts QueryOpts) string {
+				return fmt.Sprintf("http://%s/%s", stderrExtracts[1], path)
+			},
+			metricNamesStatsResetURL: fmt.Sprintf("http://%s/api/v1/admin/status/metric_names_stats/reset", stderrExtracts[1]),
+			tenantsURL:               "vmsingle-does-not-serve-tenants",
+		},
+		vminsertClient: &vminsertClient{
+			vminsertCli: cli,
+			url: func(_, path string, _ QueryOpts) string {
+				return fmt.Sprintf("http://%s/%s", stderrExtracts[1], path)
+			},
+			openTSDBURL: func(_, path string, _ QueryOpts) string {
+				return fmt.Sprintf("http://%s/%s", stderrExtracts[3], path)
+			},
+			graphiteListenAddr: stderrExtracts[2],
+			sendBlocking: func(t *testing.T, _ int, send func()) {
+				t.Helper()
+				send()
+			},
 		},
 		storageDataPath: stderrExtracts[0],
 		httpListenAddr:  stderrExtracts[1],
-
-		forceFlushURL: fmt.Sprintf("http://%s/internal/force_flush", stderrExtracts[1]),
-		forceMergeURL: fmt.Sprintf("http://%s/internal/force_merge", stderrExtracts[1]),
-
-		influxLineWriteURL:                 fmt.Sprintf("http://%s/influx/write", stderrExtracts[1]),
-		graphiteWriteAddr:                  stderrExtracts[2],
-		openTSDBHTTPURL:                    fmt.Sprintf("http://%s", stderrExtracts[3]),
-		prometheusAPIV1ImportPrometheusURL: fmt.Sprintf("http://%s/prometheus/api/v1/import/prometheus", stderrExtracts[1]),
-		prometheusAPIV1WriteURL:            fmt.Sprintf("http://%s/prometheus/api/v1/write", stderrExtracts[1]),
-		prometheusAPIV1ExportURL:           fmt.Sprintf("http://%s/prometheus/api/v1/export", stderrExtracts[1]),
-		prometheusAPIV1ExportNativeURL:     fmt.Sprintf("http://%s/prometheus/api/v1/export/native", stderrExtracts[1]),
-		prometheusAPIV1QueryURL:            fmt.Sprintf("http://%s/prometheus/api/v1/query", stderrExtracts[1]),
-		prometheusAPIV1QueryRangeURL:       fmt.Sprintf("http://%s/prometheus/api/v1/query_range", stderrExtracts[1]),
-		prometheusAPIV1SeriesURL:           fmt.Sprintf("http://%s/prometheus/api/v1/series", stderrExtracts[1]),
 	}, nil
 }
 
-// ForceFlush is a test helper function that forces the flushing of inserted
-// data, so it becomes available for searching immediately.
-func (app *Vmsingle) ForceFlush(t *testing.T) {
-	t.Helper()
-
-	_, statusCode := app.cli.Get(t, app.forceFlushURL, nil)
-	if statusCode != http.StatusOK {
-		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
-	}
-}
-
-// ForceMerge is a test helper function that forces the merging of parts.
-func (app *Vmsingle) ForceMerge(t *testing.T) {
-	t.Helper()
-
-	_, statusCode := app.cli.Get(t, app.forceMergeURL, nil)
-	if statusCode != http.StatusOK {
-		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
-	}
-}
-
-// InfluxWrite is a test helper function that inserts a
-// collection of records in Influx line format by sending a HTTP
-// POST request to /influx/write vmsingle endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#influxwrite
-func (app *Vmsingle) InfluxWrite(t *testing.T, records []string, opts QueryOpts) {
-	t.Helper()
-
-	data := []byte(strings.Join(records, "\n"))
-
-	url := app.influxLineWriteURL
-	uv := opts.asURLValues()
-	uvs := uv.Encode()
-	if len(uvs) > 0 {
-		url += "?" + uvs
-	}
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "text/plain")
-	_, statusCode := app.cli.Post(t, url, data, headers)
-	if statusCode != http.StatusNoContent {
-		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
-	}
-}
-
-// GraphiteWrite is a test helper function that sends a collection of records
-// to graphiteListenAddr port.
-//
-// See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#ingesting
-func (app *Vmsingle) GraphiteWrite(t *testing.T, records []string, _ QueryOpts) {
-	t.Helper()
-	app.cli.Write(t, app.graphiteWriteAddr, records)
-}
-
-// PrometheusAPIV1ImportCSV is a test helper function that inserts a collection
-// of records in CSV format for the given tenant by sending an HTTP POST
-// request to /api/v1/import/csv vmsingle endpoint.
-//
-// See https://docs.victoriametrics.com/single-server-victoriametrics/#how-to-import-csv-data
-func (app *Vmsingle) PrometheusAPIV1ImportCSV(t *testing.T, records []string, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/api/v1/import/csv", app.httpListenAddr)
-	uv := opts.asURLValues()
-	uvs := uv.Encode()
-	if len(uvs) > 0 {
-		url += "?" + uvs
-	}
-	data := []byte(strings.Join(records, "\n"))
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "text/plain")
-	_, statusCode := app.cli.Post(t, url, data, headers)
-	if statusCode != http.StatusNoContent {
-		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
-	}
-}
-
-// PrometheusAPIV1ImportNative is a test helper function that inserts a collection
-// of records in native format for the given tenant by sending an HTTP POST
-// request to /api/v1/import/native vmsingle endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-import-data-in-native-format
-func (app *Vmsingle) PrometheusAPIV1ImportNative(t *testing.T, data []byte, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/api/v1/import/native", app.httpListenAddr)
-	uv := opts.asURLValues()
-	uvs := uv.Encode()
-	if len(uvs) > 0 {
-		url += "?" + uvs
-	}
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "text/plain")
-	_, statusCode := app.cli.Post(t, url, data, headers)
-	if statusCode != http.StatusNoContent {
-		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
-	}
-}
-
-// OpenTSDBAPIPut is a test helper function that inserts a collection of
-// records in OpenTSDB format for the given tenant by sending an HTTP POST
-// request to /api/put vmsingle endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/integrations/opentsdb/#sending-data-via-http
-func (app *Vmsingle) OpenTSDBAPIPut(t *testing.T, records []string, opts QueryOpts) {
-	t.Helper()
-
-	// add extra label
-	url := app.openTSDBHTTPURL + "/api/put"
-	uv := opts.asURLValues()
-	uvs := uv.Encode()
-	if len(uvs) > 0 {
-		url += "?" + uvs
-	}
-	data := []byte("[" + strings.Join(records, ",") + "]")
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "text/plain")
-	_, statusCode := app.cli.Post(t, url, data, headers)
-	if statusCode != http.StatusNoContent {
-		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
-	}
-}
-
-// PrometheusAPIV1Write is a test helper function that inserts a
-// collection of records in Prometheus remote-write format by sending a HTTP
-// POST request to /prometheus/api/v1/write vmsingle endpoint.
-func (app *Vmsingle) PrometheusAPIV1Write(t *testing.T, wr prompb.WriteRequest, opts QueryOpts) {
-	t.Helper()
-
-	data := snappy.Encode(nil, wr.MarshalProtobuf(nil))
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "application/x-protobuf")
-	_, statusCode := app.cli.Post(t, app.prometheusAPIV1WriteURL, data, headers)
-	if statusCode != http.StatusNoContent {
-		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
-	}
-}
-
-// PrometheusAPIV1ImportPrometheus is a test helper function that inserts a
-// collection of records in Prometheus text exposition format by sending a HTTP
-// POST request to /prometheus/api/v1/import/prometheus vmsingle endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1importprometheus
-func (app *Vmsingle) PrometheusAPIV1ImportPrometheus(t *testing.T, records []string, opts QueryOpts) {
-	t.Helper()
-
-	// add extra label
-	url := app.prometheusAPIV1ImportPrometheusURL
-	uv := opts.asURLValues()
-	uvs := uv.Encode()
-	if len(uvs) > 0 {
-		url += "?" + uvs
-	}
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "text/plain")
-	data := []byte(strings.Join(records, "\n"))
-	_, statusCode := app.cli.Post(t, url, data, headers)
-	if statusCode != http.StatusNoContent {
-		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
-	}
-}
-
-// PrometheusAPIV1Export is a test helper function that performs the export of
-// raw samples in JSON line format by sending a HTTP POST request to
-// /prometheus/api/v1/export vmsingle endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1export
-func (app *Vmsingle) PrometheusAPIV1Export(t *testing.T, query string, opts QueryOpts) *PrometheusAPIV1QueryResponse {
-	t.Helper()
-	values := opts.asURLValues()
-	values.Add("match[]", query)
-	values.Add("format", "promapi")
-
-	res, _ := app.cli.PostForm(t, app.prometheusAPIV1ExportURL, values, opts.Headers)
-	return NewPrometheusAPIV1QueryResponse(t, res)
-}
-
-// PrometheusAPIV1ExportNative is a test helper function that performs the export of
-// raw samples in native binary format by sending an HTTP POST request to
-// /prometheus/api/v1/export/native vmselect endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1exportnative
-func (app *Vmsingle) PrometheusAPIV1ExportNative(t *testing.T, query string, opts QueryOpts) []byte {
-	t.Helper()
-
-	t.Helper()
-	values := opts.asURLValues()
-	values.Add("match[]", query)
-	values.Add("format", "promapi")
-
-	res, _ := app.cli.PostForm(t, app.prometheusAPIV1ExportNativeURL, values, opts.Headers)
-	return []byte(res)
-}
-
-// PrometheusAPIV1Query is a test helper function that performs PromQL/MetricsQL
-// instant query by sending a HTTP POST request to /prometheus/api/v1/query
-// vmsingle endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1query
-func (app *Vmsingle) PrometheusAPIV1Query(t *testing.T, query string, opts QueryOpts) *PrometheusAPIV1QueryResponse {
-	t.Helper()
-
-	values := opts.asURLValues()
-	values.Add("query", query)
-	res, _ := app.cli.PostForm(t, app.prometheusAPIV1QueryURL, values, opts.Headers)
-	return NewPrometheusAPIV1QueryResponse(t, res)
-}
-
-// PrometheusAPIV1QueryRange is a test helper function that performs
-// PromQL/MetricsQL range query by sending a HTTP POST request to
-// /prometheus/api/v1/query_range vmsingle endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1query_range
-func (app *Vmsingle) PrometheusAPIV1QueryRange(t *testing.T, query string, opts QueryOpts) *PrometheusAPIV1QueryResponse {
-	t.Helper()
-
-	values := opts.asURLValues()
-	values.Add("query", query)
-
-	res, _ := app.cli.PostForm(t, app.prometheusAPIV1QueryRangeURL, values, opts.Headers)
-	return NewPrometheusAPIV1QueryResponse(t, res)
-}
-
-// PrometheusAPIV1Series sends a query to a /prometheus/api/v1/series endpoint
-// and returns the list of time series that match the query.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1series
-func (app *Vmsingle) PrometheusAPIV1Series(t *testing.T, matchQuery string, opts QueryOpts) *PrometheusAPIV1SeriesResponse {
-	t.Helper()
-
-	values := opts.asURLValues()
-	values.Add("match[]", matchQuery)
-
-	res, _ := app.cli.PostForm(t, app.prometheusAPIV1SeriesURL, values, opts.Headers)
-	return NewPrometheusAPIV1SeriesResponse(t, res)
-}
-
-// PrometheusAPIV1SeriesCount sends a query to a /prometheus/api/v1/series/count endpoint
-// and returns the total number of time series.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1series
-func (app *Vmsingle) PrometheusAPIV1SeriesCount(t *testing.T, opts QueryOpts) *PrometheusAPIV1SeriesCountResponse {
-	t.Helper()
-
-	values := opts.asURLValues()
-
-	queryURL := fmt.Sprintf("http://%s/prometheus/api/v1/series/count", app.httpListenAddr)
-	res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	return NewPrometheusAPIV1SeriesCountResponse(t, res)
-}
-
-// PrometheusAPIV1Labels sends a query to a /prometheus/api/v1/labels endpoint
-// and returns the label names list of time series that match the query.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1labels
-func (app *Vmsingle) PrometheusAPIV1Labels(t *testing.T, matchQuery string, opts QueryOpts) *PrometheusAPIV1LabelsResponse {
-	t.Helper()
-
-	values := opts.asURLValues()
-	values.Add("match[]", matchQuery)
-
-	queryURL := fmt.Sprintf("http://%s/prometheus/api/v1/labels", app.httpListenAddr)
-	res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	return NewPrometheusAPIV1LabelsResponse(t, res)
-}
-
-// PrometheusAPIV1LabelValues sends a query to a /prometheus/api/v1/label/.../values endpoint
-// and returns the label names list of time series that match the query.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1labelvalues
-func (app *Vmsingle) PrometheusAPIV1LabelValues(t *testing.T, labelName, matchQuery string, opts QueryOpts) *PrometheusAPIV1LabelValuesResponse {
-	t.Helper()
-
-	values := opts.asURLValues()
-	values.Add("match[]", matchQuery)
-
-	queryURL := fmt.Sprintf("http://%s/prometheus/api/v1/label/%s/values", app.httpListenAddr, labelName)
-	res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	return NewPrometheusAPIV1LabelValuesResponse(t, res)
-}
-
-// PrometheusAPIV1Metadata sends a query to a /prometheus/api/v1/metadata endpoint
-// and returns the results.
-func (app *Vmsingle) PrometheusAPIV1Metadata(t *testing.T, metric string, limit int, opts QueryOpts) *PrometheusAPIV1Metadata {
-	t.Helper()
-
-	values := opts.asURLValues()
-	values.Add("metric", metric)
-	values.Add("limit", strconv.Itoa(limit))
-	queryURL := fmt.Sprintf("http://%s/prometheus/api/v1/metadata", app.httpListenAddr)
-
-	res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	return NewPrometheusAPIV1Metadata(t, res)
-}
-
-// APIV1AdminTSDBDeleteSeries deletes the series that match the query by sending
-// a request to /api/v1/admin/tsdb/delete_series.
-//
-// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1admintsdbdelete_series
-func (app *Vmsingle) APIV1AdminTSDBDeleteSeries(t *testing.T, matchQuery string, opts QueryOpts) {
-	t.Helper()
-
-	queryURL := fmt.Sprintf("http://%s/api/v1/admin/tsdb/delete_series", app.httpListenAddr)
-	values := opts.asURLValues()
-	values.Add("match[]", matchQuery)
-
-	res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	if statusCode != http.StatusNoContent {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
-	}
-}
-
-// GraphiteMetricsIndex sends a query to a /metrics/index.json
-//
-// See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#metrics-api
-func (app *Vmsingle) GraphiteMetricsIndex(t *testing.T, _ QueryOpts) GraphiteMetricsIndexResponse {
-	t.Helper()
-
-	seriesURL := fmt.Sprintf("http://%s/metrics/index.json", app.httpListenAddr)
-	res, statusCode := app.cli.Get(t, seriesURL, nil)
-	if statusCode != http.StatusOK {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
-	}
-
-	var index GraphiteMetricsIndexResponse
-	if err := json.Unmarshal([]byte(res), &index); err != nil {
-		t.Fatalf("could not unmarshal metrics index response data:\n%s\n err: %v", res, err)
-	}
-	return index
-}
-
-// GraphiteTagsTagSeries is a test helper function that registers Graphite tags
-// for a single time series by sending a HTTP POST request to
-// /graphite/tags/tagSeries vmsingle endpoint.
-func (app *Vmsingle) GraphiteTagsTagSeries(t *testing.T, record string, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/graphite/tags/tagSeries", app.httpListenAddr)
-	values := opts.asURLValues()
-	values.Add("path", record)
-
-	_, statusCode := app.cli.PostForm(t, url, values, opts.Headers)
-	if got, want := statusCode, http.StatusNotImplemented; got != want {
-		t.Fatalf("unexpected status code: got %d, want %d", got, want)
-	}
-}
-
-func (app *Vmsingle) GraphiteTagsTagMultiSeries(t *testing.T, records []string, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/graphite/tags/tagMultiSeries", app.httpListenAddr)
-	values := opts.asURLValues()
-	for _, rec := range records {
-		values.Add("path", rec)
-	}
-
-	_, statusCode := app.cli.PostForm(t, url, values, opts.Headers)
-	if got, want := statusCode, http.StatusNotImplemented; got != want {
-		t.Fatalf("unexpected status code: got %d, want %d", got, want)
-	}
-}
-
-// APIV1StatusMetricNamesStats sends a query to a /api/v1/status/metric_names_stats endpoint
-// and returns the statistics response for given params.
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#track-ingested-metrics-usage
-func (app *Vmsingle) APIV1StatusMetricNamesStats(t *testing.T, limit, le, matchPattern string, opts QueryOpts) MetricNamesStatsResponse {
-	t.Helper()
-
-	values := opts.asURLValues()
-	values.Add("limit", limit)
-	values.Add("le", le)
-	values.Add("match_pattern", matchPattern)
-	queryURL := fmt.Sprintf("http://%s/api/v1/status/metric_names_stats", app.httpListenAddr)
-
-	res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	if statusCode != http.StatusOK {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
-	}
-	var resp MetricNamesStatsResponse
-	if err := json.Unmarshal([]byte(res), &resp); err != nil {
-		t.Fatalf("could not unmarshal metric names stats response data:\n%s\n err: %v", res, err)
-	}
-	return resp
-}
-
-// APIV1AdminStatusMetricNamesStatsReset sends a query to a /api/v1/admin/status/metric_names_stats/reset endpoint
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#track-ingested-metrics-usage
-func (app *Vmsingle) APIV1AdminStatusMetricNamesStatsReset(t *testing.T, opts QueryOpts) {
-	t.Helper()
-
-	values := opts.asURLValues()
-	queryURL := fmt.Sprintf("http://%s/api/v1/admin/status/metric_names_stats/reset", app.httpListenAddr)
-
-	res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
-	if statusCode != http.StatusNoContent {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
-	}
-}
-
-// SnapshotCreate creates a database snapshot by sending a query to the
-// /snapshot/create endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots
-func (app *Vmsingle) SnapshotCreate(t *testing.T) *SnapshotCreateResponse {
-	t.Helper()
-
-	data, statusCode := app.cli.Post(t, app.SnapshotCreateURL(), nil, nil)
-	if got, want := statusCode, http.StatusOK; got != want {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
-	}
-
-	var res SnapshotCreateResponse
-	if err := json.Unmarshal([]byte(data), &res); err != nil {
-		t.Fatalf("could not unmarshal snapshot create response: data=%q, err: %v", data, err)
-	}
-
-	return &res
-}
-
-// SnapshotCreateURL returns the URL for creating snapshots.
-func (app *Vmsingle) SnapshotCreateURL() string {
-	return fmt.Sprintf("http://%s/snapshot/create", app.httpListenAddr)
-}
-
-// APIV1AdminTSDBSnapshot creates a database snapshot by sending a query to the
-// /api/v1/admin/tsdb/snapshot endpoint.
-//
-// See https://prometheus.io/docs/prometheus/latest/querying/api/#snapshot.
-func (app *Vmsingle) APIV1AdminTSDBSnapshot(t *testing.T) *APIV1AdminTSDBSnapshotResponse {
-	t.Helper()
-
-	queryURL := fmt.Sprintf("http://%s/api/v1/admin/tsdb/snapshot", app.httpListenAddr)
-	data, statusCode := app.cli.Post(t, queryURL, nil, nil)
-	if got, want := statusCode, http.StatusOK; got != want {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
-	}
-
-	var res APIV1AdminTSDBSnapshotResponse
-	if err := json.Unmarshal([]byte(data), &res); err != nil {
-		t.Fatalf("could not unmarshal prometheus snapshot create response: data=%q, err: %v", data, err)
-	}
-
-	return &res
-}
-
-// SnapshotList lists existing database snapshots by sending a query to the
-// /snapshot/list endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots
-func (app *Vmsingle) SnapshotList(t *testing.T) *SnapshotListResponse {
-	t.Helper()
-
-	queryURL := fmt.Sprintf("http://%s/snapshot/list", app.httpListenAddr)
-	data, statusCode := app.cli.Get(t, queryURL, nil)
-	if got, want := statusCode, http.StatusOK; got != want {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
-	}
-
-	var res SnapshotListResponse
-	if err := json.Unmarshal([]byte(data), &res); err != nil {
-		t.Fatalf("could not unmarshal snapshot list response: data=%q, err: %v", data, err)
-	}
-
-	return &res
-}
-
-// SnapshotDelete deletes a snapshot by sending a query to the
-// /snapshot/delete endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots
-func (app *Vmsingle) SnapshotDelete(t *testing.T, snapshotName string) *SnapshotDeleteResponse {
-	t.Helper()
-
-	queryURL := fmt.Sprintf("http://%s/snapshot/delete?snapshot=%s", app.httpListenAddr, snapshotName)
-	data, statusCode := app.cli.Delete(t, queryURL)
-	wantStatusCodes := map[int]bool{
-		http.StatusOK:                  true,
-		http.StatusInternalServerError: true,
-	}
-	if !wantStatusCodes[statusCode] {
-		t.Fatalf("unexpected status code: got %d, want %v, resp text=%q", statusCode, wantStatusCodes, data)
-	}
-
-	var res SnapshotDeleteResponse
-	if err := json.Unmarshal([]byte(data), &res); err != nil {
-		t.Fatalf("could not unmarshal snapshot delete response: data=%q, err: %v", data, err)
-	}
-
-	return &res
-}
-
-// SnapshotDeleteAll deletes all snapshots by sending a query to the
-// /snapshot/delete_all endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots
-func (app *Vmsingle) SnapshotDeleteAll(t *testing.T) *SnapshotDeleteAllResponse {
-	t.Helper()
-
-	queryURL := fmt.Sprintf("http://%s/snapshot/delete_all", app.httpListenAddr)
-	data, statusCode := app.cli.Get(t, queryURL, nil)
-	if got, want := statusCode, http.StatusOK; got != want {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
-	}
-
-	var res SnapshotDeleteAllResponse
-	if err := json.Unmarshal([]byte(data), &res); err != nil {
-		t.Fatalf("could not unmarshal snapshot delete all response: data=%q, err: %v", data, err)
-	}
-
-	return &res
-}
-
-// APIV1StatusTSDB sends a query to a /prometheus/api/v1/status/tsdb
-// //
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#tsdb-stats
-func (app *Vmsingle) APIV1StatusTSDB(t *testing.T, matchQuery string, date string, topN string, opts QueryOpts) TSDBStatusResponse {
-	t.Helper()
-
-	seriesURL := fmt.Sprintf("http://%s/prometheus/api/v1/status/tsdb", app.httpListenAddr)
-	values := opts.asURLValues()
-	addNonEmpty := func(name, value string) {
-		if len(value) == 0 {
-			return
-		}
-		values.Add(name, value)
-	}
-	addNonEmpty("match[]", matchQuery)
-	addNonEmpty("topN", topN)
-	addNonEmpty("date", date)
-
-	res, statusCode := app.cli.PostForm(t, seriesURL, values, opts.Headers)
-	if statusCode != http.StatusOK {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
-	}
-
-	var status TSDBStatusResponse
-	if err := json.Unmarshal([]byte(res), &status); err != nil {
-		t.Fatalf("could not unmarshal tsdb status response data:\n%s\n err: %v", res, err)
-	}
-	status.Sort()
-	return status
-}
-
-// ZabbixConnectorHistory is a test helper function that inserts a
-// collection of records in zabbixconnector  format by sending a HTTP
-// POST request to /zabbixconnector/api/v1/history vmsingle endpoint.
-func (app *Vmsingle) ZabbixConnectorHistory(t *testing.T, records []string, opts QueryOpts) {
-	t.Helper()
-
-	url := fmt.Sprintf("http://%s/zabbixconnector/api/v1/history", app.httpListenAddr)
-	uv := opts.asURLValues()
-	uvs := uv.Encode()
-	if len(uvs) > 0 {
-		url += "?" + uvs
-	}
-	data := []byte(strings.Join(records, "\n"))
-	headers := opts.getHeaders()
-	headers.Set("Content-Type", "application/json")
-	_, statusCode := app.cli.Post(t, url, data, headers)
-	if statusCode != http.StatusOK {
-		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
-	}
-}
-
 // HTTPAddr returns the address at which the vminsert process is
 // listening for incoming HTTP requests.
 func (app *Vmsingle) HTTPAddr() string {

apptest/vmstorage.go

@@ -1,13 +1,10 @@
 package apptest
 
 import (
-	"encoding/json"
 	"fmt"
 	"io"
-	"net/http"
 	"os"
 	"regexp"
-	"testing"
 	"time"
 )
 
@@ -15,7 +12,8 @@ import (
 // functions.
 type Vmstorage struct {
 	*app
-	*ServesMetrics
+	*metricsClient
+	*vmstorageClient
 
 	storageDataPath string
 	httpListenAddr  string
@@ -47,10 +45,11 @@ func StartVmstorageAt(instance, binary string, flags []string, cli *Client, outp
 	}
 
 	return &Vmstorage{
-		app: app,
-		ServesMetrics: &ServesMetrics{
-			metricsURL: fmt.Sprintf("http://%s/metrics", stderrExtracts[1]),
-			cli:        cli,
+		app:           app,
+		metricsClient: newMetricsClient(cli, stderrExtracts[1]),
+		vmstorageClient: &vmstorageClient{
+			vmstorageCli:   cli,
+			httpListenAddr: stderrExtracts[1],
 		},
 		storageDataPath: stderrExtracts[0],
 		httpListenAddr:  stderrExtracts[1],
@@ -71,121 +70,6 @@ func (app *Vmstorage) VmselectAddr() string {
 	return app.vmselectAddr
 }
 
-// ForceFlush is a test helper function that forces the flushing of inserted
-// data, so it becomes available for searching immediately.
-func (app *Vmstorage) ForceFlush(t *testing.T) {
-	t.Helper()
-
-	forceFlushURL := fmt.Sprintf("http://%s/internal/force_flush", app.httpListenAddr)
-	_, statusCode := app.cli.Get(t, forceFlushURL, nil)
-	if statusCode != http.StatusOK {
-		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
-	}
-}
-
-// ForceMerge is a test helper function that forces the merging of parts.
-func (app *Vmstorage) ForceMerge(t *testing.T) {
-	t.Helper()
-
-	forceMergeURL := fmt.Sprintf("http://%s/internal/force_merge", app.httpListenAddr)
-	_, statusCode := app.cli.Get(t, forceMergeURL, nil)
-	if statusCode != http.StatusOK {
-		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
-	}
-}
-
-// SnapshotCreate creates a database snapshot by sending a query to the
-// /snapshot/create endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots
-func (app *Vmstorage) SnapshotCreate(t *testing.T) *SnapshotCreateResponse {
-	t.Helper()
-
-	data, statusCode := app.cli.Post(t, app.SnapshotCreateURL(), nil, nil)
-	if got, want := statusCode, http.StatusOK; got != want {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
-	}
-
-	var res SnapshotCreateResponse
-	if err := json.Unmarshal([]byte(data), &res); err != nil {
-		t.Fatalf("could not unmarshal snapshot create response: data=%q, err: %v", data, err)
-	}
-
-	return &res
-}
-
-// SnapshotCreateURL returns the URL for creating snapshots.
-func (app *Vmstorage) SnapshotCreateURL() string {
-	return fmt.Sprintf("http://%s/snapshot/create", app.httpListenAddr)
-}
-
-// SnapshotList lists existing database snapshots by sending a query to the
-// /snapshot/list endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots
-func (app *Vmstorage) SnapshotList(t *testing.T) *SnapshotListResponse {
-	t.Helper()
-
-	queryURL := fmt.Sprintf("http://%s/snapshot/list", app.httpListenAddr)
-	data, statusCode := app.cli.Get(t, queryURL, nil)
-	if got, want := statusCode, http.StatusOK; got != want {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
-	}
-
-	var res SnapshotListResponse
-	if err := json.Unmarshal([]byte(data), &res); err != nil {
-		t.Fatalf("could not unmarshal snapshot list response: data=%q, err: %v", data, err)
-	}
-
-	return &res
-}
-
-// SnapshotDelete deletes a snapshot by sending a query to the
-// /snapshot/delete endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots
-func (app *Vmstorage) SnapshotDelete(t *testing.T, snapshotName string) *SnapshotDeleteResponse {
-	t.Helper()
-
-	queryURL := fmt.Sprintf("http://%s/snapshot/delete?snapshot=%s", app.httpListenAddr, snapshotName)
-	data, statusCode := app.cli.Delete(t, queryURL)
-	wantStatusCodes := map[int]bool{
-		http.StatusOK:                  true,
-		http.StatusInternalServerError: true,
-	}
-	if !wantStatusCodes[statusCode] {
-		t.Fatalf("unexpected status code: got %d, want %v, resp text=%q", statusCode, wantStatusCodes, data)
-	}
-
-	var res SnapshotDeleteResponse
-	if err := json.Unmarshal([]byte(data), &res); err != nil {
-		t.Fatalf("could not unmarshal snapshot delete response: data=%q, err: %v", data, err)
-	}
-
-	return &res
-}
-
-// SnapshotDeleteAll deletes all snapshots by sending a query to the
-// /snapshot/delete_all endpoint.
-//
-// See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots
-func (app *Vmstorage) SnapshotDeleteAll(t *testing.T) *SnapshotDeleteAllResponse {
-	t.Helper()
-
-	queryURL := fmt.Sprintf("http://%s/snapshot/delete_all", app.httpListenAddr)
-	data, statusCode := app.cli.Post(t, queryURL, nil, nil)
-	if got, want := statusCode, http.StatusOK; got != want {
-		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
-	}
-
-	var res SnapshotDeleteAllResponse
-	if err := json.Unmarshal([]byte(data), &res); err != nil {
-		t.Fatalf("could not unmarshal snapshot delete all response: data=%q, err: %v", data, err)
-	}
-
-	return &res
-}
-
 // String returns the string representation of the vmstorage app state.
 func (app *Vmstorage) String() string {
 	return fmt.Sprintf("{app: %s storageDataPath: %q httpListenAddr: %q vminsertAddr: %q vmselectAddr: %q}", []any{

dashboards/victoriametrics-cluster.json

@@ -3109,7 +3109,6 @@
                   "mode": "off"
                 }
               },
-              "decimals": 0,
               "links": [],
               "mappings": [],
               "min": 0,

dashboards/victoriametrics.json

@@ -3406,7 +3406,6 @@
                   "mode": "off"
                 }
               },
-              "decimals": 0,
               "links": [],
               "mappings": [],
               "min": 0,

dashboards/vm/victoriametrics-cluster.json

@@ -3110,7 +3110,6 @@
                   "mode": "off"
                 }
               },
-              "decimals": 0,
               "links": [],
               "mappings": [],
               "min": 0,

dashboards/vm/victoriametrics.json

@@ -3407,7 +3407,6 @@
                   "mode": "off"
                 }
               },
-              "decimals": 0,
               "links": [],
               "mappings": [],
               "min": 0,

dashboards/vm/vmagent.json

@@ -2946,7 +2946,6 @@
                   "mode": "off"
                 }
               },
-              "decimals": 0,
               "links": [],
               "mappings": [],
               "min": 0,
@@ -7600,6 +7599,514 @@
         "x": 0,
         "y": 43
       },
+      "id": 163,
+      "panels": [
+        {
+          "datasource": {
+            "type": "victoriametrics-metrics-datasource",
+            "uid": "$ds"
+          },
+          "description": "Positive series show bytes written by vmagent producers into Kafka. Negative series show bytes read by vmagent consumers from Kafka. Read this together with Messages in / out: a stable byte rate with rising message rate usually means smaller Kafka payloads and higher per-message overhead. Producer Kafka metrics aggregate at job level because they do not expose the full remoteWrite URL label.\n\nDocs: <a href=\"https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#estimating-message-size-and-rate\" target=\"_blank\">estimating message size and rate</a>. Kafka read docs: <a href=\"https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics\" target=\"_blank\">reading metrics</a>.",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": true,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "barWidthFactor": 0.6,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "never",
+                "showValues": false,
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "links": [],
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  }
+                ]
+              },
+              "unit": "Bps"
+            },
+            "overrides": []
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 0,
+            "y": 44
+          },
+          "id": 164,
+          "links": [
+            {
+              "title": "Docs: estimating size/rate",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#estimating-message-size-and-rate"
+            },
+            {
+              "title": "Docs: reading metrics",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics"
+            }
+          ],
+          "options": {
+            "legend": {
+              "calcs": [
+                "mean",
+                "lastNotNull",
+                "max"
+              ],
+              "displayMode": "table",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "hideZeros": false,
+              "mode": "multi",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "12.2.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "victoriametrics-metrics-datasource",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmagent_remotewrite_kafka_sent_bytes_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Produced to Kafka",
+              "range": true,
+              "refId": "A"
+            },
+            {
+              "datasource": {
+                "type": "victoriametrics-metrics-datasource",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "-sum(rate(vmagent_kafka_consumer_read_bytes_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Consumed from Kafka",
+              "range": true,
+              "refId": "B"
+            }
+          ],
+          "title": "Traffic (bytes)",
+          "type": "timeseries"
+        },
+        {
+          "datasource": {
+            "type": "victoriametrics-metrics-datasource",
+            "uid": "$ds"
+          },
+          "description": "Positive series show Kafka messages produced by vmagent. Negative series show Kafka messages consumed by vmagent. Read this together with Traffic (bytes), because a stable byte rate with rising message rate usually means smaller Kafka messages and higher per-message overhead. Producer Kafka metrics aggregate at job level because they do not expose the full remoteWrite URL label.\n\nDocs: <a href=\"https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#estimating-message-size-and-rate\" target=\"_blank\">estimating message size and rate</a>. Kafka read docs: <a href=\"https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics\" target=\"_blank\">reading metrics</a>.",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": true,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "barWidthFactor": 0.6,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "never",
+                "showValues": false,
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "links": [],
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  }
+                ]
+              },
+              "unit": "ops"
+            },
+            "overrides": []
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 12,
+            "y": 44
+          },
+          "id": 165,
+          "links": [
+            {
+              "title": "Docs: estimating size/rate",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#estimating-message-size-and-rate"
+            },
+            {
+              "title": "Docs: reading metrics",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics"
+            }
+          ],
+          "options": {
+            "legend": {
+              "calcs": [
+                "mean",
+                "lastNotNull",
+                "max"
+              ],
+              "displayMode": "table",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "hideZeros": false,
+              "mode": "multi",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "12.2.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "victoriametrics-metrics-datasource",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmagent_remotewrite_kafka_messages_sent_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Produced to Kafka",
+              "range": true,
+              "refId": "A"
+            },
+            {
+              "datasource": {
+                "type": "victoriametrics-metrics-datasource",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "-sum(rate(vmagent_kafka_messages_read_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Consumed from Kafka",
+              "range": true,
+              "refId": "B"
+            }
+          ],
+          "title": "Messages in / out",
+          "type": "timeseries"
+        },
+        {
+          "datasource": {
+            "type": "victoriametrics-metrics-datasource",
+            "uid": "$ds"
+          },
+          "description": "Kafka producer-side errors from vmagent remote write. This panel shows send errors and delivery errors reported by Kafka producers.\n\nKafka write docs: <a href=\"https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#writing-metrics\" target=\"_blank\">writing metrics</a>.",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": false,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "barWidthFactor": 0.6,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "never",
+                "showValues": false,
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "links": [],
+              "mappings": [],
+              "min": 0,
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": 0
+                  },
+                  {
+                    "color": "red",
+                    "value": 80
+                  }
+                ]
+              },
+              "unit": "ops"
+            },
+            "overrides": []
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 0,
+            "y": 52
+          },
+          "id": 167,
+          "links": [
+            {
+              "title": "Docs: writing metrics",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#writing-metrics"
+            },
+            {
+              "title": "Docs: reading metrics",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics"
+            }
+          ],
+          "options": {
+            "legend": {
+              "calcs": [
+                "mean",
+                "lastNotNull",
+                "max"
+              ],
+              "displayMode": "table",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "hideZeros": false,
+              "mode": "multi",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "12.2.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "victoriametrics-metrics-datasource",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmagent_remotewrite_kafka_messages_send_errors_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Producer send errors",
+              "range": true,
+              "refId": "A"
+            },
+            {
+              "datasource": {
+                "type": "victoriametrics-metrics-datasource",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmagent_remotewrite_kafka_messages_delivery_errors_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Producer delivery errors",
+              "range": true,
+              "refId": "B"
+            }
+          ],
+          "title": "Producer errors",
+          "type": "timeseries"
+        },
+        {
+          "datasource": {
+            "type": "victoriametrics-metrics-datasource",
+            "uid": "$ds"
+          },
+          "description": "Kafka consumer-side errors from vmagent. This panel shows client errors and ingest errors reported while reading from Kafka and passing data further downstream.\n\nKafka read docs: <a href=\"https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics\" target=\"_blank\">reading metrics</a>.",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": false,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "barWidthFactor": 0.6,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "never",
+                "showValues": false,
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "links": [],
+              "mappings": [],
+              "min": 0,
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": 0
+                  },
+                  {
+                    "color": "red",
+                    "value": 80
+                  }
+                ]
+              },
+              "unit": "ops"
+            },
+            "overrides": []
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 12,
+            "y": 52
+          },
+          "id": 168,
+          "links": [
+            {
+              "title": "Docs: reading metrics",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics"
+            }
+          ],
+          "options": {
+            "legend": {
+              "calcs": [
+                "mean",
+                "lastNotNull",
+                "max"
+              ],
+              "displayMode": "table",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "hideZeros": false,
+              "mode": "multi",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "12.2.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "victoriametrics-metrics-datasource",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmagent_kafka_client_errors_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Consumer client errors",
+              "range": true,
+              "refId": "C"
+            },
+            {
+              "datasource": {
+                "type": "victoriametrics-metrics-datasource",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmagent_kafka_ingest_errors_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Consumer ingest errors",
+              "range": true,
+              "refId": "D"
+            }
+          ],
+          "title": "Consumer errors",
+          "type": "timeseries"
+        }
+      ],
+      "title": "Kafka (Enterprise)",
+      "type": "row"
+    },
+    {
+      "collapsed": true,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 60
+      },
       "id": 113,
       "panels": [
         {
@@ -8579,4 +9086,4 @@
   "title": "VictoriaMetrics - vmagent (VM)",
   "uid": "G7Z9GzMGz_vm",
   "version": 1
-}
+}

dashboards/vm/vmalert.json

@@ -2324,7 +2324,6 @@
                   "mode": "off"
                 }
               },
-              "decimals": 0,
               "links": [],
               "mappings": [],
               "min": 0,

dashboards/vm/vmauth.json

@@ -202,6 +202,7 @@
         "defaults": {
           "mappings": [],
           "min": 0,
+          "noValue": "0",
           "thresholds": {
             "mode": "absolute",
             "steps": [
@@ -239,7 +240,7 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "12.2.0",
+      "pluginVersion": "12.4.3",
       "targets": [
         {
           "datasource": {
@@ -561,8 +562,7 @@
                 "value": 80
               }
             ]
-          },
-          "unit": "s"
+          }
         },
         "overrides": []
       },
@@ -599,7 +599,7 @@
           },
           "editorMode": "code",
           "exemplar": false,
-          "expr": "sum(min_over_time(vm_app_uptime_seconds{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (job)",
+          "expr": "sum(min_over_time(up{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (job)",
           "format": "time_series",
           "instant": false,
           "interval": "",
@@ -623,6 +623,342 @@
       "title": "Overview",
       "type": "row"
     },
+    {
+      "datasource": {
+        "type": "victoriametrics-metrics-datasource",
+        "uid": "$ds"
+      },
+      "description": "Shows the rate of requests per user.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "barWidthFactor": 0.6,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "showValues": false,
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": 0
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 0,
+        "y": 9
+      },
+      "id": 11,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "hideZeros": false,
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "12.4.3",
+      "targets": [
+        {
+          "datasource": {
+            "type": "victoriametrics-metrics-datasource",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(vmauth_user_requests_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by(username) > 0",
+          "legendFormat": "__auto",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "victoriametrics-metrics-datasource",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(vmauth_unauthorized_user_requests_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) > 0",
+          "legendFormat": "unauthorized_user",
+          "range": true,
+          "refId": "B"
+        }
+      ],
+      "title": "Requests rate",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "victoriametrics-metrics-datasource",
+        "uid": "$ds"
+      },
+      "description": "Shows duration in seconds of user requests by quantile.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "barWidthFactor": 0.6,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "showValues": false,
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": 0
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 12,
+        "y": 9
+      },
+      "id": 19,
+      "options": {
+        "legend": {
+          "calcs": [
+            "max",
+            "mean"
+          ],
+          "displayMode": "table",
+          "placement": "bottom",
+          "showLegend": true,
+          "sortBy": "Max",
+          "sortDesc": true
+        },
+        "tooltip": {
+          "hideZeros": false,
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "12.4.3",
+      "targets": [
+        {
+          "datasource": {
+            "type": "victoriametrics-metrics-datasource",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "max(vmauth_user_request_duration_seconds{job=~\"$job\", instance=~\"$instance\", username=~\"$user\", quantile=~\"(0.99|0.5)\"}) by (quantile, username) > 0",
+          "legendFormat": "user: {{username}} q: {{ quantile}}",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "victoriametrics-metrics-datasource",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "max(vmauth_unauthorized_user_request_duration_seconds{job=~\"$job\", instance=~\"$instance\", quantile=~\"(0.99|0.5)\"}) by (quantile) > 0",
+          "legendFormat": "user: unauthorized q: {{ quantile}}",
+          "range": true,
+          "refId": "B"
+        }
+      ],
+      "title": "Requests duration",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "victoriametrics-metrics-datasource",
+        "uid": "$ds"
+      },
+      "description": "Shows the request error rate per user.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "barWidthFactor": 0.6,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "showValues": false,
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": 0
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 0,
+        "y": 18
+      },
+      "id": 37,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "hideZeros": false,
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "12.4.3",
+      "targets": [
+        {
+          "datasource": {
+            "type": "victoriametrics-metrics-datasource",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(vmauth_user_request_errors_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by (username) > 0",
+          "legendFormat": "__auto",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "victoriametrics-metrics-datasource",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(vmauth_unauthorized_user_request_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) > 0",
+          "legendFormat": "unauthorized_user",
+          "range": true,
+          "refId": "B"
+        }
+      ],
+      "title": "Requests error rate",
+      "type": "timeseries"
+    },
     {
       "datasource": {
         "type": "victoriametrics-metrics-datasource",
@@ -688,8 +1024,8 @@
       "gridPos": {
         "h": 9,
         "w": 12,
-        "x": 0,
-        "y": 9
+        "x": 12,
+        "y": 18
       },
       "id": 16,
       "options": {
@@ -705,7 +1041,7 @@
           "sort": "none"
         }
       },
-      "pluginVersion": "12.3.0",
+      "pluginVersion": "12.4.3",
       "targets": [
         {
           "datasource": {
@@ -713,8 +1049,7 @@
             "uid": "$ds"
           },
           "editorMode": "code",
-          "expr": "sum(rate(vmauth_http_request_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (reason)",
-          "hide": false,
+          "expr": "sum(rate(vmauth_http_request_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (reason) > 0",
           "legendFormat": "__auto",
           "range": true,
           "refId": "A"
@@ -728,353 +1063,7 @@
         "type": "victoriametrics-metrics-datasource",
         "uid": "$ds"
       },
-      "description": " The number of concurrent connections processed by vmauth reached one of limits. Possible solutions:\n- increase global limit with flag -maxConcurrentRequests\n- increase limit with flag: -maxConcurrentPerUserRequests for all users or with config option `max_concurrent_requests` per user.\n- deploy additional vmauth replicas\n- check requests latency at backend service and allocate resources to it if needed",
-      "fieldConfig": {
-        "defaults": {
-          "color": {
-            "mode": "palette-classic"
-          },
-          "custom": {
-            "axisBorderShow": false,
-            "axisCenteredZero": false,
-            "axisColorMode": "text",
-            "axisLabel": "",
-            "axisPlacement": "auto",
-            "barAlignment": 0,
-            "barWidthFactor": 0.6,
-            "drawStyle": "bars",
-            "fillOpacity": 0,
-            "gradientMode": "none",
-            "hideFrom": {
-              "legend": false,
-              "tooltip": false,
-              "viz": false
-            },
-            "insertNulls": false,
-            "lineInterpolation": "linear",
-            "lineWidth": 1,
-            "pointSize": 5,
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "showPoints": "auto",
-            "showValues": false,
-            "spanNulls": false,
-            "stacking": {
-              "group": "A",
-              "mode": "none"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "mappings": [],
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": 0
-              },
-              {
-                "color": "red",
-                "value": 80
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 9,
-        "w": 12,
-        "x": 12,
-        "y": 9
-      },
-      "id": 10,
-      "options": {
-        "legend": {
-          "calcs": [],
-          "displayMode": "list",
-          "placement": "bottom",
-          "showLegend": true
-        },
-        "tooltip": {
-          "hideZeros": false,
-          "mode": "single",
-          "sort": "none"
-        }
-      },
-      "pluginVersion": "12.3.0",
-      "targets": [
-        {
-          "datasource": {
-            "type": "victoriametrics-metrics-datasource",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_user_concurrent_requests_limit_reached_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by(username)  > 0",
-          "interval": "1m",
-          "legendFormat": "__auto",
-          "range": true,
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "victoriametrics-metrics-datasource",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_unauthorized_user_concurrent_requests_limit_reached_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) > 0",
-          "hide": false,
-          "legendFormat": "unauthorized",
-          "range": true,
-          "refId": "B"
-        },
-        {
-          "datasource": {
-            "type": "victoriametrics-metrics-datasource",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_concurrent_requests_limit_reached_total[$__rate_interval])) > 0",
-          "hide": false,
-          "legendFormat": "global at {{ $instance }}",
-          "range": true,
-          "refId": "C"
-        }
-      ],
-      "title": "Concurrent limit reached",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "victoriametrics-metrics-datasource",
-        "uid": "$ds"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "color": {
-            "mode": "palette-classic"
-          },
-          "custom": {
-            "axisBorderShow": false,
-            "axisCenteredZero": false,
-            "axisColorMode": "text",
-            "axisLabel": "",
-            "axisPlacement": "auto",
-            "barAlignment": 0,
-            "barWidthFactor": 0.6,
-            "drawStyle": "line",
-            "fillOpacity": 0,
-            "gradientMode": "none",
-            "hideFrom": {
-              "legend": false,
-              "tooltip": false,
-              "viz": false
-            },
-            "insertNulls": false,
-            "lineInterpolation": "linear",
-            "lineWidth": 1,
-            "pointSize": 5,
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "showPoints": "auto",
-            "showValues": false,
-            "spanNulls": false,
-            "stacking": {
-              "group": "A",
-              "mode": "none"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "mappings": [],
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": 0
-              },
-              {
-                "color": "red",
-                "value": 80
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 9,
-        "w": 12,
-        "x": 0,
-        "y": 18
-      },
-      "id": 11,
-      "options": {
-        "legend": {
-          "calcs": [],
-          "displayMode": "list",
-          "placement": "bottom",
-          "showLegend": true
-        },
-        "tooltip": {
-          "hideZeros": false,
-          "mode": "single",
-          "sort": "none"
-        }
-      },
-      "pluginVersion": "12.3.0",
-      "targets": [
-        {
-          "datasource": {
-            "type": "victoriametrics-metrics-datasource",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_user_requests_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by(username)",
-          "hide": false,
-          "legendFormat": "__auto",
-          "range": true,
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "victoriametrics-metrics-datasource",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_unauthorized_user_requests_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))",
-          "hide": false,
-          "legendFormat": "unauthorized_user",
-          "range": true,
-          "refId": "B"
-        }
-      ],
-      "title": "User requests rate",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "victoriametrics-metrics-datasource",
-        "uid": "$ds"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "color": {
-            "mode": "palette-classic"
-          },
-          "custom": {
-            "axisBorderShow": false,
-            "axisCenteredZero": false,
-            "axisColorMode": "text",
-            "axisLabel": "",
-            "axisPlacement": "auto",
-            "barAlignment": 0,
-            "barWidthFactor": 0.6,
-            "drawStyle": "line",
-            "fillOpacity": 0,
-            "gradientMode": "none",
-            "hideFrom": {
-              "legend": false,
-              "tooltip": false,
-              "viz": false
-            },
-            "insertNulls": false,
-            "lineInterpolation": "linear",
-            "lineWidth": 1,
-            "pointSize": 5,
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "showPoints": "auto",
-            "showValues": false,
-            "spanNulls": false,
-            "stacking": {
-              "group": "A",
-              "mode": "none"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "mappings": [],
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": 0
-              },
-              {
-                "color": "red",
-                "value": 80
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 9,
-        "w": 12,
-        "x": 12,
-        "y": 18
-      },
-      "id": 37,
-      "options": {
-        "legend": {
-          "calcs": [],
-          "displayMode": "list",
-          "placement": "bottom",
-          "showLegend": true
-        },
-        "tooltip": {
-          "hideZeros": false,
-          "mode": "single",
-          "sort": "none"
-        }
-      },
-      "pluginVersion": "12.3.0",
-      "targets": [
-        {
-          "datasource": {
-            "type": "victoriametrics-metrics-datasource",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_user_request_errors_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by (username) > 0",
-          "hide": false,
-          "legendFormat": "__auto",
-          "range": true,
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "victoriametrics-metrics-datasource",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_unauthorized_user_request_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) > 0",
-          "hide": false,
-          "legendFormat": "unauthorized_user",
-          "range": true,
-          "refId": "B"
-        }
-      ],
-      "title": "User requests error rate",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "victoriametrics-metrics-datasource",
-        "uid": "$ds"
-      },
-      "description": "Shows percent utilization of  per concurrent requests capacity.",
+      "description": "Shows the percentage utilization of concurrent request capacity per user.",
       "fieldConfig": {
         "defaults": {
           "color": {
@@ -1158,7 +1147,7 @@
           "sort": "desc"
         }
       },
-      "pluginVersion": "12.3.0",
+      "pluginVersion": "12.4.3",
       "targets": [
         {
           "datasource": {
@@ -1167,14 +1156,13 @@
           },
           "editorMode": "code",
           "expr": "max(\nmax_over_time(vmauth_user_concurrent_requests_current{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])\n/ \nvmauth_user_concurrent_requests_capacity{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}\n) by(username) > 0\n",
-          "hide": false,
           "interval": "5m",
           "legendFormat": "__auto",
           "range": true,
           "refId": "A"
         }
       ],
-      "title": "User concurrent requests usage",
+      "title": "Concurrent requests usage",
       "type": "timeseries"
     },
     {
@@ -1182,7 +1170,7 @@
         "type": "victoriametrics-metrics-datasource",
         "uid": "$ds"
       },
-      "description": "Shows duration in seconds of user requests by quantile.",
+      "description": " The number of concurrent connections processed by vmauth reached one of limits. Possible solutions:\n- increase global limit with flag -maxConcurrentRequests\n- increase limit with flag: -maxConcurrentPerUserRequests for all users or with config option `max_concurrent_requests` per user.\n- deploy additional vmauth replicas\n- check requests latency at backend service and allocate resources to it if needed",
       "fieldConfig": {
         "defaults": {
           "color": {
@@ -1196,7 +1184,7 @@
             "axisPlacement": "auto",
             "barAlignment": 0,
             "barWidthFactor": 0.6,
-            "drawStyle": "line",
+            "drawStyle": "bars",
             "fillOpacity": 0,
             "gradientMode": "none",
             "hideFrom": {
@@ -1235,8 +1223,7 @@
                 "value": 80
               }
             ]
-          },
-          "unit": "s"
+          }
         },
         "overrides": []
       },
@@ -1246,18 +1233,13 @@
         "x": 12,
         "y": 27
       },
-      "id": 19,
+      "id": 10,
       "options": {
         "legend": {
-          "calcs": [
-            "max",
-            "mean"
-          ],
-          "displayMode": "table",
+          "calcs": [],
+          "displayMode": "list",
           "placement": "bottom",
-          "showLegend": true,
-          "sortBy": "Max",
-          "sortDesc": true
+          "showLegend": true
         },
         "tooltip": {
           "hideZeros": false,
@@ -1265,7 +1247,7 @@
           "sort": "none"
         }
       },
-      "pluginVersion": "12.3.0",
+      "pluginVersion": "12.4.3",
       "targets": [
         {
           "datasource": {
@@ -1273,9 +1255,9 @@
             "uid": "$ds"
           },
           "editorMode": "code",
-          "expr": "max(vmauth_user_request_duration_seconds{job=~\"$job\", instance=~\"$instance\", username=~\"$user\", quantile=~\"(0.99|0.5)\"}) by (quantile, username) > 0",
-          "hide": false,
-          "legendFormat": "user: {{username}} q: {{ quantile}}",
+          "expr": "sum(rate(vmauth_user_concurrent_requests_limit_reached_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by(username)  > 0",
+          "interval": "1m",
+          "legendFormat": "__auto",
           "range": true,
           "refId": "A"
         },
@@ -1285,14 +1267,24 @@
             "uid": "$ds"
           },
           "editorMode": "code",
-          "expr": "max(vmauth_unauthorized_user_request_duration_seconds{job=~\"$job\", instance=~\"$instance\", quantile=~\"(0.99|0.5)\"}) by (quantile) > 0",
-          "hide": false,
-          "legendFormat": "user: unauthorized q: {{ quantile}}",
+          "expr": "sum(rate(vmauth_unauthorized_user_concurrent_requests_limit_reached_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) > 0",
+          "legendFormat": "unauthorized",
           "range": true,
           "refId": "B"
+        },
+        {
+          "datasource": {
+            "type": "victoriametrics-metrics-datasource",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(vmauth_concurrent_requests_limit_reached_total[$__rate_interval])) > 0",
+          "legendFormat": "global at {{ $instance }}",
+          "range": true,
+          "refId": "C"
         }
       ],
-      "title": "User requests duration",
+      "title": "Concurrent limit reached",
       "type": "timeseries"
     },
     {
@@ -2599,7 +2591,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ",
+          "description": "Shows the backend request error rate per user.\nThe value can be higher than the request error rate if:\n1. A single request is retried multiple times due to transient network errors, such as proxy idle timeout misconfiguration or sockets being closed by the OS.\n2. The request fails and is retried on other backends because of configured retry_status_codes.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2611,8 +2603,8 @@
                 "axisColorMode": "text",
                 "axisLabel": "",
                 "axisPlacement": "auto",
-                "axisSoftMin": 0,
                 "barAlignment": 0,
+                "barWidthFactor": 0.6,
                 "drawStyle": "line",
                 "fillOpacity": 0,
                 "gradientMode": "none",
@@ -2622,13 +2614,14 @@
                   "viz": false
                 },
                 "insertNulls": false,
-                "lineInterpolation": "stepAfter",
+                "lineInterpolation": "linear",
                 "lineWidth": 1,
                 "pointSize": 5,
                 "scaleDistribution": {
                   "type": "linear"
                 },
-                "showPoints": "never",
+                "showPoints": "auto",
+                "showValues": false,
                 "spanNulls": false,
                 "stacking": {
                   "group": "A",
@@ -2638,23 +2631,20 @@
                   "mode": "off"
                 }
               },
-              "decimals": 0,
-              "links": [],
               "mappings": [],
               "thresholds": {
                 "mode": "absolute",
                 "steps": [
                   {
                     "color": "green",
-                    "value": null
+                    "value": 0
                   },
                   {
                     "color": "red",
                     "value": 80
                   }
                 ]
-              },
-              "unit": "none"
+              }
             },
             "overrides": []
           },
@@ -2662,26 +2652,23 @@
             "h": 8,
             "w": 12,
             "x": 0,
-            "y": 47
+            "y": 46
           },
-          "id": 37,
+          "id": 41,
           "options": {
             "legend": {
-              "calcs": [
-                "lastNotNull"
-              ],
-              "displayMode": "table",
+              "calcs": [],
+              "displayMode": "list",
               "placement": "bottom",
-              "showLegend": true,
-              "sortBy": "Last *",
-              "sortDesc": true
+              "showLegend": true
             },
             "tooltip": {
-              "mode": "multi",
-              "sort": "desc"
+              "hideZeros": false,
+              "mode": "single",
+              "sort": "none"
             }
           },
-          "pluginVersion": "9.1.0",
+          "pluginVersion": "12.4.3",
           "targets": [
             {
               "datasource": {
@@ -2689,14 +2676,24 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)",
-              "format": "time_series",
-              "instant": false,
-              "legendFormat": "{{job}}",
+              "expr": "sum(rate(vmauth_user_request_backend_errors_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by (username) > 0",
+              "legendFormat": "__auto",
+              "range": true,
               "refId": "A"
+            },
+            {
+              "datasource": {
+                "type": "victoriametrics-metrics-datasource",
+                "uid": "$ds"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmauth_unauthorized_user_request_backend_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) > 0",
+              "legendFormat": "unauthorized_user",
+              "range": true,
+              "refId": "B"
             }
           ],
-          "title": "Restarts ($job)",
+          "title": "Requests backend error rate",
           "type": "timeseries"
         },
         {

dashboards/vmagent.json

@@ -2945,7 +2945,6 @@
                   "mode": "off"
                 }
               },
-              "decimals": 0,
               "links": [],
               "mappings": [],
               "min": 0,
@@ -7599,6 +7598,514 @@
         "x": 0,
         "y": 43
       },
+      "id": 163,
+      "panels": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "$ds"
+          },
+          "description": "Positive series show bytes written by vmagent producers into Kafka. Negative series show bytes read by vmagent consumers from Kafka. Read this together with Messages in / out: a stable byte rate with rising message rate usually means smaller Kafka payloads and higher per-message overhead. Producer Kafka metrics aggregate at job level because they do not expose the full remoteWrite URL label.\n\nDocs: <a href=\"https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#estimating-message-size-and-rate\" target=\"_blank\">estimating message size and rate</a>. Kafka read docs: <a href=\"https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics\" target=\"_blank\">reading metrics</a>.",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": true,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "barWidthFactor": 0.6,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "never",
+                "showValues": false,
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "links": [],
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  }
+                ]
+              },
+              "unit": "Bps"
+            },
+            "overrides": []
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 0,
+            "y": 44
+          },
+          "id": 164,
+          "links": [
+            {
+              "title": "Docs: estimating size/rate",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#estimating-message-size-and-rate"
+            },
+            {
+              "title": "Docs: reading metrics",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics"
+            }
+          ],
+          "options": {
+            "legend": {
+              "calcs": [
+                "mean",
+                "lastNotNull",
+                "max"
+              ],
+              "displayMode": "table",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "hideZeros": false,
+              "mode": "multi",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "12.2.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmagent_remotewrite_kafka_sent_bytes_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Produced to Kafka",
+              "range": true,
+              "refId": "A"
+            },
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "-sum(rate(vmagent_kafka_consumer_read_bytes_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Consumed from Kafka",
+              "range": true,
+              "refId": "B"
+            }
+          ],
+          "title": "Traffic (bytes)",
+          "type": "timeseries"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "$ds"
+          },
+          "description": "Positive series show Kafka messages produced by vmagent. Negative series show Kafka messages consumed by vmagent. Read this together with Traffic (bytes), because a stable byte rate with rising message rate usually means smaller Kafka messages and higher per-message overhead. Producer Kafka metrics aggregate at job level because they do not expose the full remoteWrite URL label.\n\nDocs: <a href=\"https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#estimating-message-size-and-rate\" target=\"_blank\">estimating message size and rate</a>. Kafka read docs: <a href=\"https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics\" target=\"_blank\">reading metrics</a>.",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": true,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "barWidthFactor": 0.6,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "never",
+                "showValues": false,
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "links": [],
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  }
+                ]
+              },
+              "unit": "ops"
+            },
+            "overrides": []
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 12,
+            "y": 44
+          },
+          "id": 165,
+          "links": [
+            {
+              "title": "Docs: estimating size/rate",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#estimating-message-size-and-rate"
+            },
+            {
+              "title": "Docs: reading metrics",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics"
+            }
+          ],
+          "options": {
+            "legend": {
+              "calcs": [
+                "mean",
+                "lastNotNull",
+                "max"
+              ],
+              "displayMode": "table",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "hideZeros": false,
+              "mode": "multi",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "12.2.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmagent_remotewrite_kafka_messages_sent_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Produced to Kafka",
+              "range": true,
+              "refId": "A"
+            },
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "-sum(rate(vmagent_kafka_messages_read_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Consumed from Kafka",
+              "range": true,
+              "refId": "B"
+            }
+          ],
+          "title": "Messages in / out",
+          "type": "timeseries"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "$ds"
+          },
+          "description": "Kafka producer-side errors from vmagent remote write. This panel shows send errors and delivery errors reported by Kafka producers.\n\nKafka write docs: <a href=\"https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#writing-metrics\" target=\"_blank\">writing metrics</a>.",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": false,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "barWidthFactor": 0.6,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "never",
+                "showValues": false,
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "links": [],
+              "mappings": [],
+              "min": 0,
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": 0
+                  },
+                  {
+                    "color": "red",
+                    "value": 80
+                  }
+                ]
+              },
+              "unit": "ops"
+            },
+            "overrides": []
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 0,
+            "y": 52
+          },
+          "id": 167,
+          "links": [
+            {
+              "title": "Docs: writing metrics",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#writing-metrics"
+            },
+            {
+              "title": "Docs: reading metrics",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics"
+            }
+          ],
+          "options": {
+            "legend": {
+              "calcs": [
+                "mean",
+                "lastNotNull",
+                "max"
+              ],
+              "displayMode": "table",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "hideZeros": false,
+              "mode": "multi",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "12.2.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmagent_remotewrite_kafka_messages_send_errors_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Producer send errors",
+              "range": true,
+              "refId": "A"
+            },
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmagent_remotewrite_kafka_messages_delivery_errors_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Producer delivery errors",
+              "range": true,
+              "refId": "B"
+            }
+          ],
+          "title": "Producer errors",
+          "type": "timeseries"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "$ds"
+          },
+          "description": "Kafka consumer-side errors from vmagent. This panel shows client errors and ingest errors reported while reading from Kafka and passing data further downstream.\n\nKafka read docs: <a href=\"https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics\" target=\"_blank\">reading metrics</a>.",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": false,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "barWidthFactor": 0.6,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "never",
+                "showValues": false,
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "links": [],
+              "mappings": [],
+              "min": 0,
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": 0
+                  },
+                  {
+                    "color": "red",
+                    "value": 80
+                  }
+                ]
+              },
+              "unit": "ops"
+            },
+            "overrides": []
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 12,
+            "y": 52
+          },
+          "id": 168,
+          "links": [
+            {
+              "title": "Docs: reading metrics",
+              "url": "https://docs.victoriametrics.com/victoriametrics/integrations/kafka/#reading-metrics"
+            }
+          ],
+          "options": {
+            "legend": {
+              "calcs": [
+                "mean",
+                "lastNotNull",
+                "max"
+              ],
+              "displayMode": "table",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "hideZeros": false,
+              "mode": "multi",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "12.2.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmagent_kafka_client_errors_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Consumer client errors",
+              "range": true,
+              "refId": "C"
+            },
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${ds}"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmagent_kafka_ingest_errors_total{job=~\"$job\"}[$__rate_interval])) by (job)",
+              "legendFormat": "Consumer ingest errors",
+              "range": true,
+              "refId": "D"
+            }
+          ],
+          "title": "Consumer errors",
+          "type": "timeseries"
+        }
+      ],
+      "title": "Kafka (Enterprise)",
+      "type": "row"
+    },
+    {
+      "collapsed": true,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 60
+      },
       "id": 113,
       "panels": [
         {
@@ -8578,4 +9085,4 @@
   "title": "VictoriaMetrics - vmagent",
   "uid": "G7Z9GzMGz",
   "version": 1
-}
+}

dashboards/vmalert.json

@@ -2323,7 +2323,6 @@
                   "mode": "off"
                 }
               },
-              "decimals": 0,
               "links": [],
               "mappings": [],
               "min": 0,

dashboards/vmauth.json

@@ -201,6 +201,7 @@
         "defaults": {
           "mappings": [],
           "min": 0,
+          "noValue": "0",
           "thresholds": {
             "mode": "absolute",
             "steps": [
@@ -238,7 +239,7 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "12.2.0",
+      "pluginVersion": "12.4.3",
       "targets": [
         {
           "datasource": {
@@ -560,8 +561,7 @@
                 "value": 80
               }
             ]
-          },
-          "unit": "s"
+          }
         },
         "overrides": []
       },
@@ -598,7 +598,7 @@
           },
           "editorMode": "code",
           "exemplar": false,
-          "expr": "sum(min_over_time(vm_app_uptime_seconds{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (job)",
+          "expr": "sum(min_over_time(up{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (job)",
           "format": "time_series",
           "instant": false,
           "interval": "",
@@ -622,6 +622,342 @@
       "title": "Overview",
       "type": "row"
     },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "$ds"
+      },
+      "description": "Shows the rate of requests per user.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "barWidthFactor": 0.6,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "showValues": false,
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": 0
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 0,
+        "y": 9
+      },
+      "id": 11,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "hideZeros": false,
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "12.4.3",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(vmauth_user_requests_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by(username) > 0",
+          "legendFormat": "__auto",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(vmauth_unauthorized_user_requests_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) > 0",
+          "legendFormat": "unauthorized_user",
+          "range": true,
+          "refId": "B"
+        }
+      ],
+      "title": "Requests rate",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "$ds"
+      },
+      "description": "Shows duration in seconds of user requests by quantile.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "barWidthFactor": 0.6,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "showValues": false,
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": 0
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 12,
+        "y": 9
+      },
+      "id": 19,
+      "options": {
+        "legend": {
+          "calcs": [
+            "max",
+            "mean"
+          ],
+          "displayMode": "table",
+          "placement": "bottom",
+          "showLegend": true,
+          "sortBy": "Max",
+          "sortDesc": true
+        },
+        "tooltip": {
+          "hideZeros": false,
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "12.4.3",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "max(vmauth_user_request_duration_seconds{job=~\"$job\", instance=~\"$instance\", username=~\"$user\", quantile=~\"(0.99|0.5)\"}) by (quantile, username) > 0",
+          "legendFormat": "user: {{username}} q: {{ quantile}}",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "max(vmauth_unauthorized_user_request_duration_seconds{job=~\"$job\", instance=~\"$instance\", quantile=~\"(0.99|0.5)\"}) by (quantile) > 0",
+          "legendFormat": "user: unauthorized q: {{ quantile}}",
+          "range": true,
+          "refId": "B"
+        }
+      ],
+      "title": "Requests duration",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "$ds"
+      },
+      "description": "Shows the request error rate per user.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "barWidthFactor": 0.6,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "showValues": false,
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": 0
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 0,
+        "y": 18
+      },
+      "id": 37,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "hideZeros": false,
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "12.4.3",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(vmauth_user_request_errors_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by (username) > 0",
+          "legendFormat": "__auto",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(vmauth_unauthorized_user_request_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) > 0",
+          "legendFormat": "unauthorized_user",
+          "range": true,
+          "refId": "B"
+        }
+      ],
+      "title": "Requests error rate",
+      "type": "timeseries"
+    },
     {
       "datasource": {
         "type": "prometheus",
@@ -687,8 +1023,8 @@
       "gridPos": {
         "h": 9,
         "w": 12,
-        "x": 0,
-        "y": 9
+        "x": 12,
+        "y": 18
       },
       "id": 16,
       "options": {
@@ -704,7 +1040,7 @@
           "sort": "none"
         }
       },
-      "pluginVersion": "12.3.0",
+      "pluginVersion": "12.4.3",
       "targets": [
         {
           "datasource": {
@@ -712,8 +1048,7 @@
             "uid": "$ds"
           },
           "editorMode": "code",
-          "expr": "sum(rate(vmauth_http_request_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (reason)",
-          "hide": false,
+          "expr": "sum(rate(vmauth_http_request_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (reason) > 0",
           "legendFormat": "__auto",
           "range": true,
           "refId": "A"
@@ -727,353 +1062,7 @@
         "type": "prometheus",
         "uid": "$ds"
       },
-      "description": " The number of concurrent connections processed by vmauth reached one of limits. Possible solutions:\n- increase global limit with flag -maxConcurrentRequests\n- increase limit with flag: -maxConcurrentPerUserRequests for all users or with config option `max_concurrent_requests` per user.\n- deploy additional vmauth replicas\n- check requests latency at backend service and allocate resources to it if needed",
-      "fieldConfig": {
-        "defaults": {
-          "color": {
-            "mode": "palette-classic"
-          },
-          "custom": {
-            "axisBorderShow": false,
-            "axisCenteredZero": false,
-            "axisColorMode": "text",
-            "axisLabel": "",
-            "axisPlacement": "auto",
-            "barAlignment": 0,
-            "barWidthFactor": 0.6,
-            "drawStyle": "bars",
-            "fillOpacity": 0,
-            "gradientMode": "none",
-            "hideFrom": {
-              "legend": false,
-              "tooltip": false,
-              "viz": false
-            },
-            "insertNulls": false,
-            "lineInterpolation": "linear",
-            "lineWidth": 1,
-            "pointSize": 5,
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "showPoints": "auto",
-            "showValues": false,
-            "spanNulls": false,
-            "stacking": {
-              "group": "A",
-              "mode": "none"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "mappings": [],
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": 0
-              },
-              {
-                "color": "red",
-                "value": 80
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 9,
-        "w": 12,
-        "x": 12,
-        "y": 9
-      },
-      "id": 10,
-      "options": {
-        "legend": {
-          "calcs": [],
-          "displayMode": "list",
-          "placement": "bottom",
-          "showLegend": true
-        },
-        "tooltip": {
-          "hideZeros": false,
-          "mode": "single",
-          "sort": "none"
-        }
-      },
-      "pluginVersion": "12.3.0",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_user_concurrent_requests_limit_reached_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by(username)  > 0",
-          "interval": "1m",
-          "legendFormat": "__auto",
-          "range": true,
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_unauthorized_user_concurrent_requests_limit_reached_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) > 0",
-          "hide": false,
-          "legendFormat": "unauthorized",
-          "range": true,
-          "refId": "B"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_concurrent_requests_limit_reached_total[$__rate_interval])) > 0",
-          "hide": false,
-          "legendFormat": "global at {{ $instance }}",
-          "range": true,
-          "refId": "C"
-        }
-      ],
-      "title": "Concurrent limit reached",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "$ds"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "color": {
-            "mode": "palette-classic"
-          },
-          "custom": {
-            "axisBorderShow": false,
-            "axisCenteredZero": false,
-            "axisColorMode": "text",
-            "axisLabel": "",
-            "axisPlacement": "auto",
-            "barAlignment": 0,
-            "barWidthFactor": 0.6,
-            "drawStyle": "line",
-            "fillOpacity": 0,
-            "gradientMode": "none",
-            "hideFrom": {
-              "legend": false,
-              "tooltip": false,
-              "viz": false
-            },
-            "insertNulls": false,
-            "lineInterpolation": "linear",
-            "lineWidth": 1,
-            "pointSize": 5,
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "showPoints": "auto",
-            "showValues": false,
-            "spanNulls": false,
-            "stacking": {
-              "group": "A",
-              "mode": "none"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "mappings": [],
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": 0
-              },
-              {
-                "color": "red",
-                "value": 80
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 9,
-        "w": 12,
-        "x": 0,
-        "y": 18
-      },
-      "id": 11,
-      "options": {
-        "legend": {
-          "calcs": [],
-          "displayMode": "list",
-          "placement": "bottom",
-          "showLegend": true
-        },
-        "tooltip": {
-          "hideZeros": false,
-          "mode": "single",
-          "sort": "none"
-        }
-      },
-      "pluginVersion": "12.3.0",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_user_requests_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by(username)",
-          "hide": false,
-          "legendFormat": "__auto",
-          "range": true,
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_unauthorized_user_requests_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))",
-          "hide": false,
-          "legendFormat": "unauthorized_user",
-          "range": true,
-          "refId": "B"
-        }
-      ],
-      "title": "User requests rate",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "$ds"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "color": {
-            "mode": "palette-classic"
-          },
-          "custom": {
-            "axisBorderShow": false,
-            "axisCenteredZero": false,
-            "axisColorMode": "text",
-            "axisLabel": "",
-            "axisPlacement": "auto",
-            "barAlignment": 0,
-            "barWidthFactor": 0.6,
-            "drawStyle": "line",
-            "fillOpacity": 0,
-            "gradientMode": "none",
-            "hideFrom": {
-              "legend": false,
-              "tooltip": false,
-              "viz": false
-            },
-            "insertNulls": false,
-            "lineInterpolation": "linear",
-            "lineWidth": 1,
-            "pointSize": 5,
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "showPoints": "auto",
-            "showValues": false,
-            "spanNulls": false,
-            "stacking": {
-              "group": "A",
-              "mode": "none"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "mappings": [],
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": 0
-              },
-              {
-                "color": "red",
-                "value": 80
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 9,
-        "w": 12,
-        "x": 12,
-        "y": 18
-      },
-      "id": 37,
-      "options": {
-        "legend": {
-          "calcs": [],
-          "displayMode": "list",
-          "placement": "bottom",
-          "showLegend": true
-        },
-        "tooltip": {
-          "hideZeros": false,
-          "mode": "single",
-          "sort": "none"
-        }
-      },
-      "pluginVersion": "12.3.0",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_user_request_errors_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by (username) > 0",
-          "hide": false,
-          "legendFormat": "__auto",
-          "range": true,
-          "refId": "A"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "$ds"
-          },
-          "editorMode": "code",
-          "expr": "sum(rate(vmauth_unauthorized_user_request_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) > 0",
-          "hide": false,
-          "legendFormat": "unauthorized_user",
-          "range": true,
-          "refId": "B"
-        }
-      ],
-      "title": "User requests error rate",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "$ds"
-      },
-      "description": "Shows percent utilization of  per concurrent requests capacity.",
+      "description": "Shows the percentage utilization of concurrent request capacity per user.",
       "fieldConfig": {
         "defaults": {
           "color": {
@@ -1157,7 +1146,7 @@
           "sort": "desc"
         }
       },
-      "pluginVersion": "12.3.0",
+      "pluginVersion": "12.4.3",
       "targets": [
         {
           "datasource": {
@@ -1166,14 +1155,13 @@
           },
           "editorMode": "code",
           "expr": "max(\nmax_over_time(vmauth_user_concurrent_requests_current{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])\n/ \nvmauth_user_concurrent_requests_capacity{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}\n) by(username) > 0\n",
-          "hide": false,
           "interval": "5m",
           "legendFormat": "__auto",
           "range": true,
           "refId": "A"
         }
       ],
-      "title": "User concurrent requests usage",
+      "title": "Concurrent requests usage",
       "type": "timeseries"
     },
     {
@@ -1181,7 +1169,7 @@
         "type": "prometheus",
         "uid": "$ds"
       },
-      "description": "Shows duration in seconds of user requests by quantile.",
+      "description": " The number of concurrent connections processed by vmauth reached one of limits. Possible solutions:\n- increase global limit with flag -maxConcurrentRequests\n- increase limit with flag: -maxConcurrentPerUserRequests for all users or with config option `max_concurrent_requests` per user.\n- deploy additional vmauth replicas\n- check requests latency at backend service and allocate resources to it if needed",
       "fieldConfig": {
         "defaults": {
           "color": {
@@ -1195,7 +1183,7 @@
             "axisPlacement": "auto",
             "barAlignment": 0,
             "barWidthFactor": 0.6,
-            "drawStyle": "line",
+            "drawStyle": "bars",
             "fillOpacity": 0,
             "gradientMode": "none",
             "hideFrom": {
@@ -1234,8 +1222,7 @@
                 "value": 80
               }
             ]
-          },
-          "unit": "s"
+          }
         },
         "overrides": []
       },
@@ -1245,18 +1232,13 @@
         "x": 12,
         "y": 27
       },
-      "id": 19,
+      "id": 10,
       "options": {
         "legend": {
-          "calcs": [
-            "max",
-            "mean"
-          ],
-          "displayMode": "table",
+          "calcs": [],
+          "displayMode": "list",
           "placement": "bottom",
-          "showLegend": true,
-          "sortBy": "Max",
-          "sortDesc": true
+          "showLegend": true
         },
         "tooltip": {
           "hideZeros": false,
@@ -1264,7 +1246,7 @@
           "sort": "none"
         }
       },
-      "pluginVersion": "12.3.0",
+      "pluginVersion": "12.4.3",
       "targets": [
         {
           "datasource": {
@@ -1272,9 +1254,9 @@
             "uid": "$ds"
           },
           "editorMode": "code",
-          "expr": "max(vmauth_user_request_duration_seconds{job=~\"$job\", instance=~\"$instance\", username=~\"$user\", quantile=~\"(0.99|0.5)\"}) by (quantile, username) > 0",
-          "hide": false,
-          "legendFormat": "user: {{username}} q: {{ quantile}}",
+          "expr": "sum(rate(vmauth_user_concurrent_requests_limit_reached_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by(username)  > 0",
+          "interval": "1m",
+          "legendFormat": "__auto",
           "range": true,
           "refId": "A"
         },
@@ -1284,14 +1266,24 @@
             "uid": "$ds"
           },
           "editorMode": "code",
-          "expr": "max(vmauth_unauthorized_user_request_duration_seconds{job=~\"$job\", instance=~\"$instance\", quantile=~\"(0.99|0.5)\"}) by (quantile) > 0",
-          "hide": false,
-          "legendFormat": "user: unauthorized q: {{ quantile}}",
+          "expr": "sum(rate(vmauth_unauthorized_user_concurrent_requests_limit_reached_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) > 0",
+          "legendFormat": "unauthorized",
           "range": true,
           "refId": "B"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "$ds"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(vmauth_concurrent_requests_limit_reached_total[$__rate_interval])) > 0",
+          "legendFormat": "global at {{ $instance }}",
+          "range": true,
+          "refId": "C"
         }
       ],
-      "title": "User requests duration",
+      "title": "Concurrent limit reached",
       "type": "timeseries"
     },
     {
@@ -2598,7 +2590,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ",
+          "description": "Shows the backend request error rate per user.\nThe value can be higher than the request error rate if:\n1. A single request is retried multiple times due to transient network errors, such as proxy idle timeout misconfiguration or sockets being closed by the OS.\n2. The request fails and is retried on other backends because of configured retry_status_codes.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2610,8 +2602,8 @@
                 "axisColorMode": "text",
                 "axisLabel": "",
                 "axisPlacement": "auto",
-                "axisSoftMin": 0,
                 "barAlignment": 0,
+                "barWidthFactor": 0.6,
                 "drawStyle": "line",
                 "fillOpacity": 0,
                 "gradientMode": "none",
@@ -2621,13 +2613,14 @@
                   "viz": false
                 },
                 "insertNulls": false,
-                "lineInterpolation": "stepAfter",
+                "lineInterpolation": "linear",
                 "lineWidth": 1,
                 "pointSize": 5,
                 "scaleDistribution": {
                   "type": "linear"
                 },
-                "showPoints": "never",
+                "showPoints": "auto",
+                "showValues": false,
                 "spanNulls": false,
                 "stacking": {
                   "group": "A",
@@ -2637,23 +2630,20 @@
                   "mode": "off"
                 }
               },
-              "decimals": 0,
-              "links": [],
               "mappings": [],
               "thresholds": {
                 "mode": "absolute",
                 "steps": [
                   {
                     "color": "green",
-                    "value": null
+                    "value": 0
                   },
                   {
                     "color": "red",
                     "value": 80
                   }
                 ]
-              },
-              "unit": "none"
+              }
             },
             "overrides": []
           },
@@ -2661,26 +2651,23 @@
             "h": 8,
             "w": 12,
             "x": 0,
-            "y": 47
+            "y": 46
           },
-          "id": 37,
+          "id": 41,
           "options": {
             "legend": {
-              "calcs": [
-                "lastNotNull"
-              ],
-              "displayMode": "table",
+              "calcs": [],
+              "displayMode": "list",
               "placement": "bottom",
-              "showLegend": true,
-              "sortBy": "Last *",
-              "sortDesc": true
+              "showLegend": true
             },
             "tooltip": {
-              "mode": "multi",
-              "sort": "desc"
+              "hideZeros": false,
+              "mode": "single",
+              "sort": "none"
             }
           },
-          "pluginVersion": "9.1.0",
+          "pluginVersion": "12.4.3",
           "targets": [
             {
               "datasource": {
@@ -2688,14 +2675,24 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)",
-              "format": "time_series",
-              "instant": false,
-              "legendFormat": "{{job}}",
+              "expr": "sum(rate(vmauth_user_request_backend_errors_total{job=~\"$job\", instance=~\"$instance\", username=~\"$user\"}[$__rate_interval])) by (username) > 0",
+              "legendFormat": "__auto",
+              "range": true,
               "refId": "A"
+            },
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "$ds"
+              },
+              "editorMode": "code",
+              "expr": "sum(rate(vmauth_unauthorized_user_request_backend_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) > 0",
+              "legendFormat": "unauthorized_user",
+              "range": true,
+              "refId": "B"
             }
           ],
-          "title": "Restarts ($job)",
+          "title": "Requests backend error rate",
           "type": "timeseries"
         },
         {

deployment/docker/Makefile

@@ -7,7 +7,7 @@ ROOT_IMAGE ?= alpine:3.23.4
 ROOT_IMAGE_SCRATCH ?= scratch
 CERTS_IMAGE := alpine:3.23.4
 
-GO_BUILDER_IMAGE := golang:1.26.2
+GO_BUILDER_IMAGE := golang:1.26.3
 
 BUILDER_IMAGE := local/builder:2.0.0-$(shell echo $(GO_BUILDER_IMAGE) | tr :/ __)-1
 BASE_IMAGE := local/base:1.1.4-$(shell echo $(ROOT_IMAGE) | tr :/ __)-$(shell echo $(CERTS_IMAGE) | tr :/ __)

deployment/docker/compose-vm-cluster.yml

@@ -3,7 +3,7 @@ services:
   #  It scrapes targets defined in --promscrape.config
   #  And forward them to --remoteWrite.url
   vmagent:
-    image: victoriametrics/vmagent:v1.140.0
+    image: victoriametrics/vmagent:v1.143.0
     depends_on:
       - "vmauth"
     ports:
@@ -42,14 +42,14 @@ services:
   # vmstorage shards. Each shard receives 1/N of all metrics sent to vminserts,
   # where N is number of vmstorages (2 in this case).
   vmstorage-1:
-    image: victoriametrics/vmstorage:v1.140.0-cluster
+    image: victoriametrics/vmstorage:v1.143.0-cluster
     volumes:
       - strgdata-1:/storage
     command:
       - "--storageDataPath=/storage"
     restart: always
   vmstorage-2:
-    image: victoriametrics/vmstorage:v1.140.0-cluster
+    image: victoriametrics/vmstorage:v1.143.0-cluster
     volumes:
       - strgdata-2:/storage
     command:
@@ -59,7 +59,7 @@ services:
   # vminsert is ingestion frontend. It receives metrics pushed by vmagent,
   # pre-process them and distributes across configured vmstorage shards.
   vminsert-1:
-    image: victoriametrics/vminsert:v1.140.0-cluster
+    image: victoriametrics/vminsert:v1.143.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -68,7 +68,7 @@ services:
       - "--storageNode=vmstorage-2:8400"
     restart: always
   vminsert-2:
-    image: victoriametrics/vminsert:v1.140.0-cluster
+    image: victoriametrics/vminsert:v1.143.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -80,7 +80,7 @@ services:
   # vmselect is a query fronted. It serves read queries in MetricsQL or PromQL.
   # vmselect collects results from configured `--storageNode` shards.
   vmselect-1:
-    image: victoriametrics/vmselect:v1.140.0-cluster
+    image: victoriametrics/vmselect:v1.143.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -90,7 +90,7 @@ services:
       - "--vmalert.proxyURL=http://vmalert:8880"
     restart: always
   vmselect-2:
-    image: victoriametrics/vmselect:v1.140.0-cluster
+    image: victoriametrics/vmselect:v1.143.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -105,7 +105,7 @@ services:
   # read requests from Grafana, vmui, vmalert among vmselects.
   # It can be used as an authentication proxy.
   vmauth:
-    image: victoriametrics/vmauth:v1.140.0
+    image: victoriametrics/vmauth:v1.143.0
     depends_on:
       - "vmselect-1"
       - "vmselect-2"
@@ -119,7 +119,7 @@ services:
 
   # vmalert executes alerting and recording rules
   vmalert:
-    image: victoriametrics/vmalert:v1.140.0
+    image: victoriametrics/vmalert:v1.143.0
     depends_on:
       - "vmauth"
     ports:

deployment/docker/compose-vm-single.yml

@@ -3,7 +3,7 @@ services:
   #  It scrapes targets defined in --promscrape.config
   #  And forward them to --remoteWrite.url
   vmagent:
-    image: victoriametrics/vmagent:v1.140.0
+    image: victoriametrics/vmagent:v1.143.0
     depends_on:
       - "victoriametrics"
     ports:
@@ -18,7 +18,7 @@ services:
   # VictoriaMetrics instance, a single process responsible for
   # storing metrics and serve read requests.
   victoriametrics:
-    image: victoriametrics/victoria-metrics:v1.140.0
+    image: victoriametrics/victoria-metrics:v1.143.0
     ports:
       - 8428:8428
       - 8089:8089
@@ -59,7 +59,7 @@ services:
 
   # vmalert executes alerting and recording rules
   vmalert:
-    image: victoriametrics/vmalert:v1.140.0
+    image: victoriametrics/vmalert:v1.143.0
     depends_on:
       - "victoriametrics"
       - "alertmanager"

deployment/docker/vmanomaly/vmanomaly-integration/compose.yml

@@ -1,6 +1,6 @@
 services:
   vmagent:
-    image: victoriametrics/vmagent:v1.140.0
+    image: victoriametrics/vmagent:v1.143.0
     depends_on:
       - "victoriametrics"
     ports:
@@ -14,7 +14,7 @@ services:
     restart: always
 
   victoriametrics:
-    image: victoriametrics/victoria-metrics:v1.140.0
+    image: victoriametrics/victoria-metrics:v1.143.0
     ports:
       - 8428:8428
     volumes:
@@ -40,7 +40,7 @@ services:
     restart: always
 
   vmalert:
-    image: victoriametrics/vmalert:v1.140.0
+    image: victoriametrics/vmalert:v1.143.0
     depends_on:
       - "victoriametrics"
     ports:
@@ -59,7 +59,7 @@ services:
       - '--external.alert.source=explore?orgId=1&left=["now-1h","now","VictoriaMetrics",{"expr": },{"mode":"Metrics"},{"ui":[true,true,true,"none"]}]'
     restart: always
   vmanomaly:
-    image: victoriametrics/vmanomaly:v1.29.3
+    image: victoriametrics/vmanomaly:v1.29.4
     depends_on:
       - "victoriametrics"
     ports:

docs/Makefile

@@ -61,11 +61,11 @@ docs-update-vmsingle-flags:
 ifndef TAG
 	$(error TAG must be provided to update flags in docs)
 endif
-	git checkout $(TAG) && $(MAKE) victoria-metrics && \
-	./bin/victoria-metrics -help > /tmp/victoria_metrics_common_flags_tmp.md
+	(cd /tmp/vm-opensource && $(MAKE) victoria-metrics)
+	(cd /tmp/vm-opensource && ./bin/victoria-metrics -help > /tmp/victoria_metrics_common_flags_tmp.md)
 
-	git checkout $(TAG)-enterprise && $(MAKE) victoria-metrics && \
-	./bin/victoria-metrics -help > /tmp/victoria_metrics_enterprise_flags_tmp.md
+	(cd /tmp/vm-enterprise && $(MAKE) victoria-metrics)
+	(cd /tmp/vm-enterprise && ./bin/victoria-metrics -help > /tmp/victoria_metrics_enterprise_flags_tmp.md)
 
 	echo "$$FLAGS_HEADER" > docs/victoriametrics/victoria_metrics_common_flags.md && \
 	cat /tmp/victoria_metrics_common_flags_tmp.md >> docs/victoriametrics/victoria_metrics_common_flags.md && \
@@ -90,10 +90,11 @@ docs-update-vmauth-flags:
 ifndef TAG
 	$(error TAG must be provided to update flags in docs)
 endif
-	git checkout $(TAG) && $(MAKE) vmauth && \
-	./bin/vmauth -help > /tmp/vmauth_common_flags_tmp.md
-	git checkout $(TAG)-enterprise && $(MAKE) vmauth && \
-	./bin/vmauth -help > /tmp/vmauth_enterprise_flags_tmp.md
+	(cd /tmp/vm-opensource && $(MAKE) vmauth)
+	(cd /tmp/vm-opensource && ./bin/vmauth -help > /tmp/vmauth_common_flags_tmp.md)
+
+	(cd /tmp/vm-enterprise && $(MAKE) vmauth)
+	(cd /tmp/vm-enterprise && ./bin/vmauth -help > /tmp/vmauth_enterprise_flags_tmp.md)
 
 	echo "$$FLAGS_HEADER" > docs/victoriametrics/vmauth_common_flags.md
 	cat /tmp/vmauth_common_flags_tmp.md >> docs/victoriametrics/vmauth_common_flags.md
@@ -115,11 +116,11 @@ docs-update-vmagent-flags:
 ifndef TAG
 	$(error TAG must be provided to update flags in docs)
 endif
-	git checkout $(TAG) && $(MAKE) vmagent && \
-	./bin/vmagent -help > /tmp/vmagent_common_flags_tmp.md
+	(cd /tmp/vm-opensource && $(MAKE) vmagent)
+	(cd /tmp/vm-opensource && ./bin/vmagent -help > /tmp/vmagent_common_flags_tmp.md)
 
-	git checkout $(TAG)-enterprise && $(MAKE) vmagent && \
-	./bin/vmagent -help > /tmp/vmagent_enterprise_flags_tmp.md
+	(cd /tmp/vm-enterprise && $(MAKE) vmagent)
+	(cd /tmp/vm-enterprise && ./bin/vmagent -help > /tmp/vmagent_enterprise_flags_tmp.md)
 
 	echo "$$FLAGS_HEADER" > docs/victoriametrics/vmagent_common_flags.md && \
 	cat /tmp/vmagent_common_flags_tmp.md >> docs/victoriametrics/vmagent_common_flags.md && \
@@ -143,11 +144,11 @@ docs-update-vmalert-flags:
 ifndef TAG
 	$(error TAG must be provided to update flags in docs)
 endif
-	git checkout $(TAG) && $(MAKE) vmalert && \
-	./bin/vmalert -help > /tmp/vmalert_common_flags_tmp.md
+	(cd /tmp/vm-opensource && $(MAKE) vmalert)
+	(cd /tmp/vm-opensource && ./bin/vmalert -help > /tmp/vmalert_common_flags_tmp.md)
 
-	git checkout $(TAG)-enterprise && $(MAKE) vmalert && \
-	./bin/vmalert -help > /tmp/vmalert_enterprise_flags_tmp.md
+	(cd /tmp/vm-enterprise && $(MAKE) vmalert)
+	(cd /tmp/vm-enterprise && ./bin/vmalert -help > /tmp/vmalert_enterprise_flags_tmp.md)
 
 	echo "$$FLAGS_HEADER" > docs/victoriametrics/vmalert_common_flags.md && \
 	cat /tmp/vmalert_common_flags_tmp.md >> docs/victoriametrics/vmalert_common_flags.md && \
@@ -170,11 +171,11 @@ docs-update-vmselect-flags:
 ifndef TAG
 	$(error TAG must be provided to update flags in docs)
 endif
-	git checkout $(TAG)-cluster && $(MAKE) vmselect && \
-	./bin/vmselect -help > /tmp/vmselect_common_flags_tmp.md
+	(cd /tmp/vm-opensource-cluster && $(MAKE) vmselect)
+	(cd /tmp/vm-opensource-cluster && ./bin/vmselect -help > /tmp/vmselect_common_flags_tmp.md)
 
-	git checkout $(TAG)-enterprise-cluster && $(MAKE) vmselect && \
-	./bin/vmselect -help > /tmp/vmselect_enterprise_flags_tmp.md
+	(cd /tmp/vm-enterprise-cluster && $(MAKE) vmselect)
+	(cd /tmp/vm-enterprise-cluster && ./bin/vmselect -help > /tmp/vmselect_enterprise_flags_tmp.md)
 
 	echo "$$FLAGS_HEADER" > docs/victoriametrics/vmselect_common_flags.md && \
 	cat /tmp/vmselect_common_flags_tmp.md >> docs/victoriametrics/vmselect_common_flags.md && \
@@ -199,11 +200,11 @@ docs-update-vminsert-flags:
 ifndef TAG
 	$(error TAG must be provided to update flags in docs)
 endif
-	git checkout $(TAG)-cluster && $(MAKE) vminsert && \
-	./bin/vminsert -help > /tmp/vminsert_common_flags_tmp.md
+	(cd /tmp/vm-opensource-cluster && $(MAKE) vminsert)
+	(cd /tmp/vm-opensource-cluster && ./bin/vminsert -help > /tmp/vminsert_common_flags_tmp.md)
 
-	git checkout $(TAG)-enterprise-cluster && $(MAKE) vminsert && \
-	./bin/vminsert -help > /tmp/vminsert_enterprise_flags_tmp.md
+	(cd /tmp/vm-enterprise-cluster && $(MAKE) vminsert)
+	(cd /tmp/vm-enterprise-cluster && ./bin/vminsert -help > /tmp/vminsert_enterprise_flags_tmp.md)
 
 	echo "$$FLAGS_HEADER" > docs/victoriametrics/vminsert_common_flags.md && \
 	cat /tmp/vminsert_common_flags_tmp.md >> docs/victoriametrics/vminsert_common_flags.md && \
@@ -235,11 +236,11 @@ docs-update-vmstorage-flags:
 ifndef TAG
 	$(error TAG must be provided to update flags in docs)
 endif
-	git checkout $(TAG)-cluster && $(MAKE) vmstorage && \
-	./bin/vmstorage -help > /tmp/vmstorage_common_flags_tmp.md
+	(cd /tmp/vm-opensource-cluster && $(MAKE) vmstorage)
+	(cd /tmp/vm-opensource-cluster && ./bin/vmstorage -help > /tmp/vmstorage_common_flags_tmp.md)
 
-	git checkout $(TAG)-enterprise-cluster && $(MAKE) vmstorage && \
-	./bin/vmstorage -help > /tmp/vmstorage_enterprise_flags_tmp.md
+	(cd /tmp/vm-enterprise-cluster && $(MAKE) vmstorage)
+	(cd /tmp/vm-enterprise-cluster && ./bin/vmstorage -help > /tmp/vmstorage_enterprise_flags_tmp.md)
 
 	echo "$$FLAGS_HEADER" > docs/victoriametrics/vmstorage_common_flags.md && \
 	cat /tmp/vmstorage_common_flags_tmp.md >> docs/victoriametrics/vmstorage_common_flags.md && \
@@ -263,13 +264,13 @@ docs-update-vmctl-flags:
 ifndef TAG
 	$(error TAG must be provided to update flags in docs)
 endif
-	git checkout $(TAG) && $(MAKE) vmctl && \
-	./bin/vmctl -help > /tmp/vmctl_flags_tmp.md && \
-	./bin/vmctl opentsdb -help > /tmp/vmctl_opentsdb_flags_tmp.md && \
-	./bin/vmctl influx -help > /tmp/vmctl_influx_flags_tmp.md && \
-	./bin/vmctl remote-read -help > /tmp/vmctl_remote-read_flags_tmp.md && \
-	./bin/vmctl prometheus -help > /tmp/vmctl_prometheus_flags_tmp.md && \
-	./bin/vmctl vm-native -help > /tmp/vmctl_vm-native_flags_tmp.md
+	(cd /tmp/vm-opensource && $(MAKE) vmctl)
+	(cd /tmp/vm-opensource && ./bin/vmctl -help > /tmp/vmctl_flags_tmp.md)
+	(cd /tmp/vm-opensource && ./bin/vmctl opentsdb -help > /tmp/vmctl_opentsdb_flags_tmp.md)
+	(cd /tmp/vm-opensource && ./bin/vmctl influx -help > /tmp/vmctl_influx_flags_tmp.md)
+	(cd /tmp/vm-opensource && ./bin/vmctl remote-read -help > /tmp/vmctl_remote-read_flags_tmp.md)
+	(cd /tmp/vm-opensource && ./bin/vmctl prometheus -help > /tmp/vmctl_prometheus_flags_tmp.md)
+	(cd /tmp/vm-opensource && ./bin/vmctl vm-native -help > /tmp/vmctl_vm-native_flags_tmp.md)
 
 	echo "$$FLAGS_HEADER" > docs/victoriametrics/vmctl/vmctl_flags.md && \
 	cat /tmp/vmctl_flags_tmp.md >> docs/victoriametrics/vmctl/vmctl_flags.md && \
@@ -306,6 +307,10 @@ endif
 	# remove Version line and the actual version line from vmctl_flags.md to reduce diffs noise
 	sed -i '/^VERSION:/,+1d' docs/victoriametrics/vmctl/vmctl_flags.md
 
+	# adjust flags with dynamic default values
+	# remove after https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9680 implemented
+	sed -i '/prom-tmp-dir-path/ s|(default: "[^"]*")|(default: os.TempDir())|' docs/victoriametrics/vmctl/vmctl_prometheus_flags.md
+
 # docs-update-flags updates flags in the documentation
 # using the actual binaries compiled from the provided $TAG.
 # The command also normalizes the output a bit.
@@ -324,12 +329,27 @@ endif
 	# Install using: brew install gnu-sed gawk
 	# Add tools to PATH see how in `brew info gnu-sed` and `brew info gawk
 
-	orig_branch=$$(git rev-parse --abbrev-ref HEAD); \
-	$(MAKE) docs-update-vmctl-flags && git checkout "$$orig_branch" && \
-	$(MAKE) docs-update-vmsingle-flags && git checkout "$$orig_branch" && \
-	$(MAKE) docs-update-vmalert-flags && git checkout "$$orig_branch" && \
-	$(MAKE) docs-update-vmauth-flags && git checkout "$$orig_branch" && \
-	$(MAKE) docs-update-vmagent-flags && git checkout "$$orig_branch" && \
-	$(MAKE) docs-update-vmselect-flags && git checkout "$$orig_branch" && \
-	$(MAKE) docs-update-vminsert-flags && git checkout "$$orig_branch" && \
-	$(MAKE) docs-update-vmstorage-flags && git checkout "$$orig_branch"
+	rm -rf /tmp/vm-enterprise
+	git worktree remove /tmp/vm-enterprise || true
+	git worktree add /tmp/vm-enterprise $(TAG)-enterprise
+
+	rm -rf /tmp/vm-enterprise-cluster
+	git worktree remove /tmp/vm-enterprise-cluster || true
+	git worktree add /tmp/vm-enterprise-cluster $(TAG)-enterprise-cluster
+
+	rm -rf /tmp/vm-opensource
+	git worktree remove /tmp/vm-opensource || true
+	git worktree add /tmp/vm-opensource $(TAG)
+
+	rm -rf /tmp/vm-opensource-cluster
+	git worktree remove /tmp/vm-opensource-cluster || true
+	git worktree add /tmp/vm-opensource-cluster $(TAG)-cluster
+
+	$(MAKE) docs-update-vmctl-flags
+	$(MAKE) docs-update-vmsingle-flags
+	$(MAKE) docs-update-vmalert-flags
+	$(MAKE) docs-update-vmauth-flags
+	$(MAKE) docs-update-vmagent-flags
+	$(MAKE) docs-update-vmselect-flags
+	$(MAKE) docs-update-vminsert-flags
+	$(MAKE) docs-update-vmstorage-flags

docs/ai-tools/README.md

@@ -1,6 +1,11 @@
-VictoriaMetrics Observability Stack integrates with AI assistants through MCP servers and agent skills.
-These integrations allow AI agents and automation tools to query metrics, logs, and traces, analyze telemetry data, 
-and assist engineers with debugging and observability tasks.
+VictoriaMetrics Observability Stack integrates with AI assistants through [MCP servers](https://docs.victoriametrics.com/ai-tools/#mcp-servers)
+and [agent skills](https://docs.victoriametrics.com/ai-tools/#agent-skills).
+The integrations allow AI agents and automation tools to query Metrics, Logs, and Traces, analyze telemetry data, 
+and assist engineers with debugging, observability tasks, root cause analysis, anomaly detection, etc.
+
+Support of [OpenTelemetry](https://docs.victoriametrics.com/opentelemetry/) for Metrics, Logs, and Traces
+makes VictoriaMetrics Observability Stack optimal for [AI observability](https://docs.victoriametrics.com/ai-tools/#ai-observability).
+Any SDK or AI assistant that can emit telemetry signals in OpenTelemetry format can be integrated with VictoriaMetrics.
 
 # MCP Servers
 
@@ -72,7 +77,6 @@ Capabilities include:
 
 See more details at [VictoriaMetrics/mcp-vmanomaly](https://github.com/VictoriaMetrics/mcp-vmanomaly).
 
-
 # Agent Skills
 
 [Agent skills](https://github.com/VictoriaMetrics/skills) help AI agents and automation tools understand, operate, 
@@ -90,4 +94,17 @@ To install the available skills for AI agents, run:
 npx skills add VictoriaMetrics/skills
 ```
 
-See more details at [VictoriaMetrics/skills](https://github.com/VictoriaMetrics/skills).
+See more details at [VictoriaMetrics/skills](https://github.com/VictoriaMetrics/skills).
+
+# AI observability
+
+VictoriaMetrics Observability Stack is optimal for monitoring AI agents using auto-instrumentation libraries
+like [OpenLLMetry](https://github.com/traceloop/openllmetry), [OpenInference](https://github.com/Arize-ai/openinference),
+[OpenLIT](https://victoriametrics.com/blog/ai-agents-observability/#using-openlit).
+Please see more details in [AI Agents Observability with OpenTelemetry and the VictoriaMetrics Stack](https://victoriametrics.com/blog/ai-agents-observability).
+
+AI code assistants like Claude Code, OpenAI Codex, Gemini CLI, Qwen Code, and OpenCode expose internal telemetry that
+helps to monitor cost usage, analytics, performance, compliance and improves troubleshooting experience. All major
+AI coding tools support OpenTelemetry and can be easily integrated into VictoriaMetrics Observability Stack.
+Please see more details in [Vibe coding tools observability with VictoriaMetrics Stack and OpenTelemetry
+](https://victoriametrics.com/blog/vibe-coding-observability/).

docs/anomaly-detection/CHANGELOG.md

@@ -14,6 +14,15 @@ aliases:
 ---
 Please find the changelog for VictoriaMetrics Anomaly Detection below.
 
+## v1.29.4
+Released: 2026-05-15
+
+- IMPROVEMENT: Optimized [BacktestingScheduler](https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#backtesting-scheduler) exact mode for [online models](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-models) (which are also used in [UI](https://docs.victoriametrics.com/anomaly-detection/ui/)-triggered tasks), leading to 2-200x faster results and more responsive UI interactions.
+
+- UI: Updated [vmanomaly UI](https://docs.victoriametrics.com/anomaly-detection/ui/) from [v1.6.1](https://docs.victoriametrics.com/anomaly-detection/ui/#v161) to [v1.7.0](https://docs.victoriametrics.com/anomaly-detection/ui/#v170), see respective [release notes](https://docs.victoriametrics.com/anomaly-detection/ui/#v170) for details. Notable changes include iterative anomaly detection with progress bar, model inference speedups, improved AI Copilot UX and various bug fixes.
+
+- BUGFIX: Made model-level `queries` and `schedulers` attachment semantics explicit and safer. Omitting these args still keeps the legacy default of attaching a model to all queries or schedulers with a warning, while `queries: null`, `queries: []`, `schedulers: null`, and `schedulers: []` now mean the model is intentionally unattached and will be dropped from active execution. Use `queries: all` or `schedulers: all` to request all attachments explicitly. Orphan models, queries, and schedulers are logged and removed during config validation, including hot reload.
+
 ## v1.29.3
 Released: 2026-04-16
 

docs/anomaly-detection/FAQ.md

@@ -423,7 +423,7 @@ services:
   # ...
   vmanomaly:
     container_name: vmanomaly
-    image: victoriametrics/vmanomaly:v1.29.3
+    image: victoriametrics/vmanomaly:v1.29.4
     # ...
     restart: always
     volumes:
@@ -641,7 +641,7 @@ options:
 Here’s an example of using the config splitter to divide configurations based on the `extra_filters` argument from the reader section:
 
 ```sh
-docker pull victoriametrics/vmanomaly:v1.29.3 && docker image tag victoriametrics/vmanomaly:v1.29.3 vmanomaly
+docker pull victoriametrics/vmanomaly:v1.29.4 && docker image tag victoriametrics/vmanomaly:v1.29.4 vmanomaly
 ```
 
 ```sh

docs/anomaly-detection/QuickStart.md

@@ -122,7 +122,7 @@ Below are the steps to get `vmanomaly` up and running inside a Docker container:
 1. Pull Docker image:
 
 ```sh
-docker pull victoriametrics/vmanomaly:v1.29.3
+docker pull victoriametrics/vmanomaly:v1.29.4
 ```
 
 2. Create the license file with your license key.
@@ -142,7 +142,7 @@ docker run -it \
     -v ./license:/license \
     -v ./config.yaml:/config.yaml \
     -p 8490:8490 \
-    victoriametrics/vmanomaly:v1.29.3 \
+    victoriametrics/vmanomaly:v1.29.4 \
     /config.yaml \
     --licenseFile=/license \
     --loggerLevel=INFO \
@@ -159,7 +159,7 @@ docker run -it \
     -e VMANOMALY_DATA_DUMPS_DIR=/tmp/vmanomaly/data \
     -e VMANOMALY_MODEL_DUMPS_DIR=/tmp/vmanomaly/models \
     -p 8490:8490 \
-    victoriametrics/vmanomaly:v1.29.3 \
+    victoriametrics/vmanomaly:v1.29.4 \
     /config.yaml \
     --licenseFile=/license \
     --loggerLevel=INFO \
@@ -172,7 +172,7 @@ services:
   # ...
   vmanomaly:
     container_name: vmanomaly
-    image: victoriametrics/vmanomaly:v1.29.3
+    image: victoriametrics/vmanomaly:v1.29.4
     # ...
     restart: always
     volumes:

docs/anomaly-detection/UI.md

@@ -315,7 +315,7 @@ docker run -it --rm \
   -e VMANOMALY_MCP_SERVER_URL=http://mcp-vmanomaly:8081/mcp \
   -p 8080:8080 \
   -p 8490:8490 \
-  victoriametrics/vmanomaly:v1.29.3 \
+  victoriametrics/vmanomaly:v1.29.4 \
   vmanomaly_config.yaml
 ```
 
@@ -640,6 +640,26 @@ If the **results** look good and the **model configuration should be deployed in
 
 ## Changelog
 
+### v1.7.0
+Released: 2026-05-15
+
+vmanomaly version: [v1.29.4](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1294)
+
+- FEATURE: Improved [AI Copilot](#ai-assistance) to 
+  - support textual attachments, such as configuration files, query examples, model outputs, etc.
+  - operate with current time when suggesting time range changes, e.g. "current month" or "from the beginning of the last month until now"
+- FEATURE: improve infer jobs scheduled from UI to
+  - run 2-100x faster for [online models](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-models) depending on a configuration vs [1.6.1](#v161) timings
+  - show stage-aware progress bar, e.g. "getting data", "fitting model", "inferring on chunk".
+- IMPROVEMENT: "Advanced Options" design is improved, section is collapsed by default to save vertical space, yet can be encoded as always open in UI state URL.
+- IMPROVEMENT: dropdowns in UI are now searcheable and constrained in size for better UX, especially when many options are available (e.g. models list, tenants list, etc.).
+- BUGFIX: in generated config ("Show Config" menu)
+  - special YAML values (like `-.inf`, `.inf`, `.nan`) are now properly quoted and formatted to avoid JSON converting issues when copied to Kubernetes CRs, which previously lead to rejection of the manifest before vmanomaly can consume it.
+  - with Data Source selected as "Logs/Traces" `reader.class` is now correctly set to `vlogs` (previously `vm`) in generated config, when "model only" toggle is turned off.
+- BUGFIX: now "Hide Common Labels" toggle in "Table View" works correctly and does not show common labels in the legend columns when turned on.
+- BUGFIX: improved dropdowns for better accessibility to be searcheable and constrained in size.
+- BUGFIX: "Prettify query" now works correctly for "Metrics" datasources.
+
 ### v1.6.1
 Released: 2026-04-16
 

docs/anomaly-detection/components/models.md

@@ -1265,7 +1265,7 @@ monitoring:
 Let's pull the docker image for `vmanomaly`:
 
 ```sh
-docker pull victoriametrics/vmanomaly:v1.29.2
+docker pull victoriametrics/vmanomaly:v1.29.4
 ```
 
 Now we can run the docker container putting as volumes both config and model file:
@@ -1279,7 +1279,7 @@ docker run -it \
 -v $(PWD)/license:/license \
 -v $(PWD)/custom_model.py:/vmanomaly/model/custom.py \
 -v $(PWD)/custom.yaml:/config.yaml \
-victoriametrics/vmanomaly:v1.29.2 /config.yaml \
+victoriametrics/vmanomaly:v1.29.4 /config.yaml \
 --licenseFile=/license
 --watch
 ```

docs/anomaly-detection/guides/guide-vmanomaly-vmalert/README.md

@@ -395,7 +395,7 @@ services:
     restart: always
   vmanomaly:
     container_name: vmanomaly
-    image: victoriametrics/vmanomaly:v1.29.3
+    image: victoriametrics/vmanomaly:v1.29.4
     depends_on:
       - "victoriametrics"
     ports:

docs/guides/collecting-openshift-logs-with-victoria-logs/README.md

@@ -6,31 +6,133 @@ build:
 sitemap:
   disable: true
 ---
-This guide covers OpenShift cluster configuration for collecting and storing logs in Victoria Logs.
+
+This guide explains how to collect and store logs from an OpenShift cluster in VictoriaLogs.
 
 ## Pre-Requirements
 
 * [OpenShift cluster](https://www.redhat.com/en/technologies/cloud-computing/openshift)
 * Admin access to OpenShift cluster
-* [kubectl installed](https://kubernetes.io/docs/tasks/tools/install-kubectl) and configured to access OpenShift cluster
+* [kubectl](https://kubernetes.io/docs/tasks/tools/install-kubectl) or [oc](https://github.com/openshift/oc) installed and configured to access OpenShift cluster
 * [Helm installed](https://helm.sh/docs/intro/install)
 
-## Install Red Hat OpenShift Logging operator 
+> [!NOTE] Note
+> You can replace every `kubectl` command in this guide with `oc`. They are interchangeable in most cases on OpenShift clusters.
 
-[Cluster logging operator](https://github.com/openshift/cluster-logging-operator) is a logging solution to support aggregated cluster logging. It is using [Vector](https://vector.dev/) for logs collection and shipping to remote storage.
+## Overview
 
-In order to install the operator, navigate to the OpenShift web console and select the `Operators` tab. Then, click on `OperatorHub` and search for `Red Hat OpenShift Logging`. Click on the `Red Hat OpenShift Logging` operator and then click on `Install`.
+To collect OpenShift logs, we're going to:
 
-![Install logging operator](install-oc-logging-operator.webp)
+1. [Install VictoriaLogs](https://docs.victoriametrics.com/guides/collecting-openshift-logs-with-victoria-logs/#install-victoria-logs) in the OpenShift Cluster
+2. [Configure a service account](https://docs.victoriametrics.com/guides/collecting-openshift-logs-with-victoria-logs/#rbac-configuration) to access the logs
+3. [Install the OpenShift Logging operator](https://docs.victoriametrics.com/guides/collecting-openshift-logs-with-victoria-logs/#install-red-hat-openshift-logging-operator)
+4. [Configure a Log Forwarder](https://docs.victoriametrics.com/guides/collecting-openshift-logs-with-victoria-logs/#configure-logs-forwarding)
+5. [Test log ingestion](https://docs.victoriametrics.com/guides/collecting-openshift-logs-with-victoria-logs/#verify-logs-ingestion) in VictoriaLogs
 
+## Install VictoriaLogs {#install-victoria-logs}
 
-## RBAC configuration
+Run the following command to add the [VictoriaMetrics Helm repository](https://github.com/VictoriaMetrics/helm-charts):
 
-Create a service account and cluster role binding for the service account to access the logs. 
-OpenShift provides separate `ClusterRoles` for monitoring of different types of logs: `audit`, `infrastructure` and `application`. 
+```shell
+helm repo add vm https://victoriametrics.github.io/helm-charts/
+helm repo update
+```
 
-The following configuration will allow the service account to collect all types of logs:
-```yaml
+To verify that everything is set up correctly, you may run this command:
+
+```shell
+helm search repo vm/
+```
+
+You should get a list similar to this:
+
+```text
+NAME                                    CHART VERSION   APP VERSION     DESCRIPTION
+vm/victoria-logs-agent                  0.1.1           v1.50.0         VictoriaLogs Agent - accepts logs from various ...
+vm/victoria-logs-collector              0.3.1           v1.50.0         VictoriaLogs Collector - collects logs from Kub...
+vm/victoria-logs-single                 0.12.2          v1.50.0         The VictoriaLogs single Helm chart deploys Vict...
+...
+```
+
+Create a minimal configuration file to run VictoriaLogs in OpenShift:
+
+```shell
+cat <<EOF >vl-values.yml
+securityContext:
+  enabled: true
+  allowPrivilegeEscalation: false
+  capabilities:
+    drop:
+      - ALL
+  readOnlyRootFilesystem: true
+
+podSecurityContext:
+  enabled: true
+  runAsNonRoot: true
+EOF
+```
+
+> Note that, depending on the OpenShift cluster configuration, additional security settings might be required.
+
+Create a namespace for VictoriaLogs called `vl`:
+
+```shell
+kubectl create namespace vl
+```
+
+Install VictoriaLogs with the following command:
+
+```shell
+helm upgrade --namespace vl --install vl vm/victoria-logs-single -f vl-values.yml
+```
+
+You should see a message like this:
+
+```text
+Release "vl" does not exist. Installing it now.
+NAME: vl
+LAST DEPLOYED: Fri Apr 17 01:05:42 2026
+NAMESPACE: vl
+STATUS: deployed
+REVISION: 1
+DESCRIPTION: Install complete
+TEST SUITE: None
+NOTES:
+The VictoriaLogs write api can be accessed via port 9428 on the following DNS name from within your cluster:
+    vl-victoria-logs-single-server-0.vl-victoria-logs-single-server.vl.svc.cluster.local.
+
+Logs Ingestion:
+  Get the VictoriaLogs service URL by running these commands in the same shell:
+    kubectl --namespace vl port-forward svc/vl-victoria-logs-single-server 9428:9428
+    echo http://localhost:9428
+
+  Write URL inside the kubernetes cluster:
+    http://vl-victoria-logs-single-server.vl.svc.cluster.local.:9428<protocol-specific-write-endpoint>
+
+  See the documentation for log ingestion and supported write endpoints at https://docs.victoriametrics.com/victorialogs/data-ingestion/.
+
+Read Data:
+  The following URL can be used to query data:
+    http://vl-victoria-logs-single-server.vl.svc.cluster.local.:9428
+
+  See the documentation for log querying UI at https://docs.victoriametrics.com/victorialogs/querying/#web-ui or HTTP API at https://docs.victoriametrics.com/victorialogs/querying/#http-api
+```
+
+Note the "Write URL" value as you'll need it later. In the example above, the value is:
+
+```text
+http://vl-victoria-logs-single-server.vl.svc.cluster.local.:9428
+```
+
+## RBAC Configuration
+
+Create a service account and cluster role binding for the service account to collect and forward the logs.
+OpenShift provides separate `ClusterRoles` for monitoring of different types of logs: `audit`, `infrastructure`, and `application`. 
+
+Create a file to configure the service account and cluster role bindings:
+
+```shell
+cat <<EOF >vl-rbac.yml
 kind: ServiceAccount
 apiVersion: v1
 metadata:
@@ -77,52 +179,42 @@ roleRef:
   name: collect-application-logs
 ```
 
-Alternatively, you can use OpenShift console to create the service account and cluster role binding. 
-Navigate to `ServiceAccounts` and click on `Create Service Account`. Fill in the name `victorialogs` and namespace `openshift-logging` and click on `Create`. 
-Then, navigate to `RoleBindings` and create a binding for each `ClusterRole` for subject `victorialogs` in `openshift-logging` namespace.
+Install the roles in OpenShift with:
 
-
-## Install Victoria Logs
-
-Add Victoria Metrics Helm [repository](https://github.com/VictoriaMetrics/helm-charts):
-```bash
-helm repo add vm https://victoriametrics.github.io/helm-charts/
+```shell
+kubectl apply -f vl-rbac.yml
 ```
 
-Minimal configuration for VictoriaLogs running in OpenShift:
-```yaml
-securityContext:
-  enabled: true
-  allowPrivilegeEscalation: false
-  capabilities:
-    drop:
-      - ALL
-  readOnlyRootFilesystem: true
+Alternatively, you can use the OpenShift web console to create the service account and cluster role binding. To do this:
 
-podSecurityContext:
-  enabled: true
-  runAsNonRoot: true
-```
-Save the configuration to `vl.yaml`.
+1. Navigate to **ServiceAccounts**.
+2. Click on **Create Service Account**.
+3. Fill in the name `victorialogs` and namespace `openshift-logging`.
+4. Click on **Create**. 
+5. Navigate to **RoleBindings**.
+6. Create a binding for each `ClusterRole` for subject `victorialogs` in `openshift-logging` namespace.
 
-> Note, that depending on the OpenShift cluster configuration, additional security settings might be required.
+## Install Red Hat OpenShift Logging operator 
 
-Create namespace for VictoriaLogs:
-```bash
-kubectl create namespace vl
-```
+The [Cluster logging operator](https://github.com/openshift/cluster-logging-operator) is a logging solution to support aggregated cluster logging. It is using [Vector](https://vector.dev/) for log collection and shipping to remote storage.
 
-Install VictoriaLogs with the following command:
-```bash
-helm upgrade --namespace vl --install vl vm/victoria-logs-single -f vl.yaml
-```
+To install the operator:
+
+1. Navigate to **Ecosystem** > **Software Catalog**
+2. Search for "OpenShift Logging" and select the operator.
+    ![Screenshot of OpenShift web console](software-catalog-openshift-logging-1.webp)
+3. Press **Install**.
+4. Confirm the settings and press **Install** again.
+    ![Screenshot of OpenShift web console](software-catalog-openshift-logging-options-3.webp)
 
 ## Configure logs forwarding
 
-Cluster logging operator uses `ClusterLogForwarder` resource for logs forwarding configuration.
+We need to create a `ClusterLogForwarder` resource to forward logs from the OpenShift Logging operator to VictoriaLogs.
 
-Here is an example configuration to forward all cluster logs to VictoriaLogs:
-```yaml
+Run the following command to create the resource file:
+
+```shell
+cat <<EOF > vl-forwarder.yml
 apiVersion: observability.openshift.io/v1
 kind: ClusterLogForwarder
 metadata:
@@ -160,7 +252,7 @@ spec:
         - application
       name: application
       outputRefs:
-        - victorialogs-audit
+        - victorialogs
     - inputRefs:
         - infrastructure
       name: infrastructure
@@ -170,21 +262,66 @@ spec:
         - audit
       name: audit
       outputRefs:
-        - victorialogs
+        - victorialogs-audit
   serviceAccount:
     name: victorialogs
+EOF
 ```
 
-It is also possible to configure logs forwarding using OpenShift console. Navigate to `Operators` tab and click on `Installed Operators`. Then, click on `Red Hat OpenShift Logging` and navigate to `ClusterLogForwarders`. Click on `Create ClusterLogForwarder`. 
-Configure the forwarding to VictoriaLogs using the provided form and click on `Create`.
-![Create logs forwarders menu](create-cluster-logs-forwarder.webp)
-![Create forwarder config](create-cluster-logs-forwarder-2.webp)
+Then install the resource with:
 
-## Verify logs collection
+```shell
+kubectl apply -f vl-forwarder.yml
+```
 
-To verify that logs are collected and stored in VictoriaLogs, navigate to the VictoriaLogs web interface.
+Alternatively, you can configure log forwarding in the OpenShift web console. To do this:
+1. Navigate to **Operators** tab
+2. Click on **Installed Operators**.
+3. Find **Red Hat OpenShift Logging**
+4. Navigate to **ClusterLogForwarders**.
+5. Click on **Create ClusterLogForwarder**.
+    ![Screenshot of OpenShift web console](software-catalog-openshift-logging-forwarder-5.webp)
+6. Use the form to configure each type of forwarder.
+    ![Screenshot of OpenShift web console](forwarder-form.webp)
+7. Click **Create**
 
-![VictoriaLogs](openshift-logs.webp)
+## Verify logs ingestion
+
+We can verify that logs are being collected using the VictoriaLogs VMUI.
+
+First, find the service name for the VMUI with:
+
+```shell
+kubectl get svc -n vl -l app.kubernetes.io/instance=vl
+```
+
+You should get a result similar to this. Note the name of the service:
+
+```text
+NAME                             TYPE        CLUSTER-IP   EXTERNAL-IP   PORT(S)    AGE
+vl-victoria-logs-single-server   ClusterIP   None         <none>        9428/TCP   113s
+```
+
+Then, port-forward the VMUI service console with:
+
+```shell
+kubectl -n vl port-forward svc/vl-victoria-logs-single-server 9428:9428
+```
+
+Open your browser in `http://localhost:9428/select/vmui/#/overview` and verify that logs are being collected. This overview page shows the number of log entries being consumed in real time.
+
+![Screenshot of VMUI for VictoriaLogs](vmui-overview.webp)
+<figcaption style="text-align: center; font-style: italic;">Overview pane in VMUI</figcaption>
+
+You can query your logs in the **Query** tab, found in `http://localhost:9428/select/vmui`. 
+You can filter streams on the left side pane to filter logs and use [LogsQL](https://docs.victoriametrics.com/victorialogs/logsql/) to search for entries. Note that logs will have `log_type` attached to them to distinguish between different types of logs.
+
+![Screenshot of VMUI for VictoriaLogs](vmui-query-filters.webp)
+<figcaption style="text-align: center; font-style: italic;">Query pane in VMUI</figcaption>
+
+## See also
+
+- [VictoriaLogs Quickstart](https://docs.victoriametrics.com/victorialogs/quickstart/)
+- [Logs Reference](https://docs.victoriametrics.com/victorialogs/logsql/)
+- [LogsQL Examples](https://docs.victoriametrics.com/victorialogs/logsql-examples/)
 
-Logs will be available in the interface and can be queried using [LogsQL](https://docs.victoriametrics.com/victorialogs/logsql/).
-Note that logs will have `log_type` attached to them to distinguish between different types of logs.