lib/promutil: Weak pointer based labels compressor

required for https://github.com/VictoriaMetrics/vmdocs/issues/164

### Describe Your Changes

Please provide a brief description of the changes you made. Be as
specific as possible to help others understand the purpose and impact of
your modifications.

### Checklist

The following checks are **mandatory**:

- [ ] My change adheres to [VictoriaMetrics contributing
guidelines](https://docs.victoriametrics.com/victoriametrics/contributing/#pull-request-checklist).
- [ ] My change adheres to [VictoriaMetrics development
goals](https://docs.victoriametrics.com/victoriametrics/goals/).

.github/copilot-instructions.md

@@ -0,0 +1,23 @@
+# Project Overview
+
+VictoriaMetrics is a fast, cost-saving, and scalable solution for monitoring and managing time series data. It delivers high performance and reliability, making it an ideal choice for businesses of all sizes.
+
+## Folder Structure
+
+- `/app`: Contains the compilable binaries.
+- `/lib`: Contains the golang reusable libraries
+- `/docs/victoriametrics`: Contains documentation for the project.
+- `/apptest/tests`: Contains integration tests.
+
+## Libraries and Frameworks
+
+- Backend: Golang, no framework. Use third-party libraries sparingly.
+- Frontend: React.
+
+## Code review guidelines
+
+Ensure the feature or bugfix includes a changelog entry in /docs/victoriametrics/changelog/CHANGELOG.md.
+Verify the entry is under the ## tip section and matches the structure and style of existing entries.
+Chore-only changes may be omitted from the changelog.
+
+

.github/workflows/build.yml

@@ -31,43 +31,48 @@ concurrency:
 
 jobs:
   build:
-    name: Build
+    name: ${{ matrix.os }}-${{ matrix.arch }}
     runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - os: linux
+            arch: 386
+          - os: linux
+            arch: amd64
+          - os: linux
+            arch: arm64
+          - os: linux
+            arch: arm
+          - os: linux
+            arch: ppc64le
+          - os: darwin
+            arch: amd64
+          - os: darwin
+            arch: arm64
+          - os: freebsd
+            arch: amd64
+          - os: openbsd
+            arch: amd64
+          - os: windows
+            arch: amd64
     steps:
-      - name: Free space
-        run: |
-          # cleanup up space to free additional ~20GiB of memory
-          # which are lacking for multiplaform images build
-          formatByteCount() { echo $(numfmt --to=iec-i --suffix=B --padding=7 $1'000'); }
-          getAvailableSpace() { echo $(df -a $1 | awk 'NR > 1 {avail+=$4} END {print avail}'); }
-          BEFORE=$(getAvailableSpace)
-          sudo rm -rf /usr/local/lib/android || true
-          sudo rm -rf /usr/share/dotnet || true
-          sudo rm -rf /opt/ghc || true
-          sudo rm -rf /usr/local/.ghcup || true
-          AFTER=$(getAvailableSpace)
-          SAVED=$((AFTER-BEFORE))
-          echo "Saved $(formatByteCount $SAVED)"
-
       - name: Code checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Setup Go
         id: go
         uses: actions/setup-go@v5
         with:
+          cache-dependency-path: |
+            go.sum
+            Makefile
+            app/**/Makefile
           go-version: stable
-          cache: false
 
-      - name: Cache Go artifacts
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/go-build
-            ~/go/bin
-            ~/go/pkg/mod
-          key: go-artifacts-${{ runner.os }}-crossbuild-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
-          restore-keys: go-artifacts-${{ runner.os }}-crossbuild-
+      - name: Build victoria-metrics for ${{ matrix.os }}-${{ matrix.arch }}
+        run: make victoria-metrics-${{ matrix.os }}-${{ matrix.arch }}
 
-      - name: Run crossbuild
-        run: make crossbuild
+      - name: Build vmutils for ${{ matrix.os }}-${{ matrix.arch }}
+        run: make vmutils-${{ matrix.os }}-${{ matrix.arch }}

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

@@ -29,7 +29,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Set up Go
         id: go

.github/workflows/docs.yaml

@@ -16,12 +16,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           path: __vm
 
       - name: Checkout private code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           repository: VictoriaMetrics/vmdocs
           token: ${{ secrets.VM_BOT_GH_TOKEN }}

.github/workflows/test.yml

@@ -1,4 +1,4 @@
-name: main
+name: test
 
 on:
   push:
@@ -25,39 +25,41 @@ concurrency:
   cancel-in-progress: true
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
 
+
 jobs:
   lint:
     name: lint
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Setup Go
         id: go
         uses: actions/setup-go@v5
         with:
-          cache: false
+          cache-dependency-path: |
+            go.sum
+            Makefile
+            app/**/Makefile
           go-version: stable
 
-      - name: Cache Go artifacts
+
+      - name: Cache golangci-lint
         uses: actions/cache@v4
         with:
           path: |
-            ~/.cache/go-build
+            ~/.cache/golangci-lint
             ~/go/bin
-            ~/go/pkg/mod
-          key: go-artifacts-${{ runner.os }}-check-all-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
-          restore-keys: go-artifacts-${{ runner.os }}-check-all-
+          key: golangci-lint-${{ runner.os }}-${{ hashFiles('.golangci.yml') }}
 
       - name: Run check-all
         run: |
           make check-all
           git diff --exit-code
 
-  test:
-    name: test
-    needs: lint
+  unit:
+    name: unit
     runs-on: ubuntu-latest
 
     strategy:
@@ -69,25 +71,18 @@ jobs:
 
     steps:
       - name: Code checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Setup Go
         id: go
         uses: actions/setup-go@v5
         with:
-          cache: false
+          cache-dependency-path: |
+            go.sum
+            Makefile
+            app/**/Makefile
           go-version: stable
 
-      - name: Cache Go artifacts
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/go-build
-            ~/go/bin
-            ~/go/pkg/mod
-          key: go-artifacts-${{ runner.os }}-${{ matrix.scenario }}-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
-          restore-keys: go-artifacts-${{ runner.os }}-${{ matrix.scenario }}-
-
       - name: Run tests
         run: GOGC=10 make ${{ matrix.scenario}}
 
@@ -96,31 +91,23 @@ jobs:
         with:
           files: ./coverage.txt
 
-  integration-test:
-    name: integration-test
-    needs: [lint, test]
+  integration:
+    name: integration
     runs-on: ubuntu-latest
 
     steps:
       - name: Code checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Setup Go
         id: go
         uses: actions/setup-go@v5
         with:
-          cache: false
+          cache-dependency-path: |
+            go.sum
+            Makefile
+            app/**/Makefile
           go-version: stable
 
-      - name: Cache Go artifacts
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/go-build
-            ~/go/bin
-            ~/go/pkg/mod
-          key: go-artifacts-${{ runner.os }}-${{ matrix.scenario }}-${{ steps.go.outputs.go-version }}-${{ hashFiles('go.sum', 'Makefile', 'app/**/Makefile') }}
-          restore-keys: go-artifacts-${{ runner.os }}-${{ matrix.scenario }}-
-
       - name: Run integration tests
         run: make integration-test

.github/workflows/vmui.yml

@@ -32,7 +32,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Setup Node
         uses: actions/setup-node@v4

Makefile

@@ -12,11 +12,12 @@ PKG_TAG := $(BUILDINFO_TAG)
 endif
 
 EXTRA_DOCKER_TAG_SUFFIX ?=
+EXTRA_GO_BUILD_TAGS ?=
 
 GO_BUILDINFO = -X '$(PKG_PREFIX)/lib/buildinfo.Version=$(APP_NAME)-$(DATEINFO_TAG)-$(BUILDINFO_TAG)'
 TAR_OWNERSHIP ?= --owner=1000 --group=1000
 
-GOLANGCI_LINT_VERSION := 2.2.1
+GOLANGCI_LINT_VERSION := 2.4.0
 
 .PHONY: $(MAKECMDGOALS)
 
@@ -169,9 +170,11 @@ vmutils-windows-amd64: \
 	vmrestore-windows-amd64 \
 	vmctl-windows-amd64
 
+# When adding a new crossbuild target, please also add it to the .github/workflows/build.yml
 crossbuild:
 	$(MAKE_PARALLEL) victoria-metrics-crossbuild vmutils-crossbuild
 
+# When adding a new crossbuild target, please also add it to the .github/workflows/build.yml
 victoria-metrics-crossbuild: \
 	victoria-metrics-linux-386 \
 	victoria-metrics-linux-amd64 \
@@ -184,6 +187,7 @@ victoria-metrics-crossbuild: \
 	victoria-metrics-openbsd-amd64 \
 	victoria-metrics-windows-amd64
 
+# When adding a new crossbuild target, please also add it to the .github/workflows/build.yml
 vmutils-crossbuild: \
 	vmutils-linux-386 \
 	vmutils-linux-amd64 \
@@ -467,16 +471,16 @@ vendor-update:
 	go mod vendor
 
 app-local:
-	CGO_ENABLED=1 go build $(RACE) -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
+	CGO_ENABLED=1 go build $(RACE) -ldflags "$(GO_BUILDINFO)" -tags "$(EXTRA_GO_BUILD_TAGS)" -o bin/$(APP_NAME)$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
 
 app-local-pure:
-	CGO_ENABLED=0 go build $(RACE) -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)-pure$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
+	CGO_ENABLED=0 go build $(RACE) -ldflags "$(GO_BUILDINFO)" -tags "$(EXTRA_GO_BUILD_TAGS)" -o bin/$(APP_NAME)-pure$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
 
 app-local-goos-goarch:
-	CGO_ENABLED=$(CGO_ENABLED) GOOS=$(GOOS) GOARCH=$(GOARCH) go build $(RACE) -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)-$(GOOS)-$(GOARCH)$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
+	CGO_ENABLED=$(CGO_ENABLED) GOOS=$(GOOS) GOARCH=$(GOARCH) go build $(RACE) -ldflags "$(GO_BUILDINFO)" -tags "$(EXTRA_GO_BUILD_TAGS)" -o bin/$(APP_NAME)-$(GOOS)-$(GOARCH)$(RACE) $(PKG_PREFIX)/app/$(APP_NAME)
 
 app-local-windows-goarch:
-	CGO_ENABLED=0 GOOS=windows GOARCH=$(GOARCH) go build $(RACE) -ldflags "$(GO_BUILDINFO)" -o bin/$(APP_NAME)-windows-$(GOARCH)$(RACE).exe $(PKG_PREFIX)/app/$(APP_NAME)
+	CGO_ENABLED=0 GOOS=windows GOARCH=$(GOARCH) go build $(RACE) -ldflags "$(GO_BUILDINFO)" -tags "$(EXTRA_GO_BUILD_TAGS)" -o bin/$(APP_NAME)-windows-$(GOARCH)$(RACE).exe $(PKG_PREFIX)/app/$(APP_NAME)
 
 quicktemplate-gen: install-qtc
 	qtc

app/victoria-metrics/self_scraper.go

@@ -57,7 +57,8 @@ func selfScraper(scrapeInterval time.Duration) {
 		appmetrics.WritePrometheusMetrics(&bb)
 		s := bytesutil.ToUnsafeString(bb.B)
 		rows.Reset()
-		rows.Unmarshal(s)
+		// VictoriaMetrics components don't expose metadata yet, only need to parse samples
+		rows.UnmarshalWithErrLogger(s, nil)
 		mrs = mrs[:0]
 		for i := range rows.Rows {
 			r := &rows.Rows[i]

app/vmagent/opentelemetry/request_handler.go

@@ -8,6 +8,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/firehose"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/opentelemetry/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
@@ -16,9 +17,11 @@ import (
 )
 
 var (
-	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="opentelemetry"}`)
-	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="opentelemetry"}`)
-	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="opentelemetry"}`)
+	rowsInserted           = metrics.NewCounter(`vmagent_rows_inserted_total{type="opentelemetry"}`)
+	metadataInserted       = metrics.NewCounter(`vmagent_metadata_inserted_total{type="opentelemetry"}`)
+	rowsTenantInserted     = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="opentelemetry"}`)
+	metadataTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_metadata_total{type="opentelemetry"}`)
+	rowsPerInsert          = metrics.NewHistogram(`vmagent_rows_per_insert{type="opentelemetry"}`)
 )
 
 // InsertHandler processes opentelemetry metrics.
@@ -36,12 +39,12 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
 			return fmt.Errorf("json encoding isn't supported for opentelemetry format. Use protobuf encoding")
 		}
 	}
-	return stream.ParseStream(req.Body, encoding, processBody, func(tss []prompb.TimeSeries) error {
-		return insertRows(at, tss, extraLabels)
+	return stream.ParseStream(req.Body, encoding, processBody, func(tss []prompb.TimeSeries, mms []prompb.MetricMetadata) error {
+		return insertRows(at, tss, mms, extraLabels)
 	})
 }
 
-func insertRows(at *auth.Token, tss []prompb.TimeSeries, extraLabels []prompb.Label) error {
+func insertRows(at *auth.Token, tss []prompb.TimeSeries, mms []prompb.MetricMetadata, extraLabels []prompb.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
@@ -63,14 +66,33 @@ func insertRows(at *auth.Token, tss []prompb.TimeSeries, extraLabels []prompb.La
 		})
 	}
 	ctx.WriteRequest.Timeseries = tssDst
+
+	var metadataTotal int
+	if promscrape.IsMetadataEnabled() {
+		var accountID, projectID uint32
+		if at != nil {
+			accountID = at.AccountID
+			projectID = at.ProjectID
+			for i := range mms {
+				mm := &mms[i]
+				mm.AccountID = accountID
+				mm.ProjectID = projectID
+			}
+		}
+		ctx.WriteRequest.Metadata = mms
+		metadataTotal = len(mms)
+	}
+
 	ctx.Labels = labels
 	ctx.Samples = samples
 	if !remotewrite.TryPush(at, &ctx.WriteRequest) {
 		return remotewrite.ErrQueueFullHTTPRetry
 	}
 	rowsInserted.Add(rowsTotal)
+	metadataInserted.Add(metadataTotal)
 	if at != nil {
 		rowsTenantInserted.Get(at).Add(rowsTotal)
+		metadataTenantInserted.Get(at).Add(metadataTotal)
 	}
 	rowsPerInsert.Update(float64(rowsTotal))
 	return nil

app/vmagent/prometheusimport/request_handler.go

@@ -8,6 +8,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
@@ -16,9 +17,12 @@ import (
 )
 
 var (
-	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="prometheus"}`)
-	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="prometheus"}`)
-	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="prometheus"}`)
+	rowsInserted           = metrics.NewCounter(`vmagent_rows_inserted_total{type="prometheus"}`)
+	metadataInserted       = metrics.NewCounter(`vmagent_metadata_inserted_total{type="prometheus"}`)
+	rowsTenantInserted     = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="prometheus"}`)
+	metadataTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_metadata_total{type="prometheus"}`)
+
+	rowsPerInsert = metrics.NewHistogram(`vmagent_rows_per_insert{type="prometheus"}`)
 )
 
 // InsertHandler processes `/api/v1/import/prometheus` request.
@@ -32,18 +36,19 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
 		return err
 	}
 	encoding := req.Header.Get("Content-Encoding")
-	return stream.Parse(req.Body, defaultTimestamp, encoding, true, func(rows []prometheus.Row) error {
-		return insertRows(at, rows, extraLabels)
+	return stream.Parse(req.Body, defaultTimestamp, encoding, true, promscrape.IsMetadataEnabled(), func(rows []prometheus.Row, mms []prometheus.Metadata) error {
+		return insertRows(at, rows, mms, extraLabels)
 	}, func(s string) {
 		httpserver.LogError(req, s)
 	})
 }
 
-func insertRows(at *auth.Token, rows []prometheus.Row, extraLabels []prompb.Label) error {
+func insertRows(at *auth.Token, rows []prometheus.Row, mms []prometheus.Metadata, extraLabels []prompb.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
 	tssDst := ctx.WriteRequest.Timeseries[:0]
+	mmsDst := ctx.WriteRequest.Metadata[:0]
 	labels := ctx.Labels[:0]
 	samples := ctx.Samples[:0]
 	for i := range rows {
@@ -70,15 +75,35 @@ func insertRows(at *auth.Token, rows []prometheus.Row, extraLabels []prompb.Labe
 			Samples: samples[len(samples)-1:],
 		})
 	}
+	var accountID, projectID uint32
+	if at != nil {
+		accountID = at.AccountID
+		projectID = at.ProjectID
+	}
+	for i := range mms {
+		mm := &mms[i]
+		mmsDst = append(mmsDst, prompb.MetricMetadata{
+			MetricFamilyName: mm.Metric,
+			Help:             mm.Help,
+			Type:             mm.Type,
+			// there is no unit in Prometheus exposition formats
+
+			AccountID: accountID,
+			ProjectID: projectID,
+		})
+	}
 	ctx.WriteRequest.Timeseries = tssDst
+	ctx.WriteRequest.Metadata = mmsDst
 	ctx.Labels = labels
 	ctx.Samples = samples
 	if !remotewrite.TryPush(at, &ctx.WriteRequest) {
 		return remotewrite.ErrQueueFullHTTPRetry
 	}
 	rowsInserted.Add(len(rows))
+	metadataInserted.Add(len(mms))
 	if at != nil {
 		rowsTenantInserted.Get(at).Add(len(rows))
+		metadataTenantInserted.Get(at).Add(len(mms))
 	}
 	rowsPerInsert.Update(float64(len(rows)))
 	return nil

app/vmagent/promremotewrite/request_handler.go

@@ -7,6 +7,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmagent/remotewrite"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/promremotewrite/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/tenantmetrics"
@@ -14,9 +15,11 @@ import (
 )
 
 var (
-	rowsInserted       = metrics.NewCounter(`vmagent_rows_inserted_total{type="promremotewrite"}`)
-	rowsTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="promremotewrite"}`)
-	rowsPerInsert      = metrics.NewHistogram(`vmagent_rows_per_insert{type="promremotewrite"}`)
+	rowsInserted           = metrics.NewCounter(`vmagent_rows_inserted_total{type="promremotewrite"}`)
+	metadataInserted       = metrics.NewCounter(`vmagent_metadata_inserted_total{type="promremotewrite"}`)
+	rowsTenantInserted     = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_rows_total{type="promremotewrite"}`)
+	metadataTenantInserted = tenantmetrics.NewCounterMap(`vmagent_tenant_inserted_metadata_total{type="promremotewrite"}`)
+	rowsPerInsert          = metrics.NewHistogram(`vmagent_rows_per_insert{type="promremotewrite"}`)
 )
 
 // InsertHandler processes remote write for prometheus.
@@ -26,17 +29,18 @@ func InsertHandler(at *auth.Token, req *http.Request) error {
 		return err
 	}
 	isVMRemoteWrite := req.Header.Get("Content-Encoding") == "zstd"
-	return stream.Parse(req.Body, isVMRemoteWrite, func(tss []prompb.TimeSeries) error {
-		return insertRows(at, tss, extraLabels)
+	return stream.Parse(req.Body, isVMRemoteWrite, func(tss []prompb.TimeSeries, mms []prompb.MetricMetadata) error {
+		return insertRows(at, tss, mms, extraLabels)
 	})
 }
 
-func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, extraLabels []prompb.Label) error {
+func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, mms []prompb.MetricMetadata, extraLabels []prompb.Label) error {
 	ctx := common.GetPushCtx()
 	defer common.PutPushCtx(ctx)
 
 	rowsTotal := 0
 	tssDst := ctx.WriteRequest.Timeseries[:0]
+	mmsDst := ctx.WriteRequest.Metadata[:0]
 	labels := ctx.Labels[:0]
 	samples := ctx.Samples[:0]
 	for i := range timeseries {
@@ -65,6 +69,30 @@ func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, extraLabels []pr
 		})
 	}
 	ctx.WriteRequest.Timeseries = tssDst
+
+	var metadataTotal int
+	if promscrape.IsMetadataEnabled() {
+		var accountID, projectID uint32
+		if at != nil {
+			accountID = at.AccountID
+			projectID = at.ProjectID
+		}
+		for i := range mms {
+			mm := &mms[i]
+			mmsDst = append(mmsDst, prompb.MetricMetadata{
+				MetricFamilyName: mm.MetricFamilyName,
+				Help:             mm.Help,
+				Type:             mm.Type,
+				Unit:             mm.Unit,
+
+				AccountID: accountID,
+				ProjectID: projectID,
+			})
+		}
+		ctx.WriteRequest.Metadata = mmsDst
+		metadataTotal = len(mms)
+	}
+
 	ctx.Labels = labels
 	ctx.Samples = samples
 	if !remotewrite.TryPush(at, &ctx.WriteRequest) {
@@ -73,7 +101,9 @@ func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, extraLabels []pr
 	rowsInserted.Add(rowsTotal)
 	if at != nil {
 		rowsTenantInserted.Get(at).Add(rowsTotal)
+		metadataTenantInserted.Get(at).Add(metadataTotal)
 	}
+	metadataInserted.Add(metadataTotal)
 	rowsPerInsert.Update(float64(rowsTotal))
 	return nil
 }

app/vmagent/remotewrite/pendingseries.go

@@ -24,9 +24,10 @@ import (
 
 var (
 	flushInterval = flag.Duration("remoteWrite.flushInterval", time.Second, "Interval for flushing the data to remote storage. "+
-		"This option takes effect only when less than 10K data points per second are pushed to -remoteWrite.url")
+		"This option takes effect only when less than -remoteWrite.maxRowsPerBlock data points per -remoteWrite.flushInterval are pushed to -remoteWrite.url")
 	maxUnpackedBlockSize = flagutil.NewBytes("remoteWrite.maxBlockSize", 8*1024*1024, "The maximum block size to send to remote storage. Bigger blocks may improve performance at the cost of the increased memory usage. See also -remoteWrite.maxRowsPerBlock")
 	maxRowsPerBlock      = flag.Int("remoteWrite.maxRowsPerBlock", 10000, "The maximum number of samples to send in each block to remote storage. Higher number may improve performance at the cost of the increased memory usage. See also -remoteWrite.maxBlockSize")
+	maxMetadataPerBlock  = flag.Int("remoteWrite.maxMetadataPerBlock", 5000, "The maximum number of metadata to send in each block to remote storage. Higher number may improve performance at the cost of the increased memory usage. See also -remoteWrite.maxBlockSize")
 	vmProtoCompressLevel = flag.Int("remoteWrite.vmProtoCompressLevel", 0, "The compression level for VictoriaMetrics remote write protocol. "+
 		"Higher values reduce network traffic at the cost of higher CPU usage. Negative values reduce CPU usage at the cost of increased network traffic. "+
 		"See https://docs.victoriametrics.com/victoriametrics/vmagent/#victoriametrics-remote-write-protocol")
@@ -60,9 +61,16 @@ func (ps *pendingSeries) MustStop() {
 	ps.periodicFlusherWG.Wait()
 }
 
-func (ps *pendingSeries) TryPush(tss []prompb.TimeSeries) bool {
+func (ps *pendingSeries) TryPushTimeSeries(tss []prompb.TimeSeries) bool {
 	ps.mu.Lock()
-	ok := ps.wr.tryPush(tss)
+	ok := ps.wr.tryPushTimeSeries(tss)
+	ps.mu.Unlock()
+	return ok
+}
+
+func (ps *pendingSeries) TryPushMetadata(mms []prompb.MetricMetadata) bool {
+	ps.mu.Lock()
+	ok := ps.wr.tryPushMetadata(mms)
 	ps.mu.Unlock()
 	return ok
 }
@@ -111,26 +119,34 @@ type writeRequest struct {
 	wr prompb.WriteRequest
 
 	tss     []prompb.TimeSeries
+	mms     []prompb.MetricMetadata
 	labels  []prompb.Label
 	samples []prompb.Sample
 
 	// buf holds labels data
 	buf []byte
+	// metadatabuf holds metadata data
+	metadatabuf []byte
 }
 
 func (wr *writeRequest) reset() {
 	// Do not reset lastFlushTime, fq, isVMRemoteWrite, significantFigures and roundDigits, since they are reused.
 
 	wr.wr.Timeseries = nil
+	wr.wr.Metadata = nil
 
 	clear(wr.tss)
 	wr.tss = wr.tss[:0]
 
+	clear(wr.mms)
+	wr.mms = wr.mms[:0]
+
 	promrelabel.CleanLabels(wr.labels)
 	wr.labels = wr.labels[:0]
 
 	wr.samples = wr.samples[:0]
 	wr.buf = wr.buf[:0]
+	wr.metadatabuf = wr.metadatabuf[:0]
 }
 
 // mustFlushOnStop force pushes wr data into wr.fq
@@ -138,6 +154,7 @@ func (wr *writeRequest) reset() {
 // This is needed in order to properly save in-memory data to persistent queue on graceful shutdown.
 func (wr *writeRequest) mustFlushOnStop() {
 	wr.wr.Timeseries = wr.tss
+	wr.wr.Metadata = wr.mms
 	if !tryPushWriteRequest(&wr.wr, wr.mustWriteBlock, wr.isVMRemoteWrite.Load()) {
 		logger.Panicf("BUG: final flush must always return true")
 	}
@@ -151,6 +168,7 @@ func (wr *writeRequest) mustWriteBlock(block []byte) bool {
 
 func (wr *writeRequest) tryFlush() bool {
 	wr.wr.Timeseries = wr.tss
+	wr.wr.Metadata = wr.mms
 	wr.lastFlushTime.Store(fasttime.UnixTimestamp())
 	if !tryPushWriteRequest(&wr.wr, wr.fq.TryWriteBlock, wr.isVMRemoteWrite.Load()) {
 		return false
@@ -174,7 +192,49 @@ func adjustSampleValues(samples []prompb.Sample, significantFigures, roundDigits
 	}
 }
 
-func (wr *writeRequest) tryPush(src []prompb.TimeSeries) bool {
+func (wr *writeRequest) tryPushMetadata(mms []prompb.MetricMetadata) bool {
+	mmdDst := wr.mms
+	maxMetadataPerBlock := *maxMetadataPerBlock
+	for i := range mms {
+		if len(wr.mms) >= maxMetadataPerBlock {
+			if !wr.tryFlush() {
+				return false
+			}
+			mmdDst = wr.mms
+		}
+		mmSrc := &mms[i]
+		mmdDst = append(mmdDst, prompb.MetricMetadata{})
+		wr.copyMetadata(&mmdDst[len(mmdDst)-1], mmSrc)
+	}
+	wr.mms = mmdDst
+	return true
+}
+
+func (wr *writeRequest) copyMetadata(dst, src *prompb.MetricMetadata) {
+	// Direct copy for non-string fields, which are safe by value.
+	dst.Type = src.Type
+	dst.Unit = src.Unit
+
+	// Pre-allocate memory for all string fields.
+	neededBufLen := len(src.MetricFamilyName) + len(src.Help)
+	bufLen := len(wr.metadatabuf)
+	wr.metadatabuf = slicesutil.SetLength(wr.metadatabuf, bufLen+neededBufLen)
+	buf := wr.metadatabuf[:bufLen]
+
+	// Copy MetricFamilyName
+	bufLen = len(buf)
+	buf = append(buf, src.MetricFamilyName...)
+	dst.MetricFamilyName = bytesutil.ToUnsafeString(buf[bufLen:])
+
+	// Copy Help
+	bufLen = len(buf)
+	buf = append(buf, src.Help...)
+	dst.Help = bytesutil.ToUnsafeString(buf[bufLen:])
+
+	wr.metadatabuf = buf
+}
+
+func (wr *writeRequest) tryPushTimeSeries(src []prompb.TimeSeries) bool {
 	tssDst := wr.tss
 	maxSamplesPerBlock := *maxRowsPerBlock
 	// Allow up to 10x of labels per each block on average.
@@ -241,7 +301,7 @@ func (wr *writeRequest) copyTimeSeries(dst, src *prompb.TimeSeries) {
 var marshalConcurrencyCh = make(chan struct{}, cgroup.AvailableCPUs())
 
 func tryPushWriteRequest(wr *prompb.WriteRequest, tryPushBlock func(block []byte) bool, isVMRemoteWrite bool) bool {
-	if len(wr.Timeseries) == 0 {
+	if wr.IsEmpty() {
 		// Nothing to push
 		return true
 	}
@@ -267,6 +327,7 @@ func tryPushWriteRequest(wr *prompb.WriteRequest, tryPushBlock func(block []byte
 			compressBufPool.Put(zb)
 			if ok {
 				blockSizeRows.Update(float64(len(wr.Timeseries)))
+				blockMetadataRows.Update(float64(len(wr.Metadata)))
 				blockSizeBytes.Update(float64(zbLen))
 			}
 			return ok
@@ -278,47 +339,86 @@ func tryPushWriteRequest(wr *prompb.WriteRequest, tryPushBlock func(block []byte
 		<-marshalConcurrencyCh
 	}
 
-	// Too big block. Recursively split it into smaller parts if possible.
-	if len(wr.Timeseries) == 1 {
-		// A single time series left. Recursively split its samples into smaller parts if possible.
+	// Split timeseries or metadata into two smaller blocks
+	switch len(wr.Timeseries) {
+	case 0:
+		if len(wr.Metadata) == 1 {
+			logger.Warnf("dropping a metadata exceeding -remoteWrite.maxBlockSize=%d bytes", maxUnpackedBlockSize.N)
+			return true
+		}
+		metadata := wr.Metadata
+		n := len(metadata) / 2
+		wr.Metadata = metadata[:n]
+		if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
+			wr.Metadata = metadata
+			return false
+		}
+		wr.Metadata = metadata[n:]
+		if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
+			wr.Metadata = metadata
+			return false
+		}
+		wr.Metadata = metadata
+		return true
+
+	case 1:
+		// A single time series left. Recursively split its samples and metadata into smaller parts if possible.
 		samples := wr.Timeseries[0].Samples
-		if len(samples) == 1 {
-			logger.Warnf("dropping a sample for metric with too long labels exceeding -remoteWrite.maxBlockSize=%d bytes", maxUnpackedBlockSize.N)
+		metaData := wr.Metadata
+		if len(samples) == 1 && len(metaData) <= 1 {
+			logger.Warnf("dropping a sample for metric and %d metadata which are exceeding -remoteWrite.maxBlockSize=%d bytes", len(metaData), maxUnpackedBlockSize.N)
 			return true
 		}
 		n := len(samples) / 2
+		m := len(metaData) / 2
 		wr.Timeseries[0].Samples = samples[:n]
+		wr.Metadata = metaData[:m]
 		if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
 			wr.Timeseries[0].Samples = samples
+			wr.Metadata = metaData
 			return false
 		}
 		wr.Timeseries[0].Samples = samples[n:]
+		wr.Metadata = metaData[m:]
 		if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
 			wr.Timeseries[0].Samples = samples
+			wr.Metadata = metaData
 			return false
 		}
 		wr.Timeseries[0].Samples = samples
+		wr.Metadata = metaData
+		return true
+
+	default:
+		// Split both timeseries and metadata.
+		timeseries := wr.Timeseries
+		metaData := wr.Metadata
+		n := len(timeseries) / 2
+		m := len(metaData) / 2
+		wr.Timeseries = timeseries[:n]
+		wr.Metadata = metaData[:m]
+		if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
+			wr.Timeseries = timeseries
+			wr.Metadata = metaData
+			return false
+		}
+		wr.Timeseries = timeseries[n:]
+		wr.Metadata = metaData[m:]
+		if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
+			wr.Timeseries = timeseries
+			wr.Metadata = metaData
+			return false
+		}
+		wr.Timeseries = timeseries
+		wr.Metadata = metaData
 		return true
 	}
-	timeseries := wr.Timeseries
-	n := len(timeseries) / 2
-	wr.Timeseries = timeseries[:n]
-	if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
-		wr.Timeseries = timeseries
-		return false
-	}
-	wr.Timeseries = timeseries[n:]
-	if !tryPushWriteRequest(wr, tryPushBlock, isVMRemoteWrite) {
-		wr.Timeseries = timeseries
-		return false
-	}
-	wr.Timeseries = timeseries
-	return true
 }
 
 var (
-	blockSizeBytes = metrics.NewHistogram(`vmagent_remotewrite_block_size_bytes`)
-	blockSizeRows  = metrics.NewHistogram(`vmagent_remotewrite_block_size_rows`)
+	blockSizeBytes    = metrics.NewHistogram(`vmagent_remotewrite_block_size_bytes`)
+	blockSizeRows     = metrics.NewHistogram(`vmagent_remotewrite_block_size_rows`)
+	blockMetadataRows = metrics.NewHistogram(`vmagent_remotewrite_block_metadata_rows`)
 )
 
 var (

app/vmagent/remotewrite/remotewrite.go

@@ -209,7 +209,7 @@ func Init() {
 	// In this case it is impossible to prevent from sending many duplicates of samples passed to TryPush() to all the configured -remoteWrite.url
 	// if these samples couldn't be sent to the -remoteWrite.url with the disabled persistent queue. So it is better sending samples
 	// to the remaining -remoteWrite.url and dropping them on the blocked queue.
-	dropSamplesOnFailureGlobal = *dropSamplesOnOverload || disableOnDiskQueueAny && len(disableOnDiskQueues) > 1
+	dropSamplesOnFailureGlobal = *dropSamplesOnOverload || disableOnDiskQueueAny && len(*remoteWriteURLs) > 1
 
 	dropDanglingQueues()
 
@@ -388,13 +388,7 @@ func TryPush(at *auth.Token, wr *prompb.WriteRequest) bool {
 
 func tryPush(at *auth.Token, wr *prompb.WriteRequest, forceDropSamplesOnFailure bool) bool {
 	tss := wr.Timeseries
-
-	var tenantRctx *relabelCtx
-	if at != nil {
-		// Convert at to (vm_account_id, vm_project_id) labels.
-		tenantRctx = getRelabelCtx()
-		defer putRelabelCtx(tenantRctx)
-	}
+	mms := wr.Metadata
 
 	// Quick check whether writes to configured remote storage systems are blocked.
 	// This allows saving CPU time spent on relabeling and block compression
@@ -411,6 +405,23 @@ func tryPush(at *auth.Token, wr *prompb.WriteRequest, forceDropSamplesOnFailure
 		return true
 	}
 
+	// Push metadata separately from time series, since it doesn't need sharding,
+	// relabeling, stream aggregation, deduplication, etc.
+	if !tryPushMetadataToRemoteStorages(rwctxs, mms, forceDropSamplesOnFailure) {
+		return false
+	}
+
+	if len(tss) == 0 {
+		return true
+	}
+
+	var tenantRctx *relabelCtx
+	if at != nil {
+		// Convert at to (vm_account_id, vm_project_id) labels.
+		tenantRctx = getRelabelCtx()
+		defer putRelabelCtx(tenantRctx)
+	}
+
 	var rctx *relabelCtx
 	rcs := allRelabelConfigs.Load()
 	pcsGlobal := rcs.global
@@ -481,7 +492,7 @@ func tryPush(at *auth.Token, wr *prompb.WriteRequest, forceDropSamplesOnFailure
 			deduplicatorGlobal.Push(tssBlock)
 			tssBlock = tssBlock[:0]
 		}
-		if !tryPushBlockToRemoteStorages(rwctxs, tssBlock, forceDropSamplesOnFailure) {
+		if !tryPushTimeSeriesToRemoteStorages(rwctxs, tssBlock, forceDropSamplesOnFailure) {
 			return false
 		}
 	}
@@ -520,18 +531,49 @@ func getEligibleRemoteWriteCtxs(tss []prompb.TimeSeries, forceDropSamplesOnFailu
 	return rwctxs, true
 }
 
-func pushToRemoteStoragesTrackDropped(tss []prompb.TimeSeries) {
+func pushTimeSeriesToRemoteStoragesTrackDropped(tss []prompb.TimeSeries) {
 	rwctxs, _ := getEligibleRemoteWriteCtxs(tss, true)
 	if len(rwctxs) == 0 {
 		return
 	}
 
-	if !tryPushBlockToRemoteStorages(rwctxs, tss, true) {
-		logger.Panicf("BUG: tryPushBlockToRemoteStorages() must return true when forceDropSamplesOnFailure=true")
+	if !tryPushTimeSeriesToRemoteStorages(rwctxs, tss, true) {
+		logger.Panicf("BUG: tryPushTimeSeriesToRemoteStorages() must return true when forceDropSamplesOnFailure=true")
 	}
 }
 
-func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompb.TimeSeries, forceDropSamplesOnFailure bool) bool {
+func tryPushMetadataToRemoteStorages(rwctxs []*remoteWriteCtx, mms []prompb.MetricMetadata, forceDropSamplesOnFailure bool) bool {
+	if len(mms) == 0 {
+		// Nothing to push
+		return true
+	}
+	// Do not shard metadata even if -remoteWrite.shardByURL is set, just replicate it among rwctxs.
+	// Since metadata is usually small and there is no guarantee that metadata can be sent to
+	// the same remote storage with the corresponding metrics.
+	//
+	// Push metadata to remote storage systems in parallel to reduce
+	// the time needed for sending the data to multiple remote storage systems.
+	var wg sync.WaitGroup
+	wg.Add(len(rwctxs))
+	var anyPushFailed atomic.Bool
+	for _, rwctx := range rwctxs {
+		go func(rwctx *remoteWriteCtx) {
+			defer wg.Done()
+			if !rwctx.tryPushMetadataInternal(mms) {
+				rwctx.pushFailures.Inc()
+				if forceDropSamplesOnFailure {
+					rwctx.metadataDroppedOnPushFailure.Add(len(mms))
+					return
+				}
+				anyPushFailed.Store(true)
+			}
+		}(rwctx)
+	}
+	wg.Wait()
+	return !anyPushFailed.Load()
+}
+
+func tryPushTimeSeriesToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompb.TimeSeries, forceDropSamplesOnFailure bool) bool {
 	if len(tssBlock) == 0 {
 		// Nothing to push
 		return true
@@ -539,7 +581,7 @@ func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompb.Ti
 
 	if len(rwctxs) == 1 {
 		// Fast path - just push data to the configured single remote storage
-		return rwctxs[0].TryPush(tssBlock, forceDropSamplesOnFailure)
+		return rwctxs[0].TryPushTimeSeries(tssBlock, forceDropSamplesOnFailure)
 	}
 
 	// We need to push tssBlock to multiple remote storages.
@@ -550,11 +592,11 @@ func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompb.Ti
 		if replicas <= 0 {
 			replicas = 1
 		}
-		return tryShardingBlockAmongRemoteStorages(rwctxs, tssBlock, replicas, forceDropSamplesOnFailure)
+		return tryShardingTimeSeriesAmongRemoteStorages(rwctxs, tssBlock, replicas, forceDropSamplesOnFailure)
 	}
 
 	// Replicate tssBlock samples among rwctxs.
-	// Push tssBlock to remote storage systems in parallel in order to reduce
+	// Push tssBlock to remote storage systems in parallel to reduce
 	// the time needed for sending the data to multiple remote storage systems.
 	var wg sync.WaitGroup
 	wg.Add(len(rwctxs))
@@ -562,7 +604,7 @@ func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompb.Ti
 	for _, rwctx := range rwctxs {
 		go func(rwctx *remoteWriteCtx) {
 			defer wg.Done()
-			if !rwctx.TryPush(tssBlock, forceDropSamplesOnFailure) {
+			if !rwctx.TryPushTimeSeries(tssBlock, forceDropSamplesOnFailure) {
 				anyPushFailed.Store(true)
 			}
 		}(rwctx)
@@ -571,7 +613,7 @@ func tryPushBlockToRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompb.Ti
 	return !anyPushFailed.Load()
 }
 
-func tryShardingBlockAmongRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompb.TimeSeries, replicas int, forceDropSamplesOnFailure bool) bool {
+func tryShardingTimeSeriesAmongRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []prompb.TimeSeries, replicas int, forceDropSamplesOnFailure bool) bool {
 	x := getTSSShards(len(rwctxs))
 	defer putTSSShards(x)
 
@@ -590,7 +632,7 @@ func tryShardingBlockAmongRemoteStorages(rwctxs []*remoteWriteCtx, tssBlock []pr
 		wg.Add(1)
 		go func(rwctx *remoteWriteCtx, tss []prompb.TimeSeries) {
 			defer wg.Done()
-			if !rwctx.TryPush(tss, forceDropSamplesOnFailure) {
+			if !rwctx.TryPushTimeSeries(tss, forceDropSamplesOnFailure) {
 				anyPushFailed.Store(true)
 			}
 		}(rwctx, shard)
@@ -797,8 +839,9 @@ type remoteWriteCtx struct {
 	rowsPushedAfterRelabel *metrics.Counter
 	rowsDroppedByRelabel   *metrics.Counter
 
-	pushFailures             *metrics.Counter
-	rowsDroppedOnPushFailure *metrics.Counter
+	pushFailures                 *metrics.Counter
+	metadataDroppedOnPushFailure *metrics.Counter
+	rowsDroppedOnPushFailure     *metrics.Counter
 }
 
 func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks int, sanitizedURL string) *remoteWriteCtx {
@@ -862,8 +905,9 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, maxInmemoryBlocks in
 		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)),
 
-		pushFailures:             metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_push_failures_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
-		rowsDroppedOnPushFailure: metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_samples_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)),
+		rowsDroppedOnPushFailure:     metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_samples_dropped_total{path=%q,url=%q}`, queuePath, sanitizedURL)),
 	}
 	rwctx.initStreamAggrConfig()
 
@@ -897,10 +941,10 @@ func (rwctx *remoteWriteCtx) MustStop() {
 	rwctx.rowsDroppedByRelabel = nil
 }
 
-// TryPush sends tss series to the configured remote write endpoint
+// TryPushTimeSeries sends tss series to the configured remote write endpoint
 //
-// TryPush doesn't modify tss, so tss can be passed concurrently to TryPush across distinct rwctx instances.
-func (rwctx *remoteWriteCtx) TryPush(tss []prompb.TimeSeries, forceDropSamplesOnFailure bool) bool {
+// TryPushTimeSeries doesn't modify tss, so tss can be passed concurrently to TryPush across distinct rwctx instances.
+func (rwctx *remoteWriteCtx) TryPushTimeSeries(tss []prompb.TimeSeries, forceDropSamplesOnFailure bool) bool {
 	var rctx *relabelCtx
 	var v *[]prompb.TimeSeries
 	defer func() {
@@ -953,7 +997,7 @@ func (rwctx *remoteWriteCtx) TryPush(tss []prompb.TimeSeries, forceDropSamplesOn
 	}
 
 	// Try pushing tss to remote storage
-	if rwctx.tryPushInternal(tss) {
+	if rwctx.tryPushTimeSeriesInternal(tss) {
 		return true
 	}
 
@@ -985,7 +1029,7 @@ func dropAggregatedSeries(src []prompb.TimeSeries, matchIdxs []byte, dropInput b
 }
 
 func (rwctx *remoteWriteCtx) pushInternalTrackDropped(tss []prompb.TimeSeries) {
-	if rwctx.tryPushInternal(tss) {
+	if rwctx.tryPushTimeSeriesInternal(tss) {
 		return
 	}
 	if !rwctx.fq.IsPersistentQueueDisabled() {
@@ -996,7 +1040,14 @@ func (rwctx *remoteWriteCtx) pushInternalTrackDropped(tss []prompb.TimeSeries) {
 	rwctx.rowsDroppedOnPushFailure.Add(rowsCount)
 }
 
-func (rwctx *remoteWriteCtx) tryPushInternal(tss []prompb.TimeSeries) bool {
+func (rwctx *remoteWriteCtx) tryPushMetadataInternal(mms []prompb.MetricMetadata) bool {
+	pss := rwctx.pss
+	idx := rwctx.pssNextIdx.Add(1) % uint64(len(pss))
+
+	return pss[idx].TryPushMetadata(mms)
+}
+
+func (rwctx *remoteWriteCtx) tryPushTimeSeriesInternal(tss []prompb.TimeSeries) bool {
 	var rctx *relabelCtx
 	var v *[]prompb.TimeSeries
 	defer func() {
@@ -1020,7 +1071,7 @@ func (rwctx *remoteWriteCtx) tryPushInternal(tss []prompb.TimeSeries) bool {
 	pss := rwctx.pss
 	idx := rwctx.pssNextIdx.Add(1) % uint64(len(pss))
 
-	return pss[idx].TryPush(tss)
+	return pss[idx].TryPushTimeSeries(tss)
 }
 
 var tssPool = &sync.Pool{

app/vmagent/remotewrite/remotewrite_test.go

@@ -106,7 +106,7 @@ func TestRemoteWriteContext_TryPush_ImmutableTimeseries(t *testing.T) {
 
 		// copy inputTss to make sure it is not mutated during TryPush call
 		copy(expectedTss, inputTss)
-		if !rwctx.TryPush(inputTss, false) {
+		if !rwctx.TryPushTimeSeries(inputTss, false) {
 			t.Fatalf("cannot push samples to rwctx")
 		}
 

app/vmagent/remotewrite/streamaggr.go

@@ -141,7 +141,7 @@ func initStreamAggrConfigGlobal() {
 	}
 	dedupInterval := *streamAggrGlobalDedupInterval
 	if dedupInterval > 0 {
-		deduplicatorGlobal = streamaggr.NewDeduplicator(pushToRemoteStoragesTrackDropped, *streamAggrGlobalEnableWindows, dedupInterval, *streamAggrGlobalDropInputLabels, "dedup-global")
+		deduplicatorGlobal = streamaggr.NewDeduplicator(pushTimeSeriesToRemoteStoragesTrackDropped, *streamAggrGlobalEnableWindows, dedupInterval, *streamAggrGlobalDropInputLabels, "dedup-global")
 	}
 }
 
@@ -216,7 +216,7 @@ func newStreamAggrConfigGlobal() (*streamaggr.Aggregators, error) {
 		EnableWindows:        *streamAggrGlobalEnableWindows,
 	}
 
-	sas, err := streamaggr.LoadFromFile(path, pushToRemoteStoragesTrackDropped, opts, "global")
+	sas, err := streamaggr.LoadFromFile(path, pushTimeSeriesToRemoteStoragesTrackDropped, opts, "global")
 	if err != nil {
 		return nil, fmt.Errorf("cannot load -streamAggr.config=%q: %w", *streamAggrGlobalConfig, err)
 	}

app/vmalert-tool/unittest/testdata/rules.yaml

@@ -15,6 +15,10 @@ groups:
       - alert: SameAlertNameWithDifferentGroup
         expr: absent(test)
         for: 1m
+      - alert: AlertWithTemplate
+        expr: test
+        annotations:
+          queryAnno: '{{ query "foo" | first | value }}'
 
   - name: group2
     rules:

app/vmalert-tool/unittest/testdata/test1.yaml

@@ -10,7 +10,9 @@ tests:
     input_series:
       - series: "test"
         values: "_x5 1x5 _ stale"
-
+      - series: "foo"
+        values: "1x20"
+  
     alert_rule_test:
       - eval_time: 1m
         groupname: group1
@@ -32,6 +34,14 @@ tests:
         groupname: group1
         alertname: SameAlertNameWithDifferentGroup
         exp_alerts: []
+      - eval_time: 6m
+        groupname: group1
+        alertname: AlertWithTemplate
+        exp_alerts:
+          - exp_labels:
+              cluster: prod
+            exp_annotations:
+              queryAnno: '1'
 
     metricsql_expr_test:
       - expr: test
@@ -50,6 +60,8 @@ tests:
         values: "0+0x1440"
       - series: "test"
         values: "0+1x1440"
+      - series: "foo"
+        values: "1x20"
 
     metricsql_expr_test:
       - expr: count(ALERTS) by (alertgroup, alertname, alertstate)
@@ -59,6 +71,8 @@ tests:
             value: 1
           - labels: '{alertgroup="group1", alertname="InstanceDown", alertstate="pending"}'
             value: 1
+          - labels: '{alertgroup="group1", alertname="AlertWithTemplate", alertstate="firing"}'
+            value: 1
       - expr: t1
         eval_time: 4m
         exp_samples:

app/vmalert-tool/unittest/unittest.go

@@ -366,6 +366,7 @@ func (tg *testGroup) test(evalInterval time.Duration, groupOrderMap map[string]i
 			mergedExternalLabels[k] = v
 		}
 		ng := rule.NewGroup(group, q, time.Minute, mergedExternalLabels)
+		ng.Init()
 		groups = append(groups, ng)
 	}
 

app/vmalert/config/config.go

@@ -295,10 +295,7 @@ func parse(files map[string][]byte, validateTplFn ValidateTplFn, validateExpress
 }
 
 func parseConfig(data []byte) ([]Group, error) {
-	data, err := envtemplate.ReplaceBytes(data)
-	if err != nil {
-		return nil, fmt.Errorf("cannot expand environment vars: %w", err)
-	}
+	data = envtemplate.ReplaceBytes(data)
 
 	var result []Group
 	type cfgFile struct {
@@ -310,13 +307,13 @@ func parseConfig(data []byte) ([]Group, error) {
 	decoder := yaml.NewDecoder(bytes.NewReader(data))
 	for {
 		var cf cfgFile
-		if err = decoder.Decode(&cf); err != nil {
+		if err := decoder.Decode(&cf); err != nil {
 			if err == io.EOF { // EOF indicates no more documents to read
 				break
 			}
 			return nil, err
 		}
-		if err = checkOverflow(cf.XXX, "config"); err != nil {
+		if err := checkOverflow(cf.XXX, "config"); err != nil {
 			return nil, err
 		}
 		result = append(result, cf.Groups...)

app/vmalert/remotewrite/client_test.go

@@ -182,7 +182,7 @@ func (rw *rwServer) handler(w http.ResponseWriter, r *http.Request) {
 		rw.err(w, fmt.Errorf("decode err: %w", err))
 		return
 	}
-	wru := &prompb.WriteRequestUnmarshaller{}
+	wru := &prompb.WriteRequestUnmarshaler{}
 	wr, err := wru.UnmarshalProtobuf(b)
 	if err != nil {
 		rw.err(w, fmt.Errorf("unmarhsal err: %w", err))

app/vmalert/replay.go

@@ -28,8 +28,8 @@ var (
 		"Defines how many retries to make before giving up on rule if request for it returns an error.")
 	disableProgressBar = flag.Bool("replay.disableProgressBar", false, "Whether to disable rendering progress bars during the replay. "+
 		"Progress bar rendering might be verbose or break the logs parsing, so it is recommended to be disabled when not used in interactive mode.")
-	ruleEvaluationConcurrency = flag.Int("replay.ruleEvaluationConcurrency", 1, "The maximum number of concurrent `/query_range` requests for a single rule. "+
-		"Increasing this value when replaying for a long time and a single request range is limited by `-replay.maxDatapointsPerQuery`.")
+	ruleEvaluationConcurrency = flag.Int("replay.ruleEvaluationConcurrency", 1, "The maximum number of concurrent '/query_range' requests when replay recording rule or alerting rule with for=0. "+
+		"Increasing this value when replaying for a long time, since each request is limited by -replay.maxDatapointsPerQuery.")
 )
 
 func replay(groupsCfg []config.Group, qb datasource.QuerierBuilder, rw remotewrite.RWClient) (totalRows, droppedRows int, err error) {

app/vmalert/replay_test.go

@@ -246,24 +246,33 @@ func TestReplay(t *testing.T) {
 
 	// multiple rules + rule concurrency + group concurrency
 	f("2021-01-01T12:00:00.000Z", "2021-01-01T12:02:30.000Z", 1, 3, 0, []config.Group{
-		{Rules: []config.Rule{{Alert: "foo-group-single-concurrent", Expr: "sum(up) > 1"}, {Alert: "bar-group-single-concurrent", Expr: "max(up) < 1"}}, Concurrency: 2}}, &fakeReplayQuerier{
+		{Rules: []config.Rule{{Alert: "foo-group-single-concurrent", For: promutil.NewDuration(30 * time.Second), Expr: "sum(up) > 1"}, {Alert: "bar-group-single-concurrent", Expr: "max(up) < 1"}}, Concurrency: 2}}, &fakeReplayQuerier{
 		registry: map[string]map[string][]datasource.Metric{
 			"sum(up) > 1": {
-				"12:00:00+12:01:00": {},
-				"12:01:00+12:02:00": {{
-					Timestamps: []int64{1},
+				"12:00:00+12:01:00": {{
+					Timestamps: []int64{1609502460},
+					Values:     []float64{1},
+				}},
+				"12:01:00+12:02:00": {{
+					Timestamps: []int64{1609502520},
+					Values:     []float64{1},
+				}},
+				"12:02:00+12:02:30": {{
+					Timestamps: []int64{1609502580},
 					Values:     []float64{1},
 				}},
-				"12:02:00+12:02:30": {},
 			},
 			"max(up) < 1": {
-				"12:00:00+12:01:00": {},
+				"12:00:00+12:01:00": {{
+					Timestamps: []int64{1609502460},
+					Values:     []float64{1},
+				}},
 				"12:01:00+12:02:00": {{
-					Timestamps: []int64{1},
+					Timestamps: []int64{1609502520},
 					Values:     []float64{1},
 				}},
 				"12:02:00+12:02:30": {},
 			},
 		},
-	}, 4)
+	}, 10)
 }

app/vmalert/rule/alerting.go

@@ -341,11 +341,15 @@ func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]
 		return []datasource.Metric{{Timestamps: []int64{0}, Values: []float64{math.NaN()}}}, nil
 	}
 	for _, s := range res.Data {
-		ls, as, err := ar.expandTemplates(s, qFn, time.Time{})
+		ls, err := ar.expandLabelTemplates(s)
 		if err != nil {
-			return nil, fmt.Errorf("failed to expand templates: %s", err)
+			return nil, err
 		}
 		alertID := hash(ls.processed)
+		as, err := ar.expandAnnotationTemplates(s, qFn, time.Time{}, ls)
+		if err != nil {
+			return nil, err
+		}
 		a := ar.newAlert(s, time.Time{}, ls.processed, as) // initial alert
 
 		prevT := time.Time{}
@@ -363,7 +367,7 @@ func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]
 				a.State = notifier.StatePending
 				a.ActiveAt = at
 				// re-template the annotations as active timestamp is changed
-				_, a.Annotations, _ = ar.expandTemplates(s, qFn, at)
+				a.Annotations, _ = ar.expandAnnotationTemplates(s, qFn, at, ls)
 				a.Start = time.Time{}
 			} else if at.Sub(a.ActiveAt) >= ar.For && a.State != notifier.StateFiring {
 				a.State = notifier.StateFiring
@@ -376,13 +380,15 @@ func (ar *AlertingRule) execRange(ctx context.Context, start, end time.Time) ([]
 			}
 			result = append(result, ar.alertToTimeSeries(a, s.Timestamps[i])...)
 
-			// save alert's state on last iteration, so it can be used on the next execRange call
-			if at.Equal(end) {
+			// if for>0, save alert's state on last iteration, so it can be used on the next execRange call
+			if ar.For > 0 && at.Equal(end) {
 				holdAlertState[alertID] = a
 			}
 		}
 	}
-	ar.alerts = holdAlertState
+	if len(holdAlertState) > 0 {
+		ar.alerts = holdAlertState
+	}
 	return result, nil
 }
 
@@ -428,9 +434,22 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
 	expandedLabels := make([]*labelSet, len(res.Data))
 	expandedAnnotations := make([]map[string]string, len(res.Data))
 	for i, m := range res.Data {
-		ls, as, err := ar.expandTemplates(m, qFn, ts)
+		ls, err := ar.expandLabelTemplates(m)
 		if err != nil {
-			curState.Err = fmt.Errorf("failed to expand templates: %w", err)
+			curState.Err = err
+			return nil, curState.Err
+		}
+		at := ts
+		alertID := hash(ls.processed)
+		if a, ok := ar.alerts[alertID]; ok {
+			// modify activeAt for annotation templating if the alert has already triggered(in state Pending or Firing)
+			if a.State != notifier.StateInactive {
+				at = a.ActiveAt
+			}
+		}
+		as, err := ar.expandAnnotationTemplates(m, qFn, at, ls)
+		if err != nil {
+			curState.Err = err
 			return nil, curState.Err
 		}
 		expandedLabels[i] = ls
@@ -473,6 +492,7 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
 			a.KeepFiringSince = time.Time{}
 			continue
 		}
+
 		a := ar.newAlert(m, ts, labels.processed, annotations)
 		a.ID = alertID
 		a.State = notifier.StatePending
@@ -536,12 +556,18 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
 	return append(tss, ar.toTimeSeries(ts.Unix())...), nil
 }
 
-func (ar *AlertingRule) expandTemplates(m datasource.Metric, qFn templates.QueryFn, ts time.Time) (*labelSet, map[string]string, error) {
+func (ar *AlertingRule) expandLabelTemplates(m datasource.Metric) (*labelSet, error) {
+	qFn := func(_ string) ([]datasource.Metric, error) {
+		return nil, fmt.Errorf("`query` template isn't supported in rule label")
+	}
 	ls, err := ar.toLabels(m, qFn)
 	if err != nil {
-		return nil, nil, fmt.Errorf("failed to expand labels: %w", err)
+		return nil, fmt.Errorf("failed to expand label templates: %s", err)
 	}
+	return ls, nil
+}
 
+func (ar *AlertingRule) expandAnnotationTemplates(m datasource.Metric, qFn templates.QueryFn, activeAt time.Time, ls *labelSet) (map[string]string, error) {
 	tplData := notifier.AlertTplData{
 		Value:    m.Values[0],
 		Type:     ar.Type.String(),
@@ -549,14 +575,14 @@ func (ar *AlertingRule) expandTemplates(m datasource.Metric, qFn templates.Query
 		Expr:     ar.Expr,
 		AlertID:  hash(ls.processed),
 		GroupID:  ar.GroupID,
-		ActiveAt: ts,
+		ActiveAt: activeAt,
 		For:      ar.For,
 	}
 	as, err := notifier.ExecTemplate(qFn, ar.Annotations, tplData)
 	if err != nil {
-		return nil, nil, fmt.Errorf("failed to template annotations: %w", err)
+		return nil, fmt.Errorf("failed to expand annotation templates: %s", err)
 	}
-	return ls, as, nil
+	return as, nil
 }
 
 // toTimeSeries creates `ALERTS` and `ALERTS_FOR_STATE` for active alerts

app/vmalert/rule/alerting_test.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"reflect"
 	"sort"
+	"strconv"
 	"strings"
 	"sync"
 	"testing"
@@ -267,8 +268,15 @@ func TestAlertingRule_Exec(t *testing.T) {
 				if got.State != exp.State {
 					t.Fatalf("evalIndex %d: expected state %d; got %d", i, exp.State, got.State)
 				}
+				if rule.Annotations != nil && exp.Annotations != nil {
+					if !reflect.DeepEqual(got.Annotations, exp.Annotations) {
+						t.Fatalf("evalIndex %d: expected annotations %v; got %v", i, exp.Annotations, got.Annotations)
+					}
+				}
 			}
 		}
+		// reset ts for next test
+		ts, _ = time.Parse(time.RFC3339, "2024-10-29T00:00:00Z")
 	}
 
 	f(newTestAlertingRule("empty", 0), [][]datasource.Metric{}, nil, nil)
@@ -522,7 +530,7 @@ func TestAlertingRule_Exec(t *testing.T) {
 		},
 	})
 
-	f(newTestAlertingRule("for-pending=>firing=>inactive=>pending=>firing", defaultStep), [][]datasource.Metric{
+	f(newTestAlertingRuleWithCustomFields("for-pending=>firing=>inactive=>pending=>firing", defaultStep, 0, 0, map[string]string{"activeAt": "{{ $activeAt.UnixMilli }}"}), [][]datasource.Metric{
 		{metricWithLabels(t, "name", "foo")},
 		{metricWithLabels(t, "name", "foo")},
 		// empty step to set alert inactive
@@ -530,11 +538,11 @@ func TestAlertingRule_Exec(t *testing.T) {
 		{metricWithLabels(t, "name", "foo")},
 		{metricWithLabels(t, "name", "foo")},
 	}, map[int][]testAlert{
-		0: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}}},
-		1: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
-		2: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive}}},
-		3: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending}}},
-		4: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring}}},
+		0: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending, Annotations: map[string]string{"activeAt": strconv.FormatInt(ts.UnixMilli(), 10)}}}},
+		1: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring, Annotations: map[string]string{"activeAt": strconv.FormatInt(ts.UnixMilli(), 10)}}}},
+		2: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateInactive, Annotations: map[string]string{"activeAt": strconv.FormatInt(ts.UnixMilli(), 10)}}}},
+		3: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StatePending, Annotations: map[string]string{"activeAt": strconv.FormatInt(ts.Add(defaultStep*3).UnixMilli(), 10)}}}},
+		4: {{labels: []string{"name", "foo"}, alert: &notifier.Alert{State: notifier.StateFiring, Annotations: map[string]string{"activeAt": strconv.FormatInt(ts.Add(defaultStep*3).UnixMilli(), 10)}}}},
 	}, nil)
 
 	f(newTestAlertingRuleWithCustomFields("for-pending=>firing=>keepfiring=>firing", defaultStep, 0, defaultStep, nil), [][]datasource.Metric{

app/vmalert/rule/group.go

@@ -587,6 +587,11 @@ func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoi
 
 func replayRuleRange(r Rule, ri rangeIterator, bar *pb.ProgressBar, rw remotewrite.RWClient, replayRuleRetryAttempts, ruleEvaluationConcurrency int) int {
 	fmt.Printf("> Rule %q (ID: %d)\n", r, r.ID())
+	// alerting rule with for>0 can't be replayed concurrently, since the status change might depend on the previous evaluation
+	// see https://github.com/VictoriaMetrics/VictoriaMetrics/commit/abcb21aa5ee918ba9a4e9cde495dba06e1e9564c
+	if r, ok := r.(*AlertingRule); ok && r.For > 0 {
+		ruleEvaluationConcurrency = 1
+	}
 	sem := make(chan struct{}, ruleEvaluationConcurrency)
 	wg := sync.WaitGroup{}
 	res := make(chan int, int(ri.end.Sub(ri.start)/ri.step)+1)

app/vmalert/rule/recording_test.go

@@ -437,7 +437,7 @@ func TestRecordingRuleExec_Negative(t *testing.T) {
 
 	_, err = rr.exec(context.TODO(), time.Now(), 0)
 	if err != nil {
-		t.Fatalf("cannot execute recroding rule: %s", err)
+		t.Fatalf("cannot execute recording rule: %s", err)
 	}
 }
 

app/vmauth/auth_config.go

@@ -723,14 +723,11 @@ func reloadAuthConfigData(data []byte) (bool, error) {
 }
 
 func parseAuthConfig(data []byte) (*AuthConfig, error) {
-	data, err := envtemplate.ReplaceBytes(data)
-	if err != nil {
-		return nil, fmt.Errorf("cannot expand environment vars: %w", err)
-	}
+	data = envtemplate.ReplaceBytes(data)
 	ac := &AuthConfig{
 		ms: metrics.NewSet(),
 	}
-	if err = yaml.UnmarshalStrict(data, ac); err != nil {
+	if err := yaml.UnmarshalStrict(data, ac); err != nil {
 		return nil, fmt.Errorf("cannot unmarshal AuthConfig data: %w", err)
 	}
 

app/vmbackup/Makefile

@@ -1,106 +1,110 @@
 # All these commands must run from repository root.
 
+# special tag to reduce resulting binary size
+# See this issue https://github.com/VictoriaMetrics/VictoriaMetrics/issues/8008
+VMBACKUP_GO_BUILD_TAGS=disable_grpc_modules
+
 vmbackup:
-	APP_NAME=vmbackup $(MAKE) app-local
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-local
 
 vmbackup-race:
-	APP_NAME=vmbackup RACE=-race $(MAKE) app-local
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) RACE=-race $(MAKE) app-local
 
 vmbackup-prod:
-	APP_NAME=vmbackup $(MAKE) app-via-docker
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-via-docker
 
 vmbackup-pure-prod:
-	APP_NAME=vmbackup $(MAKE) app-via-docker-pure
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-via-docker-pure
 
 vmbackup-linux-amd64-prod:
-	APP_NAME=vmbackup $(MAKE) app-via-docker-linux-amd64
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-via-docker-linux-amd64
 
 vmbackup-linux-arm-prod:
-	APP_NAME=vmbackup $(MAKE) app-via-docker-linux-arm
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-via-docker-linux-arm
 
 vmbackup-linux-arm64-prod:
-	APP_NAME=vmbackup $(MAKE) app-via-docker-linux-arm64
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-via-docker-linux-arm64
 
 vmbackup-linux-ppc64le-prod:
-	APP_NAME=vmbackup $(MAKE) app-via-docker-linux-ppc64le
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-via-docker-linux-ppc64le
 
 vmbackup-linux-386-prod:
-	APP_NAME=vmbackup $(MAKE) app-via-docker-linux-386
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-via-docker-linux-386
 
 vmbackup-darwin-amd64-prod:
-	APP_NAME=vmbackup $(MAKE) app-via-docker-darwin-amd64
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-via-docker-darwin-amd64
 
 vmbackup-darwin-arm64-prod:
-	APP_NAME=vmbackup $(MAKE) app-via-docker-darwin-arm64
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-via-docker-darwin-arm64
 
 vmbackup-freebsd-amd64-prod:
-	APP_NAME=vmbackup $(MAKE) app-via-docker-freebsd-amd64
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-via-docker-freebsd-amd64
 
 vmbackup-openbsd-amd64-prod:
-	APP_NAME=vmbackup $(MAKE) app-via-docker-openbsd-amd64
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-via-docker-openbsd-amd64
 
 vmbackup-windows-amd64-prod:
-	APP_NAME=vmbackup $(MAKE) app-via-docker-windows-amd64
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-via-docker-windows-amd64
 
 package-vmbackup:
-	APP_NAME=vmbackup $(MAKE) package-via-docker
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) package-via-docker
 
 package-vmbackup-pure:
-	APP_NAME=vmbackup $(MAKE) package-via-docker-pure
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) package-via-docker-pure
 
 package-vmbackup-amd64:
-	APP_NAME=vmbackup $(MAKE) package-via-docker-amd64
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) package-via-docker-amd64
 
 package-vmbackup-arm:
-	APP_NAME=vmbackup $(MAKE) package-via-docker-arm
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) package-via-docker-arm
 
 package-vmbackup-arm64:
-	APP_NAME=vmbackup $(MAKE) package-via-docker-arm64
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) package-via-docker-arm64
 
 package-vmbackup-ppc64le:
-	APP_NAME=vmbackup $(MAKE) package-via-docker-ppc64le
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) package-via-docker-ppc64le
 
 package-vmbackup-386:
-	APP_NAME=vmbackup $(MAKE) package-via-docker-386
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) package-via-docker-386
 
 publish-vmbackup:
-	APP_NAME=vmbackup $(MAKE) publish-via-docker
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) publish-via-docker
 
 vmbackup-linux-amd64:
-	APP_NAME=vmbackup CGO_ENABLED=1 GOOS=linux GOARCH=amd64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) CGO_ENABLED=1 GOOS=linux GOARCH=amd64 $(MAKE) app-local-goos-goarch
 
 vmbackup-linux-arm:
-	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=linux GOARCH=arm $(MAKE) app-local-goos-goarch
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=linux GOARCH=arm $(MAKE) app-local-goos-goarch
 
 vmbackup-linux-arm64:
-	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=linux GOARCH=arm64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=linux GOARCH=arm64 $(MAKE) app-local-goos-goarch
 
 vmbackup-linux-ppc64le:
-	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le $(MAKE) app-local-goos-goarch
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le $(MAKE) app-local-goos-goarch
 
 vmbackup-linux-s390x:
-	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
 
 vmbackup-linux-loong64:
-	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=linux GOARCH=loong64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=linux GOARCH=loong64 $(MAKE) app-local-goos-goarch
 
 vmbackup-linux-386:
-	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=linux GOARCH=386 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=linux GOARCH=386 $(MAKE) app-local-goos-goarch
 
 vmbackup-darwin-amd64:
-	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=darwin GOARCH=amd64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=darwin GOARCH=amd64 $(MAKE) app-local-goos-goarch
 
 vmbackup-darwin-arm64:
-	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=darwin GOARCH=arm64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=darwin GOARCH=arm64 $(MAKE) app-local-goos-goarch
 
 vmbackup-freebsd-amd64:
-	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=freebsd GOARCH=amd64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=freebsd GOARCH=amd64 $(MAKE) app-local-goos-goarch
 
 vmbackup-openbsd-amd64:
-	APP_NAME=vmbackup CGO_ENABLED=0 GOOS=openbsd GOARCH=amd64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=openbsd GOARCH=amd64 $(MAKE) app-local-goos-goarch
 
 vmbackup-windows-amd64:
-	GOARCH=amd64 APP_NAME=vmbackup $(MAKE) app-local-windows-goarch
+	GOARCH=amd64 APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-local-windows-goarch
 
 vmbackup-pure:
-	APP_NAME=vmbackup $(MAKE) app-local-pure
+	APP_NAME=vmbackup EXTRA_GO_BUILD_TAGS=$(VMBACKUP_GO_BUILD_TAGS) $(MAKE) app-local-pure

app/vminsert/opentelemetry/request_handler.go

@@ -33,7 +33,7 @@ func InsertHandler(req *http.Request) error {
 			return fmt.Errorf("json encoding isn't supported for opentelemetry format. Use protobuf encoding")
 		}
 	}
-	return stream.ParseStream(req.Body, encoding, processBody, func(tss []prompb.TimeSeries) error {
+	return stream.ParseStream(req.Body, encoding, processBody, func(tss []prompb.TimeSeries, _ []prompb.MetricMetadata) error {
 		return insertRows(tss, extraLabels)
 	})
 }

app/vminsert/prometheusimport/request_handler.go

@@ -7,6 +7,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vminsert/relabel"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/prometheus/stream"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/protoparserutil"
@@ -29,7 +30,7 @@ func InsertHandler(req *http.Request) error {
 		return err
 	}
 	encoding := req.Header.Get("Content-Encoding")
-	return stream.Parse(req.Body, defaultTimestamp, encoding, true, func(rows []prometheus.Row) error {
+	return stream.Parse(req.Body, defaultTimestamp, encoding, true, promscrape.IsMetadataEnabled(), func(rows []prometheus.Row, _ []prometheus.Metadata) error {
 		return insertRows(rows, extraLabels)
 	}, func(s string) {
 		httpserver.LogError(req, s)

app/vminsert/promremotewrite/request_handler.go

@@ -23,7 +23,7 @@ func InsertHandler(req *http.Request) error {
 		return err
 	}
 	isVMRemoteWrite := req.Header.Get("Content-Encoding") == "zstd"
-	return stream.Parse(req.Body, isVMRemoteWrite, func(tss []prompb.TimeSeries) error {
+	return stream.Parse(req.Body, isVMRemoteWrite, func(tss []prompb.TimeSeries, _ []prompb.MetricMetadata) error {
 		return insertRows(tss, extraLabels)
 	})
 }

app/vmrestore/Makefile

@@ -1,106 +1,110 @@
 # All these commands must run from repository root.
 
+# special tag to reduce resulting binary size
+# See this issue https://github.com/VictoriaMetrics/VictoriaMetrics/issues/8008
+VMRESTORE_GO_BUILD_TAGS=disable_grpc_modules
+
 vmrestore:
-	APP_NAME=vmrestore $(MAKE) app-local
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-local
 
 vmrestore-race:
-	APP_NAME=vmrestore RACE=-race $(MAKE) app-local
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) RACE=-race $(MAKE) app-local
 
 vmrestore-prod:
-	APP_NAME=vmrestore $(MAKE) app-via-docker
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-via-docker
 
 vmrestore-pure-prod:
-	APP_NAME=vmrestore $(MAKE) app-via-docker-pure
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-via-docker-pure
 
 vmrestore-linux-amd64-prod:
-	APP_NAME=vmrestore $(MAKE) app-via-docker-linux-amd64
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-via-docker-linux-amd64
 
 vmrestore-linux-arm-prod:
-	APP_NAME=vmrestore $(MAKE) app-via-docker-linux-arm
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-via-docker-linux-arm
 
 vmrestore-linux-arm64-prod:
-	APP_NAME=vmrestore $(MAKE) app-via-docker-linux-arm64
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-via-docker-linux-arm64
 
 vmrestore-linux-ppc64le-prod:
-	APP_NAME=vmrestore $(MAKE) app-via-docker-linux-ppc64le
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-via-docker-linux-ppc64le
 
 vmrestore-linux-386-prod:
-	APP_NAME=vmrestore $(MAKE) app-via-docker-linux-386
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-via-docker-linux-386
 
 vmrestore-darwin-amd64-prod:
-	APP_NAME=vmrestore $(MAKE) app-via-docker-darwin-amd64
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-via-docker-darwin-amd64
 
 vmrestore-darwin-arm64-prod:
-	APP_NAME=vmrestore $(MAKE) app-via-docker-darwin-arm64
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-via-docker-darwin-arm64
 
 vmrestore-freebsd-amd64-prod:
-	APP_NAME=vmrestore $(MAKE) app-via-docker-freebsd-amd64
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-via-docker-freebsd-amd64
 
 vmrestore-openbsd-amd64-prod:
-	APP_NAME=vmrestore $(MAKE) app-via-docker-openbsd-amd64
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-via-docker-openbsd-amd64
 
 vmrestore-windows-amd64-prod:
-	APP_NAME=vmrestore $(MAKE) app-via-docker-windows-amd64
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-via-docker-windows-amd64
 
 package-vmrestore:
-	APP_NAME=vmrestore $(MAKE) package-via-docker
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) package-via-docker
 
 package-vmrestore-pure:
-	APP_NAME=vmrestore $(MAKE) package-via-docker-pure
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) package-via-docker-pure
 
 package-vmrestore-amd64:
-	APP_NAME=vmrestore $(MAKE) package-via-docker-amd64
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) package-via-docker-amd64
 
 package-vmrestore-arm:
-	APP_NAME=vmrestore $(MAKE) package-via-docker-arm
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) package-via-docker-arm
 
 package-vmrestore-arm64:
-	APP_NAME=vmrestore $(MAKE) package-via-docker-arm64
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) package-via-docker-arm64
 
 package-vmrestore-ppc64le:
-	APP_NAME=vmrestore $(MAKE) package-via-docker-ppc64le
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) package-via-docker-ppc64le
 
 package-vmrestore-386:
-	APP_NAME=vmrestore $(MAKE) package-via-docker-386
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) package-via-docker-386
 
 publish-vmrestore:
-	APP_NAME=vmrestore $(MAKE) publish-via-docker
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) publish-via-docker
 
 vmrestore-linux-amd64:
-	APP_NAME=vmrestore CGO_ENABLED=1 GOOS=linux GOARCH=amd64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) CGO_ENABLED=1 GOOS=linux GOARCH=amd64 $(MAKE) app-local-goos-goarch
 
 vmrestore-linux-arm:
-	APP_NAME=vmrestore CGO_ENABLED=0 GOOS=linux GOARCH=arm $(MAKE) app-local-goos-goarch
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=linux GOARCH=arm $(MAKE) app-local-goos-goarch
 
 vmrestore-linux-arm64:
-	APP_NAME=vmrestore CGO_ENABLED=0 GOOS=linux GOARCH=arm64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=linux GOARCH=arm64 $(MAKE) app-local-goos-goarch
 
 vmrestore-linux-ppc64le:
-	APP_NAME=vmrestore CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le $(MAKE) app-local-goos-goarch
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=linux GOARCH=ppc64le $(MAKE) app-local-goos-goarch
 
 vmrestore-linux-s390x:
-	APP_NAME=vmrestore CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=linux GOARCH=s390x $(MAKE) app-local-goos-goarch
 
 vmrestore-linux-loong64:
-	APP_NAME=vmrestore CGO_ENABLED=0 GOOS=linux GOARCH=loong64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=linux GOARCH=loong64 $(MAKE) app-local-goos-goarch
 
 vmrestore-linux-386:
-	APP_NAME=vmrestore CGO_ENABLED=0 GOOS=linux GOARCH=386 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=linux GOARCH=386 $(MAKE) app-local-goos-goarch
 
 vmrestore-darwin-amd64:
-	APP_NAME=vmrestore CGO_ENABLED=0 GOOS=darwin GOARCH=amd64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=darwin GOARCH=amd64 $(MAKE) app-local-goos-goarch
 
 vmrestore-darwin-arm64:
-	APP_NAME=vmrestore CGO_ENABLED=0 GOOS=darwin GOARCH=arm64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=darwin GOARCH=arm64 $(MAKE) app-local-goos-goarch
 
 vmrestore-freebsd-amd64:
-	APP_NAME=vmrestore CGO_ENABLED=0 GOOS=freebsd GOARCH=amd64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=freebsd GOARCH=amd64 $(MAKE) app-local-goos-goarch
 
 vmrestore-openbsd-amd64:
-	APP_NAME=vmrestore CGO_ENABLED=0 GOOS=openbsd GOARCH=amd64 $(MAKE) app-local-goos-goarch
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) CGO_ENABLED=0 GOOS=openbsd GOARCH=amd64 $(MAKE) app-local-goos-goarch
 
 vmrestore-windows-amd64:
-	GOARCH=amd64 APP_NAME=vmrestore $(MAKE) app-local-windows-goarch
+	GOARCH=amd64 APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-local-windows-goarch
 
 vmrestore-pure:
-	APP_NAME=vmrestore $(MAKE) app-local-pure
+	APP_NAME=vmrestore EXTRA_GO_BUILD_TAGS=$(VMRESTORE_GO_BUILD_TAGS) $(MAKE) app-local-pure

app/vmselect/graphite/eval.go

@@ -17,6 +17,9 @@ import (
 var maxGraphiteSeries = flag.Int("search.maxGraphiteSeries", 300e3, "The maximum number of time series, which can be scanned during queries to Graphite Render API. "+
 	"See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#render-api")
 
+var maxGraphitePathExpressionLen = flag.Int("search.maxGraphitePathExpressionLen", 1024, "The maximum length of pathExpression field in Graphite series. "+
+	"Longer expressions are truncated to prevent memory exhaustion on complex nested queries. Set to 0 to disable truncation.")
+
 type evalConfig struct {
 	startTime   int64
 	endTime     int64
@@ -53,6 +56,21 @@ func (ec *evalConfig) newTimestamps(step int64) []int64 {
 	return timestamps
 }
 
+// safePathExpression creates a pathExpression string from the given expression,
+// truncating it if it exceeds the maximum allowed length to prevent memory exhaustion.
+func safePathExpression(expr graphiteql.Expr) string {
+	if expr == nil {
+		return ""
+	}
+
+	pathExpr := string(expr.AppendString(nil))
+	maxLen := *maxGraphitePathExpressionLen
+	if maxLen > 0 && len(pathExpr) > maxLen {
+		return pathExpr[:maxLen] + "..."
+	}
+	return pathExpr
+}
+
 type series struct {
 	Name       string
 	Tags       map[string]string
@@ -169,7 +187,7 @@ func newNextSeriesForSearchQuery(ec *evalConfig, sq *storage.SearchQuery, expr g
 				Timestamps:     append([]int64{}, rs.Timestamps...),
 				Values:         append([]float64{}, rs.Values...),
 				expr:           expr,
-				pathExpression: string(expr.AppendString(nil)),
+				pathExpression: safePathExpression(expr),
 			}
 			s.summarize(aggrAvg, ec.startTime, ec.endTime, ec.storageStep, 0)
 			t := timerpool.Get(30 * time.Second)

app/vmselect/graphite/eval_test.go

@@ -4178,3 +4178,170 @@ func formatTimestamps(tss []int64) string {
 	fmt.Fprintf(&sb, " ]")
 	return sb.String()
 }
+
+func TestSafePathExpression(t *testing.T) {
+	// Save original value and restore after test
+	originalMaxLen := *maxGraphitePathExpressionLen
+	defer func() {
+		*maxGraphitePathExpressionLen = originalMaxLen
+	}()
+
+	t.Run("nil expression", func(t *testing.T) {
+		result := safePathExpression(nil)
+		if result != "" {
+			t.Fatalf("expected empty string for nil expression, got: %q", result)
+		}
+	})
+
+	t.Run("short expression - no truncation", func(t *testing.T) {
+		*maxGraphitePathExpressionLen = 50
+		expr := &graphiteql.MetricExpr{Query: "metric.cpu.usage"}
+		result := safePathExpression(expr)
+		expected := "metric.cpu.usage"
+		if result != expected {
+			t.Fatalf("expected %q, got %q", expected, result)
+		}
+	})
+
+	t.Run("long expression - with truncation", func(t *testing.T) {
+		*maxGraphitePathExpressionLen = 20
+		longQuery := "vertica.metrics.fr4.verticamultitenant-eon.request_resource_consumption.very_long_metric_name"
+		expr := &graphiteql.MetricExpr{Query: longQuery}
+		result := safePathExpression(expr)
+		expectedPrefix := longQuery[:20]
+		expectedSuffix := "..."
+		expected := expectedPrefix + expectedSuffix
+
+		if result != expected {
+			t.Fatalf("expected %q, got %q", expected, result)
+		}
+		if len(result) != 23 { // 20 + 3 for "..."
+			t.Fatalf("expected result length 23, got %d", len(result))
+		}
+		if !strings.HasSuffix(result, "...") {
+			t.Fatalf("expected result to end with '...', got %q", result)
+		}
+	})
+
+	t.Run("truncation disabled", func(t *testing.T) {
+		*maxGraphitePathExpressionLen = 0 // Disable truncation
+		longQuery := "very.long.metric.name.that.would.normally.be.truncated.but.should.not.be"
+		expr := &graphiteql.MetricExpr{Query: longQuery}
+		result := safePathExpression(expr)
+
+		if result != longQuery {
+			t.Fatalf("expected full string %q when truncation disabled, got %q", longQuery, result)
+		}
+	})
+
+	t.Run("function expression", func(t *testing.T) {
+		*maxGraphitePathExpressionLen = 30
+		// Create a function expression: sum(metric.cpu.usage)
+		args := []*graphiteql.ArgExpr{
+			{Expr: &graphiteql.MetricExpr{Query: "metric.cpu.usage"}},
+		}
+		funcExpr := &graphiteql.FuncExpr{
+			FuncName: "sum",
+			Args:     args,
+		}
+
+		result := safePathExpression(funcExpr)
+		expected := "sum(metric.cpu.usage)"
+
+		if result != expected {
+			t.Fatalf("expected %q, got %q", expected, result)
+		}
+	})
+
+	t.Run("complex nested function - truncated", func(t *testing.T) {
+		*maxGraphitePathExpressionLen = 15
+		// Create nested functions: sum(avg(metric.cpu.usage))
+		innerArgs := []*graphiteql.ArgExpr{
+			{Expr: &graphiteql.MetricExpr{Query: "metric.cpu.usage"}},
+		}
+		innerFunc := &graphiteql.FuncExpr{
+			FuncName: "avg",
+			Args:     innerArgs,
+		}
+		outerArgs := []*graphiteql.ArgExpr{
+			{Expr: innerFunc},
+		}
+		outerFunc := &graphiteql.FuncExpr{
+			FuncName: "sum",
+			Args:     outerArgs,
+		}
+
+		result := safePathExpression(outerFunc)
+
+		if len(result) != 18 { // 15 + 3 for "..."
+			t.Fatalf("expected result length 18, got %d", len(result))
+		}
+		if !strings.HasSuffix(result, "...") {
+			t.Fatalf("expected result to end with '...', got %q", result)
+		}
+		if !strings.HasPrefix(result, "sum(avg(metric") {
+			t.Fatalf("expected result to start with 'sum(avg(metric', got %q", result)
+		}
+	})
+
+	t.Run("boundary case - exact length", func(t *testing.T) {
+		*maxGraphitePathExpressionLen = 10
+		expr := &graphiteql.MetricExpr{Query: "metric.cpu"} // Exactly 10 characters
+		result := safePathExpression(expr)
+		expected := "metric.cpu"
+
+		if result != expected {
+			t.Fatalf("expected %q, got %q", expected, result)
+		}
+	})
+
+	t.Run("boundary case - one character over", func(t *testing.T) {
+		*maxGraphitePathExpressionLen = 10
+		expr := &graphiteql.MetricExpr{Query: "metric.cpu.x"} // 11 characters
+		result := safePathExpression(expr)
+		expected := "metric.cpu..."
+
+		if result != expected {
+			t.Fatalf("expected %q, got %q", expected, result)
+		}
+	})
+}
+
+func TestSafePathExpressionFromString(t *testing.T) {
+	// Save original value and restore after test
+	originalMaxLen := *maxGraphitePathExpressionLen
+	defer func() {
+		*maxGraphitePathExpressionLen = originalMaxLen
+	}()
+
+	t.Run("short string - no truncation", func(t *testing.T) {
+		*maxGraphitePathExpressionLen = 50
+		input := "sumSeries(metric1,metric2)"
+		result := safePathExpressionFromString(input)
+
+		if result != input {
+			t.Fatalf("expected %q, got %q", input, result)
+		}
+	})
+
+	t.Run("long string - with truncation", func(t *testing.T) {
+		*maxGraphitePathExpressionLen = 20
+		input := "sumSeries(very.long.metric.name.that.exceeds.limit,another.metric)"
+		result := safePathExpressionFromString(input)
+		expected := "sumSeries(very.long...."
+
+		if result != expected {
+			t.Fatalf("expected %q, got %q", expected, result)
+		}
+	})
+
+	t.Run("truncation disabled", func(t *testing.T) {
+		*maxGraphitePathExpressionLen = 0
+		input := "very.long.string.that.would.normally.be.truncated"
+		result := safePathExpressionFromString(input)
+
+		if result != input {
+			t.Fatalf("expected full string when truncation disabled, got %q", result)
+		}
+	})
+}

app/vmselect/graphite/render_api_test.go

@@ -10,7 +10,7 @@ func TestParseIntervalSuccess(t *testing.T) {
 		t.Helper()
 		interval, err := parseInterval(s)
 		if err != nil {
-			t.Fatalf("unexpected error in parseInterva(%q): %s", s, err)
+			t.Fatalf("unexpected error in parseInterval(%q): %s", s, err)
 		}
 		if interval != intervalExpected {
 			t.Fatalf("unexpected result for parseInterval(%q); got %d; want %d", s, interval, intervalExpected)

app/vmselect/graphite/transform.go

@@ -17,6 +17,16 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/cgroup"
 )
 
+// safePathExpressionFromString truncates a pathExpression string if it exceeds
+// the maximum allowed length to prevent memory exhaustion.
+func safePathExpressionFromString(pathExpr string) string {
+	maxLen := *maxGraphitePathExpressionLen
+	if maxLen > 0 && len(pathExpr) > maxLen {
+		return pathExpr[:maxLen] + "..."
+	}
+	return pathExpr
+}
+
 // nextSeriesFunc must return the next series to process.
 //
 // nextSeriesFunc must release all the occupied resources before returning non-nil error.
@@ -319,7 +329,7 @@ func aggregateSeries(ec *evalConfig, expr graphiteql.Expr, nextSeries nextSeries
 		Tags:           tags,
 		Timestamps:     ec.newTimestamps(step),
 		Values:         as.Finalize(xFilesFactor),
-		pathExpression: name,
+		pathExpression: safePathExpressionFromString(name),
 		expr:           expr,
 		step:           step,
 	}
@@ -1124,7 +1134,7 @@ func constantLine(ec *evalConfig, expr graphiteql.Expr, n float64) nextSeriesFun
 		Timestamps:     []int64{ec.startTime, ec.startTime + step, ec.startTime + 2*step},
 		Values:         []float64{n, n, n},
 		expr:           expr,
-		pathExpression: string(expr.AppendString(nil)),
+		pathExpression: safePathExpression(expr),
 		step:           step,
 	}
 	return singleSeriesFunc(s)

app/vmselect/graphiteql/lexer_test.go

@@ -17,7 +17,7 @@ func TestScanStringSuccess(t *testing.T) {
 			t.Fatalf("unexpected string scanned from %s; got %s; want %s", s, result, sExpected)
 		}
 		if !strings.HasPrefix(s, result) {
-			t.Fatalf("invalid prefix for scanne string %s: %s", s, result)
+			t.Fatalf("invalid prefix for scanned string %s: %s", s, result)
 		}
 	}
 	f(`""`, `""`)

app/vmselect/graphiteql/parser.go

@@ -210,7 +210,7 @@ func (p *parser) parseMetricExprOrFuncCall() (Expr, error) {
 		}
 		return fe, nil
 	default:
-		// Metric epxression or bool expression or None.
+		// Metric expression or bool expression or None.
 		if isBool(ident) {
 			be := &BoolExpr{
 				B: strings.EqualFold(ident, "true"),

app/vmselect/netstorage/netstorage.go

@@ -269,7 +269,7 @@ func (rss *Results) runParallel(qt *querytracer.Tracer, f func(rs *Result, worke
 	}
 
 	// Slow path - spin up multiple local workers for parallel data processing.
-	// Do not use global workers pool, since it increases inter-CPU memory ping-poing,
+	// Do not use global workers pool, since it increases inter-CPU memory ping-pong,
 	// which reduces the scalability on systems with many CPU cores.
 
 	// Prepare the work for workers.
@@ -485,7 +485,7 @@ func (pts *packedTimeseries) unpackTo(dst []*sortBlock, tbf *tmpBlocksFile, tr s
 	}
 
 	// Slow path - spin up multiple local workers for parallel data unpacking.
-	// Do not use global workers pool, since it increases inter-CPU memory ping-poing,
+	// Do not use global workers pool, since it increases inter-CPU memory ping-pong,
 	// which reduces the scalability on systems with many CPU cores.
 
 	// Prepare the work for workers.

app/vmselect/netstorage/tmp_blocks_file.go

@@ -135,7 +135,7 @@ func (tbf *tmpBlocksFile) WriteBlockRefData(b []byte) (tmpBlockAddr, error) {
 	return addr, nil
 }
 
-// Len() returnt tbf size in bytes.
+// Len() return tbf size in bytes.
 func (tbf *tmpBlocksFile) Len() uint64 {
 	return tbf.offset
 }

app/vmselect/promql/binary_op.go

@@ -188,7 +188,7 @@ func newBinaryOpFunc(bf func(left, right float64, isBool bool) float64) binaryOp
 			rightValues := right[i].Values
 			dstValues := dst[i].Values
 			if len(leftValues) != len(rightValues) || len(leftValues) != len(dstValues) {
-				logger.Panicf("BUG: len(leftVaues) must match len(rightValues) and len(dstValues); got %d vs %d vs %d",
+				logger.Panicf("BUG: len(leftValues) must match len(rightValues) and len(dstValues); got %d vs %d vs %d",
 					len(leftValues), len(rightValues), len(dstValues))
 			}
 			for j, a := range leftValues {

app/vmselect/promql/eval_test.go

@@ -55,7 +55,7 @@ func TestValidateMaxPointsPerSeriesFailure(t *testing.T) {
 	f := func(start, end, step int64, maxPoints int) {
 		t.Helper()
 		if err := ValidateMaxPointsPerSeries(start, end, step, maxPoints); err == nil {
-			t.Fatalf("expecint non-nil error for ValidateMaxPointsPerSeries(start=%d, end=%d, step=%d, maxPoints=%d)", start, end, step, maxPoints)
+			t.Fatalf("expecting non-nil error for ValidateMaxPointsPerSeries(start=%d, end=%d, step=%d, maxPoints=%d)", start, end, step, maxPoints)
 		}
 	}
 	// zero step

app/vmselect/promql/rollup.go

@@ -2443,13 +2443,14 @@ func rollupFake(_ *rollupFuncArg) float64 {
 	return 0
 }
 
+// getScalar expects result from a [scalar](https://prometheus.io/docs/prometheus/latest/querying/basics/#expression-language-data-types).
 func getScalar(arg any, argNum int) ([]float64, error) {
 	ts, ok := arg.([]*timeseries)
 	if !ok {
-		return nil, fmt.Errorf(`unexpected type for arg #%d; got %T; want %T`, argNum+1, arg, ts)
+		return nil, fmt.Errorf(`arg #%d must be a scalar`, argNum+1)
 	}
 	if len(ts) != 1 {
-		return nil, fmt.Errorf(`arg #%d must contain a single timeseries; got %d timeseries`, argNum+1, len(ts))
+		return nil, fmt.Errorf(`arg #%d must be a scalar`, argNum+1)
 	}
 	return ts[0].Values, nil
 }
@@ -2466,14 +2467,15 @@ func getIntNumber(arg any, argNum int) (int, error) {
 	return n, nil
 }
 
+// getString expects result from a string expression, which contains a single timeseries with only NaN values.
 func getString(tss []*timeseries, argNum int) (string, error) {
 	if len(tss) != 1 {
-		return "", fmt.Errorf(`arg #%d must contain a single timeseries; got %d timeseries`, argNum+1, len(tss))
+		return "", fmt.Errorf(`arg #%d must be a string`, argNum+1)
 	}
 	ts := tss[0]
 	for _, v := range ts.Values {
 		if !math.IsNaN(v) {
-			return "", fmt.Errorf(`arg #%d contains non-string timeseries`, argNum+1)
+			return "", fmt.Errorf(`arg #%d must be a string`, argNum+1)
 		}
 	}
 	return string(ts.MetricName.MetricGroup), nil

app/vmselect/promql/transform.go

@@ -903,7 +903,6 @@ func transformHistogramQuantile(tfa *transformFuncArg) ([]*timeseries, error) {
 
 	// Convert buckets with `vmrange` labels to buckets with `le` labels.
 	tss := vmrangeBucketsToLE(args[1])
-
 	// Parse boundsLabel. See https://github.com/prometheus/prometheus/issues/5706 for details.
 	var boundsLabel string
 	if len(args) > 2 {
@@ -1050,9 +1049,15 @@ func fixBrokenBuckets(i int, xss []leTimeseries) {
 		return
 	}
 
+	vNext := xss[0].ts.Values[i]
+	// Set the lowest bucket to 0 if its value is NaN, so it can be properly
+	// compared with upper buckets in the loop below.
+	if math.IsNaN(vNext) {
+		vNext = 0
+		xss[0].ts.Values[i] = vNext
+	}
 	// Substitute upper bucket values with lower bucket values if the upper values are NaN
 	// or are bigger than the lower bucket values.
-	vNext := xss[0].ts.Values[i]
 	for j := 1; j < len(xss); j++ {
 		v := xss[j].ts.Values[i]
 		if math.IsNaN(v) || vNext > v {

app/vmselect/promql/transform_test.go

@@ -37,6 +37,9 @@ func TestFixBrokenBuckets(t *testing.T) {
 	f([]float64{5, 1, 2, 3, nan}, []float64{5, 5, 5, 5, 5})
 	f([]float64{1, 5, 2, nan, 6, 3}, []float64{1, 5, 5, 5, 6, 6})
 	f([]float64{5, 10, 4, 3}, []float64{5, 10, 10, 10})
+	f([]float64{nan, 2, nan, 5}, []float64{0, 2, 2, 5})
+	f([]float64{nan, nan, 4, 5}, []float64{0, 0, 4, 5})
+	f([]float64{nan, nan, nan, 4}, []float64{0, 0, 0, 4})
 }
 
 func TestFixBrokenBucketsMultipleValues(t *testing.T) {
@@ -44,12 +47,11 @@ func TestFixBrokenBucketsMultipleValues(t *testing.T) {
 		t.Helper()
 		xss := make([]leTimeseries, len(values))
 		for i, v := range values {
-
 			xss[i].ts = &timeseries{
 				Values: v,
 			}
 		}
-		for i := range len(values) - 1 {
+		for i := range len(values[0]) {
 			fixBrokenBuckets(i, xss)
 		}
 		result := make([][]float64, len(values))
@@ -61,6 +63,8 @@ func TestFixBrokenBucketsMultipleValues(t *testing.T) {
 		}
 	}
 	f([][]float64{{10, 1}, {11, 2}, {13, 3}}, [][]float64{{10, 1}, {11, 2}, {13, 3}})
+	f([][]float64{{nan, nan}, {11, 2}, {13, 3}}, [][]float64{{0, 0}, {11, 2}, {13, 3}})
+	f([][]float64{{nan, nan, nan}, {11, 2, 3}, {13, 3, 4}}, [][]float64{{0, 0, 0}, {11, 2, 3}, {13, 3, 4}})
 }
 
 func TestVmrangeBucketsToLE(t *testing.T) {

app/vmselect/vmui/index.html

@@ -36,7 +36,7 @@
   <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-BT5pWGkz.js"></script>
+  <script type="module" crossorigin src="./assets/index-Ck5nH8JI.js"></script>
   <link rel="modulepreload" crossorigin href="./assets/vendor-BVRvRxZ2.js">
   <link rel="stylesheet" crossorigin href="./assets/vendor-D1GxaB_c.css">
   <link rel="stylesheet" crossorigin href="./assets/index-BHg4iVVe.css">

app/vmui/Dockerfile-web

@@ -1,4 +1,4 @@
-FROM golang:1.24.5 AS build-web-stage
+FROM golang:1.25.0 AS build-web-stage
 COPY build /build
 
 WORKDIR /build

app/vmui/packages/vmui/src/hooks/useFetchQuery.ts

@@ -152,7 +152,7 @@ export const useFetchQuery = ({
         counter++;
       }
 
-      const limitText = `Showing ${tempData.length} series out of ${totalLength} series due to performance reasons. Please narrow down the query, so it returns less series`;
+      const limitText = `Showing ${tempData.length} series out of ${totalLength} series due to performance reasons. Please narrow down the query, so it returns fewer series`;
       setWarning(totalLength > seriesLimit ? limitText : "");
       isDisplayChart ? setGraphData(tempData as MetricResult[]) : setLiveData(tempData as InstantMetricResult[]);
       setTraces(tempTraces);

app/vmui/packages/vmui/src/pages/RawQueryPage/hooks/useFetchExport.ts

@@ -131,7 +131,7 @@ export const useFetchExport = ({ hideQuery, showAllSeries }: FetchQueryParams):
 
         counter++;
       }
-      const limitText = `Showing ${tempData.length} series out of ${totalLength} series due to performance reasons. Please narrow down the query, so it returns less series`;
+      const limitText = `Showing ${tempData.length} series out of ${totalLength} series due to performance reasons. Please narrow down the query, so it returns fewer series`;
       setWarning(totalLength > seriesLimit ? limitText : "");
       setData(tempData as MetricResult[]);
       setIsLoading(false);

apptest/client.go

@@ -6,6 +6,7 @@ import (
 	"net"
 	"net/http"
 	"net/url"
+	"regexp"
 	"strconv"
 	"strings"
 	"testing"
@@ -183,3 +184,32 @@ func (app *ServesMetrics) GetMetricsByPrefix(t *testing.T, prefix string) []floa
 	}
 	return values
 }
+
+func (app *ServesMetrics) GetMetricsByRegexp(t *testing.T, re *regexp.Regexp) []float64 {
+	t.Helper()
+
+	values := []float64{}
+
+	metrics, statusCode := app.cli.Get(t, app.metricsURL)
+	if statusCode != http.StatusOK {
+		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
+	}
+	for _, metric := range strings.Split(metrics, "\n") {
+		if !re.MatchString(metric) {
+			continue
+		}
+
+		parts := strings.Split(metric, " ")
+		if len(parts) < 2 {
+			t.Fatalf("unexpected record format: got %q, want metric name and value separated by a space", metric)
+		}
+
+		value, err := strconv.ParseFloat(parts[len(parts)-1], 64)
+		if err != nil {
+			t.Fatalf("could not parse metric value %s: %v", metric, err)
+		}
+
+		values = append(values, value)
+	}
+	return values
+}

apptest/testcase.go

@@ -173,7 +173,7 @@ func (tc *TestCase) MustStartVmagent(instance string, flags []string, promScrape
 // vminsert, and one vmselect.
 //
 // Both Vmsingle and Vmcluster implement the PrometheusWriteQuerier used in
-// business logic tests to abstract out the infrasture.
+// business logic tests to abstract out the infrastructure.
 //
 // This type is not suitable for infrastructure tests where custom cluster
 // setups are often required.

apptest/tests/multilevel_test.go

@@ -17,7 +17,7 @@ func TestClusterMultilevelSelect(t *testing.T) {
 	//
 	// vmselect (L2) -> vmselect (L1) -> vmstorage <- vminsert
 	//
-	// vmisert writes data into vmstorage.
+	// vminsert writes data into vmstorage.
 	// vmselect (L2) reads that data via vmselect (L1).
 
 	vmstorage := tc.MustStartVmstorage("vmstorage", []string{

apptest/tests/vmagent_remotewrite_test.go

@@ -6,6 +6,7 @@ import (
 	"net/http/httptest"
 	"sync"
 	"testing"
+	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/apptest"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
@@ -248,3 +249,88 @@ func TestSingleVMAgentDowngradeRemoteWriteProtocol(t *testing.T) {
 		t.Fatalf("unexpected number of dropped packets; got %d, want %d", actualPacketsDroppedCount, expectedPacketsDroppedTotal)
 	}
 }
+
+func TestSingleVMAgentDropOnOverload(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()
+
+	remoteWriteSrv2 := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(http.StatusServiceUnavailable)
+	}))
+	defer remoteWriteSrv2.Close()
+
+	vmagent := tc.MustStartVmagent("vmagent", []string{
+		`-remoteWrite.flushInterval=50ms`,
+		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv.URL),
+		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv2.URL),
+		"-remoteWrite.disableOnDiskQueue=true",
+		// use only 1 worker to get a full queue faster
+		"-remoteWrite.queues=1",
+		// fastqueue size is roughly memory.Allowed() / len(urls) / *maxRowsPerBlock / 100
+		// Use very large maxRowsPerBlock to get fastqueue of minimal length(2).
+		// See initRemoteWriteCtxs function in remotewrite.go for details.
+		"-remoteWrite.maxRowsPerBlock=1000000000",
+		"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent",
+	}, ``)
+
+	const (
+		retries = 20
+		period  = 100 * time.Millisecond
+	)
+
+	waitFor := func(f func() bool) {
+		t.Helper()
+		for i := 0; i < retries; i++ {
+			if f() {
+				return
+			}
+			time.Sleep(period)
+		}
+		t.Fatalf("timed out waiting for retry #%d", retries)
+	}
+
+	// Real remote write URLs are hidden in metrics
+	url1 := "1:secret-url"
+	url2 := "2:secret-url"
+
+	// Wait until first request got flushed to remote write server
+	vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
+		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
+	}, apptest.QueryOpts{})
+
+	waitFor(
+		func() bool {
+			return vmagent.RemoteWriteRequests(t, url1) == 1 && vmagent.RemoteWriteRequests(t, url2) == 1
+		},
+	)
+
+	// Send 2 more requests, the first RW endpoint should receive everything, the second should add them to the queue
+	// since worker is busy with the first request.
+	for i := 0; i < 2; i++ {
+		vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
+			"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
+		}, apptest.QueryOpts{})
+
+		waitFor(
+			func() bool {
+				return vmagent.RemoteWriteRequests(t, url1) == 2+i && vmagent.RemoteWritePendingInmemoryBlocks(t, url2) == 1+i
+			},
+		)
+	}
+
+	// Send one more request.
+	vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
+		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
+	}, apptest.QueryOpts{})
+
+	waitFor(
+		func() bool {
+			return vmagent.RemoteWriteRequests(t, url1) == 4 && vmagent.RemoteWriteSamplesDropped(t, url2) > 0
+		},
+	)
+}

apptest/tests/vmauth_routing_test.go

@@ -1,8 +1,10 @@
 package tests
 
 import (
+	"context"
 	"fmt"
 	"io"
+	"net"
 	"net/http"
 	"net/http/httptest"
 	"net/url"
@@ -301,3 +303,82 @@ unauthorized_user:
 	assertBackendsRequestsCount(1)
 
 }
+
+func TestSingleVMAuthUseProxyProtocol(t *testing.T) {
+	tc := apptest.NewTestCase(t)
+	defer tc.Stop()
+
+	var requestsCount int
+	var actualForwardedForHeader string
+	backend := httptest.NewServer(http.HandlerFunc(func(_ http.ResponseWriter, r *http.Request) {
+		actualForwardedForHeader = r.Header.Get("X-Forwarded-For")
+		requestsCount++
+	}))
+	defer backend.Close()
+
+	authConfig := fmt.Sprintf(`
+unauthorized_user:
+  url_prefix: %s
+  `, backend.URL)
+
+	vmauth := tc.MustStartVmauth("vmauth", []string{
+		"-httpListenAddr.useProxyProtocol=true",
+	}, authConfig)
+
+	req, err := http.NewRequest("GET", fmt.Sprintf("http://%s/backend", vmauth.GetHTTPListenAddr()), nil)
+	if err != nil {
+		t.Fatalf("cannot build http.Request: %s", err)
+	}
+
+	// make request using proxy protocol
+	c := &http.Client{
+		Transport: &http.Transport{
+			DialContext: func(_ context.Context, network, addr string) (net.Conn, error) {
+				conn, err := net.Dial(network, addr)
+				if err != nil {
+					return nil, err
+				}
+
+				// Write a proxy protocol header to the connection
+				if _, err := conn.Write([]byte{
+					0x0D, 0x0A, 0x0D, 0x0A, 0x00, 0x0D, 0x0A, 0x51, 0x55, 0x49, 0x54, 0x0A, // signature
+					0x21,       // version 2
+					0x11,       // family IPv4
+					0x00, 0x0C, // length: 12 bytes (IPv4 + ports)
+					192, 168, 1, 100, // source IP
+					10, 0, 0, 1, // destination IP
+					0x1F, 0x90, // source port 8080
+					0x00, 0x50, // destination port 80
+				}); err != nil {
+					t.Fatalf("cannot send proxy protocol header: %s", err)
+				}
+
+				return conn, nil
+			},
+		},
+	}
+
+	resp, err := c.Do(req)
+	if err != nil {
+		t.Fatalf("cannot make http.Get request for target=%q: %s", req.URL, err)
+	}
+	responseText, err := io.ReadAll(resp.Body)
+	if err != nil {
+		t.Fatalf("cannot read response body: %s", err)
+	}
+	resp.Body.Close()
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("unexpected http response code: %d, want: %d, response text: %s", resp.StatusCode, http.StatusOK, responseText)
+	}
+
+	// ensure that request was proxied
+	if requestsCount != 1 {
+		t.Fatalf("expected to have %d unauthorized proxied requests, got: %d", 1, requestsCount)
+	}
+
+	// ensure that X-Forwarded-For header is set to the source IP from proxy protocol
+	expectedForwardedForHeader := "192.168.1.100"
+	if actualForwardedForHeader != expectedForwardedForHeader {
+		t.Fatalf("expected X-Forwarded-For header to be equal to proxy source IP, got: %s, want: %s'", actualForwardedForHeader, expectedForwardedForHeader)
+	}
+}

apptest/vmagent.go

@@ -104,6 +104,36 @@ func (app *Vmagent) RemoteWritePacketsDroppedTotal(t *testing.T) int {
 	return int(total)
 }
 
+// RemoteWriteSamplesDropped sums up the total number of dropped remote write samples for given remote write URL.
+func (app *Vmagent) RemoteWriteSamplesDropped(t *testing.T, url string) int {
+	re := regexp.MustCompile(fmt.Sprintf("vmagent_remotewrite_samples_dropped_total{.*url=%q.*}", url))
+	total := 0.0
+	for _, v := range app.GetMetricsByRegexp(t, re) {
+		total += v
+	}
+	return int(total)
+}
+
+// RemoteWritePendingInmemoryBlocks sums up the total number of pending in-memory blocks for given remote write URL.
+func (app *Vmagent) RemoteWritePendingInmemoryBlocks(t *testing.T, url string) int {
+	re := regexp.MustCompile(fmt.Sprintf("vmagent_remotewrite_pending_inmemory_blocks{.*url=%q.*}", url))
+	total := 0.0
+	for _, v := range app.GetMetricsByRegexp(t, re) {
+		total += v
+	}
+	return int(total)
+}
+
+// RemoteWriteRequests sums up the total number of sending requests for given remote write URL.
+func (app *Vmagent) RemoteWriteRequests(t *testing.T, url string) int {
+	re := regexp.MustCompile(fmt.Sprintf("vmagent_remotewrite_requests_total{.*url=%q.*}", url))
+	total := 0.0
+	for _, v := range app.GetMetricsByRegexp(t, re) {
+		total += v
+	}
+	return int(total)
+}
+
 // ReloadRelabelConfigs sends SIGHUP to trigger relabel config reload
 // and waits until vmagent_relabel_config_reloads_total increases.
 // Fails the test if no reload is detected within 3 seconds.
@@ -123,9 +153,7 @@ func (app *Vmagent) ReloadRelabelConfigs(t *testing.T) {
 		time.Sleep(100 * time.Millisecond)
 	}
 
-	if currTotal <= prevTotal {
-		t.Fatalf("relabel configs were not reloaded after SIGHUP signal; previous total: %f, current total: %f", prevTotal, currTotal)
-	}
+	t.Fatalf("relabel configs were not reloaded after SIGHUP signal; previous total: %f, current total: %f", prevTotal, currTotal)
 }
 
 // sendBlocking sends the data to vmstorage by executing `send` function and

apptest/vmauth.go

@@ -56,25 +56,32 @@ func StartVmauth(instance string, flags []string, cli *Client, configFilePath st
 	}, nil
 }
 
-// UpdateConfiguration performs configuration file reload for app and waits for configuration apply
-//
-// Due to second prescision of config reload metric, config cannot be reloaded more than 1 time in a second
+// UpdateConfiguration updates the vmauth configuration file with the provided YAML content,
+// sends SIGHUP to trigger config reload
+// and waits until vmauth_config_last_reload_total increases.
+// Fails the test if no reload is detected within 2 seconds.
 func (app *Vmauth) UpdateConfiguration(t *testing.T, configFileYAML string) {
 	t.Helper()
-	ct := int(time.Now().Unix())
+
 	fs.MustWriteSync(app.configFilePath, []byte(configFileYAML))
+
+	prevTotal := app.GetIntMetric(t, "vmauth_config_last_reload_total")
+
 	if err := app.process.Signal(syscall.SIGHUP); err != nil {
 		t.Fatalf("unexpected signal error: %s", err)
 	}
-	for range 10 {
-		ts := app.GetIntMetric(t, "vmauth_config_last_reload_success_timestamp_seconds")
-		if ts < ct {
-			time.Sleep(time.Millisecond * 100)
-			continue
+
+	var currTotal int
+	for range 20 {
+		currTotal = app.GetIntMetric(t, "vmauth_config_last_reload_total")
+		if currTotal > prevTotal {
+			return
 		}
-		return
+
+		time.Sleep(time.Millisecond * 100)
 	}
-	t.Fatalf("timeout waiting for config reload success")
+
+	t.Fatalf("config were not reloaded after SIGHUP signal; previous total: %d, current total: %d", prevTotal, currTotal)
 }
 
 // GetHTTPListenAddr returns listen http addr

apptest/vminsert.go

@@ -49,7 +49,7 @@ func StartVminsert(instance string, flags []string, cli *Client, output io.Write
 		graphiteListenAddrRE,
 		openTSDBListenAddrRE,
 	}
-	// Add storateNode REs to block until vminsert establishes connections with
+	// Add storageNode REs to block until vminsert establishes connections with
 	// all storage nodes. The extracted values are unused.
 	for _, sn := range storageNodes(flags) {
 		logRecord := fmt.Sprintf("successfully dialed -storageNode=\"%s\"", sn)

benchmarks/Makefile

@@ -34,26 +34,28 @@
 # for details
 tsbs: tsbs-build tsbs-generate-data tsbs-load-data tsbs-generate-queries tsbs-run-queries
 
-TSBS_SCALE := 100000
-# If GNU date is available, use it; otherwise, fall back to the standard date command
-# User can install GNU date on macOS via `brew install coreutils`
-DATE_CMD := $(shell which gdate 2>/dev/null || echo date)
-TSBS_START := $(shell $(DATE_CMD) -u -d "1 day ago 00:00:00" +"%Y-%m-%dT%H:%M:%SZ")
-TSBS_END   := $(shell $(DATE_CMD) -u -d "00:00:00" +"%Y-%m-%dT%H:%M:%SZ")
-TSBS_STEP := 80s
-TSBS_QUERIES := 1000
-TSBS_WORKERS := 4
+TSBS_SCALE ?= 100000
+TSBS_END ?= $(shell date -u +%Y-%m-%dT00:00:00Z)
+TSBS_START ?= $(shell \
+  NOW=$$(date -u +%s); \
+  START=$$((NOW - 86400)); \
+  date -u -d "@$$START" +%Y-%m-%dT00:00:00Z 2>/dev/null || \
+  date -u -r $$START +%Y-%m-%dT00:00:00Z 2>/dev/null \
+)
+TSBS_STEP ?= 80s
+TSBS_QUERIES ?= 1000
+TSBS_WORKERS ?= 4
 TSBS_DATA_FILE := /tmp/tsbs-data-$(TSBS_SCALE)-$(TSBS_START)-$(TSBS_END)-$(TSBS_STEP).gz
 TSBS_QUERY_FILE := /tmp/tsbs-queries-$(TSBS_SCALE)-$(TSBS_START)-$(TSBS_END)-$(TSBS_QUERIES).gz
 # For cluster setup use http://vminsert:8480/insert/0/influx/write
-TSBS_WRITE_URLS := http://localhost:8428/write
+TSBS_WRITE_URLS ?= http://localhost:8428/write
 # For cluster setup use http://vmselect:8481/select/0/prometheus
-TSBS_READ_URLS := http://localhost:8428
-TSBS_METRICS_URL := http://localhost:8428/metrics
+TSBS_READ_URLS ?= http://localhost:8428
+TSBS_METRICS_URL ?= http://localhost:8428/metrics
 
 # Build TSBS tools
 tsbs-build:
-	test -d /tmp/tsbs || (git clone https://github.com/timescale/tsbs.git /tmp/tsbs && \
+	test -d /tmp/tsbs/cmd/tsbs_run_queries_victoriametrics || (git clone https://github.com/timescale/tsbs.git /tmp/tsbs && \
 		cd /tmp/tsbs/cmd/tsbs_generate_data && GOBIN=/tmp/tsbs/bin go install && \
 		cd /tmp/tsbs/cmd/tsbs_generate_queries && GOBIN=/tmp/tsbs/bin go install && \
 		cd /tmp/tsbs/cmd/tsbs_load_victoriametrics && GOBIN=/tmp/tsbs/bin go install && \

dashboards/victoriametrics-cluster.json

@@ -7962,7 +7962,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "99th percentile of the number of time series read per query.",
+          "description": "Shows the max 99th percentile of time series read per query across all vmselects.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -8051,7 +8051,7 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(histogram_quantile(0.99, sum(rate(vm_series_read_per_query_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
+              "expr": "max(histogram_quantile(0.99, sum(rate(vm_series_read_per_query_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -8068,7 +8068,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) read per queried time series.",
+          "description": "Shows the max 99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) read per time series.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -8157,7 +8157,7 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(histogram_quantile(0.99, sum(rate(vm_rows_read_per_series_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
+              "expr": "max(histogram_quantile(0.99, sum(rate(vm_rows_read_per_series_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -8174,7 +8174,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) read per query.",
+          "description": "Shows the max 99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) read per query.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -8263,7 +8263,7 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(histogram_quantile(0.99, sum(rate(vm_rows_read_per_query_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
+              "expr": "max(histogram_quantile(0.99, sum(rate(vm_rows_read_per_query_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -8280,7 +8280,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) scanner per query.\n\nThis number can exceed number of DatapointsReadPerQuery if `step` query arg passed to [/api/v1/query_range](https://prometheus.io/docs/prometheus/latest/querying/api/#range-queries) is smaller than the lookbehind window set in square brackets of [rollup function](https://docs.victoriametrics.com/victoriametrics/metricsql/#rollup-functions). For example, if `increase(some_metric[1h])` is executed with the `step=5m`, then the same [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) on a hour time range are scanned `1h/5m=12` times. See [this article](https://valyala.medium.com/how-to-optimize-promql-and-metricsql-queries-85a1b75bf986) for details.",
+          "description": "Shows the max 99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) scanner per query.\n\nThis number can exceed number of DatapointsReadPerQuery if `step` query arg passed to [/api/v1/query_range](https://prometheus.io/docs/prometheus/latest/querying/api/#range-queries) is smaller than the lookbehind window set in square brackets of [rollup function](https://docs.victoriametrics.com/victoriametrics/metricsql/#rollup-functions). For example, if `increase(some_metric[1h])` is executed with the `step=5m`, then the same [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) on a hour time range are scanned `1h/5m=12` times. See [this article](https://valyala.medium.com/how-to-optimize-promql-and-metricsql-queries-85a1b75bf986) for details.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -8369,7 +8369,7 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(histogram_quantile(0.99, sum(rate(vm_rows_scanned_per_query_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
+              "expr": "max(histogram_quantile(0.99, sum(rate(vm_rows_scanned_per_query_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,

dashboards/vm/victoriametrics-cluster.json

@@ -7963,7 +7963,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "99th percentile of the number of time series read per query.",
+          "description": "Shows the max 99th percentile of time series read per query across all vmselects.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -8052,7 +8052,7 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(histogram_quantile(0.99, sum(rate(vm_series_read_per_query_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
+              "expr": "max(histogram_quantile(0.99, sum(rate(vm_series_read_per_query_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -8069,7 +8069,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) read per queried time series.",
+          "description": "Shows the max 99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) read per time series.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -8158,7 +8158,7 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(histogram_quantile(0.99, sum(rate(vm_rows_read_per_series_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
+              "expr": "max(histogram_quantile(0.99, sum(rate(vm_rows_read_per_series_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -8175,7 +8175,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) read per query.",
+          "description": "Shows the max 99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) read per query.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -8264,7 +8264,7 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(histogram_quantile(0.99, sum(rate(vm_rows_read_per_query_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
+              "expr": "max(histogram_quantile(0.99, sum(rate(vm_rows_read_per_query_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -8281,7 +8281,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) scanner per query.\n\nThis number can exceed number of DatapointsReadPerQuery if `step` query arg passed to [/api/v1/query_range](https://victoriametrics-metrics-datasource.io/docs/victoriametrics-metrics-datasource/latest/querying/api/#range-queries) is smaller than the lookbehind window set in square brackets of [rollup function](https://docs.victoriametrics.com/victoriametrics/metricsql/#rollup-functions). For example, if `increase(some_metric[1h])` is executed with the `step=5m`, then the same [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) on a hour time range are scanned `1h/5m=12` times. See [this article](https://valyala.medium.com/how-to-optimize-promql-and-metricsql-queries-85a1b75bf986) for details.",
+          "description": "Shows the max 99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) scanner per query.\n\nThis number can exceed number of DatapointsReadPerQuery if `step` query arg passed to [/api/v1/query_range](https://victoriametrics-metrics-datasource.io/docs/victoriametrics-metrics-datasource/latest/querying/api/#range-queries) is smaller than the lookbehind window set in square brackets of [rollup function](https://docs.victoriametrics.com/victoriametrics/metricsql/#rollup-functions). For example, if `increase(some_metric[1h])` is executed with the `step=5m`, then the same [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) on a hour time range are scanned `1h/5m=12` times. See [this article](https://valyala.medium.com/how-to-optimize-promql-and-metricsql-queries-85a1b75bf986) for details.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -8370,7 +8370,7 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(histogram_quantile(0.99, sum(rate(vm_rows_scanned_per_query_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
+              "expr": "max(histogram_quantile(0.99, sum(rate(vm_rows_scanned_per_query_bucket{job=~\"$job_select\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,

dashboards/vm/vmagent.json

@@ -7966,7 +7966,7 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(rate(vm_promscrape_scraped_samples_sum{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, instance)\n+ sum(rate(vmagent_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, instance)",
+              "expr": "sum(rate({__name__=~\"vm_promscrape_scraped_samples_sum|vmagent_rows_inserted_total\",job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, instance)",
               "hide": false,
               "interval": "",
               "legendFormat": "in {{instance}} {{job}}",
@@ -8244,4 +8244,4 @@
   "uid": "G7Z9GzMGz_vm",
   "version": 1,
   "weekStart": ""
-}
+}

dashboards/vmagent.json

@@ -7965,7 +7965,7 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(rate(vm_promscrape_scraped_samples_sum{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, instance)\n+ sum(rate(vmagent_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, instance)",
+              "expr": "sum(rate({__name__=~\"vm_promscrape_scraped_samples_sum|vmagent_rows_inserted_total\",job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, instance)",
               "hide": false,
               "interval": "",
               "legendFormat": "in {{instance}} {{job}}",
@@ -8243,4 +8243,4 @@
   "uid": "G7Z9GzMGz",
   "version": 1,
   "weekStart": ""
-}
+}

deployment/docker/Makefile

@@ -7,7 +7,7 @@ ROOT_IMAGE ?= alpine:3.22.1
 ROOT_IMAGE_SCRATCH ?= scratch
 CERTS_IMAGE := alpine:3.22.1
 
-GO_BUILDER_IMAGE := golang:1.24.5-alpine
+GO_BUILDER_IMAGE := golang:1.25.0-alpine
 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 :/ __)
 DOCKER ?= docker
@@ -43,7 +43,7 @@ app-via-docker: package-builder
 		$(BUILDER_IMAGE) \
 		go build $(RACE) -trimpath -buildvcs=false \
 			-ldflags "-extldflags '-static' $(GO_BUILDINFO)" \
-			-tags 'netgo osusergo musl' \
+			-tags 'netgo osusergo musl $(EXTRA_GO_BUILD_TAGS)' \
 			-o bin/$(APP_NAME)$(APP_SUFFIX)-prod $(PKG_PREFIX)/app/$(APP_NAME)
 
 app-via-docker-windows: package-builder
@@ -58,7 +58,7 @@ app-via-docker-windows: package-builder
 		$(BUILDER_IMAGE) \
 		go build $(RACE) -trimpath -buildvcs=false \
 			-ldflags "-s -w -extldflags '-static' $(GO_BUILDINFO)" \
-			-tags 'netgo osusergo' \
+			-tags 'netgo osusergo $(EXTRA_GO_BUILD_TAGS)' \
 			-o bin/$(APP_NAME)-windows$(APP_SUFFIX)-prod.exe $(PKG_PREFIX)/app/$(APP_NAME)
 
 package-via-docker: package-base

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:v1.122.0
+    image: victoriametrics/vmagent:v1.124.0
     depends_on:
       - "vmauth"
     ports:
@@ -35,14 +35,14 @@ 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:v1.122.0-cluster
+    image: victoriametrics/vmstorage:v1.124.0-cluster
     volumes:
       - strgdata-1:/storage
     command:
       - "--storageDataPath=/storage"
     restart: always
   vmstorage-2:
-    image: victoriametrics/vmstorage:v1.122.0-cluster
+    image: victoriametrics/vmstorage:v1.124.0-cluster
     volumes:
       - strgdata-2:/storage
     command:
@@ -52,7 +52,7 @@ 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:v1.122.0-cluster
+    image: victoriametrics/vminsert:v1.124.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -61,7 +61,7 @@ services:
       - "--storageNode=vmstorage-2:8400"
     restart: always
   vminsert-2:
-    image: victoriametrics/vminsert:v1.122.0-cluster
+    image: victoriametrics/vminsert:v1.124.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -73,7 +73,7 @@ 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:v1.122.0-cluster
+    image: victoriametrics/vmselect:v1.124.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -83,7 +83,7 @@ services:
       - "--vmalert.proxyURL=http://vmalert:8880"
     restart: always
   vmselect-2:
-    image: victoriametrics/vmselect:v1.122.0-cluster
+    image: victoriametrics/vmselect:v1.124.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -98,7 +98,7 @@ services:
   # read requests from Grafana, vmui, vmalert among vmselects.
   # It can be used as an authentication proxy.
   vmauth:
-    image: victoriametrics/vmauth:v1.122.0
+    image: victoriametrics/vmauth:v1.124.0
     depends_on:
       - "vmselect-1"
       - "vmselect-2"
@@ -112,7 +112,7 @@ services:
 
   # vmalert executes alerting and recording rules
   vmalert:
-    image: victoriametrics/vmalert:v1.122.0
+    image: victoriametrics/vmalert:v1.124.0
     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:v1.122.0
+    image: victoriametrics/vmagent:v1.124.0
     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:v1.122.0
+    image: victoriametrics/victoria-metrics:v1.124.0
     ports:
       - 8428:8428
       - 8089:8089
@@ -54,7 +54,7 @@ services:
 
   # vmalert executes alerting and recording rules
   vmalert:
-    image: victoriametrics/vmalert:v1.122.0
+    image: victoriametrics/vmalert:v1.124.0
     depends_on:
       - "victoriametrics"
       - "alertmanager"

deployment/docker/rules/alerts.yml

@@ -100,7 +100,7 @@ groups:
           summary: "Churn rate is more than 10% on \"{{ $labels.instance }}\" for the last 15m"
           description: "VM constantly creates new time series on \"{{ $labels.instance }}\".\n
             This effect is known as Churn Rate.\n
-            High Churn Rate tightly connected with database performance and may
+            High Churn Rate is tightly connected with database performance and may
             result in unexpected OOM's or slow queries."
 
       - alert: TooHighChurnRate24h
@@ -117,7 +117,7 @@ groups:
           description: "The number of created new time series over last 24h is 3x times higher than
             current number of active series on \"{{ $labels.instance }}\".\n
             This effect is known as Churn Rate.\n
-            High Churn Rate tightly connected with database performance and may
+            High Churn Rate is tightly connected with database performance and may
             result in unexpected OOM's or slow queries."
 
       - alert: TooHighSlowInsertsRate
@@ -135,4 +135,4 @@ groups:
           summary: "Percentage of slow inserts is more than 5% on \"{{ $labels.instance }}\" for the last 15m"
           description: "High rate of slow inserts on \"{{ $labels.instance }}\" may be a sign of resource exhaustion
             for the current load. It is likely more RAM is needed for optimal handling of the current number of active time series.
-            See also https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3976#issuecomment-1476883183"
+            See also https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3976#issuecomment-1476883183"

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

@@ -1,6 +1,6 @@
 services:
   vmagent:
-    image: victoriametrics/vmagent:v1.122.0
+    image: victoriametrics/vmagent:v1.124.0
     depends_on:
       - "victoriametrics"
     ports:
@@ -14,7 +14,7 @@ services:
     restart: always
 
   victoriametrics:
-    image: victoriametrics/victoria-metrics:v1.122.0
+    image: victoriametrics/victoria-metrics:v1.124.0
     ports:
       - 8428:8428
     volumes:
@@ -40,7 +40,7 @@ services:
     restart: always
 
   vmalert:
-    image: victoriametrics/vmalert:v1.122.0
+    image: victoriametrics/vmalert:v1.124.0
     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:v1.25.2
+    image: victoriametrics/vmanomaly:v1.25.3
     depends_on:
       - "victoriametrics"
     ports:

deployment/docker/vmanomaly/vmanomaly-node-exporter-preset/dashboard.json

@@ -1005,7 +1005,7 @@
           "refId": "A"
         }
       ],
-      "title": "Anoamlies: Read Latency",
+      "title": "Anomalies: Read Latency",
       "type": "state-timeline"
     },
     {

deployment/logs-benchmark/docker-compose-elk.yml

@@ -18,7 +18,7 @@ services:
       - vlogs
 
   generator:
-    image: golang:1.24.5-alpine
+    image: golang:1.25.0-alpine
     restart: always
     working_dir: /go/src/app
     volumes:

deployment/logs-benchmark/docker-compose-loki.yml

@@ -2,7 +2,7 @@ version: "3"
 
 services:
   generator:
-    image: golang:1.24.5-alpine
+    image: golang:1.25.0-alpine
     restart: always
     working_dir: /go/src/app
     volumes:

deployment/logs-benchmark/readme.md

@@ -4,12 +4,12 @@ Benchmark compares VictoriaLogs with ELK stack and Grafana Loki.
 
 Benchmark is based on:
 
-- Logs from this repository - https://github.com/logpai/loghub
+- Logs from this repository - [https://github.com/logpai/loghub](https://github.com/logpai/loghub)
 - [logs generator](./generator)
 
 For ELK suite it uses:
 
-- filebeat - https://www.elastic.co/beats/filebeat
+- filebeat - [https://www.elastic.co/beats/filebeat](https://www.elastic.co/beats/filebeat)
 - elastic + kibana
 
 For Grafana Loki suite it uses:
@@ -24,7 +24,7 @@ For Grafana Loki suite it uses:
 
 - VictoriaLogs instance
 - vmsingle - port forwarded to `localhost:8428` to see UI
-- exporters for system metris
+- exporters for system metrics
 
 ELK suite uses [docker-compose-elk.yml](./docker-compose-elk.yml) with the following services:
 
@@ -54,7 +54,7 @@ Each filebeat than writes logs to elastic and VictoriaLogs via elasticsearch-com
 1. Download and unarchive logs by running:
 
 ```shell
-cd source_logs 
+cd source_logs
 bash download.sh
 ```
 
@@ -74,11 +74,11 @@ Unarchived logs size per file for reference:
  13G hadoop-*.log
 ```
 
-2. (optional) If needed, adjust amount of logs sent by generator by modifying `-outputRateLimitItems` and
+1. (optional) If needed, adjust amount of logs sent by generator by modifying `-outputRateLimitItems` and
    `outputRateLimitPeriod` parameters in [docker-compose.yml](./docker-compose.yml). By default, it is configured to
    send 10000 logs per second.
 
-3. (optional) Build victoria-logs image and adjust `image` parameter in [docker-compose.yml](./docker-compose.yml):
+1. (optional) Build victoria-logs image and adjust `image` parameter in [docker-compose.yml](./docker-compose.yml):
 
 ```shell
 make package-victoria-logs
@@ -95,26 +95,27 @@ output.elasticsearch:
   hosts: [ "http://vlogs:9428/insert/elasticsearch/" ]
 ```
 
-4. Choose a suite to run.
+1. Choose a suite to run.
 
    In order to run ELK suite use the following command:
-   ```
+
+   ```sh
    make docker-up-elk
    ```
+
    In order to run Loki suite use the following command:
-   ```
+
+   ```sh
    make docker-up-loki
    ```
 
-
-5. Navigate to `http://localhost:3000/` to see Grafana dashboards with resource usage
+1. Navigate to `http://localhost:3000/` to see Grafana dashboards with resource usage
    comparison.
 
    Navigate to `http://localhost:3000/d/hkm6P6_4z/elastic-vs-vlogs` to see ELK suite results.
 
    Navigate to `http://localhost:3000/d/hkm6P6_4y/loki-vs-vlogs` to see Loki suite results.
 
-
 Example results vs ELK:
 
 ![elk-grafana-dashboard.png](results/elk-grafana-dashboard.png)

docs/anomaly-detection/CHANGELOG.md

@@ -14,6 +14,19 @@ aliases:
 ---
 Please find the changelog for VictoriaMetrics Anomaly Detection below.
 
+## v1.25.3
+Released: 2025-08-19
+
+- FEATURE: Added forecasting capabilities to the [`ProphetModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet) this allows users to generate *future* (point-wise and interval) predictions with offsets defined by `forecast_at` argument (e.g. `['1d', '1w']`) at *current* timestamp and store these in respective series, e.g. `yhat_1d`, `yhat_lower_1d`, `yhat_upper_1d`, etc. This feature is particularly useful for scenarios where future predictions are needed, such as capacity planning or trend analysis. See [FAQ](https://docs.victoriametrics.com/anomaly-detection/faq/#forecasting) for more details.
+
+- IMPROVEMENT: Added `logger_levels` argument to `settings` [config section](https://docs.victoriametrics.com/anomaly-detection/components/settings/#logger-levels) to allow setting specific log levels for individual components. Useful for debugging specific components. For example, `logger_levels: { "reader.vm": "DEBUG" }` will set the log level for the `VmReader` component to `DEBUG`, while leaving other components at their default log levels. Also is supported in [hot reload](https://docs.victoriametrics.com/anomaly-detection/components/#hot-reload) mode, allowing for dynamic log level changes without service restarts.
+
+- IMPROVEMENT: Added logging of URLs used for querying VictoriaMetrics TSDB in [`VmReader`](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader) to ease the debugging of incomplete data retrieval, incorrect endpoints, or misconfigured tenant IDs. The URLs are logged at the `DEBUG` level, so you can control their verbosity using the `--loggerLevelComponents` argument with `reader.vm=DEBUG` or `reader=DEBUG` to see the URLs in the logs.
+
+- IMPROVEMENT: Added `offset` [argument](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader) to `VmReader` on reader and query levels to allow for flexible time offset adjustments in the reader. Useful for correcting for data collection delays. The `offset` can be specified as a string (e.g., "15s", "-20s") and will be applied to all queries processed by the reader. See [FAQ](https://docs.victoriametrics.com/anomaly-detection/faq/#using-offsets) for more details.
+
+- BUGFIX: Resolved the issue where symlink-ed configuration files were not properly processed by [hot reload](https://docs.victoriametrics.com/anomaly-detection/components/#hot-reload) mechanism, leading to the service not picking up changes made to the original files. Now it properly resolves symlinks and reloads the configuration when the original file is modified.
+
 ## v1.25.2
 Released: 2025-07-30
 

docs/anomaly-detection/FAQ.md

@@ -54,6 +54,25 @@ Respective config is defined in a [`reader`](https://docs.victoriametrics.com/an
 ## Handling noisy input data
 `vmanomaly` operates on data fetched from VictoriaMetrics using [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/) queries, so the initial data quality can be fine-tuned with aggregation, grouping, and filtering to reduce noise and improve anomaly detection accuracy.
 
+## Using offsets
+`vmanomaly` supports {{% available_from "v1.25.3" anomaly %}} the use of offsets in the [`reader`](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader) section to adjust the time range of the data being queried. This can be particularly useful for correcting for data collection delays or other timing issues. It can be also defined or overridden on [per-query basis](https://docs.victoriametrics.com/anomaly-detection/components/reader/#per-query-parameters).
+
+For example, if you want to query data with a 60-second delay (e.g. data collection happened 1 sec ago, however, timestamps written to VictoriaMetrics are 60 seconds in the past), you can set the `offset` argument to `-60s` in the reader section:
+
+```yaml
+reader:
+  class: 'vm'
+  datasource_url: 'http://localhost:8428'
+  sampling_period: '10s'
+  offset: '-60s'
+  queries:
+    vmb:
+      expr: 'avg(vm_blocks)'
+    cpu_custom_offset:
+      expr: 'avg(rate(vm_cpu_usage[5m]))'
+      offset: '-30s'  # this will override the global offset for this query only
+```
+
 ## Handling timezones
 
 `vmanomaly` supports timezone-aware anomaly detection {{% available_from "v1.18.0" anomaly %}} through a `tz` argument, available both at the [reader level](https://docs.victoriametrics.com/anomaly-detection/components/reader#vm-reader) and at the [query level](https://docs.victoriametrics.com/anomaly-detection/components/reader/#per-query-parameters).
@@ -179,6 +198,22 @@ While `vmanomaly` detects anomalies and produces scores, it *does not directly g
 
 <img src="https://docs.victoriametrics.com/anomaly-detection/guides/guide-vmanomaly-vmalert/guide-vmanomaly-vmalert_overview.webp" alt="node_exporter_example_diagram" style="width:60%"/>
 
+Once anomaly scores are written back to VictoriaMetrics, you can use [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/) expressions subset in `vmalert` to define alerting rules based on these scores. Reasonable defaults are `anomaly_score > 1`:
+
+```yaml
+groups:
+- name: vmanomaly_alerts
+  rules:
+  - alert: HighAnomalyScore
+    expr: anomaly_score > 1  # or similar expressions, like `min(anomaly_score{...}) by (...) > 1`
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Anomaly score > 1 for {{ $labels.for }} query"
+      description: "Anomaly score is {{ $value }} for query {{ $labels.for }}. Value: {{ $value }}."
+```
+
 ## Preventing alert fatigue
 Produced anomaly scores are designed in such a way that values from 0.0 to 1.0 indicate non-anomalous data, while a value greater than 1.0 is generally classified as an anomaly. However, there are no perfect models for anomaly detection, that's why reasonable defaults expressions like `anomaly_score > 1` may not work 100% of the time. However, anomaly scores, produced by `vmanomaly` are written back as metrics to VictoriaMetrics, where tools like [`vmalert`](https://docs.victoriametrics.com/victoriametrics/vmalert/) can use [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/) expressions to fine-tune alerting thresholds and conditions, balancing between avoiding [false negatives](https://victoriametrics.com/blog/victoriametrics-anomaly-detection-handbook-chapter-1/#false-negative) and reducing [false positives](https://victoriametrics.com/blog/victoriametrics-anomaly-detection-handbook-chapter-1/#false-positive).
 
@@ -228,6 +263,117 @@ writer:
 
 Configuration above will produce N intervals of full length (`fit_window`=14d + `fit_every`=1h) until `to_iso` timestamp is reached to run N consecutive `fit` calls to train models; Then these models will be used to produce `M = [fit_every / sampling_frequency]` infer datapoints for `fit_every` range at the end of each such interval, imitating M consecutive calls of `infer_every` in `PeriodicScheduler` [config](https://docs.victoriametrics.com/anomaly-detection/components/scheduler#periodic-scheduler). These datapoints then will be written back to VictoriaMetrics TSDB, defined in `writer` [section](https://docs.victoriametrics.com/anomaly-detection/components/writer#vm-writer) for further visualization (i.e. in VMUI or Grafana)
 
+## Forecasting
+
+Not intended for forecasting in its core, `vmanomaly` can still be used to produce forecasts using [ProphetModel](https://docs.victoriametrics.com/anomaly-detection/components/models#prophet) {{% available_from "v1.25.3" anomaly %}}, which can be helpful in scenarios like capacity planning, resource allocation, or trend analysis, if the underlying data is complex and can't be handled by inline MetricsQL queries, including [predict_linear](https://docs.victoriametrics.com/victoriametrics/metricsql/#predict_linear).
+
+> However, please note that this mode should be used with care, as the model will produce `yhat_{h}` (and probably `yhat_lower_{h}`, and `yhat_upper_{h}`) time series **for each timeseries returned by input queries and for each forecasting horizon specified in `forecast_at` argument, which can lead to a significant increase in the number of active timeseries in VictoriaMetrics TSDB**.
+
+Here's an example of how to produce forecasts using `vmanomaly` and combine it with the regular model, e.g. to estimate daily outcomes for a disk usage metric:
+
+```yaml
+# https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#periodic-scheduler
+schedulers:
+  periodic_5m:  # this scheduler will be used to produce anomaly scores each 5 minutes using "regular" simple model
+    class: 'periodic'
+    fit_every: '30d'
+    fit_window: '3d'
+    infer_every: '5m'
+  periodic_forecast:  # this scheduler will be used to produce forecasts each 24h using "daily" model
+    class: 'periodic'
+    fit_every: '7d'
+    fit_window: '730d' # to fit the model on 2 years of data to account for seasonality and holidays
+    infer_every: '24h'
+# https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader
+reader:
+  class: 'vm'
+  datasource_url: 'http://play.victoriametrics.com'
+  tenant_id: '0:0'
+  sampling_period: '5m'
+  # other reader params ...
+  queries:
+    disk_usage_perc_5m:
+      expr: |
+        max_over_time(
+          1 - (node_filesystem_avail_bytes{mountpoint="/",fstype!="rootfs"} 
+          / 
+          node_filesystem_size_bytes{mountpoint="/",fstype!="rootfs"}),
+          1h
+        )
+      data_range: [0, 1]
+      # step: '1m'  # default will be inherited from sampling_period
+    disk_usage_perc_1d:
+      expr: |
+        max_over_time(
+          1 - (node_filesystem_avail_bytes{mountpoint="/",fstype!="rootfs"} 
+          / 
+          node_filesystem_size_bytes{mountpoint="/",fstype!="rootfs"}),
+          24h
+        )
+      step: '1d'  # override default step to 1d, as we want to produce daily forecasts
+      data_range: [0, 1]
+# https://docs.victoriametrics.com/anomaly-detection/components/models/
+models:
+  quantile_5m:
+    class: 'quantile_online'  # online model, which updates itself each infer call
+    queries: ['disk_usage_perc_5m']
+    schedulers: ['periodic_5m']
+    clip_predictions: True
+    detection_direction: 'above_expected'  # as we are interested in spikes in capacity planning
+    quantiles: [0.25, 0.5, 0.75]  # to produce median and upper quartiles
+    iqr_threshold: 2.0
+
+  prophet_1d:
+    class: 'prophet'
+    queries: ['disk_usage_perc_1d']
+    schedulers: ['periodic_forecast']
+    clip_predictions: True
+    detection_direction: 'above_expected'  # as we are interested in spikes in capacity planning
+    forecast_at: ['3d', '7d']  # this will produce forecasts for 3 and 7 days ahead
+    provide_series: ['yhat', 'yhat_upper']  # to write forecasts back to VictoriaMetrics, omitting `yhat_lower` as it is not needed in this example
+    # other model params, yearly_seasonality may stay
+    # https://facebook.github.io/prophet/docs/quick_start#python-api
+    args:
+      interval_width: 0.98  # see https://facebook.github.io/prophet/docs/uncertainty_intervals
+      country_holidays: 'US'
+# https://docs.victoriametrics.com/anomaly-detection/components/writer/#vm-writer
+writer:
+  class: 'vm'
+  datasource_url: '{your_victoriametrics_url_for_writing}'
+  # tenant_id: '0:0' # or your tenant ID if using clustered VictoriaMetrics
+  # other writer params ...
+  # https://docs.victoriametrics.com/anomaly-detection/components/writer/#metrics-formatting
+  metric_format:
+    __name__: $VAR
+    for: $QUERY_KEY
+```
+
+Then, respective alerts can be configured in [`vmalert`](https://docs.victoriametrics.com/victoriametrics/vmalert/) to notify disk exhaustion risks, e.g. if the forecasted disk usage exceeds 90% in the next 3 days:
+
+```yaml
+groups:
+- name: disk_usage_alerts
+  rules:
+  - alert: DiskUsageHigh
+    expr: |
+      yhat_7d{for="disk_usage_perc_1d"} > 0.9
+    for: 24h
+    labels:
+      severity: critical
+    annotations:
+      summary: "Disk usage is forecasted to exceed 90% in the next 3 days"
+      description: "Disk usage is forecasted to exceed 90% in the next 3 days for instance {{ $labels.instance }}. Forecasted value: {{ $value }}."
+  - alert: DiskUsageCritical
+    expr: |
+      yhat_3d{for="disk_usage_perc_1d"} > 0.95
+    for: 24h
+    labels:
+      severity: critical
+    annotations:
+      summary: "Disk usage is forecasted to exceed 95% in the next 3 days"
+      description: "Disk usage is forecasted to exceed 95% in the next 3 days for instance {{ $labels.instance }}. Forecasted value: {{ $value }}."
+```
+
 ## Resource consumption of vmanomaly
 `vmanomaly` itself is a lightweight service, resource usage is primarily dependent on [scheduling](https://docs.victoriametrics.com/anomaly-detection/components/scheduler) (how often and on what data to fit/infer your models), [# and size of timeseries returned by your queries](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader), and the complexity of the employed [models](https://docs.victoriametrics.com/anomaly-detection/components/models). Its resource usage is directly related to these factors, making it adaptable to various operational scales. Various optimizations are available to balance between RAM usage, processing speed, and model capacity. These options are described in the sections below.
 
@@ -243,7 +389,7 @@ services:
   # ...
   vmanomaly:
     container_name: vmanomaly
-    image: victoriametrics/vmanomaly:v1.25.2
+    image: victoriametrics/vmanomaly:v1.25.3
     # ...
     ports:
       - "8490:8490"
@@ -456,7 +602,7 @@ 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:v1.25.2 && docker image tag victoriametrics/vmanomaly:v1.25.2 vmanomaly
+docker pull victoriametrics/vmanomaly:v1.25.3 && docker image tag victoriametrics/vmanomaly:v1.25.3 vmanomaly
 ```
 
 ```sh

docs/anomaly-detection/QuickStart.md

@@ -121,13 +121,13 @@ Below are the steps to get `vmanomaly` up and running inside a Docker container:
 1. Pull Docker image:
 
 ```sh
-docker pull victoriametrics/vmanomaly:v1.25.2
+docker pull victoriametrics/vmanomaly:v1.25.3
 ```
 
 2. (Optional step) tag the `vmanomaly` Docker image:
 
 ```sh
-docker image tag victoriametrics/vmanomaly:v1.25.2 vmanomaly
+docker image tag victoriametrics/vmanomaly:v1.25.3 vmanomaly
 ```
 
 3. Start the `vmanomaly` Docker container with a *license file*, use the command below.
@@ -163,7 +163,7 @@ docker run -it --user 1000:1000 \
 services:
   # ...
   vmanomaly:
-    image: victoriametrics/vmanomaly:v1.25.2
+    image: victoriametrics/vmanomaly:v1.25.3
     volumes:
         $YOUR_LICENSE_FILE_PATH:/license
         $YOUR_CONFIG_FILE_PATH:/config.yml
@@ -220,6 +220,14 @@ settings:
   n_workers: 4  # number of workers to run workload in parallel, set to 0 or negative number to use all available CPU cores
   anomaly_score_outside_data_range: 5.0  # default anomaly score for anomalies outside expected data range
   restore_state: True  # restore state from previous run, available since v1.24.0
+  # https://docs.victoriametrics.com/anomaly-detection/components/settings/#logger-levels
+  # to override service-global logger levels, use the `logger_levels` section
+  logger_levels:  
+    # vmanomaly: info
+    # scheduler: info
+    # reader: info
+    # writer: info
+    model.prophet: warning
 
 schedulers:
   1d_1m:
@@ -299,6 +307,9 @@ For optimal service behavior, consider the following tweaks when configuring `vm
 - Set up [anomaly score dashboard](https://docs.victoriametrics.com/anomaly-detection/presets/#grafana-dashboard) to visualize the results of anomaly detection.
 - Set up [self-monitoring dashboard](https://docs.victoriametrics.com/anomaly-detection/self-monitoring/) to monitor the health of `vmanomaly` service and its components.
 
+**Logging**:
+- Tune logging levels in the `settings.logger_levels` [section](https://docs.victoriametrics.com/anomaly-detection/components/settings/#logger-levels) to control the verbosity of logs. This can help in debugging and monitoring the service behavior, as well as in disabling excessive logging for production environments.
+
 ## Check also
 
 Please refer to the following links for a deeper understanding of Anomaly Detection and `vmanomaly`:

docs/anomaly-detection/components/models.md

@@ -652,7 +652,7 @@ models:
 
 > `ProphetModel` is a [univariate](#univariate-models), [non-rolling](#non-rolling-models), [offline](#offline-models) model.
 
-> {{% available_from "v1.18.2" anomaly %}} the format for `tz_seasonalities` has been updated to enhance flexibility. Previously, it accepted a list of strings (e.g., `['hod', 'minute']`). Now, it follows the same structure as custom seasonalities defined in the `seasonalities` argument (e.g., `{"name": "hod", "fourier_order": 5, "mode": "additive"}`). This change is backward-compatible, so older configurations will be automatically converted to the new format using default values.
+> {{% available_from "v1.25.3" anomaly %}} Producing forecasts for future timestamps is now supported. To enable this, set the `forecast_at` argument to a list of relative future offsets (e.g., `['1h', '1d']`). The model will then generate forecasts for these future timestamps, which can be useful for planning and resource allocation. Output series are affected by [provide_series](#provide-series) argument, which need to include at least `yhat` for point-wise forecasts (and `yhat_lower` or/and `yhat_upper` for respective confidence intervals). See the example below for more details.
 
 *Parameters specific for vmanomaly*:
 
@@ -661,7 +661,11 @@ models:
 - `scale`{{% available_from "v1.18.0" anomaly %}} (float): Is used to adjust the margins between `yhat` and [`yhat_lower`, `yhat_upper`]. New margin = `|yhat_* - yhat_lower| * scale`. Defaults to 1 (no scaling is applied). See `scale`[common arg](https://docs.victoriametrics.com/anomaly-detection/components/models/#scale) section for detailed instructions and 2-sided option.
 - `tz_aware`{{% available_from "v1.18.0" anomaly %}} (bool): Enables handling of timezone-aware timestamps. Default is `False`. Should be used with `tz_seasonalities` and `tz_use_cyclical_encoding` parameters.
 - `tz_seasonalities`{{% available_from "v1.18.0" anomaly %}} (list[dict]): Specifies timezone-aware seasonal components. Requires `tz_aware=True`. Supported options include `minute`, `hod` (hour of day), `dow` (day of week), and `month` (month of year). {{% available_from "v1.18.2" anomaly %}} users can configure additional parameters for each seasonality, such as `fourier_order`, `prior_scale`, and `mode`. For more details, please refer to the **Timezone-unaware** configuration example below.
+  > {{% available_from "v1.18.2" anomaly %}} the format for `tz_seasonalities` has been updated to enhance flexibility. Previously, it accepted a list of strings (e.g., `['hod', 'minute']`). Now, it follows the same structure as custom seasonalities defined in the `seasonalities` argument (e.g., `{"name": "hod", "fourier_order": 5, "mode": "additive"}`). This change is backward-compatible, so older configurations will be automatically converted to the new format using default values.
 - `tz_use_cyclical_encoding`{{% available_from "v1.18.0" anomaly %}} (bool): If set to `True`, applies [cyclical encoding technique](https://www.kaggle.com/code/avanwyk/encoding-cyclical-features-for-deep-learning) to timezone-aware seasonalities. Should be used with `tz_aware=True` and `tz_seasonalities`.
+- `forecast_at`{{% available_from "v1.25.3" anomaly %}} (list[str]): Specifies future relative offsets for which forecasts should be generated (e.g., `['1h', '1d']`). Works similarly to [predict_linear](https://docs.victoriametrics.com/victoriametrics/metricsql/#predict_linear) in MetricQL, but with more flexibility and seasonality support - produced series will have *the same timestamp* as the other [output](#vmanomaly-output) series, but with the forecasted value for the *future timestamp*. Defaults to `[]` (empty list, meaning no future forecasts are produced). If set, `provide_series` must include at least `yhat` for point-wise forecasts (and `yhat_lower` or/and `yhat_upper` for respective confidence intervals). For example, if `forecast_at` is set to `['1h', '1d']`, the model will produce forecasts for both the next hour and the next day, and these series can be accessed by `yhat_1h`, `yhat_lower_1h`, `yhat_upper_1h`, `yhat_1d`, `yhat_lower_1d`, and `yhat_upper_1d` in the output, respectively. See [FAQ](https://docs.victoriametrics.com/anomaly-detection/faq/#forecasting) for more details.
+
+> `forecast_at` parameter can lead to **significant increase in active timeseries** if you have a lot of time series returned by your queries, as it will produce additional series for each of the future timestamps specified in `forecast_at` (optionally multiplied by 1-3 if interval forecasts are included). For example, if you have 1000 time series returned by your query and set `forecast_at` to `[1h, 1d, 1w]`, and `provide_series` includes `yhat_lower` and `yhat_upper`, it will produce 1000 (series) * 3 (intervals) * 3 (predictions, point + interval) = 9000 additional timeseries. Consider using it only on small subset of metrics (e.g. grouped by `host` or `region`) to avoid this issue, as it also **proportionally (to the number of `forecast_at` elements) increases the timings of inference calls**.
 
 > Apart from standard [`vmanomaly` output](#vmanomaly-output), Prophet model can provide additional metrics.
 
@@ -1308,7 +1312,7 @@ monitoring:
 Let's pull the docker image for `vmanomaly`:
 
 ```sh
-docker pull victoriametrics/vmanomaly:v1.25.2
+docker pull victoriametrics/vmanomaly:v1.25.3
 ```
 
 Now we can run the docker container putting as volumes both config and model file:
@@ -1322,7 +1326,7 @@ docker run -it \
 -v $(PWD)/license:/license \
 -v $(PWD)/custom_model.py:/vmanomaly/model/custom.py \
 -v $(PWD)/custom.yaml:/config.yaml \
-victoriametrics/vmanomaly:v1.25.2 /config.yaml \
+victoriametrics/vmanomaly:v1.25.3 /config.yaml \
 --licenseFile=/license
 ```
 

docs/anomaly-detection/components/reader.md

@@ -85,14 +85,18 @@ There is change{{% available_from "v1.13.0" anomaly %}} of [`queries`](https://d
 
   > The recommended approach for using per-query `tenant_id`s is to set both `reader.tenant_id` and `writer.tenant_id` to `multitenant`. See [this section](https://docs.victoriametrics.com/anomaly-detection/components/writer/#multitenancy-support) for more details. Configurations where `reader.tenant_id` equals `writer.tenant_id` and is not `multitenant` are also considered safe, provided there is a single, DISTINCT `tenant_id` defined in the reader (either at the reader level or the query level, if set).
 
+- `offset` {{% available_from "v1.25.3" anomaly %}} (string): this optional argument allows specifying a time offset for the query, which can be useful for adjusting the query time range to account for data collection delays or other timing issues. The offset is specified as a string (e.g., "15s", "-20s") and will be applied to the query time range. Valid resolutions are `ms`, `s`, `m`, `h`, `d` (miliseconds, seconds, minutes, hours, days). If not set, defaults to `0s` (0). See [FAQ](https://docs.victoriametrics.com/anomaly-detection/faq/#using-offsets) for more details.
+
 ### Per-query config example
 ```yaml
 reader:
   class: 'vm'
   sampling_period: '1m'
+  datasource_url: 'https://play.victoriametrics.com/'  # source victoriametrics/prometheus
   max_points_per_query: 10000
   data_range: [0, 'inf']
   tenant_id: 'multitenant'
+  offset: '0s'  # optional, defaults to 0s if not set
   # other reader params ...
   queries:
     ingestion_rate_t1:
@@ -109,6 +113,7 @@ reader:
       max_points_per_query: 5000 # overrides reader-level value of 10000 for `ingestion_rate` query
       tz: 'America/New_York'  # to override reader-wise `tz`
       tenant_id: '2:0'  # overriding tenant_id to isolate data
+      offset: '-15s'  # to override reader-wise `offset` and query data 15 seconds earlier to account for data collection delays
 ```
 
 ### Config parameters
@@ -395,10 +400,24 @@ Optional argument{{% available_from "v1.18.0" anomaly %}} specifies the [IANA](h
 Optional argument{{% available_from "v1.18.1" anomaly %}} allows defining **valid** data ranges for input of all the queries in `queries`. Defaults to `["-inf", "inf"]` if not set and can be overridden on a [per-query basis](#per-query-parameters).
             </td>
         </tr>
+        <tr>
+            <td>
+
+<span style="white-space: nowrap;">`offset`</span>
+            </td>
+            <td>
+
+`60s`
+            </td>
+            <td>
+Optional argument{{% available_from "v1.25.3" anomaly %}} allows specifying a time offset for all queries in `queries`. Defaults to `0s` (0) if not set and can be overridden on a [per-query basis](#per-query-parameters).
+            </td>
+        </tr>
     </tbody>
 </table>
 
-Config file example:
+<br>
+Config section example:
 
 ```yaml
 reader:
@@ -407,6 +426,7 @@ reader:
   tenant_id: '0:0'
   tz: 'America/New_York'
   data_range: [1, 'inf']  # reader-level
+  offset: '0s'  # reader-level
   queries:
     ingestion_rate:
       expr: 'sum(rate(vm_rows_inserted_total[5m])) by (type) > 0'
@@ -414,6 +434,7 @@ reader:
       data_range: [0, 'inf']  # if set, overrides reader-level data_range
       tz: 'Australia/Sydney'  # if set, overrides reader-level tz
       # tenant_id: '1:0'  # if set, overrides reader-level tenant_id
+      # offset: '-15s'  # if set, overrides reader-level offset
   sampling_period: '1m'
   query_from_last_seen_timestamp: True  # false by default
   latency_offset: '1ms'

docs/anomaly-detection/components/settings.md

@@ -305,3 +305,27 @@ reader:  # can be partially reused, because its class and datasource URL are unc
 This means that the service upon restart:
 1. Won't restore the state of `zscore_online` model, because its `z_threshold` argument **has changed**, retraining from scratch is needed on the last `fit_window` = 24 hours of data for `q1`, `q2` and `q3` (as model's `queries` arg is not set so it defaults to all queries found in the reader).
 2. Will **partially** restore the state of `prophet` model, because its class and schedulers are unchanged, but **only instances trained on timeseries returned by `q1` query**. New fit/infer jobs will be set for new query `q3`. The old query `q2` artifacts will be dropped upon restart - all respective models and data for (`prophet`, `q2`) combination will be removed from the database file and from the disk.
+
+
+### Logger Levels
+
+{{% available_from "v1.25.3" anomaly %}} `vmanomaly` service supports per-component logger levels, allowing to control the verbosity of logs for each component independently. This can be useful for debugging or monitoring specific components without overwhelming the logs with information from other components. Prefixes are also supported, allowing to set the logger level for all components with a specific prefix.
+
+The logger levels can be set in the `settings` section of the config file under `logger_levels` key, where the key is the component name or prefix and the value is the desired logger level. The available logger levels are: `debug`, `info`, `warning`, `error`, and `critical`.
+
+> Best used in combination with [hot-reload](https://docs.victoriametrics.com/anomaly-detection/components/#hot-reload) to change the logger levels *on-the-fly* without restarting the service through a short-circuit config check than doesn't even trigger the state restoration logic.
+
+Here's an example configuration that sets the logger level for the `reader` component to `debug` and for the `writer` component to `critical`, while `--loggerLevel` [command line argument](https://docs.victoriametrics.com/anomaly-detection/quickstart/#command-line-arguments) sets the default logger level to `INFO` for all (the other) components, unless overridden by the config:
+
+> If commented out in hot-reload mode during hot-reload event, the logger level for the component will be set back to what `--loggerLevel` command line argument is set to, which defaults to `info` if not specified.
+
+```yaml
+settings:
+  n_workers: 4
+  restore_state: True  # enables state restoration
+  logger_levels:
+    reader.vm: debug  # affects only VmReader logs
+    model: warning  # applies to all components with 'model' prefix, such as 'model.zscore_online', 'model.prophet', etc.
+    # once commented out in hot-reload mode, will use the default logger level set by --loggerLevel command line argument
+    # monitoring.push: critical
+```

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

@@ -2,9 +2,9 @@
 
 - To use *vmanomaly*, part of the enterprise package, a license key is required. Obtain your key [here](https://victoriametrics.com/products/enterprise/trial/) for this tutorial or for enterprise use.
 - In the tutorial, we'll be using the following VictoriaMetrics components:
-  -  [VictoriaMetrics Single-Node](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) (v1.122.0)
-  -  [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/) (v1.122.0)
-  -  [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) (v1.122.0)
+  -  [VictoriaMetrics Single-Node](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) (v1.124.0)
+  -  [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/) (v1.124.0)
+  -  [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) (v1.124.0)
 - [Grafana](https://grafana.com/) (v.10.2.1)
 - [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/)
 - [Node exporter](https://github.com/prometheus/node_exporter#node-exporter) (v1.7.0) and [Alertmanager](https://prometheus.io/docs/alerting/latest/alertmanager/) (v0.27.0)
@@ -315,7 +315,7 @@ Let's wrap it all up together into the `docker-compose.yml` file.
 services:
   vmagent:
     container_name: vmagent
-    image: victoriametrics/vmagent:v1.122.0
+    image: victoriametrics/vmagent:v1.124.0
     depends_on:
       - "victoriametrics"
     ports:
@@ -332,7 +332,7 @@ services:
 
   victoriametrics:
     container_name: victoriametrics
-    image: victoriametrics/victoria-metrics:v1.122.0
+    image: victoriametrics/victoria-metrics:v1.124.0
     ports:
       - 8428:8428
     volumes:
@@ -365,7 +365,7 @@ services:
 
   vmalert:
     container_name: vmalert
-    image: victoriametrics/vmalert:v1.122.0
+    image: victoriametrics/vmalert:v1.124.0
     depends_on:
       - "victoriametrics"
     ports:
@@ -387,7 +387,7 @@ services:
     restart: always
   vmanomaly:
     container_name: vmanomaly
-    image: victoriametrics/vmanomaly:v1.25.2
+    image: victoriametrics/vmanomaly:v1.25.3
     depends_on:
       - "victoriametrics"
     ports:

docs/guides/grafana-vmgateway-openid-configuration/README.md

@@ -241,27 +241,27 @@ services:
       - grafana_data:/var/lib/grafana/
 
   vmsingle:
-    image: victoriametrics/victoria-metrics:v1.122.0
+    image: victoriametrics/victoria-metrics:v1.124.0
     command:
       - -httpListenAddr=0.0.0.0:8429
 
   vmstorage:
-    image: victoriametrics/vmstorage:v1.122.0-cluster
+    image: victoriametrics/vmstorage:v1.124.0-cluster
 
   vminsert:
-    image: victoriametrics/vminsert:v1.122.0-cluster
+    image: victoriametrics/vminsert:v1.124.0-cluster
     command:
       - -storageNode=vmstorage:8400
       - -httpListenAddr=0.0.0.0:8480
 
   vmselect:
-    image: victoriametrics/vmselect:v1.122.0-cluster
+    image: victoriametrics/vmselect:v1.124.0-cluster
     command:
       - -storageNode=vmstorage:8401
       - -httpListenAddr=0.0.0.0:8481
 
   vmagent:
-    image: victoriametrics/vmagent:v1.122.0
+    image: victoriametrics/vmagent:v1.124.0
     volumes:
       - ./scrape.yaml:/etc/vmagent/config.yaml
     command:
@@ -270,7 +270,7 @@ services:
       - -remoteWrite.url=http://vmsingle:8429/api/v1/write
 
   vmgateway-cluster:
-    image: victoriametrics/vmgateway:v1.122.0-enterprise
+    image: victoriametrics/vmgateway:v1.124.0-enterprise
     ports:
       - 8431:8431
     volumes:
@@ -286,7 +286,7 @@ services:
       - -auth.oidcDiscoveryEndpoints=http://keycloak:8080/realms/master/.well-known/openid-configuration
 
   vmgateway-single:
-    image: victoriametrics/vmgateway:v1.122.0-enterprise
+    image: victoriametrics/vmgateway:v1.124.0-enterprise
     ports:
       - 8432:8431
     volumes:
@@ -397,7 +397,7 @@ Once iDP configuration is done, vmagent configuration needs to be updated to use
 
 ```yaml
   vmagent:
-    image: victoriametrics/vmagent:v1.122.0
+    image: victoriametrics/vmagent:v1.124.0
     volumes:
       - ./scrape.yaml:/etc/vmagent/config.yaml
       - ./vmagent-client-secret:/etc/vmagent/oauth2-client-secret

docs/victoriametrics/Articles.md

@@ -104,6 +104,8 @@ Articles about VictoriaLogs have been moved at [https://docs.victoriametrics.com
 
 ## Our articles
 
+See [our blog](https://victoriametrics.com/blog) for the latest articles written by the Victoriametrics team
+
 ### Announcements
 
 * [Open-source strategy at VictoriaMetrics](https://www.youtube.com/watch?v=-DbbIZzFHIY)

docs/victoriametrics/Cluster-VictoriaMetrics.md

@@ -373,6 +373,8 @@ The multi-level cluster setup for `vminsert` nodes has the following shortcoming
 These issues are addressed by [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) when it runs in [multitenancy mode](https://docs.victoriametrics.com/victoriametrics/vmagent/#multitenancy).
 `vmagent` buffers data, which must be sent to a particular AZ, when this AZ is temporarily unavailable. The buffer is stored on disk. The buffered data is sent to AZ as soon as it becomes available.
 
+See the [cluster instability troubleshooting guide](https://docs.victoriametrics.com/victoriametrics/troubleshooting/#cluster-instability) for details on diagnosing and mitigating networking problems.
+
 ### vmstorage groups at vmselect
 
 `vmselect` can be configured to query multiple distinct groups of `vmstorage` nodes with individual `-replicationFactor` per each group.
@@ -462,23 +464,22 @@ for sending data from `vminsert` to `vmstorage` node according to `-vminsertAddr
 
 The currently discovered `vmstorage` nodes can be [monitored](#monitoring) with `vm_rpc_vmstorage_is_reachable` and `vm_rpc_vmstorage_is_read_only` metrics.
 
+Discovery mechanism could be also used together with [vmstorage group](#vmstorage-groups-at-vmselect). Consider the following example:
+
+```bash
+/path/to/vmselect \
+  -globalReplicationFactor=2 \
+  -storageNode=g1/file:/path/to/file-with-vmstorage-list/ \      # Group g1: static list from file
+  -storageNode=g2/srv+vmstorage-autodiscovery \                  # Group g2: nodes discovered dynamically via SRV records
+  -storageNode=g3/host7,g3/host8,g3/host9                        # Group g3: statically defined hostnames
+```
+
+Each `-storageNode` parameter assigns one or more storage nodes to a specific group (e.g., `g1`, `g2`, `g3`).
+The automatically discovered nodes retain the [vmstorage group](#vmstorage-groups-at-vmselect) prefix to maintain consistent group mapping.
 
 ### Environment variables
 
-All the VictoriaMetrics components allow referring environment variables in command-line flags via `%{ENV_VAR}` syntax.
-For example, `-metricsAuthKey=%{METRICS_AUTH_KEY}` is automatically expanded to `-metricsAuthKey=top-secret`
-if `METRICS_AUTH_KEY=top-secret` environment variable exists at VictoriaMetrics startup.
-This expansion is performed by VictoriaMetrics itself.
-
-VictoriaMetrics recursively expands `%{ENV_VAR}` references in environment variables on startup.
-For example, `FOO=%{BAR}` environment variable is expanded to `FOO=abc` if `BAR=a%{BAZ}` and `BAZ=bc`.
-
-Additionally, all the VictoriaMetrics components allow setting flag values via environment variables according to these rules:
-
-- The `-envflag.enable` flag must be set
-- Each `.` in flag names must be substituted by `_` (for example `-insert.maxQueueDuration <duration>` will translate to `insert_maxQueueDuration=<duration>`)
-- For repeating flags, an alternative syntax can be used by joining the different values into one using `,` as separator (for example `-storageNode <nodeA> -storageNode <nodeB>` will translate to `storageNode=<nodeA>,<nodeB>`)
-- It is possible setting prefix for environment vars with `-envflag.prefix`. For instance, if `-envflag.prefix=VM_`, then env vars must be prepended with `VM_`
+See [these docs](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#environment-variables).
 
 ## Security
 
@@ -528,24 +529,19 @@ See how to request a free trial license [here](https://victoriametrics.com/produ
 
 ## Monitoring
 
-All the cluster components expose various metrics in Prometheus-compatible format at `/metrics` page on the TCP port set in `-httpListenAddr` command-line flag.
+All the cluster components [expose various metrics](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/deployment/docker/prometheus-vm-cluster.yml)
+in Prometheus-compatible format at `/metrics` page on the TCP port set in `-httpListenAddr` command-line flag. 
 By default, the following TCP ports are used:
 
 - `vminsert` - 8480
 - `vmselect` - 8481
 - `vmstorage` - 8482
 
-It is recommended setting up [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/)
-or Prometheus to scrape `/metrics` pages from all the cluster components, so they can be monitored and analyzed
-with [the official Grafana dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176).
-Graphs on these dashboards contain useful hints - hover the `i` icon at the top left corner of each graph in order to read it.
+> Prefer giving distinct scrape job names per each component type. I.e. `vmstorage`, `vminsert` and `vmselect` should have corresponding job names.
 
-If you use Google Cloud Managed Prometheus for scraping metrics from VictoriaMetrics components, then pass `-metrics.exposeMetadata`
-command-line to them, so they add `TYPE` and `HELP` comments per each exposed metric at `/metrics` page.
-See [these docs](https://cloud.google.com/stackdriver/docs/managed-prometheus/troubleshooting#missing-metric-type) for details.
+Use [the official Grafana dashboard for VictoriaMetrics cluster](https://grafana.com/grafana/dashboards/11176).
 
-It is recommended setting up alerts in [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/) or in Prometheus from [this list](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/deployment/docker#alerts).
-See more details in the article [VictoriaMetrics Monitoring](https://victoriametrics.com/blog/victoriametrics-monitoring/).
+See more details on [how to monitor VictoriaMetrics components](https://docs.victoriametrics.com/#monitoring).
 
 ## Cardinality limiter
 
@@ -1339,6 +1335,8 @@ Below is the output for `/path/to/vminsert -help`:
      Replication factor for the ingested data, i.e. how many copies to make among distinct -storageNode instances. Note that vmselect must run with -dedup.minScrapeInterval=1ms for data de-duplication when replicationFactor is greater than 1. Higher values for -dedup.minScrapeInterval at vmselect is OK (default 1)
   -rpc.disableCompression
      Whether to disable compression for the data sent from vminsert to vmstorage. This reduces CPU usage at the cost of higher network bandwidth usage
+  -rpc.handshakeTimeout duration
+     Timeout for RPC handshake between vminsert/vmselect and vmstorage. Increase this value if transient handshake failures occur. (default 5s)
   -search.denyPartialResponse
      Whether to deny partial responses if a part of -storageNode instances fail to perform queries; this trades availability over consistency; see also -search.maxQueryDuration
   -sortLabels
@@ -1580,6 +1578,8 @@ Below is the output for `/path/to/vmselect -help`:
   -replicationFactor array
      How many copies of every ingested sample is available across -storageNode nodes. vmselect continues returning full responses when up to replicationFactor-1 vmstorage nodes are temporarily unavailable. See also -globalReplicationFactor and -search.skipSlowReplicas (default 1)
      Supports an array of `key:value` entries separated by comma or specified via multiple flags.
+  -rpc.handshakeTimeout duration
+     Timeout for RPC handshake between vminsert/vmselect and vmstorage. Increase this value if transient handshake failures occur. (default 5s)
   -search.cacheTimestampOffset duration
      The maximum duration since the current time for response data, which is always queried from the original raw data, without using the response cache. Increase this value if you see gaps in responses due to time synchronization issues between VictoriaMetrics and data sources (default 5m0s)
   -search.denyPartialResponse
@@ -1626,6 +1626,8 @@ Below is the output for `/path/to/vmselect -help`:
      The maximum number of time series, which can be returned from /api/v1/export* APIs. This option allows limiting memory usage (default 10000000)
   -search.maxFederateSeries int
      The maximum number of time series, which can be returned from /federate. This option allows limiting memory usage (default 1000000)
+  -search.maxGraphitePathExpressionLen int
+     The maximum length of pathExpression field in Graphite series. Longer expressions are truncated to prevent memory exhaustion on complex nested queries. Set to 0 to disable truncation. (default 1024)
   -search.maxGraphiteSeries int
      The maximum number of time series, which can be scanned during queries to Graphite Render API. See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#render-api (default 300000)
   -search.maxGraphiteTagKeys int
@@ -1870,6 +1872,10 @@ Below is the output for `/path/to/vmstorage -help`:
      Interval for reloading the license file specified via -licenseFile. See https://victoriametrics.com/products/enterprise/ . This flag is available only in Enterprise binaries (default 1h0m0s)
   -logNewSeries
      Whether to log new series. This option is for debug purposes only. It can lead to performance issues when big number of new series are ingested into VictoriaMetrics
+  -logNewSeriesAuthKey value
+     authKey, which must be passed in query string to /internal/log_new_series. It overrides -httpAuth.*
+     Flag value can be read from the given file when using -logNewSeriesAuthKey=file:///abs/path/to/file or -logNewSeriesAuthKey=file://./relative/path/to/file .
+     Flag value can be read from the given http/https url when using -logNewSeriesAuthKey=http://host/path or -logNewSeriesAuthKey=https://host/path
   -loggerDisableTimestamps
      Whether to disable writing timestamps in logs
   -loggerErrorsPerSecondLimit int
@@ -1942,6 +1948,8 @@ Below is the output for `/path/to/vmstorage -help`:
      The offset for performing indexdb rotation. If set to 0, then the indexdb rotation is performed at 4am UTC time per each -retentionPeriod. If set to 2h, then the indexdb rotation is performed at 4am EET time (the timezone with +2h offset)
   -rpc.disableCompression
      Whether to disable compression of the data sent from vmstorage to vmselect. This reduces CPU usage at the cost of higher network bandwidth usage
+  -rpc.handshakeTimeout duration
+     Timeout for RPC handshake between vminsert/vmselect and vmstorage. Increase this value if transient handshake failures occur. (default 5s)
   -search.maxConcurrentRequests int
      The maximum number of concurrent vmselect requests the vmstorage can process at -vmselectAddr. It shouldn't be high, since a single request usually saturates a CPU core, and many concurrently executed requests may require high amounts of memory. See also -search.maxQueueDuration
   -search.maxQueueDuration duration

docs/victoriametrics/FAQ.md

@@ -29,6 +29,17 @@ See the full list of [Prominent Features](https://docs.victoriametrics.com/victo
 
 Yes. See [these benchmarks](https://docs.victoriametrics.com/victoriametrics/articles/#benchmarks).
 
+## How does Victoriametrics work?
+
+See the list of technical articles on VictoriaMetrics components:
+1. [How VictoriaMetrics Agent (**vmagent**) Works](https://victoriametrics.com/blog/vmagent-how-it-works)
+1. [How **vmstorage** Handles Data Ingestion](https://victoriametrics.com/blog/vmstorage-how-it-handles-data-ingestion)
+1. [How **vmstorage** Processes Data: Retention, Merging, Deduplication,...](https://victoriametrics.com/blog/vmstorage-retention-merging-deduplication)
+1. [When Metrics Meet **vminsert**: A Data-Delivery Story](https://victoriametrics.com/blog/vminsert-how-it-works)
+1. [How **vmstorage**'s IndexDB Works](https://victoriametrics.com/blog/vmstorage-how-indexdb-works)
+1. [How **vmstorage** Handles Query Requests From vmselect](https://victoriametrics.com/blog/vmstorage-how-it-handles-query-requests)
+1. [Inside **vmselect**: The Query Processing Engine of VictoriaMetrics](https://victoriametrics.com/blog/vmselect-how-it-works)
+
 ## How to start using VictoriaMetrics?
 
 Follow the [Quick Start guide](https://docs.victoriametrics.com/victoriametrics/quick-start/).

docs/victoriametrics/LTS-releases.md

@@ -27,5 +27,5 @@ to [the latest available releases](https://docs.victoriametrics.com/victoriametr
 
 ## Currently supported LTS release lines
 
-- v1.110.x - the latest one is [v1.110.14 LTS release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.110.14)
-- v1.102.x - the latest one is [v1.102.26 LTS release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.102.26)
+- v1.122.x - the latest one is [v1.122.2 LTS release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.122.2)
+- v1.110.x - the latest one is [v1.110.16 LTS release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.110.16)

docs/victoriametrics/Quick-Start.md

@@ -57,9 +57,9 @@ and performing [regular upgrades](https://docs.victoriametrics.com/victoriametri
 Download the newest available [VictoriaMetrics release](https://docs.victoriametrics.com/victoriametrics/changelog/)
 from [DockerHub](https://hub.docker.com/r/victoriametrics/victoria-metrics) or [Quay](https://quay.io/repository/victoriametrics/victoria-metrics?tab=tags):
 ```sh
-docker pull victoriametrics/victoria-metrics:v1.122.0
+docker pull victoriametrics/victoria-metrics:v1.124.0
 docker run -it --rm -v `pwd`/victoria-metrics-data:/victoria-metrics-data -p 8428:8428 \
- victoriametrics/victoria-metrics:v1.122.0 --selfScrapeInterval=5s -storageDataPath=victoria-metrics-data
+ victoriametrics/victoria-metrics:v1.124.0 --selfScrapeInterval=5s -storageDataPath=victoria-metrics-data
 ```
 _For Enterprise images see [this link](https://docs.victoriametrics.com/victoriametrics/enterprise/#docker-images)._
 

docs/victoriametrics/README.md

@@ -1,3 +1,9 @@
+---
+build:
+  list: never
+  publishResources: false
+  render: never
+---
 VictoriaMetrics is a fast, cost-effective and scalable monitoring solution and time series database.
 See [case studies for VictoriaMetrics](https://docs.victoriametrics.com/victoriametrics/casestudies/).
 
@@ -155,13 +161,14 @@ if `METRICS_AUTH_KEY=top-secret` environment variable exists at VictoriaMetrics
 This expansion is performed by VictoriaMetrics itself.
 
 VictoriaMetrics recursively expands `%{ENV_VAR}` references in environment variables on startup.
-For example, `FOO=%{BAR}` environment variable is expanded to `FOO=abc` if `BAR=a%{BAZ}` and `BAZ=bc`.
+For example, `FOO=%{BAR}` environment variable is expanded to `FOO=abc` if `BAR=a%{BAZ}` and `BAZ=bc` environment variables exist.
 
 Additionally, all the VictoriaMetrics components allow setting flag values via environment variables according to these rules:
 
 * The `-envflag.enable` flag must be set.
 * Each `.` char in flag name must be substituted with `_` (for example `-insert.maxQueueDuration <duration>` will translate to `insert_maxQueueDuration=<duration>`).
-* For repeating flags an alternative syntax can be used by joining the different values into one using `,` char as separator (for example `-storageNode <nodeA> -storageNode <nodeB>` will translate to `storageNode=<nodeA>,<nodeB>`).
+* Repated flags can be replaced by an environment variable with `,`-separted values for the repeated flags.
+  For example `-storageNode <nodeA> -storageNode <nodeB>` command-line flags can be set as `storageNode=<nodeA>,<nodeB>` environment variable.
 * Environment var prefix can be set via `-envflag.prefix` flag. For instance, if `-envflag.prefix=VM_`, then env vars must be prepended with `VM_`.
 
 ### Setting up service
@@ -942,7 +949,7 @@ Note that it could be required to flush response cache after importing historica
 
 ### How to import data in Prometheus exposition format
 
-VictoriaMetrics accepts data in [Prometheus exposition format](https://github.com/prometheus/docs/blob/master/content/docs/instrumenting/exposition_formats.md#text-based-format),
+VictoriaMetrics accepts data in [Prometheus exposition format](https://github.com/prometheus/docs/blob/main/docs/instrumenting/exposition_formats.md),
 in [OpenMetrics format](https://github.com/OpenObservability/OpenMetrics/blob/master/specification/OpenMetrics.md)
 and in [Pushgateway format](https://github.com/prometheus/pushgateway#url) via `/api/v1/import/prometheus` path.
 
@@ -1754,33 +1761,30 @@ mkfs.ext4 ... -O 64bit,huge_file,extent -T huge
 ## Monitoring
 
 VictoriaMetrics exports internal metrics in Prometheus exposition format at `/metrics` page.
-These metrics can be scraped via [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) or any other Prometheus-compatible scraper.
+These metrics [can be scraped](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/deployment/docker/prometheus-vm-single.yml)
+via [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) or any other Prometheus-compatible scraper.
 
-If you use Google Cloud Managed Prometheus for scraping metrics from VictoriaMetrics components, then pass `-metrics.exposeMetadata`
-command-line to them, so they add `TYPE` and `HELP` comments per each exposed metric at `/metrics` page.
-See [these docs](https://cloud.google.com/stackdriver/docs/managed-prometheus/troubleshooting#missing-metric-type) for details.
+> Single-node VictoriaMetrics can self-scrape its metrics when `-selfScrapeInterval` command-line flag is
+set to duration greater than 0. For example, `-selfScrapeInterval=10s` scrapes `/metrics` page every 10 seconds.
+ 
+See the list of official [Grafana dashboards for VictoriaMetrics components](https://grafana.com/orgs/victoriametrics/dashboards).
 
-Alternatively, single-node VictoriaMetrics can self-scrape the metrics when `-selfScrapeInterval` command-line flag is 
-set to duration greater than 0. For example, `-selfScrapeInterval=10s` would enable self-scraping of `/metrics` page 
-with 10 seconds interval.
+Please follow the monitoring recommendations below: 
 
-_Please note, never use loadbalancer address for scraping metrics. All the monitored components should be scraped directly by their address._
-
-Official Grafana dashboards available for [single-node](https://grafana.com/grafana/dashboards/10229)
-and [clustered](https://grafana.com/grafana/dashboards/11176) VictoriaMetrics.
-
-Graphs on the dashboards contain useful hints - hover the `i` icon in the top left corner of each graph to read it.
-
-We recommend setting up [alerts](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/deployment/docker#alerts)
+* Prefer giving distinct scrape job names per each component type. I.e. `vmagent` and `vmalert` should have corresponding job names.
+* Never use load balancer address for scraping metrics. All the monitored components should be scraped directly by their address.
+* Set up [recommended alerts](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/deployment/docker#alerts)
 via [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/) or via Prometheus.
-
-VictoriaMetrics exposes currently running queries and their execution times at [`active queries` page](#active-queries).
-
-VictoriaMetrics exposes queries, which take the most time to execute, at [`top queries` page](#top-queries).
+* See currently running queries and their execution times at [`active queries` page](#active-queries).
+* See queries that take the most time to execute at [`top queries` page](#top-queries).
 
 See also [VictoriaMetrics Monitoring](https://victoriametrics.com/blog/victoriametrics-monitoring/)
 and [troubleshooting docs](https://docs.victoriametrics.com/victoriametrics/troubleshooting/).
 
+> VictoriaMetrics components do not expose metadata `TYPE` and `HELP` fields on `/metrics` page.
+> Services like Google Cloud Managed Prometheus could require metadata to be present for scraping. In this case, pass `-metrics.exposeMetadata`
+command-line to them. See [these docs](https://cloud.google.com/stackdriver/docs/managed-prometheus/troubleshooting#missing-metric-type) for details.
+
 ## TSDB stats
 
 VictoriaMetrics returns TSDB stats at `/api/v1/status/tsdb` page in the way similar to Prometheus - see [these Prometheus docs](https://prometheus.io/docs/prometheus/latest/querying/api/#tsdb-stats). VictoriaMetrics accepts the following optional query args at `/api/v1/status/tsdb` page:
@@ -2801,6 +2805,8 @@ Pass `-help` to VictoriaMetrics in order to see the list of supported command-li
      The maximum number of time series, which can be returned from /api/v1/export* APIs. This option allows limiting memory usage (default 10000000)
   -search.maxFederateSeries int
      The maximum number of time series, which can be returned from /federate. This option allows limiting memory usage (default 1000000)
+  -search.maxGraphitePathExpressionLen int
+     The maximum length of pathExpression field in Graphite series. Longer expressions are truncated to prevent memory exhaustion on complex nested queries. Set to 0 to disable truncation. (default 1024)
   -search.maxGraphiteSeries int
      The maximum number of time series, which can be scanned during queries to Graphite Render API. See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#render-api (default 300000)
   -search.maxGraphiteTagKeys int

docs/victoriametrics/Troubleshooting.md

@@ -437,6 +437,19 @@ The most common sources of cluster instability are:
   If this can't be guaranteed, set `-sortLabels=true` cmd-line flag to `vminsert`. Please note, sorting may increase
   CPU usage for `vminsert`.
 
+- Network instability between cluster components (`vminsert`, `vmselect`, `vmstorage`) may lead to increased error rates, timeouts, or degraded performance. 
+  Check resource usage graphs for all components on [the official Grafana dashboard for VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#monitoring). 
+  If the graphs show high CPU usage, then the cluster is likely overloaded and requires more resources.
+  Note that short-lived 100% CPU spikes may not be visible in metrics with typical 10–30s scrape intervals, 
+  but can still cause transient network failures. In such cases, check CPU usage at the OS level with higher-resolution tools. 
+  Consider increasing `-vmstorageDialTimeout` and `-rpc.handshakeTimeout`{{% available_from "v1.124.0" %}} to mitigate the effects of CPU spikes.
+  
+  If resource usage looks normal but networking issues still occur, then the root cause is likely outside VictoriaMetrics.
+  This may be caused by unreliable or congested network links, especially across availability zones or regions. 
+  In multi-AZ setups, consider [a multi-level cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#multi-level-cluster-setup) with region-local load balancers to reduce cross-zone connections. 
+  If the network cannot be improved, increasing timeouts such as `-vmstorageDialTimeout`, `-rpc.handshakeTimeout`{{% available_from "v1.124.0" %}}, or `-search.maxQueueDuration` may help, but should be done cautiously, as higher timeouts can impact cluster stability in other ways.
+  Keep in mind that VictoriaMetrics assumes reliable networking between components. If the network is unstable, the overall cluster stability may degrade regardless of resource availability. 
+
 The obvious solution against VictoriaMetrics cluster instability is to make sure cluster components
 have enough free resources for graceful processing of the increased workload.
 See [capacity planning docs](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#capacity-planning)

docs/victoriametrics/_index.md

@@ -5,6 +5,7 @@ menu:
     weight: 10
     identifier: victoriametrics
     pageRef: "/"
+canonical: /victoriametrics/single-server-victoriametrics/
 tags:
   - metrics
 ---

docs/victoriametrics/changelog/CHANGELOG.md

@@ -1,3 +1,9 @@
+---
+build:
+  list: never
+  publishResources: false
+  render: never
+---
 The following `tip` changes can be tested by building VictoriaMetrics components from the latest commits according to the following docs:
 
 * [How to build single-node VictoriaMetrics](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-build-from-sources)
@@ -18,7 +24,32 @@ See also [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-rel
 
 ## tip
 
+* FEATURE: upgrade Go builder from Go1.24.6 to Go1.25. See [Go1.25 release notes](https://tip.golang.org/doc/go1.25).
+
+## [v1.124.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.124.0)
+
+Released at 2025-08-15
+
+* SECURITY: upgrade Go builder from Go1.24.5 to Go1.24.6. See [the list of issues addressed in Go1.24.6](https://github.com/golang/go/issues?q=milestone%3AGo1.24.6+label%3ACherryPickApproved).
+
+* FEATURE: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and [vmselect](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/) in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): protect graphite `/render` API endpoint with new flag `-search.maxGraphitePathExpressionLen`. See this PR [#9534](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/9534) for details.
 * FEATURE: expose `vm_total_disk_space_bytes` metric at the [`/metrics` page](https://docs.victoriametrics.com/#monitoring), which shows the total disk space for the data directory specified via [`-storageDataPath`](https://docs.victoriametrics.com/#storage). This metric can be useful for building alerts and graphs for the percentatge of free disk space via `vm_free_disk_space_bytes / vm_total_disk_space_bytes`. See [this comment](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/9523#issuecomment-3149459926).
+* FEATURE: all: leave non-existing environment variables as is in config files instead of failure. For example, if the file referred by `-promscrape.config` contains `%{NON_EXISTING_ENV_VAR}` placeholder, then it is left as is instead of failing to load the file. This simplifies the usage of environment variables in config files and in command-line flags according to [these docs](https://docs.victoriametrics.com/victoriametrics/#environment-variables). Users can easily notice non-existing env vars in config files and in command-line flags by looking at their values - they will literally contain `%{NON_EXISTING_ENV_VAR}` strings.
+* FEATURE: `vmselect`, `vminsert` and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): add rpc handshake timeout configuration via `-rpc.handshakeTimeout` flag (default 5s). Set deadline for the entire handshake process instead of per-operation timeout. See [#9345](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9345) for more details.
+* FEATURE: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/): add `-enableMetadata` command-line flag to allow sending metadata to the configured `-remoteWrite.url`, metadata can be scraped from targets, received via VictoriaMetrics remote write, Prometheus remote write v1 or OpenTelemetry protocol. See [#2974](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2974).
+
+* BUGFIX: [vmagent](https://docs.victoriametrics.com/vmagent/): treat single `remoteWrite.disableOnDiskQueue` flag the same way as if it is explicitly specified for each remote write url. See [#9565](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9565) for details.
+* BUGFIX: [vmalert-tool](https://docs.victoriametrics.com/victoriametrics/vmalert-tool/): print a proper error message when templating function fails during execution. Previously, vmalert-tool could throw a misleading panic message instead.
+* BUGFIX: [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/): properly read proxy-protocol header. See this PR [#9546](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/9546) for details.
+* BUGFIX: [dashboards/vmagent](https://grafana.com/grafana/dashboards/12683): fix samples rate panel not showing data in case vmagent is not scraping metrics. Previously, the panel would not display "samples in" results if vmagent only accepts metrics via push protocols.
+* BUGFIX: [vmselect](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/) in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): prevent resource leak on partial responses for `/federate` API requests. This this PR [9536](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/9536) for details. Thanks to the @fxrlv.
+* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): prevent performance degradation on hitting daily or hourly series cardinality limits. See this issue [9554](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9554) for details.
+* BUGFIX: [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/): gracefully handle `histogram_quantile` calculation for histograms where buckets are created on demand. This change isn't needed for users who use native instrumentation SDKs for metrics from [VictoriaMetrics](https://github.com/VictoriaMetrics/metrics), [Prometheus](https://prometheus.io/docs/instrumenting/clientlibs/) or [OpenTelemetry](https://opentelemetry.io/docs/languages/).
+* BUGFIX: [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/): return a proper error message when the function argument is expected to be a string or scalar.
+* BUGFIX: [dashboards/victoriametrics-cluster](https://grafana.com/grafana/dashboards/11176): fix panels showing 99th percentile of series or samples read per query or per series. Before, panels were showing the summarized value across all vmselect instances, which didn't make much sense. Now, panels show the max value across the vmselect instances, making it easier to understand complexity of the heaviest queries served.
+* BUGFIX: [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/): fix potential data race and missing firing states when replaying alerting rule with `-replay.ruleEvaluationConcurrency>1`.
+* BUGFIX: [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/): fix the `{{ $activeAt }}` variable value in annotation templating when the alert has already triggered. See this issue [#9543](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9543) for details.
+* BUGFIX: [vmbackup](https://docs.victoriametrics.com/vmbackup/), [vmbackupmanager](https://docs.victoriametrics.com/vmbackupmanager/): allow enabling checksum calculation for PUT requests by using `-s3ChecksumAlgorithm` command-line flag. This is required for S3 configurations with WORM being enabled. See [#9532](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9532).
 
 ## [v1.123.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.123.0)
 
@@ -36,6 +67,38 @@ Released at 2025-08-01
 * BUGFIX: [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/): do not configure `-httpListenAddr.useProxyProtocol` for `-httpInternalListenAddr`. See this issue [#9515](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9515) for details.
 * BUGFIX: [vmui](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmui): always display the tenant selector if the list of tenants is not empty. See [#9396](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9396).
 
+## [v1.122.2](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.122.2)
+
+Released at 2025-08-15
+
+**v1.122.x is a line of [LTS releases](https://docs.victoriametrics.com/lts-releases/). It contains important up-to-date bugfixes for [VictoriaMetrics enterprise](https://docs.victoriametrics.com/enterprise.html).
+All these fixes are also included in [the latest community release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest).
+The v1.122.x line will be supported for at least 12 months since [v1.122.0](https://docs.victoriametrics.com/changelog/#v11220) release**
+
+* SECURITY: upgrade Go builder from Go1.24.5 to Go1.24.6. See [the list of issues addressed in Go1.24.6](https://github.com/golang/go/issues?q=milestone%3AGo1.24.6+label%3ACherryPickApproved).
+
+* BUGFIX: [vmagent](https://docs.victoriametrics.com/vmagent/): treat single `remoteWrite.disableOnDiskQueue` flag the same way as if it is explicitly specified for each remote write url. See [#9565](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9565) for details.
+* BUGFIX: [vmalert-tool](https://docs.victoriametrics.com/victoriametrics/vmalert-tool/): print a proper error message when templating function fails during execution. Previously, vmalert-tool could throw a misleading panic message instead.
+* BUGFIX: [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/): properly read proxy-protocol header. See this PR [#9546](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/9546) for details.
+* BUGFIX: [vmselect](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/) in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): prevent resource leak on partial responses for `/federate` API requests. This this PR [9536](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/9536) for details. Thanks to the @fxrlv.
+* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): prevent performance degradation on hitting daily or hourly series cardinality limits. See this issue [9554](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9554) for details.
+* BUGFIX: [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/): gracefully handle `histogram_quantile` calculation for histograms where buckets are created on demand. This change isn't needed for users who use native instrumentation SDKs for metrics from [VictoriaMetrics](https://github.com/VictoriaMetrics/metrics), [Prometheus](https://prometheus.io/docs/instrumenting/clientlibs/) or [OpenTelemetry](https://opentelemetry.io/docs/languages/).
+* BUGFIX: [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/): return a proper error message when the function argument is expected to be a string or scalar.
+* BUGFIX: [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/): fix potential data race and missing firing states when replaying alerting rule with `-replay.ruleEvaluationConcurrency>1`.
+* BUGFIX: [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/): fix the `{{ $activeAt }}` variable value in annotation templating when the alert has already triggered. See this issue [#9543](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9543) for details.
+* BUGFIX: [vmbackup](https://docs.victoriametrics.com/vmbackup/), [vmbackupmanager](https://docs.victoriametrics.com/vmbackupmanager/): allow enabling checksum calculation for PUT requests by using `-s3ChecksumAlgorithm` command-line flag. This is required for S3 configurations with WORM being enabled. See [#9532](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9532).
+
+## [v1.122.1](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.122.1)
+
+Released at 2025-08-01
+
+**v1.122.x is a line of [LTS releases](https://docs.victoriametrics.com/lts-releases/). It contains important up-to-date bugfixes for [VictoriaMetrics enterprise](https://docs.victoriametrics.com/enterprise.html).
+All these fixes are also included in [the latest community release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest).
+The v1.122.x line will be supported for at least 12 months since [v1.122.0](https://docs.victoriametrics.com/changelog/#v11220) release**
+
+* BUGFIX: [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/): do not configure `-httpListenAddr.useProxyProtocol` for `-httpInternalListenAddr`. See this issue [#9515](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9515) for details.
+* BUGFIX: [vmui](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmui): always display the tenant selector if the list of tenants is not empty. See [#9396](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9396).
+
 ## [v1.122.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.122.0)
 
 Released at 2025-07-18
@@ -159,7 +222,7 @@ Released at 2025-05-23
 
 Released at 2025-05-15
 
-**Update Note 1:** `latest` and `stable` tags for docker images will no longer be updated. It is required to use specific version tags for docker images to continue receiving updates. See [#7336](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7336) for details.
+**Update Note 1:** `stable` tag has been removed and will no longer receive updates. It is required to use specific version tags for docker images to continue receiving updates. See [#7336](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7336) for details.
 
 * BUGFIX: [vmsingle](https://docs.victoriametrics.com/single-server-victoriametrics/), `vminsert` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/cluster-victoriametrics/) and [vmagent](https://docs.victoriametrics.com/vmagent/): fixed duplication in Datadog sketches aggregation metrics. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/8836) for details.
 * BUGFIX: [vmagent](https://docs.victoriametrics.com/vmagent/): properly initialize relabel config reloading metrics for `-remoteWrite.relabelConfig` and `-remoteWrite.urlRelabelConfig` flags. The bug was introduced in versions [v1.117.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.117.0), [v1.110.7](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.110.7), [v1.102.20](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.102.20). The fix was released in [v1.117.1](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.117.1) and backported to [v1.110.8](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.110.8) and [v1.102.21](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.102.21).
@@ -381,6 +444,48 @@ Released at 2025-02-10
 * BUGFIX: [Single-node VictoriaMetrics](https://docs.victoriametrics.com/) and [vmselect](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): fix discrepancies when using `or` binary operator. See [this](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7759) and [this](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7640) issues for details.
 * BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): properly update number of unique series for [cardinality limiter](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#cardinality-limiter) on ingestion. Previously, limit could undercount the real number of the ingested unique series. 
 
+## [v1.110.16](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.110.16)
+
+Released at 2025-08-15
+
+**v1.110.x is a line of [LTS releases](https://docs.victoriametrics.com/lts-releases/). It contains important up-to-date bugfixes for [VictoriaMetrics enterprise](https://docs.victoriametrics.com/enterprise.html).
+All these fixes are also included in [the latest community release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest).
+The v1.110.x line will be supported for at least 12 months since [v1.110.0](https://docs.victoriametrics.com/changelog/#v11100) release**
+
+* SECURITY: upgrade Go builder from Go1.24.5 to Go1.24.6. See [the list of issues addressed in Go1.24.6](https://github.com/golang/go/issues?q=milestone%3AGo1.24.6+label%3ACherryPickApproved).
+
+* BUGFIX: [vmagent](https://docs.victoriametrics.com/vmagent/): treat single `remoteWrite.disableOnDiskQueue` flag the same way as if it is explicitly specified for each remote write url. See [#9565](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9565) for details.
+* BUGFIX: [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/): properly read proxy-protocol header. See this PR [#9546](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/9546) for details.
+* BUGFIX: [vmselect](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/) in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): prevent resource leak on partial responses for `/federate` API requests. This this PR [9536](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/9536) for details. Thanks to the @fxrlv.
+* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): prevent performance degradation on hitting daily or hourly series cardinality limits. See this issue [9554](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9554) for details.
+* BUGFIX: [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/): gracefully handle `histogram_quantile` calculation for histograms where buckets are created on demand. This change isn't needed for users who use native instrumentation SDKs for metrics from [VictoriaMetrics](https://github.com/VictoriaMetrics/metrics), [Prometheus](https://prometheus.io/docs/instrumenting/clientlibs/) or [OpenTelemetry](https://opentelemetry.io/docs/languages/).
+* BUGFIX: [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/): return a proper error message when the function argument is expected to be a string or scalar.
+* BUGFIX: [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/): fix the `{{ $activeAt }}` variable value in annotation templating when the alert has already triggered. See this issue [#9543](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9543) for details.
+* BUGFIX: [vmbackup](https://docs.victoriametrics.com/vmbackup/), [vmbackupmanager](https://docs.victoriametrics.com/vmbackupmanager/): allow enabling checksum calculation for PUT requests by using `-s3ChecksumAlgorithm` command-line flag. This is required for S3 configurations with WORM being enabled. See [#9532](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9532).
+
+## [v1.110.15](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.110.15)
+
+Released at 2025-08-01
+
+**v1.110.x is a line of [LTS releases](https://docs.victoriametrics.com/lts-releases/). It contains important up-to-date bugfixes for [VictoriaMetrics enterprise](https://docs.victoriametrics.com/enterprise.html).
+All these fixes are also included in [the latest community release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest).
+The v1.110.x line will be supported for at least 12 months since [v1.110.0](https://docs.victoriametrics.com/changelog/#v11100) release**
+
+* BUGFIX: [vmui](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmui): always display the tenant selector if the list of tenants is not empty. See [#9396](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9396).
+
+## [v1.110.14](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.110.14)
+
+Released at 2025-07-18
+
+**v1.110.x is a line of [LTS releases](https://docs.victoriametrics.com/lts-releases/). It contains important up-to-date bugfixes for [VictoriaMetrics enterprise](https://docs.victoriametrics.com/enterprise.html).
+All these fixes are also included in [the latest community release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest).
+The v1.110.x line will be supported for at least 12 months since [v1.110.0](https://docs.victoriametrics.com/changelog/#v11100) release**
+
+* SECURITY: upgrade Go builder from Go1.24.4 to Go1.24.5. See [the list of issues addressed in Go1.24.5](https://github.com/golang/go/issues?q=milestone%3AGo1.24.5+label%3ACherryPickApproved).
+* SECURITY: upgrade base docker image (Alpine) from 3.22.0 to 3.22.1. See [Alpine 3.22.1 release notes](https://www.alpinelinux.org/posts/Alpine-3.19.8-3.20.7-3.21.4-3.22.1-released.html).
+
+* BUGFIX: all VictoriaMetrics components: fix `process_cpu_cores_available` metric to respect both logical CPU cores and cgroup CPU quota. Previously, it could report incorrect values in containerized environments with no cgroup limits. See [#9449](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/9449).
+
 ## [v1.110.13](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.110.13)
 
 Released at 2025-07-04

docs/victoriametrics/changelog/_index.md

@@ -8,6 +8,7 @@ menu:
     weight: 100
 tags:
   - metrics
+canonical: /victoriametrics/changelog/changelog_2025/
 aliases:
   - /CHANGELOG.html
   - /changelog/index.html

docs/victoriametrics/enterprise.md

@@ -89,7 +89,7 @@ VictoriaMetrics Enterprise components are available in the following forms:
 It is allowed to run VictoriaMetrics Enterprise components in [cases listed here](#valid-cases-for-victoriametrics-enterprise).
 
 Binary releases of VictoriaMetrics Enterprise are available [at the releases page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest).
-Enterprise binaries and packages have `enterprise` suffix in their names. For example, `victoria-metrics-linux-amd64-v1.122.0-enterprise.tar.gz`.
+Enterprise binaries and packages have `enterprise` suffix in their names. For example, `victoria-metrics-linux-amd64-v1.124.0-enterprise.tar.gz`.
 
 In order to run binary release of VictoriaMetrics Enterprise component, please download the `*-enterprise.tar.gz` archive for your OS and architecture
 from the [releases page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest) and unpack it. Then run the unpacked binary.
@@ -107,8 +107,8 @@ For example, the following command runs VictoriaMetrics Enterprise binary with t
 obtained at [this page](https://victoriametrics.com/products/enterprise/trial/):
 
 ```sh
-wget https://github.com/VictoriaMetrics/VictoriaMetrics/releases/download/v1.122.0/victoria-metrics-linux-amd64-v1.122.0-enterprise.tar.gz
-tar -xzf victoria-metrics-linux-amd64-v1.122.0-enterprise.tar.gz
+wget https://github.com/VictoriaMetrics/VictoriaMetrics/releases/download/v1.124.0/victoria-metrics-linux-amd64-v1.124.0-enterprise.tar.gz
+tar -xzf victoria-metrics-linux-amd64-v1.124.0-enterprise.tar.gz
 ./victoria-metrics-prod -license=BASE64_ENCODED_LICENSE_KEY
 ```
 
@@ -123,7 +123,7 @@ Alternatively, VictoriaMetrics Enterprise license can be stored in the file and
 It is allowed to run VictoriaMetrics Enterprise components in [cases listed here](#valid-cases-for-victoriametrics-enterprise).
 
 Docker images for VictoriaMetrics Enterprise are available at VictoriaMetrics [Docker Hub](https://hub.docker.com/u/victoriametrics) and [Quay](https://quay.io/organization/victoriametrics).
-Enterprise docker images have `enterprise` suffix in their names. For example, `victoriametrics/victoria-metrics:v1.122.0-enterprise`.
+Enterprise docker images have `enterprise` suffix in their names. For example, `victoriametrics/victoria-metrics:v1.124.0-enterprise`.
 
 In order to run Docker image of VictoriaMetrics Enterprise component, it is required to provide the license key via command-line
 flag as described [here](#binary-releases).
@@ -133,13 +133,13 @@ Enterprise license key can be obtained at [this page](https://victoriametrics.co
 For example, the following command runs VictoriaMetrics Enterprise Docker image with the specified license key:
 
 ```sh
-docker run --name=victoria-metrics victoriametrics/victoria-metrics:v1.122.0-enterprise -license=BASE64_ENCODED_LICENSE_KEY
+docker run --name=victoria-metrics victoriametrics/victoria-metrics:v1.124.0-enterprise -license=BASE64_ENCODED_LICENSE_KEY
 ```
 
 Alternatively, the license code can be stored in the file and then referred via `-licenseFile` command-line flag:
 
 ```sh
-docker run --name=victoria-metrics -v /vm-license:/vm-license  victoriametrics/victoria-metrics:v1.122.0-enterprise -licenseFile=/path/to/vm-license
+docker run --name=victoria-metrics -v /vm-license:/vm-license  victoriametrics/victoria-metrics:v1.124.0-enterprise -licenseFile=/path/to/vm-license
 ```
 
 Example docker-compose configuration:
@@ -148,7 +148,7 @@ version: "3.5"
 services:
   victoriametrics:
     container_name: victoriametrics
-    image: victoriametrics/victoria-metrics:v1.122.0
+    image: victoriametrics/victoria-metrics:v1.124.0
     ports:
       - 8428:8428
     volumes:
@@ -180,7 +180,7 @@ is used to provide key in plain-text:
 ```yaml
 server:
   image:
-    tag: v1.122.0-enterprise
+    tag: v1.124.0-enterprise
 
 license:
   key: {BASE64_ENCODED_LICENSE_KEY}
@@ -191,7 +191,7 @@ In order to provide key via existing secret, the following values file is used:
 ```yaml
 server:
   image:
-    tag: v1.122.0-enterprise
+    tag: v1.124.0-enterprise
 
 license:
   secret:
@@ -240,7 +240,7 @@ spec:
   license:
     key: {BASE64_ENCODED_LICENSE_KEY}
   image:
-    tag: v1.122.0-enterprise
+    tag: v1.124.0-enterprise
 ```
 
 In order to provide key via existing secret, the following custom resource is used:
@@ -257,7 +257,7 @@ spec:
       name: vm-license
       key: license
   image:
-    tag: v1.122.0-enterprise
+    tag: v1.124.0-enterprise
 ```
 
 Example secret with license key:
@@ -290,7 +290,7 @@ Builds are available for amd64 and arm64
 
 Example archive:
 
-`victoria-metrics-linux-amd64-v1.122.0-enterprise.tar.gz`
+`victoria-metrics-linux-amd64-v1.124.0-enterprise.tar.gz`
 
 Includes:
 
@@ -299,7 +299,7 @@ Includes:
 
 Example Docker image:
 
-`victoriametrics/victoria-metrics:v1.122.0-enterprise-fips` – uses the FIPS-compatible binary and based on `scratch` image.
+`victoriametrics/victoria-metrics:v1.124.0-enterprise-fips` – uses the FIPS-compatible binary and based on `scratch` image.
 
 ## Monitoring license expiration
 

docs/victoriametrics/scrape_config_examples.md

@@ -36,8 +36,8 @@ scrape_configs:
 After you created the `scrape.yaml` file, download and unpack [single-node VictoriaMetrics](https://docs.victoriametrics.com/) to the same directory:
 
 ```
-wget https://github.com/VictoriaMetrics/VictoriaMetrics/releases/download/v1.122.0/victoria-metrics-linux-amd64-v1.122.0.tar.gz
-tar xzf victoria-metrics-linux-amd64-v1.122.0.tar.gz
+wget https://github.com/VictoriaMetrics/VictoriaMetrics/releases/download/v1.124.0/victoria-metrics-linux-amd64-v1.124.0.tar.gz
+tar xzf victoria-metrics-linux-amd64-v1.124.0.tar.gz
 ```
 
 Then start VictoriaMetrics and instruct it to scrape targets defined in `scrape.yaml` and save scraped metrics
@@ -152,8 +152,8 @@ Then start [single-node VictoriaMetrics](https://docs.victoriametrics.com/) acco
 
 ```yaml
 # Download and unpack single-node VictoriaMetrics
-wget https://github.com/VictoriaMetrics/VictoriaMetrics/releases/download/v1.122.0/victoria-metrics-linux-amd64-v1.122.0.tar.gz
-tar xzf victoria-metrics-linux-amd64-v1.122.0.tar.gz
+wget https://github.com/VictoriaMetrics/VictoriaMetrics/releases/download/v1.124.0/victoria-metrics-linux-amd64-v1.124.0.tar.gz
+tar xzf victoria-metrics-linux-amd64-v1.124.0.tar.gz
 
 # Run single-node VictoriaMetrics with the given scrape.yaml
 ./victoria-metrics-prod -promscrape.config=scrape.yaml

docs/victoriametrics/vmagent.md

@@ -596,6 +596,15 @@ in order to compare it to the current response body. The memory usage may be red
 When staleness tracking is disabled, then `vmagent` doesn't track the number of new time series per each scrape,
 e.g. it sets `scrape_series_added` metric to zero. See [these docs](#automatically-generated-metrics) for details.
 
+## Metric metadata
+
+By default, `vmagent` ignores metric metadata exposed by scrape targets in [Prometheus exposition format](https://github.com/prometheus/docs/blob/main/docs/instrumenting/exposition_formats.md), received via [Prometheus remote write v1](https://prometheus.io/docs/specs/prw/remote_write_spec/) or [OpenTelemetry protocol](https://github.com/open-telemetry/opentelemetry-proto/blob/v1.7.0/opentelemetry/proto/metrics/v1/metrics.proto). Set `-enableMetadata=true` to enable metadata processing{{% available_from "v1.124.0" %}}.
+During processing, metadata won't be dropped or modified by [relabeling](https://docs.victoriametrics.com/victoriametrics/relabeling/) or [streaming aggregation](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/).
+
+When `-enableMultitenantHandlers` is enabled, vmagent adds tenant info to metadata received via the [multitenant endpoints](https://docs.victoriametrics.com/victoriametrics/vmagent/#multitenancy) (/insert/<accountID>/<suffix>). However, if `vm_account_id` or `vm_project_id` labels are added directly to metrics before reaching vmagent, and vmagent writes to the [vminsert multitenant endpoints](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#multitenancy-via-labels), the tenant info won't be attached and the metadata will be stored under the default tenant of VictoriaMetrics cluster.
+
+>Enabling metadata requires extra memory, disk space, and network traffic.
+
 ## Stream parsing mode
 
 By default, `vmagent` parses the full response from the scrape target, applies [relabeling](https://docs.victoriametrics.com/victoriametrics/relabeling/)
@@ -796,8 +805,8 @@ In this case `-remoteWrite.disableOnDiskQueue` command-line flag can be passed t
 and the `-remoteWrite.disableOnDiskQueue` command-line flag is set:
 
 - It returns `429 Too Many Requests` HTTP error to clients, which send data to `vmagent` via [supported HTTP endpoints](#how-to-push-data-to-vmagent).
-  If `-remoteWrite.dropSamplesOnOverload` command-line flag is set or if multiple `-remoteWrite.disableOnDiskQueue` command-line flags are set
-  for different `-remoteWrite.url` options, then the ingested samples are silently dropped instead of returning the error to clients.
+  If `-remoteWrite.dropSamplesOnOverload` command-line flag is set or if multiple `-remoteWrite.url` command-line flags are set, 
+  then the ingested samples are silently dropped instead of returning the error to clients.
 - It suspends consuming data from [Kafka side](#reading-metrics-from-kafka) or [Google PubSub side](#google-pubsub-integration) until the remote storage becomes available.
   If `-remoteWrite.dropSamplesOnOverload` command-line flag is set or if multiple `-remoteWrite.disableOnDiskQueue` command-line flags are set
   for different `-remoteWrite.url` options, then the fetched samples are silently dropped instead of suspending data consumption from Kafka or Google PubSub.
@@ -1497,6 +1506,8 @@ See the docs at https://docs.victoriametrics.com/victoriametrics/vmagent/ .
      Whether to disable the ability to trace queries. See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#query-tracing
   -dryRun
      Whether to check config files without running vmagent. The following files are checked: -promscrape.config, -remoteWrite.relabelConfig, -remoteWrite.urlRelabelConfig, -remoteWrite.streamAggr.config . Unknown config entries aren't allowed in -promscrape.config by default. This can be changed by passing -promscrape.config.strictParse=false command-line flag
+  -enableMetadata
+     Whether to enable metadata processing for metrics scraped from targets, received via VictoriaMetrics remote write, Prometheus remote write v1 or OpenTelemetry protocol. See also remoteWrite.maxMetadataPerBlock
   -enableMultitenantHandlers
      Whether to process incoming data via multitenant insert handlers according to https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#url-format . By default incoming data is processed via single-node insert handlers according to https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-import-time-series-data .See https://docs.victoriametrics.com/victoriametrics/vmagent/#multitenancy for details
   -enableTCP6
@@ -1936,7 +1947,7 @@ See the docs at https://docs.victoriametrics.com/victoriametrics/vmagent/ .
   -remoteWrite.dropSamplesOnOverload
      Whether to drop samples when -remoteWrite.disableOnDiskQueue is set and if the samples cannot be pushed into the configured -remoteWrite.url systems in a timely manner. See https://docs.victoriametrics.com/victoriametrics/vmagent/#disabling-on-disk-persistence
   -remoteWrite.flushInterval duration
-     Interval for flushing the data to remote storage. This option takes effect only when less than 10K data points per second are pushed to -remoteWrite.url (default 1s)
+     Interval for flushing the data to remote storage. This option takes effect only when less than -remoteWrite.maxRowsPerBlock data points per -remoteWrite.flushInterval are pushed to -remoteWrite.url (default 1s)
   -remoteWrite.forcePromProto array
      Whether to force Prometheus remote write protocol for sending data to the corresponding -remoteWrite.url . See https://docs.victoriametrics.com/victoriametrics/vmagent/#victoriametrics-remote-write-protocol
      Supports array of values separated by comma or specified via multiple flags.
@@ -1967,6 +1978,8 @@ See the docs at https://docs.victoriametrics.com/victoriametrics/vmagent/ .
      Empty values are set to default value.
   -remoteWrite.maxHourlySeries int
      The maximum number of unique series vmagent can send to remote storage systems during the last hour. Excess series are logged and dropped. This can be useful for limiting series cardinality. See https://docs.victoriametrics.com/victoriametrics/vmagent/#cardinality-limiter
+  -remoteWrite.maxMetadataPerBlock int
+     The maximum number of metadata to send in each block to remote storage. Higher number may improve performance at the cost of the increased memory usage. See also -remoteWrite.maxBlockSize (default 5000)
   -remoteWrite.maxRowsPerBlock int
      The maximum number of samples to send in each block to remote storage. Higher number may improve performance at the cost of the increased memory usage. See also -remoteWrite.maxBlockSize (default 10000)
   -remoteWrite.oauth2.clientID array

docs/victoriametrics/vmalert.md

@@ -865,8 +865,8 @@ There are following non-required `replay` flags:
 * `-replay.disableProgressBar` - whether to disable progress bar which shows progress work.
   Progress bar may generate a lot of log records, which is not formatted as standard VictoriaMetrics logger.
   It could break logs parsing by external system and generate additional load on it.
-* `-replay.ruleEvaluationConcurrency` -  The maximum number of concurrent `/query_range` requests for a single rule. 
-  Increasing this value when replaying for a long time and a single request range is limited by `-replay.maxDatapointsPerQuery`.
+* `-replay.ruleEvaluationConcurrency` -  The maximum number of concurrent `/query_range` requests when replay recording rule or alerting rule with for=0.
+  Increasing this value when replaying for a long time, since each request is limited by `-replay.maxDatapointsPerQuery`.
   The default value is `1`.
 
 See full description for these flags in `./vmalert -help`.

docs/victoriametrics/vmbackupmanager.md

@@ -110,7 +110,7 @@ Backup manager launched with the following configuration:
 ```sh
 export NODE_IP=192.168.0.10
 export VMSTORAGE_ENDPOINT=http://127.0.0.1:8428
-./vmbackupmanager -dst=gs://vmstorage-data/$NODE_IP -credsFilePath=credentials.json -storageDataPath=/vmstorage-data -snapshot.createURL=$VMSTORAGE_ENDPOINT/snapshot/create -eula
+./vmbackupmanager -dst=gs://vmstorage-data/$NODE_IP -credsFilePath=credentials.json -storageDataPath=/vmstorage-data -snapshot.createURL=$VMSTORAGE_ENDPOINT/snapshot/create -licenseFile=/path/to/vm-license
 ```
 
 Expected logs in vmbackupmanager:
@@ -170,7 +170,7 @@ We enable backup retention policy for backup manager by using following configur
 export NODE_IP=192.168.0.10
 export VMSTORAGE_ENDPOINT=http://127.0.0.1:8428
 ./vmbackupmanager -dst=gs://vmstorage-data/$NODE_IP -credsFilePath=credentials.json -storageDataPath=/vmstorage-data -snapshot.createURL=$VMSTORAGE_ENDPOINT/snapshot/create
--keepLastDaily=3 -eula
+-keepLastDaily=3 -licenseFile=/path/to/vm-license
 ```
 
 Expected logs in backup manager on start:
@@ -196,14 +196,14 @@ You can protect any backup against deletion by retention policy with the `vmback
 For instance:
 
 ```sh
-./vmbackupmanager backup lock daily/2021-02-13 -dst=<DST_PATH> -storageDataPath=/vmstorage-data -eula
+./vmbackupmanager backup lock daily/2021-02-13 -dst=<DST_PATH> -storageDataPath=/vmstorage-data
 ```
 
 After that the backup won't be deleted by retention policy.
 You can view the `locked` attribute in backup list:
 
 ```sh
-./vmbackupmanager backup list -dst=<DST_PATH> -storageDataPath=/vmstorage-data -eula
+./vmbackupmanager backup list -dst=<DST_PATH> -storageDataPath=/vmstorage-data
 ```
 
 To remove protection, you can use the command `vmbackupmanager backups unlock`.
@@ -211,7 +211,7 @@ To remove protection, you can use the command `vmbackupmanager backups unlock`.
 For example:
 
 ```sh
-./vmbackupmanager backup unlock daily/2021-02-13 -dst=<DST_PATH> -storageDataPath=/vmstorage-data -eula
+./vmbackupmanager backup unlock daily/2021-02-13 -dst=<DST_PATH> -storageDataPath=/vmstorage-data
 ```
 
 ## API methods

docs/victoriametrics/vmctl/vmctl.md

@@ -1,3 +1,9 @@
+---
+build:
+  list: never
+  publishResources: false
+  render: never
+---
 VictoriaMetrics command-line tool (**vmctl**) provides the following migration modes:
 - [Prometheus](https://docs.victoriametrics.com/victoriametrics/vmctl/prometheus/) to VictoriaMetrics via [snapshot](https://prometheus.io/docs/prometheus/latest/querying/api/#snapshot)
 - [InfluxDB](https://docs.victoriametrics.com/victoriametrics/vmctl/influxdb/) to VictoriaMetrics
@@ -26,9 +32,9 @@ vmctl command-line tool is available as:
 
 Download and unpack vmctl:
 ```sh
-wget https://github.com/VictoriaMetrics/VictoriaMetrics/releases/download/v1.122.0/vmutils-darwin-arm64-v1.122.0.tar.gz
+wget https://github.com/VictoriaMetrics/VictoriaMetrics/releases/download/v1.124.0/vmutils-darwin-arm64-v1.124.0.tar.gz
 
-tar xzf vmutils-darwin-arm64-v1.122.0.tar.gz
+tar xzf vmutils-darwin-arm64-v1.124.0.tar.gz
 ```
 
 Once binary is unpacked, see the full list of supported modes by running the following command:
@@ -352,4 +358,4 @@ Moved to [vmctl/victoriametrics](https://docs.victoriametrics.com/victoriametric
 
 ###### Tuning
 
-Moved to [vmctl#migration-tips](https://docs.victoriametrics.com/victoriametrics/vmctl#migration-tips).
+Moved to [vmctl#migration-tips](https://docs.victoriametrics.com/victoriametrics/vmctl#migration-tips).

docs/victoriametrics/vmgateway.md

@@ -88,7 +88,7 @@ Start the single version of VictoriaMetrics
 Start vmgateway
 
 ```sh
-./bin/vmgateway -eula -enable.auth -read.url http://localhost:8428 --write.url http://localhost:8428
+./bin/vmgateway -licenseFile=/path/to/vm-license -enable.auth -read.url http://localhost:8428 --write.url http://localhost:8428
 ```
 
 Retrieve data from the database
@@ -163,9 +163,9 @@ EOF
 # start cluster
 
 # start vmstorage, vmselect and vminsert
-./bin/vmstorage -eula
-./bin/vmselect -eula -storageNode 127.0.0.1:8401
-./bin/vminsert -eula -storageNode 127.0.0.1:8400
+./bin/vmstorage -licenseFile=/path/to/vm-license
+./bin/vmselect -licenseFile=/path/to/vm-license -storageNode 127.0.0.1:8401
+./bin/vminsert -licenseFile=/path/to/vm-license -storageNode 127.0.0.1:8400
 
 # create base rate limiting config:
 cat << EOF > limit.yaml
@@ -184,7 +184,7 @@ limits:
 EOF
 
 # start gateway with `-clusterMode`
-./bin/vmgateway -eula -enable.rateLimit -ratelimit.config limit.yaml -datasource.url http://localhost:8428 -enable.auth -clusterMode -write.url=http://localhost:8480 --read.url=http://localhost:8481
+./bin/vmgateway -licenseFile=/path/to/vm-license -enable.rateLimit -ratelimit.config limit.yaml -datasource.url http://localhost:8428 -enable.auth -clusterMode -write.url=http://localhost:8480 --read.url=http://localhost:8481
 
 # ingest simple metric to tenant 1:5
 curl 'http://localhost:8431/api/v1/import/prometheus' -X POST  -d 'foo{bar="baz1"} 123' -H 'Authorization: Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJleHAiOjE2MjAxNjIwMDAwMDAsInZtX2FjY2VzcyI6eyJ0ZW5hbnRfaWQiOnsiYWNjb3VudF9pZCI6MTV9fX0.PB1_KXDKPUp-40pxOGk6lt_jt9Yq80PIMpWVJqSForQ'
@@ -210,7 +210,7 @@ Note that both flags support passing multiple keys and also can be used together
 
 Example usage:
 ```sh
-./bin/vmgateway -eula \
+./bin/vmgateway -licenseFile=/path/to/vm-license \
   -enable.auth \
   -write.url=http://localhost:8480 \
   -read.url=http://localhost:8481 \
@@ -238,7 +238,7 @@ When `auth.oidcDiscoveryEndpoints` is specified `vmgateway` will fetch JWKS keys
 
 Example usage for tokens issued by Azure Active Directory:
 ```sh
-/bin/vmgateway -eula \
+/bin/vmgateway -licenseFile=/path/to/vm-license \
   -enable.auth \
   -write.url=http://localhost:8480 \
   -read.url=http://localhost:8481 \
@@ -247,7 +247,7 @@ Example usage for tokens issued by Azure Active Directory:
 
 Example usage for tokens issued by Google:
 ```sh
-/bin/vmgateway -eula \
+/bin/vmgateway -licenseFile=/path/to/vm-license \
   -enable.auth \
   -write.url=http://localhost:8480 \
   -read.url=http://localhost:8481 \
@@ -263,7 +263,7 @@ When `auth.jwksEndpoints` is specified `vmgateway` will fetch public keys from t
 
 Example usage for tokens issued by Azure Active Directory:
 ```sh
-/bin/vmgateway -eula \
+/bin/vmgateway -licenseFile=/path/to/vm-license \
   -enable.auth \
   -write.url=http://localhost:8480 \
   -read.url=http://localhost:8481 \
@@ -272,7 +272,7 @@ Example usage for tokens issued by Azure Active Directory:
 
 Example usage for tokens issued by Google:
 ```sh
-/bin/vmgateway -eula \
+/bin/vmgateway -licenseFile=/path/to/vm-license \
   -enable.auth \
   -write.url=http://localhost:8480 \
   -read.url=http://localhost:8481 \

go.mod

@@ -1,12 +1,6 @@
 module github.com/VictoriaMetrics/VictoriaMetrics
 
-go 1.24.5
-
-// This is needed in order to avoid vmbackup and vmrestore binary size increase by 20MB
-// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/8008
-//
-// TODO: remove this entry after https://github.com/googleapis/google-cloud-go/issues/11448 is fixed
-replace cloud.google.com/go/storage => cloud.google.com/go/storage v1.43.0
+go 1.25.0
 
 // Pin AWS libraries to version before 2025-01-15
 // Release notes: https://github.com/aws/aws-sdk-go-v2/releases/tag/release-2025-01-15
@@ -34,7 +28,7 @@ require (
 	github.com/Azure/azure-sdk-for-go/sdk/storage/azblob v1.6.2
 	github.com/VictoriaMetrics/VictoriaLogs v0.0.0-20250728123024-98593029b5aa
 	github.com/VictoriaMetrics/easyproto v0.1.4
-	github.com/VictoriaMetrics/fastcache v1.12.5
+	github.com/VictoriaMetrics/fastcache v1.13.0
 	github.com/VictoriaMetrics/metrics v1.39.1
 	github.com/VictoriaMetrics/metricsql v0.84.6
 	github.com/aws/aws-sdk-go-v2 v1.37.1
@@ -66,13 +60,18 @@ require (
 )
 
 require (
+	cel.dev/expr v0.24.0 // indirect
 	cloud.google.com/go v0.121.4 // indirect
 	cloud.google.com/go/auth v0.16.3 // indirect
 	cloud.google.com/go/auth/oauth2adapt v0.2.8 // indirect
 	cloud.google.com/go/compute/metadata v0.7.0 // indirect
 	cloud.google.com/go/iam v1.5.2 // indirect
+	cloud.google.com/go/monitoring v1.24.2 // indirect
 	github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.2 // indirect
 	github.com/AzureAD/microsoft-authentication-library-for-go v1.4.2 // indirect
+	github.com/GoogleCloudPlatform/opentelemetry-operations-go/detectors/gcp v1.27.0 // indirect
+	github.com/GoogleCloudPlatform/opentelemetry-operations-go/exporter/metric v0.53.0 // indirect
+	github.com/GoogleCloudPlatform/opentelemetry-operations-go/internal/resourcemapping v0.53.0 // indirect
 	github.com/VividCortex/ewma v1.2.0 // indirect
 	github.com/alecthomas/units v0.0.0-20240927000941-0f3dac36c52b // indirect
 	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.0 // indirect
@@ -92,11 +91,15 @@ require (
 	github.com/aws/smithy-go v1.22.5 // indirect
 	github.com/bboreham/go-loser v0.0.0-20230920113527-fcc2c21820a3 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
+	github.com/cncf/xds/go v0.0.0-20250501225837-2ac532fd4443 // indirect
 	github.com/cpuguy83/go-md2man/v2 v2.0.7 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/dennwc/varint v1.0.0 // indirect
+	github.com/envoyproxy/go-control-plane/envoy v1.32.4 // indirect
+	github.com/envoyproxy/protoc-gen-validate v1.2.1 // indirect
 	github.com/fatih/color v1.18.0 // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
+	github.com/go-jose/go-jose/v4 v4.0.5 // indirect
 	github.com/go-logr/logr v1.4.3 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-viper/mapstructure/v2 v2.4.0 // indirect
@@ -127,6 +130,7 @@ require (
 	github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatautil v0.131.0 // indirect
 	github.com/open-telemetry/opentelemetry-collector-contrib/processor/deltatocumulativeprocessor v0.131.0 // indirect
 	github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c // indirect
+	github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10 // indirect
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/prometheus/client_golang v1.23.0 // indirect
 	github.com/prometheus/client_model v0.6.2 // indirect
@@ -136,9 +140,11 @@ require (
 	github.com/puzpuzpuz/xsync/v3 v3.5.1 // indirect
 	github.com/rivo/uniseg v0.4.7 // indirect
 	github.com/russross/blackfriday/v2 v2.1.0 // indirect
+	github.com/spiffe/go-spiffe/v2 v2.5.0 // indirect
 	github.com/stretchr/testify v1.10.0 // indirect
 	github.com/valyala/bytebufferpool v1.0.0 // indirect
 	github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342 // indirect
+	github.com/zeebo/errs v1.4.0 // indirect
 	go.opentelemetry.io/auto/sdk v1.1.0 // indirect
 	go.opentelemetry.io/collector/component v1.37.0 // indirect
 	go.opentelemetry.io/collector/confmap v1.37.0 // indirect
@@ -151,6 +157,7 @@ require (
 	go.opentelemetry.io/collector/processor v1.37.0 // indirect
 	go.opentelemetry.io/collector/semconv v0.128.0 // indirect
 	go.opentelemetry.io/contrib/bridges/otelzap v0.12.0 // indirect
+	go.opentelemetry.io/contrib/detectors/gcp v1.36.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.62.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/httptrace/otelhttptrace v0.62.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.62.0 // indirect
@@ -158,6 +165,7 @@ require (
 	go.opentelemetry.io/otel/log v0.13.0 // indirect
 	go.opentelemetry.io/otel/metric v1.37.0 // indirect
 	go.opentelemetry.io/otel/sdk v1.37.0 // indirect
+	go.opentelemetry.io/otel/sdk/metric v1.37.0 // indirect
 	go.opentelemetry.io/otel/trace v1.37.0 // indirect
 	go.uber.org/atomic v1.11.0 // indirect
 	go.uber.org/goleak v1.3.0 // indirect

go.sum

@@ -1,3 +1,5 @@
+cel.dev/expr v0.24.0 h1:56OvJKSH3hDGL0ml5uSxZmz3/3Pq4tJ+fb1unVLAFcY=
+cel.dev/expr v0.24.0/go.mod h1:hLPLo1W4QUmuYdA72RBX06QTs6MXw941piREPl3Yfiw=
 cloud.google.com/go v0.121.4 h1:cVvUiY0sX0xwyxPwdSU2KsF9knOVmtRyAMt8xou0iTs=
 cloud.google.com/go v0.121.4/go.mod h1:XEBchUiHFJbz4lKBZwYBDHV/rSyfFktk737TLDU089s=
 cloud.google.com/go/auth v0.16.3 h1:kabzoQ9/bobUmnseYnBO6qQG7q4a/CffFRlJSxv2wCc=
@@ -8,10 +10,16 @@ cloud.google.com/go/compute/metadata v0.7.0 h1:PBWF+iiAerVNe8UCHxdOt6eHLVc3ydFeO
 cloud.google.com/go/compute/metadata v0.7.0/go.mod h1:j5MvL9PprKL39t166CoB1uVHfQMs4tFQZZcKwksXUjo=
 cloud.google.com/go/iam v1.5.2 h1:qgFRAGEmd8z6dJ/qyEchAuL9jpswyODjA2lS+w234g8=
 cloud.google.com/go/iam v1.5.2/go.mod h1:SE1vg0N81zQqLzQEwxL2WI6yhetBdbNQuTvIKCSkUHE=
+cloud.google.com/go/logging v1.13.0 h1:7j0HgAp0B94o1YRDqiqm26w4q1rDMH7XNRU34lJXHYc=
+cloud.google.com/go/logging v1.13.0/go.mod h1:36CoKh6KA/M0PbhPKMq6/qety2DCAErbhXT62TuXALA=
 cloud.google.com/go/longrunning v0.6.7 h1:IGtfDWHhQCgCjwQjV9iiLnUta9LBCo8R9QmAFsS/PrE=
 cloud.google.com/go/longrunning v0.6.7/go.mod h1:EAFV3IZAKmM56TyiE6VAP3VoTzhZzySwI/YI1s/nRsY=
-cloud.google.com/go/storage v1.43.0 h1:CcxnSohZwizt4LCzQHWvBf1/kvtHUn7gk9QERXPyXFs=
-cloud.google.com/go/storage v1.43.0/go.mod h1:ajvxEa7WmZS1PxvKRq4bq0tFT3vMd502JwstCcYv0Q0=
+cloud.google.com/go/monitoring v1.24.2 h1:5OTsoJ1dXYIiMiuL+sYscLc9BumrL3CarVLL7dd7lHM=
+cloud.google.com/go/monitoring v1.24.2/go.mod h1:x7yzPWcgDRnPEv3sI+jJGBkwl5qINf+6qY4eq0I9B4U=
+cloud.google.com/go/storage v1.56.0 h1:iixmq2Fse2tqxMbWhLWC9HfBj1qdxqAmiK8/eqtsLxI=
+cloud.google.com/go/storage v1.56.0/go.mod h1:Tpuj6t4NweCLzlNbw9Z9iwxEkrSem20AetIeH/shgVU=
+cloud.google.com/go/trace v1.11.6 h1:2O2zjPzqPYAHrn3OKl029qlqG6W8ZdYaOWRyr8NgMT4=
+cloud.google.com/go/trace v1.11.6/go.mod h1:GA855OeDEBiBMzcckLPE2kDunIpC72N+Pq8WFieFjnI=
 github.com/Azure/azure-sdk-for-go/sdk/azcore v1.18.2 h1:Hr5FTipp7SL07o2FvoVOX9HRiRH3CR3Mj8pxqCcdD5A=
 github.com/Azure/azure-sdk-for-go/sdk/azcore v1.18.2/go.mod h1:QyVsSSN64v5TGltphKLQ2sQxe4OBQg0J1eKRcVBnfgE=
 github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.10.1 h1:B+blDbyVIG3WaikNxPnhPiJ1MThR03b3vKGtER95TP4=
@@ -34,14 +42,22 @@ github.com/AzureAD/microsoft-authentication-library-for-go v1.4.2 h1:oygO0locgZJ
 github.com/AzureAD/microsoft-authentication-library-for-go v1.4.2/go.mod h1:wP83P5OoQ5p6ip3ScPr0BAq0BvuPAvacpEuSzyouqAI=
 github.com/Code-Hex/go-generics-cache v1.5.1 h1:6vhZGc5M7Y/YD8cIUcY8kcuQLB4cHR7U+0KMqAA0KcU=
 github.com/Code-Hex/go-generics-cache v1.5.1/go.mod h1:qxcC9kRVrct9rHeiYpFWSoW1vxyillCVzX13KZG8dl4=
-github.com/Microsoft/go-winio v0.6.1 h1:9/kr64B9VUZrLm5YYwbGtUJnMgqWVOdUAXu6Migciow=
-github.com/Microsoft/go-winio v0.6.1/go.mod h1:LRdKpFKfdobln8UmuiYcKPot9D2v6svN5+sAH+4kjUM=
+github.com/GoogleCloudPlatform/opentelemetry-operations-go/detectors/gcp v1.27.0 h1:ErKg/3iS1AKcTkf3yixlZ54f9U1rljCkQyEXWUnIUxc=
+github.com/GoogleCloudPlatform/opentelemetry-operations-go/detectors/gcp v1.27.0/go.mod h1:yAZHSGnqScoU556rBOVkwLze6WP5N+U11RHuWaGVxwY=
+github.com/GoogleCloudPlatform/opentelemetry-operations-go/exporter/metric v0.53.0 h1:owcC2UnmsZycprQ5RfRgjydWhuoxg71LUfyiQdijZuM=
+github.com/GoogleCloudPlatform/opentelemetry-operations-go/exporter/metric v0.53.0/go.mod h1:ZPpqegjbE99EPKsu3iUWV22A04wzGPcAY/ziSIQEEgs=
+github.com/GoogleCloudPlatform/opentelemetry-operations-go/internal/cloudmock v0.53.0 h1:4LP6hvB4I5ouTbGgWtixJhgED6xdf67twf9PoY96Tbg=
+github.com/GoogleCloudPlatform/opentelemetry-operations-go/internal/cloudmock v0.53.0/go.mod h1:jUZ5LYlw40WMd07qxcQJD5M40aUxrfwqQX1g7zxYnrQ=
+github.com/GoogleCloudPlatform/opentelemetry-operations-go/internal/resourcemapping v0.53.0 h1:Ron4zCA/yk6U7WOBXhTJcDpsUBG9npumK6xw2auFltQ=
+github.com/GoogleCloudPlatform/opentelemetry-operations-go/internal/resourcemapping v0.53.0/go.mod h1:cSgYe11MCNYunTnRXrKiR/tHc0eoKjICUuWpNZoVCOo=
+github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
+github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
 github.com/VictoriaMetrics/VictoriaLogs v0.0.0-20250728123024-98593029b5aa h1:qTB0QsUpBe/WzXQKcALj3Ossizb2daUHXmaVoWFdVlE=
 github.com/VictoriaMetrics/VictoriaLogs v0.0.0-20250728123024-98593029b5aa/go.mod h1:jeov7Un2x4Dpxw2Qn2MWa0kbwNn1Gc2Iw+8gvPqGsZk=
 github.com/VictoriaMetrics/easyproto v0.1.4 h1:r8cNvo8o6sR4QShBXQd1bKw/VVLSQma/V2KhTBPf+Sc=
 github.com/VictoriaMetrics/easyproto v0.1.4/go.mod h1:QlGlzaJnDfFd8Lk6Ci/fuLxfTo3/GThPs2KH23mv710=
-github.com/VictoriaMetrics/fastcache v1.12.5 h1:966OX9JjqYmDAFdp3wEXLwzukiHIm+GVlZHv6B8KW3k=
-github.com/VictoriaMetrics/fastcache v1.12.5/go.mod h1:K+JGPBn0sueFlLjZ8rcVM0cKkWKNElKyQXmw57QOoYI=
+github.com/VictoriaMetrics/fastcache v1.13.0 h1:AW4mheMR5Vd9FkAPUv+NH6Nhw+fmbTMGMsNAoA/+4G0=
+github.com/VictoriaMetrics/fastcache v1.13.0/go.mod h1:hHXhl4DA2fTL2HTZDJFXWgW0LNjo6B+4aj2Wmng3TjU=
 github.com/VictoriaMetrics/metrics v1.39.1 h1:AT7jz7oSpAK9phDl5O5Tmy06nXnnzALwqVnf4ros3Ow=
 github.com/VictoriaMetrics/metrics v1.39.1/go.mod h1:XE4uudAAIRaJE614Tl5HMrtoEU6+GDZO4QTnNSsZRuA=
 github.com/VictoriaMetrics/metricsql v0.84.6 h1:r1rl05prim/r+Me4BUULaZQYXn2eZa3dnrtk+hY3X90=
@@ -131,8 +147,11 @@ github.com/edsrzf/mmap-go v1.2.0/go.mod h1:19H/e8pUPLicwkyNgOykDXkJ9F0MHE+Z52B8E
 github.com/emicklei/go-restful/v3 v3.11.0 h1:rAQeMHw1c7zTmncogyy8VvRZwtkmkZ4FxERmMY4rD+g=
 github.com/emicklei/go-restful/v3 v3.11.0/go.mod h1:6n3XBCmQQb25CM2LCACGz8ukIrRry+4bhvbpWn3mrbc=
 github.com/envoyproxy/go-control-plane v0.13.4 h1:zEqyPVyku6IvWCFwux4x9RxkLOMUL+1vC9xUFv5l2/M=
+github.com/envoyproxy/go-control-plane v0.13.4/go.mod h1:kDfuBlDVsSj2MjrLEtRWtHlsWIFcGyB2RMO44Dc5GZA=
 github.com/envoyproxy/go-control-plane/envoy v1.32.4 h1:jb83lalDRZSpPWW2Z7Mck/8kXZ5CQAFYVjQcdVIr83A=
 github.com/envoyproxy/go-control-plane/envoy v1.32.4/go.mod h1:Gzjc5k8JcJswLjAx1Zm+wSYE20UrLtt7JZMWiWQXQEw=
+github.com/envoyproxy/go-control-plane/ratelimit v0.1.0 h1:/G9QYbddjL25KvtKTv3an9lx6VBE2cnb8wp1vEGNYGI=
+github.com/envoyproxy/go-control-plane/ratelimit v0.1.0/go.mod h1:Wk+tMFAFbCXaJPzVVHnPgRKdUdwW/KdbRt94AzgRee4=
 github.com/envoyproxy/protoc-gen-validate v1.2.1 h1:DEo3O99U8j4hBFwbJfrz9VtgcDfUKS7KJ7spH3d86P8=
 github.com/envoyproxy/protoc-gen-validate v1.2.1/go.mod h1:d/C80l/jxXLdfEIhX1W2TmLfsJ31lvEjwamM4DxlWXU=
 github.com/facette/natsort v0.0.0-20181210072756-2cd4dd1e2dcb h1:IT4JYU7k4ikYg1SCxNI1/Tieq/NFvh6dzLdgi7eu0tM=
@@ -145,6 +164,8 @@ github.com/fsnotify/fsnotify v1.8.0 h1:dAwr6QBTBZIkG8roQaJjGof0pp0EeF+tNV7YBP3F/
 github.com/fsnotify/fsnotify v1.8.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=
 github.com/fxamacker/cbor/v2 v2.7.0 h1:iM5WgngdRBanHcxugY4JySA0nk1wZorNOpTgCMedv5E=
 github.com/fxamacker/cbor/v2 v2.7.0/go.mod h1:pxXPTn3joSm21Gbwsv0w9OSA2y1HFR9qXEeXQVeNoDQ=
+github.com/go-jose/go-jose/v4 v4.0.5 h1:M6T8+mKZl/+fNNuFHvGIzDz7BTLQPIounk/b9dw3AaE=
+github.com/go-jose/go-jose/v4 v4.0.5/go.mod h1:s3P1lRrkT8igV8D9OjyL4WRyHvjB6a4JSllnOrmmBOA=
 github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
 github.com/go-logr/logr v1.4.3 h1:CjnDlHq8ikf6E492q6eKboGOC0T8CDaOvkHCIg8idEI=
 github.com/go-logr/logr v1.4.3/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
@@ -340,6 +361,8 @@ github.com/scaleway/scaleway-sdk-go v1.0.0-beta.32 h1:4+LP7qmsLSGbmc66m1s5dKRMBw
 github.com/scaleway/scaleway-sdk-go v1.0.0-beta.32/go.mod h1:kzh+BSAvpoyHHdHBCDhmSWtBc1NbLMZ2lWHqnBoxFks=
 github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
 github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
+github.com/spiffe/go-spiffe/v2 v2.5.0 h1:N2I01KCUkv1FAjZXJMwh95KK1ZIQLYbPfhaxw8WS0hE=
+github.com/spiffe/go-spiffe/v2 v2.5.0/go.mod h1:P+NxobPc6wXhVtINNtFjNWGBTreew1GBUCwT2wPmb7g=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
 github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
@@ -376,6 +399,8 @@ github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342 h1:FnBeRrxr7OU4VvAz
 github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342/go.mod h1:Ohn+xnUBiLI6FVj/9LpzZWtj1/D6lUovWYBkxHVV3aM=
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
+github.com/zeebo/errs v1.4.0 h1:XNdoD/RRMKP7HD0UhJnIzUy74ISdGGxURlYG8HSWSfM=
+github.com/zeebo/errs v1.4.0/go.mod h1:sgbWHsvVuTPHcqJJGQ1WhI5KbWlHYz+2+2C/LSEtCw4=
 go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=
 go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
 go.opentelemetry.io/collector/component v1.37.0 h1:yc5X0WhZwlpJ+W8Sg1fpRRjiUu3nByLe1wVOKWWRWRQ=
@@ -416,6 +441,8 @@ go.opentelemetry.io/collector/semconv v0.128.0 h1:MzYOz7Vgb3Kf5D7b49pqqgeUhEmOCu
 go.opentelemetry.io/collector/semconv v0.128.0/go.mod h1:OPXer4l43X23cnjLXIZnRj/qQOjSuq4TgBLI76P9hns=
 go.opentelemetry.io/contrib/bridges/otelzap v0.12.0 h1:FGre0nZh5BSw7G73VpT3xs38HchsfPsa2aZtMp0NPOs=
 go.opentelemetry.io/contrib/bridges/otelzap v0.12.0/go.mod h1:X2PYPViI2wTPIMIOBjG17KNybTzsrATnvPJ02kkz7LM=
+go.opentelemetry.io/contrib/detectors/gcp v1.36.0 h1:F7q2tNlCaHY9nMKHR6XH9/qkp8FktLnIcy6jJNyOCQw=
+go.opentelemetry.io/contrib/detectors/gcp v1.36.0/go.mod h1:IbBN8uAIIx734PTonTPxAxnjc2pQTxWNkwfstZ+6H2k=
 go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.62.0 h1:rbRJ8BBoVMsQShESYZ0FkvcITu8X8QNwJogcLUmDNNw=
 go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.62.0/go.mod h1:ru6KHrNtNHxM4nD/vd6QrLVWgKhxPYgblq4VAtNawTQ=
 go.opentelemetry.io/contrib/instrumentation/net/http/httptrace/otelhttptrace v0.62.0 h1:wCeciVlAfb5DC8MQl/DlmAv/FVPNpQgFvI/71+hatuc=
@@ -424,6 +451,8 @@ go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.62.0 h1:Hf9xI/X
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.62.0/go.mod h1:NfchwuyNoMcZ5MLHwPrODwUF1HWCXWrL31s8gSAdIKY=
 go.opentelemetry.io/otel v1.37.0 h1:9zhNfelUvx0KBfu/gb+ZgeAfAgtWrfHJZcAqFC228wQ=
 go.opentelemetry.io/otel v1.37.0/go.mod h1:ehE/umFRLnuLa/vSccNq9oS1ErUlkkK71gMcN34UG8I=
+go.opentelemetry.io/otel/exporters/stdout/stdoutmetric v1.36.0 h1:rixTyDGXFxRy1xzhKrotaHy3/KXdPhlWARrCgK+eqUY=
+go.opentelemetry.io/otel/exporters/stdout/stdoutmetric v1.36.0/go.mod h1:dowW6UsM9MKbJq5JTz2AMVp3/5iW5I/TStsk8S+CfHw=
 go.opentelemetry.io/otel/log v0.13.0 h1:yoxRoIZcohB6Xf0lNv9QIyCzQvrtGZklVbdCoyb7dls=
 go.opentelemetry.io/otel/log v0.13.0/go.mod h1:INKfG4k1O9CL25BaM1qLe0zIedOpvlS5Z7XgSbmN83E=
 go.opentelemetry.io/otel/log/logtest v0.13.0 h1:xxaIcgoEEtnwdgj6D6Uo9K/Dynz9jqIxSDu2YObJ69Q=

lib/appmetrics/appmetrics.go

@@ -28,7 +28,7 @@ func initExposeMetadata() {
 	metrics.ExposeMetadata(*exposeMetadata)
 }
 
-var versionRe = regexp.MustCompile(`v\d+\.\d+\.\d+(?:-enterprise)?(?:-cluster)?`)
+var versionRe = regexp.MustCompile(`v\d+\.\d+\.\d+(?:-enterprise)?(?:-cluster.*)?`)
 
 // WritePrometheusMetrics writes all the registered metrics to w in Prometheus exposition format.
 func WritePrometheusMetrics(w io.Writer) {