update documentation

Previously, config like this:
```
users:
  - jwt:
      skip_verify: true
    url_prefix:
      - "http://backend"
```
Would print a message saying that 0 users were loaded which leads to
confusion.

Related PR https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11050/

.github/workflows/build.yml

@@ -22,8 +22,7 @@ on:
       - '!app/vmui/**'
       - '.github/workflows/build.yml'
 
-permissions:
-  contents: read
+permissions: {}
 
 concurrency:
   cancel-in-progress: true
@@ -32,6 +31,8 @@ concurrency:
 jobs:
   build:
     name: ${{ matrix.os }}-${{ matrix.arch }}
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
@@ -57,15 +58,17 @@ jobs:
             arch: amd64
           - os: openbsd
             arch: amd64
+          - os: netbsd
+            arch: amd64
           - os: windows
             arch: amd64
     steps:
       - name: Code checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Setup Go
         id: go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
           cache-dependency-path: |
             go.sum

.github/workflows/changelog-linter.yml

@@ -5,11 +5,15 @@ on:
     paths:
       - "docs/victoriametrics/changelog/CHANGELOG.md"
 
+permissions: {}
+
 jobs:
   tip-lint:
+    permissions:
+      contents: read
     runs-on: 'ubuntu-latest'
     steps:
-      - uses: 'actions/checkout@v6'
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           # needed for proper diff
           fetch-depth: 0

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

@@ -3,12 +3,16 @@ name: check-commit-signed
 on:
   pull_request:
 
+permissions: {}
+
 jobs:
   check-commit-signed:
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           fetch-depth: 0  # we need full history for commit verification
 

.github/workflows/check-licenses.yml

@@ -6,20 +6,22 @@ on:
   pull_request:
     paths:
       - 'vendor'
-permissions:
-  contents: read
+
+permissions: {}
 
 jobs:
   build:
     name: Build
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@master
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Setup Go
         id: go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
           go-version-file: 'go.mod'
           cache: false
@@ -27,7 +29,7 @@ jobs:
       - run: go version
 
       - name: Cache Go artifacts
-        uses: actions/cache@v5
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
         with:
           path: |
             ~/.cache/go-build

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

@@ -18,6 +18,8 @@ concurrency:
   cancel-in-progress: true
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
 
+permissions: {}
+
 jobs:
   analyze:
     name: Analyze
@@ -29,18 +31,18 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Set up Go
         id: go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
           cache: false
           go-version-file: 'go.mod'
       - run: go version
 
       - name: Cache Go artifacts
-        uses: actions/cache@v5
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
         with:
           path: |
             ~/.cache/go-build
@@ -50,14 +52,14 @@ jobs:
           restore-keys: go-artifacts-${{ runner.os }}-codeql-analyze-${{ steps.go.outputs.go-version }}-
 
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@v4.35.1
+        uses: github/codeql-action/init@e46ed2cbd01164d986452f91f178727624ae40d7  # v4.35.3
         with:
           languages: go
 
       - name: Autobuild
-        uses: github/codeql-action/autobuild@v4.35.1
+        uses: github/codeql-action/autobuild@e46ed2cbd01164d986452f91f178727624ae40d7  # v4.35.3
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v4.35.1
+        uses: github/codeql-action/analyze@e46ed2cbd01164d986452f91f178727624ae40d7  # v4.35.3
         with:
           category: 'language:go'

.github/workflows/docs.yaml

@@ -7,28 +7,30 @@ on:
       - 'docs/**'
       - '.github/workflows/docs.yaml'
   workflow_dispatch: {}
-permissions:
-  contents: read  # This is required for actions/checkout and to commit back image update
-  deployments: write
+
+permissions: {}
+
 jobs:
   build:
     name: Build
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           path: __vm
 
       - name: Checkout private code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           repository: VictoriaMetrics/vmdocs
           token: ${{ secrets.VM_BOT_GH_TOKEN }}
           path: __vm-docs
 
       - name: Import GPG key
-        uses: crazy-max/ghaction-import-gpg@v7
+        uses: crazy-max/ghaction-import-gpg@2dc316deee8e90f13e1a351ab510b4d5bc0c82cd  # v7.0.0
         id: import-gpg
         with:
           gpg_private_key: ${{ secrets.VM_BOT_GPG_PRIVATE_KEY }}

.github/workflows/test.yml

@@ -18,8 +18,7 @@ on:
       - 'go.*'
       - '.github/workflows/main.yml'
 
-permissions:
-  contents: read
+permissions: {}
 
 concurrency:
   cancel-in-progress: true
@@ -29,14 +28,16 @@ concurrency:
 jobs:
   lint:
     name: lint
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Setup Go
         id: go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
           cache-dependency-path: |
             go.sum
@@ -47,7 +48,7 @@ jobs:
       - run: go version
 
       - name: Cache golangci-lint
-        uses: actions/cache@v5
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
         with:
           path: |
             ~/.cache/golangci-lint
@@ -61,6 +62,8 @@ jobs:
 
   unit:
     name: unit
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
 
     strategy:
@@ -72,11 +75,11 @@ jobs:
 
     steps:
       - name: Code checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Setup Go
         id: go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
           cache-dependency-path: |
             go.sum
@@ -90,15 +93,17 @@ jobs:
 
   apptest:
     name: apptest
+    permissions:
+      contents: read
     runs-on: apptest
 
     steps:
       - name: Code checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Setup Go
         id: go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
           cache-dependency-path: |
             go.sum

.github/workflows/vmui.yml

@@ -16,11 +16,7 @@ on:
       - 'app/vmui/packages/vmui/**'
       - '.github/workflows/vmui.yml'
 
-permissions:
-  contents: read
-  packages: read
-  pull-requests: read
-  checks: write
+permissions: {}
 
 concurrency:
   cancel-in-progress: true
@@ -29,14 +25,18 @@ concurrency:
 jobs:
   vmui-checks:
     name: VMUI Checks (lint, test, typecheck)
+    permissions:
+      checks: write
+      contents: read
+      pull-requests: read
     runs-on: ubuntu-latest
     steps:
       - name: Code checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
       - name: Cache node_modules
         id: cache
-        uses: actions/cache@v5
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
         with:
           path: app/vmui/packages/vmui/node_modules
           key: vmui-deps-${{ runner.os }}-${{ hashFiles('app/vmui/packages/vmui/package-lock.json', 'app/vmui/Dockerfile-build') }}
@@ -69,7 +69,7 @@ jobs:
           VMUI_SKIP_INSTALL: true
 
       - name: Annotate Code Linting Results
-        uses: ataylorme/eslint-annotate-action@v3
+        uses: ataylorme/eslint-annotate-action@d57a1193d4c59cbfbf3f86c271f42612f9dbd9e9  # 3.0.0
         with:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           report-json: app/vmui/packages/vmui/vmui-lint-report.json

Makefile

@@ -485,8 +485,8 @@ apptest-legacy: victoria-metrics-race vmbackup-race vmrestore-race
 		curl --output-dir /tmp -LO $${URL}/$${VMSINGLE} && tar xzf /tmp/$${VMSINGLE} -C $${DIR} && \
 		curl --output-dir /tmp -LO $${URL}/$${VMCLUSTER} && tar xzf /tmp/$${VMCLUSTER} -C $${DIR} \
 	); \
-	VM_LEGACY_VMSINGLE_PATH=$${DIR}/victoria-metrics-prod \
-	VM_LEGACY_VMSTORAGE_PATH=$${DIR}/vmstorage-prod \
+	VMSINGLE_V1_132_0_PATH=$${DIR}/victoria-metrics-prod \
+	VMSTORAGE_V1_132_0_PATH=$${DIR}/vmstorage-prod \
 	go test ./apptest/tests -run="^TestLegacySingle.*"
 
 benchmark:
@@ -535,6 +535,15 @@ remove-golangci-lint:
 govulncheck: install-govulncheck
 	govulncheck ./...
 
+govulncheck-docker:
+	docker run -w $(PWD) -v $(PWD):$(PWD) \
+		-v govulncheck-gomod-cache:/root/go/pkg/mod \
+		-v govulncheck-gobuild-cache:/root/.cache/go-build \
+		-v govulncheck-go-bin:/root/go/bin \
+		--env="GOCACHE=/root/.cache/go-build" \
+		--env="GOMODCACHE=/root/go/pkg/mod" \
+		"$(GO_BUILDER_IMAGE)" /bin/sh -c "which govulncheck || go install golang.org/x/vuln/cmd/govulncheck@latest && govulncheck ./..."
+
 install-govulncheck:
 	which govulncheck || go install golang.org/x/vuln/cmd/govulncheck@latest
 

SECURITY.md

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

app/victoria-metrics/main.go

@@ -22,7 +22,6 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/pushmetrics"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
 )
 
 var (
@@ -30,21 +29,11 @@ var (
 	useProxyProtocol = flagutil.NewArrayBool("httpListenAddr.useProxyProtocol", "Whether to use proxy protocol for connections accepted at the corresponding -httpListenAddr . "+
 		"See https://www.haproxy.org/download/1.8/doc/proxy-protocol.txt . "+
 		"With enabled proxy protocol http server cannot serve regular /metrics endpoint. Use -pushmetrics.url for metrics pushing")
-	minScrapeInterval = flag.Duration("dedup.minScrapeInterval", 0, "Leave only the last sample in every time series per each discrete interval "+
-		"equal to -dedup.minScrapeInterval > 0. See also -streamAggr.dedupInterval and https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication")
 	dryRun = flag.Bool("dryRun", false, "Whether to check config files without running VictoriaMetrics. The following config files are checked: "+
 		"-promscrape.config, -relabelConfig and -streamAggr.config. Unknown config entries aren't allowed in -promscrape.config by default. "+
 		"This can be changed with -promscrape.config.strictParse=false command-line flag")
-	inmemoryDataFlushInterval = flag.Duration("inmemoryDataFlushInterval", 5*time.Second, "The interval for guaranteed saving of in-memory data to disk. "+
-		"The saved data survives unclean shutdowns such as OOM crash, hardware reset, SIGKILL, etc. "+
-		"Bigger intervals may help increase the lifetime of flash storage with limited write cycles (e.g. Raspberry PI). "+
-		"Smaller intervals increase disk IO load. Minimum supported value is 1s")
 	maxIngestionRate = flag.Int("maxIngestionRate", 0, "The maximum number of samples vmsingle can receive per second. Data ingestion is paused when the limit is exceeded. "+
 		"By default there are no limits on samples ingestion rate.")
-	finalDedupScheduleInterval = flag.Duration("storage.finalDedupScheduleCheckInterval", time.Hour, "The interval for checking when final deduplication process should be started."+
-		"Storage unconditionally adds 25% jitter to the interval value on each check evaluation."+
-		" Changing the interval to the bigger values may delay downsampling, deduplication for historical data."+
-		" See also https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication")
 )
 
 func main() {
@@ -87,12 +76,6 @@ func main() {
 	}
 	logger.Infof("starting VictoriaMetrics at %q...", listenAddrs)
 	startTime := time.Now()
-	storage.SetDedupInterval(*minScrapeInterval)
-	storage.SetDataFlushInterval(*inmemoryDataFlushInterval)
-	if *finalDedupScheduleInterval < time.Hour {
-		logger.Fatalf("-dedup.finalDedupScheduleCheckInterval cannot be smaller than 1 hour; got %s", *finalDedupScheduleInterval)
-	}
-	storage.SetFinalDedupScheduleInterval(*finalDedupScheduleInterval)
 	vmstorage.Init(promql.ResetRollupResultCacheIfNeeded)
 	vmselect.Init()
 	vminsertcommon.StartIngestionRateLimiter(*maxIngestionRate)

app/vmagent/main.go

@@ -83,6 +83,9 @@ var (
 	maxLabelsPerTimeseries = flag.Int("maxLabelsPerTimeseries", 0, "The maximum number of labels per time series to be accepted. Series with superfluous labels are ignored. In this case the vm_rows_ignored_total{reason=\"too_many_labels\"} metric at /metrics page is incremented")
 	maxLabelNameLen        = flag.Int("maxLabelNameLen", 0, "The maximum length of label names in the accepted time series. Series with longer label name are ignored. In this case the vm_rows_ignored_total{reason=\"too_long_label_name\"} metric at /metrics page is incremented")
 	maxLabelValueLen       = flag.Int("maxLabelValueLen", 0, "The maximum length of label values in the accepted time series. Series with longer label value are ignored. In this case the vm_rows_ignored_total{reason=\"too_long_label_value\"} metric at /metrics page is incremented")
+
+	enableMultitenancyViaHeaders = flag.Bool("enableMultitenancyViaHeaders", false, "Enables multitenancy via HTTP headers. "+
+		"See https://docs.victoriametrics.com/victoriametrics/vmagent/#multitenancy")
 )
 
 var (
@@ -115,6 +118,7 @@ func main() {
 	remotewrite.InitSecretFlags()
 	buildinfo.Init()
 	logger.Init()
+	opentelemetry.Init()
 	timeserieslimits.Init(*maxLabelsPerTimeseries, *maxLabelNameLen, *maxLabelValueLen)
 
 	if promscrape.IsDryRun() {
@@ -216,7 +220,7 @@ func getOpenTSDBHTTPInsertHandler() func(req *http.Request) error {
 	}
 	return func(req *http.Request) error {
 		path := strings.ReplaceAll(req.URL.Path, "//", "/")
-		at, err := getAuthTokenFromPath(path)
+		at, err := getAuthTokenFromPath(path, req.Header)
 		if err != nil {
 			return fmt.Errorf("cannot obtain auth token from path %q: %w", path, err)
 		}
@@ -224,8 +228,15 @@ func getOpenTSDBHTTPInsertHandler() func(req *http.Request) error {
 	}
 }
 
-func getAuthTokenFromPath(path string) (*auth.Token, error) {
-	p, err := httpserver.ParsePath(path)
+func parsePath(path string, header http.Header) (*httpserver.Path, error) {
+	if *enableMultitenancyViaHeaders {
+		return httpserver.ParsePathAndHeaders(path, header)
+	}
+	return httpserver.ParsePath(path)
+}
+
+func getAuthTokenFromPath(path string, header http.Header) (*auth.Token, error) {
+	p, err := parsePath(path, header)
 	if err != nil {
 		return nil, fmt.Errorf("cannot parse multitenant path: %w", err)
 	}
@@ -559,14 +570,15 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 }
 
 func processMultitenantRequest(w http.ResponseWriter, r *http.Request, path string) bool {
-	p, err := httpserver.ParsePath(path)
+	p, err := parsePath(path, r.Header)
 	if err != nil {
 		// Cannot parse multitenant path. Skip it - probably it will be parsed later.
 		return false
 	}
 	if p.Prefix != "insert" {
-		httpserver.Errorf(w, r, `unsupported multitenant prefix: %q; expected "insert"`, p.Prefix)
-		return true
+		// processMultitenantRequest is called for all unmatched path variants,
+		// but we should try parsing only /insert prefixed to avoid catching all possible paths.
+		return false
 	}
 	at, err := auth.NewTokenPossibleMultitenant(p.AuthToken)
 	if err != nil {

app/vmagent/opentelemetry/request_handler.go

@@ -25,6 +25,11 @@ var (
 	rowsPerInsert          = metrics.NewHistogram(`vmagent_rows_per_insert{type="opentelemetry"}`)
 )
 
+// Init must be called after flag.Parse and before using the opentelemetry package.
+func Init() {
+	stream.InitDecodeOptions()
+}
+
 // InsertHandlerForReader processes metrics from given reader.
 func InsertHandlerForReader(at *auth.Token, r io.Reader, encoding string) error {
 	return stream.ParseStream(r, encoding, nil, func(tss []prompb.TimeSeries, mms []prompb.MetricMetadata) error {

app/vmagent/remotewrite/client.go

@@ -2,6 +2,7 @@ package remotewrite
 
 import (
 	"bytes"
+	"context"
 	"errors"
 	"fmt"
 	"io"
@@ -59,6 +60,8 @@ var (
 		"Multiple headers must be delimited by '^^': -remoteWrite.headers='header1:value1^^header2:value2'")
 
 	basicAuthUsername     = flagutil.NewArrayString("remoteWrite.basicAuth.username", "Optional basic auth username to use for the corresponding -remoteWrite.url")
+	basicAuthUsernameFile = flagutil.NewArrayString("remoteWrite.basicAuth.usernameFile", "Optional path to basic auth username to use for the corresponding -remoteWrite.url. "+
+		"The file is re-read every second")
 	basicAuthPassword     = flagutil.NewArrayString("remoteWrite.basicAuth.password", "Optional basic auth password to use for the corresponding -remoteWrite.url")
 	basicAuthPasswordFile = flagutil.NewArrayString("remoteWrite.basicAuth.passwordFile", "Optional path to basic auth password to use for the corresponding -remoteWrite.url. "+
 		"The file is re-read every second")
@@ -223,12 +226,14 @@ func getAuthConfig(argIdx int) (*promauth.Config, error) {
 		hdrs = strings.Split(headersValue, "^^")
 	}
 	username := basicAuthUsername.GetOptionalArg(argIdx)
+	usernameFile := basicAuthUsernameFile.GetOptionalArg(argIdx)
 	password := basicAuthPassword.GetOptionalArg(argIdx)
 	passwordFile := basicAuthPasswordFile.GetOptionalArg(argIdx)
 	var basicAuthCfg *promauth.BasicAuthConfig
-	if username != "" || password != "" || passwordFile != "" {
+	if username != "" || usernameFile != "" || password != "" || passwordFile != "" {
 		basicAuthCfg = &promauth.BasicAuthConfig{
 			Username:     username,
+			UsernameFile: usernameFile,
 			Password:     promauth.NewSecret(password),
 			PasswordFile: passwordFile,
 		}
@@ -306,11 +311,6 @@ func (c *client) runWorker() {
 		if !ok {
 			return
 		}
-		if len(block) == 0 {
-			// skip empty data blocks from sending
-			// see https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6241
-			continue
-		}
 		go func() {
 			startTime := time.Now()
 			ch <- c.sendBlock(block)
@@ -326,15 +326,20 @@ func (c *client) runWorker() {
 			c.fq.MustWriteBlockIgnoreDisabledPQ(block)
 			return
 		case <-c.stopCh:
-			// c must be stopped. Wait for a while in the hope the block will be sent.
-			graceDuration := 5 * time.Second
+			// c must be stopped. Wait up to 5 seconds for the in-flight request to complete.
+			// If it succeeds, drain the remaining in-memory queue before returning.
+			stopCtx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+			defer cancel()
+
 			select {
 			case ok := <-ch:
 				if !ok {
 					// Return unsent block to the queue.
 					c.fq.MustWriteBlockIgnoreDisabledPQ(block)
+				} else {
+					c.drainInMemoryQueue(stopCtx, block[:0])
 				}
-			case <-time.After(graceDuration):
+			case <-stopCtx.Done():
 				// Return unsent block to the queue.
 				c.fq.MustWriteBlockIgnoreDisabledPQ(block)
 			}
@@ -466,7 +471,7 @@ again:
 				goto again
 			}
 
-			logger.Warnf("failed to repack zstd block (%s bytes) to snappy: %s; The block will be rejected. "+
+			logger.Warnf("failed to repack zstd block (%d bytes) to snappy: %s; The block will be rejected. "+
 				"Possible cause: ungraceful shutdown leading to persisted queue corruption.",
 				zstdBlockLen, err)
 		}
@@ -504,6 +509,32 @@ again:
 	goto again
 }
 
+func (c *client) drainInMemoryQueue(stopCtx context.Context, block []byte) {
+	var ok bool
+	for {
+		select {
+		case <-stopCtx.Done():
+			return
+		default:
+		}
+
+		block, ok = c.fq.MustReadInMemoryBlock(block[:0])
+		if !ok {
+			// The in memory queue has already been drained,
+			// or persisted queue is being used.
+			// In this case it is guaranteed that fq will be empty
+			return
+		}
+
+		// at this stage c.stopCh should be closed
+		// so sendBlock function should not perform retries
+		if ok := c.sendBlock(block); !ok {
+			c.fq.MustWriteBlockIgnoreDisabledPQ(block)
+			return
+		}
+	}
+}
+
 var remoteWriteRejectedLogger = logger.WithThrottler("remoteWriteRejected", 5*time.Second)
 var remoteWriteRetryLogger = logger.WithThrottler("remoteWriteRetry", 5*time.Second)
 

app/vmagent/remotewrite/client_test.go

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

app/vmagent/remotewrite/remotewrite.go

@@ -79,7 +79,8 @@ var (
 		"writing them to remote storage. "+
 		"Examples: -remoteWrite.roundDigits=2 would round 1.236 to 1.24, while -remoteWrite.roundDigits=-1 would round 126.78 to 130. "+
 		"By default, digits rounding is disabled. Set it to 100 for disabling it for a particular remote storage. "+
-		"This option may be used for improving data compression for the stored metrics")
+		"This option may be used for improving data compression for the stored metrics. "+
+		"See also -remoteWrite.significantFigures")
 	sortLabels = flag.Bool("sortLabels", false, `Whether to sort labels for incoming samples before writing them to all the configured remote storage systems. `+
 		`This may be needed for reducing memory usage at remote storage when the order of labels in incoming samples is random. `+
 		`For example, if m{k1="v1",k2="v2"} may be sent as m{k2="v2",k1="v1"}`+
@@ -151,6 +152,10 @@ func InitSecretFlags() {
 		// remoteWrite.url can contain authentication codes, so hide it at `/metrics` output.
 		flagutil.RegisterSecretFlag("remoteWrite.url")
 	}
+	// remoteWrite.proxyURL can contain authentication codes.
+	flagutil.RegisterSecretFlag("remoteWrite.proxyURL")
+	// remoteWrite.headers can contain auth headers such as Authorization and API keys.
+	flagutil.RegisterSecretFlag("remoteWrite.headers")
 }
 
 var (
@@ -167,6 +172,18 @@ func Init() {
 	if len(*remoteWriteURLs) == 0 {
 		logger.Fatalf("at least one `-remoteWrite.url` command-line flag must be set")
 	}
+	if *shardByURL && len(*disableOnDiskQueue) > 1 {
+		disableOnDiskQueues := *disableOnDiskQueue
+
+		firstValue := disableOnDiskQueues[0]
+		for _, v := range disableOnDiskQueues[1:] {
+			if firstValue != v {
+				logger.Fatalf("all -remoteWrite.url targets must have the same -remoteWrite.disableOnDiskQueue setting when -remoteWrite.shardByURL is enabled; " +
+					"either enable or disable -remoteWrite.disableOnDiskQueue for all targets")
+			}
+		}
+	}
+
 	if limit := getMaxHourlySeries(); limit > 0 {
 		hourlySeriesLimiter = bloomfilter.NewLimiter(limit, time.Hour)
 		_ = metrics.NewGauge(`vmagent_hourly_series_limit_max_series`, func() float64 {
@@ -285,6 +302,7 @@ func initRemoteWriteCtxs(urls []string) {
 		rwctxs[i] = newRemoteWriteCtx(i, remoteWriteURL, sanitizedURL)
 		rwctxIdx[i] = i
 	}
+	fs.RegisterPathFsMetrics(*tmpDataPath)
 
 	if *shardByURL {
 		consistentHashNodes := make([]string, 0, len(urls))
@@ -498,7 +516,9 @@ func tryPush(at *auth.Token, wr *prompb.WriteRequest, forceDropSamplesOnFailure
 //
 // calculateHealthyRwctxIdx will rely on the order of rwctx to be in ascending order.
 func getEligibleRemoteWriteCtxs(tss []prompb.TimeSeries, forceDropSamplesOnFailure bool) ([]*remoteWriteCtx, bool) {
-	if !disableOnDiskQueueAny {
+	// When -remoteWrite.shardByURL=true always use all configured remote writes to preserve stable metrics distribution across shards.
+	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10507
+	if !disableOnDiskQueueAny || *shardByURL {
 		return rwctxsGlobal, true
 	}
 
@@ -513,12 +533,6 @@ func getEligibleRemoteWriteCtxs(tss []prompb.TimeSeries, forceDropSamplesOnFailu
 				return nil, false
 			}
 			rowsCount := getRowsCount(tss)
-			if *shardByURL {
-				// Todo: When shardByURL is enabled, the following metrics won't be 100% accurate. Because vmagent don't know
-				// which rwctx should data be pushed to yet. Let's consider the hashing algorithm fair and will distribute
-				// data to all rwctxs evenly.
-				rowsCount = rowsCount / len(rwctxsGlobal)
-			}
 			rwctx.rowsDroppedOnPushFailure.Add(rowsCount)
 		}
 	}
@@ -698,7 +712,7 @@ func shardAmountRemoteWriteCtx(tssBlock []prompb.TimeSeries, shards [][]prompb.T
 			}
 			tmpLabels.Labels = hashLabels
 		}
-		h := getLabelsHash(hashLabels)
+		h := getLabelsHashForShard(hashLabels)
 
 		// Get the rwctxIdx through consistent hashing and then map it to the index in shards.
 		// The rwctxIdx is not always equal to the shardIdx, for example, when some rwctx are not available.
@@ -789,11 +803,28 @@ var (
 	dailySeriesLimitRowsDropped  = metrics.NewCounter(`vmagent_daily_series_limit_rows_dropped_total`)
 )
 
+// getLabelsHashForShard is a separate function from getLabelsHash because
+// it omits the '=' separator between label name and value for backward compatibility.
+// Changing it would re-shard all series across remoteWrite targets.
+func getLabelsHashForShard(labels []prompb.Label) uint64 {
+	bb := labelsHashBufPool.Get()
+	b := bb.B[:0]
+	for _, label := range labels {
+		b = append(b, label.Name...)
+		b = append(b, label.Value...)
+	}
+	h := xxhash.Sum64(b)
+	bb.B = b
+	labelsHashBufPool.Put(bb)
+	return h
+}
+
 func getLabelsHash(labels []prompb.Label) uint64 {
 	bb := labelsHashBufPool.Get()
 	b := bb.B[:0]
 	for _, label := range labels {
 		b = append(b, label.Name...)
+		b = append(b, '=')
 		b = append(b, label.Value...)
 	}
 	h := xxhash.Sum64(b)

app/vmagent/remotewrite/remotewrite_test.go

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

app/vmalert-tool/unittest/unittest.go

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

app/vmalert/config/config.go

@@ -113,15 +113,15 @@ func (g *Group) Validate(validateTplFn ValidateTplFn, validateExpressions bool)
 			// because correct types must be inherited after unmarshalling.
 			exprValidator := g.Type.ValidateExpr
 			if err := exprValidator(r.Expr); err != nil {
-				return fmt.Errorf("invalid expression for rule  %q: %w", ruleName, err)
+				return fmt.Errorf("invalid expression for rule %q: %w", ruleName, err)
 			}
 		}
 		if validateTplFn != nil {
 			if err := validateTplFn(r.Annotations); err != nil {
-				return fmt.Errorf("invalid annotations for rule  %q: %w", ruleName, err)
+				return fmt.Errorf("invalid annotations for rule %q: %w", ruleName, err)
 			}
 			if err := validateTplFn(r.Labels); err != nil {
-				return fmt.Errorf("invalid labels for rule  %q: %w", ruleName, err)
+				return fmt.Errorf("invalid labels for rule %q: %w", ruleName, err)
 			}
 		}
 	}

app/vmalert/config/config_test.go

@@ -121,7 +121,7 @@ func TestParse_Failure(t *testing.T) {
 	f([]string{"testdata/dir/rules2-bad.rules"}, "function \"unknown\" not defined")
 	f([]string{"testdata/dir/rules3-bad.rules"}, "either `record` or `alert` must be set")
 	f([]string{"testdata/dir/rules4-bad.rules"}, "either `record` or `alert` must be set")
-	f([]string{"testdata/rules/rules1-bad.rules"}, "bad graphite expr")
+	f([]string{"testdata/rules/rules1-bad.rules"}, "bad GraphiteQL expr")
 	f([]string{"testdata/rules/vlog-rules0-bad.rules"}, "bad LogsQL expr")
 	f([]string{"testdata/dir/rules6-bad.rules"}, "missing ':' in header")
 	f([]string{"testdata/rules/rules-multi-doc-bad.rules"}, "unknown fields")
@@ -283,7 +283,7 @@ func TestGroupValidate_Failure(t *testing.T) {
 				Expr:   "up | 0",
 			},
 		},
-	}, true, "bad prometheus expr")
+	}, true, "bad MetricsQL expr")
 
 	f(&Group{
 		Name: "test graphite expr",
@@ -293,7 +293,7 @@ func TestGroupValidate_Failure(t *testing.T) {
 				"description": "some-description",
 			}},
 		},
-	}, true, "bad graphite expr")
+	}, true, "bad GraphiteQL expr")
 
 	f(&Group{
 		Name: "test vlogs expr",
@@ -327,7 +327,7 @@ func TestGroupValidate_Failure(t *testing.T) {
 				Expr:   "sum(up == 0 ) by (host)",
 			},
 		},
-	}, true, "bad graphite expr")
+	}, true, "bad GraphiteQL expr")
 
 	f(&Group{
 		Name: "test vlogs with prometheus exp",
@@ -351,7 +351,7 @@ func TestGroupValidate_Failure(t *testing.T) {
 				For:    promutil.NewDuration(10 * time.Millisecond),
 			},
 		},
-	}, true, "bad prometheus expr")
+	}, true, "bad MetricsQL expr")
 }
 
 func TestGroupValidate_Success(t *testing.T) {

app/vmalert/config/types.go

@@ -66,11 +66,11 @@ func (t *Type) ValidateExpr(expr string) error {
 	switch t.String() {
 	case "graphite":
 		if _, err := graphiteql.Parse(expr); err != nil {
-			return fmt.Errorf("bad graphite expr: %q, err: %w", expr, err)
+			return fmt.Errorf("bad GraphiteQL expr: %q, err: %w", expr, err)
 		}
 	case "prometheus":
 		if _, err := metricsql.Parse(expr); err != nil {
-			return fmt.Errorf("bad prometheus expr: %q, err: %w", expr, err)
+			return fmt.Errorf("bad MetricsQL expr: %q, err: %w", expr, err)
 		}
 	case "vlogs":
 		q, err := logstorage.ParseStatsQuery(expr, 0)

app/vmalert/datasource/client_test.go

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

app/vmalert/datasource/init.go

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

app/vmalert/notifier/alertmanager.go

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

app/vmalert/notifier/config_watcher.go

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

app/vmalert/notifier/init.go

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

app/vmalert/notifier/notifier.go

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

app/vmalert/remoteread/init.go

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

app/vmalert/remotewrite/client.go

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

app/vmalert/remotewrite/client_test.go

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

app/vmalert/remotewrite/debug_client.go

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

app/vmalert/remotewrite/init.go

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

app/vmalert/rule/group.go

@@ -8,6 +8,7 @@ import (
 	"hash/fnv"
 	"maps"
 	"net/url"
+	"path"
 	"sync"
 	"time"
 
@@ -42,6 +43,9 @@ var (
 		"For example, if lookback=1h then range from now() to now()-1h will be scanned.")
 	maxStartDelay = flag.Duration("group.maxStartDelay", 5*time.Minute, "Defines the max delay before starting the group evaluation. Group's start is artificially delayed for random duration on interval"+
 		" [0..min(--group.maxStartDelay, group.interval)]. This helps smoothing out the load on the configured datasource, so evaluations aren't executed too close to each other.")
+	ruleStripFilePath = flag.Bool("rule.stripFilePath", false, "Whether to strip rule file paths in logs and all API responses, including /metrics. "+
+		"For example, file path '/path/to/tenant_id/rules.yml' will be stripped to 'groupHashID/rules.yml'. "+
+		"This flag may be useful for hiding sensitive information in file paths, such as S3 bucket details.")
 )
 
 // Group is an entity for grouping rules
@@ -91,6 +95,7 @@ type groupMetrics struct {
 	iterationTotal    *metrics.Counter
 	iterationDuration *metrics.Summary
 	iterationMissed   *metrics.Counter
+	iterationReset    *metrics.Counter
 	iterationInterval *metrics.Gauge
 }
 
@@ -147,6 +152,12 @@ func NewGroup(cfg config.Group, qb datasource.QuerierBuilder, defaultInterval ti
 		g.EvalDelay = &cfg.EvalDelay.D
 	}
 	g.id = g.CreateID()
+	// strip file path from group.File after generated group ID when ruleStripFilePath is set,
+	// so it won't be exposed in logs and api responses
+	if *ruleStripFilePath {
+		_, filename := path.Split(g.File)
+		g.File = fmt.Sprintf("%d/%s", g.id, filename)
+	}
 	for _, h := range cfg.Headers {
 		g.Headers[h.Key] = h.Value
 	}
@@ -320,6 +331,7 @@ func (g *Group) Init() {
 	g.metrics.iterationTotal = g.metrics.set.NewCounter(fmt.Sprintf(`vmalert_iteration_total{%s}`, labels))
 	g.metrics.iterationDuration = g.metrics.set.NewSummary(fmt.Sprintf(`vmalert_iteration_duration_seconds{%s}`, labels))
 	g.metrics.iterationMissed = g.metrics.set.NewCounter(fmt.Sprintf(`vmalert_iteration_missed_total{%s}`, labels))
+	g.metrics.iterationReset = g.metrics.set.NewCounter(fmt.Sprintf(`vmalert_iteration_reset_total{%s}`, labels))
 	g.metrics.iterationInterval = g.metrics.set.NewGauge(fmt.Sprintf(`vmalert_iteration_interval_seconds{%s}`, labels), func() float64 {
 		i := g.Interval.Seconds()
 		return i
@@ -464,14 +476,16 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
 			if missed < 0 {
 				// missed can become < 0 due to irregular delays during evaluation
 				// which can result in time.Since(evalTS) < g.Interval;
-				// or the system wall clock was changed backward
-				missed = 0
+				// or the system wall clock was changed backward,
+				// Reset the evalTS to the current time.
 				evalTS = time.Now()
+				g.metrics.iterationReset.Inc()
+			} else {
+				evalTS = evalTS.Add((missed + 1) * g.Interval)
 			}
 			if missed > 0 {
 				g.metrics.iterationMissed.Inc()
 			}
-			evalTS = evalTS.Add((missed + 1) * g.Interval)
 
 			eval(evalCtx, evalTS)
 		}

app/vmalert/rule/group_test.go

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

app/vmalert/rule/web.go

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

app/vmalert/templates/template.go

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

app/vmalert/templates/template_test.go

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

app/vmalert/vmalertutil/auth.go

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

app/vmalert/web.go

@@ -11,6 +11,8 @@ import (
 	"strconv"
 	"strings"
 
+	"github.com/VictoriaMetrics/metricsql"
+
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/rule"
@@ -160,12 +162,12 @@ func (rh *requestHandler) handler(w http.ResponseWriter, r *http.Request) bool {
 
 	case "/vmalert/api/v1/alerts", "/api/v1/alerts":
 		// path used by Grafana for ng alerting
-		gf, err := newGroupsFilter(r)
+		af, err := newAlertsFilter(r)
 		if err != nil {
 			errJson(w, r, err)
 			return true
 		}
-		data, err := rh.listAlerts(gf)
+		data, err := rh.listAlerts(af)
 		if err != nil {
 			errJson(w, r, err)
 			return true
@@ -325,6 +327,48 @@ func (gf *groupsFilter) matches(group *rule.Group) bool {
 	return true
 }
 
+type alertsFilter struct {
+	gf    *groupsFilter
+	match [][]metricsql.LabelFilter
+}
+
+func getMatchFilters(matches []string) ([][]metricsql.LabelFilter, *httpserver.ErrorWithStatusCode) {
+	if len(matches) == 0 {
+		return nil, nil
+	}
+	tfss := make([][]metricsql.LabelFilter, 0, len(matches))
+	for _, s := range matches {
+		expr, err := metricsql.Parse(s)
+		if err != nil {
+			return nil, errResponse(fmt.Errorf(`invalid parameter "match[]": failed to parse %q: %w`, s, err), http.StatusBadRequest)
+		}
+		me, ok := expr.(*metricsql.MetricExpr)
+		if !ok {
+			return nil, errResponse(fmt.Errorf(`invalid parameter "match[]": expecting metricSelector; got %q`, expr.AppendString(nil)), http.StatusBadRequest)
+		}
+		if len(me.LabelFilterss) == 0 {
+			return nil, errResponse(fmt.Errorf(`invalid parameter "match[]": labelFilterss cannot be empty`), http.StatusBadRequest)
+		}
+		tfss = append(tfss, me.LabelFilterss...)
+	}
+	return tfss, nil
+}
+
+func newAlertsFilter(r *http.Request) (*alertsFilter, *httpserver.ErrorWithStatusCode) {
+	gf, err := newGroupsFilter(r)
+	if err != nil {
+		return nil, err
+	}
+
+	var af alertsFilter
+	af.gf = gf
+	af.match, err = getMatchFilters(r.Form["match[]"])
+	if err != nil {
+		return nil, err
+	}
+	return &af, nil
+}
+
 // see https://prometheus.io/docs/prometheus/latest/querying/api/#rules
 type rulesFilter struct {
 	gf             *groupsFilter
@@ -335,6 +379,7 @@ type rulesFilter struct {
 	maxGroups      int
 	pageNum        int
 	search         string
+	match          [][]metricsql.LabelFilter
 	extendedStates bool
 }
 
@@ -355,7 +400,10 @@ func newRulesFilter(r *http.Request) (*rulesFilter, *httpserver.ErrorWithStatusC
 			return nil, errResponse(fmt.Errorf(`invalid parameter "type": not supported value %q`, ruleTypeParam), http.StatusBadRequest)
 		}
 	}
-
+	rf.match, err = getMatchFilters(r.Form["match[]"])
+	if err != nil {
+		return nil, err
+	}
 	states := vs["state"]
 	if len(states) == 0 {
 		states = vs["filter"]
@@ -416,12 +464,47 @@ func (rf *rulesFilter) matchesRule(r *rule.ApiRule) bool {
 	if len(rf.ruleNames) > 0 && !slices.Contains(rf.ruleNames, r.Name) {
 		return false
 	}
+	if !areLabelsMatch(r.Labels, rf.match) {
+		return false
+	}
 	if len(rf.states) == 0 {
 		return true
 	}
 	return slices.Contains(rf.states, r.State)
 }
 
+func areLabelsMatch(labels map[string]string, matches [][]metricsql.LabelFilter) bool {
+	if len(matches) == 0 {
+		return true
+	}
+	// labels need to match at least one of the provided match[] arg
+	return slices.ContainsFunc(matches, func(filters []metricsql.LabelFilter) bool {
+		for _, mf := range filters {
+			if !isLabelFilterMatch(labels[mf.Label], mf) {
+				return false
+			}
+		}
+		return true
+	})
+}
+
+func isLabelFilterMatch(s string, match metricsql.LabelFilter) bool {
+	if !match.IsRegexp {
+		if match.IsNegative {
+			return s != match.Value
+		}
+		return s == match.Value
+	}
+	re, err := metricsql.CompileRegexpAnchored(match.Value)
+	if err != nil {
+		return false
+	}
+	if match.IsNegative {
+		return !re.MatchString(s)
+	}
+	return re.MatchString(s)
+}
+
 func (rh *requestHandler) groups(rf *rulesFilter) *listGroupsResponse {
 	rh.m.groupsMu.RLock()
 	defer rh.m.groupsMu.RUnlock()
@@ -543,14 +626,14 @@ func (rh *requestHandler) groupAlerts() []rule.GroupAlerts {
 	return gAlerts
 }
 
-func (rh *requestHandler) listAlerts(gf *groupsFilter) ([]byte, *httpserver.ErrorWithStatusCode) {
+func (rh *requestHandler) listAlerts(af *alertsFilter) ([]byte, *httpserver.ErrorWithStatusCode) {
 	rh.m.groupsMu.RLock()
 	defer rh.m.groupsMu.RUnlock()
 
 	lr := listAlertsResponse{Status: "success"}
 	lr.Data.Alerts = make([]*rule.ApiAlert, 0)
 	for _, group := range rh.m.groups {
-		if !gf.matches(group) {
+		if !af.gf.matches(group) {
 			continue
 		}
 		g := group.ToAPI()
@@ -558,7 +641,11 @@ func (rh *requestHandler) listAlerts(gf *groupsFilter) ([]byte, *httpserver.Erro
 			if r.Type != rule.TypeAlerting {
 				continue
 			}
-			lr.Data.Alerts = append(lr.Data.Alerts, r.Alerts...)
+			for _, alert := range r.Alerts {
+				if areLabelsMatch(alert.Labels, af.match) {
+					lr.Data.Alerts = append(lr.Data.Alerts, alert)
+				}
+			}
 		}
 	}
 

app/vmalert/web.qtpl

@@ -348,7 +348,7 @@
                 typeK, ns := keys[i], targets[notifier.TargetType(keys[i])]
                 count := len(ns)
             %}
-            <div class="w-100 flex-column vm-group">
+            <div class="w-100 flex-column">
                 <span class="d-flex justify-content-between" id="group-{%s typeK %}">
                     <a href="#group-{%s typeK %}">{%s typeK %} ({%d count %})</a>
                     <span
@@ -361,7 +361,7 @@
                 <div id="item-{%s typeK %}" class="collapse show">
                     <table class="table table-striped table-hover table-sm">
                         <thead>
-                            <tr class="vm-item">
+                            <tr>
                                 <th scope="col">Labels</th>
                                 <th scope="col">Address</th>
                             </tr>

app/vmalert/web.qtpl.go

@@ -1115,7 +1115,7 @@ func StreamListTargets(qw422016 *qt422016.Writer, r *http.Request, targets map[n
 
 //line app/vmalert/web.qtpl:350
 			qw422016.N().S(`
-            <div class="w-100 flex-column vm-group">
+            <div class="w-100 flex-column">
                 <span class="d-flex justify-content-between" id="group-`)
 //line app/vmalert/web.qtpl:352
 			qw422016.E().S(typeK)
@@ -1152,7 +1152,7 @@ func StreamListTargets(qw422016 *qt422016.Writer, r *http.Request, targets map[n
 			qw422016.N().S(`" class="collapse show">
                     <table class="table table-striped table-hover table-sm">
                         <thead>
-                            <tr class="vm-item">
+                            <tr>
                                 <th scope="col">Labels</th>
                                 <th scope="col">Address</th>
                             </tr>

app/vmalert/web_test.go

@@ -10,6 +10,8 @@ import (
 	"testing"
 	"time"
 
+	"github.com/VictoriaMetrics/metricsql"
+
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
@@ -37,12 +39,14 @@ func TestHandler(t *testing.T) {
 			Concurrency: 1,
 			Rules: []config.Rule{
 				{
-					ID:    0,
-					Alert: "alert",
+					ID:     0,
+					Alert:  "alert",
+					Labels: map[string]string{"job": "foo"},
 				},
 				{
 					ID:     1,
 					Record: "record",
+					Labels: map[string]string{"job": "bar"},
 				},
 			},
 		}, fq, 1*time.Minute, nil)
@@ -128,6 +132,18 @@ func TestHandler(t *testing.T) {
 		if length := len(lr.Data.Alerts); length != 2 {
 			t.Fatalf("expected 2 alert got %d", length)
 		}
+
+		lr = listAlertsResponse{}
+		getResp(t, ts.URL+`/api/v1/alerts?match[]={job="foo"}`, &lr, 200)
+		if length := len(lr.Data.Alerts); length != 3 {
+			t.Fatalf("expected 3 alerts got %d", length)
+		}
+
+		lr = listAlertsResponse{}
+		getResp(t, ts.URL+`/api/v1/alerts?match[]={job="bar"}`, &lr, 200)
+		if length := len(lr.Data.Alerts); length != 0 {
+			t.Fatalf("expected 0 alerts got %d", length)
+		}
 	})
 	t.Run("/api/v1/alert?alertID&groupID", func(t *testing.T) {
 		expAlert := rule.NewAlertAPI(ar, ar.GetAlerts()[0])
@@ -242,6 +258,13 @@ func TestHandler(t *testing.T) {
 		check("/vmalert/api/v1/rules?datasource_type=graphite", 200, 1, 2)
 		check("/vmalert/api/v1/rules?datasource_type=graphiti", 400, 0, 0)
 
+		// invalid match[] params
+		check(`/vmalert/api/v1/rules?match[]={job=!"foo"}`, 400, 0, 0)
+		check(`/vmalert/api/v1/rules?match[]={job="foo"}`, 200, 3, 3)
+		check(`/vmalert/api/v1/rules?match[]={job="bar"}`, 200, 3, 3)
+		check(`/vmalert/api/v1/rules?match[]={job="bar"}&match[]={job="foo"}`, 200, 3, 6)
+		check(`/vmalert/api/v1/rules?match[]={job="barzz"}`, 200, 0, 0)
+
 		// no filtering expected due to bad params
 		check("/api/v1/rules?type=badParam", 400, 0, 0)
 		check("/api/v1/rules?foo=bar", 200, 3, 6)
@@ -367,3 +390,116 @@ func TestEmptyResponse(t *testing.T) {
 		}
 	})
 }
+
+func TestMatchesRule(t *testing.T) {
+	parseMatch := func(t *testing.T, selectors []string) [][]metricsql.LabelFilter {
+		t.Helper()
+		var match [][]metricsql.LabelFilter
+		for _, s := range selectors {
+			expr, err := metricsql.Parse(s)
+			if err != nil {
+				t.Fatalf("failed to parse selector %q: %v", s, err)
+			}
+			me, ok := expr.(*metricsql.MetricExpr)
+			if !ok {
+				t.Fatalf("expected MetricExpr for %q, got %T", s, expr)
+			}
+			match = append(match, me.LabelFilterss...)
+		}
+		return match
+	}
+
+	f := func(t *testing.T, selectors []string, labels map[string]string, wantMatch bool) {
+		t.Helper()
+		rf := &rulesFilter{
+			gf:    &groupsFilter{},
+			match: parseMatch(t, selectors),
+		}
+		r := &rule.ApiRule{Labels: labels}
+		got := rf.matchesRule(r)
+		if got != wantMatch {
+			t.Fatalf("matchesRule(%v) with selectors %v: got %v, want %v",
+				labels, selectors, got, wantMatch)
+		}
+	}
+
+	f(t, nil, map[string]string{"foo": "bar"}, true)
+
+	f(t, []string{`{foo="bar"}`}, map[string]string{"foo": "bar"}, true)
+	f(t, []string{`{foo="bar"}`}, map[string]string{"foo": "baz"}, false)
+
+	f(t, []string{`{foo="bar"}`}, map[string]string{"bar": "baz"}, false)
+	f(t, []string{`{foo=""}`}, map[string]string{"bar": "baz"}, true)
+
+	f(t, []string{`{foo!="bar"}`}, map[string]string{"foo": "baz"}, true)
+	f(t, []string{`{foo!="bar"}`}, map[string]string{"foo": "bar"}, false)
+
+	f(t, []string{`{foo=~"bar.*"}`}, map[string]string{"foo": "bar"}, true)
+	f(t, []string{`{foo=~"bar.*"}`}, map[string]string{"foo": "baz"}, false)
+	f(t, []string{`{bar=~"baz|bar"}`}, map[string]string{"bar": "baz"}, true)
+	f(t, []string{`{bar=~"baz|bar"}`}, map[string]string{"bar": "bar"}, true)
+	f(t, []string{`{bar=~"baz|bar"}`}, map[string]string{"bar": "foo"}, false)
+
+	f(t, []string{`{foo!~"bar.*"}`}, map[string]string{"foo": "baz"}, true)
+	f(t, []string{`{foo!~"bar.*"}`}, map[string]string{"foo": "bar"}, false)
+
+	// single match[] with multiple filters
+	f(t,
+		[]string{`{job="foo",instance="bar"}`},
+		map[string]string{"job": "foo", "instance": "bar"},
+		true,
+	)
+	f(t,
+		[]string{`{job="foo",instance="bar"}`},
+		map[string]string{"job": "other", "instance": "bar"},
+		false,
+	)
+
+	f(t,
+		[]string{`{foo="bar",baz=~"b.*"}`},
+		map[string]string{"foo": "bar", "baz": "bazinga"},
+		true,
+	)
+	f(t,
+		[]string{`{foo="bar",baz=~"b.*"}`},
+		map[string]string{"foo": "other", "baz": "bazinga"},
+		false,
+	)
+
+	// multiple matches[]
+	f(t,
+		[]string{`{foo="bar"}`, `{foo="baz"}`},
+		map[string]string{"foo": "baz"},
+		true,
+	)
+	f(t,
+		[]string{`{foo="bar"}`, `{foo="baz"}`},
+		map[string]string{"foo": "unknown"},
+		false,
+	)
+	f(t,
+		[]string{`{foo=~"bar.*"}`, `{bar=~"baz.*"}`},
+		map[string]string{"bar": "bazinga"},
+		true,
+	)
+	f(t,
+		[]string{`{foo=~"bar.*"}`, `{bar=~"baz.*"}`},
+		map[string]string{"foo": "bartender"},
+		true,
+	)
+	f(t,
+		[]string{`{foo=~"bar.*"}`, `{bar=~"baz.*"}`},
+		map[string]string{"foo": "other", "bar": "other"},
+		false,
+	)
+	f(t,
+		[]string{`{job="foo",instance="bar"}`, `{foo="bar"}`},
+		map[string]string{"foo": "bar"},
+		true,
+	)
+	f(t,
+		[]string{`{job="foo", instance="bar"}`, `{foo="bar"}`},
+		map[string]string{"instance": "barr", "job": "foo"},
+		false,
+	)
+}

app/vmauth/auth_config.go

@@ -610,6 +610,7 @@ func areEqualBackendURLs(a, b []*backendURL) bool {
 }
 
 // getFirstAvailableBackendURL returns the first available backendURL, which isn't broken.
+// If all backendURLs are broken, then returns the first backendURL.
 //
 // backendURL.put() must be called on the returned backendURL after the request is complete.
 func getFirstAvailableBackendURL(bus []*backendURL) *backendURL {
@@ -628,21 +629,22 @@ func getFirstAvailableBackendURL(bus []*backendURL) *backendURL {
 			return bu
 		}
 	}
-	return nil
+
+	// All backend urls are unavailable, then returning a first one, it could help increase the success rate of the requests。
+	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10837#issuecomment-4307050980.
+	bu.get()
+	return bu
 }
 
 // getLeastLoadedBackendURL returns a non-broken backendURL with the lowest number of concurrent requests.
+// If all backendURLs are broken, then returns the first backendURL.
 //
 // backendURL.put() must be called on the returned backendURL after the request is complete.
 func getLeastLoadedBackendURL(bus []*backendURL, atomicCounter *atomic.Uint32) *backendURL {
+	firstBu := bus[0]
 	if len(bus) == 1 {
-		// Fast path - return the only backend url.
-		bu := bus[0]
-		if bu.isBroken() {
-			return nil
-		}
-		bu.get()
-		return bu
+		firstBu.get()
+		return firstBu
 	}
 
 	// Slow path - select other backend urls.
@@ -680,7 +682,10 @@ func getLeastLoadedBackendURL(bus []*backendURL, atomicCounter *atomic.Uint32) *
 	}
 	buMin := bus[buMinIdx]
 	if buMin.isBroken() {
-		return nil
+		// If all backendURLs are broken, then returns the first backendURL.
+		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10837#issuecomment-4307050980.
+		firstBu.get()
+		return firstBu
 	}
 	buMin.get()
 	atomicCounter.CompareAndSwap(n+1, buMinIdx+1)
@@ -884,7 +889,8 @@ func reloadAuthConfig() (bool, error) {
 	}
 
 	mp := authUsers.Load()
-	logger.Infof("loaded information about %d users from -auth.config=%q", len(*mp), *authConfigPath)
+	jwtc := jwtAuthCache.Load()
+	logger.Infof("loaded information about %d users from -auth.config=%q", len(*mp)+len(jwtc.users), *authConfigPath)
 	return true, nil
 }
 

app/vmauth/auth_config_test.go

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

app/vmauth/example_config.yml

@@ -130,6 +130,16 @@ users:
   - "http://vmselect1:8481/select/{{.MetricsTenant}}/prometheus"
   - "http://vmselect2:8481/select/{{.MetricsTenant}}/prometheus"
 
+# JWT-based routing using header-based tenant identification (VictoriaMetrics cluster)
+# The AccountID and ProjectID from JWT vm_access claims are injected as HTTP headers.
+- name: jwt-header-tenant
+  jwt:
+    skip_verify: true
+  headers:
+  - "AccountID: {{.MetricsAccountID}}"
+  - "ProjectID: {{.MetricsProjectID}}"
+  url_prefix: "http://vminsert:8480/insert/prometheus"
+
 # Requests without Authorization header are proxied according to `unauthorized_user` section.
 # Requests are proxied in round-robin fashion between `url_prefix` backends.
 # The deny_partial_response query arg is added to all the proxied requests.

app/vmauth/jwt.go

@@ -17,6 +17,8 @@ import (
 
 const (
 	metricsTenantPlaceholder       = `{{.MetricsTenant}}`
+	metricsAccountIDPlaceholder    = `{{.MetricsAccountID}}`
+	metricsProjectIDPlaceholder    = `{{.MetricsProjectID}}`
 	metricsExtraLabelsPlaceholder  = `{{.MetricsExtraLabels}}`
 	metricsExtraFiltersPlaceholder = `{{.MetricsExtraFilters}}`
 
@@ -30,6 +32,8 @@ const (
 
 var allPlaceholders = []string{
 	metricsTenantPlaceholder,
+	metricsAccountIDPlaceholder,
+	metricsProjectIDPlaceholder,
 	metricsExtraLabelsPlaceholder,
 	metricsExtraFiltersPlaceholder,
 	logsAccountIDPlaceholder,
@@ -40,6 +44,8 @@ var allPlaceholders = []string{
 
 var urlPathPlaceHolders = []string{
 	metricsTenantPlaceholder,
+	metricsAccountIDPlaceholder,
+	metricsProjectIDPlaceholder,
 	logsAccountIDPlaceholder,
 	logsProjectIDPlaceholder,
 }
@@ -371,6 +377,8 @@ func jwtClaimsData(vma *jwt.VMAccessClaim) map[string][]string {
 	data := map[string][]string{
 		// TODO: optimize at parsing stage
 		metricsTenantPlaceholder:       {fmt.Sprintf("%d:%d", vma.MetricsAccountID, vma.MetricsProjectID)},
+		metricsAccountIDPlaceholder:    {fmt.Sprintf("%d", vma.MetricsAccountID)},
+		metricsProjectIDPlaceholder:    {fmt.Sprintf("%d", vma.MetricsProjectID)},
 		metricsExtraLabelsPlaceholder:  vma.MetricsExtraLabels,
 		metricsExtraFiltersPlaceholder: vma.MetricsExtraFilters,
 

app/vmauth/jwt_test.go

@@ -170,13 +170,13 @@ users:
   url_prefix: http://foo.bar
 `, "cannot parse public key from file \""+publicKeyFile+"\": failed to parse key \"invalidPEM\": failed to decode PEM block containing public key")
 
-	// unsupported placeholder in a header
+	// unsupported placeholder in a URL path
 	f(`
 users:
 - jwt: 
     skip_verify: true
   url_prefix: http://foo.bar/{{.UnsupportedPlaceholder}}/foo`,
-		"invalid placeholder found in URL request path: \"/{{.UnsupportedPlaceholder}}/foo\", supported values are: {{.MetricsTenant}}, {{.MetricsExtraLabels}}, {{.MetricsExtraFilters}}, {{.LogsAccountID}}, {{.LogsProjectID}}, {{.LogsExtraFilters}}, {{.LogsExtraStreamFilters}}",
+		"invalid placeholder found in URL request path: \"/{{.UnsupportedPlaceholder}}/foo\", supported values are: {{.MetricsTenant}}, {{.MetricsAccountID}}, {{.MetricsProjectID}}, {{.MetricsExtraLabels}}, {{.MetricsExtraFilters}}, {{.LogsAccountID}}, {{.LogsProjectID}}, {{.LogsExtraFilters}}, {{.LogsExtraStreamFilters}}",
 	)
 	// unsupported placeholder in a header
 	f(`
@@ -187,7 +187,7 @@ users:
     - "AccountID: {{.UnsupportedPlaceholder}}"
   url_prefix: http://foo.bar
 `,
-		"request header: \"AccountID\" has unsupported placeholder: \"{{.UnsupportedPlaceholder}}\", supported values are: {{.MetricsTenant}}, {{.MetricsExtraLabels}}, {{.MetricsExtraFilters}}, {{.LogsAccountID}}, {{.LogsProjectID}}, {{.LogsExtraFilters}}, {{.LogsExtraStreamFilters}}",
+		"request header: \"AccountID\" has unsupported placeholder: \"{{.UnsupportedPlaceholder}}\", supported values are: {{.MetricsTenant}}, {{.MetricsAccountID}}, {{.MetricsProjectID}}, {{.MetricsExtraLabels}}, {{.MetricsExtraFilters}}, {{.LogsAccountID}}, {{.LogsProjectID}}, {{.LogsExtraFilters}}, {{.LogsExtraStreamFilters}}",
 	)
 
 	// spaces in templating not allowed
@@ -199,7 +199,19 @@ users:
     - "AccountID: {{ .LogsAccountID }}"
   url_prefix: http://foo.bar
 `,
-		"request header: \"AccountID\" has unsupported placeholder: \"{{ .LogsAccountID }}\", supported values are: {{.MetricsTenant}}, {{.MetricsExtraLabels}}, {{.MetricsExtraFilters}}, {{.LogsAccountID}}, {{.LogsProjectID}}, {{.LogsExtraFilters}}, {{.LogsExtraStreamFilters}}",
+		"request header: \"AccountID\" has unsupported placeholder: \"{{ .LogsAccountID }}\", supported values are: {{.MetricsTenant}}, {{.MetricsAccountID}}, {{.MetricsProjectID}}, {{.MetricsExtraLabels}}, {{.MetricsExtraFilters}}, {{.LogsAccountID}}, {{.LogsProjectID}}, {{.LogsExtraFilters}}, {{.LogsExtraStreamFilters}}",
+	)
+
+	// placeholder must match the entire header value
+	f(`
+users:
+- jwt: 
+    skip_verify: true
+  headers:
+    - "AccountID: foo {{.MetricsAccountID}}"
+  url_prefix: http://foo.bar
+`,
+		"request header: \"AccountID\" has unsupported placeholder: \"foo {{.MetricsAccountID}}\", supported values are: {{.MetricsTenant}}, {{.MetricsAccountID}}, {{.MetricsProjectID}}, {{.MetricsExtraLabels}}, {{.MetricsExtraFilters}}, {{.LogsAccountID}}, {{.LogsProjectID}}, {{.LogsExtraFilters}}, {{.LogsExtraStreamFilters}}",
 	)
 
 	// oidc is not an object
@@ -364,10 +376,25 @@ users:
   url_prefix: http://foo.bar
 `, validRSAPublicKey, validECDSAPublicKey))
 
+	// metrics header placeholders
 	f(`
 users:
 - jwt:
     skip_verify: true
+  headers:
+  - "MetricsAccountID: {{.MetricsAccountID}}"
+  - "MetricsProjectID: {{.MetricsProjectID}}"
+  url_prefix: http://foo.bar
+`)
+
+	// logs header placeholders
+	f(`
+users:
+- jwt:
+    skip_verify: true
+  headers:
+  - "LogsAccountID: {{.LogsAccountID}}"
+  - "LogsProjectID: {{.LogsProjectID}}"
   url_prefix: http://foo.bar
 `)
 

app/vmauth/main.go

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

app/vmauth/main_test.go

@@ -19,6 +19,7 @@ import (
 	"os"
 	"path/filepath"
 	"sort"
+	"strconv"
 	"strings"
 	"sync/atomic"
 	"testing"
@@ -544,6 +545,31 @@ requested_url={BACKEND}/path2/foo/?de=fg`
 	if n := retries.Load(); n != 2 {
 		t.Fatalf("unexpected number of retries; got %d; want 2", n)
 	}
+
+	// make sure that empty config value erases client extra filters and extra labels
+	cfgStr = `
+unauthorized_user:
+  url_prefix: {BACKEND}/foo?bar=baz&extra_filters[]=&extra_label=&extra_filters=`
+	requestURL = "http://some-host.com/abc/def?some_arg=some_value&extra_filters[]=baz&extra_label=tenant=admin&extra_filters=bar"
+	backendHandler = func(w http.ResponseWriter, r *http.Request) {
+		h := w.Header()
+		h.Set("Connection", "close")
+		h.Set("Foo", "bar")
+
+		var bb bytes.Buffer
+		if err := r.Header.Write(&bb); err != nil {
+			panic(fmt.Errorf("unexpected error when marshaling headers: %w", err))
+		}
+		fmt.Fprintf(w, "requested_url=http://%s%s\n%s", r.Host, r.URL, bb.String())
+	}
+	responseExpected = `
+statusCode=200
+Foo: bar
+requested_url={BACKEND}/foo/abc/def?bar=baz&extra_filters=&extra_filters%5B%5D=&extra_label=&some_arg=some_value
+Pass-Header: abc
+User-Agent: vmauth
+X-Forwarded-For: 12.34.56.78, 42.2.3.84`
+	f(cfgStr, requestURL, backendHandler, responseExpected)
 }
 
 func TestJWTRequestHandler(t *testing.T) {
@@ -850,6 +876,30 @@ users:
 		responseExpected,
 	)
 
+	// test header injection and URL templating with individual placeholders
+	request = httptest.NewRequest(`GET`, "http://some-host.com/api/v1/query", nil)
+	request.Header.Set(`Authorization`, `Bearer `+fullToken)
+	responseExpected = `
+statusCode=200
+path: /select/123/234/api/v1/query
+query:
+headers:
+    AccountID=123
+    ProjectID=234`
+	f(fmt.Sprintf(
+		`
+users:
+- jwt:
+    public_keys:
+    - %q
+  url_prefix: {BACKEND}/select/{{.MetricsAccountID}}/{{.MetricsProjectID}}
+  headers:
+  - "AccountID: {{.MetricsAccountID}}"
+  - "ProjectID: {{.MetricsProjectID}}"`, string(publicKeyPEM)),
+		request,
+		responseExpected,
+	)
+
 	// extra_label and extra_filters from vm_access claim merged with statically defined
 	request = httptest.NewRequest(`GET`, "http://some-host.com/api/v1/query", nil)
 	request.Header.Set(`Authorization`, `Bearer `+fullToken)
@@ -1831,7 +1881,7 @@ func (r *mockBody) Read(p []byte) (n int, err error) {
 }
 
 func TestBufferedBody_RetrySuccess(t *testing.T) {
-	f := func(s string, maxBodySize int) {
+	f := func(s string, maxSizeToRetry, bufferSize int) {
 		t.Helper()
 
 		defaultRequestBufferSize := requestBufferSize.String()
@@ -1840,7 +1890,7 @@ func TestBufferedBody_RetrySuccess(t *testing.T) {
 				t.Fatalf("cannot reset requestBufferSize: %s", err)
 			}
 		}()
-		if err := requestBufferSize.Set(fmt.Sprintf("%d", maxBodySize)); err != nil {
+		if err := requestBufferSize.Set(strconv.Itoa(bufferSize)); err != nil {
 			t.Fatalf("cannot set requestBufferSize: %s", err)
 		}
 
@@ -1850,7 +1900,7 @@ func TestBufferedBody_RetrySuccess(t *testing.T) {
 				t.Fatalf("cannot reset maxRequestBodySizeToRetry: %s", err)
 			}
 		}()
-		if err := maxRequestBodySizeToRetry.Set("0"); err != nil {
+		if err := maxRequestBodySizeToRetry.Set(strconv.Itoa(maxSizeToRetry)); err != nil {
 			t.Fatalf("cannot set maxRequestBodySizeToRetry: %s", err)
 		}
 
@@ -1879,16 +1929,20 @@ func TestBufferedBody_RetrySuccess(t *testing.T) {
 		}
 	}
 
-	f("", 0)
-	f("", -1)
-	f("", 100)
-	f("foo", 100)
-	f("foobar", 100)
-	f(newTestString(1000), 1001)
+	f("", 0, 2000)
+	f("", 0, 0)
+	f("", -1, 2000)
+	f("", 100, 2000)
+	f("foo", 100, 2000)
+	f("foobar", 100, 2000)
+	f("foobar", 100, 0)
+	f("foobar", 100, -1)
+	f(newTestString(1000), 1001, 2000)
+	f(newTestString(1000), 1001, 500)
 }
 
 func TestBufferedBody_RetrySuccessPartialRead(t *testing.T) {
-	f := func(s string, maxBodySize int) {
+	f := func(s string, maxSizeToRetry, bufferSize int) {
 		t.Helper()
 
 		// Check the case with partial read
@@ -1898,7 +1952,7 @@ func TestBufferedBody_RetrySuccessPartialRead(t *testing.T) {
 				t.Fatalf("cannot reset requestBufferSize: %s", err)
 			}
 		}()
-		if err := requestBufferSize.Set(fmt.Sprintf("%d", maxBodySize)); err != nil {
+		if err := requestBufferSize.Set(strconv.Itoa(bufferSize)); err != nil {
 			t.Fatalf("cannot set requestBufferSize: %s", err)
 		}
 
@@ -1908,7 +1962,7 @@ func TestBufferedBody_RetrySuccessPartialRead(t *testing.T) {
 				t.Fatalf("cannot reset maxRequestBodySizeToRetry: %s", err)
 			}
 		}()
-		if err := maxRequestBodySizeToRetry.Set("0"); err != nil {
+		if err := maxRequestBodySizeToRetry.Set(strconv.Itoa(maxSizeToRetry)); err != nil {
 			t.Fatalf("cannot set maxRequestBodySizeToRetry: %s", err)
 		}
 
@@ -1952,16 +2006,20 @@ func TestBufferedBody_RetrySuccessPartialRead(t *testing.T) {
 		}
 	}
 
-	f("", 0)
-	f("", -1)
-	f("", 100)
-	f("foo", 100)
-	f("foobar", 100)
-	f(newTestString(1000), 1001)
+	f("", 0, 2000)
+	f("", 0, 0)
+	f("", -1, 2000)
+	f("", 100, 2000)
+	f("foo", 100, 2000)
+	f("foobar", 100, 2000)
+	f("foobar", 100, 0)
+	f("foobar", 100, -1)
+	f(newTestString(1000), 1001, 2000)
+	f(newTestString(1000), 1001, 500)
 }
 
 func TestBufferedBody_RetryFailureTooBigBody(t *testing.T) {
-	f := func(s string, maxBodySize int) {
+	f := func(s string, maxSizeToRetry, bufferSize int) {
 		t.Helper()
 
 		defaultRequestBufferSize := requestBufferSize.String()
@@ -1970,7 +2028,7 @@ func TestBufferedBody_RetryFailureTooBigBody(t *testing.T) {
 				t.Fatalf("cannot reset requestBufferSize: %s", err)
 			}
 		}()
-		if err := requestBufferSize.Set("0"); err != nil {
+		if err := requestBufferSize.Set(strconv.Itoa(bufferSize)); err != nil {
 			t.Fatalf("cannot set requestBufferSize: %s", err)
 		}
 
@@ -1980,7 +2038,7 @@ func TestBufferedBody_RetryFailureTooBigBody(t *testing.T) {
 				t.Fatalf("cannot reset maxRequestBodySizeToRetry: %s", err)
 			}
 		}()
-		if err := maxRequestBodySizeToRetry.Set(fmt.Sprintf("%d", maxBodySize)); err != nil {
+		if err := maxRequestBodySizeToRetry.Set(strconv.Itoa(maxSizeToRetry)); err != nil {
 			t.Fatalf("cannot set maxRequestBodySizeToRetry: %s", err)
 		}
 
@@ -2025,12 +2083,17 @@ func TestBufferedBody_RetryFailureTooBigBody(t *testing.T) {
 	}
 
 	const maxBodySize = 1000
-	f(newTestString(maxBodySize+1), maxBodySize)
-	f(newTestString(2*maxBodySize), maxBodySize)
+	f(newTestString(maxBodySize+1), 0, 2*maxBodySize)
+	f(newTestString(maxBodySize+1), -1, 2*maxBodySize)
+	f(newTestString(maxBodySize+1), maxBodySize, 0)
+	f(newTestString(maxBodySize+1), maxBodySize, -1)
+	f(newTestString(maxBodySize+1), maxBodySize, maxBodySize)
+	f(newTestString(maxBodySize+1), maxBodySize, 2*maxBodySize)
+	f(newTestString(2*maxBodySize), maxBodySize, 0)
 }
 
-func TestBufferedBody_RetryFailureZeroOrNegativeMaxBodySize(t *testing.T) {
-	f := func(s string, maxBodySize int) {
+func TestBufferedBody_RetryDisabledByMaxRequestBodySizeToRetry(t *testing.T) {
+	f := func(s string, maxSizeToRetry, bufferSize int) {
 		t.Helper()
 
 		defaultRequestBufferSize := requestBufferSize.String()
@@ -2039,10 +2102,20 @@ func TestBufferedBody_RetryFailureZeroOrNegativeMaxBodySize(t *testing.T) {
 				t.Fatalf("cannot reset requestBufferSize: %s", err)
 			}
 		}()
-		if err := requestBufferSize.Set(fmt.Sprintf("%d", maxBodySize)); err != nil {
+		if err := requestBufferSize.Set(strconv.Itoa(bufferSize)); err != nil {
 			t.Fatalf("cannot set requestBufferSize: %s", err)
 		}
 
+		defaultMaxRequestBodySizeToRetry := maxRequestBodySizeToRetry.String()
+		defer func() {
+			if err := maxRequestBodySizeToRetry.Set(defaultMaxRequestBodySizeToRetry); err != nil {
+				t.Fatalf("cannot reset maxRequestBodySizeToRetry: %s", err)
+			}
+		}()
+		if err := maxRequestBodySizeToRetry.Set(strconv.Itoa(maxSizeToRetry)); err != nil {
+			t.Fatalf("cannot set maxRequestBodySizeToRetry: %s", err)
+		}
+
 		ctx := context.Background()
 		rb, err := bufferRequestBody(ctx, io.NopCloser(bytes.NewBufferString(s)), "foo")
 		if err != nil {
@@ -2051,8 +2124,8 @@ func TestBufferedBody_RetryFailureZeroOrNegativeMaxBodySize(t *testing.T) {
 		bb, ok := rb.(*bufferedBody)
 		canRetry := !ok || bb.canRetry()
 
-		if !canRetry {
-			t.Fatalf("canRetry() must return true before reading anything")
+		if canRetry {
+			t.Fatalf("canRetry() must return false before reading anything")
 		}
 		data, err := io.ReadAll(rb)
 		if err != nil {
@@ -2066,19 +2139,19 @@ func TestBufferedBody_RetryFailureZeroOrNegativeMaxBodySize(t *testing.T) {
 		}
 
 		data, err = io.ReadAll(rb)
-		if err != nil {
-			t.Fatalf("unexpected error in io.ReadAll: %s", err)
+		if err == nil {
+			t.Fatalf("expecting non-nil error")
 		}
-		if string(data) != s {
-			t.Fatalf("unexpected data read\ngot\n%s\nwant\n%s", data, s)
+		if len(data) != 0 {
+			t.Fatalf("unexpected non-empty data read: %q", data)
 		}
 	}
 
-	f("foobar", 0)
-	f(newTestString(1000), 0)
+	f("foobar", 0, 2048)
+	f(newTestString(1000), 0, 2048)
 
-	f("foobar", -1)
-	f(newTestString(1000), -1)
+	f("foobar", -1, 2048)
+	f(newTestString(1000), -1, 2048)
 }
 
 func newTestString(sLen int) string {

app/vmctl/flags.go

@@ -146,7 +146,8 @@ var (
 			Name:  vmRoundDigits,
 			Value: 100,
 			Usage: "Round metric values to the given number of decimal digits after the point. " +
-				"This option may be used for increasing on-disk compression level for the stored metrics",
+				"This option may be used for increasing on-disk compression level for the stored metrics. " +
+				"See also --vm-significant-figures option",
 		},
 		&cli.StringSliceFlag{
 			Name:  vmExtraLabel,
@@ -500,6 +501,96 @@ var (
 	}
 )
 
+const (
+	mimirPath             = "mimir-path"
+	mimirTenantID         = "mimir-tenant-id"
+	mimirConcurrency      = "mimir-concurrency"
+	mimirFilterTimeStart  = "mimir-filter-time-start"
+	mimirFilterTimeEnd    = "mimir-filter-time-end"
+	mimirFilterLabel      = "mimir-filter-label"
+	mimirFilterLabelValue = "mimir-filter-label-value"
+
+	mimirCredsFilePath           = "mimir-creds-file-path"
+	mimirConfigFilePath          = "mimir-config-file-path"
+	mimirConfigProfile           = "mimir-config-profile"
+	mimirCustomS3Endpoint        = "mimir-custom-s3-endpoint"
+	mimirS3ForcePathStyle        = "mimir-s3-force-path-style"
+	mimirS3TLSInsecureSkipVerify = "mimir-s3-tls-insecure-skip-verify"
+	mimirSSEKMSKeyID             = "mimir-s3-sse-kms-key-id"
+	mimirSSEAlgorithm            = "mimir-s3-sse-algorithm"
+)
+
+var (
+	mimirFlags = []cli.Flag{
+		&cli.StringFlag{
+			Name:     mimirPath,
+			Usage:    "Path to Mimir storage bucket or local folder.",
+			Required: true,
+		},
+		&cli.StringFlag{
+			Name:  mimirTenantID,
+			Usage: "Tenant ID for Mimir storage",
+		},
+		&cli.IntFlag{
+			Name:  mimirConcurrency,
+			Usage: "Number of concurrently running block readers",
+			Value: 1,
+		},
+		&cli.StringFlag{
+			Name:     mimirFilterTimeStart,
+			Usage:    "The time filter in RFC3339 format to select timeseries with timestamp equal or higher than provided value. E.g. '2020-01-01T20:07:00Z'",
+			Required: true,
+		},
+		&cli.StringFlag{
+			Name:     mimirFilterTimeEnd,
+			Usage:    "The time filter in RFC3339 format to select timeseries with timestamp equal or lower than provided value. E.g. '2020-01-01T20:07:00Z'",
+			Required: true,
+		},
+		&cli.StringFlag{
+			Name:  mimirFilterLabel,
+			Usage: "Mimir label name to filter timeseries by. E.g. '__name__' will filter timeseries by name.",
+		},
+		&cli.StringFlag{
+			Name:  mimirFilterLabelValue,
+			Usage: fmt.Sprintf("Regular expression to filter label from %q flag.", mimirFilterLabel),
+			Value: ".*",
+		},
+		&cli.StringFlag{
+			Name:  mimirCredsFilePath,
+			Usage: "Path to file with GCS or S3 credentials. Credentials are loaded from default locations if not set. See https://cloud.google.com/iam/docs/creating-managing-service-account-keys and https://docs.aws.amazon.com/general/latest/gr/aws-security-credentials.html",
+		},
+		&cli.StringFlag{
+			Name:  mimirConfigFilePath,
+			Usage: "Path to file with S3 configs. Configs are loaded from default location if not set. See https://docs.aws.amazon.com/general/latest/gr/aws-security-credentials.html",
+		},
+		&cli.StringFlag{
+			Name:  mimirConfigProfile,
+			Usage: "Profile name for S3 configs. If no set, the value of the environment variable will be loaded (AWS_PROFILE or AWS_DEFAULT_PROFILE), or if both not set, DefaultSharedConfigProfile is used",
+		},
+		&cli.StringFlag{
+			Name:  mimirCustomS3Endpoint,
+			Usage: "Custom S3 endpoint for use with S3-compatible storages (e.g. MinIO). S3 is used if not set",
+		},
+		&cli.BoolFlag{
+			Name:  mimirS3ForcePathStyle,
+			Usage: "Prefixing endpoint with bucket name when set false, true by default.",
+			Value: true,
+		},
+		&cli.BoolFlag{
+			Name:  mimirS3TLSInsecureSkipVerify,
+			Usage: "Whether to skip TLS verification when connecting to the S3 endpoint.",
+		},
+		&cli.StringFlag{
+			Name:  mimirSSEKMSKeyID,
+			Usage: "SSE KMS Key ID for use with S3-compatible storages.",
+		},
+		&cli.StringFlag{
+			Name:  mimirSSEAlgorithm,
+			Usage: "SSE algorithm for use with S3-compatible storages.",
+		},
+	}
+)
+
 const (
 	vmNativeFilterMatch       = "vm-native-filter-match"
 	vmNativeFilterTimeStart   = "vm-native-filter-time-start"

app/vmctl/main.go

@@ -18,6 +18,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/auth"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/backoff"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/barpool"
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/mimir"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/native"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/remoteread"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
@@ -297,12 +298,12 @@ func main() {
 				},
 			},
 			{
-				Name:   "thanos",
-				Usage:  "Migrate time series from Thanos blocks (supports raw and downsampled data)",
-				Flags:  mergeFlags(globalFlags, thanosFlags, vmFlags),
+				Name:   "mimir",
+				Usage:  "Migrate time series from Mimir object storage or local filesystem",
+				Flags:  mergeFlags(globalFlags, mimirFlags, vmFlags),
 				Before: beforeFn,
 				Action: func(c *cli.Context) error {
-					fmt.Println("Thanos import mode")
+					fmt.Println("Mimir import mode")
 
 					vmCfg, err := initConfigVM(c)
 					if err != nil {
@@ -314,6 +315,54 @@ func main() {
 						return fmt.Errorf("failed to create VM importer: %s", err)
 					}
 
+					mCfg := mimir.Config{
+						Filter: mimir.Filter{
+							TimeMin:    c.String(mimirFilterTimeStart),
+							TimeMax:    c.String(mimirFilterTimeEnd),
+							Label:      c.String(mimirFilterLabel),
+							LabelValue: c.String(mimirFilterLabelValue),
+						},
+						Path:                    c.String(mimirPath),
+						TenantID:                c.String(mimirTenantID),
+						CredsFilePath:           c.String(mimirCredsFilePath),
+						ConfigFilePath:          c.String(mimirConfigFilePath),
+						ConfigProfile:           c.String(mimirConfigProfile),
+						CustomS3Endpoint:        c.String(mimirCustomS3Endpoint),
+						S3ForcePathStyle:        c.Bool(mimirS3ForcePathStyle),
+						S3TLSInsecureSkipVerify: c.Bool(mimirS3TLSInsecureSkipVerify),
+						SSEKMSKeyID:             c.String(mimirSSEKMSKeyID),
+						SSEAlgorithm:            c.String(mimirSSEAlgorithm),
+					}
+					cl, err := mimir.NewClient(ctx, mCfg)
+					if err != nil {
+						return fmt.Errorf("failed to create mimir client: %s", err)
+					}
+
+					pp := prometheusProcessor{
+						cl:        cl,
+						im:        importer,
+						cc:        c.Int(mimirConcurrency),
+						isVerbose: c.Bool(globalVerbose),
+					}
+					return pp.run(ctx)
+				},
+			},
+			{
+				Name:   "thanos",
+				Usage:  "Migrate time series from Thanos blocks (supports raw and downsampled data)",
+				Flags:  mergeFlags(globalFlags, thanosFlags, vmFlags),
+				Before: beforeFn,
+				Action: func(c *cli.Context) error {
+					fmt.Println("Thanos import mode")
+					vmCfg, err := initConfigVM(c)
+					if err != nil {
+						return fmt.Errorf("failed to init VM configuration: %s", err)
+					}
+
+					importer, err = vm.NewImporter(ctx, vmCfg)
+					if err != nil {
+						return fmt.Errorf("failed to create VM importer: %s", err)
+					}
 					thanosCfg := thanos.Config{
 						Snapshot: c.String(thanosSnapshot),
 						Filter: thanos.Filter{

app/vmctl/mimir/lazyreader.go

@@ -0,0 +1,195 @@
+package mimir
+
+import (
+	"fmt"
+	"log"
+	"os"
+	"path/filepath"
+	"sync"
+
+	"github.com/oklog/ulid/v2"
+	"github.com/prometheus/prometheus/tsdb"
+	"github.com/prometheus/prometheus/tsdb/tombstones"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/backup/common"
+)
+
+var _ tsdb.BlockReader = (*lazyBlockReader)(nil)
+
+// lazyBlockReader is stores block id and segment num information.
+// It is used to lazily fetch and parse block data.
+// It implements tsdb.BlockReader interface.
+type lazyBlockReader struct {
+	// Block ID.
+	ID ulid.ULID
+	// SegmentsNum stores the number of chunks segments in the block.
+	SegmentsNum int
+
+	mu          sync.Mutex
+	reader      *tsdb.Block
+	tempDirPath string
+	fs          common.RemoteFS
+	err         error
+}
+
+// newLazyBlockReader returns a new LazyBlockReader for the given block.
+func newLazyBlockReader(block *Block, fs common.RemoteFS) (*lazyBlockReader, error) {
+	if block.SegmentsFormat != "1b6d" {
+		return nil, fmt.Errorf("unsupported segments format: %s", block.SegmentsFormat)
+	}
+
+	return &lazyBlockReader{
+		ID:          block.ID,
+		SegmentsNum: block.SegmentsNum,
+		fs:          fs,
+	}, nil
+}
+
+func (lbr *lazyBlockReader) initialize() error {
+	lbr.mu.Lock()
+	defer lbr.mu.Unlock()
+	if lbr.reader != nil {
+		return nil
+	}
+	// fetching block and parse it and store it in lbr.reader
+	temp, err := lbr.mkTempDir()
+	if err != nil {
+		return fmt.Errorf("failed to create temp dir: %s", err)
+	}
+
+	lbr.tempDirPath = temp
+
+	// TODO: replace fetchFile and writeFile with buffered IO if needed
+	meta, err := lbr.fetchFile(metaFilename)
+	if err != nil {
+		return err
+	}
+	if err := lbr.writeFile(temp, metaFilename, meta); err != nil {
+		return fmt.Errorf("failed to write meta file: %w", err)
+	}
+	idx, err := lbr.fetchFile(indexFilename)
+	if err != nil {
+		return fmt.Errorf("failed to fetch index file %q: %w", indexFilename, err)
+	}
+	if err := lbr.writeFile(temp, indexFilename, idx); err != nil {
+		return err
+	}
+
+	for i := 1; i <= lbr.SegmentsNum; i++ {
+		// segments formats has format 1b06d
+		// https://github.com/grafana/mimir/blob/main/pkg/storage/tsdb/bucketindex/index.go#L32
+		chunkName := fmt.Sprintf("%06d", i)
+		blockChunkPath := filepath.Join("chunks", chunkName)
+		chunk, err := lbr.fetchFile(blockChunkPath)
+		if err != nil {
+			return fmt.Errorf("failed to fetch chunk file: %q: %w", chunkName, err)
+		}
+		if err := lbr.writeFile(temp, blockChunkPath, chunk); err != nil {
+			return fmt.Errorf("failed to write chunk file: %q: %s", chunkName, err)
+		}
+	}
+
+	// Set postingDecoder to nil because
+	// If it is nil then a default decoder is used, compatible with Prometheus v2.
+	pb, err := tsdb.OpenBlock(nil, temp, nil, nil)
+	if err != nil {
+		return fmt.Errorf("failed to open block %q: %w", lbr.ID, err)
+	}
+	lbr.reader = pb
+	return nil
+}
+
+// Index returns an IndexReader over the block's data.
+func (lbr *lazyBlockReader) Index() (tsdb.IndexReader, error) {
+	if err := lbr.initialize(); err != nil {
+		return nil, err
+	}
+	return lbr.reader.Index()
+}
+
+// Chunks returns a ChunkReader over the block's data.
+func (lbr *lazyBlockReader) Chunks() (tsdb.ChunkReader, error) {
+	if err := lbr.initialize(); err != nil {
+		return nil, err
+	}
+	return lbr.reader.Chunks()
+}
+
+// Tombstones returns a tombstones.Reader over the block's deleted data.
+func (lbr *lazyBlockReader) Tombstones() (tombstones.Reader, error) {
+	if err := lbr.initialize(); err != nil {
+		return nil, err
+	}
+	return lbr.reader.Tombstones()
+}
+
+// Meta provides meta information about the block reader.
+func (lbr *lazyBlockReader) Meta() tsdb.BlockMeta {
+	if err := lbr.initialize(); err != nil {
+		lbr.err = fmt.Errorf("cannot get BlockMeta: %w", err)
+		return tsdb.BlockMeta{}
+	}
+	return lbr.reader.Meta()
+}
+
+// Size returns the number of bytes that the block takes up on disk.
+func (lbr *lazyBlockReader) Size() int64 {
+	if err := lbr.initialize(); err != nil {
+		lbr.err = fmt.Errorf("error get Size of the block: %s, return zero size", err)
+		return 0
+	}
+	return lbr.reader.Size()
+}
+
+// Err returns the last error that occurred on the block reader.
+func (lbr *lazyBlockReader) Err() error {
+	return lbr.err
+}
+
+// Close closes block and releases all resources
+func (lbr *lazyBlockReader) Close() error {
+	lbr.mu.Lock()
+	defer lbr.mu.Unlock()
+	if lbr.reader == nil {
+		return nil
+	}
+
+	err := lbr.reader.Close()
+	if err := os.RemoveAll(lbr.tempDirPath); err != nil {
+		log.Printf("failed to remove temp dir: %s", err)
+	}
+	lbr.reader = nil
+	lbr.tempDirPath = ""
+
+	return err
+}
+
+func (lbr *lazyBlockReader) mkTempDir() (string, error) {
+	temp, err := os.MkdirTemp("", lbr.ID.String())
+	if err != nil {
+		return "", fmt.Errorf("failed to create temp dir: %s", err)
+	}
+	err = os.Mkdir(filepath.Join(temp, "chunks"), os.ModePerm)
+	if err != nil {
+		return "", fmt.Errorf("failed to create temp dir: %s", err)
+	}
+	return temp, nil
+}
+
+func (lbr *lazyBlockReader) fetchFile(filePath string) ([]byte, error) {
+	blockID := lbr.ID.String()
+	blockPath := filepath.Join(blockID, filePath)
+	has, err := lbr.fs.HasFile(blockPath)
+	if err != nil {
+		return nil, err
+	}
+	if !has {
+		return nil, fmt.Errorf("block meta %s not found", blockID)
+	}
+	return lbr.fs.ReadFile(blockPath)
+}
+
+func (lbr *lazyBlockReader) writeFile(folder string, filename string, file []byte) error {
+	fileName := filepath.Join(folder, filename)
+	return os.WriteFile(fileName, file, os.ModePerm)
+}

app/vmctl/mimir/mimir.go

@@ -0,0 +1,238 @@
+package mimir
+
+import (
+	"bytes"
+	"compress/gzip"
+	"context"
+	"encoding/json"
+	"fmt"
+	"log"
+
+	"github.com/oklog/ulid/v2"
+	"github.com/prometheus/prometheus/model/labels"
+	"github.com/prometheus/prometheus/tsdb"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/prometheus"
+	utils "github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/vmctlutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/backup/common"
+)
+
+const (
+	bucketIndex                   = "bucket-index.json"
+	bucketIndexCompressedFilename = bucketIndex + ".gz"
+	metaFilename                  = "meta.json"
+	indexFilename                 = "index"
+)
+
+// BlockDeletionMark holds the information about a block's deletion mark in the index.
+// This type was copied from the mimir repository https://github.com/grafana/mimir/blob/main/pkg/storage/tsdb/bucketindex/index.go#L234.
+type BlockDeletionMark struct {
+	// Block ID.
+	ID ulid.ULID `json:"block_id"`
+
+	// DeletionTime is a unix timestamp (seconds precision) of when the block was marked to be deleted.
+	DeletionTime int64 `json:"deletion_time"`
+}
+
+// Block holds the information about a block in the index.
+// This is a partial implementation of the https://github.com/grafana/mimir/blob/main/pkg/storage/tsdb/bucketindex/index.go#L73
+type Block struct {
+	// Block ID.
+	ID ulid.ULID `json:"block_id"`
+
+	// MinTime and MaxTime specify the time range all samples in the block are in (millis precision).
+	MinTime int64 `json:"min_time"`
+	MaxTime int64 `json:"max_time"`
+
+	// SegmentsFormat and SegmentsNum stores the format and number of chunks segments
+	// in the block.
+	SegmentsFormat string `json:"segments_format,omitempty"`
+	SegmentsNum    int    `json:"segments_num,omitempty"`
+}
+
+// Index contains all known blocks and markers of a tenant.
+// This is a partial implementation pof the https://github.com/grafana/mimir/blob/main/pkg/storage/tsdb/bucketindex/index.go#L36
+type Index struct {
+	// Version of the index format.
+	Version int `json:"version"`
+
+	// List of complete blocks (partial blocks are excluded from the index).
+	Blocks []*Block `json:"blocks"`
+}
+
+// Config contains a list of params needed
+// for reading mimir snapshots
+type Config struct {
+	// Path to remote storage bucket
+	Path string
+	// TenantID is the tenant id for the storage
+	TenantID string
+
+	Filter Filter
+
+	CredsFilePath           string
+	ConfigFilePath          string
+	ConfigProfile           string
+	CustomS3Endpoint        string
+	S3ForcePathStyle        bool
+	S3TLSInsecureSkipVerify bool
+
+	SSEKMSKeyID  string
+	SSEAlgorithm string
+}
+
+// Filter contains configuration for filtering
+// the timeseries
+type Filter struct {
+	TimeMin    string
+	TimeMax    string
+	Label      string
+	LabelValue string
+}
+
+// Client is a wrapper over Prometheus tsdb.DBReader
+type Client struct {
+	common.RemoteFS
+	filter filter
+}
+
+type filter struct {
+	min, max   int64
+	label      string
+	labelValue string
+}
+
+func (f filter) inRange(minTime, maxTime int64) bool {
+	fmin, fmax := f.min, f.max
+	if minTime == 0 {
+		fmin = minTime
+	}
+	if fmax == 0 {
+		fmax = maxTime
+	}
+	return minTime <= fmax && fmin <= maxTime
+}
+
+// NewClient creates and validates new Client
+// with given Config
+func NewClient(ctx context.Context, cfg Config) (*Client, error) {
+	if cfg.Path == "" {
+		return nil, fmt.Errorf("path cannot be empty")
+	}
+
+	if cfg.TenantID != "" {
+		cfg.Path = fmt.Sprintf("%s/%s", cfg.Path, cfg.TenantID)
+	}
+
+	var c Client
+	rfs, err := newRemoteFS(ctx, cfg)
+	if err != nil {
+		return nil, fmt.Errorf("cannot parse `-src`=%q: %w", cfg.Path, err)
+	}
+
+	c.RemoteFS = rfs
+	timeMin, err := utils.ParseTime(cfg.Filter.TimeMin)
+	if err != nil {
+		return nil, fmt.Errorf("failed to parse min time in filter: %s", err)
+	}
+	timeMax, err := utils.ParseTime(cfg.Filter.TimeMax)
+	if err != nil {
+		return nil, fmt.Errorf("failed to parse max time in filter: %s", err)
+	}
+	c.filter = filter{
+		min:        timeMin.UnixMilli(),
+		max:        timeMax.UnixMilli(),
+		label:      cfg.Filter.Label,
+		labelValue: cfg.Filter.LabelValue,
+	}
+	return &c, nil
+}
+
+// Explore a fetches bucket-index.json file from a remote storage or local filesystem
+// and filter blocks via the defined time range, but does not take into account label filters.
+func (c *Client) Explore() ([]tsdb.BlockReader, error) {
+
+	log.Printf("Fetching blocks from remote storage")
+
+	indexFile, err := c.fetchIndexFile()
+	if err != nil {
+		return nil, fmt.Errorf("failed to fetch index file: %s", err)
+	}
+
+	var blocksToImport []tsdb.BlockReader
+	for _, block := range indexFile.Blocks {
+		if !c.filter.inRange(block.MinTime, block.MaxTime) {
+			// Skipping block outside of time range
+			continue
+		}
+
+		if block.ID.String() == "" {
+			continue
+		}
+
+		lazyBlockReader, err := newLazyBlockReader(block, c.RemoteFS)
+		if err != nil {
+			return nil, fmt.Errorf("failed to create lazy block reader: %s", err)
+		}
+		blocksToImport = append(blocksToImport, lazyBlockReader)
+	}
+
+	return blocksToImport, nil
+}
+
+// Read reads the given BlockReader according to configured
+// time and label filters.
+func (c *Client) Read(ctx context.Context, block tsdb.BlockReader) (*prometheus.CloseableSeriesSet, error) {
+	meta := block.Meta()
+	if b, ok := block.(*lazyBlockReader); ok && b.Err() != nil {
+		return nil, fmt.Errorf("failed to read block: %s", b.Err())
+	}
+
+	if meta.ULID.String() == "" {
+		return nil, fmt.Errorf("unexpected block without id")
+	}
+
+	minTime, maxTime := meta.MinTime, meta.MaxTime
+	if c.filter.min != 0 {
+		minTime = c.filter.min
+	}
+	if c.filter.max != 0 {
+		maxTime = c.filter.max
+	}
+	q, err := tsdb.NewBlockQuerier(block, minTime, maxTime)
+	if err != nil {
+		return nil, err
+	}
+	ss := q.Select(ctx, false, nil, labels.MustNewMatcher(labels.MatchRegexp, c.filter.label, c.filter.labelValue))
+	return &prometheus.CloseableSeriesSet{SeriesSet: ss, Close: q.Close}, nil
+}
+
+func (c *Client) fetchIndexFile() (*Index, error) {
+	has, err := c.HasFile(bucketIndexCompressedFilename)
+	if err != nil {
+		return nil, err
+	}
+	if !has {
+		return nil, fmt.Errorf("bucket-index.json.gz not found")
+	}
+
+	file, err := c.ReadFile(bucketIndexCompressedFilename)
+	if err != nil {
+		return nil, fmt.Errorf("failed to read bucket index: %s", err)
+	}
+
+	r := bytes.NewReader(file)
+	// Read all the content.
+	gzipReader, err := gzip.NewReader(r)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create gzip reader: %s", err)
+	}
+
+	var indexFile Index
+	err = json.NewDecoder(gzipReader).Decode(&indexFile)
+	if err != nil {
+		return nil, fmt.Errorf("failed to decode bucket index: %s", err)
+	}
+
+	return &indexFile, nil
+}

app/vmctl/mimir/remotefs.go

@@ -0,0 +1,93 @@
+package mimir
+
+import (
+	"context"
+	"fmt"
+	"path/filepath"
+	"strings"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/backup/azremote"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/backup/common"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/backup/fsremote"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/backup/gcsremote"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/backup/s3remote"
+)
+
+// newRemoteFS returns new remote fs from the given Config.
+func newRemoteFS(ctx context.Context, cfg Config) (common.RemoteFS, error) {
+	if len(cfg.Path) == 0 {
+		return nil, fmt.Errorf("path cannot be empty")
+	}
+	n := strings.Index(cfg.Path, "://")
+	if n < 0 {
+		return nil, fmt.Errorf("missing scheme in path %q. Supported schemes: `gs://`, `s3://`, `azblob://`, `fs://`", cfg.Path)
+	}
+	scheme := cfg.Path[:n]
+	dir := cfg.Path[n+len("://"):]
+	switch scheme {
+	case "fs":
+		if !filepath.IsAbs(dir) {
+			return nil, fmt.Errorf("dir must be absolute; got %q", dir)
+		}
+		fsr := &fsremote.FS{
+			Dir: filepath.Clean(dir),
+		}
+		return fsr, nil
+	case "gcs", "gs":
+		n := strings.Index(dir, "/")
+		if n < 0 {
+			return nil, fmt.Errorf("missing directory on the gcs bucket %q", dir)
+		}
+		bucket := dir[:n]
+		dir = dir[n:]
+		fsr := &gcsremote.FS{
+			CredsFilePath: cfg.CredsFilePath,
+			Bucket:        bucket,
+			Dir:           dir,
+		}
+		if err := fsr.Init(ctx); err != nil {
+			return nil, fmt.Errorf("cannot initialize connection to gcs: %w", err)
+		}
+		return fsr, nil
+	case "azblob":
+		n := strings.Index(dir, "/")
+		if n < 0 {
+			return nil, fmt.Errorf("missing directory on the AZBlob container %q", dir)
+		}
+		bucket := dir[:n]
+		dir = dir[n:]
+		fsr := &azremote.FS{
+			Container: bucket,
+			Dir:       dir,
+		}
+		if err := fsr.Init(ctx); err != nil {
+			return nil, fmt.Errorf("cannot initialize connection to AZBlob: %w", err)
+		}
+		return fsr, nil
+	case "s3":
+		n := strings.Index(dir, "/")
+		if n < 0 {
+			return nil, fmt.Errorf("missing directory on the s3 bucket %q", dir)
+		}
+		bucket := dir[:n]
+		dir = dir[n:]
+		fsr := &s3remote.FS{
+			CredsFilePath:         cfg.CredsFilePath,
+			ConfigFilePath:        cfg.ConfigFilePath,
+			CustomEndpoint:        cfg.CustomS3Endpoint,
+			TLSInsecureSkipVerify: cfg.S3TLSInsecureSkipVerify,
+			S3ForcePathStyle:      cfg.S3ForcePathStyle,
+			ProfileName:           cfg.ConfigProfile,
+			Bucket:                bucket,
+			Dir:                   dir,
+			SSEKMSKeyId:           cfg.SSEKMSKeyID,
+			SSEAlgorithm:          s3remote.StringToEncryptionAlgorithm(cfg.SSEAlgorithm),
+		}
+		if err := fsr.Init(ctx); err != nil {
+			return nil, fmt.Errorf("cannot initialize connection to s3: %w", err)
+		}
+		return fsr, nil
+	default:
+		return nil, fmt.Errorf("unsupported scheme %q", scheme)
+	}
+}

app/vmctl/prometheus.go

@@ -3,6 +3,7 @@ package main
 import (
 	"context"
 	"fmt"
+	"io"
 	"log"
 	"strings"
 	"sync"
@@ -18,10 +19,17 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/vm"
 )
 
+// Runner is an interface for fetching and reading
+// snapshot blocks
+type Runner interface {
+	Explore() ([]tsdb.BlockReader, error)
+	Read(context.Context, tsdb.BlockReader) (*prometheus.CloseableSeriesSet, error)
+}
+
 type prometheusProcessor struct {
-	// prometheus client fetches and reads
+	// Runner fetches and reads
 	// snapshot blocks
-	cl *prometheus.Client
+	cl Runner
 	// importer performs import requests
 	// for timeseries data returned from
 	// snapshot blocks
@@ -48,7 +56,7 @@ func (pp *prometheusProcessor) run(ctx context.Context) error {
 		return nil
 	}
 
-	if err := pp.processBlocks(blocks); err != nil {
+	if err := pp.processBlocks(ctx, blocks); err != nil {
 		return fmt.Errorf("migration failed: %s", err)
 	}
 
@@ -57,11 +65,17 @@ func (pp *prometheusProcessor) run(ctx context.Context) error {
 	return nil
 }
 
-func (pp *prometheusProcessor) do(b tsdb.BlockReader) error {
-	ss, err := pp.cl.Read(b)
+func (pp *prometheusProcessor) do(ctx context.Context, b tsdb.BlockReader) error {
+	css, err := pp.cl.Read(ctx, b)
 	if err != nil {
 		return fmt.Errorf("failed to read block: %s", err)
 	}
+	defer func() {
+		if err := css.Close(); err != nil {
+			log.Printf("cannot close SeriesSet for block: %q : %s\n", b.Meta().ULID, err)
+		}
+	}()
+	ss := css.SeriesSet
 	var it chunkenc.Iterator
 	for ss.Next() {
 		var name string
@@ -114,7 +128,7 @@ func (pp *prometheusProcessor) do(b tsdb.BlockReader) error {
 	return ss.Err()
 }
 
-func (pp *prometheusProcessor) processBlocks(blocks []tsdb.BlockReader) error {
+func (pp *prometheusProcessor) processBlocks(ctx context.Context, blocks []tsdb.BlockReader) error {
 	promBlocksTotal.Add(len(blocks))
 	bar := barpool.AddWithTemplate(fmt.Sprintf(barTpl, "Processing blocks"), len(blocks))
 	if err := barpool.Start(); err != nil {
@@ -130,11 +144,16 @@ func (pp *prometheusProcessor) processBlocks(blocks []tsdb.BlockReader) error {
 	for range pp.cc {
 		wg.Go(func() {
 			for br := range blockReadersCh {
-				if err := pp.do(br); err != nil {
+				if err := pp.do(ctx, br); err != nil {
 					promErrorsTotal.Inc()
-					errCh <- fmt.Errorf("read failed for block %q: %s", br.Meta().ULID, err)
+					errCh <- fmt.Errorf("cannot read block %q: %s", br.Meta().ULID, err)
 					return
 				}
+				if cb, ok := br.(io.Closer); ok {
+					if err := cb.Close(); err != nil {
+						errCh <- fmt.Errorf("cannot close block: %q: %w", br.Meta().ULID, err)
+					}
+				}
 				promBlocksProcessed.Inc()
 				bar.Increment()
 			}

app/vmctl/prometheus/prometheus.go

@@ -8,6 +8,8 @@ import (
 	"github.com/prometheus/prometheus/model/labels"
 	"github.com/prometheus/prometheus/storage"
 	"github.com/prometheus/prometheus/tsdb"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/vmctlutil"
 )
 
 // Config contains a list of params needed
@@ -60,13 +62,13 @@ func NewClient(cfg Config) (*Client, error) {
 		return nil, fmt.Errorf("failed to open snapshot %q: %s", cfg.Snapshot, err)
 	}
 	c := &Client{DBReadOnly: db}
-	minTime, maxTime, err := parseTime(cfg.Filter.TimeMin, cfg.Filter.TimeMax)
+	timeMin, timeMax, err := parseTime(cfg.Filter.TimeMin, cfg.Filter.TimeMax)
 	if err != nil {
 		return nil, fmt.Errorf("failed to parse time in filter: %s", err)
 	}
 	c.filter = filter{
-		min:        minTime,
-		max:        maxTime,
+		min:        timeMin,
+		max:        timeMax,
 		label:      cfg.Filter.Label,
 		labelValue: cfg.Filter.LabelValue,
 	}
@@ -83,7 +85,7 @@ func (c *Client) Explore() ([]tsdb.BlockReader, error) {
 	if err != nil {
 		return nil, fmt.Errorf("failed to fetch blocks: %s", err)
 	}
-	s := &Stats{
+	s := &vmctlutil.Stats{
 		Filtered: c.filter.min != 0 || c.filter.max != 0 || c.filter.label != "",
 		Blocks:   len(blocks),
 	}
@@ -108,9 +110,15 @@ func (c *Client) Explore() ([]tsdb.BlockReader, error) {
 	return blocksToImport, nil
 }
 
+// CloseableSeriesSet defines a SeriesSet with Close method
+type CloseableSeriesSet struct {
+	SeriesSet storage.SeriesSet
+	Close     func() error
+}
+
 // Read reads the given BlockReader according to configured
 // time and label filters.
-func (c *Client) Read(block tsdb.BlockReader) (storage.SeriesSet, error) {
+func (c *Client) Read(ctx context.Context, block tsdb.BlockReader) (*CloseableSeriesSet, error) {
 	minTime, maxTime := block.Meta().MinTime, block.Meta().MaxTime
 	if c.filter.min != 0 {
 		minTime = c.filter.min
@@ -122,8 +130,8 @@ func (c *Client) Read(block tsdb.BlockReader) (storage.SeriesSet, error) {
 	if err != nil {
 		return nil, err
 	}
-	ss := q.Select(context.Background(), false, nil, labels.MustNewMatcher(labels.MatchRegexp, c.filter.label, c.filter.labelValue))
-	return ss, nil
+	ss := q.Select(ctx, false, nil, labels.MustNewMatcher(labels.MatchRegexp, c.filter.label, c.filter.labelValue))
+	return &CloseableSeriesSet{ss, q.Close}, nil
 }
 
 func parseTime(start, end string) (int64, int64, error) {

app/vmctl/vmctlutil/stats.go

@@ -1,4 +1,4 @@
-package prometheus
+package vmctlutil
 
 import (
 	"fmt"
@@ -18,7 +18,7 @@ type Stats struct {
 
 // String returns string representation for s.
 func (s Stats) String() string {
-	str := fmt.Sprintf("Prometheus snapshot stats:\n"+
+	str := fmt.Sprintf("Snapshot stats:\n"+
 		"  blocks found: %d;\n"+
 		"  blocks skipped by time filter: %d;\n"+
 		"  min time: %d (%v);\n"+

app/vmctl/vmctlutil/time_test.go

@@ -20,6 +20,9 @@ func TestGetTime_Failure(t *testing.T) {
 
 	// negative time
 	f("-292273086-05-16T16:47:06Z")
+
+	// relative duration that resolves to a timestamp before 1970
+	f("-9223372036.855")
 }
 
 func TestGetTime_Success(t *testing.T) {
@@ -77,9 +80,6 @@ func TestGetTime_Success(t *testing.T) {
 	// float timestamp representation",
 	f("1562529662.324", time.Date(2019, 7, 7, 20, 01, 02, 324e6, time.UTC))
 
-	// negative timestamp
-	f("-9223372036.855", time.Date(1970, 01, 01, 00, 00, 00, 00, time.UTC))
-
 	// big timestamp
 	f("1223372036855", time.Date(2008, 10, 7, 9, 33, 56, 855e6, time.UTC))
 

app/vminsert/main.go

@@ -89,6 +89,7 @@ var staticServer = http.FileServer(http.FS(staticFiles))
 func Init() {
 	relabel.Init()
 	common.InitStreamAggr()
+	opentelemetry.Init()
 	protoparserutil.StartUnmarshalWorkers()
 	if len(*graphiteListenAddr) > 0 {
 		graphiteServer = graphiteserver.MustStart(*graphiteListenAddr, *graphiteUseProxyProtocol, graphite.InsertHandler)

app/vminsert/opentelemetry/request_handler.go

@@ -20,6 +20,11 @@ var (
 	metadataInserted = metrics.NewCounter(`vm_metadata_rows_inserted_total{type="opentelemetry"}`)
 )
 
+// Init must be called after flag.Parse and before using the opentelemetry package.
+func Init() {
+	stream.InitDecodeOptions()
+}
+
 // InsertHandler processes opentelemetry metrics.
 func InsertHandler(req *http.Request) error {
 	extraLabels, err := protoparserutil.GetExtraLabels(req)

app/vmselect/main.go

@@ -60,15 +60,17 @@ func getDefaultMaxConcurrentRequests() int {
 
 // Init initializes vmselect
 func Init() {
-	tmpDirPath := *vmstorage.DataPath + "/tmp"
+	tmpDirPath := vmstorage.DataPath() + "/tmp"
 	fs.MustRemoveDirContents(tmpDirPath)
 	netstorage.InitTmpBlocksDir(tmpDirPath)
-	promql.InitRollupResultCache(*vmstorage.DataPath + "/cache/rollupResult")
+	promql.InitRollupResultCache(vmstorage.DataPath() + "/cache/rollupResult")
 	prometheus.InitMaxUniqueTimeseries(*maxConcurrentRequests)
 
 	concurrencyLimitCh = make(chan struct{}, *maxConcurrentRequests)
 	initVMUIConfig()
 	initVMAlertProxy()
+
+	flagutil.RegisterSecretFlag("vmalert.proxyURL")
 }
 
 // Stop stops vmselect
@@ -262,6 +264,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		return true
 	case "/api/v1/export":
 		exportRequests.Inc()
+		httpserver.EnableCORS(w, r)
 		if err := prometheus.ExportHandler(startTime, w, r); err != nil {
 			exportErrors.Inc()
 			httpserver.Errorf(w, r, "%s", err)
@@ -270,6 +273,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		return true
 	case "/api/v1/export/csv":
 		exportCSVRequests.Inc()
+		httpserver.EnableCORS(w, r)
 		if err := prometheus.ExportCSVHandler(startTime, w, r); err != nil {
 			exportCSVErrors.Inc()
 			httpserver.Errorf(w, r, "%s", err)
@@ -278,6 +282,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		return true
 	case "/api/v1/export/native":
 		exportNativeRequests.Inc()
+		httpserver.EnableCORS(w, r)
 		if err := prometheus.ExportNativeHandler(startTime, w, r); err != nil {
 			exportNativeErrors.Inc()
 			httpserver.Errorf(w, r, "%s", err)

app/vmselect/netstorage/netstorage.go

@@ -990,9 +990,6 @@ func ExportBlocks(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline sear
 		return fmt.Errorf("timeout exceeded before starting data export: %s", deadline.String())
 	}
 	tr := sq.GetTimeRange()
-	if err := vmstorage.CheckTimeRange(tr); err != nil {
-		return err
-	}
 	tfss, err := setupTfss(qt, tr, sq.TagFilterss, sq.MaxMetrics, deadline)
 	if err != nil {
 		return err
@@ -1098,9 +1095,6 @@ func SearchMetricNames(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline
 
 	// Setup search.
 	tr := sq.GetTimeRange()
-	if err := vmstorage.CheckTimeRange(tr); err != nil {
-		return nil, err
-	}
 	tfss, err := setupTfss(qt, tr, sq.TagFilterss, sq.MaxMetrics, deadline)
 	if err != nil {
 		return nil, err
@@ -1127,9 +1121,6 @@ func ProcessSearchQuery(qt *querytracer.Tracer, sq *storage.SearchQuery, deadlin
 
 	// Setup search.
 	tr := sq.GetTimeRange()
-	if err := vmstorage.CheckTimeRange(tr); err != nil {
-		return nil, err
-	}
 	tfss, err := setupTfss(qt, tr, sq.TagFilterss, sq.MaxMetrics, deadline)
 	if err != nil {
 		return nil, err

app/vmselect/prometheus/federate.qtpl

@@ -2,13 +2,16 @@
 	"math"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/netstorage"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+    "github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
+    "github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
 ) %}
 
 {% stripspace %}
 
 // Federate writes rs in /federate format.
 // See https://prometheus.io/docs/prometheus/latest/federation/
-{% func Federate(rs *netstorage.Result) %}
+{% func Federate(rs *netstorage.Result, escapeScheme string) %}
 	{% code
 		values := rs.Values
 		timestamps := rs.Timestamps
@@ -24,10 +27,54 @@
 			See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3185
 		{% endcomment %}
 		{% return %}
-	{% endif %}
-	{%= prometheusMetricName(&rs.MetricName) %}{% space %}
+    {% endif %}
+
+    {% switch escapeScheme %}
+       {% case federateEscapeSchemeUTF8 %}
+          {%= prometheusFederateMetricNameUTF8(&rs.MetricName) %}{% space %}
+
+       {% case federateEscapeSchemeUnderscore %}
+         {%= prometheusFederateMetricNameEscapeUnderscore(&rs.MetricName) %}{% space %}
+
+       {% case "" %}
+         {%= prometheusMetricName(&rs.MetricName) %}{% space %}
+    {% endswitch %}
+
 	{%f= lastValue %}{% space %}
 	{%dl= timestamps[len(timestamps)-1] %}{% newline %}
 {% endfunc %}
 
+{% func prometheusFederateMetricNameEscapeUnderscore(mn *storage.MetricName) %}
+	{%s= promrelabel.SanitizeMetricName(bytesutil.ToUnsafeString(mn.MetricGroup)) %}
+	{% if len(mn.Tags) > 0 %}
+	{
+		{% code tags := mn.Tags %}
+		{%s= promrelabel.SanitizeLabelName(bytesutil.ToUnsafeString(tags[0].Key)) %}={%= escapePrometheusLabel(tags[0].Value) %}
+		{% code tags = tags[1:] %}
+		{% for i := range tags %}
+			{% code tag := &tags[i] %}
+			,{%s= promrelabel.SanitizeLabelName(bytesutil.ToUnsafeString(tag.Key)) %}={%= escapePrometheusLabel(tag.Value) %}
+		{% endfor %}
+	}
+	{% endif %}
+{% endfunc %}
+
+{% func prometheusFederateMetricNameUTF8(mn *storage.MetricName) %}
+	{
+        {%= escapePrometheusLabel(mn.MetricGroup) %}
+        {% if len(mn.Tags) > 0 %}
+        ,
+		{% code tags := mn.Tags %}
+		{%= escapePrometheusLabel(tags[0].Key) %}={%= escapePrometheusLabel(tags[0].Value) %}
+		{% code tags = tags[1:] %}
+		{% for i := range tags %}
+			{% code tag := &tags[i] %}
+			,{%= escapePrometheusLabel(tag.Key) %}={%= escapePrometheusLabel(tag.Value) %}
+		{% endfor %}
+        {% endif %}
+	}
+{% endfunc %}
+
+
+
 {% endstripspace %}

app/vmselect/prometheus/federate.qtpl.go

@@ -9,82 +9,241 @@ import (
 	"math"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/netstorage"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
 )
 
 // Federate writes rs in /federate format.// See https://prometheus.io/docs/prometheus/latest/federation/
 
-//line app/vmselect/prometheus/federate.qtpl:11
+//line app/vmselect/prometheus/federate.qtpl:14
 import (
 	qtio422016 "io"
 
 	qt422016 "github.com/valyala/quicktemplate"
 )
 
-//line app/vmselect/prometheus/federate.qtpl:11
+//line app/vmselect/prometheus/federate.qtpl:14
 var (
 	_ = qtio422016.Copy
 	_ = qt422016.AcquireByteBuffer
 )
 
-//line app/vmselect/prometheus/federate.qtpl:11
-func StreamFederate(qw422016 *qt422016.Writer, rs *netstorage.Result) {
-//line app/vmselect/prometheus/federate.qtpl:13
+//line app/vmselect/prometheus/federate.qtpl:14
+func StreamFederate(qw422016 *qt422016.Writer, rs *netstorage.Result, escapeScheme string) {
+//line app/vmselect/prometheus/federate.qtpl:16
 	values := rs.Values
 	timestamps := rs.Timestamps
 
-//line app/vmselect/prometheus/federate.qtpl:16
+//line app/vmselect/prometheus/federate.qtpl:19
 	if len(timestamps) == 0 || len(values) == 0 {
-//line app/vmselect/prometheus/federate.qtpl:16
+//line app/vmselect/prometheus/federate.qtpl:19
 		return
-//line app/vmselect/prometheus/federate.qtpl:16
+//line app/vmselect/prometheus/federate.qtpl:19
 	}
-//line app/vmselect/prometheus/federate.qtpl:18
+//line app/vmselect/prometheus/federate.qtpl:21
 	lastValue := values[len(values)-1]
 
-//line app/vmselect/prometheus/federate.qtpl:20
+//line app/vmselect/prometheus/federate.qtpl:23
 	if math.IsNaN(lastValue) {
-//line app/vmselect/prometheus/federate.qtpl:26
+//line app/vmselect/prometheus/federate.qtpl:29
 		return
-//line app/vmselect/prometheus/federate.qtpl:27
+//line app/vmselect/prometheus/federate.qtpl:30
 	}
-//line app/vmselect/prometheus/federate.qtpl:28
-	streamprometheusMetricName(qw422016, &rs.MetricName)
-//line app/vmselect/prometheus/federate.qtpl:28
-	qw422016.N().S(` `)
-//line app/vmselect/prometheus/federate.qtpl:29
+//line app/vmselect/prometheus/federate.qtpl:32
+	switch escapeScheme {
+//line app/vmselect/prometheus/federate.qtpl:33
+	case federateEscapeSchemeUTF8:
+//line app/vmselect/prometheus/federate.qtpl:34
+		streamprometheusFederateMetricNameUTF8(qw422016, &rs.MetricName)
+//line app/vmselect/prometheus/federate.qtpl:34
+		qw422016.N().S(` `)
+//line app/vmselect/prometheus/federate.qtpl:36
+	case federateEscapeSchemeUnderscore:
+//line app/vmselect/prometheus/federate.qtpl:37
+		streamprometheusFederateMetricNameEscapeUnderscore(qw422016, &rs.MetricName)
+//line app/vmselect/prometheus/federate.qtpl:37
+		qw422016.N().S(` `)
+//line app/vmselect/prometheus/federate.qtpl:39
+	case "":
+//line app/vmselect/prometheus/federate.qtpl:40
+		streamprometheusMetricName(qw422016, &rs.MetricName)
+//line app/vmselect/prometheus/federate.qtpl:40
+		qw422016.N().S(` `)
+//line app/vmselect/prometheus/federate.qtpl:41
+	}
+//line app/vmselect/prometheus/federate.qtpl:43
 	qw422016.N().F(lastValue)
-//line app/vmselect/prometheus/federate.qtpl:29
+//line app/vmselect/prometheus/federate.qtpl:43
 	qw422016.N().S(` `)
-//line app/vmselect/prometheus/federate.qtpl:30
+//line app/vmselect/prometheus/federate.qtpl:44
 	qw422016.N().DL(timestamps[len(timestamps)-1])
-//line app/vmselect/prometheus/federate.qtpl:30
+//line app/vmselect/prometheus/federate.qtpl:44
 	qw422016.N().S(`
 `)
-//line app/vmselect/prometheus/federate.qtpl:31
+//line app/vmselect/prometheus/federate.qtpl:45
 }
 
-//line app/vmselect/prometheus/federate.qtpl:31
-func WriteFederate(qq422016 qtio422016.Writer, rs *netstorage.Result) {
-//line app/vmselect/prometheus/federate.qtpl:31
+//line app/vmselect/prometheus/federate.qtpl:45
+func WriteFederate(qq422016 qtio422016.Writer, rs *netstorage.Result, escapeScheme string) {
+//line app/vmselect/prometheus/federate.qtpl:45
 	qw422016 := qt422016.AcquireWriter(qq422016)
-//line app/vmselect/prometheus/federate.qtpl:31
-	StreamFederate(qw422016, rs)
-//line app/vmselect/prometheus/federate.qtpl:31
+//line app/vmselect/prometheus/federate.qtpl:45
+	StreamFederate(qw422016, rs, escapeScheme)
+//line app/vmselect/prometheus/federate.qtpl:45
 	qt422016.ReleaseWriter(qw422016)
-//line app/vmselect/prometheus/federate.qtpl:31
+//line app/vmselect/prometheus/federate.qtpl:45
 }
 
-//line app/vmselect/prometheus/federate.qtpl:31
-func Federate(rs *netstorage.Result) string {
-//line app/vmselect/prometheus/federate.qtpl:31
+//line app/vmselect/prometheus/federate.qtpl:45
+func Federate(rs *netstorage.Result, escapeScheme string) string {
+//line app/vmselect/prometheus/federate.qtpl:45
 	qb422016 := qt422016.AcquireByteBuffer()
-//line app/vmselect/prometheus/federate.qtpl:31
-	WriteFederate(qb422016, rs)
-//line app/vmselect/prometheus/federate.qtpl:31
+//line app/vmselect/prometheus/federate.qtpl:45
+	WriteFederate(qb422016, rs, escapeScheme)
+//line app/vmselect/prometheus/federate.qtpl:45
 	qs422016 := string(qb422016.B)
-//line app/vmselect/prometheus/federate.qtpl:31
+//line app/vmselect/prometheus/federate.qtpl:45
 	qt422016.ReleaseByteBuffer(qb422016)
-//line app/vmselect/prometheus/federate.qtpl:31
+//line app/vmselect/prometheus/federate.qtpl:45
 	return qs422016
-//line app/vmselect/prometheus/federate.qtpl:31
+//line app/vmselect/prometheus/federate.qtpl:45
+}
+
+//line app/vmselect/prometheus/federate.qtpl:47
+func streamprometheusFederateMetricNameEscapeUnderscore(qw422016 *qt422016.Writer, mn *storage.MetricName) {
+//line app/vmselect/prometheus/federate.qtpl:48
+	qw422016.N().S(promrelabel.SanitizeMetricName(bytesutil.ToUnsafeString(mn.MetricGroup)))
+//line app/vmselect/prometheus/federate.qtpl:49
+	if len(mn.Tags) > 0 {
+//line app/vmselect/prometheus/federate.qtpl:49
+		qw422016.N().S(`{`)
+//line app/vmselect/prometheus/federate.qtpl:51
+		tags := mn.Tags
+
+//line app/vmselect/prometheus/federate.qtpl:52
+		qw422016.N().S(promrelabel.SanitizeLabelName(bytesutil.ToUnsafeString(tags[0].Key)))
+//line app/vmselect/prometheus/federate.qtpl:52
+		qw422016.N().S(`=`)
+//line app/vmselect/prometheus/federate.qtpl:52
+		streamescapePrometheusLabel(qw422016, tags[0].Value)
+//line app/vmselect/prometheus/federate.qtpl:53
+		tags = tags[1:]
+
+//line app/vmselect/prometheus/federate.qtpl:54
+		for i := range tags {
+//line app/vmselect/prometheus/federate.qtpl:55
+			tag := &tags[i]
+
+//line app/vmselect/prometheus/federate.qtpl:55
+			qw422016.N().S(`,`)
+//line app/vmselect/prometheus/federate.qtpl:56
+			qw422016.N().S(promrelabel.SanitizeLabelName(bytesutil.ToUnsafeString(tag.Key)))
+//line app/vmselect/prometheus/federate.qtpl:56
+			qw422016.N().S(`=`)
+//line app/vmselect/prometheus/federate.qtpl:56
+			streamescapePrometheusLabel(qw422016, tag.Value)
+//line app/vmselect/prometheus/federate.qtpl:57
+		}
+//line app/vmselect/prometheus/federate.qtpl:57
+		qw422016.N().S(`}`)
+//line app/vmselect/prometheus/federate.qtpl:59
+	}
+//line app/vmselect/prometheus/federate.qtpl:60
+}
+
+//line app/vmselect/prometheus/federate.qtpl:60
+func writeprometheusFederateMetricNameEscapeUnderscore(qq422016 qtio422016.Writer, mn *storage.MetricName) {
+//line app/vmselect/prometheus/federate.qtpl:60
+	qw422016 := qt422016.AcquireWriter(qq422016)
+//line app/vmselect/prometheus/federate.qtpl:60
+	streamprometheusFederateMetricNameEscapeUnderscore(qw422016, mn)
+//line app/vmselect/prometheus/federate.qtpl:60
+	qt422016.ReleaseWriter(qw422016)
+//line app/vmselect/prometheus/federate.qtpl:60
+}
+
+//line app/vmselect/prometheus/federate.qtpl:60
+func prometheusFederateMetricNameEscapeUnderscore(mn *storage.MetricName) string {
+//line app/vmselect/prometheus/federate.qtpl:60
+	qb422016 := qt422016.AcquireByteBuffer()
+//line app/vmselect/prometheus/federate.qtpl:60
+	writeprometheusFederateMetricNameEscapeUnderscore(qb422016, mn)
+//line app/vmselect/prometheus/federate.qtpl:60
+	qs422016 := string(qb422016.B)
+//line app/vmselect/prometheus/federate.qtpl:60
+	qt422016.ReleaseByteBuffer(qb422016)
+//line app/vmselect/prometheus/federate.qtpl:60
+	return qs422016
+//line app/vmselect/prometheus/federate.qtpl:60
+}
+
+//line app/vmselect/prometheus/federate.qtpl:62
+func streamprometheusFederateMetricNameUTF8(qw422016 *qt422016.Writer, mn *storage.MetricName) {
+//line app/vmselect/prometheus/federate.qtpl:62
+	qw422016.N().S(`{`)
+//line app/vmselect/prometheus/federate.qtpl:64
+	streamescapePrometheusLabel(qw422016, mn.MetricGroup)
+//line app/vmselect/prometheus/federate.qtpl:65
+	if len(mn.Tags) > 0 {
+//line app/vmselect/prometheus/federate.qtpl:65
+		qw422016.N().S(`,`)
+//line app/vmselect/prometheus/federate.qtpl:67
+		tags := mn.Tags
+
+//line app/vmselect/prometheus/federate.qtpl:68
+		streamescapePrometheusLabel(qw422016, tags[0].Key)
+//line app/vmselect/prometheus/federate.qtpl:68
+		qw422016.N().S(`=`)
+//line app/vmselect/prometheus/federate.qtpl:68
+		streamescapePrometheusLabel(qw422016, tags[0].Value)
+//line app/vmselect/prometheus/federate.qtpl:69
+		tags = tags[1:]
+
+//line app/vmselect/prometheus/federate.qtpl:70
+		for i := range tags {
+//line app/vmselect/prometheus/federate.qtpl:71
+			tag := &tags[i]
+
+//line app/vmselect/prometheus/federate.qtpl:71
+			qw422016.N().S(`,`)
+//line app/vmselect/prometheus/federate.qtpl:72
+			streamescapePrometheusLabel(qw422016, tag.Key)
+//line app/vmselect/prometheus/federate.qtpl:72
+			qw422016.N().S(`=`)
+//line app/vmselect/prometheus/federate.qtpl:72
+			streamescapePrometheusLabel(qw422016, tag.Value)
+//line app/vmselect/prometheus/federate.qtpl:73
+		}
+//line app/vmselect/prometheus/federate.qtpl:74
+	}
+//line app/vmselect/prometheus/federate.qtpl:74
+	qw422016.N().S(`}`)
+//line app/vmselect/prometheus/federate.qtpl:76
+}
+
+//line app/vmselect/prometheus/federate.qtpl:76
+func writeprometheusFederateMetricNameUTF8(qq422016 qtio422016.Writer, mn *storage.MetricName) {
+//line app/vmselect/prometheus/federate.qtpl:76
+	qw422016 := qt422016.AcquireWriter(qq422016)
+//line app/vmselect/prometheus/federate.qtpl:76
+	streamprometheusFederateMetricNameUTF8(qw422016, mn)
+//line app/vmselect/prometheus/federate.qtpl:76
+	qt422016.ReleaseWriter(qw422016)
+//line app/vmselect/prometheus/federate.qtpl:76
+}
+
+//line app/vmselect/prometheus/federate.qtpl:76
+func prometheusFederateMetricNameUTF8(mn *storage.MetricName) string {
+//line app/vmselect/prometheus/federate.qtpl:76
+	qb422016 := qt422016.AcquireByteBuffer()
+//line app/vmselect/prometheus/federate.qtpl:76
+	writeprometheusFederateMetricNameUTF8(qb422016, mn)
+//line app/vmselect/prometheus/federate.qtpl:76
+	qs422016 := string(qb422016.B)
+//line app/vmselect/prometheus/federate.qtpl:76
+	qt422016.ReleaseByteBuffer(qb422016)
+//line app/vmselect/prometheus/federate.qtpl:76
+	return qs422016
+//line app/vmselect/prometheus/federate.qtpl:76
 }

app/vmselect/prometheus/federate_test.go

@@ -8,15 +8,15 @@ import (
 )
 
 func TestFederate(t *testing.T) {
-	f := func(rs *netstorage.Result, expectedResult string) {
+	f := func(rs *netstorage.Result, escapeScheme string, expectedResult string) {
 		t.Helper()
-		result := Federate(rs)
+		result := Federate(rs, escapeScheme)
 		if result != expectedResult {
 			t.Fatalf("unexpected result; got\n%s\nwant\n%s", result, expectedResult)
 		}
 	}
 
-	f(&netstorage.Result{}, ``)
+	f(&netstorage.Result{}, ``, ``)
 
 	f(&netstorage.Result{
 		MetricName: storage.MetricName{
@@ -39,5 +39,60 @@ func TestFederate(t *testing.T) {
 		},
 		Values:     []float64{1.23},
 		Timestamps: []int64{123},
-	}, `foo{a="b",qqq="\\",abc="a<b\"\\c"} 1.23 123`+"\n")
+	}, ``, `foo{a="b",qqq="\\",abc="a<b\"\\c"} 1.23 123`+"\n")
+
+	f(&netstorage.Result{
+		MetricName: storage.MetricName{
+			MetricGroup: []byte("foo.bar"),
+			Tags: []storage.Tag{
+				{
+					Key:   []byte("some.!other"),
+					Value: []byte("value.unchanged!."),
+				},
+				{
+					Key:   []byte("qqq"),
+					Value: []byte("\\"),
+				},
+				{
+					Key:   []byte("!key"),
+					Value: []byte("value"),
+				},
+				{
+					Key: []byte("abc"),
+					// Verify that < isn't encoded. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5431
+					Value: []byte("a<b\"\\c"),
+				},
+			},
+		},
+		Values:     []float64{1.23},
+		Timestamps: []int64{123},
+	}, federateEscapeSchemeUnderscore, `foo_bar{some__other="value.unchanged!.",qqq="\\",_key="value",abc="a<b\"\\c"} 1.23 123`+"\n")
+
+	f(&netstorage.Result{
+		MetricName: storage.MetricName{
+			MetricGroup: []byte("foo.bar"),
+			Tags: []storage.Tag{
+				{
+					Key:   []byte("some.!other"),
+					Value: []byte("value.unchanged!."),
+				},
+				{
+					Key:   []byte("qqq"),
+					Value: []byte("\\"),
+				},
+				{
+					Key:   []byte("!key"),
+					Value: []byte("value"),
+				},
+				{
+					Key: []byte(`ab"c`),
+					// Verify that < isn't encoded. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5431
+					Value: []byte("a<b\"\\c"),
+				},
+			},
+		},
+		Values:     []float64{1.23},
+		Timestamps: []int64{123},
+	}, federateEscapeSchemeUTF8, `{"foo.bar","some.!other"="value.unchanged!.","qqq"="\\","!key"="value","ab\"c"="a<b\"\\c"} 1.23 123`+"\n")
+
 }

app/vmselect/prometheus/federate_timing_test.go

@@ -9,16 +9,17 @@ import (
 )
 
 func BenchmarkFederate(b *testing.B) {
+
 	rs := &netstorage.Result{
 		MetricName: storage.MetricName{
-			MetricGroup: []byte("foo_bar_bazaaaa_total"),
+			MetricGroup: []byte("foo_bar_?_._bazaaaa_total"),
 			Tags: []storage.Tag{
 				{
-					Key:   []byte("instance"),
+					Key:   []byte("instance:job"),
 					Value: []byte("foobarbaz:2344"),
 				},
 				{
-					Key:   []byte("job"),
+					Key:   []byte("job.name"),
 					Value: []byte("aaabbbccc"),
 				},
 			},
@@ -27,12 +28,22 @@ func BenchmarkFederate(b *testing.B) {
 		Timestamps: []int64{1234567890},
 	}
 
-	b.ReportAllocs()
-	b.RunParallel(func(pb *testing.PB) {
-		var bb bytes.Buffer
-		for pb.Next() {
-			bb.Reset()
-			WriteFederate(&bb, rs)
-		}
-	})
+	f := func(name, escapeScheme string) {
+		b.Helper()
+
+		b.Run(name, func(b *testing.B) {
+			b.ReportAllocs()
+			b.RunParallel(func(pb *testing.PB) {
+				var bb bytes.Buffer
+				for pb.Next() {
+					bb.Reset()
+					WriteFederate(&bb, rs, escapeScheme)
+				}
+			})
+		})
+	}
+
+	f("without escape", "")
+	f("allow-utf-8", federateEscapeSchemeUTF8)
+	f("legacy-underscore", federateEscapeSchemeUnderscore)
 }

app/vmselect/prometheus/prometheus.go

@@ -108,6 +108,11 @@ func PrettifyQuery(w http.ResponseWriter, r *http.Request) {
 	_ = bw.Flush()
 }
 
+const (
+	federateEscapeSchemeUnderscore = "underscore"
+	federateEscapeSchemeUTF8       = "utf-8"
+)
+
 // FederateHandler implements /federate . See https://prometheus.io/docs/prometheus/latest/federation/
 func FederateHandler(startTime time.Time, w http.ResponseWriter, r *http.Request) error {
 	defer federateDuration.UpdateDuration(startTime)
@@ -132,6 +137,21 @@ func FederateHandler(startTime time.Time, w http.ResponseWriter, r *http.Request
 		return fmt.Errorf("cannot fetch data for %q: %w", sq, err)
 	}
 
+	// add best-effort format negotiation
+	// modern version of Prometheus always set allow-utf-8 in order to properly parse utf-8 names and labels
+	// prometheus below v3 uses underscore escaping by default and it's the most common standard
+	var escapeScheme string
+	accept := r.Header.Get("Accept")
+	if len(accept) > 0 && strings.Contains(accept, "allow-utf-8") {
+		escapeScheme = federateEscapeSchemeUTF8
+	}
+	// try fallback to legacy underscore escaping if needed for Prometheus only,
+	// it's not widely used after Prometheus v3.0 release
+	// most of the Prometheus scrapers already use allow-utf-8 header
+	isPrometheus := strings.HasPrefix(r.UserAgent(), "Prometheus")
+	if len(escapeScheme) == 0 && isPrometheus {
+		escapeScheme = federateEscapeSchemeUnderscore
+	}
 	w.Header().Set("Content-Type", "text/plain; charset=utf-8")
 	bw := bufferedwriter.Get(w)
 	defer bufferedwriter.Put(bw)
@@ -141,7 +161,7 @@ func FederateHandler(startTime time.Time, w http.ResponseWriter, r *http.Request
 			return err
 		}
 		bb := sw.getBuffer(workerID)
-		WriteFederate(bb, rs)
+		WriteFederate(bb, rs, escapeScheme)
 		return sw.maybeFlushBuffer(bb)
 	})
 	if err == nil {

app/vmselect/promql/exec_test.go

@@ -8801,6 +8801,17 @@ func TestExecSuccess(t *testing.T) {
 		resultExpected := []netstorage.Result{r}
 		f(q, resultExpected)
 	})
+	t.Run(`range()`, func(t *testing.T) {
+		t.Parallel()
+		q := `range()`
+		r := netstorage.Result{
+			MetricName: metricNameExpected,
+			Values:     []float64{1000, 1000, 1000, 1000, 1000, 1000},
+			Timestamps: timestampsExpected,
+		}
+		resultExpected := []netstorage.Result{r}
+		f(q, resultExpected)
+	})
 	t.Run(`step()`, func(t *testing.T) {
 		t.Parallel()
 		q := `time() / step()`

app/vmselect/promql/rollup.go

@@ -2439,8 +2439,15 @@ func rollupIntegrate(rfa *rollupFuncArg) float64 {
 		prevTimestamp = timestamp
 		prevValue = v
 	}
-	dt := float64(rfa.currTimestamp-prevTimestamp) / 1e3
-	sum += prevValue * dt
+	// Only extrapolate the last value through to currTimestamp when the time
+	// series has any sample after the lookbehind window. When realNextValue is
+	// NaN the series has effectively ended at prevTimestamp, so accruing area
+	// past it would overcount the integral.
+	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9474
+	if !math.IsNaN(rfa.realNextValue) {
+		dt := float64(rfa.currTimestamp-prevTimestamp) / 1e3
+		sum += prevValue * dt
+	}
 	return sum
 }
 

app/vmselect/promql/rollup_test.go

@@ -1385,10 +1385,65 @@ func TestRollupFuncsNoWindow(t *testing.T) {
 		if samplesScanned != 24 {
 			t.Fatalf("expecting 24 samplesScanned from rollupConfig.Do; got %d", samplesScanned)
 		}
-		valuesExpected := []float64{nan, 2.148, 1.593, 1.156, 1.36}
+		// At tEnd=160 the series has no samples past the window (last sample is at
+		// ts=130), so integrate() must not extrapolate prevValue through tEnd.
+		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9474
+		valuesExpected := []float64{nan, 2.148, 1.593, 1.156, 0.34}
 		timestampsExpected := []int64{0, 40, 80, 120, 160}
 		testRowsEqual(t, values, rc.Timestamps, valuesExpected, timestampsExpected)
 	})
+	t.Run("integrate_past_series_end", func(t *testing.T) {
+		// Constant series of value 1.0 from t=0..3600s (1h) at 60s step.
+		// Query integrate(metric[1h]) across t=0..10800s with 600s step.
+		// For t=0..3600s the window overlap with the data is [0,t], so the integral grows from 0 to 3600 (seconds).
+		// After the series ends, integrate must NOT keep accruing 3600 — it
+		// should taper to 0 once the lookbehind window is entirely past the
+		// last sample.
+		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9474
+		var testValues []int64
+		var testTimestamps []float64
+		for t := int64(0); t <= 3600_000; t += 60_000 {
+			testValues = append(testValues, t)
+			testTimestamps = append(testTimestamps, 1.0)
+		}
+		rc := rollupConfig{
+			Func:               rollupIntegrate,
+			Start:              0,
+			End:                10800_000,
+			Step:               600_000,
+			Window:             3600_000,
+			MaxPointsPerSeries: 1e4,
+		}
+		rc.Timestamps = rc.getTimestamps()
+		values, _ := rc.Do(nil, testTimestamps, testValues)
+		for i, ti := range rc.Timestamps {
+			v := values[i]
+
+			// For t<=3600s: window overlap is [0,ti], integral equals ti in seconds.
+			if ti <= 3600_000 {
+				expV := float64(ti / 1e3)
+				if v != expV {
+					t.Fatalf("unexpected integrate result at t=%ds, want=%.3f got=%.3f", ti/1e3, expV, v)
+				}
+				continue
+			}
+			// For 3600s<t<7200s: data is partially outside the window, so the
+			// integral shrinks linearly from 3600 to 0 as t approaches 7200s.
+			if ti > 3600_000 && ti < 7200_000 {
+				expV := float64((7200_000 - ti) / 1e3)
+				if v != expV {
+					t.Fatalf("unexpected integrate result at t=%ds, want=%.3f got=%.3f", ti/1e3, expV, v)
+				}
+				continue
+			}
+			if ti >= 7200_000 {
+				// Window entirely past data end: must be NaN.
+				if !math.IsNaN(v) {
+					t.Fatalf("unexpected integrate result at t=%ds, want=NaN got=%.3f", ti/1e3, v)
+				}
+			}
+		}
+	})
 	t.Run("distinct_over_time_1", func(t *testing.T) {
 		rc := rollupConfig{
 			Func:               rollupDistinct,

app/vmselect/promql/transform.go

@@ -90,6 +90,7 @@ var transformFuncs = map[string]transformFunc{
 	"rand":                       newTransformRand(newRandFloat64),
 	"rand_exponential":           newTransformRand(newRandExpFloat64),
 	"rand_normal":                newTransformRand(newRandNormFloat64),
+	"range":                      newTransformFuncZeroArgs(transformRange),
 	"range_avg":                  newTransformFuncRange(runningAvg),
 	"range_first":                transformRangeFirst,
 	"range_last":                 transformRangeLast,
@@ -2808,6 +2809,10 @@ func transformEnd(tfa *transformFuncArg) float64 {
 	return float64(tfa.ec.End) / 1e3
 }
 
+func transformRange(tfa *transformFuncArg) float64 {
+	return float64(tfa.ec.End-tfa.ec.Start) / 1e3
+}
+
 // copyTimeseries returns a copy of tss.
 func copyTimeseries(tss []*timeseries) []*timeseries {
 	rvs := make([]*timeseries, len(tss))

app/vmselect/searchutil/searchutil.go

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

app/vmselect/searchutil/searchutil_test.go

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

app/vmselect/vmui/index.html

@@ -37,11 +37,11 @@
   <meta property="og:title" content="UI for VictoriaMetrics">
   <meta property="og:url" content="https://victoriametrics.com/">
   <meta property="og:description" content="Explore and troubleshoot your VictoriaMetrics data">
-  <script type="module" crossorigin src="./assets/index-fsxQMWD9.js"></script>
+  <script type="module" crossorigin src="./assets/index-U3iNn2Tx.js"></script>
   <link rel="modulepreload" crossorigin href="./assets/rolldown-runtime-COnpUsM8.js">
-  <link rel="modulepreload" crossorigin href="./assets/vendor-BF3F25aG.js">
+  <link rel="modulepreload" crossorigin href="./assets/vendor-C8Kwp93_.js">
   <link rel="stylesheet" crossorigin href="./assets/vendor-CnsZ1jie.css">
-  <link rel="stylesheet" crossorigin href="./assets/index-D2OEy8Ra.css">
+  <link rel="stylesheet" crossorigin href="./assets/index-BL7jEFBa.css">
 </head>
 <body>
 <noscript>You need to enable JavaScript to run this app.</noscript>

app/vmstorage/main.go

@@ -31,6 +31,7 @@ import (
 )
 
 var (
+	storageDataPath = flag.String("storageDataPath", "victoria-metrics-data", "Path to storage data")
 	retentionPeriod = flagutil.NewRetentionDuration("retentionPeriod", "1M", "Data with timestamps outside the retentionPeriod is automatically deleted. The minimum retentionPeriod is 24h or 1d. "+
 		"See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#retention. See also -retentionFilter")
 	futureRetention = flagutil.NewRetentionDuration("futureRetention", "2d", "Data with timestamps bigger than now+futureRetention is automatically deleted. "+
@@ -43,9 +44,6 @@ var (
 
 	precisionBits = flag.Int("precisionBits", 64, "The number of precision bits to store per each value. Lower precision bits improves data compression at the cost of precision loss")
 
-	// DataPath is a path to storage data.
-	DataPath = flag.String("storageDataPath", "victoria-metrics-data", "Path to storage data")
-
 	_ = flag.Duration("finalMergeDelay", 0, "Deprecated: this flag does nothing")
 	_ = flag.Int("bigMergeConcurrency", 0, "Deprecated: this flag does nothing")
 	_ = flag.Int("smallMergeConcurrency", 0, "Deprecated: this flag does nothing")
@@ -53,11 +51,17 @@ var (
 	retentionTimezoneOffset = flag.Duration("retentionTimezoneOffset", 0, "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)")
+	minScrapeInterval = flag.Duration("dedup.minScrapeInterval", 0, "Leave only the last sample in every time series per each discrete interval "+
+		"equal to -dedup.minScrapeInterval > 0. See also -streamAggr.dedupInterval and https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication")
+	inmemoryDataFlushInterval = flag.Duration("inmemoryDataFlushInterval", 5*time.Second, "The interval for guaranteed saving of in-memory data to disk. "+
+		"The saved data survives unclean shutdowns such as OOM crash, hardware reset, SIGKILL, etc. "+
+		"Bigger intervals may help increase the lifetime of flash storage with limited write cycles (e.g. Raspberry PI). "+
+		"Smaller intervals increase disk IO load. Minimum supported value is 1s")
 
 	logNewSeries = flag.Bool("logNewSeries", false, "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")
-	denyQueriesOutsideRetention = flag.Bool("denyQueriesOutsideRetention", false, "Whether to deny queries outside the configured -retentionPeriod. "+
-		"When set, then /api/v1/query_range would return '503 Service Unavailable' error for queries with 'from' value outside -retentionPeriod. "+
+	denyQueriesOutsideRetention = flag.Bool("denyQueriesOutsideRetention", false, "Whether to deny queries outside the configured -retentionPeriod and -futureRetention. "+
+		"When set, then /api/v1/query_range will return an error for queries with 'from' value outside -retentionPeriod or 'to' value beyond -futureRetention. "+
 		"This may be useful when multiple data sources with distinct retentions are hidden behind query-tee")
 	maxHourlySeries = flag.Int64("storage.maxHourlySeries", 0, "The maximum number of unique series can be added to the storage during the last hour. "+
 		"Excess series are logged and dropped. This can be useful for limiting series cardinality. See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#cardinality-limiter . "+
@@ -70,6 +74,11 @@ var (
 
 	minFreeDiskSpaceBytes = flagutil.NewBytes("storage.minFreeDiskSpaceBytes", 100e6, "The minimum free disk space at -storageDataPath after which the storage stops accepting new data")
 
+	finalDedupScheduleInterval = flag.Duration("storage.finalDedupScheduleCheckInterval", time.Hour, "The interval for checking when final deduplication process should be started."+
+		"Storage unconditionally adds 25% jitter to the interval value on each check evaluation."+
+		" Changing the interval to the bigger values may delay downsampling, deduplication for historical data."+
+		" See also https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication")
+
 	cacheSizeStorageTSID = flagutil.NewBytes("storage.cacheSizeStorageTSID", 0, "Overrides max size for storage/tsid cache. "+
 		"See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#cache-tuning")
 	cacheSizeStorageMetricName = flagutil.NewBytes("storage.cacheSizeStorageMetricName", 0, "Overrides max size for storage/metricName cache. "+
@@ -103,19 +112,8 @@ var (
 		"If set to 0 or a negative value, defaults to 1% of allowed memory.")
 )
 
-// CheckTimeRange returns true if the given tr is denied for querying.
-func CheckTimeRange(tr storage.TimeRange) error {
-	if !*denyQueriesOutsideRetention {
-		return nil
-	}
-	minAllowedTimestamp := int64(fasttime.UnixTimestamp()*1000) - retentionPeriod.Milliseconds()
-	if tr.MinTimestamp > minAllowedTimestamp {
-		return nil
-	}
-	return &httpserver.ErrorWithStatusCode{
-		Err:        fmt.Errorf("the given time range %s is outside the allowed -retentionPeriod=%s according to -denyQueriesOutsideRetention", &tr, retentionPeriod),
-		StatusCode: http.StatusServiceUnavailable,
-	}
+func DataPath() string {
+	return *storageDataPath
 }
 
 // Init initializes vmstorage.
@@ -124,11 +122,16 @@ func Init(resetCacheIfNeeded func(mrs []storage.MetricRow)) {
 		logger.Fatalf("invalid `-precisionBits`: %s", err)
 	}
 
-	resetResponseCacheIfNeeded = resetCacheIfNeeded
+	storage.SetDedupInterval(*minScrapeInterval)
+	storage.SetDataFlushInterval(*inmemoryDataFlushInterval)
 	storage.LegacySetRetentionTimezoneOffset(*retentionTimezoneOffset)
 	storage.SetFreeDiskSpaceLimit(minFreeDiskSpaceBytes.N)
 	storage.SetTSIDCacheSize(cacheSizeStorageTSID.IntN())
 	storage.SetTagFiltersCacheSize(cacheSizeIndexDBTagFilters.IntN())
+	if *finalDedupScheduleInterval < time.Hour {
+		logger.Fatalf("-storage.finalDedupScheduleCheckInterval cannot be smaller than 1 hour; got %s", *finalDedupScheduleInterval)
+	}
+	storage.SetFinalDedupScheduleInterval(*finalDedupScheduleInterval)
 	storage.SetMetricNamesStatsCacheSize(cacheSizeMetricNamesStats.IntN())
 	storage.SetMetricNameCacheSize(cacheSizeStorageMetricName.IntN())
 	storage.SetMetadataStorageSize(metadataStorageSize.IntN())
@@ -147,21 +150,21 @@ func Init(resetCacheIfNeeded func(mrs []storage.MetricRow)) {
 	if *idbPrefillStart > 23*time.Hour {
 		logger.Panicf("-storage.idbPrefillStart cannot exceed 23 hours; got %s", idbPrefillStart)
 	}
-	logger.Infof("opening storage at %q with -retentionPeriod=%s", *DataPath, retentionPeriod)
+	fs.RegisterPathFsMetrics(*storageDataPath)
+	logger.Infof("opening storage at %q with -retentionPeriod=%s", *storageDataPath, retentionPeriod)
 	startTime := time.Now()
-	WG = syncwg.WaitGroup{}
 	opts := storage.OpenOptions{
-		Retention:             retentionPeriod.Duration(),
-		FutureRetention:       futureRetention.Duration(),
-		MaxHourlySeries:       getMaxHourlySeries(),
-		MaxDailySeries:        getMaxDailySeries(),
-		DisablePerDayIndex:    *disablePerDayIndex,
-		TrackMetricNamesStats: *trackMetricNamesStats,
-		IDBPrefillStart:       *idbPrefillStart,
-		LogNewSeries:          *logNewSeries,
+		Retention:                   retentionPeriod.Duration(),
+		FutureRetention:             futureRetention.Duration(),
+		DenyQueriesOutsideRetention: *denyQueriesOutsideRetention,
+		MaxHourlySeries:             getMaxHourlySeries(),
+		MaxDailySeries:              getMaxDailySeries(),
+		DisablePerDayIndex:          *disablePerDayIndex,
+		TrackMetricNamesStats:       *trackMetricNamesStats,
+		IDBPrefillStart:             *idbPrefillStart,
+		LogNewSeries:                *logNewSeries,
 	}
-	strg := storage.MustOpenStorage(*DataPath, opts)
-	Storage = strg
+	strg := storage.MustOpenStorage(*storageDataPath, opts)
 	initStaleSnapshotsRemover(strg)
 
 	var m storage.Metrics
@@ -172,7 +175,7 @@ func Init(resetCacheIfNeeded func(mrs []storage.MetricRow)) {
 	rowsCount := tm.SmallRowsCount + tm.BigRowsCount
 	sizeBytes := tm.SmallSizeBytes + tm.BigSizeBytes
 	logger.Infof("successfully opened storage %q in %.3f seconds; partsCount: %d; blocksCount: %d; rowsCount: %d; sizeBytes: %d",
-		*DataPath, time.Since(startTime).Seconds(), partsCount, blocksCount, rowsCount, sizeBytes)
+		*storageDataPath, time.Since(startTime).Seconds(), partsCount, blocksCount, rowsCount, sizeBytes)
 
 	// register storage metrics
 	storageMetrics = metrics.NewSet()
@@ -180,6 +183,10 @@ func Init(resetCacheIfNeeded func(mrs []storage.MetricRow)) {
 		writeStorageMetrics(w, strg)
 	})
 	metrics.RegisterSet(storageMetrics)
+
+	WG = syncwg.WaitGroup{}
+	resetResponseCacheIfNeeded = resetCacheIfNeeded
+	Storage = strg
 }
 
 var storageMetrics *metrics.Set
@@ -324,7 +331,7 @@ func Stop() {
 	metrics.UnregisterSet(storageMetrics, true)
 	storageMetrics = nil
 
-	logger.Infof("gracefully closing the storage at %s", *DataPath)
+	logger.Infof("gracefully closing the storage at %s", *storageDataPath)
 	startTime := time.Now()
 	WG.WaitAndBlock()
 	stopStaleSnapshotsRemover()
@@ -351,6 +358,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 			startTime := time.Now()
 			if err := Storage.ForceMergePartitions(partitionNamePrefix); err != nil {
 				logger.Errorf("error in forced merge for partition_prefix=%q: %s", partitionNamePrefix, err)
+				return
 			}
 			logger.Infof("forced merge for partition_prefix=%q has been successfully finished in %.3f seconds", partitionNamePrefix, time.Since(startTime).Seconds())
 		}()
@@ -364,6 +372,7 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		Storage.DebugFlush()
 		return true
 	}
+
 	if path == "/internal/log_new_series" {
 		if !httpserver.CheckAuthFlag(w, r, logNewSeriesAuthKey) {
 			return true
@@ -528,15 +537,15 @@ func writeStorageMetrics(w io.Writer, strg *storage.Storage) {
 	tm := &m.TableMetrics
 	idbm := &m.TableMetrics.IndexDBMetrics
 
-	metrics.WriteGaugeUint64(w, fmt.Sprintf(`vm_free_disk_space_bytes{path=%q}`, *DataPath), fs.MustGetFreeSpace(*DataPath))
-	metrics.WriteGaugeUint64(w, fmt.Sprintf(`vm_free_disk_space_limit_bytes{path=%q}`, *DataPath), uint64(minFreeDiskSpaceBytes.N))
-	metrics.WriteGaugeUint64(w, fmt.Sprintf(`vm_total_disk_space_bytes{path=%q}`, *DataPath), fs.MustGetTotalSpace(*DataPath))
+	metrics.WriteGaugeUint64(w, fmt.Sprintf(`vm_free_disk_space_bytes{path=%q}`, *storageDataPath), fs.MustGetFreeSpace(*storageDataPath))
+	metrics.WriteGaugeUint64(w, fmt.Sprintf(`vm_free_disk_space_limit_bytes{path=%q}`, *storageDataPath), uint64(minFreeDiskSpaceBytes.N))
+	metrics.WriteGaugeUint64(w, fmt.Sprintf(`vm_total_disk_space_bytes{path=%q}`, *storageDataPath), fs.MustGetTotalSpace(*storageDataPath))
 
 	isReadOnly := 0
 	if strg.IsReadOnly() {
 		isReadOnly = 1
 	}
-	metrics.WriteGaugeUint64(w, fmt.Sprintf(`vm_storage_is_read_only{path=%q}`, *DataPath), uint64(isReadOnly))
+	metrics.WriteGaugeUint64(w, fmt.Sprintf(`vm_storage_is_read_only{path=%q}`, *storageDataPath), uint64(isReadOnly))
 
 	metrics.WriteGaugeUint64(w, `vm_active_merges{type="storage/inmemory"}`, tm.ActiveInmemoryMerges)
 	metrics.WriteGaugeUint64(w, `vm_active_merges{type="storage/small"}`, tm.ActiveSmallMerges)

app/vmui/Dockerfile-web

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

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

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

app/vmui/packages/vmui/package.json

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

app/vmui/packages/vmui/src/api/types.ts

@@ -3,6 +3,7 @@ export interface MetricBase {
   metric: {
     [key: string]: string;
   };
+  nullTimestamps?: number[];
 }
 
 export interface MetricResult extends MetricBase {

app/vmui/packages/vmui/src/components/Chart/ChartTooltip/ChartTooltip.tsx

@@ -16,6 +16,7 @@ export interface ChartTooltipProps {
   point: { top: number, left: number };
   unit?: string;
   statsFormatted?: SeriesItemStatsFormatted;
+  description?: ReactNode;
   isSticky?: boolean;
   info?: ReactNode;
   marker?: string;
@@ -34,6 +35,7 @@ const ChartTooltip: FC<ChartTooltipProps> = ({
   unit = "",
   info,
   statsFormatted,
+  description,
   isSticky,
   marker,
   duplicateCount = 0,
@@ -173,6 +175,7 @@ const ChartTooltip: FC<ChartTooltipProps> = ({
           ))}
         </table>
       )}
+      {description && <p className="vm-chart-tooltip__description">{description}</p>}
       {info && <p className="vm-chart-tooltip__info">{info}</p>}
     </div>
   ), u.root);

app/vmui/packages/vmui/src/components/Chart/ChartTooltip/style.scss

@@ -143,4 +143,10 @@ $chart-tooltip-y: -1 * ($padding-global + $chart-tooltip-half-icon);
     word-break: break-all;
     white-space: pre-wrap;
   }
+
+  &__description {
+    word-break: break-word;
+    white-space: pre-wrap;
+    opacity: 0.85;
+  }
 }

app/vmui/packages/vmui/src/components/Configurators/QueryEditor/warningText.ts

@@ -1,7 +1,7 @@
-export const seriesFetchedWarning = `No match! 
+export const seriesFetchedWarning = `No match!
 This query hasn't selected any time series from database.
 Either the requested metrics are missing in the database,
 or there is a typo in series selector.`;
 
 export const partialWarning = `The shown results are marked as PARTIAL.
-The result is marked as partial if one or more vmstorage nodes failed to respond to the query.`;
+The result is marked as partial if one or more storage nodes failed to respond to the query.`;

app/vmui/packages/vmui/src/components/ExploreAlerts/RulesHeader/index.tsx

@@ -71,7 +71,7 @@ const RulesHeader = ({
           <TextField
             label="Search"
             value={search}
-            placeholder="Filter by rule, name or labels"
+            placeholder="Filter by group or rule name"
             startIcon={<SearchIcon />}
             onChange={onChangeSearch}
           />

app/vmui/packages/vmui/src/components/Main/Tabs/TabItem.tsx

@@ -1,6 +1,5 @@
 import { Component, FC, Ref } from "preact/compat";
 import classNames from "classnames";
-import { getCssVariable } from "../../../utils/theme";
 import { TabItemType } from "./Tabs";
 import TabItemWrapper from "./TabItemWrapper";
 import "./style.scss";
@@ -8,7 +7,6 @@ import "./style.scss";
 interface TabItemProps {
   activeItem: string
   item: TabItemType
-  color?: string
   onChange?: (value: string) => void
   activeNavRef: Ref<Component>
   isNavLink?: boolean
@@ -17,7 +15,6 @@ interface TabItemProps {
 const TabItem: FC<TabItemProps> = ({
   activeItem,
   item,
-  color = getCssVariable("color-primary"),
   activeNavRef,
   onChange,
   isNavLink
@@ -35,7 +32,6 @@ const TabItem: FC<TabItemProps> = ({
       })}
       isNavLink={isNavLink}
       to={item.value}
-      style={{ color: color }}
       onClick={createHandlerClickTab(item.value)}
       ref={activeItem === item.value ? activeNavRef : undefined}
     >

app/vmui/packages/vmui/src/components/Main/Tabs/TabItemWrapper.tsx

@@ -6,7 +6,6 @@ interface TabItemWrapperProps {
   to: string
   isNavLink?: boolean
   className: string
-  style: { color: string }
   children: ReactNode
   onClick: () => void
 }

app/vmui/packages/vmui/src/components/Main/Tabs/Tabs.tsx

@@ -1,6 +1,5 @@
 import { Component, FC, useRef, useState } from "preact/compat";
 import { ReactNode, useEffect } from "react";
-import { getCssVariable } from "../../../utils/theme";
 import TabItem from "./TabItem";
 import "./style.scss";
 import useWindowSize from "../../../hooks/useWindowSize";
@@ -15,7 +14,6 @@ export interface TabItemType {
 interface TabsProps {
   activeItem: string
   items: TabItemType[]
-  color?: string
   onChange?: (value: string) => void
   indicatorPlacement?: "bottom" | "top"
   isNavLink?: boolean
@@ -24,7 +22,6 @@ interface TabsProps {
 const Tabs: FC<TabsProps> = ({
   activeItem,
   items,
-  color = getCssVariable("color-primary"),
   onChange,
   indicatorPlacement = "bottom",
   isNavLink,
@@ -48,14 +45,13 @@ const Tabs: FC<TabsProps> = ({
         activeItem={activeItem}
         item={item}
         onChange={onChange}
-        color={color}
         activeNavRef={activeNavRef}
         isNavLink={isNavLink}
       />
     ))}
     <div
       className="vm-tabs__indicator"
-      style={{ ...indicatorPosition, borderColor: color }}
+      style={{ ...indicatorPosition }}
     />
   </div>;
 };

app/vmui/packages/vmui/src/components/Main/Tabs/style.scss

@@ -14,7 +14,7 @@
     align-items: center;
     justify-content: center;
     padding: $padding-global $padding-small;
-    color: inherit;
+    color: $color-primary;
     text-decoration: none;
     text-transform: capitalize;
     font-size: inherit;
@@ -46,5 +46,6 @@
     position: absolute;
     border-bottom: 2px solid;
     transition: width 200ms ease, left 300ms cubic-bezier(0.280, 0.840, 0.420, 1);
+    border-color: $color-primary;
   }
 }

app/vmui/packages/vmui/src/hooks/uplot/useLineTooltip.ts

@@ -4,7 +4,7 @@ import { ChartTooltipProps } from "../../components/Chart/ChartTooltip/ChartTool
 import { SeriesItem } from "../../types";
 import dayjs from "dayjs";
 import { DATE_FULL_TIMEZONE_FORMAT } from "../../constants/date";
-import { formatPrettyNumber, getMetricName } from "../../utils/uplot";
+import { getMetricName } from "../../utils/uplot";
 import { MetricResult } from "../../api/types";
 import useEventListener from "../useEventListener";
 
@@ -15,19 +15,65 @@ interface LineTooltipHook {
   unit?: string;
 }
 
+// Pixel proximity for detecting hover over null-timestamp X markers drawn at chart bottom.
+const NULL_HOVER_PROX = 8;
+// Half the visual marker height in CSS px (BASE_POINT_SIZE * 1.4 / 2 from scatter.ts).
+// scatter.ts lifts the marker center by this amount above yMin so the icon sits inside
+// the plot area; the hover y-anchor must match that offset.
+const NULL_MARKER_HALF_CSS = 2.8;
+
+interface NullHover {
+  seriesIdx: number;
+  timestamp: number;
+}
+
+const findNullHover = (u: uPlot): NullHover | null => {
+  const cursorLeft = u.cursor.left ?? -1;
+  const cursorTop = u.cursor.top ?? -1;
+  if (cursorLeft < 0 || cursorTop < 0) return null;
+
+  const scaleY = u.scales["1"];
+  if (!scaleY || scaleY.min == null) return null;
+  const yPos = u.valToPos(scaleY.min, "1") - NULL_MARKER_HALF_CSS;
+  if (Math.abs(cursorTop - yPos) > NULL_HOVER_PROX) return null;
+
+  let best: { seriesIdx: number; timestamp: number; dist: number } | null = null;
+  for (let s = 1; s < u.series.length; s++) {
+    const seriesItem = u.series[s] as SeriesItem;
+    if (!seriesItem.show) continue;
+    const nullTs = seriesItem.nullTimestamps;
+    if (!nullTs || !nullTs.length) continue;
+
+    for (let i = 0; i < nullTs.length; i++) {
+      const t = nullTs[i];
+      const xPos = u.valToPos(t, "x");
+      const dist = Math.abs(cursorLeft - xPos);
+      if (dist < NULL_HOVER_PROX && (best === null || dist < best.dist)) {
+        best = { seriesIdx: s, timestamp: t, dist };
+      }
+    }
+  }
+  return best ? { seriesIdx: best.seriesIdx, timestamp: best.timestamp } : null;
+};
+
+const NULL_DESCRIPTION = "\"null\" can be a staleness marker or an actual NaN/null value produced by exporter.";
+
 const useLineTooltip = ({ u, metrics, series, unit }: LineTooltipHook) => {
   const [showTooltip, setShowTooltip] = useState(false);
   const [tooltipIdx, setTooltipIdx] = useState({ seriesIdx: -1, dataIdx: -1 });
+  const [nullTooltip, setNullTooltip] = useState<NullHover | null>(null);
   const [stickyTooltips, setStickyToolTips] = useState<ChartTooltipProps[]>([]);
 
   const resetTooltips = () => {
     setStickyToolTips([]);
     setTooltipIdx({ seriesIdx: -1, dataIdx: -1 });
+    setNullTooltip(null);
   };
 
   const setCursor = (u: uPlot) => {
     const dataIdx = u.cursor.idx ?? -1;
     setTooltipIdx(prev => ({ ...prev, dataIdx }));
+    setNullTooltip(findNullHover(u));
   };
 
   const seriesFocus = (u: uPlot, sidx: (number | null)) => {
@@ -35,7 +81,36 @@ const useLineTooltip = ({ u, metrics, series, unit }: LineTooltipHook) => {
     setTooltipIdx(prev => ({ ...prev, seriesIdx }));
   };
 
+  const getNullTooltipProps = (hit: NullHover): ChartTooltipProps => {
+    const { seriesIdx, timestamp } = hit;
+    const metricItem = metrics[seriesIdx - 1];
+    const seriesItem = series[seriesIdx] as SeriesItem;
+
+    const groups = new Set(metrics.map(m => m.group));
+    const group = metricItem?.group || 0;
+
+    const yMin = u?.scales?.[1]?.min ?? 0;
+    const point = {
+      top: u ? u.valToPos(yMin, seriesItem?.scale || "1") - NULL_MARKER_HALF_CSS : 0,
+      left: u ? u.valToPos(timestamp, "x") : 0,
+    };
+
+    return {
+      u,
+      id: `null_${seriesIdx}_${timestamp}`,
+      title: groups.size > 1 ? `Query ${group}` : "",
+      dates: [dayjs(timestamp * 1000).tz().format(DATE_FULL_TIMEZONE_FORMAT)],
+      value: "null",
+      info: getMetricName(metricItem, seriesItem),
+      description: NULL_DESCRIPTION,
+      marker: `${seriesItem?.stroke}`,
+      point,
+    };
+  };
+
   const getTooltipProps = useCallback((): ChartTooltipProps => {
+    if (nullTooltip) return getNullTooltipProps(nullTooltip);
+
     const { seriesIdx, dataIdx } = tooltipIdx;
     const metricItem = metrics[seriesIdx - 1];
     const seriesItem = series[seriesIdx] as SeriesItem;
@@ -44,8 +119,6 @@ const useLineTooltip = ({ u, metrics, series, unit }: LineTooltipHook) => {
     const group = metricItem?.group || 0;
 
     const value = u?.data?.[seriesIdx]?.[dataIdx] || 0;
-    const min = u?.scales?.[1]?.min || 0;
-    const max = u?.scales?.[1]?.max || 1;
     const date = u?.data?.[0]?.[dataIdx] || 0;
 
     let duplicateCount = 1;
@@ -80,13 +153,13 @@ const useLineTooltip = ({ u, metrics, series, unit }: LineTooltipHook) => {
       id: `${seriesIdx}_${dataIdx}`,
       title: groups.size > 1 ? `Query ${group}` : "",
       dates: [date ? dayjs(date * 1000).tz().format(DATE_FULL_TIMEZONE_FORMAT) : "-"],
-      value: formatPrettyNumber(value, min, max),
+      value: value.toLocaleString("en-US", { maximumFractionDigits: 20 }),
       info: getMetricName(metricItem, seriesItem),
       statsFormatted: seriesItem?.statsFormatted,
       marker: `${seriesItem?.stroke}`,
       duplicateCount,
     };
-  }, [u, tooltipIdx, metrics, series, unit]);
+  }, [u, tooltipIdx, metrics, series, unit, nullTooltip]);
 
   const handleClick = useCallback(() => {
     if (!showTooltip) return;
@@ -101,8 +174,9 @@ const useLineTooltip = ({ u, metrics, series, unit }: LineTooltipHook) => {
   };
 
   useEffect(() => {
-    setShowTooltip(tooltipIdx.dataIdx !== -1 && tooltipIdx.seriesIdx !== -1);
-  }, [tooltipIdx]);
+    const normalHit = tooltipIdx.dataIdx !== -1 && tooltipIdx.seriesIdx !== -1;
+    setShowTooltip(normalHit || nullTooltip !== null);
+  }, [tooltipIdx, nullTooltip]);
 
   useEventListener("click", handleClick);
 

app/vmui/packages/vmui/src/pages/CustomPanel/utils.test.ts

@@ -20,7 +20,7 @@ describe("convertMetricsDataToCSV", () => {
       },
     ];
     const result = convertMetricsDataToCSV(data);
-    expect(result).toBe("header1,header2\n123,value2");
+    expect(result).toBe("header1,header2,__timestamp__,__value__\n123,value2,1623945600,123");
   });
 
   it("should return a valid CSV string for multiple metric entries with values", () => {
@@ -43,7 +43,7 @@ describe("convertMetricsDataToCSV", () => {
       },
     ];
     const result = convertMetricsDataToCSV(data);
-    expect(result).toBe("header1,header2\n123,value2\n456,value4");
+    expect(result).toBe("header1,header2,__timestamp__,__value__\n123,value2,1623945600,123\n456,value4,1623949200,456");
   });
 
   it("should handle metric entries with multiple values field", () => {
@@ -58,7 +58,7 @@ describe("convertMetricsDataToCSV", () => {
       },
     ];
     const result = convertMetricsDataToCSV(data);
-    expect(result).toBe("header1,header2\n123-456,values");
+    expect(result).toBe("header1,header2,__timestamp__,__value__\n123-456,values,-,-");
   });
 
   it("should handle a combination of metric entries with value and values", () => {
@@ -81,6 +81,19 @@ describe("convertMetricsDataToCSV", () => {
       },
     ];
     const result = convertMetricsDataToCSV(data);
-    expect(result).toBe("header1,header2\n123,first\n456-789,second");
+    expect(result).toBe("header1,header2,__timestamp__,__value__\n123,first,1623945600,123\n456-789,second,-,-");
   });
+
+  it("should return value and timestamp if metric field is empty", () => {
+    const data: InstantMetricResult[] = [
+      {
+        value: [1623945600, "123"],
+        group: 0,
+        metric: {}
+      },
+    ];
+    const result = convertMetricsDataToCSV(data);
+    expect(result).toBe("__timestamp__,__value__\n1623945600,123");
+  });
+
 });

app/vmui/packages/vmui/src/pages/CustomPanel/utils.ts

@@ -3,16 +3,22 @@ import { getColumns, MetricCategory } from "../../hooks/useSortedCategories";
 import { formatValueToCSV } from "../../utils/csv";
 
 const getHeaders = (data: InstantMetricResult[]): string => {
-  return getColumns(data).map(({ key }) => key).join(",");
+  const metricHeaders = getColumns(data).map(({ key }) => key);
+  return [...metricHeaders, "__timestamp__", "__value__"].join(",");
 };
 
 const getRows = (data: InstantMetricResult[], headers: MetricCategory[]) => {
-  return data?.map(d => headers.map(c => formatValueToCSV(d.metric[c.key] || "-")).join(","));
+  return data?.map(d => {
+    const metricPart = headers.map(c => formatValueToCSV(d.metric[c.key] || "-"));
+    const timestamp = d.value ? formatValueToCSV(String(d.value[0])) : "-";
+    const value = d.value ? formatValueToCSV(d.value[1]) : "-";
+    return [...metricPart, timestamp, value].join(",");
+  });
 };
 
 export const convertMetricsDataToCSV = (data: InstantMetricResult[]): string => {
+  if (!data.length) return "";
   const headers = getHeaders(data);
-  if (!headers.length) return "";
   const rows = getRows(data, getColumns(data));
   return [headers, ...rows].join("\n");
 };

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

@@ -149,15 +149,21 @@ export const useFetchExport = ({ hideQuery, showAllSeries }: FetchQueryParams):
             const pointsToTake = shouldDownsample ? maxPointsPerSeries : totalPoints;
             const step = shouldDownsample ? totalPoints / maxPointsPerSeries : 1;
 
-            const values: [number, number][] = Array.from({ length: pointsToTake }, (_, i) => {
+            const values: [number, number][] = new Array(pointsToTake);
+            const nullTimestamps: number[] = [];
+            for (let i = 0; i < pointsToTake; i++) {
               const idx = shouldDownsample ? Math.floor(i * step) : i;
-              return [rawTimestamps[idx] / 1000, rawValues[idx]];
-            });
+              const ts = rawTimestamps[idx] / 1000;
+              const raw = rawValues[idx];
+              if (raw === null) nullTimestamps.push(ts);
+              values[i] = [ts, raw as number];
+            }
 
             tempData.push({
               group: counter,
               metric: jsonLine.metric,
               values,
+              nullTimestamps,
             } as MetricBase);
           }
 

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

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

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

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

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

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

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

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