build(deps): bump github/codeql-action from 4.35.3 to 4.36.2

Bumps [github/codeql-action](https://github.com/github/codeql-action) from 4.35.3 to 4.36.2.
- [Release notes](https://github.com/github/codeql-action/releases)
- [Changelog](https://github.com/github/codeql-action/blob/main/CHANGELOG.md)
- [Commits](e46ed2cbd0...8aad20d150)

---
updated-dependencies:
- dependency-name: github/codeql-action
  dependency-version: 4.36.2
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

.github/workflows/build.yml

@@ -33,7 +33,8 @@ jobs:
     name: ${{ matrix.os }}-${{ matrix.arch }}
     permissions:
       contents: read
-    runs-on: ubuntu-latest
+    # Runs on dedicated runner with extra resources to increase build speed.
+    runs-on: 'vm-runner'
     strategy:
       fail-fast: false
       matrix:
@@ -65,6 +66,8 @@ jobs:
     steps:
       - name: Code checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Setup Go
         id: go

.github/workflows/changelog-linter.yml

@@ -17,6 +17,7 @@ jobs:
         with:
           # needed for proper diff
           fetch-depth: 0
+          persist-credentials: false
 
       - name: 'Validate that changelog changes are under ## tip'
         run: |

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

@@ -15,6 +15,7 @@ jobs:
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           fetch-depth: 0  # we need full history for commit verification
+          persist-credentials: false
 
       - name: Check commit signatures
         run: |

.github/workflows/check-licenses.yml

@@ -18,6 +18,8 @@ jobs:
     steps:
       - name: Code checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Setup Go
         id: go

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

@@ -32,6 +32,8 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Set up Go
         id: go
@@ -52,14 +54,14 @@ jobs:
           restore-keys: go-artifacts-${{ runner.os }}-codeql-analyze-${{ steps.go.outputs.go-version }}-
 
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@e46ed2cbd01164d986452f91f178727624ae40d7  # v4.35.3
+        uses: github/codeql-action/init@8aad20d150bbac5944a9f9d289da16a4b0d87c1e  # v4.36.2
         with:
           languages: go
 
       - name: Autobuild
-        uses: github/codeql-action/autobuild@e46ed2cbd01164d986452f91f178727624ae40d7  # v4.35.3
+        uses: github/codeql-action/autobuild@8aad20d150bbac5944a9f9d289da16a4b0d87c1e  # v4.36.2
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@e46ed2cbd01164d986452f91f178727624ae40d7  # v4.35.3
+        uses: github/codeql-action/analyze@8aad20d150bbac5944a9f9d289da16a4b0d87c1e  # v4.36.2
         with:
           category: 'language:go'

.github/workflows/docs.yaml

@@ -21,6 +21,7 @@ jobs:
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           path: __vm
+          persist-credentials: false
 
       - name: Checkout private code
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
@@ -28,6 +29,7 @@ jobs:
           repository: VictoriaMetrics/vmdocs
           token: ${{ secrets.VM_BOT_GH_TOKEN }}
           path: __vm-docs
+          persist-credentials: true
 
       - name: Import GPG key
         uses: crazy-max/ghaction-import-gpg@2dc316deee8e90f13e1a351ab510b4d5bc0c82cd  # v7.0.0

.github/workflows/test.yml

@@ -30,10 +30,13 @@ jobs:
     name: lint
     permissions:
       contents: read
-    runs-on: ubuntu-latest
+    # Runs on dedicated runner with extra resources since golangci-lint requires extra memory
+    runs-on: 'vm-runner'
     steps:
       - name: Code checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Setup Go
         id: go
@@ -64,7 +67,8 @@ jobs:
     name: unit
     permissions:
       contents: read
-    runs-on: ubuntu-latest
+    # Runs on dedicated runner with extra resources to increase tests speed.
+    runs-on: 'vm-runner'
 
     strategy:
       matrix:
@@ -76,6 +80,8 @@ jobs:
     steps:
       - name: Code checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Setup Go
         id: go
@@ -95,11 +101,14 @@ jobs:
     name: apptest
     permissions:
       contents: read
+    # Runs on dedicated runner to isolate app tests from other tests.
     runs-on: apptest
 
     steps:
       - name: Code checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Setup Go
         id: go

.github/workflows/vmui.yml

@@ -33,6 +33,8 @@ jobs:
     steps:
       - name: Code checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Cache node_modules
         id: cache

.golangci.yml

@@ -1,29 +1,25 @@
 version: "2"
 linters:
+  enable:
+    - errorlint
   settings:
     errcheck:
       exclude-functions:
-        - fmt.Fprintf
-        - fmt.Fprint
         - (net/http.ResponseWriter).Write
+    errorlint:
+      errorf: true
+      # Do not enable `comparison` and `asserts`: they produce false positives,
+      # since many call sites intentionally compare sentinel errors directly (e.g. err == io.EOF)
+      # when the producer is documented to return them unwrapped. See https://github.com/VictoriaMetrics/VictoriaLogs/pull/1490
+      comparison: false
+      asserts: false
   exclusions:
     generated: lax
     presets:
-      - common-false-positives
-      - legacy
       - std-error-handling
     rules:
       - linters:
           - staticcheck
         text: 'SA(4003|1019|5011):'
     paths:
-      - third_party$
-      - builtin$
-      - examples$
-formatters:
-  exclusions:
-    generated: lax
-    paths:
-      - third_party$
-      - builtin$
-      - examples$
+      - ^app/vmui/

Makefile

@@ -17,7 +17,7 @@ EXTRA_GO_BUILD_TAGS ?=
 GO_BUILDINFO = -X '$(PKG_PREFIX)/lib/buildinfo.Version=$(APP_NAME)-$(DATEINFO_TAG)-$(BUILDINFO_TAG)'
 TAR_OWNERSHIP ?= --owner=1000 --group=1000
 
-GOLANGCI_LINT_VERSION := 2.9.0
+GOLANGCI_LINT_VERSION := 2.12.2
 
 .PHONY: $(MAKECMDGOALS)
 
@@ -527,7 +527,7 @@ golangci-lint: install-golangci-lint
 	golangci-lint run --build-tags 'synctest'
 
 install-golangci-lint:
-	which golangci-lint && (golangci-lint --version | grep -q $(GOLANGCI_LINT_VERSION)) || curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v$(GOLANGCI_LINT_VERSION)
+	which golangci-lint && (golangci-lint --version | grep -q $(GOLANGCI_LINT_VERSION)) || curl -sSfL https://golangci-lint.run/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v$(GOLANGCI_LINT_VERSION)
 
 remove-golangci-lint:
 	rm -rf `which golangci-lint`

app/victoria-metrics/test/prom_writer.go

@@ -10,7 +10,7 @@ import (
 func Compress(wr WriteRequest) []byte {
 	data, err := wr.Marshal()
 	if err != nil {
-		panic(fmt.Errorf("BUG: cannot compress WriteRequest: %s", err))
+		panic(fmt.Errorf("BUG: cannot compress WriteRequest: %w", err))
 	}
 	return snappy.Encode(nil, data)
 }

app/vmagent/remotewrite/client.go

@@ -187,7 +187,7 @@ func newHTTPClient(argIdx int, remoteWriteURL, sanitizedURL string, fq *persiste
 	return c
 }
 
-func (c *client) init(argIdx, concurrency int, sanitizedURL string) {
+func (c *client) init(argIdx int, sanitizedURL string) {
 	limitReached := metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_rate_limit_reached_total{url=%q}`, c.sanitizedURL))
 	if bytesPerSec := rateLimit.GetOptionalArg(argIdx); bytesPerSec > 0 {
 		logger.Infof("applying %d bytes per second rate limit for -remoteWrite.url=%q", bytesPerSec, sanitizedURL)
@@ -204,11 +204,20 @@ func (c *client) init(argIdx, concurrency int, sanitizedURL string) {
 	c.packetsDropped = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_packets_dropped_total{url=%q}`, c.sanitizedURL))
 	c.retriesCount = metrics.GetOrCreateCounter(fmt.Sprintf(`vmagent_remotewrite_retries_count_total{url=%q}`, c.sanitizedURL))
 	c.sendDuration = metrics.GetOrCreateFloatCounter(fmt.Sprintf(`vmagent_remotewrite_send_duration_seconds_total{url=%q}`, c.sanitizedURL))
-	metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_queues{url=%q}`, c.sanitizedURL), func() float64 {
-		return float64(concurrency)
-	})
-	for range concurrency {
-		c.wg.Go(c.runWorker)
+	workers := queues.GetOptionalArg(argIdx)
+	if workers <= 0 {
+		workers = 1
+	}
+	inmemoryWorkers := inmemoryQueues.GetOptionalArg(argIdx)
+	for range inmemoryWorkers {
+		c.wg.Go(func() {
+			c.runWorker(c.fq.MustReadInMemoryBlockBlocking)
+		})
+	}
+	for range workers {
+		c.wg.Go(func() {
+			c.runWorker(c.fq.MustReadBlock)
+		})
 	}
 	logger.Infof("initialized client for -remoteWrite.url=%q", c.sanitizedURL)
 }
@@ -302,12 +311,12 @@ func getAWSAPIConfig(argIdx int) (*awsapi.Config, error) {
 	return cfg, nil
 }
 
-func (c *client) runWorker() {
+func (c *client) runWorker(readBlock func(dst []byte) ([]byte, bool)) {
 	var ok bool
 	var block []byte
 	ch := make(chan bool, 1)
 	for {
-		block, ok = c.fq.MustReadBlock(block[:0])
+		block, ok = readBlock(block[:0])
 		if !ok {
 			return
 		}

app/vmagent/remotewrite/pendingseries.go

@@ -209,13 +209,12 @@ func (wr *writeRequest) tryPushMetadata(mms []prompb.MetricMetadata) bool {
 func (wr *writeRequest) copyMetadata(dst, src *prompb.MetricMetadata) {
 	// Direct copy for non-string fields, which are safe by value.
 	dst.Type = src.Type
-	dst.Unit = src.Unit
 
 	dst.AccountID = src.AccountID
 	dst.ProjectID = src.ProjectID
 
 	// Pre-allocate memory for all string fields.
-	neededBufLen := len(src.MetricFamilyName) + len(src.Help)
+	neededBufLen := len(src.MetricFamilyName) + len(src.Help) + len(src.Unit)
 	bufLen := len(wr.metadatabuf)
 	wr.metadatabuf = slicesutil.SetLength(wr.metadatabuf, bufLen+neededBufLen)
 	buf := wr.metadatabuf[:bufLen]
@@ -230,6 +229,11 @@ func (wr *writeRequest) copyMetadata(dst, src *prompb.MetricMetadata) {
 	buf = append(buf, src.Help...)
 	dst.Help = bytesutil.ToUnsafeString(buf[bufLen:])
 
+	// Copy Unit
+	bufLen = len(buf)
+	buf = append(buf, src.Unit...)
+	dst.Unit = bytesutil.ToUnsafeString(buf[bufLen:])
+
 	wr.metadatabuf = buf
 }
 

app/vmagent/remotewrite/remotewrite.go

@@ -66,6 +66,9 @@ var (
 	queues = flagutil.NewArrayInt("remoteWrite.queues", cgroup.AvailableCPUs()*2, "The number of concurrent queues to each -remoteWrite.url. Set more queues if default number of queues "+
 		"isn't enough for sending high volume of collected data to remote storage. "+
 		"Default value depends on the number of available CPU cores. It should work fine in most cases since it minimizes resource usage")
+	inmemoryQueues = flagutil.NewArrayInt("remoteWrite.inmemoryQueues", 0, "The number of additional workers per each -remoteWrite.url, which send only recently ingested data from the in-memory queue, "+
+		"while the file-based queue at -remoteWrite.tmpDataPath is drained by workers configured via -remoteWrite.queues. "+
+		"This reduces delivery lag for fresh samples when the file-based queue contains a backlog accumulated during remote storage outages.")
 	showRemoteWriteURL = flag.Bool("remoteWrite.showURL", false, "Whether to show -remoteWrite.url in the exported metrics. "+
 		"It is hidden by default, since it can contain sensitive info such as auth key")
 	maxPendingBytesPerURL = flagutil.NewArrayBytes("remoteWrite.maxDiskUsagePerURL", 0, "The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath "+
@@ -906,7 +909,8 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
 	}
 
 	isPQDisabled := disableOnDiskQueue.GetOptionalArg(argIdx)
-	queuesSize := queues.GetOptionalArg(argIdx)
+	inmemoryQueueSize := inmemoryQueues.GetOptionalArg(argIdx)
+	queuesSize := queues.GetOptionalArg(argIdx) + inmemoryQueueSize
 	if queuesSize > maxQueues {
 		queuesSize = maxQueues
 	} else if queuesSize <= 0 {
@@ -923,7 +927,13 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
 	if maxInmemoryBlocks < 2 {
 		maxInmemoryBlocks = 2
 	}
-	fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytes, isPQDisabled)
+	fqOpts := persistentqueue.OpenFastQueueOpts{
+		MaxInmemoryBlocks:      maxInmemoryBlocks,
+		MaxPendingBytes:        maxPendingBytes,
+		IsPQDisabled:           isPQDisabled,
+		PrioritizeInmemoryData: inmemoryQueueSize > 0,
+	}
+	fq := persistentqueue.MustOpenFastQueueWithOpts(queuePath, sanitizedURL, fqOpts)
 	_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_data_bytes{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
 		return float64(fq.GetPendingBytes())
 	})
@@ -936,6 +946,9 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
 		}
 		return 0
 	})
+	metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_queues{url=%q}`, sanitizedURL), func() float64 {
+		return float64(queuesSize)
+	})
 
 	var c *client
 	switch remoteWriteURL.Scheme {
@@ -944,7 +957,7 @@ func newRemoteWriteCtx(argIdx int, remoteWriteURL *url.URL, sanitizedURL string)
 	default:
 		logger.Fatalf("unsupported scheme: %s for remoteWriteURL: %s, want `http`, `https`", remoteWriteURL.Scheme, sanitizedURL)
 	}
-	c.init(argIdx, queuesSize, sanitizedURL)
+	c.init(argIdx, sanitizedURL)
 
 	// Initialize pss
 	sf := significantFigures.GetOptionalArg(argIdx)

app/vmalert-tool/unittest/input.go

@@ -61,15 +61,15 @@ func parseInputSeries(input []series, interval *promutil.Duration, startStamp ti
 	for _, data := range input {
 		expr, err := metricsql.Parse(data.Series)
 		if err != nil {
-			return res, fmt.Errorf("failed to parse series %s: %v", data.Series, err)
+			return res, fmt.Errorf("failed to parse series %s: %w", data.Series, err)
 		}
 		promvals, err := parseInputValue(data.Values, true)
 		if err != nil {
-			return res, fmt.Errorf("failed to parse input series value %s: %v", data.Values, err)
+			return res, fmt.Errorf("failed to parse input series value %s: %w", data.Values, err)
 		}
 		metricExpr, ok := expr.(*metricsql.MetricExpr)
 		if !ok || len(metricExpr.LabelFilterss) != 1 {
-			return res, fmt.Errorf("got invalid input series %s: %v", data.Series, err)
+			return res, fmt.Errorf("got invalid input series %s: %w", data.Series, err)
 		}
 		samples := make([]testutil.Sample, 0, len(promvals))
 		ts := startStamp

app/vmalert-tool/unittest/recording.go

@@ -53,13 +53,13 @@ Outer:
 			if s.Labels != "" {
 				metricsqlExpr, err := metricsql.Parse(s.Labels)
 				if err != nil {
-					checkErrs = append(checkErrs, fmt.Errorf("\n    expr: %q, time: %s, err: %v", mt.Expr,
+					checkErrs = append(checkErrs, fmt.Errorf("\n    expr: %q, time: %s, err: %w", mt.Expr,
 						mt.EvalTime.Duration().String(), fmt.Errorf("failed to parse labels %q: %w", s.Labels, err)))
 					continue Outer
 				}
 				metricsqlMetricExpr, ok := metricsqlExpr.(*metricsql.MetricExpr)
 				if !ok || len(metricsqlMetricExpr.LabelFilterss) > 1 {
-					checkErrs = append(checkErrs, fmt.Errorf("\n    expr: %q, time: %s, err: %v", mt.Expr,
+					checkErrs = append(checkErrs, fmt.Errorf("\n    expr: %q, time: %s, err: %w", mt.Expr,
 						mt.EvalTime.Duration().String(), fmt.Errorf("got invalid exp_samples: %q", s.Labels)))
 					continue Outer
 				}

app/vmalert-tool/unittest/unittest.go

@@ -329,11 +329,11 @@ func (tg *testGroup) test(evalInterval time.Duration, groupOrderMap map[string]i
 
 	q, err := datasource.Init(nil)
 	if err != nil {
-		return []error{fmt.Errorf("failed to init datasource: %v", err)}
+		return []error{fmt.Errorf("failed to init datasource: %w", err)}
 	}
 	rw, err := remotewrite.NewDebugClient()
 	if err != nil {
-		return []error{fmt.Errorf("failed to init wr: %v", err)}
+		return []error{fmt.Errorf("failed to init wr: %w", err)}
 	}
 
 	alertEvalTimesMap := map[time.Duration]struct{}{}

app/vmalert/config/config.go

@@ -173,9 +173,9 @@ func (r *Rule) String() string {
 	if r.Alert != "" {
 		ruleType = "alerting"
 	}
-	b := strings.Builder{}
-	b.WriteString(fmt.Sprintf("%s rule %q", ruleType, r.Name()))
-	b.WriteString(fmt.Sprintf("; expr: %q", r.Expr))
+	var b strings.Builder
+	fmt.Fprintf(&b, "%s rule %q", ruleType, r.Name())
+	fmt.Fprintf(&b, "; expr: %q", r.Expr)
 
 	kv := sortMap(r.Labels)
 	for i := range kv {

app/vmalert/datasource/client_prom.go

@@ -89,7 +89,7 @@ func (pi *promInstant) Unmarshal(b []byte) error {
 		labels.Visit(func(key []byte, v *fastjson.Value) {
 			lv, errLocal := v.StringBytes()
 			if errLocal != nil {
-				err = fmt.Errorf("error when parsing label value %q: %s", v, errLocal)
+				err = fmt.Errorf("error when parsing label value %q: %w", v, errLocal)
 				return
 			}
 			r.Labels = append(r.Labels, prompb.Label{
@@ -112,7 +112,7 @@ func (pi *promInstant) Unmarshal(b []byte) error {
 		r.Timestamps = []int64{sample[0].GetInt64()}
 		val, err := sample[1].StringBytes()
 		if err != nil {
-			return fmt.Errorf("error when parsing `value` object %q: %s", sample[1], err)
+			return fmt.Errorf("error when parsing `value` object %q: %w", sample[1], err)
 		}
 		f, err := strconv.ParseFloat(bytesutil.ToUnsafeString(val), 64)
 		if err != nil {

app/vmalert/main.go

@@ -315,6 +315,11 @@ func configReload(ctx context.Context, m *manager, groupsCfg []config.Group, sig
 
 	parseFn := config.Parse
 	for {
+		select {
+		case <-ctx.Done():
+			return
+		default:
+		}
 		select {
 		case <-ctx.Done():
 			return

app/vmalert/rule/alerting.go

@@ -601,7 +601,7 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
 func (ar *AlertingRule) expandLabelTemplates(m datasource.Metric, qFn templates.QueryFn) (*labelSet, error) {
 	ls, err := ar.toLabels(m, qFn)
 	if err != nil {
-		return ls, fmt.Errorf("failed to expand label templates: %s", err)
+		return ls, fmt.Errorf("failed to expand label templates: %w", err)
 	}
 	return ls, nil
 }
@@ -620,7 +620,7 @@ func (ar *AlertingRule) expandAnnotationTemplates(m datasource.Metric, qFn templ
 	}
 	as, err := notifier.ExecTemplate(qFn, ar.Annotations, tplData)
 	if err != nil {
-		return as, fmt.Errorf("failed to expand annotation templates: %s", err)
+		return as, fmt.Errorf("failed to expand annotation templates: %w", err)
 	}
 	return as, nil
 }

app/vmalert/rule/recording_test.go

@@ -457,12 +457,10 @@ func TestSetIntervalAsTimeFilter(t *testing.T) {
 	f(`* | count()`, "vlogs", true)
 	f(`error OR _time:5m  | count()`, "vlogs", true)
 	f(`(_time: 5m AND error) OR (_time: 5m AND warn) | count()`, "vlogs", true)
-	f(`* | error OR _time:5m | count()`, "vlogs", true)
 
 	f(`_time:5m | count()`, "vlogs", false)
 	f(`_time:2023-04-25T22:45:59Z | count()`, "vlogs", false)
 	f(`error AND _time:5m | count()`, "vlogs", false)
-	f(`* | error AND _time:5m | count()`, "vlogs", false)
 }
 
 func TestRecordingRuleExec_Partial(t *testing.T) {

app/vmalert/web.go

@@ -77,7 +77,7 @@ var (
 func marshalJson(v any, kind string) ([]byte, *httpserver.ErrorWithStatusCode) {
 	data, err := json.Marshal(v)
 	if err != nil {
-		return nil, errResponse(fmt.Errorf("failed to marshal %s: %s", kind, err), http.StatusInternalServerError)
+		return nil, errResponse(fmt.Errorf("failed to marshal %s: %w", kind, err), http.StatusInternalServerError)
 	}
 	return data, nil
 }

app/vmauth/auth_config.go

@@ -840,6 +840,11 @@ func authConfigReloader(sighupCh <-chan os.Signal) {
 	}
 
 	for {
+		select {
+		case <-stopCh:
+			return
+		default:
+		}
 		select {
 		case <-stopCh:
 			return
@@ -906,7 +911,8 @@ func reloadAuthConfigData(data []byte) (bool, error) {
 		return false, fmt.Errorf("failed to parse auth config: %w", err)
 	}
 
-	jui, oidcDP, err := parseJWTUsers(ac)
+	oidcDP := &oidcDiscovererPool{}
+	jui, err := parseJWTUsers(ac, oidcDP)
 	if err != nil {
 		return false, fmt.Errorf("failed to parse JWT users from auth config: %w", err)
 	}

app/vmauth/jwt.go

@@ -72,9 +72,8 @@ type JWTConfig struct {
 	verifierPool atomic.Pointer[jwt.VerifierPool]
 }
 
-func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
+func parseJWTUsers(ac *AuthConfig, oidcDP *oidcDiscovererPool) ([]*UserInfo, error) {
 	jui := make([]*UserInfo, 0, len(ac.Users))
-	oidcDP := &oidcDiscovererPool{}
 
 	uniqClaims := make(map[string]*UserInfo)
 	var sortedClaims []string
@@ -85,10 +84,10 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
 		}
 
 		if ui.AuthToken != "" || ui.BearerToken != "" || ui.Username != "" || ui.Password != "" {
-			return nil, nil, fmt.Errorf("auth_token, bearer_token, username and password cannot be specified if jwt is set")
+			return nil, fmt.Errorf("auth_token, bearer_token, username and password cannot be specified if jwt is set")
 		}
 		if len(jwtToken.PublicKeys) == 0 && len(jwtToken.PublicKeyFiles) == 0 && !jwtToken.SkipVerify && jwtToken.OIDC == nil {
-			return nil, nil, fmt.Errorf("jwt must contain at least a single public key, public_key_files, oidc or have skip_verify=true")
+			return nil, fmt.Errorf("jwt must contain at least a single public key, public_key_files, oidc or have skip_verify=true")
 		}
 		var claimsString string
 		sortedClaims = sortedClaims[:0]
@@ -97,7 +96,7 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
 			sortedClaims = append(sortedClaims, fmt.Sprintf("%s=%s", ck, cv))
 			pc, err := jwt.NewClaim(ck, cv)
 			if err != nil {
-				return nil, nil, fmt.Errorf("incorrect match claim, key=%q, value regex=%q: %w", ck, cv, err)
+				return nil, fmt.Errorf("incorrect match claim, key=%q, value regex=%q: %w", ck, cv, err)
 			}
 			parsedClaims = append(parsedClaims, pc)
 		}
@@ -106,7 +105,7 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
 		claimsString = strings.Join(sortedClaims, ",")
 
 		if oldUI, ok := uniqClaims[claimsString]; ok {
-			return nil, nil, fmt.Errorf("duplicate match claims=%q found for name=%q at idx=%d; the previous one is set for name=%q", claimsString, ui.Name, idx, oldUI.Name)
+			return nil, fmt.Errorf("duplicate match claims=%q found for name=%q at idx=%d; the previous one is set for name=%q", claimsString, ui.Name, idx, oldUI.Name)
 		}
 		uniqClaims[claimsString] = &ui
 		if len(jwtToken.PublicKeys) > 0 || len(jwtToken.PublicKeyFiles) > 0 {
@@ -115,7 +114,7 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
 			for i := range jwtToken.PublicKeys {
 				k, err := jwt.ParseKey([]byte(jwtToken.PublicKeys[i]))
 				if err != nil {
-					return nil, nil, err
+					return nil, err
 				}
 				keys = append(keys, k)
 			}
@@ -123,52 +122,52 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
 			for _, filePath := range jwtToken.PublicKeyFiles {
 				keyData, err := os.ReadFile(filePath)
 				if err != nil {
-					return nil, nil, fmt.Errorf("cannot read public key from file %q: %w", filePath, err)
+					return nil, fmt.Errorf("cannot read public key from file %q: %w", filePath, err)
 				}
 				k, err := jwt.ParseKey(keyData)
 				if err != nil {
-					return nil, nil, fmt.Errorf("cannot parse public key from file %q: %w", filePath, err)
+					return nil, fmt.Errorf("cannot parse public key from file %q: %w", filePath, err)
 				}
 				keys = append(keys, k)
 			}
 
 			vp, err := jwt.NewVerifierPool(keys)
 			if err != nil {
-				return nil, nil, err
+				return nil, err
 			}
 
 			jwtToken.verifierPool.Store(vp)
 		}
 		if jwtToken.OIDC != nil {
 			if len(jwtToken.PublicKeys) > 0 || len(jwtToken.PublicKeyFiles) > 0 || jwtToken.SkipVerify {
-				return nil, nil, fmt.Errorf("jwt with oidc cannot contain public keys or have skip_verify=true")
+				return nil, fmt.Errorf("jwt with oidc cannot contain public keys or have skip_verify=true")
 			}
 
 			if jwtToken.OIDC.Issuer == "" {
-				return nil, nil, fmt.Errorf("oidc issuer cannot be empty")
+				return nil, fmt.Errorf("oidc issuer cannot be empty")
 			}
 			isserURL, err := url.Parse(jwtToken.OIDC.Issuer)
 			if err != nil {
-				return nil, nil, fmt.Errorf("oidc issuer %q must be a valid URL", jwtToken.OIDC.Issuer)
+				return nil, fmt.Errorf("oidc issuer %q must be a valid URL", jwtToken.OIDC.Issuer)
 			}
 			if isserURL.Scheme != "https" && isserURL.Scheme != "http" {
-				return nil, nil, fmt.Errorf("oidc issuer %q must have http or https scheme", jwtToken.OIDC.Issuer)
+				return nil, fmt.Errorf("oidc issuer %q must have http or https scheme", jwtToken.OIDC.Issuer)
 			}
 
 			oidcDP.createOrAdd(ui.JWT.OIDC.Issuer, &ui.JWT.verifierPool)
 		}
 
 		if err := parseJWTPlaceholdersForUserInfo(&ui, true); err != nil {
-			return nil, nil, err
+			return nil, err
 		}
 
 		if err := ui.initURLs(); err != nil {
-			return nil, nil, err
+			return nil, err
 		}
 
 		metricLabels, err := ui.getMetricLabels()
 		if err != nil {
-			return nil, nil, fmt.Errorf("cannot parse metric_labels: %w", err)
+			return nil, fmt.Errorf("cannot parse metric_labels: %w", err)
 		}
 		ui.requests = ac.ms.GetOrCreateCounter(`vmauth_user_requests_total` + metricLabels)
 		ui.requestErrors = ac.ms.GetOrCreateCounter(`vmauth_user_request_errors_total` + metricLabels)
@@ -187,7 +186,7 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
 
 		rt, err := newRoundTripper(ui.TLSCAFile, ui.TLSCertFile, ui.TLSKeyFile, ui.TLSServerName, ui.TLSInsecureSkipVerify)
 		if err != nil {
-			return nil, nil, fmt.Errorf("cannot initialize HTTP RoundTripper: %w", err)
+			return nil, fmt.Errorf("cannot initialize HTTP RoundTripper: %w", err)
 		}
 		ui.rt = rt
 
@@ -200,7 +199,7 @@ func parseJWTUsers(ac *AuthConfig) ([]*UserInfo, *oidcDiscovererPool, error) {
 		return len(jui[i].JWT.MatchClaims) > len(jui[j].JWT.MatchClaims)
 	})
 
-	return jui, oidcDP, nil
+	return jui, nil
 }
 
 var tokenPool sync.Pool

app/vmauth/jwt_test.go

@@ -39,16 +39,14 @@ XOtclIk1uhc03oL9nOQ=
 			}
 			return
 		}
-		users, oidcDP, err := parseJWTUsers(ac)
+		oidcDP := &oidcDiscovererPool{}
+		users, err := parseJWTUsers(ac, oidcDP)
 		if err == nil {
 			t.Fatalf("expecting non-nil error; got %v", users)
 		}
 		if expErr != err.Error() {
 			t.Fatalf("unexpected error; got\n%q\nwant \n%q", err.Error(), expErr)
 		}
-		if oidcDP != nil {
-			t.Fatalf("expecting nil oidcDP; got %v", oidcDP)
-		}
 	}
 
 	// unauthorized_user cannot be used with jwt
@@ -326,7 +324,8 @@ XOtclIk1uhc03oL9nOQ=
 			t.Fatalf("unexpected error: %s", err)
 		}
 
-		jui, oidcDP, err := parseJWTUsers(ac)
+		oidcDP := &oidcDiscovererPool{}
+		jui, err := parseJWTUsers(ac, oidcDP)
 		if err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}

app/vmauth/main_test.go

@@ -1639,7 +1639,7 @@ func (w *fakeResponseWriter) WriteHeader(statusCode int) {
 		"X-Content-Type-Options": true,
 	})
 	if err != nil {
-		panic(fmt.Errorf("cannot marshal headers: %s", err))
+		panic(fmt.Errorf("cannot marshal headers: %w", err))
 	}
 }
 

app/vmauth/oidc.go

@@ -161,7 +161,7 @@ func fetchAndParseJWKs(ctx context.Context, jwksURI string) (*jwt.VerifierPool,
 
 	vp, err := jwt.ParseJWKs(b)
 	if err != nil {
-		return nil, fmt.Errorf("failed to parse jwks keys from %q: %v", jwksURI, err)
+		return nil, fmt.Errorf("failed to parse jwks keys from %q: %w", jwksURI, err)
 	}
 
 	return vp, nil
@@ -188,7 +188,7 @@ func getOpenIDConfiguration(ctx context.Context, issuer string) (openidConfig, e
 
 	var cfg openidConfig
 	if err := json.NewDecoder(resp.Body).Decode(&cfg); err != nil {
-		return openidConfig{}, fmt.Errorf("failed to decode openid config from %q: %s", configURL, err)
+		return openidConfig{}, fmt.Errorf("failed to decode openid config from %q: %w", configURL, err)
 	}
 
 	return cfg, nil

app/vmctl/README.md

@@ -1,3 +1,3 @@
 See vmctl docs [here](https://docs.victoriametrics.com/victoriametrics/vmctl/).
 
-vmctl docs can be edited at [docs/vmctl.md](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/docs/victoriametrics/vmctl.md).
+vmctl docs can be edited at [docs/vmctl.md](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/docs/victoriametrics/vmctl/vmctl.md).

app/vmctl/auth/auth.go

@@ -131,16 +131,13 @@ func (ac *authContext) initFromBasicAuthConfig(ba *BasicAuthConfig) error {
 	if ba.Username == "" {
 		return fmt.Errorf("missing `username` in `basic_auth` section")
 	}
-	if ba.Password != "" {
-		ac.getAuthHeader = func() string {
-			// See https://en.wikipedia.org/wiki/Basic_access_authentication
-			token := ba.Username + ":" + ba.Password
-			token64 := base64.StdEncoding.EncodeToString([]byte(token))
-			return "Basic " + token64
-		}
-		ac.authDigest = fmt.Sprintf("basic(username=%q, password=%q)", ba.Username, ba.Password)
-		return nil
+	ac.getAuthHeader = func() string {
+		// See https://en.wikipedia.org/wiki/Basic_access_authentication
+		token := ba.Username + ":" + ba.Password
+		token64 := base64.StdEncoding.EncodeToString([]byte(token))
+		return "Basic " + token64
 	}
+	ac.authDigest = fmt.Sprintf("basic(username=%q, password=%q)", ba.Username, ba.Password)
 	return nil
 }
 

app/vmctl/flags.go

@@ -69,6 +69,8 @@ const (
 	vmAddr               = "vm-addr"
 	vmUser               = "vm-user"
 	vmPassword           = "vm-password"
+	vmHeaders            = "vm-headers"
+	vmBearerToken        = "vm-bearer-token"
 	vmAccountID          = "vm-account-id"
 	vmConcurrency        = "vm-concurrency"
 	vmCompress           = "vm-compress"
@@ -112,6 +114,16 @@ var (
 			Usage:   "VictoriaMetrics password for basic auth",
 			EnvVars: []string{"VM_PASSWORD"},
 		},
+		&cli.StringFlag{
+			Name: vmHeaders,
+			Usage: "Optional HTTP headers to send with each request to the corresponding destination address. \n" +
+				"For example, --vm-headers='My-Auth:foobar' would send 'My-Auth: foobar' HTTP header with every request to the corresponding destination address. \n" +
+				"Multiple headers must be delimited by '^^': --vm-headers='header1:value1^^header2:value2'",
+		},
+		&cli.StringFlag{
+			Name:  vmBearerToken,
+			Usage: "Optional bearer auth token to use for the corresponding --vm-addr",
+		},
 		&cli.StringFlag{
 			Name: vmAccountID,
 			Usage: "AccountID is an arbitrary 32-bit integer identifying namespace for data ingestion (aka tenant). \n" +

app/vmctl/influx.go

@@ -43,7 +43,7 @@ func newInfluxProcessor(ic *influx.Client, im *vm.Importer, cc int, separator st
 func (ip *influxProcessor) run(ctx context.Context) error {
 	series, err := ip.ic.Explore()
 	if err != nil {
-		return fmt.Errorf("explore query failed: %s", err)
+		return fmt.Errorf("explore query failed: %w", err)
 	}
 	if len(series) < 1 {
 		return fmt.Errorf("found no timeseries to import")
@@ -71,7 +71,7 @@ func (ip *influxProcessor) run(ctx context.Context) error {
 			for s := range seriesCh {
 				if err := ip.do(s); err != nil {
 					influxErrorsTotal.Inc()
-					errCh <- fmt.Errorf("request failed for %q.%q: %s", s.Measurement, s.Field, err)
+					errCh <- fmt.Errorf("request failed for %q.%q: %w", s.Measurement, s.Field, err)
 					return
 				}
 				influxSeriesProcessed.Inc()
@@ -84,10 +84,10 @@ func (ip *influxProcessor) run(ctx context.Context) error {
 	for _, s := range series {
 		select {
 		case infErr := <-errCh:
-			return fmt.Errorf("influx error: %s", infErr)
+			return fmt.Errorf("influx error: %w", infErr)
 		case vmErr := <-ip.im.Errors():
 			influxErrorsTotal.Inc()
-			return fmt.Errorf("import process failed: %s", wrapErr(vmErr, ip.isVerbose))
+			return fmt.Errorf("import process failed: %w", wrapErr(vmErr, ip.isVerbose))
 		case seriesCh <- s:
 		}
 	}
@@ -100,11 +100,11 @@ func (ip *influxProcessor) run(ctx context.Context) error {
 	for vmErr := range ip.im.Errors() {
 		if vmErr.Err != nil {
 			influxErrorsTotal.Inc()
-			return fmt.Errorf("import process failed: %s", wrapErr(vmErr, ip.isVerbose))
+			return fmt.Errorf("import process failed: %w", wrapErr(vmErr, ip.isVerbose))
 		}
 	}
 	for err := range errCh {
-		return fmt.Errorf("import process failed: %s", err)
+		return fmt.Errorf("import process failed: %w", err)
 	}
 
 	log.Println("Import finished!")
@@ -119,7 +119,7 @@ const valueField = "value"
 func (ip *influxProcessor) do(s *influx.Series) error {
 	cr, err := ip.ic.FetchDataPoints(s)
 	if err != nil {
-		return fmt.Errorf("failed to fetch datapoints: %s", err)
+		return fmt.Errorf("failed to fetch datapoints: %w", err)
 	}
 	defer func() {
 		_ = cr.Close()

app/vmctl/influx/influx.go

@@ -96,10 +96,10 @@ func NewClient(cfg Config) (*Client, error) {
 	}
 	hc, err := influx.NewHTTPClient(c)
 	if err != nil {
-		return nil, fmt.Errorf("failed to establish conn: %s", err)
+		return nil, fmt.Errorf("failed to establish conn: %w", err)
 	}
 	if _, _, err := hc.Ping(time.Second); err != nil {
-		return nil, fmt.Errorf("ping failed: %s", err)
+		return nil, fmt.Errorf("ping failed: %w", err)
 	}
 
 	chunkSize := cfg.ChunkSize
@@ -155,7 +155,7 @@ func (c *Client) Explore() ([]*Series, error) {
 	// {"measurement1": ["value1", "value2"]}
 	mFields, err := c.fieldsByMeasurement()
 	if err != nil {
-		return nil, fmt.Errorf("failed to get field keys: %s", err)
+		return nil, fmt.Errorf("failed to get field keys: %w", err)
 	}
 
 	if len(mFields) < 1 {
@@ -165,12 +165,12 @@ func (c *Client) Explore() ([]*Series, error) {
 	// {"measurement1": {"tag1", "tag2"}}
 	measurementTags, err := c.getMeasurementTags()
 	if err != nil {
-		return nil, fmt.Errorf("failed to get tags of measurements: %s", err)
+		return nil, fmt.Errorf("failed to get tags of measurements: %w", err)
 	}
 
 	series, err := c.getSeries()
 	if err != nil {
-		return nil, fmt.Errorf("failed to get series: %s", err)
+		return nil, fmt.Errorf("failed to get series: %w", err)
 	}
 
 	var iSeries []*Series
@@ -237,7 +237,7 @@ func (cr *ChunkedResponse) Next() ([]int64, []float64, error) {
 		return nil, nil, err
 	}
 	if resp.Error() != nil {
-		return nil, nil, fmt.Errorf("response error for %s: %s", cr.iq.Command, resp.Error())
+		return nil, nil, fmt.Errorf("response error for %s: %w", cr.iq.Command, resp.Error())
 	}
 	if len(resp.Results) != 1 {
 		return nil, nil, fmt.Errorf("unexpected number of results in response: %d", len(resp.Results))
@@ -259,14 +259,13 @@ func (cr *ChunkedResponse) Next() ([]int64, []float64, error) {
 
 	fieldValues, ok := r.values[cr.field]
 	if !ok {
-		return nil, nil, fmt.Errorf("response doesn't contain filed %q", cr.field)
+		return nil, nil, fmt.Errorf("response doesn't contain field %q", cr.field)
 	}
 	values := make([]float64, len(fieldValues))
 	for i, fv := range fieldValues {
 		v, err := toFloat64(fv)
 		if err != nil {
-			return nil, nil, fmt.Errorf("failed to convert value %q.%v to float64: %s",
-				cr.field, v, err)
+			return nil, nil, fmt.Errorf("failed to convert value %q.%v to float64: %w", cr.field, v, err)
 		}
 		values[i] = v
 	}
@@ -294,7 +293,7 @@ func (c *Client) FetchDataPoints(s *Series) (*ChunkedResponse, error) {
 	}
 	cr, err := c.QueryAsChunk(iq)
 	if err != nil {
-		return nil, fmt.Errorf("query %q err: %s", iq.Command, err)
+		return nil, fmt.Errorf("query %q err: %w", iq.Command, err)
 	}
 	return &ChunkedResponse{cr, iq, s.Field}, nil
 }
@@ -308,7 +307,7 @@ func (c *Client) fieldsByMeasurement() (map[string][]string, error) {
 	log.Printf("fetching fields: %s", stringify(q))
 	qValues, err := c.do(q)
 	if err != nil {
-		return nil, fmt.Errorf("error while executing query %q: %s", q.Command, err)
+		return nil, fmt.Errorf("error while executing query %q: %w", q.Command, err)
 	}
 
 	var total int
@@ -352,7 +351,7 @@ func (c *Client) getSeries() ([]*Series, error) {
 	log.Printf("fetching series: %s", stringify(q))
 	cr, err := c.QueryAsChunk(q)
 	if err != nil {
-		return nil, fmt.Errorf("error while executing query %q: %s", q.Command, err)
+		return nil, fmt.Errorf("error while executing query %q: %w", q.Command, err)
 	}
 
 	const key = "key"
@@ -366,7 +365,7 @@ func (c *Client) getSeries() ([]*Series, error) {
 			return nil, err
 		}
 		if resp.Error() != nil {
-			return nil, fmt.Errorf("response error for query %q: %s", q.Command, resp.Error())
+			return nil, fmt.Errorf("response error for query %q: %w", q.Command, resp.Error())
 		}
 		qValues, err := parseResult(resp.Results[0])
 		if err != nil {
@@ -417,7 +416,7 @@ func (c *Client) getMeasurementTags() (map[string]map[string]struct{}, error) {
 	log.Printf("fetching tag keys: %s", stringify(q))
 	cr, err := c.QueryAsChunk(q)
 	if err != nil {
-		return nil, fmt.Errorf("error while executing query %q: %s", q.Command, err)
+		return nil, fmt.Errorf("error while executing query %q: %w", q.Command, err)
 	}
 
 	const tagKey = "tagKey"
@@ -432,7 +431,7 @@ func (c *Client) getMeasurementTags() (map[string]map[string]struct{}, error) {
 			return nil, err
 		}
 		if resp.Error() != nil {
-			return nil, fmt.Errorf("response error for query %q: %s", q.Command, resp.Error())
+			return nil, fmt.Errorf("response error for query %q: %w", q.Command, resp.Error())
 		}
 		qValues, err := parseResult(resp.Results[0])
 		if err != nil {
@@ -455,10 +454,10 @@ func (c *Client) getMeasurementTags() (map[string]map[string]struct{}, error) {
 func (c *Client) do(q influx.Query) ([]queryValues, error) {
 	res, err := c.Query(q)
 	if err != nil {
-		return nil, fmt.Errorf("query error: %s", err)
+		return nil, fmt.Errorf("query error: %w", err)
 	}
 	if res.Error() != nil {
-		return nil, fmt.Errorf("response error: %s", res.Error())
+		return nil, fmt.Errorf("response error: %w", res.Error())
 	}
 	if len(res.Results) < 1 {
 		return nil, fmt.Errorf("query returned 0 results")

app/vmctl/influx/parser.go

@@ -71,7 +71,7 @@ func toFloat64(v any) (float64, error) {
 func parseDate(dateStr string) (int64, error) {
 	startTime, err := time.Parse(time.RFC3339, dateStr)
 	if err != nil {
-		return 0, fmt.Errorf("cannot parse %q: %s", dateStr, err)
+		return 0, fmt.Errorf("cannot parse %q: %w", dateStr, err)
 	}
 	return startTime.UnixNano() / 1e6, nil
 }
@@ -92,7 +92,7 @@ func (s *Series) unmarshal(v string) error {
 	var err error
 	s.LabelPairs, err = unmarshalTags(v[n+1:], noEscapeChars)
 	if err != nil {
-		return fmt.Errorf("failed to unmarhsal tags: %s", err)
+		return fmt.Errorf("failed to unmarhsal tags: %w", err)
 	}
 	return nil
 }

app/vmctl/main.go

@@ -88,7 +88,7 @@ func main() {
 
 					tr, err := promauth.NewTLSTransport(certFile, keyFile, caFile, serverName, insecureSkipVerify, "vmctl_opentsdb")
 					if err != nil {
-						return fmt.Errorf("failed to create transport for -%s=%q: %s", otsdbAddr, addr, err)
+						return fmt.Errorf("failed to create transport for -%s=%q: %w", otsdbAddr, addr, err)
 					}
 					oCfg := opentsdb.Config{
 						Addr:       addr,
@@ -103,17 +103,17 @@ func main() {
 					}
 					otsdbClient, err := opentsdb.NewClient(oCfg)
 					if err != nil {
-						return fmt.Errorf("failed to create opentsdb client: %s", err)
+						return fmt.Errorf("failed to create opentsdb client: %w", err)
 					}
 
 					vmCfg, err := initConfigVM(c)
 					if err != nil {
-						return fmt.Errorf("failed to init VM configuration: %s", err)
+						return fmt.Errorf("failed to init VM configuration: %w", err)
 					}
 
 					importer, err := vm.NewImporter(ctx, vmCfg)
 					if err != nil {
-						return fmt.Errorf("failed to create VM importer: %s", err)
+						return fmt.Errorf("failed to create VM importer: %w", err)
 					}
 
 					otsdbProcessor := newOtsdbProcessor(otsdbClient, importer, c.Int(otsdbConcurrency), c.Bool(globalVerbose))
@@ -137,7 +137,7 @@ func main() {
 
 					tc, err := promauth.NewTLSConfig(certFile, keyFile, caFile, serverName, insecureSkipVerify)
 					if err != nil {
-						return fmt.Errorf("failed to create TLS Config: %s", err)
+						return fmt.Errorf("failed to create TLS Config: %w", err)
 					}
 
 					iCfg := influx.Config{
@@ -157,17 +157,17 @@ func main() {
 
 					influxClient, err := influx.NewClient(iCfg)
 					if err != nil {
-						return fmt.Errorf("failed to create influx client: %s", err)
+						return fmt.Errorf("failed to create influx client: %w", err)
 					}
 
 					vmCfg, err := initConfigVM(c)
 					if err != nil {
-						return fmt.Errorf("failed to init VM configuration: %s", err)
+						return fmt.Errorf("failed to init VM configuration: %w", err)
 					}
 
 					importer, err = vm.NewImporter(ctx, vmCfg)
 					if err != nil {
-						return fmt.Errorf("failed to create VM importer: %s", err)
+						return fmt.Errorf("failed to create VM importer: %w", err)
 					}
 
 					processor := newInfluxProcessor(
@@ -203,7 +203,7 @@ func main() {
 
 					tr, err := promauth.NewTLSTransport(certFile, keyFile, caFile, serverName, insecureSkipVerify, "vmctl_remoteread")
 					if err != nil {
-						return fmt.Errorf("failed to create transport for -%s=%q: %s", remoteReadSrcAddr, addr, err)
+						return fmt.Errorf("failed to create transport for -%s=%q: %w", remoteReadSrcAddr, addr, err)
 					}
 
 					// Backwards compatible default values if none provided by user
@@ -227,17 +227,17 @@ func main() {
 						DisablePathAppend: c.Bool(remoteReadDisablePathAppend),
 					})
 					if err != nil {
-						return fmt.Errorf("error create remote read client: %s", err)
+						return fmt.Errorf("error create remote read client: %w", err)
 					}
 
 					vmCfg, err := initConfigVM(c)
 					if err != nil {
-						return fmt.Errorf("failed to init VM configuration: %s", err)
+						return fmt.Errorf("failed to init VM configuration: %w", err)
 					}
 
 					importer, err := vm.NewImporter(ctx, vmCfg)
 					if err != nil {
-						return fmt.Errorf("failed to create VM importer: %s", err)
+						return fmt.Errorf("failed to create VM importer: %w", err)
 					}
 
 					rmp := remoteReadProcessor{
@@ -265,12 +265,12 @@ func main() {
 
 					vmCfg, err := initConfigVM(c)
 					if err != nil {
-						return fmt.Errorf("failed to init VM configuration: %s", err)
+						return fmt.Errorf("failed to init VM configuration: %w", err)
 					}
 
 					importer, err = vm.NewImporter(ctx, vmCfg)
 					if err != nil {
-						return fmt.Errorf("failed to create VM importer: %s", err)
+						return fmt.Errorf("failed to create VM importer: %w", err)
 					}
 
 					promCfg := prometheus.Config{
@@ -285,7 +285,7 @@ func main() {
 					}
 					cl, err := prometheus.NewClient(promCfg)
 					if err != nil {
-						return fmt.Errorf("failed to create prometheus client: %s", err)
+						return fmt.Errorf("failed to create prometheus client: %w", err)
 					}
 
 					pp := prometheusProcessor{
@@ -307,12 +307,12 @@ func main() {
 
 					vmCfg, err := initConfigVM(c)
 					if err != nil {
-						return fmt.Errorf("failed to init VM configuration: %s", err)
+						return fmt.Errorf("failed to init VM configuration: %w", err)
 					}
 
 					importer, err = vm.NewImporter(ctx, vmCfg)
 					if err != nil {
-						return fmt.Errorf("failed to create VM importer: %s", err)
+						return fmt.Errorf("failed to create VM importer: %w", err)
 					}
 
 					mCfg := mimir.Config{
@@ -335,7 +335,7 @@ func main() {
 					}
 					cl, err := mimir.NewClient(ctx, mCfg)
 					if err != nil {
-						return fmt.Errorf("failed to create mimir client: %s", err)
+						return fmt.Errorf("failed to create mimir client: %w", err)
 					}
 
 					pp := prometheusProcessor{
@@ -356,12 +356,12 @@ func main() {
 					fmt.Println("Thanos import mode")
 					vmCfg, err := initConfigVM(c)
 					if err != nil {
-						return fmt.Errorf("failed to init VM configuration: %s", err)
+						return fmt.Errorf("failed to init VM configuration: %w", err)
 					}
 
 					importer, err = vm.NewImporter(ctx, vmCfg)
 					if err != nil {
-						return fmt.Errorf("failed to create VM importer: %s", err)
+						return fmt.Errorf("failed to create VM importer: %w", err)
 					}
 					thanosCfg := thanos.Config{
 						Snapshot: c.String(thanosSnapshot),
@@ -374,7 +374,7 @@ func main() {
 					}
 					cl, err := thanos.NewClient(thanosCfg)
 					if err != nil {
-						return fmt.Errorf("failed to create thanos client: %s", err)
+						return fmt.Errorf("failed to create thanos client: %w", err)
 					}
 
 					var aggrTypes []thanos.AggrType
@@ -382,7 +382,7 @@ func main() {
 						for _, typeStr := range aggrTypesStr {
 							aggrType, err := thanos.ParseAggrType(typeStr)
 							if err != nil {
-								return fmt.Errorf("failed to parse aggregate type %q: %s", typeStr, err)
+								return fmt.Errorf("failed to parse aggregate type %q: %w", typeStr, err)
 							}
 							aggrTypes = append(aggrTypes, aggrType)
 						}
@@ -415,7 +415,7 @@ func main() {
 					bfMinDuration := c.Duration(vmNativeBackoffMinDuration)
 					bf, err := backoff.New(bfRetries, bfFactor, bfMinDuration)
 					if err != nil {
-						return fmt.Errorf("failed to create backoff object: %s", err)
+						return fmt.Errorf("failed to create backoff object: %w", err)
 					}
 
 					disableKeepAlive := c.Bool(vmNativeDisableHTTPKeepAlive)
@@ -439,7 +439,7 @@ func main() {
 
 					srcTC, err := promauth.NewTLSConfig(srcCertFile, srcKeyFile, srcCAFile, srcServerName, srcInsecureSkipVerify)
 					if err != nil {
-						return fmt.Errorf("failed to create TLS Config: %s", err)
+						return fmt.Errorf("failed to create TLS Config: %w", err)
 					}
 
 					trSrc := httputil.NewTransport(false, "vmctl_src")
@@ -457,7 +457,7 @@ func main() {
 						auth.WithBearer(c.String(vmNativeDstBearerToken)),
 						auth.WithHeaders(c.String(vmNativeDstHeaders)))
 					if err != nil {
-						return fmt.Errorf("error initialize auth config for destination: %s", dstAddr)
+						return fmt.Errorf("error initialize auth config for destination: %s: %w", dstAddr, err)
 					}
 
 					// create TLS config
@@ -469,7 +469,7 @@ func main() {
 
 					dstTC, err := promauth.NewTLSConfig(dstCertFile, dstKeyFile, dstCAFile, dstServerName, dstInsecureSkipVerify)
 					if err != nil {
-						return fmt.Errorf("failed to create TLS Config: %s", err)
+						return fmt.Errorf("failed to create TLS Config: %w", err)
 					}
 
 					trDst := httputil.NewTransport(false, "vmctl_dst")
@@ -534,7 +534,7 @@ func main() {
 					log.Printf("verifying block at path=%q", blockPath)
 					f, err := os.OpenFile(blockPath, os.O_RDONLY, 0600)
 					if err != nil {
-						return cli.Exit(fmt.Errorf("cannot open exported block at path=%q err=%w", blockPath, err), 1)
+						return cli.Exit(fmt.Errorf("cannot open exported block at path=%q: %w", blockPath, err), 1)
 					}
 					defer f.Close()
 					var blocksCount atomic.Uint64
@@ -542,7 +542,7 @@ func main() {
 						blocksCount.Add(1)
 						return nil
 					}); err != nil {
-						return cli.Exit(fmt.Errorf("cannot parse block at path=%q, blocksCount=%d, err=%w", blockPath, blocksCount.Load(), err), 1)
+						return cli.Exit(fmt.Errorf("cannot parse block at path=%q, blocksCount=%d: %w", blockPath, blocksCount.Load(), err), 1)
 					}
 					log.Printf("successfully verified block at path=%q, blockCount=%d", blockPath, blocksCount.Load())
 					return nil
@@ -563,11 +563,11 @@ func main() {
 	}()
 
 	err = app.Run(os.Args)
+	pushmetrics.StopAndPush()
 	if err != nil {
 		log.Fatalln(err)
 	}
 	log.Printf("Total time: %v", time.Since(start))
-	pushmetrics.StopAndPush()
 }
 
 func initConfigVM(c *cli.Context) (vm.Config, error) {
@@ -585,7 +585,7 @@ func initConfigVM(c *cli.Context) (vm.Config, error) {
 
 	tr, err := promauth.NewTLSTransport(certFile, keyFile, caFile, serverName, insecureSkipVerify, "vmctl_client")
 	if err != nil {
-		return vm.Config{}, fmt.Errorf("failed to create transport for -%s=%q: %s", vmAddr, addr, err)
+		return vm.Config{}, fmt.Errorf("failed to create transport for -%s=%q: %w", vmAddr, addr, err)
 	}
 
 	bfRetries := c.Int(vmBackoffRetries)
@@ -593,14 +593,21 @@ func initConfigVM(c *cli.Context) (vm.Config, error) {
 	bfMinDuration := c.Duration(vmBackoffMinDuration)
 	bf, err := backoff.New(bfRetries, bfFactor, bfMinDuration)
 	if err != nil {
-		return vm.Config{}, fmt.Errorf("failed to create backoff object: %s", err)
+		return vm.Config{}, fmt.Errorf("failed to create backoff object: %w", err)
+	}
+
+	authCfg, err := auth.Generate(
+		auth.WithBasicAuth(c.String(vmUser), c.String(vmPassword)),
+		auth.WithBearer(c.String(vmBearerToken)),
+		auth.WithHeaders(c.String(vmHeaders)))
+	if err != nil {
+		return vm.Config{}, fmt.Errorf("error initialize auth config for destination: %s: %w", addr, err)
 	}
 
 	return vm.Config{
 		Addr:               addr,
 		Transport:          tr,
-		User:               c.String(vmUser),
-		Password:           c.String(vmPassword),
+		AuthCfg:            authCfg,
 		Concurrency:        uint8(c.Int(vmConcurrency)),
 		Compress:           c.Bool(vmCompress),
 		AccountID:          c.String(vmAccountID),

app/vmctl/mimir/lazyreader.go

@@ -54,7 +54,7 @@ func (lbr *lazyBlockReader) initialize() error {
 	// 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)
+		return fmt.Errorf("failed to create temp dir: %w", err)
 	}
 
 	lbr.tempDirPath = temp
@@ -85,7 +85,7 @@ func (lbr *lazyBlockReader) initialize() error {
 			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)
+			return fmt.Errorf("failed to write chunk file: %q: %w", chunkName, err)
 		}
 	}
 
@@ -135,7 +135,7 @@ func (lbr *lazyBlockReader) Meta() tsdb.BlockMeta {
 // 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)
+		lbr.err = fmt.Errorf("error get Size of the block: %w, return zero size", err)
 		return 0
 	}
 	return lbr.reader.Size()
@@ -167,11 +167,11 @@ func (lbr *lazyBlockReader) Close() error {
 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)
+		return "", fmt.Errorf("failed to create temp dir: %w", err)
 	}
 	err = os.Mkdir(filepath.Join(temp, "chunks"), os.ModePerm)
 	if err != nil {
-		return "", fmt.Errorf("failed to create temp dir: %s", err)
+		return "", fmt.Errorf("failed to create temp dir: %w", err)
 	}
 	return temp, nil
 }

app/vmctl/mimir/mimir.go

@@ -133,11 +133,11 @@ func NewClient(ctx context.Context, cfg Config) (*Client, error) {
 	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)
+		return nil, fmt.Errorf("failed to parse min time in filter: %w", err)
 	}
 	timeMax, err := utils.ParseTime(cfg.Filter.TimeMax)
 	if err != nil {
-		return nil, fmt.Errorf("failed to parse max time in filter: %s", err)
+		return nil, fmt.Errorf("failed to parse max time in filter: %w", err)
 	}
 	c.filter = filter{
 		min:        timeMin.UnixMilli(),
@@ -156,7 +156,7 @@ func (c *Client) Explore() ([]tsdb.BlockReader, error) {
 
 	indexFile, err := c.fetchIndexFile()
 	if err != nil {
-		return nil, fmt.Errorf("failed to fetch index file: %s", err)
+		return nil, fmt.Errorf("failed to fetch index file: %w", err)
 	}
 
 	var blocksToImport []tsdb.BlockReader
@@ -172,7 +172,7 @@ func (c *Client) Explore() ([]tsdb.BlockReader, error) {
 
 		lazyBlockReader, err := newLazyBlockReader(block, c.RemoteFS)
 		if err != nil {
-			return nil, fmt.Errorf("failed to create lazy block reader: %s", err)
+			return nil, fmt.Errorf("failed to create lazy block reader: %w", err)
 		}
 		blocksToImport = append(blocksToImport, lazyBlockReader)
 	}
@@ -185,7 +185,7 @@ func (c *Client) Explore() ([]tsdb.BlockReader, error) {
 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())
+		return nil, fmt.Errorf("failed to read block: %w", b.Err())
 	}
 
 	if meta.ULID.String() == "" {
@@ -218,20 +218,20 @@ func (c *Client) fetchIndexFile() (*Index, error) {
 
 	file, err := c.ReadFile(bucketIndexCompressedFilename)
 	if err != nil {
-		return nil, fmt.Errorf("failed to read bucket index: %s", err)
+		return nil, fmt.Errorf("failed to read bucket index: %w", 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)
+		return nil, fmt.Errorf("failed to create gzip reader: %w", 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 nil, fmt.Errorf("failed to decode bucket index: %w", err)
 	}
 
 	return &indexFile, nil

app/vmctl/native/client.go

@@ -47,7 +47,7 @@ func (c *Client) Explore(ctx context.Context, f Filter, tenantID string, start,
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
 	if err != nil {
 		exploreRequestsErrorsTotal.Inc()
-		return nil, fmt.Errorf("cannot create request to %q: %s", url, err)
+		return nil, fmt.Errorf("cannot create request to %q: %w", url, err)
 	}
 
 	params := req.URL.Query()
@@ -60,14 +60,14 @@ func (c *Client) Explore(ctx context.Context, f Filter, tenantID string, start,
 	if err != nil {
 		exploreRequestsErrorsTotal.Inc()
 		exploreDuration.UpdateDuration(startTime)
-		return nil, fmt.Errorf("series request failed: %s", err)
+		return nil, fmt.Errorf("series request failed: %w", err)
 	}
 
 	var response Response
 	if err := json.NewDecoder(resp.Body).Decode(&response); err != nil {
 		exploreRequestsErrorsTotal.Inc()
 		exploreDuration.UpdateDuration(startTime)
-		return nil, fmt.Errorf("cannot decode series response: %s", err)
+		return nil, fmt.Errorf("cannot decode series response: %w", err)
 	}
 	exploreDuration.UpdateDuration(startTime)
 	return response.MetricNames, resp.Body.Close()
@@ -80,19 +80,19 @@ func (c *Client) ImportPipe(ctx context.Context, dstURL string, pr *io.PipeReade
 	req, err := http.NewRequestWithContext(ctx, http.MethodPost, dstURL, pr)
 	if err != nil {
 		importRequestsErrorsTotal.Inc()
-		return fmt.Errorf("cannot create import request to %q: %s", c.Addr, err)
+		return fmt.Errorf("cannot create import request to %q: %w", c.Addr, err)
 	}
 
 	importResp, err := c.do(req, http.StatusNoContent)
 	if err != nil {
 		importRequestsErrorsTotal.Inc()
 		importDuration.UpdateDuration(startTime)
-		return fmt.Errorf("import request failed: %s", err)
+		return fmt.Errorf("import request failed: %w", err)
 	}
 	if err := importResp.Body.Close(); err != nil {
 		importRequestsErrorsTotal.Inc()
 		importDuration.UpdateDuration(startTime)
-		return fmt.Errorf("cannot close import response body: %s", err)
+		return fmt.Errorf("cannot close import response body: %w", err)
 	}
 	importDuration.UpdateDuration(startTime)
 	return nil
@@ -105,7 +105,7 @@ func (c *Client) ExportPipe(ctx context.Context, url string, f Filter) (io.ReadC
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
 	if err != nil {
 		exportRequestsErrorsTotal.Inc()
-		return nil, fmt.Errorf("cannot create request to %q: %s", c.Addr, err)
+		return nil, fmt.Errorf("cannot create request to %q: %w", c.Addr, err)
 	}
 
 	params := req.URL.Query()
@@ -136,7 +136,7 @@ func (c *Client) GetSourceTenants(ctx context.Context, f Filter) ([]string, erro
 	u := fmt.Sprintf("%s/%s", c.Addr, nativeTenantsAddr)
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, u, nil)
 	if err != nil {
-		return nil, fmt.Errorf("cannot create request to %q: %s", u, err)
+		return nil, fmt.Errorf("cannot create request to %q: %w", u, err)
 	}
 
 	params := req.URL.Query()
@@ -150,18 +150,18 @@ func (c *Client) GetSourceTenants(ctx context.Context, f Filter) ([]string, erro
 
 	resp, err := c.do(req, http.StatusOK)
 	if err != nil {
-		return nil, fmt.Errorf("tenants request failed: %s", err)
+		return nil, fmt.Errorf("tenants request failed: %w", err)
 	}
 
 	var r struct {
 		Tenants []string `json:"data"`
 	}
 	if err := json.NewDecoder(resp.Body).Decode(&r); err != nil {
-		return nil, fmt.Errorf("cannot decode tenants response: %s", err)
+		return nil, fmt.Errorf("cannot decode tenants response: %w", err)
 	}
 
 	if err := resp.Body.Close(); err != nil {
-		return nil, fmt.Errorf("cannot close tenants response body: %s", err)
+		return nil, fmt.Errorf("cannot close tenants response body: %w", err)
 	}
 
 	return r.Tenants, nil
@@ -180,7 +180,7 @@ func (c *Client) do(req *http.Request, expSC int) (*http.Response, error) {
 	if resp.StatusCode != expSC {
 		body, err := io.ReadAll(resp.Body)
 		if err != nil {
-			return nil, fmt.Errorf("failed to read response body for status code %d: %s", resp.StatusCode, err)
+			return nil, fmt.Errorf("failed to read response body for status code %d: %w", resp.StatusCode, err)
 		}
 		return nil, fmt.Errorf("unexpected response code %d: %s", resp.StatusCode, string(body))
 	}

app/vmctl/opentsdb.go

@@ -47,7 +47,7 @@ func (op *otsdbProcessor) run(ctx context.Context) error {
 		q := fmt.Sprintf("%s/api/suggest?type=metrics&q=%s&max=%d", op.oc.Addr, filter, op.oc.Limit)
 		m, err := op.oc.FindMetrics(q)
 		if err != nil {
-			return fmt.Errorf("metric discovery failed for %q: %s", q, err)
+			return fmt.Errorf("metric discovery failed for %q: %w", q, err)
 		}
 		metrics = append(metrics, m...)
 	}
@@ -76,7 +76,7 @@ func (op *otsdbProcessor) run(ctx context.Context) error {
 		log.Printf("Starting work on %s", metric)
 		serieslist, err := op.oc.FindSeries(metric)
 		if err != nil {
-			return fmt.Errorf("couldn't retrieve series list for %s : %s", metric, err)
+			return fmt.Errorf("couldn't retrieve series list for %s: %w", metric, err)
 		}
 		/*
 			Create channels for collecting/processing series and errors
@@ -95,7 +95,7 @@ func (op *otsdbProcessor) run(ctx context.Context) error {
 				for s := range seriesCh {
 					if err := op.do(s); err != nil {
 						otsdbErrorsTotal.Inc()
-						errCh <- fmt.Errorf("couldn't retrieve series for %s : %s", metric, err)
+						errCh <- fmt.Errorf("couldn't retrieve series for %s: %w", metric, err)
 						return
 					}
 					otsdbSeriesProcessed.Inc()
@@ -112,7 +112,7 @@ func (op *otsdbProcessor) run(ctx context.Context) error {
 		// check for any lingering errors on the query side
 		for otsdbErr := range errCh {
 			if runErr == nil {
-				runErr = fmt.Errorf("import process failed: \n%s", otsdbErr)
+				runErr = fmt.Errorf("import process failed:\n%w", otsdbErr)
 			}
 		}
 		bar.Finish()
@@ -125,7 +125,7 @@ func (op *otsdbProcessor) run(ctx context.Context) error {
 	for vmErr := range op.im.Errors() {
 		if vmErr.Err != nil {
 			otsdbErrorsTotal.Inc()
-			return fmt.Errorf("import process failed: %s", wrapErr(vmErr, op.isVerbose))
+			return fmt.Errorf("import process failed: %w", wrapErr(vmErr, op.isVerbose))
 		}
 	}
 	log.Println("Import finished!")
@@ -141,12 +141,12 @@ func (op *otsdbProcessor) sendQueries(ctx context.Context, serieslist []opentsdb
 			for _, tr := range rt.QueryRanges {
 				select {
 				case <-ctx.Done():
-					return fmt.Errorf("context canceled: %s", ctx.Err())
+					return fmt.Errorf("context canceled: %w", ctx.Err())
 				case otsdbErr := <-errCh:
 					otsdbErrorsTotal.Inc()
-					return fmt.Errorf("opentsdb error: %s", otsdbErr)
+					return fmt.Errorf("opentsdb error: %w", otsdbErr)
 				case vmErr := <-op.im.Errors():
-					return fmt.Errorf("import process failed: %s", wrapErr(vmErr, op.isVerbose))
+					return fmt.Errorf("import process failed: %w", wrapErr(vmErr, op.isVerbose))
 				case seriesCh <- queryObj{
 					Tr: tr, StartTime: startTime,
 					Series: series, Rt: opentsdb.RetentionMeta{
@@ -166,7 +166,7 @@ func (op *otsdbProcessor) do(s queryObj) error {
 	end := s.StartTime - s.Tr.End
 	data, err := op.oc.GetData(s.Series, s.Rt, start, end, op.oc.MsecsTime)
 	if err != nil {
-		return fmt.Errorf("failed to collect data for %v in %v:%v :: %v", s.Series, s.Rt, s.Tr, err)
+		return fmt.Errorf("failed to collect data for %v in %v:%v :: %w", s.Series, s.Rt, s.Tr, err)
 	}
 	if len(data.Timestamps) < 1 || len(data.Values) < 1 {
 		log.Printf("no data found for %v in %v:%v...skipping", s.Series, s.Rt, s.Tr)

app/vmctl/opentsdb/opentsdb.go

@@ -106,7 +106,7 @@ func (c Client) FindMetrics(q string) ([]string, error) {
 
 	resp, err := c.c.Get(q)
 	if err != nil {
-		return nil, fmt.Errorf("failed to send GET request to %q: %s", q, err)
+		return nil, fmt.Errorf("failed to send GET request to %q: %w", q, err)
 	}
 	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != 200 {
@@ -114,12 +114,12 @@ func (c Client) FindMetrics(q string) ([]string, error) {
 	}
 	body, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return nil, fmt.Errorf("could not retrieve metric data from %q: %s", q, err)
+		return nil, fmt.Errorf("could not retrieve metric data from %q: %w", q, err)
 	}
 	var metriclist []string
 	err = json.Unmarshal(body, &metriclist)
 	if err != nil {
-		return nil, fmt.Errorf("failed to read response from %q: %s", q, err)
+		return nil, fmt.Errorf("failed to read response from %q: %w", q, err)
 	}
 	return metriclist, nil
 }
@@ -130,7 +130,7 @@ func (c Client) FindSeries(metric string) ([]Meta, error) {
 	q := fmt.Sprintf("%s/api/search/lookup?m=%s&limit=%d", c.Addr, metric, c.Limit)
 	resp, err := c.c.Get(q)
 	if err != nil {
-		return nil, fmt.Errorf("failed to send GET request to %q: %s", q, err)
+		return nil, fmt.Errorf("failed to send GET request to %q: %w", q, err)
 	}
 	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != 200 {
@@ -138,12 +138,12 @@ func (c Client) FindSeries(metric string) ([]Meta, error) {
 	}
 	body, err := io.ReadAll(resp.Body)
 	if err != nil {
-		return nil, fmt.Errorf("could not retrieve series data from %q: %s", q, err)
+		return nil, fmt.Errorf("could not retrieve series data from %q: %w", q, err)
 	}
 	var results MetaResults
 	err = json.Unmarshal(body, &results)
 	if err != nil {
-		return nil, fmt.Errorf("failed to read response from %q: %s", q, err)
+		return nil, fmt.Errorf("failed to read response from %q: %w", q, err)
 	}
 	return results.Results, nil
 }
@@ -183,7 +183,7 @@ func (c Client) GetData(series Meta, rt RetentionMeta, start int64, end int64, m
 	q := fmt.Sprintf("%s/api/query?%s", c.Addr, queryStr)
 	resp, err := c.c.Get(q)
 	if err != nil {
-		return Metric{}, fmt.Errorf("failed to send GET request to %q: %s", q, err)
+		return Metric{}, fmt.Errorf("failed to send GET request to %q: %w", q, err)
 	}
 	defer func() { _ = resp.Body.Close() }()
 	/*
@@ -303,7 +303,7 @@ func NewClient(cfg Config) (*Client, error) {
 	for _, r := range cfg.Retentions {
 		ret, err := convertRetention(r, offsetSecs, cfg.MsecsTime)
 		if err != nil {
-			return &Client{}, fmt.Errorf("couldn't parse retention %q :: %v", r, err)
+			return &Client{}, fmt.Errorf("couldn't parse retention %q :: %w", r, err)
 		}
 		retentions = append(retentions, ret)
 	}

app/vmctl/opentsdb/parser.go

@@ -88,7 +88,7 @@ func convertRetention(retention string, offset int64, msecTime bool) (Retention,
 	}
 	queryLengthDuration, err := convertDuration(chunks[2])
 	if err != nil {
-		return Retention{}, fmt.Errorf("invalid ttl (second order) duration string: %q: %s", chunks[2], err)
+		return Retention{}, fmt.Errorf("invalid ttl (second order) duration string: %q: %w", chunks[2], err)
 	}
 	// set ttl in milliseconds, unless we aren't using millisecond time in OpenTSDB...then use seconds
 	queryLength := queryLengthDuration.Milliseconds()
@@ -110,7 +110,7 @@ func convertRetention(retention string, offset int64, msecTime bool) (Retention,
 
 	aggTimeDuration, err := convertDuration(aggregates[1])
 	if err != nil {
-		return Retention{}, fmt.Errorf("invalid aggregation time duration string: %q: %s", aggregates[1], err)
+		return Retention{}, fmt.Errorf("invalid aggregation time duration string: %q: %w", aggregates[1], err)
 	}
 	aggTime := aggTimeDuration.Milliseconds()
 	if !msecTime {
@@ -119,7 +119,7 @@ func convertRetention(retention string, offset int64, msecTime bool) (Retention,
 
 	rowLengthDuration, err := convertDuration(chunks[1])
 	if err != nil {
-		return Retention{}, fmt.Errorf("invalid row length (first order) duration string: %q: %s", chunks[1], err)
+		return Retention{}, fmt.Errorf("invalid row length (first order) duration string: %q: %w", chunks[1], err)
 	}
 	// set length of each row in milliseconds, unless we aren't using millisecond time in OpenTSDB...then use seconds
 	rowLength := rowLengthDuration.Milliseconds()

app/vmctl/prometheus.go

@@ -46,7 +46,7 @@ type prometheusProcessor struct {
 func (pp *prometheusProcessor) run(ctx context.Context) error {
 	blocks, err := pp.cl.Explore()
 	if err != nil {
-		return fmt.Errorf("explore failed: %s", err)
+		return fmt.Errorf("explore failed: %w", err)
 	}
 	if len(blocks) < 1 {
 		return fmt.Errorf("found no blocks to import")
@@ -57,7 +57,7 @@ func (pp *prometheusProcessor) run(ctx context.Context) error {
 	}
 
 	if err := pp.processBlocks(ctx, blocks); err != nil {
-		return fmt.Errorf("migration failed: %s", err)
+		return fmt.Errorf("migration failed: %w", err)
 	}
 
 	log.Println("Import finished!")
@@ -68,7 +68,7 @@ func (pp *prometheusProcessor) run(ctx context.Context) error {
 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)
+		return fmt.Errorf("failed to read block: %w", err)
 	}
 	defer func() {
 		if err := css.Close(); err != nil {
@@ -146,7 +146,7 @@ func (pp *prometheusProcessor) processBlocks(ctx context.Context, blocks []tsdb.
 			for br := range blockReadersCh {
 				if err := pp.do(ctx, br); err != nil {
 					promErrorsTotal.Inc()
-					errCh <- fmt.Errorf("cannot read block %q: %s", br.Meta().ULID, err)
+					errCh <- fmt.Errorf("cannot read block %q: %w", br.Meta().ULID, err)
 					return
 				}
 				if cb, ok := br.(io.Closer); ok {
@@ -164,11 +164,11 @@ func (pp *prometheusProcessor) processBlocks(ctx context.Context, blocks []tsdb.
 		select {
 		case promErr := <-errCh:
 			close(blockReadersCh)
-			return fmt.Errorf("prometheus error: %s", promErr)
+			return fmt.Errorf("prometheus error: %w", promErr)
 		case vmErr := <-pp.im.Errors():
 			close(blockReadersCh)
 			promErrorsTotal.Inc()
-			return fmt.Errorf("import process failed: %s", wrapErr(vmErr, pp.isVerbose))
+			return fmt.Errorf("import process failed: %w", wrapErr(vmErr, pp.isVerbose))
 		case blockReadersCh <- br:
 		}
 	}
@@ -182,11 +182,11 @@ func (pp *prometheusProcessor) processBlocks(ctx context.Context, blocks []tsdb.
 	for vmErr := range pp.im.Errors() {
 		if vmErr.Err != nil {
 			promErrorsTotal.Inc()
-			return fmt.Errorf("import process failed: %s", wrapErr(vmErr, pp.isVerbose))
+			return fmt.Errorf("import process failed: %w", wrapErr(vmErr, pp.isVerbose))
 		}
 	}
 	for err := range errCh {
-		return fmt.Errorf("import process failed: %s", err)
+		return fmt.Errorf("import process failed: %w", err)
 	}
 
 	return nil

app/vmctl/prometheus/prometheus.go

@@ -59,12 +59,12 @@ func (f filter) inRange(minV, maxV int64) bool {
 func NewClient(cfg Config) (*Client, error) {
 	db, err := tsdb.OpenDBReadOnly(cfg.Snapshot, cfg.TemporaryDir, nil)
 	if err != nil {
-		return nil, fmt.Errorf("failed to open snapshot %q: %s", cfg.Snapshot, err)
+		return nil, fmt.Errorf("failed to open snapshot %q: %w", cfg.Snapshot, err)
 	}
 	c := &Client{DBReadOnly: db}
 	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)
+		return nil, fmt.Errorf("failed to parse time in filter: %w", err)
 	}
 	c.filter = filter{
 		min:        timeMin,
@@ -83,7 +83,7 @@ func NewClient(cfg Config) (*Client, error) {
 func (c *Client) Explore() ([]tsdb.BlockReader, error) {
 	blocks, err := c.Blocks()
 	if err != nil {
-		return nil, fmt.Errorf("failed to fetch blocks: %s", err)
+		return nil, fmt.Errorf("failed to fetch blocks: %w", err)
 	}
 	s := &vmctlutil.Stats{
 		Filtered: c.filter.min != 0 || c.filter.max != 0 || c.filter.label != "",
@@ -142,14 +142,14 @@ func parseTime(start, end string) (int64, int64, error) {
 	if start != "" {
 		v, err := time.Parse(time.RFC3339, start)
 		if err != nil {
-			return 0, 0, fmt.Errorf("failed to parse %q: %s", start, err)
+			return 0, 0, fmt.Errorf("failed to parse %q: %w", start, err)
 		}
 		s = v.UnixNano() / int64(time.Millisecond)
 	}
 	if end != "" {
 		v, err := time.Parse(time.RFC3339, end)
 		if err != nil {
-			return 0, 0, fmt.Errorf("failed to parse %q: %s", end, err)
+			return 0, 0, fmt.Errorf("failed to parse %q: %w", end, err)
 		}
 		e = v.UnixNano() / int64(time.Millisecond)
 	}

app/vmctl/remoteread.go

@@ -44,7 +44,7 @@ func (rrp *remoteReadProcessor) run(ctx context.Context) error {
 
 	ranges, err := stepper.SplitDateRange(*rrp.filter.timeStart, *rrp.filter.timeEnd, rrp.filter.chunk, rrp.filter.timeReverse)
 	if err != nil {
-		return fmt.Errorf("failed to create date ranges for the given time filters: %v", err)
+		return fmt.Errorf("failed to create date ranges for the given time filters: %w", err)
 	}
 
 	question := fmt.Sprintf("Selected time range %q - %q will be split into %d ranges according to %q step. Continue?",
@@ -74,7 +74,7 @@ func (rrp *remoteReadProcessor) run(ctx context.Context) error {
 			for r := range rangeC {
 				if err := rrp.do(ctx, r); err != nil {
 					remoteReadErrorsTotal.Inc()
-					errCh <- fmt.Errorf("request failed for: %s", err)
+					errCh <- fmt.Errorf("request failed for: %w", err)
 					return
 				}
 				remoteReadRangesProcessed.Inc()
@@ -86,10 +86,10 @@ func (rrp *remoteReadProcessor) run(ctx context.Context) error {
 	for _, r := range ranges {
 		select {
 		case infErr := <-errCh:
-			return fmt.Errorf("remote read error: %s", infErr)
+			return fmt.Errorf("remote read error: %w", infErr)
 		case vmErr := <-rrp.dst.Errors():
 			remoteReadErrorsTotal.Inc()
-			return fmt.Errorf("import process failed: %s", wrapErr(vmErr, rrp.isVerbose))
+			return fmt.Errorf("import process failed: %w", wrapErr(vmErr, rrp.isVerbose))
 		case rangeC <- &remoteread.Filter{
 			StartTimestampMs: r[0].UnixMilli(),
 			EndTimestampMs:   r[1].UnixMilli(),
@@ -105,11 +105,11 @@ func (rrp *remoteReadProcessor) run(ctx context.Context) error {
 	for vmErr := range rrp.dst.Errors() {
 		if vmErr.Err != nil {
 			remoteReadErrorsTotal.Inc()
-			return fmt.Errorf("import process failed: %s", wrapErr(vmErr, rrp.isVerbose))
+			return fmt.Errorf("import process failed: %w", wrapErr(vmErr, rrp.isVerbose))
 		}
 	}
 	for err := range errCh {
-		return fmt.Errorf("import process failed: %s", err)
+		return fmt.Errorf("import process failed: %w", err)
 	}
 
 	return nil
@@ -119,7 +119,7 @@ func (rrp *remoteReadProcessor) do(ctx context.Context, filter *remoteread.Filte
 	return rrp.src.Read(ctx, filter, func(series *vm.TimeSeries) error {
 		if err := rrp.dst.Input(series); err != nil {
 			return fmt.Errorf(
-				"failed to read data for time range start: %d, end: %d, %s",
+				"failed to read data for time range start: %d, end: %d: %w",
 				filter.StartTimestampMs, filter.EndTimestampMs, err)
 		}
 		return nil

app/vmctl/remoteread/remoteread.go

@@ -157,7 +157,7 @@ func (c *Client) Read(ctx context.Context, filter *Filter, streamCb StreamCallba
 		if errors.Is(err, context.Canceled) {
 			return fmt.Errorf("fetch request has ben cancelled")
 		}
-		return fmt.Errorf("error while fetching data from remote storage: %s", err)
+		return fmt.Errorf("error while fetching data from remote storage: %w", err)
 	}
 	return nil
 }

app/vmctl/thanos/client.go

@@ -52,7 +52,7 @@ func (f filter) inRange(minV, maxV int64) bool {
 func NewClient(cfg Config) (*Client, error) {
 	minTime, maxTime, err := parseTime(cfg.Filter.TimeMin, cfg.Filter.TimeMax)
 	if err != nil {
-		return nil, fmt.Errorf("failed to parse time in filter: %s", err)
+		return nil, fmt.Errorf("failed to parse time in filter: %w", err)
 	}
 	return &Client{
 		snapshotPath: cfg.Snapshot,
@@ -183,14 +183,14 @@ func parseTime(start, end string) (int64, int64, error) {
 	if start != "" {
 		v, err := time.Parse(time.RFC3339, start)
 		if err != nil {
-			return 0, 0, fmt.Errorf("failed to parse %q: %s", start, err)
+			return 0, 0, fmt.Errorf("failed to parse %q: %w", start, err)
 		}
 		s = v.UnixNano() / int64(time.Millisecond)
 	}
 	if end != "" {
 		v, err := time.Parse(time.RFC3339, end)
 		if err != nil {
-			return 0, 0, fmt.Errorf("failed to parse %q: %s", end, err)
+			return 0, 0, fmt.Errorf("failed to parse %q: %w", end, err)
 		}
 		e = v.UnixNano() / int64(time.Millisecond)
 	}

app/vmctl/thanos_processor.go

@@ -36,7 +36,7 @@ func (tp *thanosProcessor) run(ctx context.Context) error {
 	// Use the first aggregate type to explore blocks (block list is the same for all types)
 	blocks, err := tp.cl.Explore(tp.aggrTypes[0])
 	if err != nil {
-		return fmt.Errorf("explore failed: %s", err)
+		return fmt.Errorf("explore failed: %w", err)
 	}
 	if len(blocks) < 1 {
 		return fmt.Errorf("found no blocks to import")
@@ -84,7 +84,7 @@ func (tp *thanosProcessor) run(ctx context.Context) error {
 		log.Println("Processing raw blocks (resolution=0)...")
 		stats, err := tp.processBlocks(rawBlocks, thanos.AggrTypeNone, bar)
 		if err != nil {
-			return fmt.Errorf("migration failed for raw blocks: %s", err)
+			return fmt.Errorf("migration failed for raw blocks: %w", err)
 		}
 		phases = append(phases, phaseStats{
 			name:    "raw",
@@ -108,7 +108,7 @@ func (tp *thanosProcessor) run(ctx context.Context) error {
 
 		aggrBlocks, err := tp.cl.Explore(aggrType)
 		if err != nil {
-			return fmt.Errorf("explore failed for aggr type %s: %s", aggrType, err)
+			return fmt.Errorf("explore failed for aggr type %s: %w", aggrType, err)
 		}
 
 		var downsampledOnly []thanos.BlockInfo
@@ -128,7 +128,7 @@ func (tp *thanosProcessor) run(ctx context.Context) error {
 		stats, err := tp.processBlocks(downsampledOnly, aggrType, bar)
 		thanos.CloseBlocks(aggrBlocks)
 		if err != nil {
-			return fmt.Errorf("migration failed for aggr type %s: %s", aggrType, err)
+			return fmt.Errorf("migration failed for aggr type %s: %w", aggrType, err)
 		}
 		phases = append(phases, phaseStats{
 			name:    aggrType.String(),
@@ -153,7 +153,7 @@ func (tp *thanosProcessor) run(ctx context.Context) error {
 	for vmErr := range tp.im.Errors() {
 		if vmErr.Err != nil {
 			thanosErrorsTotal.Inc()
-			return fmt.Errorf("import process failed: %s", wrapErr(vmErr, tp.isVerbose))
+			return fmt.Errorf("import process failed: %w", wrapErr(vmErr, tp.isVerbose))
 		}
 	}
 
@@ -184,7 +184,7 @@ func (tp *thanosProcessor) processBlocks(blocks []thanos.BlockInfo, aggrType tha
 				seriesCount, samplesCount, err := tp.do(bi, aggrType)
 				if err != nil {
 					thanosErrorsTotal.Inc()
-					errCh <- fmt.Errorf("read failed for block %q with aggr %s: %s", bi.Block.Meta().ULID, aggrType, err)
+					errCh <- fmt.Errorf("read failed for block %q with aggr %s: %w", bi.Block.Meta().ULID, aggrType, err)
 					return
 				}
 
@@ -209,12 +209,12 @@ func (tp *thanosProcessor) processBlocks(blocks []thanos.BlockInfo, aggrType tha
 		case thanosErr := <-errCh:
 			close(blockReadersCh)
 			wg.Wait()
-			return processBlocksStats{}, fmt.Errorf("thanos error: %s", thanosErr)
+			return processBlocksStats{}, fmt.Errorf("thanos error: %w", thanosErr)
 		case vmErr := <-tp.im.Errors():
 			close(blockReadersCh)
 			wg.Wait()
 			thanosErrorsTotal.Inc()
-			return processBlocksStats{}, fmt.Errorf("import process failed: %s", wrapErr(vmErr, tp.isVerbose))
+			return processBlocksStats{}, fmt.Errorf("import process failed: %w", wrapErr(vmErr, tp.isVerbose))
 		case blockReadersCh <- bi:
 		}
 	}
@@ -223,7 +223,7 @@ func (tp *thanosProcessor) processBlocks(blocks []thanos.BlockInfo, aggrType tha
 	wg.Wait()
 	close(errCh)
 	for err := range errCh {
-		return processBlocksStats{}, fmt.Errorf("import process failed: %s", err)
+		return processBlocksStats{}, fmt.Errorf("import process failed: %w", err)
 	}
 
 	return processBlocksStats{
@@ -236,7 +236,7 @@ func (tp *thanosProcessor) processBlocks(blocks []thanos.BlockInfo, aggrType tha
 func (tp *thanosProcessor) do(bi thanos.BlockInfo, aggrType thanos.AggrType) (uint64, uint64, error) {
 	ss, err := tp.cl.Read(bi)
 	if err != nil {
-		return 0, 0, fmt.Errorf("failed to read block: %s", err)
+		return 0, 0, fmt.Errorf("failed to read block: %w", err)
 	}
 	defer ss.Close() // Ensure querier is closed even on early returns
 

app/vmctl/utils.go

@@ -74,9 +74,9 @@ func wrapErr(vmErr *vm.ImportError, verbose bool) error {
 		verboseMsg = "(enable `--verbose` output to get more details)"
 	}
 	if vmErr.Err == nil {
-		return fmt.Errorf("%s\n\tLatest delivered batch for timestamps range %d - %d %s\n%s",
+		return fmt.Errorf("%w\n\tLatest delivered batch for timestamps range %d - %d %s\n%s",
 			vmErr.Err, minTS, maxTS, verboseMsg, errTS)
 	}
-	return fmt.Errorf("%s\n\tImporting batch failed for timestamps range %d - %d %s\n%s",
+	return fmt.Errorf("%w\n\tImporting batch failed for timestamps range %d - %d %s\n%s",
 		vmErr.Err, minTS, maxTS, verboseMsg, errTS)
 }

app/vmctl/vm/vm.go

@@ -12,6 +12,7 @@ import (
 	"sync"
 	"time"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/auth"
 	"github.com/VictoriaMetrics/metrics"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/backoff"
@@ -27,6 +28,8 @@ type Config struct {
 	//   --httpListenAddr value for single node version
 	//   --httpListenAddr value of vmselect  component for cluster version
 	Addr string
+
+	AuthCfg *auth.Config
 	// Transport allows specifying custom http.Transport
 	Transport *http.Transport
 	// Concurrency defines number of worker
@@ -40,10 +43,6 @@ type Config struct {
 	// BatchSize defines how many samples
 	// importer collects before sending the import request
 	BatchSize int
-	// User name for basic auth
-	User string
-	// Password for basic auth
-	Password string
 	// SignificantFigures defines the number of significant figures to leave
 	// in metric values before importing.
 	// Zero value saves all the significant decimal places
@@ -65,11 +64,10 @@ type Config struct {
 // see https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-import-time-series-data
 type Importer struct {
 	addr       string
+	authCfg    *auth.Config
 	client     *http.Client
 	importPath string
 	compress   bool
-	user       string
-	password   string
 
 	close  chan struct{}
 	input  chan *TimeSeries
@@ -148,8 +146,7 @@ func NewImporter(ctx context.Context, cfg Config) (*Importer, error) {
 		client:     client,
 		importPath: importPath,
 		compress:   cfg.Compress,
-		user:       cfg.User,
-		password:   cfg.Password,
+		authCfg:    cfg.AuthCfg,
 		rl:         limiter.NewLimiter(cfg.RateLimit),
 		close:      make(chan struct{}),
 		input:      make(chan *TimeSeries, cfg.Concurrency*4),
@@ -163,7 +160,7 @@ func NewImporter(ctx context.Context, cfg Config) (*Importer, error) {
 		importDuration:            metrics.GetOrCreateHistogram(`vmctl_importer_request_duration_seconds`),
 	}
 	if err := im.Ping(); err != nil {
-		return nil, fmt.Errorf("ping to %q failed: %s", addr, err)
+		return nil, fmt.Errorf("ping to %q failed: %w", addr, err)
 	}
 
 	if cfg.BatchSize < 1 {
@@ -289,7 +286,7 @@ func (im *Importer) flush(ctx context.Context, b []*TimeSeries) error {
 	retryableFunc := func() error { return im.Import(b) }
 	attempts, err := im.backoff.Retry(ctx, retryableFunc)
 	if err != nil {
-		return fmt.Errorf("import failed with %d retries: %s", attempts, err)
+		return fmt.Errorf("import failed with %d retries: %w", attempts, err)
 	}
 	im.s.Lock()
 	im.s.retries = attempts
@@ -302,10 +299,10 @@ func (im *Importer) Ping() error {
 	url := fmt.Sprintf("%s/health", im.addr)
 	req, err := http.NewRequest(http.MethodGet, url, nil)
 	if err != nil {
-		return fmt.Errorf("cannot create request to %q: %s", im.addr, err)
+		return fmt.Errorf("cannot create request to %q: %w", im.addr, err)
 	}
-	if im.user != "" {
-		req.SetBasicAuth(im.user, im.password)
+	if im.authCfg != nil {
+		im.authCfg.SetHeaders(req, true)
 	}
 	resp, err := im.client.Do(req)
 	if err != nil {
@@ -332,10 +329,10 @@ func (im *Importer) Import(tsBatch []*TimeSeries) error {
 	req, err := http.NewRequest(http.MethodPost, im.importPath, pr)
 	if err != nil {
 		im.importRequestsErrorsTotal.Inc()
-		return fmt.Errorf("cannot create request to %q: %s", im.addr, err)
+		return fmt.Errorf("cannot create request to %q: %w", im.addr, err)
 	}
-	if im.user != "" {
-		req.SetBasicAuth(im.user, im.password)
+	if im.authCfg != nil {
+		im.authCfg.SetHeaders(req, true)
 	}
 	if im.compress {
 		req.Header.Set("Content-Encoding", "gzip")
@@ -352,7 +349,7 @@ func (im *Importer) Import(tsBatch []*TimeSeries) error {
 		zw, err := gzip.NewWriterLevel(w, 1)
 		if err != nil {
 			im.importRequestsErrorsTotal.Inc()
-			return fmt.Errorf("unexpected error when creating gzip writer: %s", err)
+			return fmt.Errorf("unexpected error when creating gzip writer: %w", err)
 		}
 		w = zw
 	}
@@ -411,7 +408,7 @@ var ErrBadRequest = errors.New("bad request")
 func (im *Importer) do(req *http.Request) error {
 	resp, err := im.client.Do(req)
 	if err != nil {
-		return fmt.Errorf("unexpected error when performing request: %s", err)
+		return fmt.Errorf("unexpected error when performing request: %w", err)
 	}
 	defer func() {
 		_ = resp.Body.Close()
@@ -419,7 +416,7 @@ func (im *Importer) do(req *http.Request) error {
 	if resp.StatusCode != http.StatusNoContent {
 		body, err := io.ReadAll(resp.Body)
 		if err != nil {
-			return fmt.Errorf("failed to read response body for status code %d: %s", resp.StatusCode, err)
+			return fmt.Errorf("failed to read response body for status code %d: %w", resp.StatusCode, err)
 		}
 		if resp.StatusCode == http.StatusBadRequest {
 			return fmt.Errorf("%w: unexpected response code %d: %s", ErrBadRequest, resp.StatusCode, string(body))

app/vmctl/vm_native.go

@@ -55,14 +55,14 @@ func (p *vmNativeProcessor) run(ctx context.Context) error {
 
 	start, err := vmctlutil.ParseTime(p.filter.TimeStart)
 	if err != nil {
-		return fmt.Errorf("failed to parse %s, provided: %s, error: %w", vmNativeFilterTimeStart, p.filter.TimeStart, err)
+		return fmt.Errorf("failed to parse %s, provided: %s: %w", vmNativeFilterTimeStart, p.filter.TimeStart, err)
 	}
 
 	end := time.Now().In(start.Location())
 	if p.filter.TimeEnd != "" {
 		end, err = vmctlutil.ParseTime(p.filter.TimeEnd)
 		if err != nil {
-			return fmt.Errorf("failed to parse %s, provided: %s, error: %w", vmNativeFilterTimeEnd, p.filter.TimeEnd, err)
+			return fmt.Errorf("failed to parse %s, provided: %s: %w", vmNativeFilterTimeEnd, p.filter.TimeEnd, err)
 		}
 	}
 
@@ -91,7 +91,7 @@ func (p *vmNativeProcessor) run(ctx context.Context) error {
 		err := p.runBackfilling(ctx, tenantID, ranges)
 		if err != nil {
 			migrationErrorsTotal.Inc()
-			return fmt.Errorf("migration failed: %s", err)
+			return fmt.Errorf("migration failed: %w", err)
 		}
 
 		if p.interCluster {
@@ -157,7 +157,7 @@ func (p *vmNativeProcessor) runSingle(ctx context.Context, f native.Filter, srcU
 			}
 		default:
 		}
-		return fmt.Errorf("failed to write into %q: %s", p.dst.Addr, err)
+		return fmt.Errorf("failed to write into %q: %w", p.dst.Addr, err)
 	}
 
 	p.s.Lock()
@@ -184,7 +184,7 @@ func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string,
 
 	importAddr, err := vm.AddExtraLabelsToImportPath(importAddr, p.dst.ExtraLabels)
 	if err != nil {
-		return fmt.Errorf("failed to add labels to import path: %s", err)
+		return fmt.Errorf("failed to add labels to import path: %w", err)
 	}
 	dstURL := fmt.Sprintf("%s/%s", p.dst.Addr, importAddr)
 
@@ -222,7 +222,7 @@ func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string,
 		format = fmt.Sprintf(nativeWithBackoffTpl, barPrefix)
 		metricsMap, err = p.explore(ctx, p.src, tenantID, ranges)
 		if err != nil {
-			return fmt.Errorf("failed to explore metric names: %s", err)
+			return fmt.Errorf("failed to explore metric names: %w", err)
 		}
 		if len(metricsMap) == 0 {
 			errMsg := "no metrics found"
@@ -295,7 +295,7 @@ func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string,
 			case <-ctx.Done():
 				return fmt.Errorf("context canceled")
 			case infErr := <-errCh:
-				return fmt.Errorf("export/import error: %s", infErr)
+				return fmt.Errorf("export/import error: %w", infErr)
 			case filterCh <- native.Filter{
 				Match:     match,
 				TimeStart: times[0].Format(time.RFC3339),
@@ -313,7 +313,7 @@ func (p *vmNativeProcessor) runBackfilling(ctx context.Context, tenantID string,
 	close(errCh)
 
 	for err := range errCh {
-		return fmt.Errorf("import process failed: %s", err)
+		return fmt.Errorf("import process failed: %w", err)
 	}
 
 	return nil
@@ -405,7 +405,16 @@ func buildMatchWithFilter(filter string, metricName string) (string, error) {
 			if len(tf.Key) == 0 {
 				continue
 			}
-			a = append(a, tf.String())
+			switch {
+			case tf.IsNegative && tf.IsRegexp:
+				a = append(a, fmt.Sprintf("%s!~%q", tf.Key, tf.Value))
+			case tf.IsNegative:
+				a = append(a, fmt.Sprintf("%s!=%q", tf.Key, tf.Value))
+			case tf.IsRegexp:
+				a = append(a, fmt.Sprintf("%s=~%q", tf.Key, tf.Value))
+			default:
+				a = append(a, fmt.Sprintf("%s=%q", tf.Key, tf.Value))
+			}
 		}
 		a = append(a, nameFilter)
 		filters = append(filters, strings.Join(a, ","))

app/vmselect/main.go

@@ -6,8 +6,6 @@ import (
 	"flag"
 	"fmt"
 	"net/http"
-	nethttputil "net/http/httputil"
-	"net/url"
 	"strings"
 	"time"
 
@@ -29,6 +27,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/querytracer"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timerpool"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/vmalertproxy"
 )
 
 var (
@@ -38,7 +37,10 @@ var (
 	resetCacheAuthKey    = flagutil.NewPassword("search.resetCacheAuthKey", "Optional authKey for resetting rollup cache via /internal/resetRollupResultCache call. It could be passed via authKey query arg. It overrides -httpAuth.*")
 	logSlowQueryDuration = flag.Duration("search.logSlowQueryDuration", 5*time.Second, "Log queries with execution time exceeding this value. Zero disables slow query logging. "+
 		"See also -search.logQueryMemoryUsage")
-	vmalertProxyURL = flag.String("vmalert.proxyURL", "", "Optional URL for proxying requests to vmalert. For example, if -vmalert.proxyURL=http://vmalert:8880 , then alerting API requests such as /api/v1/rules from Grafana will be proxied to http://vmalert:8880/api/v1/rules")
+
+	vmalertProxyURL = flag.String("vmalert.proxyURL", "", "Optional URL for proxying requests to vmalert. For example, if -vmalert.proxyURL=http://vmalert:8880 , "+
+		"then alerting API requests such as /api/v1/rules from Grafana will be proxied to http://vmalert:8880/api/v1/rules . "+
+		"See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmalert")
 )
 
 var slowQueries = metrics.NewCounter(`vm_slow_queries_total`)
@@ -55,8 +57,8 @@ func Init(vmselectMaxConcurrentRequests int, vmselectMaxQueueDuration time.Durat
 	concurrencyLimitCh = make(chan struct{}, maxConcurrentRequests)
 
 	initVMUIConfig()
-	initVMAlertProxy()
 
+	vmalertproxy.Init(*vmalertProxyURL)
 	flagutil.RegisterSecretFlag("vmalert.proxyURL")
 }
 
@@ -514,10 +516,11 @@ func handleStaticAndSimpleRequests(w http.ResponseWriter, r *http.Request, path
 		if len(*vmalertProxyURL) == 0 {
 			w.WriteHeader(http.StatusBadRequest)
 			w.Header().Set("Content-Type", "application/json")
-			fmt.Fprintf(w, "%s", `{"status":"error","msg":"for accessing vmalert flag '-vmalert.proxyURL' must be configured"}`)
+			fmt.Fprintf(w, "%s", `{"status":"error","msg":"the '-vmalert.proxyURL' command-line must be configured; `+
+				`see https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmalert"}`)
 			return true
 		}
-		proxyVMAlertRequests(w, r, path)
+		vmalertproxy.HandleRequest(w, r, path)
 		return true
 	}
 
@@ -555,7 +558,7 @@ func handleStaticAndSimpleRequests(w http.ResponseWriter, r *http.Request, path
 	case "/api/v1/rules", "/rules":
 		rulesRequests.Inc()
 		if len(*vmalertProxyURL) > 0 {
-			proxyVMAlertRequests(w, r, path)
+			vmalertproxy.HandleRequest(w, r, path)
 			return true
 		}
 		// Return dumb placeholder for https://prometheus.io/docs/prometheus/latest/querying/api/#rules
@@ -565,7 +568,7 @@ func handleStaticAndSimpleRequests(w http.ResponseWriter, r *http.Request, path
 	case "/api/v1/alerts", "/alerts":
 		alertsRequests.Inc()
 		if len(*vmalertProxyURL) > 0 {
-			proxyVMAlertRequests(w, r, path)
+			vmalertproxy.HandleRequest(w, r, path)
 			return true
 		}
 		// Return dumb placeholder for https://prometheus.io/docs/prometheus/latest/querying/api/#alerts
@@ -575,7 +578,7 @@ func handleStaticAndSimpleRequests(w http.ResponseWriter, r *http.Request, path
 	case "/api/v1/notifiers", "/notifiers":
 		notifiersRequests.Inc()
 		if len(*vmalertProxyURL) > 0 {
-			proxyVMAlertRequests(w, r, path)
+			vmalertproxy.HandleRequest(w, r, path)
 			return true
 		}
 		w.Header().Set("Content-Type", "application/json")
@@ -722,48 +725,7 @@ var (
 	metricNamesStatsResetErrors   = metrics.NewCounter(`vm_http_request_errors_total{path="/api/v1/admin/status/metric_names_stats/reset"}`)
 )
 
-func proxyVMAlertRequests(w http.ResponseWriter, r *http.Request, path string) {
-	defer func() {
-		err := recover()
-		if err == nil || err == http.ErrAbortHandler {
-			// Suppress http.ErrAbortHandler panic.
-			// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1353
-			return
-		}
-		// Forward other panics to the caller.
-		panic(err)
-	}()
-	req := r.Clone(r.Context())
-	req.URL.Path = strings.TrimPrefix(path, "prometheus")
-	req.Host = vmalertProxyHost
-
-	if strings.HasPrefix(r.Header.Get(`User-Agent`), `Grafana`) {
-		// Grafana currently supports only Prometheus-style alerts. If other alert types
-		// (e.g. logs or traces) are returned, it may fail with "Error loading alerts".
-		//
-		// Grafana queries the vmalert API directly, bypassing the VictoriaMetrics datasource,
-		// so query params (such as datasource_type) cannot be enforced on the Grafana side.
-		//
-		// To ensure compatibility, we detect Grafana requests via the User-Agent and enforce
-		// `datasource_type=prometheus`.
-		//
-		// See:
-		// - https://github.com/VictoriaMetrics/victoriametrics-datasource/issues/329#issuecomment-3847585443
-		// - https://github.com/VictoriaMetrics/victoriametrics-datasource/issues/59
-		q := req.URL.Query()
-		q.Set("datasource_type", "prometheus")
-		req.URL.RawQuery = q.Encode()
-		req.RequestURI = ""
-	}
-
-	vmalertProxy.ServeHTTP(w, req)
-}
-
-var (
-	vmalertProxyHost string
-	vmalertProxy     *nethttputil.ReverseProxy
-	vmuiConfig       string
-)
+var vmuiConfig string
 
 func initVMUIConfig() {
 	var cfg struct {
@@ -795,16 +757,3 @@ func initVMUIConfig() {
 	}
 	vmuiConfig = string(data)
 }
-
-// initVMAlertProxy must be called after flag.Parse(), since it uses command-line flags.
-func initVMAlertProxy() {
-	if len(*vmalertProxyURL) == 0 {
-		return
-	}
-	proxyURL, err := url.Parse(*vmalertProxyURL)
-	if err != nil {
-		logger.Fatalf("cannot parse -vmalert.proxyURL=%q: %s", *vmalertProxyURL, err)
-	}
-	vmalertProxyHost = proxyURL.Host
-	vmalertProxy = nethttputil.NewSingleHostReverseProxy(proxyURL)
-}

app/vmselect/prometheus/metadata_response.qtpl

@@ -15,7 +15,7 @@ See https://prometheus.io/docs/prometheus/latest/querying/api/#querying-metric-m
 			currentItem := 0
 		 %}
 		{% for _, row := range result %}
-			"{%s string(row.MetricFamilyName) %}": [
+			{%q= string(row.MetricFamilyName) %}: [
 					{
 						"type": {%q= row.Type.String() %},
             {% if len(row.Unit) > 0 -%}

app/vmselect/prometheus/metadata_response.qtpl.go

@@ -35,12 +35,10 @@ func StreamMetadataResponse(qw422016 *qt422016.Writer, result []*metricsmetadata
 
 //line app/vmselect/prometheus/metadata_response.qtpl:17
 	for _, row := range result {
-//line app/vmselect/prometheus/metadata_response.qtpl:17
-		qw422016.N().S(`"`)
 //line app/vmselect/prometheus/metadata_response.qtpl:18
-		qw422016.E().S(string(row.MetricFamilyName))
+		qw422016.N().Q(string(row.MetricFamilyName))
 //line app/vmselect/prometheus/metadata_response.qtpl:18
-		qw422016.N().S(`": [{"type":`)
+		qw422016.N().S(`: [{"type":`)
 //line app/vmselect/prometheus/metadata_response.qtpl:20
 		qw422016.N().Q(row.Type.String())
 //line app/vmselect/prometheus/metadata_response.qtpl:20

app/vmselect/prometheus/prometheus.go

@@ -28,6 +28,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httputil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/querytracer"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
@@ -525,6 +526,7 @@ func DeleteHandler(startTime time.Time, r *http.Request) error {
 	if deletedCount > 0 {
 		promql.ResetRollupResultCache()
 	}
+	logger.Infof("/api/v1/admin/tsdb/delete_series has been called for %q. Deleted %d series.", sq.FiltersString(), deletedCount)
 	return nil
 }
 

app/vmselect/vmui/assets/rolldown-runtime-COnpUsM8.js

@@ -1 +0,0 @@
-var e=Object.create,t=Object.defineProperty,n=Object.getOwnPropertyDescriptor,r=Object.getOwnPropertyNames,i=Object.getPrototypeOf,a=Object.prototype.hasOwnProperty,o=(e,t)=>()=>(e&&(t=e(e=0)),t),s=(e,t)=>()=>(t||e((t={exports:{}}).exports,t),t.exports),c=(e,n)=>{let r={};for(var i in e)t(r,i,{get:e[i],enumerable:!0});return n||t(r,Symbol.toStringTag,{value:`Module`}),r},l=(e,i,o,s)=>{if(i&&typeof i==`object`||typeof i==`function`)for(var c=r(i),l=0,u=c.length,d;l<u;l++)d=c[l],!a.call(e,d)&&d!==o&&t(e,d,{get:(e=>i[e]).bind(null,d),enumerable:!(s=n(i,d))||s.enumerable});return e},u=(n,r,a)=>(a=n==null?{}:e(i(n)),l(r||!n||!n.__esModule?t(a,`default`,{value:n,enumerable:!0}):a,n)),d=e=>a.call(e,`module.exports`)?e[`module.exports`]:l(t({},`__esModule`,{value:!0}),e);export{u as a,d as i,o as n,c as r,s as t};

app/vmselect/vmui/assets/rolldown-runtime-Cyuzqnbw.js

@@ -0,0 +1 @@
+var e=Object.create,t=Object.defineProperty,n=Object.getOwnPropertyDescriptor,r=Object.getOwnPropertyNames,i=Object.getPrototypeOf,a=Object.prototype.hasOwnProperty,o=(e,t)=>()=>(e&&(t=e(e=0)),t),s=(e,t)=>()=>(t||(e((t={exports:{}}).exports,t),e=null),t.exports),c=(e,n)=>{let r={};for(var i in e)t(r,i,{get:e[i],enumerable:!0});return n||t(r,Symbol.toStringTag,{value:`Module`}),r},l=(e,i,o,s)=>{if(i&&typeof i==`object`||typeof i==`function`)for(var c=r(i),l=0,u=c.length,d;l<u;l++)d=c[l],!a.call(e,d)&&d!==o&&t(e,d,{get:(e=>i[e]).bind(null,d),enumerable:!(s=n(i,d))||s.enumerable});return e},u=(n,r,a)=>(a=n==null?{}:e(i(n)),l(r||!n||!n.__esModule?t(a,`default`,{value:n,enumerable:!0}):a,n)),d=e=>a.call(e,`module.exports`)?e[`module.exports`]:l(t({},`__esModule`,{value:!0}),e);export{u as a,d as i,o as n,c as r,s as t};

app/vmselect/vmui/index.html

@@ -37,9 +37,9 @@
   <meta property="og:title" content="UI for VictoriaMetrics">
   <meta property="og:url" content="https://victoriametrics.com/">
   <meta property="og:description" content="Explore and troubleshoot your VictoriaMetrics data">
-  <script type="module" crossorigin src="./assets/index-CoGukb-x.js"></script>
-  <link rel="modulepreload" crossorigin href="./assets/rolldown-runtime-COnpUsM8.js">
-  <link rel="modulepreload" crossorigin href="./assets/vendor-C8Kwp93_.js">
+  <script type="module" crossorigin src="./assets/index-CusQvJzs.js"></script>
+  <link rel="modulepreload" crossorigin href="./assets/rolldown-runtime-Cyuzqnbw.js">
+  <link rel="modulepreload" crossorigin href="./assets/vendor-B83wxFqK.js">
   <link rel="stylesheet" crossorigin href="./assets/vendor-CnsZ1jie.css">
   <link rel="stylesheet" crossorigin href="./assets/index-BBUnmLOr.css">
 </head>

app/vmstorage/main.go

@@ -10,8 +10,6 @@ import (
 	"strings"
 	"time"
 
-	"github.com/VictoriaMetrics/metrics"
-
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
@@ -23,6 +21,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/stringsutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/vminsertapi"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/vmselectapi"
+	"github.com/VictoriaMetrics/metrics"
 )
 
 var (
@@ -153,7 +152,7 @@ func Init(vmselectMaxConcurrentRequests int, resetCacheIfNeeded func(mrs []stora
 		LogNewSeries:                *logNewSeries,
 	}
 	strg := storage.MustOpenStorage(*storageDataPath, opts)
-	vmStorage = newVMStorageSingleNode(strg, vmselectMaxConcurrentRequests, resetCacheIfNeeded)
+	vmStorage = newVMStorage(strg, vmselectMaxConcurrentRequests, resetCacheIfNeeded)
 
 	var m storage.Metrics
 	strg.UpdateMetrics(&m)
@@ -175,15 +174,15 @@ func Init(vmselectMaxConcurrentRequests int, resetCacheIfNeeded func(mrs []stora
 	GetSearch = vmStorage.GetSearch
 	PutSearch = vmStorage.PutSearch
 	RequestHandler = vmStorage.requestHandler
-	DebugFlush = vmStorage.vms.s.DebugFlush
+	DebugFlush = vmStorage.s.DebugFlush
 }
 
 var storageMetrics *metrics.Set
 
 var (
-	// vmStorageSingleNode is an instance of vmstorage used by vminsert and
+	// vmStorage is an instance of vmstorage used by vminsert and
 	// vmselect for writing and reading data.
-	vmStorage      *VMStorageSingleNode
+	vmStorage      *VMStorage
 	VMInsertAPI    vminsertapi.API
 	VMSelectAPI    vmselectapi.API
 	GetSearch      func(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (*storage.Search, int, error)
@@ -209,15 +208,12 @@ func Stop() {
 	logger.Infof("the vmstorage has been stopped")
 }
 
-func (vmssn *VMStorageSingleNode) requestHandler(w http.ResponseWriter, r *http.Request) bool {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.requestHandler(w, r)
-}
-
 // requestHandler is a storage request handler.
 // TODO(@rtm0): Move to a separate file, request_handler.go
 func (vms *VMStorage) requestHandler(w http.ResponseWriter, r *http.Request) bool {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
 	path := r.URL.Path
 	if path == "/internal/force_merge" {
 		if !httpserver.CheckAuthFlag(w, r, forceMergeAuthKey) {
@@ -257,7 +253,7 @@ func (vms *VMStorage) requestHandler(w http.ResponseWriter, r *http.Request) boo
 			dealine, err = strconv.Atoi(deadlineStr)
 			if err != nil {
 				logger.Errorf("cannot parse `seconds` arg %q: %s", deadlineStr, err)
-				jsonResponseError(w, fmt.Errorf("cannot parse `seconds` arg %q: %s", deadlineStr, err))
+				jsonResponseError(w, fmt.Errorf("cannot parse `seconds` arg %q: %w", deadlineStr, err))
 				return true
 			}
 		}
@@ -361,15 +357,11 @@ var (
 	snapshotsDeleteAllErrorsTotal = metrics.NewCounter(`vm_http_request_errors_total{path="/snapshot/delete_all"}`)
 )
 
-// TODO(@rtm0): Move to metrics.go.
-func (vmssn *VMStorageSingleNode) writeStorageMetrics(w io.Writer) {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	vmssn.vms.writeStorageMetrics(w)
-}
-
 // TODO(@rtm0): Move to metrics.go.
 func (vms *VMStorage) writeStorageMetrics(w io.Writer) {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
 	strg := vms.s
 	var m storage.Metrics
 	strg.UpdateMetrics(&m)

app/vmstorage/vmstorage.go

@@ -1,6 +1,7 @@
 package vmstorage
 
 import (
+	"errors"
 	"flag"
 	"fmt"
 	"sync"
@@ -14,6 +15,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage/metricnamestats"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage/metricsmetadata"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/syncwg"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/timeutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/vmselectapi"
 )
@@ -34,7 +36,7 @@ var (
 // newVMStorage creates a new instance of of VMStorage.
 //
 // The created VMStorage instance takes ownership of s.
-func newVMStorage(s *storage.Storage, vmselectMaxConcurrentRequests int) *VMStorage {
+func newVMStorage(s *storage.Storage, vmselectMaxConcurrentRequests int, resetCacheIfNeeded func(mrs []storage.MetricRow)) *VMStorage {
 	if err := encoding.CheckPrecisionBits(uint8(*precisionBits)); err != nil {
 		logger.Fatalf("invalid -precisionBits=%d: %s", *precisionBits, err)
 	}
@@ -49,6 +51,8 @@ func newVMStorage(s *storage.Storage, vmselectMaxConcurrentRequests int) *VMStor
 		maxUniqueTimeseries:           *maxUniqueTimeseries,
 		maxUniqueTimeSeriesCalculated: maxUniqueTimeseriesCalculated,
 		staleSnapshotsRemoverCh:       make(chan struct{}),
+		wg:                            syncwg.WaitGroup{},
+		resetCacheIfNeeded:            resetCacheIfNeeded,
 	}
 	vms.initStaleSnapshotsRemover()
 	return vms
@@ -78,6 +82,17 @@ type VMStorage struct {
 	maxUniqueTimeSeriesCalculated int
 	staleSnapshotsRemoverCh       chan struct{}
 	staleSnapshotsRemoverWG       sync.WaitGroup
+
+	// wg is used to wrap every storage call into wg.Add(1) ... wg.Done()
+	// for proper graceful shutdown when Stop is called.
+	//
+	// Use syncwg instead of sync, since Add is called from concurrent
+	// goroutines.
+	wg syncwg.WaitGroup
+
+	// resetCacheIfNeeded is a callback for automatic resetting of response
+	// cache if needed.
+	resetCacheIfNeeded func(mrs []storage.MetricRow)
 }
 
 func (vms *VMStorage) initStaleSnapshotsRemover() {
@@ -103,6 +118,7 @@ func (vms *VMStorage) initStaleSnapshotsRemover() {
 func (vms *VMStorage) Stop() {
 	close(vms.staleSnapshotsRemoverCh)
 	vms.staleSnapshotsRemoverWG.Wait()
+	vms.wg.WaitAndBlock()
 	vms.s.MustClose()
 }
 
@@ -111,6 +127,14 @@ func (vms *VMStorage) Stop() {
 // The caller should limit the number of concurrent calls to WriteRows() in
 // order to limit memory usage.
 func (vms *VMStorage) WriteRows(rows []storage.MetricRow) error {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
+	if vms.s.IsReadOnly() {
+		return errReadOnly
+	}
+	vms.resetCacheIfNeeded(rows)
+
 	vms.s.AddRows(rows, uint8(*precisionBits))
 	return nil
 }
@@ -120,26 +144,41 @@ func (vms *VMStorage) WriteRows(rows []storage.MetricRow) error {
 // The caller should limit the number of concurrent calls to WriteMetadata() in
 // order to limit memory usage.
 func (vms *VMStorage) WriteMetadata(rows []metricsmetadata.Row) error {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
+	if vms.s.IsReadOnly() {
+		return errReadOnly
+	}
 	vms.s.AddMetadataRows(rows)
 	return nil
 }
 
+var errReadOnly = errors.New("the storage is in read-only mode; check -storage.minFreeDiskSpaceBytes command-line flag value")
+
 // IsReadOnly returns true is the storage is in read-only mode.
 func (vms *VMStorage) IsReadOnly() bool {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
 	return vms.s.IsReadOnly()
 }
 
 func (vms *VMStorage) InitSearch(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (vmselectapi.BlockIterator, error) {
+	vms.wg.Add(1)
+
 	tr := sq.GetTimeRange()
 	maxMetrics := vms.getMaxMetrics(sq.MaxMetrics)
 	tfss, err := vms.setupTfss(qt, sq, tr, maxMetrics, deadline)
 	if err != nil {
+		vms.wg.Done()
 		return nil, err
 	}
 	if len(tfss) == 0 {
+		vms.wg.Done()
 		return nil, fmt.Errorf("missing tag filters")
 	}
 	bi := getBlockIterator()
+	bi.wgDone = vms.wg.Done
 	bi.sr.Init(qt, vms.s, tfss, tr, maxMetrics, deadline)
 	if err := bi.sr.Error(); err != nil {
 		bi.MustClose()
@@ -161,8 +200,9 @@ func (vms *VMStorage) getMaxMetrics(searchQueryLimit int) int {
 
 // blockIterator implements vmselectapi.BlockIterator
 type blockIterator struct {
-	sr storage.Search
-	mb storage.MetricBlock
+	sr     storage.Search
+	mb     storage.MetricBlock
+	wgDone func()
 }
 
 var blockIteratorsPool sync.Pool
@@ -171,6 +211,8 @@ func (bi *blockIterator) MustClose() {
 	bi.sr.MustClose()
 	bi.mb.MetricName = nil
 	bi.mb.Block.Reset()
+	bi.wgDone()
+	bi.wgDone = nil
 	blockIteratorsPool.Put(bi)
 }
 
@@ -197,8 +239,63 @@ func (bi *blockIterator) Error() error {
 	return bi.sr.Error()
 }
 
+// GetSearch sets up an instance of storage search and returns it to the caller
+// along with the max series count that the search can return.
+//
+// This method is not part of the vmselectapi.API and must only be used by
+// vmsingle HTTP handlers.
+//
+// Callers of this method must call PutSearch() once the search instance is not
+// needed anymore.
+func (vms *VMStorage) GetSearch(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (*storage.Search, int, error) {
+	vms.wg.Add(1)
+
+	tr := sq.GetTimeRange()
+	maxMetrics := vms.getMaxMetrics(sq.MaxMetrics)
+	tfss, err := vms.setupTfss(qt, sq, tr, maxMetrics, deadline)
+	if err != nil {
+		vms.wg.Done()
+		return nil, 0, err
+	}
+
+	sr := getSearch()
+	maxSeriesCount := sr.Init(qt, vms.s, tfss, tr, sq.MaxMetrics, deadline)
+	return sr, maxSeriesCount, nil
+}
+
+// PutSearch resets the search once it is not needed anymore and puts it aside
+// for future reuse.
+//
+// This method is not part of the vmselectapi.API and must only be used by
+// vmsingle HTTP handlers.
+//
+// The method must only be used on search instances that have been created with
+// GetSearch().
+func (vms *VMStorage) PutSearch(sr *storage.Search) {
+	putSearch(sr)
+	vms.wg.Done()
+}
+
+func getSearch() *storage.Search {
+	v := ssPool.Get()
+	if v == nil {
+		return &storage.Search{}
+	}
+	return v.(*storage.Search)
+}
+
+func putSearch(sr *storage.Search) {
+	sr.MustClose()
+	ssPool.Put(sr)
+}
+
+var ssPool sync.Pool
+
 // SearchMetricNames returns metric names for the given tfss on the given tr.
 func (vms *VMStorage) SearchMetricNames(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) ([]string, error) {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
 	tr := sq.GetTimeRange()
 	maxMetrics := sq.MaxMetrics
 	if maxMetrics <= 0 {
@@ -219,6 +316,9 @@ func (vms *VMStorage) SearchMetricNames(qt *querytracer.Tracer, sq *storage.Sear
 // SearchLabelValues searches for label values for the given labelName, tfss and
 // tr.
 func (vms *VMStorage) LabelValues(qt *querytracer.Tracer, sq *storage.SearchQuery, labelName string, maxLabelValues int, deadline uint64) ([]string, error) {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
 	tr := sq.GetTimeRange()
 	if maxLabelValues <= 0 || maxLabelValues > *maxTagValues {
 		maxLabelValues = *maxTagValues
@@ -244,6 +344,9 @@ func (vms *VMStorage) LabelValues(qt *querytracer.Tracer, sq *storage.SearchQuer
 // similar APIs.
 func (vms *VMStorage) TagValueSuffixes(qt *querytracer.Tracer, _, _ uint32, tr storage.TimeRange, tagKey, tagValuePrefix string, delimiter byte,
 	maxSuffixes int, deadline uint64) ([]string, error) {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
 	if maxSuffixes <= 0 || maxSuffixes > *maxTagValueSuffixesPerSearch {
 		maxSuffixes = *maxTagValueSuffixesPerSearch
 	}
@@ -260,6 +363,9 @@ func (vms *VMStorage) TagValueSuffixes(qt *querytracer.Tracer, _, _ uint32, tr s
 
 // SearchLabelNames searches for tag keys matching the given tfss on tr.
 func (vms *VMStorage) LabelNames(qt *querytracer.Tracer, sq *storage.SearchQuery, maxLabelNames int, deadline uint64) ([]string, error) {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
 	tr := sq.GetTimeRange()
 	if maxLabelNames <= 0 || maxLabelNames > *maxTagKeys {
 		maxLabelNames = *maxTagKeys
@@ -278,6 +384,8 @@ func (vms *VMStorage) LabelNames(qt *querytracer.Tracer, sq *storage.SearchQuery
 }
 
 func (vms *VMStorage) SeriesCount(_ *querytracer.Tracer, _, _ uint32, deadline uint64) (uint64, error) {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
 	return vms.s.GetSeriesCount(deadline)
 }
 
@@ -287,6 +395,9 @@ func (vms *VMStorage) Tenants(_ *querytracer.Tracer, _ storage.TimeRange, _ uint
 
 // GetTSDBStatus returns TSDB status for given filters on the given date.
 func (vms *VMStorage) TSDBStatus(qt *querytracer.Tracer, sq *storage.SearchQuery, focusLabel string, topN int, deadline uint64) (*storage.TSDBStatus, error) {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
 	tr := sq.GetTimeRange()
 	maxMetrics := sq.MaxMetrics
 	if maxMetrics <= 0 {
@@ -306,6 +417,9 @@ func (vms *VMStorage) TSDBStatus(qt *querytracer.Tracer, sq *storage.SearchQuery
 //
 // Returns the number of deleted series.
 func (vms *VMStorage) DeleteSeries(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (int, error) {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
 	tr := sq.GetTimeRange()
 	maxMetrics := sq.MaxMetrics
 	if maxMetrics <= 0 {
@@ -324,17 +438,26 @@ func (vms *VMStorage) DeleteSeries(qt *querytracer.Tracer, sq *storage.SearchQue
 }
 
 func (vms *VMStorage) RegisterMetricNames(qt *querytracer.Tracer, mrs []storage.MetricRow, _ uint64) error {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
 	vms.s.RegisterMetricNames(qt, mrs)
 	return nil
 }
 
 // GetMetricNamesUsageStats returns metric name usage stats.
 func (vms *VMStorage) GetMetricNamesUsageStats(qt *querytracer.Tracer, _ *storage.TenantToken, limit, le int, matchPattern string, _ uint64) (metricnamestats.StatsResult, error) {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
 	return vms.s.GetMetricNamesStats(qt, limit, le, matchPattern), nil
 }
 
 // ResetMetricNamesStats resets state for metric names usage tracker
 func (vms *VMStorage) ResetMetricNamesUsageStats(qt *querytracer.Tracer, _ uint64) error {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
+
 	vms.s.ResetMetricNamesStats(qt)
 	return nil
 }
@@ -371,6 +494,8 @@ func (vms *VMStorage) setupTfss(qt *querytracer.Tracer, sq *storage.SearchQuery,
 }
 
 func (vms *VMStorage) GetMetadataRecords(qt *querytracer.Tracer, _ *storage.TenantToken, limit int, metricName string, _ uint64) ([]*metricsmetadata.Row, error) {
+	vms.wg.Add(1)
+	defer vms.wg.Done()
 	return vms.s.GetMetadataRows(qt, limit, metricName), nil
 }
 

app/vmstorage/vmstorage_single_node.go

@@ -1,213 +0,0 @@
-package vmstorage
-
-import (
-	"errors"
-	"fmt"
-	"sync"
-
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/querytracer"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage/metricnamestats"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage/metricsmetadata"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/syncwg"
-	"github.com/VictoriaMetrics/VictoriaMetrics/lib/vmselectapi"
-)
-
-// newVMStorageSingleNode creates a new instance of of VMStorage for vmsingle.
-func newVMStorageSingleNode(s *storage.Storage, maxConcurrentRequests int, resetCacheIfNeeded func(mrs []storage.MetricRow)) *VMStorageSingleNode {
-	vms := newVMStorage(s, maxConcurrentRequests)
-	return &VMStorageSingleNode{
-		vms:                vms,
-		wg:                 syncwg.WaitGroup{},
-		resetCacheIfNeeded: resetCacheIfNeeded,
-	}
-}
-
-type VMStorageSingleNode struct {
-	vms *VMStorage
-
-	// wg is used to wrap every storage call into wg.Add(1) ... wg.Done()
-	// for proper graceful shutdown when Stop is called.
-	//
-	// Use syncwg instead of sync, since Add is called from concurrent
-	// goroutines.
-	wg syncwg.WaitGroup
-
-	// resetCacheIfNeeded is a callback for automatic resetting of response
-	// cache if needed.
-	resetCacheIfNeeded func(mrs []storage.MetricRow)
-}
-
-func (vmssn *VMStorageSingleNode) Stop() {
-	vmssn.wg.WaitAndBlock()
-	vmssn.vms.Stop()
-}
-
-// WriteRows writes metric rows to the storage.
-//
-// Returns an error if the storage is in read-only mode.
-//
-// The caller should limit the number of concurrent calls to WriteRows() in
-// order to limit memory usage.
-func (vmssn *VMStorageSingleNode) WriteRows(rows []storage.MetricRow) error {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-
-	if vmssn.vms.IsReadOnly() {
-		return errReadOnly
-	}
-	vmssn.resetCacheIfNeeded(rows)
-	return vmssn.vms.WriteRows(rows)
-}
-
-// WriteMetadata writes metrics metadata to storage.
-//
-// Returns an error if the storage is in read-only mode.
-//
-// The caller should limit the number of concurrent calls to WriteMetadata() in
-// order to limit memory usage.
-func (vmssn *VMStorageSingleNode) WriteMetadata(rows []metricsmetadata.Row) error {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-
-	if vmssn.vms.IsReadOnly() {
-		return errReadOnly
-	}
-	return vmssn.vms.WriteMetadata(rows)
-}
-
-var errReadOnly = errors.New("the storage is in read-only mode; check -storage.minFreeDiskSpaceBytes command-line flag value")
-
-func (vmssn *VMStorageSingleNode) IsReadOnly() bool {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.IsReadOnly()
-}
-
-func (vmssn *VMStorageSingleNode) InitSearch(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (vmselectapi.BlockIterator, error) {
-	return nil, fmt.Errorf("not implemented in vmsingle")
-}
-
-// GetSearch sets up an instance of storage search and returns it to the caller
-// along with the max series count that the search can return.
-//
-// This method is not part of the vmselectapi.API and must only be used by
-// vmsingle HTTP handlers.
-//
-// Callers of this method must call PutSearch() once the search instance is not
-// needed anymore.
-func (vmssn *VMStorageSingleNode) GetSearch(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (*storage.Search, int, error) {
-	vmssn.wg.Add(1)
-
-	tr := sq.GetTimeRange()
-	maxMetrics := vmssn.vms.getMaxMetrics(sq.MaxMetrics)
-	tfss, err := vmssn.vms.setupTfss(qt, sq, tr, maxMetrics, deadline)
-	if err != nil {
-		vmssn.wg.Done()
-		return nil, 0, err
-	}
-
-	sr := getSearch()
-	maxSeriesCount := sr.Init(qt, vmssn.vms.s, tfss, tr, sq.MaxMetrics, deadline)
-	return sr, maxSeriesCount, nil
-}
-
-// PutSearch resets the search once it is not needed anymore and puts it aside
-// for future reuse.
-//
-// This method is not part of the vmselectapi.API and must only be used by
-// vmsingle HTTP handlers.
-//
-// The method must only be used on search instances that have been created with
-// GetSearch().
-func (vmssn *VMStorageSingleNode) PutSearch(sr *storage.Search) {
-	putSearch(sr)
-	vmssn.wg.Done()
-}
-
-func getSearch() *storage.Search {
-	v := ssPool.Get()
-	if v == nil {
-		return &storage.Search{}
-	}
-	return v.(*storage.Search)
-}
-
-func putSearch(sr *storage.Search) {
-	sr.MustClose()
-	ssPool.Put(sr)
-}
-
-var ssPool sync.Pool
-
-func (vmssn *VMStorageSingleNode) SearchMetricNames(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) ([]string, error) {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.SearchMetricNames(qt, sq, deadline)
-}
-
-func (vmssn *VMStorageSingleNode) LabelValues(qt *querytracer.Tracer, sq *storage.SearchQuery, labelName string, maxLabelValues int, deadline uint64) ([]string, error) {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.LabelValues(qt, sq, labelName, maxLabelValues, deadline)
-}
-
-func (vmssn *VMStorageSingleNode) TagValueSuffixes(qt *querytracer.Tracer, accountID, projectID uint32, tr storage.TimeRange, tagKey, tagValuePrefix string, delimiter byte, maxSuffixes int, deadline uint64) ([]string, error) {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.TagValueSuffixes(qt, accountID, projectID, tr, tagKey, tagValuePrefix, delimiter, maxSuffixes, deadline)
-}
-
-func (vmssn *VMStorageSingleNode) LabelNames(qt *querytracer.Tracer, sq *storage.SearchQuery, maxLabelNames int, deadline uint64) ([]string, error) {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.LabelNames(qt, sq, maxLabelNames, deadline)
-}
-
-func (vmssn *VMStorageSingleNode) SeriesCount(qt *querytracer.Tracer, accountID, projectID uint32, deadline uint64) (uint64, error) {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.SeriesCount(qt, accountID, projectID, deadline)
-}
-
-func (vmssn *VMStorageSingleNode) Tenants(qt *querytracer.Tracer, tr storage.TimeRange, deadline uint64) ([]string, error) {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.Tenants(qt, tr, deadline)
-}
-
-func (vmssn *VMStorageSingleNode) TSDBStatus(qt *querytracer.Tracer, sq *storage.SearchQuery, focusLabel string, topN int, deadline uint64) (*storage.TSDBStatus, error) {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.TSDBStatus(qt, sq, focusLabel, topN, deadline)
-}
-
-func (vmssn *VMStorageSingleNode) DeleteSeries(qt *querytracer.Tracer, sq *storage.SearchQuery, deadline uint64) (int, error) {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.DeleteSeries(qt, sq, deadline)
-}
-
-func (vmssn *VMStorageSingleNode) RegisterMetricNames(qt *querytracer.Tracer, mrs []storage.MetricRow, deadline uint64) error {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.RegisterMetricNames(qt, mrs, deadline)
-}
-
-func (vmssn *VMStorageSingleNode) GetMetricNamesUsageStats(qt *querytracer.Tracer, tt *storage.TenantToken, limit, le int, matchPattern string, deadline uint64) (metricnamestats.StatsResult, error) {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.GetMetricNamesUsageStats(qt, tt, limit, le, matchPattern, deadline)
-}
-
-func (vmssn *VMStorageSingleNode) ResetMetricNamesUsageStats(qt *querytracer.Tracer, deadline uint64) error {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.ResetMetricNamesUsageStats(qt, deadline)
-}
-
-func (vmssn *VMStorageSingleNode) GetMetadataRecords(qt *querytracer.Tracer, tt *storage.TenantToken, limit int, metricName string, deadline uint64) ([]*metricsmetadata.Row, error) {
-	vmssn.wg.Add(1)
-	defer vmssn.wg.Done()
-	return vmssn.vms.GetMetadataRecords(qt, tt, limit, metricName, deadline)
-}

app/vmstorage/vmstorage_test.go

@@ -48,7 +48,7 @@ func TestGetMaxMetrics(t *testing.T) {
 		t.Helper()
 		*maxUniqueTimeseries = storageMaxUniqueTimeseries
 		s := storage.MustOpenStorage(t.Name(), storage.OpenOptions{})
-		vms := newVMStorage(s, maxConcurrentRequests)
+		vms := newVMStorage(s, maxConcurrentRequests, func(mrs []storage.MetricRow) {})
 		defer vms.Stop()
 		maxMetrics := vms.getMaxMetrics(searchQueryLimit)
 		if maxMetrics != expect {

app/vmui/packages/vmui/package.json

@@ -21,16 +21,16 @@
   },
   "dependencies": {
     "classnames": "^2.5.1",
-    "dayjs": "^1.11.20",
+    "dayjs": "^1.11.21",
     "lodash.debounce": "^4.0.8",
-    "marked": "^18.0.2",
-    "preact": "^10.29.1",
-    "qs": "^6.15.1",
+    "marked": "^18.0.5",
+    "preact": "^10.29.2",
+    "qs": "^6.15.2",
     "react-input-mask": "^2.0.4",
-    "react-router-dom": "^7.14.1",
+    "react-router-dom": "^7.17.0",
     "uplot": "^1.6.32",
-    "vite": "^8.0.8",
-    "web-vitals": "^5.2.0"
+    "vite": "^8.0.16",
+    "web-vitals": "^5.3.0"
   },
   "devDependencies": {
     "@eslint/eslintrc": "^3.3.5",
@@ -39,24 +39,24 @@
     "@testing-library/jest-dom": "^6.9.1",
     "@testing-library/preact": "^3.2.4",
     "@types/lodash.debounce": "^4.0.9",
-    "@types/node": "^25.6.0",
-    "@types/qs": "^6.15.0",
-    "@types/react": "^19.2.14",
+    "@types/node": "^25.9.2",
+    "@types/qs": "^6.15.1",
+    "@types/react": "^19.2.17",
     "@types/react-input-mask": "^3.0.6",
     "@types/react-router-dom": "^5.3.3",
-    "@typescript-eslint/eslint-plugin": "^8.58.2",
-    "@typescript-eslint/parser": "^8.58.2",
+    "@typescript-eslint/eslint-plugin": "^8.61.0",
+    "@typescript-eslint/parser": "^8.61.0",
     "cross-env": "^10.1.0",
     "eslint": "^9.39.2",
     "eslint-plugin-react": "^7.37.5",
     "eslint-plugin-unused-imports": "^4.4.1",
-    "globals": "^17.5.0",
-    "http-proxy-middleware": "^3.0.5",
-    "jsdom": "^29.0.2",
-    "postcss": "^8.5.10",
-    "sass-embedded": "^1.99.0",
-    "typescript": "^6.0.2",
-    "vitest": "^4.1.4"
+    "globals": "^17.6.0",
+    "http-proxy-middleware": "^4.1.0",
+    "jsdom": "^29.1.1",
+    "postcss": "^8.5.15",
+    "sass-embedded": "^1.100.0",
+    "typescript": "^6.0.3",
+    "vitest": "^4.1.8"
   },
   "browserslist": {
     "production": [

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

@@ -5,7 +5,7 @@ import uPlot from "uplot";
 import Button from "../../Main/Button/Button";
 import { CloseIcon, DragIcon } from "../../Main/Icons";
 import { SeriesItemStatsFormatted } from "../../../types";
-import { STATS_ORDER } from "../../../constants/graph";
+import { STATS_ORDER_TOOLTIP } from "../../../constants/graph";
 
 export interface ChartTooltipProps {
   u?: uPlot;
@@ -164,7 +164,7 @@ const ChartTooltip: FC<ChartTooltipProps> = ({
       </div>
       {statsFormatted && (
         <table className="vm-chart-tooltip-stats">
-          {STATS_ORDER.map((key, i) => (
+          {STATS_ORDER_TOOLTIP.map((key, i) => (
             <div
               className="vm-chart-tooltip-stats-row"
               key={i}

app/vmui/packages/vmui/src/components/Chart/Line/Legend/LegendConfigs/LegendConfigs.tsx

@@ -61,7 +61,7 @@ const LegendConfigs: FC<Props> = ({ data, isCompact }) => {
       label: "Hide Statistics",
       value: hideStats,
       onChange: onChangeStats,
-      info: "If enabled, hides the display of min, median, and max values.",
+      info: "If enabled, hides the display of min, median, max, and last values.",
     }
   ];
 

app/vmui/packages/vmui/src/components/Chart/Line/Legend/LegendItem/LegendItem.tsx

@@ -5,7 +5,7 @@ import "./style.scss";
 import classNames from "classnames";
 import { getFreeFields } from "./helpers";
 import useCopyToClipboard from "../../../../../hooks/useCopyToClipboard";
-import { STATS_ORDER } from "../../../../../constants/graph";
+import { STATS_ORDER_LEGEND } from "../../../../../constants/graph";
 import { useShowStats } from "../hooks/useShowStats";
 import { useLegendFormat } from "../hooks/useLegendFormat";
 import { getLabelAlias } from "../../../../../utils/metric";
@@ -80,7 +80,7 @@ const LegendItem: FC<LegendItemProps> = ({ legend, onChange, duplicateFields })
       </div>
       {!hideStats && showStats && (
         <div className="vm-legend-item-stats">
-          {STATS_ORDER.map((key, i) => (
+          {STATS_ORDER_LEGEND.map((key, i) => (
             <div
               className="vm-legend-item-stats-row"
               key={i}

app/vmui/packages/vmui/src/components/Chart/Line/Legend/LegendViews/LegendTable.tsx

@@ -4,11 +4,11 @@ import "./style.scss";
 import { LegendItemType } from "../../../../../types";
 import { MouseEvent } from "react";
 import classNames from "classnames";
-import { STATS_ORDER } from "../../../../../constants/graph";
+import { STATS_ORDER_LEGEND } from "../../../../../constants/graph";
 import { useShowStats } from "../hooks/useShowStats";
 import { getValueByPath } from "../../../../../utils/object";
 
-const statsColumns = STATS_ORDER.map(k => ({
+const statsColumns = STATS_ORDER_LEGEND.map(k => ({
   key: `statsFormatted.${k}`,
   title: k
 }));

app/vmui/packages/vmui/src/constants/graph.ts

@@ -26,4 +26,5 @@ export const GRAPH_SIZES: GraphSize[] = [
   },
 ];
 
-export const STATS_ORDER: (keyof SeriesItemStatsFormatted)[] = ["min", "median", "max"];
+export const STATS_ORDER_LEGEND: (keyof SeriesItemStatsFormatted)[] = ["min", "median", "max", "last"];
+export const STATS_ORDER_TOOLTIP: (keyof SeriesItemStatsFormatted)[] = ["min", "median", "max"];

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

@@ -4,6 +4,7 @@ export interface SeriesItemStatsFormatted {
     min: string,
     max: string,
     median: string,
+    last: string,
 }
 
 export interface SeriesItem extends Series {

app/vmui/packages/vmui/src/utils/uplot/series.ts

@@ -53,6 +53,7 @@ const getSeriesStatistics = (d: MetricResult) => {
       min: formatPrettyNumber(min, min, max),
       max: formatPrettyNumber(max, min, max),
       median: formatPrettyNumber(median, min, max),
+      last: formatPrettyNumber(values.at(-1), min, max),
     },
   };
 };

apptest/README.md

@@ -4,7 +4,7 @@ The `apptest` package contains the integration tests for the VictoriaMetrics
 applications (such as vmstorage, vminsert, and vmselect).
 
 An integration test aims at verifying the behavior of an application as a whole,
-as apposed to a unit test that verifies the behavior of a building block of an
+as opposed to a unit test that verifies the behavior of a building block of an
 application.
 
 To achieve that an integration test starts an application in a separate process
@@ -19,10 +19,10 @@ work together as a system.
 The package provides a collection of helpers to start applications and make
 queries to them:
 
--   `app.go` - contains the generic code for staring an application and should
+-   `app.go` - contains the generic code for starting an application and should
     not be used by integration tests directly.
 -   `{vmstorage,vminsert,etc}.go` - build on top of `app.go` and provide the
-    code for staring a specific application.
+    code for starting a specific application.
 -   `client.go` - provides helper functions for sending HTTP requests to
     applications.
 
@@ -36,7 +36,7 @@ the application binary files to be built and put into the `bin` directory. The
 build rule used for running integration tests, `make apptest`,
 accounts for that, it builds all application binaries before running the tests.
 But if you want to run the tests without `make`, i.e. by executing
-`go test ./app/apptest`, you will need to build the binaries first (for example,
+`go test ./apptest/tests`, you will need to build the binaries first (for example,
 by executing `make all`).
 
 Not all binaries can be built from `master` branch, cluster binaries can be built

apptest/client.go

@@ -156,14 +156,14 @@ func readAllAndClose(t *testing.T, responseBody io.ReadCloser) string {
 //
 // This type is expected to be embedded by the apps that serve metrics.
 type metricsClient struct {
-	metricsCli *Client
-	url        string
+	cli *Client
+	url string
 }
 
 func newMetricsClient(cli *Client, addr string) *metricsClient {
 	return &metricsClient{
-		metricsCli: cli,
-		url:        fmt.Sprintf("http://%s/metrics", addr),
+		cli: cli,
+		url: fmt.Sprintf("http://%s/metrics", addr),
 	}
 }
 
@@ -179,7 +179,7 @@ func (c *metricsClient) GetIntMetric(t *testing.T, metricName string) int {
 func (c *metricsClient) GetMetric(t *testing.T, metricName string) float64 {
 	t.Helper()
 
-	metrics, statusCode := c.metricsCli.Get(t, c.url, nil)
+	metrics, statusCode := c.cli.Get(t, c.url, nil)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
 	}
@@ -205,7 +205,7 @@ func (c *metricsClient) GetMetricsByPrefix(t *testing.T, prefix string) []float6
 
 	values := []float64{}
 
-	metrics, statusCode := c.metricsCli.Get(t, c.url, nil)
+	metrics, statusCode := c.cli.Get(t, c.url, nil)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
 	}
@@ -234,7 +234,7 @@ func (c *metricsClient) GetMetricsByRegexp(t *testing.T, re *regexp.Regexp) []fl
 
 	values := []float64{}
 
-	metrics, statusCode := c.metricsCli.Get(t, c.url, nil)
+	metrics, statusCode := c.cli.Get(t, c.url, nil)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
 	}
@@ -270,7 +270,7 @@ func (c *metricsClient) rpcRowsSentTotal(t *testing.T) int {
 }
 
 type vmselectClient struct {
-	vmselectCli              *Client
+	cli                      *Client
 	url                      func(op, path string, opts QueryOpts) string
 	metricNamesStatsResetURL string
 	tenantsURL               string
@@ -287,7 +287,7 @@ func (c *vmselectClient) PrometheusAPIV1Export(t *testing.T, query string, opts
 	values := opts.asURLValues()
 	values.Add("match[]", query)
 	values.Add("format", "promapi")
-	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	res, _ := c.cli.PostForm(t, url, values, opts.Headers)
 	return NewPrometheusAPIV1QueryResponse(t, res)
 }
 
@@ -302,7 +302,7 @@ func (c *vmselectClient) PrometheusAPIV1ExportNative(t *testing.T, query string,
 	values := opts.asURLValues()
 	values.Add("match[]", query)
 	values.Add("format", "promapi")
-	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	res, _ := c.cli.PostForm(t, url, values, opts.Headers)
 	return []byte(res)
 }
 
@@ -315,7 +315,7 @@ func (c *vmselectClient) PrometheusAPIV1Query(t *testing.T, query string, opts Q
 	url := c.url("select", "prometheus/api/v1/query", opts)
 	values := opts.asURLValues()
 	values.Add("query", query)
-	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	res, _ := c.cli.PostForm(t, url, values, opts.Headers)
 	return NewPrometheusAPIV1QueryResponse(t, res)
 }
 
@@ -329,7 +329,7 @@ func (c *vmselectClient) PrometheusAPIV1QueryRange(t *testing.T, query string, o
 	url := c.url("select", "prometheus/api/v1/query_range", opts)
 	values := opts.asURLValues()
 	values.Add("query", query)
-	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	res, _ := c.cli.PostForm(t, url, values, opts.Headers)
 	return NewPrometheusAPIV1QueryResponse(t, res)
 }
 
@@ -342,7 +342,7 @@ func (c *vmselectClient) PrometheusAPIV1Series(t *testing.T, matchQuery string,
 	url := c.url("select", "prometheus/api/v1/series", opts)
 	values := opts.asURLValues()
 	values.Add("match[]", matchQuery)
-	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	res, _ := c.cli.PostForm(t, url, values, opts.Headers)
 	return NewPrometheusAPIV1SeriesResponse(t, res)
 }
 
@@ -354,7 +354,7 @@ func (c *vmselectClient) PrometheusAPIV1SeriesCount(t *testing.T, opts QueryOpts
 	t.Helper()
 	url := c.url("select", "prometheus/api/v1/series/count", opts)
 	values := opts.asURLValues()
-	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	res, _ := c.cli.PostForm(t, url, values, opts.Headers)
 	return NewPrometheusAPIV1SeriesCountResponse(t, res)
 }
 
@@ -367,7 +367,7 @@ func (c *vmselectClient) PrometheusAPIV1Labels(t *testing.T, matchQuery string,
 	url := c.url("select", "prometheus/api/v1/labels", opts)
 	values := opts.asURLValues()
 	values.Add("match[]", matchQuery)
-	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	res, _ := c.cli.PostForm(t, url, values, opts.Headers)
 	return NewPrometheusAPIV1LabelsResponse(t, res)
 }
 
@@ -382,7 +382,7 @@ func (c *vmselectClient) PrometheusAPIV1LabelValues(t *testing.T, labelName, mat
 	url := c.url("select", path, opts)
 	values := opts.asURLValues()
 	values.Add("match[]", matchQuery)
-	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	res, _ := c.cli.PostForm(t, url, values, opts.Headers)
 	return NewPrometheusAPIV1LabelValuesResponse(t, res)
 }
 
@@ -394,7 +394,7 @@ func (c *vmselectClient) PrometheusAPIV1Metadata(t *testing.T, metric string, li
 	values := opts.asURLValues()
 	values.Add("metric", metric)
 	values.Add("limit", strconv.Itoa(limit))
-	res, _ := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	res, _ := c.cli.PostForm(t, url, values, opts.Headers)
 	return NewPrometheusAPIV1Metadata(t, res)
 }
 
@@ -408,7 +408,7 @@ func (c *vmselectClient) PrometheusAPIV1AdminTSDBDeleteSeries(t *testing.T, matc
 	url := c.url("delete", "prometheus/api/v1/admin/tsdb/delete_series", opts)
 	values := opts.asURLValues()
 	values.Add("match[]", matchQuery)
-	res, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	res, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
 	if statusCode != http.StatusNoContent {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
 	}
@@ -426,7 +426,7 @@ func (c *vmselectClient) PrometheusAPIV1StatusMetricNamesStats(t *testing.T, lim
 	values.Add("limit", limit)
 	values.Add("le", le)
 	values.Add("match_pattern", matchPattern)
-	res, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	res, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
 	}
@@ -455,7 +455,7 @@ func (c *vmselectClient) PrometheusAPIV1StatusTSDB(t *testing.T, matchQuery stri
 	addNonEmpty("match[]", matchQuery)
 	addNonEmpty("topN", topN)
 	addNonEmpty("date", date)
-	res, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	res, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
 	}
@@ -476,7 +476,7 @@ func (c *vmselectClient) GraphiteMetricsIndex(t *testing.T, opts QueryOpts) Grap
 	t.Helper()
 
 	url := c.url("select", "graphite/metrics/index.json", opts)
-	res, statusCode := c.vmselectCli.Get(t, url, opts.Headers)
+	res, statusCode := c.cli.Get(t, url, opts.Headers)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
 	}
@@ -499,7 +499,7 @@ func (c *vmselectClient) GraphiteMetricsFind(t *testing.T, query string, opts Qu
 	url := c.url("select", "graphite/metrics/find", opts)
 	values := opts.asURLValues()
 	values.Add("query", query)
-	resText, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	resText, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, resText)
 	}
@@ -522,7 +522,7 @@ func (c *vmselectClient) GraphiteMetricsExpand(t *testing.T, query string, opts
 	url := c.url("select", "graphite/metrics/expand", opts)
 	values := opts.asURLValues()
 	values.Add("query", query)
-	resText, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	resText, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, resText)
 	}
@@ -546,7 +546,7 @@ func (c *vmselectClient) GraphiteRender(t *testing.T, target string, opts QueryO
 	values := opts.asURLValues()
 	values.Add("format", "json")
 	values.Add("target", target)
-	resText, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	resText, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, resText)
 	}
@@ -567,7 +567,7 @@ func (c *vmselectClient) GraphiteTagsTagSeries(t *testing.T, record string, opts
 	url := c.url("select", "graphite/tags/tagSeries", opts)
 	values := opts.asURLValues()
 	values.Add("path", record)
-	_, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	_, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
 	if got, want := statusCode, http.StatusNotImplemented; got != want {
 		t.Fatalf("unexpected status code: got %d, want %d", got, want)
 	}
@@ -584,7 +584,7 @@ func (c *vmselectClient) GraphiteTagsTagMultiSeries(t *testing.T, records []stri
 	for _, rec := range records {
 		values.Add("path", rec)
 	}
-	_, statusCode := c.vmselectCli.PostForm(t, url, values, opts.Headers)
+	_, statusCode := c.cli.PostForm(t, url, values, opts.Headers)
 	if got, want := statusCode, http.StatusNotImplemented; got != want {
 		t.Fatalf("unexpected status code: got %d, want %d", got, want)
 	}
@@ -598,7 +598,7 @@ func (c *vmselectClient) GraphiteTagsTagMultiSeries(t *testing.T, records []stri
 func (c *vmselectClient) PrometheusAPIV1AdminStatusMetricNamesStatsReset(t *testing.T, opts QueryOpts) {
 	t.Helper()
 	values := opts.asURLValues()
-	res, statusCode := c.vmselectCli.PostForm(t, c.metricNamesStatsResetURL, values, opts.Headers)
+	res, statusCode := c.cli.PostForm(t, c.metricNamesStatsResetURL, values, opts.Headers)
 	if statusCode != http.StatusNoContent {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
 	}
@@ -608,7 +608,7 @@ func (c *vmselectClient) PrometheusAPIV1AdminStatusMetricNamesStatsReset(t *test
 // /admin/tenants endpoint.
 func (c *vmselectClient) APIV1AdminTenants(t *testing.T, opts QueryOpts) *AdminTenantsResponse {
 	t.Helper()
-	res, statusCode := c.vmselectCli.Get(t, c.tenantsURL, opts.Headers)
+	res, statusCode := c.cli.Get(t, c.tenantsURL, opts.Headers)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
 	}
@@ -622,7 +622,7 @@ func (c *vmselectClient) APIV1AdminTenants(t *testing.T, opts QueryOpts) *AdminT
 }
 
 type vminsertClient struct {
-	vminsertCli        *Client
+	cli                *Client
 	url                func(op, path string, opts QueryOpts) string
 	openTSDBURL        func(op, path string, opts QueryOpts) string
 	graphiteListenAddr string
@@ -647,7 +647,7 @@ func (c *vminsertClient) PrometheusAPIV1ImportCSV(t *testing.T, records []string
 	headers := opts.getHeaders()
 	headers.Set("Content-Type", "text/plain")
 	c.sendBlocking(t, len(records), func() {
-		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		_, statusCode := c.cli.Post(t, url, data, headers)
 		if statusCode != http.StatusNoContent {
 			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
 		}
@@ -671,7 +671,7 @@ func (c *vminsertClient) PrometheusAPIV1ImportNative(t *testing.T, data []byte,
 	headers := opts.getHeaders()
 	headers.Set("Content-Type", "text/plain")
 	c.sendBlocking(t, 1, func() {
-		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		_, statusCode := c.cli.Post(t, url, data, headers)
 		if statusCode != http.StatusNoContent {
 			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
 		}
@@ -693,7 +693,7 @@ func (c *vminsertClient) PrometheusAPIV1Write(t *testing.T, wr prompb.WriteReque
 	headers := opts.getHeaders()
 	headers.Set("Content-Type", "application/x-protobuf")
 	c.sendBlocking(t, recordsCount, func() {
-		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		_, statusCode := c.cli.Post(t, url, data, headers)
 		if statusCode != http.StatusNoContent {
 			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
 		}
@@ -745,7 +745,7 @@ func (c *vminsertClient) PrometheusAPIV1ImportPrometheus(t *testing.T, records [
 	headers := opts.getHeaders()
 	headers.Set("Content-Type", "text/plain")
 	c.sendBlocking(t, recordsCount, func() {
-		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		_, statusCode := c.cli.Post(t, url, data, headers)
 		if statusCode != http.StatusNoContent {
 			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
 		}
@@ -771,7 +771,7 @@ func (c *vminsertClient) InfluxWrite(t *testing.T, records []string, opts QueryO
 	headers.Set("Content-Type", "text/plain")
 	c.sendBlocking(t, len(records), func() {
 		t.Helper()
-		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		_, statusCode := c.cli.Post(t, url, data, headers)
 		if statusCode != http.StatusNoContent {
 			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
 		}
@@ -805,7 +805,7 @@ func (c *vminsertClient) OpentelemetryV1Metrics(t *testing.T, md otlppb.MetricsD
 	headers := opts.getHeaders()
 	headers.Set("Content-Type", "application/x-protobuf")
 	c.sendBlocking(t, recordsCount, func() {
-		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		_, statusCode := c.cli.Post(t, url, data, headers)
 		if statusCode != http.StatusOK {
 			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
 		}
@@ -830,7 +830,7 @@ func (c *vminsertClient) OpenTSDBAPIPut(t *testing.T, records []string, opts Que
 	headers := opts.getHeaders()
 	headers.Set("Content-Type", "application/json")
 	c.sendBlocking(t, len(records), func() {
-		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		_, statusCode := c.cli.Post(t, url, data, headers)
 		if statusCode != http.StatusNoContent {
 			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
 		}
@@ -853,7 +853,7 @@ func (c *vminsertClient) ZabbixConnectorHistory(t *testing.T, records []string,
 	headers := opts.getHeaders()
 	headers.Set("Content-Type", "application/json")
 	c.sendBlocking(t, len(records), func() {
-		_, statusCode := c.vminsertCli.Post(t, url, data, headers)
+		_, statusCode := c.cli.Post(t, url, data, headers)
 		if statusCode != http.StatusOK {
 			t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
 		}
@@ -867,11 +867,11 @@ func (c *vminsertClient) ZabbixConnectorHistory(t *testing.T, records []string,
 // See https://docs.victoriametrics.com/victoriametrics/integrations/graphite/#ingesting
 func (c *vminsertClient) GraphiteWrite(t *testing.T, records []string, _ QueryOpts) {
 	t.Helper()
-	c.vminsertCli.Write(t, c.graphiteListenAddr, records)
+	c.cli.Write(t, c.graphiteListenAddr, records)
 }
 
 type vmstorageClient struct {
-	vmstorageCli   *Client
+	cli            *Client
 	httpListenAddr string
 }
 
@@ -881,7 +881,7 @@ func (c *vmstorageClient) ForceFlush(t *testing.T) {
 	t.Helper()
 
 	url := fmt.Sprintf("http://%s/internal/force_flush", c.httpListenAddr)
-	_, statusCode := c.vmstorageCli.Get(t, url, nil)
+	_, statusCode := c.cli.Get(t, url, nil)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
 	}
@@ -892,7 +892,7 @@ func (c *vmstorageClient) ForceMerge(t *testing.T) {
 	t.Helper()
 
 	url := fmt.Sprintf("http://%s/internal/force_merge", c.httpListenAddr)
-	_, statusCode := c.vmstorageCli.Get(t, url, nil)
+	_, statusCode := c.cli.Get(t, url, nil)
 	if statusCode != http.StatusOK {
 		t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
 	}
@@ -905,7 +905,7 @@ func (c *vmstorageClient) ForceMerge(t *testing.T) {
 func (c *vmstorageClient) SnapshotCreate(t *testing.T) *SnapshotCreateResponse {
 	t.Helper()
 
-	data, statusCode := c.vmstorageCli.Post(t, c.SnapshotCreateURL(), nil, nil)
+	data, statusCode := c.cli.Post(t, c.SnapshotCreateURL(), nil, nil)
 	if got, want := statusCode, http.StatusOK; got != want {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
 	}
@@ -931,7 +931,7 @@ func (c *vmstorageClient) APIV1AdminTSDBSnapshot(t *testing.T) *APIV1AdminTSDBSn
 	t.Helper()
 
 	url := fmt.Sprintf("http://%s/api/v1/admin/tsdb/snapshot", c.httpListenAddr)
-	data, statusCode := c.vmstorageCli.Post(t, url, nil, nil)
+	data, statusCode := c.cli.Post(t, url, nil, nil)
 	if got, want := statusCode, http.StatusOK; got != want {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
 	}
@@ -952,7 +952,7 @@ func (c *vmstorageClient) SnapshotList(t *testing.T) *SnapshotListResponse {
 	t.Helper()
 
 	url := fmt.Sprintf("http://%s/snapshot/list", c.httpListenAddr)
-	data, statusCode := c.vmstorageCli.Get(t, url, nil)
+	data, statusCode := c.cli.Get(t, url, nil)
 	if got, want := statusCode, http.StatusOK; got != want {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
 	}
@@ -973,7 +973,7 @@ func (c *vmstorageClient) SnapshotDelete(t *testing.T, snapshotName string) *Sna
 	t.Helper()
 
 	url := fmt.Sprintf("http://%s/snapshot/delete?snapshot=%s", c.httpListenAddr, snapshotName)
-	data, statusCode := c.vmstorageCli.Delete(t, url)
+	data, statusCode := c.cli.Delete(t, url)
 	wantStatusCodes := map[int]bool{
 		http.StatusOK:                  true,
 		http.StatusInternalServerError: true,
@@ -998,7 +998,7 @@ func (c *vmstorageClient) SnapshotDeleteAll(t *testing.T) *SnapshotDeleteAllResp
 	t.Helper()
 
 	url := fmt.Sprintf("http://%s/snapshot/delete_all", c.httpListenAddr)
-	data, statusCode := c.vmstorageCli.Post(t, url, nil, nil)
+	data, statusCode := c.cli.Post(t, url, nil, nil)
 	if got, want := statusCode, http.StatusOK; got != want {
 		t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
 	}

apptest/tests/metricsmetadata_test.go

@@ -45,11 +45,13 @@ func TestSingleMetricsMetadata(t *testing.T) {
 			{Labels: []prompb.Label{{Name: "__name__", Value: "metric_name_4"}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
 			{Labels: []prompb.Label{{Name: "__name__", Value: "metric_name_5"}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
 			{Labels: []prompb.Label{{Name: "__name__", Value: "metric_name_6"}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
+			{Labels: []prompb.Label{{Name: "__name__", Value: `metric_name_7_!@"_suffix`}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
 		},
 		Metadata: []prompb.MetricMetadata{
 			{MetricFamilyName: "metric_name_4", Help: "some help message", Type: prompb.MetricTypeSummary},
 			{MetricFamilyName: "metric_name_5", Help: "some help message", Type: prompb.MetricTypeSummary},
 			{MetricFamilyName: "metric_name_6", Help: "some help message", Type: prompb.MetricTypeStateset},
+			{MetricFamilyName: `metric_name_7_!@"_suffix`, Help: "some help message", Type: prompb.MetricTypeStateset},
 		},
 	}
 
@@ -59,12 +61,13 @@ func TestSingleMetricsMetadata(t *testing.T) {
 	expected := &apptest.PrometheusAPIV1Metadata{
 		Status: "success",
 		Data: map[string][]apptest.MetadataEntry{
-			"metric_name_1": {{Help: "some help message", Type: "gauge"}},
-			"metric_name_2": {{Help: "some help message", Type: "counter"}},
-			"metric_name_3": {{Help: "some help message", Type: "gauge"}},
-			"metric_name_4": {{Help: "some help message", Type: "summary"}},
-			"metric_name_5": {{Help: "some help message", Type: "summary"}},
-			"metric_name_6": {{Help: "some help message", Type: "stateset"}},
+			"metric_name_1":            {{Help: "some help message", Type: "gauge"}},
+			"metric_name_2":            {{Help: "some help message", Type: "counter"}},
+			"metric_name_3":            {{Help: "some help message", Type: "gauge"}},
+			"metric_name_4":            {{Help: "some help message", Type: "summary"}},
+			"metric_name_5":            {{Help: "some help message", Type: "summary"}},
+			"metric_name_6":            {{Help: "some help message", Type: "stateset"}},
+			`metric_name_7_!@"_suffix`: {{Help: "some help message", Type: "stateset"}},
 		},
 	}
 	gotStats := sut.PrometheusAPIV1Metadata(t, "", 0, apptest.QueryOpts{})
@@ -154,11 +157,13 @@ func TestClusterMetricsMetadata(t *testing.T) {
 			{Labels: []prompb.Label{{Name: "__name__", Value: "metric_name_4"}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
 			{Labels: []prompb.Label{{Name: "__name__", Value: "metric_name_5"}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
 			{Labels: []prompb.Label{{Name: "__name__", Value: "metric_name_6"}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
+			{Labels: []prompb.Label{{Name: "__name__", Value: `metric_name_7_!@"_suffix`}}, Samples: []prompb.Sample{{Value: 40, Timestamp: ingestTimestamp}}},
 		},
 		Metadata: []prompb.MetricMetadata{
 			{MetricFamilyName: "metric_name_4", Help: "some help message", Type: prompb.MetricTypeSummary},
 			{MetricFamilyName: "metric_name_5", Help: "some help message", Type: prompb.MetricTypeSummary},
 			{MetricFamilyName: "metric_name_6", Help: "some help message", Type: prompb.MetricTypeStateset},
+			{MetricFamilyName: `metric_name_7_!@"_suffix`, Help: "some help message", Type: prompb.MetricTypeStateset},
 		},
 	}
 
@@ -171,12 +176,13 @@ func TestClusterMetricsMetadata(t *testing.T) {
 		expected := &apptest.PrometheusAPIV1Metadata{
 			Status: "success",
 			Data: map[string][]apptest.MetadataEntry{
-				"metric_name_1": {{Help: "some help message", Type: "gauge"}},
-				"metric_name_2": {{Help: "some help message", Type: "counter"}},
-				"metric_name_3": {{Help: "some help message", Type: "gauge"}},
-				"metric_name_4": {{Help: "some help message", Type: "summary"}},
-				"metric_name_5": {{Help: "some help message", Type: "summary"}},
-				"metric_name_6": {{Help: "some help message", Type: "stateset"}},
+				"metric_name_1":            {{Help: "some help message", Type: "gauge"}},
+				"metric_name_2":            {{Help: "some help message", Type: "counter"}},
+				"metric_name_3":            {{Help: "some help message", Type: "gauge"}},
+				"metric_name_4":            {{Help: "some help message", Type: "summary"}},
+				"metric_name_5":            {{Help: "some help message", Type: "summary"}},
+				"metric_name_6":            {{Help: "some help message", Type: "stateset"}},
+				`metric_name_7_!@"_suffix`: {{Help: "some help message", Type: "stateset"}},
 			},
 		}
 		gotStats := vmselect.PrometheusAPIV1Metadata(t, "", 0, apptest.QueryOpts{Tenant: tenantID})

apptest/tests/vmagent_remotewrite_test.go

@@ -8,6 +8,7 @@ import (
 	"net/http/httptest"
 	"strings"
 	"sync"
+	"sync/atomic"
 	"testing"
 	"time"
 
@@ -332,13 +333,11 @@ func TestSingleVMAgentDropOnOverload(t *testing.T) {
 	vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
 		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
 	}, apptest.QueryOpts{})
-
 	waitFor(
 		func() bool {
 			return vmagent.RemoteWriteRequests(t, url1) == 1 && vmagent.RemoteWriteRequests(t, url2) == 1
 		},
 	)
-
 	// Send 2 more requests, the first RW endpoint should receive everything, the second should add them to the queue
 	// since worker is busy with the first request.
 	for i := range 2 {
@@ -641,3 +640,116 @@ func TestSingleVMAgentMultitenancy(t *testing.T) {
 		t.Fatalf("expected vmagent_tenant_inserted_rows_total to have value 1 for accountID=5, projectID=0")
 	}
 }
+
+func TestSingleVMAgentPriorizeRecentData(t *testing.T) {
+	tc := apptest.NewTestCase(t)
+	defer tc.Stop()
+
+	remoteWriteSrv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(http.StatusNoContent)
+	}))
+	defer remoteWriteSrv.Close()
+
+	var mustRW2ReturnError atomic.Bool
+	mustRW2ReturnError.Store(true)
+
+	remoteWriteSrv2 := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if mustRW2ReturnError.Load() {
+			w.WriteHeader(http.StatusServiceUnavailable)
+			return
+		}
+		w.WriteHeader(http.StatusNoContent)
+	}))
+	defer remoteWriteSrv2.Close()
+
+	vmagent := tc.MustStartDefaultRWVmagent("vmagent", []string{
+		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv.URL),
+		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv2.URL),
+		"-remoteWrite.disableOnDiskQueue=true",
+		// use only 1 worker to get a full queue faster
+		"-remoteWrite.queues=1",
+		"-remoteWrite.flushInterval=1ms",
+		"-remoteWrite.inmemoryQueues=1",
+		// fastqueue size is roughly memory.Allowed() / len(urls) / *maxRowsPerBlock / 100
+		// Use very large maxRowsPerBlock to get fastqueue of minimal length(2).
+		// See initRemoteWriteCtxs function in remotewrite.go for details.
+		"-remoteWrite.maxRowsPerBlock=1000000000",
+		"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent",
+
+		// Delay retry logic to avoid race conditions with waitFor assertions.
+		// It improves the test stability on resource-constrained runners.
+		"-remoteWrite.retryMinInterval=3s",
+		"-remoteWrite.retryMaxTime=3s",
+	})
+
+	const (
+		retries = 20
+		period  = 200 * time.Millisecond
+	)
+
+	waitFor := func(f func() bool) {
+		t.Helper()
+		for range retries {
+			if f() {
+				return
+			}
+			time.Sleep(period)
+		}
+		t.Fatalf("timed out waiting for retry #%d", retries)
+	}
+
+	// Real remote write URLs are hidden in metrics
+	url1 := "1:secret-url"
+	url2 := "2:secret-url"
+
+	// Wait until first request got flushed to remote write server
+	vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
+		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
+	}, apptest.QueryOpts{})
+	waitFor(
+		func() bool {
+			return vmagent.RemoteWriteRequests(t, url1) == 1 && vmagent.RemoteWriteRequests(t, url2) == 1
+		},
+	)
+	// Wait until second request got flushed to remote write server
+	// since there are 2 independent queues (general and in-memory) with minimal capacity of 1
+	vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
+		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
+	}, apptest.QueryOpts{})
+	waitFor(
+		func() bool {
+			return vmagent.RemoteWriteRequests(t, url1) == 2 && vmagent.RemoteWriteRequests(t, url2) == 2
+		},
+	)
+	// Send 2 more requests, the first RW endpoint should receive everything, the second should add them to the queue
+	// since worker is busy with the first request.
+	for i := range 2 {
+		vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
+			"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
+		}, apptest.QueryOpts{})
+
+		waitFor(
+			func() bool {
+				return vmagent.RemoteWriteRequests(t, url1) == 3+i && vmagent.RemoteWritePendingInmemoryBlocks(t, url2) == 1+i
+			},
+		)
+	}
+
+	// Send one more request.
+	vmagent.APIV1ImportPrometheusNoWaitFlush(t, []string{
+		"foo_bar 1 1652169600000", // 2022-05-10T08:00:00Z
+	}, apptest.QueryOpts{})
+
+	waitFor(
+		func() bool {
+			return vmagent.RemoteWriteRequests(t, url1) == 5 && vmagent.RemoteWriteSamplesDropped(t, url2) > 0
+		},
+	)
+	mustRW2ReturnError.Store(false)
+	// ensure that inmemory data correctly flushed to the remote write
+	waitFor(
+		func() bool {
+			return vmagent.RemoteWritePendingInmemoryBlocks(t, url2) == 0
+		},
+	)
+}

apptest/vminsert.go

@@ -77,7 +77,7 @@ type vminsertRuntimeValues struct {
 func newVminsert(app *app, cli *Client, rt vminsertRuntimeValues) *Vminsert {
 	metricsClient := newMetricsClient(cli, rt.httpListenAddr)
 	vminsertClient := &vminsertClient{
-		vminsertCli: cli,
+		cli: cli,
 		url: func(op, path string, opts QueryOpts) string {
 			return getClusterPath(rt.httpListenAddr, op, path, opts)
 		},

apptest/vmselect.go

@@ -48,7 +48,7 @@ func newVmselect(app *app, cli *Client, rt vmselectRuntimeValues) *Vmselect {
 		app:           app,
 		metricsClient: newMetricsClient(cli, rt.httpListenAddr),
 		vmselectClient: &vmselectClient{
-			vmselectCli: cli,
+			cli: cli,
 			url: func(op, path string, opts QueryOpts) string {
 				return getClusterPath(rt.httpListenAddr, op, path, opts)
 			},

apptest/vmsingle.go

@@ -58,11 +58,11 @@ func newVmsingle(app *app, cli *Client, rt vmsingleRuntimeValues) *Vmsingle {
 		app:           app,
 		metricsClient: newMetricsClient(cli, rt.httpListenAddr),
 		vmstorageClient: &vmstorageClient{
-			vmstorageCli:   cli,
+			cli:            cli,
 			httpListenAddr: rt.httpListenAddr,
 		},
 		vmselectClient: &vmselectClient{
-			vmselectCli: cli,
+			cli: cli,
 			url: func(op, path string, opts QueryOpts) string {
 				return fmt.Sprintf("http://%s/%s", rt.httpListenAddr, path)
 			},
@@ -70,7 +70,7 @@ func newVmsingle(app *app, cli *Client, rt vmsingleRuntimeValues) *Vmsingle {
 			tenantsURL:               "vmsingle-does-not-serve-tenants",
 		},
 		vminsertClient: &vminsertClient{
-			vminsertCli: cli,
+			cli: cli,
 			url: func(_, path string, _ QueryOpts) string {
 				return fmt.Sprintf("http://%s/%s", rt.httpListenAddr, path)
 			},

apptest/vmstorage.go

@@ -63,7 +63,7 @@ func newVmstorage(app *app, cli *Client, rt vmstorageRuntimeValues) *Vmstorage {
 		app:           app,
 		metricsClient: newMetricsClient(cli, rt.httpListenAddr),
 		vmstorageClient: &vmstorageClient{
-			vmstorageCli:   cli,
+			cli:            cli,
 			httpListenAddr: rt.httpListenAddr,
 		},
 		storageDataPath: rt.storageDataPath,

dashboards/operator.json

@@ -1695,7 +1695,7 @@
         "type": "prometheus",
         "uid": "$ds"
       },
-      "description": "Shows the time goroutines have spent in runnable state before actually running. The lower is better.\n\nHigh values or values exceeding the threshold is usually a sign of insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
+      "description": "Shows the time goroutines have spent in runnable state before actually running.\n\n**Lower is better.**\n\nHigh values or values exceeding the threshold is usually a sign of insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
       "fieldConfig": {
         "defaults": {
           "color": {

dashboards/victoriametrics-cluster.json

@@ -1960,7 +1960,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html). Helps troubleshoot high CPU usage or throttling.\nLower is better.\n\n- waiting: The percentage of time at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: The percentage of time all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 1%. It only becomes a concern if it consistently climbs above 5–10% and aligns with latency spikes or GC slowdowns.",
+          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 100ms. It only becomes a concern if it consistently climbs above 50-100ms and aligns with latency spikes or GC slowdowns.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2083,7 +2083,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\nLower is better.\n\n- waiting: Time fraction where at least one thread was blocked on memory.\n- stalled: Time fraction where every thread was blocked on memory (severe pressure).\n\nIf queries slow down and both series spike, the host is likely limited by RAM or I/O throughput.\n\nSee also major page faults rate panel in Troubleshooting section if this metric continued to be high.",
+          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2727,7 +2727,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\nThe lower the better.\n\n- waiting: at least one runnable thread blocked on block-`I/O` (disk, NVMe, network-storage) while others could still make progress.\n- stalled: all non-idle threads simultaneously waiting on `I/O`; no useful user code ran during these periods → true `I/O` thrashing.\n\nIf stalled > 0 while querying, it's recommended to increase queue depth on NVMe, raise blk-mq budgets, or relax cgroup I/O limits.",
+          "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one runnable thread blocked on IO (disk, NVMe, network-storage) while others could still make progress.\n- stalled: all non-idle threads simultaneously waiting on `I/O`.\n\nIf stalled > 0, consider increasing queue depth on NVMe, raising blk-mq budgets, or relaxing cgroup I/O limits.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -3391,7 +3391,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows the time goroutines have spent in runnable state before actually running. The lower is better.\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
+          "description": "Shows the time goroutines have spent in runnable state before actually running.\n\n**Lower is better.**\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -4110,7 +4110,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows cache miss ratio. Lower is better.",
+          "description": "Shows cache miss ratio.\n\n**Lower is better.**",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -5715,106 +5715,6 @@
           ],
           "title": "Pending",
           "type": "timeseries"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "$ds"
-          },
-          "description": "Network usage by internal VictoriaMetrics RPC protocol",
-          "fieldConfig": {
-            "defaults": {
-              "color": {
-                "mode": "palette-classic"
-              },
-              "custom": {
-                "axisCenteredZero": false,
-                "axisColorMode": "text",
-                "axisLabel": "",
-                "axisPlacement": "auto",
-                "barAlignment": 0,
-                "drawStyle": "line",
-                "fillOpacity": 10,
-                "gradientMode": "none",
-                "hideFrom": {
-                  "legend": false,
-                  "tooltip": false,
-                  "viz": false
-                },
-                "lineInterpolation": "linear",
-                "lineWidth": 1,
-                "pointSize": 5,
-                "scaleDistribution": {
-                  "type": "linear"
-                },
-                "showPoints": "never",
-                "spanNulls": false,
-                "stacking": {
-                  "group": "A",
-                  "mode": "none"
-                },
-                "thresholdsStyle": {
-                  "mode": "off"
-                }
-              },
-              "links": [],
-              "mappings": [],
-              "min": 0,
-              "thresholds": {
-                "mode": "absolute",
-                "steps": [
-                  {
-                    "color": "green"
-                  },
-                  {
-                    "color": "red",
-                    "value": 80
-                  }
-                ]
-              },
-              "unit": "bps"
-            },
-            "overrides": []
-          },
-          "gridPos": {
-            "h": 8,
-            "w": 12,
-            "x": 12,
-            "y": 8388
-          },
-          "id": 74,
-          "options": {
-            "legend": {
-              "calcs": [
-                "mean",
-                "lastNotNull",
-                "max"
-              ],
-              "displayMode": "table",
-              "placement": "bottom",
-              "showLegend": true
-            },
-            "tooltip": {
-              "mode": "multi",
-              "sort": "none"
-            }
-          },
-          "pluginVersion": "9.1.0",
-          "targets": [
-            {
-              "datasource": {
-                "type": "prometheus",
-                "uid": "$ds"
-              },
-              "editorMode": "code",
-              "expr": "sum(rate(vm_tcpdialer_written_bytes_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) * 8",
-              "legendFormat": "network usage",
-              "range": true,
-              "refId": "A"
-            }
-          ],
-          "title": "RPC network usage ($instance)",
-          "type": "timeseries"
         }
       ],
       "title": "Interconnection ($job)",

dashboards/victoriametrics.json

@@ -1954,7 +1954,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html). Helps troubleshoot high CPU usage or throttling.\nLower is better.\n\n- waiting: The percentage of time at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: The percentage of time all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 1%. It only becomes a concern if it consistently climbs above 5–10% and aligns with latency spikes or GC slowdowns.",
+          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 100ms. It only becomes a concern if it consistently climbs above 50-100ms and aligns with latency spikes or GC slowdowns.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2063,7 +2063,7 @@
               "format": "time_series",
               "interval": "",
               "intervalFactor": 2,
-              "legendFormat": "{{job}}-{{instance}} - waiting",
+              "legendFormat": "{{job}}-{{instance}} - stalled",
               "range": true,
               "refId": "B"
             }
@@ -2388,7 +2388,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\nLower is better.\n\n- waiting: Time fraction where at least one thread was blocked on memory.\n- stalled: Time fraction where every thread was blocked on memory (severe pressure).\n\nIf queries slow down and both series spike, the host is likely limited by RAM or I/O throughput.\n\nSee also major page faults rate panel in Troubleshooting section if this metric continued to be high.",
+          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -3023,7 +3023,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\nThe lower the better.",
+          "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one runnable thread blocked on IO (disk, NVMe, network-storage) while others could still make progress.\n- stalled: all non-idle threads simultaneously waiting on `I/O`.\n\nIf stalled > 0, consider increasing queue depth on NVMe, raising blk-mq budgets, or relaxing cgroup I/O limits.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -3690,7 +3690,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows the time goroutines have spent in runnable state before actually running. The lower is better.\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
+          "description": "Shows the time goroutines have spent in runnable state before actually running.\n\n**Lower is better.**\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -4510,7 +4510,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows cache miss ratio. Lower is better.",
+          "description": "Shows cache miss ratio.\n\n**Lower is better.**",
           "fieldConfig": {
             "defaults": {
               "color": {

dashboards/vm/operator.json

@@ -1696,7 +1696,7 @@
         "type": "victoriametrics-metrics-datasource",
         "uid": "$ds"
       },
-      "description": "Shows the time goroutines have spent in runnable state before actually running. The lower is better.\n\nHigh values or values exceeding the threshold is usually a sign of insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
+      "description": "Shows the time goroutines have spent in runnable state before actually running.\n\n**Lower is better.**\n\nHigh values or values exceeding the threshold is usually a sign of insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
       "fieldConfig": {
         "defaults": {
           "color": {

dashboards/vm/victoriametrics-cluster.json

@@ -1961,7 +1961,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html). Helps troubleshoot high CPU usage or throttling.\nLower is better.\n\n- waiting: The percentage of time at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: The percentage of time all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 1%. It only becomes a concern if it consistently climbs above 5–10% and aligns with latency spikes or GC slowdowns.",
+          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 100ms. It only becomes a concern if it consistently climbs above 50-100ms and aligns with latency spikes or GC slowdowns.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2084,7 +2084,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\nLower is better.\n\n- waiting: Time fraction where at least one thread was blocked on memory.\n- stalled: Time fraction where every thread was blocked on memory (severe pressure).\n\nIf queries slow down and both series spike, the host is likely limited by RAM or I/O throughput.\n\nSee also major page faults rate panel in Troubleshooting section if this metric continued to be high.",
+          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2728,7 +2728,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\nThe lower the better.\n\n- waiting: at least one runnable thread blocked on block-`I/O` (disk, NVMe, network-storage) while others could still make progress.\n- stalled: all non-idle threads simultaneously waiting on `I/O`; no useful user code ran during these periods → true `I/O` thrashing.\n\nIf stalled > 0 while querying, it's recommended to increase queue depth on NVMe, raise blk-mq budgets, or relax cgroup I/O limits.",
+          "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one runnable thread blocked on IO (disk, NVMe, network-storage) while others could still make progress.\n- stalled: all non-idle threads simultaneously waiting on `I/O`.\n\nIf stalled > 0, consider increasing queue depth on NVMe, raising blk-mq budgets, or relaxing cgroup I/O limits.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -3392,7 +3392,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows the time goroutines have spent in runnable state before actually running. The lower is better.\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
+          "description": "Shows the time goroutines have spent in runnable state before actually running.\n\n**Lower is better.**\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -4111,7 +4111,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows cache miss ratio. Lower is better.",
+          "description": "Shows cache miss ratio.\n\n**Lower is better.**",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -5716,106 +5716,6 @@
           ],
           "title": "Pending",
           "type": "timeseries"
-        },
-        {
-          "datasource": {
-            "type": "victoriametrics-metrics-datasource",
-            "uid": "$ds"
-          },
-          "description": "Network usage by internal VictoriaMetrics RPC protocol",
-          "fieldConfig": {
-            "defaults": {
-              "color": {
-                "mode": "palette-classic"
-              },
-              "custom": {
-                "axisCenteredZero": false,
-                "axisColorMode": "text",
-                "axisLabel": "",
-                "axisPlacement": "auto",
-                "barAlignment": 0,
-                "drawStyle": "line",
-                "fillOpacity": 10,
-                "gradientMode": "none",
-                "hideFrom": {
-                  "legend": false,
-                  "tooltip": false,
-                  "viz": false
-                },
-                "lineInterpolation": "linear",
-                "lineWidth": 1,
-                "pointSize": 5,
-                "scaleDistribution": {
-                  "type": "linear"
-                },
-                "showPoints": "never",
-                "spanNulls": false,
-                "stacking": {
-                  "group": "A",
-                  "mode": "none"
-                },
-                "thresholdsStyle": {
-                  "mode": "off"
-                }
-              },
-              "links": [],
-              "mappings": [],
-              "min": 0,
-              "thresholds": {
-                "mode": "absolute",
-                "steps": [
-                  {
-                    "color": "green"
-                  },
-                  {
-                    "color": "red",
-                    "value": 80
-                  }
-                ]
-              },
-              "unit": "bps"
-            },
-            "overrides": []
-          },
-          "gridPos": {
-            "h": 8,
-            "w": 12,
-            "x": 12,
-            "y": 8388
-          },
-          "id": 74,
-          "options": {
-            "legend": {
-              "calcs": [
-                "mean",
-                "lastNotNull",
-                "max"
-              ],
-              "displayMode": "table",
-              "placement": "bottom",
-              "showLegend": true
-            },
-            "tooltip": {
-              "mode": "multi",
-              "sort": "none"
-            }
-          },
-          "pluginVersion": "9.1.0",
-          "targets": [
-            {
-              "datasource": {
-                "type": "victoriametrics-metrics-datasource",
-                "uid": "$ds"
-              },
-              "editorMode": "code",
-              "expr": "sum(rate(vm_tcpdialer_written_bytes_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) * 8",
-              "legendFormat": "network usage",
-              "range": true,
-              "refId": "A"
-            }
-          ],
-          "title": "RPC network usage ($instance)",
-          "type": "timeseries"
         }
       ],
       "title": "Interconnection ($job)",

dashboards/vm/victoriametrics.json

@@ -1955,7 +1955,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html). Helps troubleshoot high CPU usage or throttling.\nLower is better.\n\n- waiting: The percentage of time at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: The percentage of time all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 1%. It only becomes a concern if it consistently climbs above 5–10% and aligns with latency spikes or GC slowdowns.",
+          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 100ms. It only becomes a concern if it consistently climbs above 50-100ms and aligns with latency spikes or GC slowdowns.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2064,7 +2064,7 @@
               "format": "time_series",
               "interval": "",
               "intervalFactor": 2,
-              "legendFormat": "{{job}}-{{instance}} - waiting",
+              "legendFormat": "{{job}}-{{instance}} - stalled",
               "range": true,
               "refId": "B"
             }
@@ -2389,7 +2389,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\nLower is better.\n\n- waiting: Time fraction where at least one thread was blocked on memory.\n- stalled: Time fraction where every thread was blocked on memory (severe pressure).\n\nIf queries slow down and both series spike, the host is likely limited by RAM or I/O throughput.\n\nSee also major page faults rate panel in Troubleshooting section if this metric continued to be high.",
+          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -3024,7 +3024,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\nThe lower the better.",
+          "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one runnable thread blocked on IO (disk, NVMe, network-storage) while others could still make progress.\n- stalled: all non-idle threads simultaneously waiting on `I/O`.\n\nIf stalled > 0, consider increasing queue depth on NVMe, raising blk-mq budgets, or relaxing cgroup I/O limits.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -3691,7 +3691,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows the time goroutines have spent in runnable state before actually running. The lower is better.\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
+          "description": "Shows the time goroutines have spent in runnable state before actually running.\n\n**Lower is better.**\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -4511,7 +4511,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows cache miss ratio. Lower is better.",
+          "description": "Shows cache miss ratio.\n\n**Lower is better.**",
           "fieldConfig": {
             "defaults": {
               "color": {

dashboards/vm/vmagent.json

@@ -2042,7 +2042,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html). Helps troubleshoot high CPU usage or throttling.\nLower is better.\n\n- waiting: The percentage of time at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: The percentage of time all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 1%. It only becomes a concern if it consistently climbs above 5–10% and aligns with latency spikes or GC slowdowns.",
+          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 100ms. It only becomes a concern if it consistently climbs above 50-100ms and aligns with latency spikes or GC slowdowns.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2165,7 +2165,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\nLower is better.\n\n- waiting: Time fraction where at least one thread was blocked on memory.\n- stalled: Time fraction where every thread was blocked on memory (severe pressure).\n\nIf queries slow down and both series spike, the host is likely limited by RAM or I/O throughput.",
+          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2542,7 +2542,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\nThe lower the better.",
+          "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one runnable thread blocked on IO (disk, NVMe, network-storage) while others could still make progress.\n- stalled: all non-idle threads simultaneously waiting on `I/O`.\n\nIf stalled > 0, consider increasing queue depth on NVMe, raising blk-mq budgets, or relaxing cgroup I/O limits.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -3015,7 +3015,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows the time goroutines have spent in runnable state before actually running. The lower is better.\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
+          "description": "Shows the time goroutines have spent in runnable state before actually running.\n\n**Lower is better.**\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -6201,7 +6201,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "The rate of ignored samples during aggregation. \nStream aggregation will drop samples with NaN values, or samples with too old timestamps. See https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#ignoring-old-samples ",
+          "description": "The rate of dropped samples during aggregation. \nStream aggregation will drop samples with NaN values, too old timestamps or samples identified as duplicates during deduplication. See https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#ignoring-old-samples ",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -6282,14 +6282,14 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(rate(vm_streamaggr_ignored_samples_total{job=~\"$job\",instance=~\"$instance\", url=~\"$url\"}[$__rate_interval]) > 0) without (instance, pod)",
+              "expr": "sum(rate({__name__=~\"vm_streamaggr_ignored_samples_total|vm_streamaggr_dedup_dropped_samples_total\", job=~\"$job\",instance=~\"$instance\", url=~\"$url\"}[$__rate_interval]) > 0) without (instance, pod)",
               "instant": false,
               "legendFormat": "__auto",
               "range": true,
               "refId": "A"
             }
           ],
-          "title": "Ignored samples ($instance)",
+          "title": "Dropped samples ($instance)",
           "type": "timeseries"
         },
         {

dashboards/vm/vmalert.json

@@ -1719,7 +1719,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html). Helps troubleshoot high CPU usage or throttling.\nLower is better.\n\n- waiting: The percentage of time at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: The percentage of time all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 1%. It only becomes a concern if it consistently climbs above 5–10% and aligns with latency spikes or GC slowdowns.",
+          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 100ms. It only becomes a concern if it consistently climbs above 50-100ms and aligns with latency spikes or GC slowdowns.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -1840,7 +1840,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\nLower is better.\n\n- waiting: Time fraction where at least one thread was blocked on memory.\n- stalled: Time fraction where every thread was blocked on memory (severe pressure).\n\nIf queries slow down and both series spike, the host is likely limited by RAM or I/O throughput.",
+          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2177,7 +2177,7 @@
             "type": "victoriametrics-metrics-datasource",
             "uid": "$ds"
           },
-          "description": "Shows the time goroutines have spent in runnable state before actually running. The lower is better.\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
+          "description": "Shows the time goroutines have spent in runnable state before actually running.\n\n**Lower is better.**\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
           "fieldConfig": {
             "defaults": {
               "color": {

dashboards/vmagent.json

@@ -2041,7 +2041,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html). Helps troubleshoot high CPU usage or throttling.\nLower is better.\n\n- waiting: The percentage of time at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: The percentage of time all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 1%. It only becomes a concern if it consistently climbs above 5–10% and aligns with latency spikes or GC slowdowns.",
+          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 100ms. It only becomes a concern if it consistently climbs above 50-100ms and aligns with latency spikes or GC slowdowns.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2164,7 +2164,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\nLower is better.\n\n- waiting: Time fraction where at least one thread was blocked on memory.\n- stalled: Time fraction where every thread was blocked on memory (severe pressure).\n\nIf queries slow down and both series spike, the host is likely limited by RAM or I/O throughput.",
+          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2541,7 +2541,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\nThe lower the better.",
+          "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one runnable thread blocked on IO (disk, NVMe, network-storage) while others could still make progress.\n- stalled: all non-idle threads simultaneously waiting on `I/O`.\n\nIf stalled > 0, consider increasing queue depth on NVMe, raising blk-mq budgets, or relaxing cgroup I/O limits.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -3014,7 +3014,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows the time goroutines have spent in runnable state before actually running. The lower is better.\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
+          "description": "Shows the time goroutines have spent in runnable state before actually running.\n\n**Lower is better.**\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -6200,7 +6200,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "The rate of ignored samples during aggregation. \nStream aggregation will drop samples with NaN values, or samples with too old timestamps. See https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#ignoring-old-samples ",
+          "description": "The rate of dropped samples during aggregation. \nStream aggregation will drop samples with NaN values, too old timestamps or samples identified as duplicates during deduplication. See https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#ignoring-old-samples ",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -6281,14 +6281,14 @@
                 "uid": "$ds"
               },
               "editorMode": "code",
-              "expr": "sum(rate(vm_streamaggr_ignored_samples_total{job=~\"$job\",instance=~\"$instance\", url=~\"$url\"}[$__rate_interval]) > 0) without (instance, pod)",
+              "expr": "sum(rate({__name__=~\"vm_streamaggr_ignored_samples_total|vm_streamaggr_dedup_dropped_samples_total\", job=~\"$job\",instance=~\"$instance\", url=~\"$url\"}[$__rate_interval]) > 0) without (instance, pod)",
               "instant": false,
               "legendFormat": "__auto",
               "range": true,
               "refId": "A"
             }
           ],
-          "title": "Ignored samples ($instance)",
+          "title": "Dropped samples ($instance)",
           "type": "timeseries"
         },
         {

dashboards/vmalert.json

@@ -1718,7 +1718,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html). Helps troubleshoot high CPU usage or throttling.\nLower is better.\n\n- waiting: The percentage of time at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: The percentage of time all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 1%. It only becomes a concern if it consistently climbs above 5–10% and aligns with latency spikes or GC slowdowns.",
+          "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 100ms. It only becomes a concern if it consistently climbs above 50-100ms and aligns with latency spikes or GC slowdowns.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -1839,7 +1839,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\nLower is better.\n\n- waiting: Time fraction where at least one thread was blocked on memory.\n- stalled: Time fraction where every thread was blocked on memory (severe pressure).\n\nIf queries slow down and both series spike, the host is likely limited by RAM or I/O throughput.",
+          "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\n**Lower is better.**\n\nPressure is measured as amount of time within 1sec time window the process was:\n- waiting: at least one thread was blocked on memory.\n- stalled: every thread was blocked on memory (severe pressure).\n\nElevated memory pressure can slowdown the process performance by utilizing more disk IO. Consider increasing amount of available RAM limit or decreasing the load on the process.\n\nSee major page faults rate panel in Troubleshooting section if this metric continued to be high.",
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -2176,7 +2176,7 @@
             "type": "prometheus",
             "uid": "$ds"
           },
-          "description": "Shows the time goroutines have spent in runnable state before actually running. The lower is better.\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
+          "description": "Shows the time goroutines have spent in runnable state before actually running.\n\n**Lower is better.**\n\nHigh values or values exceeding the threshold is usually a sign of            insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.",
           "fieldConfig": {
             "defaults": {
               "color": {

deployment/docker/compose-vm-cluster.yml

@@ -3,7 +3,7 @@ services:
   #  It scrapes targets defined in --promscrape.config
   #  And forward them to --remoteWrite.url
   vmagent:
-    image: victoriametrics/vmagent:v1.144.0
+    image: victoriametrics/vmagent:v1.146.0
     depends_on:
       - "vmauth"
     ports:
@@ -42,14 +42,14 @@ services:
   # vmstorage shards. Each shard receives 1/N of all metrics sent to vminserts,
   # where N is number of vmstorages (2 in this case).
   vmstorage-1:
-    image: victoriametrics/vmstorage:v1.144.0-cluster
+    image: victoriametrics/vmstorage:v1.146.0-cluster
     volumes:
       - strgdata-1:/storage
     command:
       - "--storageDataPath=/storage"
     restart: always
   vmstorage-2:
-    image: victoriametrics/vmstorage:v1.144.0-cluster
+    image: victoriametrics/vmstorage:v1.146.0-cluster
     volumes:
       - strgdata-2:/storage
     command:
@@ -59,7 +59,7 @@ services:
   # vminsert is ingestion frontend. It receives metrics pushed by vmagent,
   # pre-process them and distributes across configured vmstorage shards.
   vminsert-1:
-    image: victoriametrics/vminsert:v1.144.0-cluster
+    image: victoriametrics/vminsert:v1.146.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -68,7 +68,7 @@ services:
       - "--storageNode=vmstorage-2:8400"
     restart: always
   vminsert-2:
-    image: victoriametrics/vminsert:v1.144.0-cluster
+    image: victoriametrics/vminsert:v1.146.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -80,7 +80,7 @@ services:
   # vmselect is a query fronted. It serves read queries in MetricsQL or PromQL.
   # vmselect collects results from configured `--storageNode` shards.
   vmselect-1:
-    image: victoriametrics/vmselect:v1.144.0-cluster
+    image: victoriametrics/vmselect:v1.146.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -90,7 +90,7 @@ services:
       - "--vmalert.proxyURL=http://vmalert:8880"
     restart: always
   vmselect-2:
-    image: victoriametrics/vmselect:v1.144.0-cluster
+    image: victoriametrics/vmselect:v1.146.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -105,7 +105,7 @@ services:
   # read requests from Grafana, vmui, vmalert among vmselects.
   # It can be used as an authentication proxy.
   vmauth:
-    image: victoriametrics/vmauth:v1.144.0
+    image: victoriametrics/vmauth:v1.146.0
     depends_on:
       - "vmselect-1"
       - "vmselect-2"
@@ -119,7 +119,7 @@ services:
 
   # vmalert executes alerting and recording rules
   vmalert:
-    image: victoriametrics/vmalert:v1.144.0
+    image: victoriametrics/vmalert:v1.146.0
     depends_on:
       - "vmauth"
     ports:

deployment/docker/compose-vm-single.yml

@@ -3,7 +3,7 @@ services:
   #  It scrapes targets defined in --promscrape.config
   #  And forward them to --remoteWrite.url
   vmagent:
-    image: victoriametrics/vmagent:v1.144.0
+    image: victoriametrics/vmagent:v1.146.0
     depends_on:
       - "victoriametrics"
     ports:
@@ -18,7 +18,7 @@ services:
   # VictoriaMetrics instance, a single process responsible for
   # storing metrics and serve read requests.
   victoriametrics:
-    image: victoriametrics/victoria-metrics:v1.144.0
+    image: victoriametrics/victoria-metrics:v1.146.0
     ports:
       - 8428:8428
       - 8089:8089
@@ -59,7 +59,7 @@ services:
 
   # vmalert executes alerting and recording rules
   vmalert:
-    image: victoriametrics/vmalert:v1.144.0
+    image: victoriametrics/vmalert:v1.146.0
     depends_on:
       - "victoriametrics"
       - "alertmanager"

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

@@ -1,6 +1,6 @@
 services:
   vmagent:
-    image: victoriametrics/vmagent:v1.144.0
+    image: victoriametrics/vmagent:v1.146.0
     depends_on:
       - "victoriametrics"
     ports:
@@ -14,7 +14,7 @@ services:
     restart: always
 
   victoriametrics:
-    image: victoriametrics/victoria-metrics:v1.144.0
+    image: victoriametrics/victoria-metrics:v1.146.0
     ports:
       - 8428:8428
     volumes:
@@ -40,7 +40,7 @@ services:
     restart: always
 
   vmalert:
-    image: victoriametrics/vmalert:v1.144.0
+    image: victoriametrics/vmalert:v1.146.0
     depends_on:
       - "victoriametrics"
     ports:
@@ -59,7 +59,7 @@ services:
       - '--external.alert.source=explore?orgId=1&left=["now-1h","now","VictoriaMetrics",{"expr": },{"mode":"Metrics"},{"ui":[true,true,true,"none"]}]'
     restart: always
   vmanomaly:
-    image: victoriametrics/vmanomaly:v1.29.4
+    image: victoriametrics/vmanomaly:v1.29.7
     depends_on:
       - "victoriametrics"
     ports:

deployment/docker/vmanomaly/vmanomaly-integration/vmanomaly_guide_dashboard.json

@@ -43,7 +43,7 @@
         "content": "If you don't observe any data initially, please wait a few minutes for it to appear. \n\nUpon the first running the guide (if there is not enough node_exporter monitoring data collected in your system), you may notice a significant number of false positive anomalies found. The predictions will become more accurate with at least two weeks' (full `fit_window`) worth of data provided to vmanomaly.\n\nEach row displays information for a distinct mode. The query used for anomaly detection is `sum(rate(node_cpu_seconds_total[5m])) by (mode, instance, job)`.\n",
         "mode": "markdown"
       },
-      "pluginVersion": "10.2.1",
+      "pluginVersion": "12.2.0",
       "title": "Overview",
       "type": "text"
     },

docs/Makefile

@@ -32,6 +32,17 @@ docs-image:
 		--platform $(DOCKER_PLATFORM) \
 		vmdocs
 
+docs-check-links: docs-image
+	rm -rf vmdocs/public
+	docker run \
+		--rm \
+		--platform $(DOCKER_PLATFORM) \
+		-v ./vmdocs:/opt/docs \
+		$(shell for d in ./docs/*/; do printf ' -v %s:/opt/docs/content/%s' "$${d}" "$$(basename $${d})"; done) \
+		--entrypoint /bin/sh \
+		vmdocs-docker-package \
+			-c "yarn install && hugo --minify && yarn run check-links"
+
 docs-debug: docs docs-image
 	docker run \
 		--rm \
@@ -271,6 +282,8 @@ endif
 	(cd /tmp/vm-opensource && ./bin/vmctl remote-read -help > /tmp/vmctl_remote-read_flags_tmp.md)
 	(cd /tmp/vm-opensource && ./bin/vmctl prometheus -help > /tmp/vmctl_prometheus_flags_tmp.md)
 	(cd /tmp/vm-opensource && ./bin/vmctl vm-native -help > /tmp/vmctl_vm-native_flags_tmp.md)
+	(cd /tmp/vm-opensource && ./bin/vmctl thanos -help > /tmp/vmctl_thanos_flags_tmp.md)
+	(cd /tmp/vm-opensource && ./bin/vmctl mimir -help > /tmp/vmctl_mimir_flags_tmp.md)
 
 	echo "$$FLAGS_HEADER" > docs/victoriametrics/vmctl/vmctl_flags.md && \
 	cat /tmp/vmctl_flags_tmp.md >> docs/victoriametrics/vmctl/vmctl_flags.md && \
@@ -296,6 +309,14 @@ endif
 	cat /tmp/vmctl_vm-native_flags_tmp.md >> docs/victoriametrics/vmctl/vmctl_vm-native_flags.md && \
 	printf '```\n' >> docs/victoriametrics/vmctl/vmctl_vm-native_flags.md
 
+	echo "$$FLAGS_HEADER" > docs/victoriametrics/vmctl/vmctl_thanos_flags.md && \
+	cat /tmp/vmctl_thanos_flags_tmp.md >> docs/victoriametrics/vmctl/vmctl_thanos_flags.md && \
+	printf '```\n' >> docs/victoriametrics/vmctl/vmctl_thanos_flags.md
+
+	echo "$$FLAGS_HEADER" > docs/victoriametrics/vmctl/vmctl_mimir_flags.md && \
+	cat /tmp/vmctl_mimir_flags_tmp.md >> docs/victoriametrics/vmctl/vmctl_mimir_flags.md && \
+	printf '```\n' >> docs/victoriametrics/vmctl/vmctl_mimir_flags.md
+
 	# remove Total time line from all vmctl flag files to reduce diffs noise
 	sed -i '/Total time:/d' docs/victoriametrics/vmctl/vmctl_flags.md
 	sed -i '/Total time:/d' docs/victoriametrics/vmctl/vmctl_opentsdb_flags.md
@@ -303,6 +324,8 @@ endif
 	sed -i '/Total time:/d' docs/victoriametrics/vmctl/vmctl_remote-read_flags.md
 	sed -i '/Total time:/d' docs/victoriametrics/vmctl/vmctl_prometheus_flags.md
 	sed -i '/Total time:/d' docs/victoriametrics/vmctl/vmctl_vm-native_flags.md
+	sed -i '/Total time:/d' docs/victoriametrics/vmctl/vmctl_thanos_flags.md
+	sed -i '/Total time:/d' docs/victoriametrics/vmctl/vmctl_mimir_flags.md
 
 	# remove Version line and the actual version line from vmctl_flags.md to reduce diffs noise
 	sed -i '/^VERSION:/,+1d' docs/victoriametrics/vmctl/vmctl_flags.md

docs/anomaly-detection/CHANGELOG.md

@@ -14,6 +14,39 @@ aliases:
 ---
 Please find the changelog for VictoriaMetrics Anomaly Detection below.
 
+## v1.29.7
+Released: 2026-06-25
+
+- UI: updated [vmanomaly UI](https://docs.victoriametrics.com/anomaly-detection/ui/) from [v1.7.1](https://docs.victoriametrics.com/anomaly-detection/ui/#v171) to [v1.7.2](https://docs.victoriametrics.com/anomaly-detection/ui/#v172), see respective [release notes](https://docs.victoriametrics.com/anomaly-detection/ui/#v172) for details.
+
+- IMPROVEMENT: Increased high-cardinality inference scaling by optionally scattering periodic infer jobs to reduce contention on shared resources (e.g. datasource, CPU, RAM) when `settings.n_workers > 1` and `scheduler.infer_every` is smaller than the total time to fetch and process all queries. This is controlled by new `scatter_infer_jobs` boolean argument of [Periodic Scheduler](https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#parameters-1) (default: `false`).
+
+- IMPROVEMENT: Optimized internal batching for reader post-fetch series processing, exposing reader processing queue depth, and clarifying inference skip logs after data fetch timeouts.
+
+- IMPROVEMENT: Refined `VmReader` and `VLogsReader` logging after datasource request failures by suppressing the follow-up generic "No data" or "No unseen data" warning for failed fetches. Failed requests now keep the original datasource error while empty successful responses still emit the no-data warning.
+
+## v1.29.6
+Released: 2026-06-17
+
+- BUGFIX: Fixed `VLogsReader` startup and query execution when `tenant_id` is omitted or provided in short account-only form such as `"0"`. Omitted or empty tenant IDs are treated as single-node/no-tenant mode, and account-only tenant IDs are expanded to `accountID:0` before adding VictoriaLogs `AccountID`/`ProjectID` params or VM tenant labels.
+
+- BUGFIX: Hardened [`OnlineMADModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-mad) anomaly scoring for perfectly constant time series (all values identical). The model now keeps a small deterministic prediction interval when the learned MAD is zero, so values deviating from an unknown constant baseline can produce `anomaly_score > 1` (previously, all anomaly scores were `0`).
+
+## v1.29.5
+Released: 2026-06-11
+
+- UI: Updated [vmanomaly UI](https://docs.victoriametrics.com/anomaly-detection/ui/) from [v1.7.0](https://docs.victoriametrics.com/anomaly-detection/ui/#v170) to [v1.7.1](https://docs.victoriametrics.com/anomaly-detection/ui/#v171), see respective [release notes](https://docs.victoriametrics.com/anomaly-detection/ui/#v171) for details.
+
+- IMPROVEMENT: Redesigned [hot reload](https://docs.victoriametrics.com/anomaly-detection/components/#hot-reload) config change detection to content-based polling with configurable `-configCheckInterval`, improving reliability for Kubernetes ConfigMap symlink rotations and other filesystems where event delivery can be inconsistent.
+
+- IMPROVEMENT: Refined config validation errors for broken or invalid config sections, so startup and reload failures point to the affected section more clearly (e.g. YAML indentation typos).
+
+- IMPROVEMENT: Tightened config validation for [`PeriodicScheduler`](https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#periodic-scheduler) `infer_every` and [`IsolationForestModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#isolation-forest-multivariate) `contamination`, including clearer handling of missing scheduler intervals, numeric contamination strings, and invalid non-finite values.
+
+- BUGFIX: Fixed a multiprocessing startup issue with `settings.n_workers > 1` that could leave scheduled data fetch or successive inference jobs stuck and repeatedly skipped by internal scheduler.
+
+- BUGFIX: Bounded [`VmReader`](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader) and [`VLogsReader`](https://docs.victoriametrics.com/anomaly-detection/components/reader/#victorialogs-reader) data fetch and post-fetch processing waits so stalled datasource reads or multiprocessing dataframe creation no longer keep [`PeriodicScheduler`](https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#periodic-scheduler) `data_fetch` jobs running indefinitely. Previously, such stuck jobs could keep internal scheduler's `max_instances=1` slot per (scheduler, query) pair occupied, causing future data fetch, fit, or infer runs to be skipped until vmanomaly was restarted. The config validator now also warns when the configured reader timeout budget can exceed the connected scheduler interval.
+
 ## v1.29.4
 Released: 2026-05-15
 
@@ -164,7 +197,7 @@ Released: 2025-10-02
 
 - FEATURE: Introduced vmui-like [UI](https://docs.victoriametrics.com/anomaly-detection/ui/) for `vmanomaly` service to simplify the configuration and backtesting of anomaly detection models before it goes to production. It provides an intuitive interface to finetune model configurations, visualize its predictions and anomaly scores, and perform backtesting on historical data. The UI is accessible via a web browser and can be run as a [standalone service](https://docs.victoriametrics.com/anomaly-detection/ui/#preset-usage) or [integrated with productionalized deployments](https://docs.victoriametrics.com/anomaly-detection/ui/#mixed-usage). For more details, refer to the [documentation](https://docs.victoriametrics.com/anomaly-detection/ui/).
 
-- FEATURE: Added support for reading data from [VictoriaLogs stats queries](https://docs.victoriametrics.com/victorialogs/querying/#querying-log-range-stats) with `VLogsReader`. This reader allows querying and analyzing log data stored in VictoriaLogs, enabling anomaly detection on metrics generated from logs. It supports similar configuration options as `VmReader`, including `datasource_url`, `tenant_id`, `queries`, etc. For more details, refer to the [documentation](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vlogs-reader). It can be also used in [UI mode](https://docs.victoriametrics.com/anomaly-detection/ui/) for backtesting log-based anomaly detection configurations.
+- FEATURE: Added support for reading data from [VictoriaLogs stats queries](https://docs.victoriametrics.com/victorialogs/querying/#querying-log-range-stats) with `VLogsReader`. This reader allows querying and analyzing log data stored in VictoriaLogs, enabling anomaly detection on metrics generated from logs. It supports similar configuration options as `VmReader`, including `datasource_url`, `tenant_id`, `queries`, etc. For more details, refer to the [documentation](https://docs.victoriametrics.com/anomaly-detection/components/reader/#victorialogs-reader). It can be also used in [UI mode](https://docs.victoriametrics.com/anomaly-detection/ui/) for backtesting log-based anomaly detection configurations.
 
 - IMPROVEMENT: Resolved the case in the [`IsolationForestModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#isolation-forest-multivariate) with `provide_series` common model [argument](https://docs.victoriametrics.com/anomaly-detection/components/models/#provide-series) including `yhat.*` series (prediction and confidence boundaries), which are not produced by this model. Now config validation will fail with a clear error message if such series names are requested.
 
@@ -273,7 +306,7 @@ Released: 2025-06-05
 
 - FEATURE: Added `decay` [argument](https://docs.victoriametrics.com/anomaly-detection/components/models/#decay) to [online models](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-models). This parameters allows for newer data to be weighted more heavily in online models. By default this is set to 1 which means all data points are weighted the same to maintain backward compatibility with existing configs. The closer this value is to 0 the more important new data is.
 
-- IMPROVEMENT: **Restored back parallelization** in the read/fit/infer pipeline, previously disabled in [v1.22.0](#v1220-experimental) due to deadlock issues. The new implementation prevents deadlocks, allowing to control the parallelization level via `n_workers` in [settings section](https://docs.victoriametrics.com/anomaly-detection/components/settings/). It's suggested to upgrade from [v1.22.0](#v1220) - [v1.22.1](#v1221) to this version to regain the performance benefits of parallel processing.
+- IMPROVEMENT: **Restored back parallelization** in the read/fit/infer pipeline, previously disabled in [v1.22.0](#v1220-experimental) due to deadlock issues. The new implementation prevents deadlocks, allowing to control the parallelization level via `n_workers` in [settings section](https://docs.victoriametrics.com/anomaly-detection/components/settings/). It's suggested to upgrade from [v1.22.0](#v1220-experimental) - [v1.22.1](#v1221) to this version to regain the performance benefits of parallel processing.
 
 - IMPROVEMENT: Added `--dryRun` [argument](https://docs.victoriametrics.com/anomaly-detection/quickstart/#command-line-arguments) to `vmanomaly` to enable dry run mode. This mode allows to validate configuration without executing any actual operations and doesn't require a license. It is particularly useful to test the configurations before deploying them in a production environment.
 

docs/anomaly-detection/FAQ.md

@@ -53,7 +53,7 @@ Please see example graph illustrating this logic below:
 
 **VictoriaMetrics (metrics):** use full [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/) for selection, sampling, and processing; [global filters](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#prometheus-querying-api-enhancements) are also supported. See the [VmReader](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader) for the details.
 
-**VictoriaLogs (logs → metrics):** {{% available_from "v1.26.0" anomaly %}} use [LogsQL](https://docs.victoriametrics.com/victorialogs/logsql/) via the [`VLogsReader`](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vlogs-reader) to create log-derived or traces-derived metrics for anomaly detection (e.g., error rates, request latencies, error spans count). 
+**VictoriaLogs (logs → metrics):** {{% available_from "v1.26.0" anomaly %}} use [LogsQL](https://docs.victoriametrics.com/victorialogs/logsql/) via the [`VLogsReader`](https://docs.victoriametrics.com/anomaly-detection/components/reader/#victorialogs-reader) to create log-derived or traces-derived metrics for anomaly detection (e.g., error rates, request latencies, error spans count). 
 
 > [!NOTE]
 > Please note that only LogsQL queries with [stats pipe](https://docs.victoriametrics.com/victorialogs/logsql/#stats-pipe) functions [subset](https://docs.victoriametrics.com/anomaly-detection/components/reader/#valid-stats-functions) are supported, as they produce **numeric** time series.
@@ -423,7 +423,7 @@ services:
   # ...
   vmanomaly:
     container_name: vmanomaly
-    image: victoriametrics/vmanomaly:v1.29.4
+    image: victoriametrics/vmanomaly:v1.29.7
     # ...
     restart: always
     volumes:
@@ -641,7 +641,7 @@ options:
 Here’s an example of using the config splitter to divide configurations based on the `extra_filters` argument from the reader section:
 
 ```sh
-docker pull victoriametrics/vmanomaly:v1.29.4 && docker image tag victoriametrics/vmanomaly:v1.29.4 vmanomaly
+docker pull victoriametrics/vmanomaly:v1.29.7 && docker image tag victoriametrics/vmanomaly:v1.29.7 vmanomaly
 ```
 
 ```sh