Compare commits

..

1 Commits

Author SHA1 Message Date
Haley Wang
884da8ecff add extra log for resolving backend address 2026-04-19 15:28:36 +08:00
168 changed files with 2474 additions and 4895 deletions

View File

@@ -1,3 +1 @@
**PLEASE REMOVE LINE BELOW BEFORE SUBMITTING**
Before creating the PR, make sure you have read and followed the [VictoriaMetrics contributing guidelines](https://docs.victoriametrics.com/victoriametrics/contributing/#pull-request-checklist).
Before creating the PR, please read [VictoriaMetrics contributing guidelines](https://docs.victoriametrics.com/victoriametrics/contributing/#pull-request-checklist) and remove this line after confirming you understand and follow them.

View File

@@ -27,7 +27,7 @@ jobs:
- run: go version
- name: Cache Go artifacts
uses: actions/cache@v5
uses: actions/cache@v4
with:
path: |
~/.cache/go-build

View File

@@ -40,7 +40,7 @@ jobs:
- run: go version
- name: Cache Go artifacts
uses: actions/cache@v5
uses: actions/cache@v4
with:
path: |
~/.cache/go-build
@@ -50,14 +50,14 @@ jobs:
restore-keys: go-artifacts-${{ runner.os }}-codeql-analyze-${{ steps.go.outputs.go-version }}-
- name: Initialize CodeQL
uses: github/codeql-action/init@v4.35.1
uses: github/codeql-action/init@v4
with:
languages: go
- name: Autobuild
uses: github/codeql-action/autobuild@v4.35.1
uses: github/codeql-action/autobuild@v4
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v4.35.1
uses: github/codeql-action/analyze@v4
with:
category: 'language:go'

View File

@@ -47,7 +47,7 @@ jobs:
- run: go version
- name: Cache golangci-lint
uses: actions/cache@v5
uses: actions/cache@v4
with:
path: |
~/.cache/golangci-lint

View File

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

View File

@@ -77,6 +77,16 @@ func insertRows(at *auth.Token, tss []prompb.TimeSeries, mms []prompb.MetricMeta
var metadataTotal int
if prommetadata.IsEnabled() {
var accountID, projectID uint32
if at != nil {
accountID = at.AccountID
projectID = at.ProjectID
for i := range mms {
mm := &mms[i]
mm.AccountID = accountID
mm.ProjectID = projectID
}
}
ctx.WriteRequest.Metadata = mms
metadataTotal = len(mms)
}

View File

@@ -75,6 +75,11 @@ func insertRows(at *auth.Token, rows []prometheus.Row, mms []prometheus.Metadata
Samples: samples[len(samples)-1:],
})
}
var accountID, projectID uint32
if at != nil {
accountID = at.AccountID
projectID = at.ProjectID
}
for i := range mms {
mm := &mms[i]
mmsDst = append(mmsDst, prompb.MetricMetadata{
@@ -83,6 +88,8 @@ func insertRows(at *auth.Token, rows []prometheus.Row, mms []prometheus.Metadata
Type: mm.Type,
// there is no unit in Prometheus exposition formats
AccountID: accountID,
ProjectID: projectID,
})
}
ctx.WriteRequest.Timeseries = tssDst

View File

@@ -72,6 +72,11 @@ func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, mms []prompb.Met
var metadataTotal int
if prommetadata.IsEnabled() {
var accountID, projectID uint32
if at != nil {
accountID = at.AccountID
projectID = at.ProjectID
}
for i := range mms {
mm := &mms[i]
mmsDst = append(mmsDst, prompb.MetricMetadata{
@@ -80,8 +85,8 @@ func insertRows(at *auth.Token, timeseries []prompb.TimeSeries, mms []prompb.Met
Type: mm.Type,
Unit: mm.Unit,
AccountID: mm.AccountID,
ProjectID: mm.ProjectID,
AccountID: accountID,
ProjectID: projectID,
})
}
ctx.WriteRequest.Metadata = mmsDst

View File

@@ -211,9 +211,6 @@ func (wr *writeRequest) copyMetadata(dst, src *prompb.MetricMetadata) {
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)
bufLen := len(wr.metadatabuf)

View File

@@ -398,7 +398,7 @@ func tryPush(at *auth.Token, wr *prompb.WriteRequest, forceDropSamplesOnFailure
// Push metadata separately from time series, since it doesn't need sharding,
// relabeling, stream aggregation, deduplication, etc.
if !tryPushMetadataToRemoteStorages(at, rwctxs, mms, forceDropSamplesOnFailure) {
if !tryPushMetadataToRemoteStorages(rwctxs, mms, forceDropSamplesOnFailure) {
return false
}
@@ -536,18 +536,11 @@ func pushTimeSeriesToRemoteStoragesTrackDropped(tss []prompb.TimeSeries) {
}
}
func tryPushMetadataToRemoteStorages(at *auth.Token, rwctxs []*remoteWriteCtx, mms []prompb.MetricMetadata, forceDropSamplesOnFailure bool) bool {
func tryPushMetadataToRemoteStorages(rwctxs []*remoteWriteCtx, mms []prompb.MetricMetadata, forceDropSamplesOnFailure bool) bool {
if len(mms) == 0 {
// Nothing to push
return true
}
if at != nil {
for idx := range mms {
mm := &mms[idx]
mm.AccountID = at.AccountID
mm.ProjectID = at.ProjectID
}
}
// Do not shard metadata even if -remoteWrite.shardByURL is set, just replicate it among rwctxs.
// Since metadata is usually small and there is no guarantee that metadata can be sent to
// the same remote storage with the corresponding metrics.

View File

@@ -222,9 +222,6 @@ func (r *Rule) Validate() error {
if r.Expr == "" {
return fmt.Errorf("expression can't be empty")
}
if _, ok := r.Labels["__name__"]; ok {
return fmt.Errorf("invalid rule label __name__")
}
return checkOverflow(r.XXX, "rule")
}

View File

@@ -136,9 +136,6 @@ func TestRuleValidate(t *testing.T) {
if err := (&Rule{Alert: "alert"}).Validate(); err == nil {
t.Fatalf("expected empty expr error")
}
if err := (&Rule{Record: "record", Expr: "sum(test)", Labels: map[string]string{"__name__": "test"}}).Validate(); err == nil {
t.Fatalf("invalid rule label; got %s", err)
}
if err := (&Rule{Alert: "alert", Expr: "test>0"}).Validate(); err != nil {
t.Fatalf("expected valid rule; got %s", err)
}

View File

@@ -87,7 +87,6 @@ func (m *Metric) DelLabel(key string) {
for i, l := range m.Labels {
if l.Name == key {
m.Labels = append(m.Labels[:i], m.Labels[i+1:]...)
break
}
}
}

View File

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

View File

@@ -312,11 +312,9 @@ type labelSet struct {
// On k conflicts in origin set, the original value is preferred and copied
// to processed with `exported_%k` key. The copy happens only if passed v isn't equal to origin[k] value.
func (ls *labelSet) add(k, v string) {
// do not add label with empty value to the result, as it has no meaning:
// if the label already exists in the original query result, remove it to preserve compatibility with relabeling, see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10766.
// otherwise, ignore the label, see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9984.
// do not add label with empty value, since it has no meaning.
// see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9984
if v == "" {
delete(ls.processed, k)
return
}
ls.processed[k] = v

View File

@@ -1363,7 +1363,6 @@ func TestAlertingRule_ToLabels(t *testing.T) {
{Name: "instance", Value: "0.0.0.0:8800"},
{Name: "group", Value: "vmalert"},
{Name: "alertname", Value: "ConfigurationReloadFailure"},
{Name: "pod", Value: "vmalert-0"},
},
Values: []float64{1},
Timestamps: []int64{time.Now().UnixNano()},
@@ -1375,7 +1374,6 @@ func TestAlertingRule_ToLabels(t *testing.T) {
"group": "vmalert", // this shouldn't have effect since value in metric is equal
"invalid_label": "{{ .Values.mustRuntimeFail }}",
"empty_label": "", // this should be dropped
"pod": "", // this should remove the pod label from query result
},
Expr: "sum(vmalert_alerting_rules_error) by(instance, group, alertname) > 0",
Name: "AlertingRulesError",
@@ -1387,7 +1385,6 @@ func TestAlertingRule_ToLabels(t *testing.T) {
"group": "vmalert",
"alertname": "ConfigurationReloadFailure",
"alertgroup": "vmalert",
"pod": "vmalert-0",
"invalid_label": `error evaluating template: template: :1:298: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
}

View File

@@ -8,7 +8,6 @@ import (
"hash/fnv"
"maps"
"net/url"
"path"
"sync"
"time"
@@ -43,9 +42,6 @@ var (
"For example, if lookback=1h then range from now() to now()-1h will be scanned.")
maxStartDelay = flag.Duration("group.maxStartDelay", 5*time.Minute, "Defines the max delay before starting the group evaluation. Group's start is artificially delayed for random duration on interval"+
" [0..min(--group.maxStartDelay, group.interval)]. This helps smoothing out the load on the configured datasource, so evaluations aren't executed too close to each other.")
ruleStripFilePath = flag.Bool("rule.stripFilePath", false, "Whether to strip rule file paths in logs and all API responses, including /metrics. "+
"For example, file path '/path/to/tenant_id/rules.yml' will be stripped to 'groupHashID/rules.yml'. "+
"This flag may be useful for hiding sensitive information in file paths, such as S3 bucket details.")
)
// Group is an entity for grouping rules
@@ -151,12 +147,6 @@ func NewGroup(cfg config.Group, qb datasource.QuerierBuilder, defaultInterval ti
g.EvalDelay = &cfg.EvalDelay.D
}
g.id = g.CreateID()
// strip file path from group.File after generated group ID when ruleStripFilePath is set,
// so it won't be exposed in logs and api responses
if *ruleStripFilePath {
_, filename := path.Split(g.File)
g.File = fmt.Sprintf("%d/%s", g.id, filename)
}
for _, h := range cfg.Headers {
g.Headers[h.Key] = h.Value
}
@@ -419,9 +409,6 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
g.mu.Unlock()
defer g.evalCancel()
// start the interval ticker before the first evaluation,
// so that the evaluation timestamps of groups with the `eval_offset` option are also aligned,
// see https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10773
t := time.NewTicker(g.Interval)
defer t.Stop()

View File

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

View File

@@ -293,11 +293,9 @@ func (rr *RecordingRule) toTimeSeries(m datasource.Metric) prompb.TimeSeries {
}
// add extra labels configured by user
for k := range rr.Labels {
// do not add label with empty value to the result, as it has no meaning:
// if the label already exists in the original query result, remove it to preserve compatibility with relabeling, see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10766.
// otherwise, ignore the label, see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9984.
// do not add label with empty value, since it has no meaning.
// see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9984
if rr.Labels[k] == "" {
m.DelLabel(k)
continue
}
existingLabel := promrelabel.GetLabelByName(m.Labels, k)

View File

@@ -163,13 +163,11 @@ func TestRecordingRule_Exec(t *testing.T) {
f(&RecordingRule{
Name: "job:foo",
Labels: map[string]string{
"source": "test",
"empty_label": "", // this should be dropped
"pod": "", // this should remove the pod label from query result
"source": "test",
},
}, [][]datasource.Metric{{
metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "foo", "pod", "vmalert-0"),
metricWithValueAndLabels(t, 1, "__name__", "bar", "job", "bar", "source", "origin", "pod", "vmalert-1"),
metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "foo"),
metricWithValueAndLabels(t, 1, "__name__", "bar", "job", "bar", "source", "origin"),
metricWithValueAndLabels(t, 1, "__name__", "baz", "job", "baz", "source", "test"),
}}, [][]prompb.TimeSeries{{
newTimeSeries([]float64{2}, []int64{ts.UnixNano()}, []prompb.Label{

View File

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

View File

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

View File

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

View File

@@ -362,62 +362,40 @@ func (up *URLPrefix) setLoadBalancingPolicy(loadBalancingPolicy string) error {
}
type backendURLs struct {
bhc backendHealthCheck
healthChecksContext context.Context
healthChecksCancel func()
healthChecksWG sync.WaitGroup
bus []*backendURL
}
type backendHealthCheck struct {
ctx context.Context
// mu protects fields below
cancel func()
mu sync.Mutex
isStopped bool
wg sync.WaitGroup
}
func (bhc *backendHealthCheck) run(hc func()) {
bhc.mu.Lock()
defer bhc.mu.Unlock()
if bhc.isStopped {
return
}
bhc.wg.Go(hc)
}
func (bhc *backendHealthCheck) stop() {
bhc.mu.Lock()
bhc.cancel()
bhc.isStopped = true
bhc.mu.Unlock()
bhc.wg.Wait()
}
func newBackendURLs() *backendURLs {
ctx, cancel := context.WithCancel(context.Background())
return &backendURLs{
bhc: backendHealthCheck{
ctx: ctx,
cancel: cancel,
},
healthChecksContext: ctx,
healthChecksCancel: cancel,
}
}
func (bus *backendURLs) add(u *url.URL) {
bus.bus = append(bus.bus, &backendURL{
url: u,
bhc: &bus.bhc,
hasPlaceHolders: hasAnyPlaceholders(u),
url: u,
healthCheckContext: bus.healthChecksContext,
healthCheckWG: &bus.healthChecksWG,
hasPlaceHolders: hasAnyPlaceholders(u),
})
}
func (bus *backendURLs) stopHealthChecks() {
bus.bhc.stop()
bus.healthChecksCancel()
bus.healthChecksWG.Wait()
}
type backendURL struct {
broken atomic.Bool
bhc *backendHealthCheck
healthCheckContext context.Context
healthCheckWG *sync.WaitGroup
concurrentRequests atomic.Int32
@@ -432,7 +410,7 @@ func (bu *backendURL) isBroken() bool {
func (bu *backendURL) setBroken() {
if bu.broken.CompareAndSwap(false, true) {
bu.bhc.run(func() {
bu.healthCheckWG.Go(func() {
bu.runHealthCheck()
bu.broken.Store(false)
})
@@ -454,11 +432,11 @@ func (bu *backendURL) runHealthCheck() {
case <-t.C:
// Verify network connectivity via TCP dial before marking backend healthy.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/9997
ctx, cancel := context.WithTimeout(bu.bhc.ctx, time.Second)
ctx, cancel := context.WithTimeout(bu.healthCheckContext, time.Second)
c, err := netutil.Dialer.DialContext(ctx, "tcp", addr)
cancel()
if err != nil {
if errors.Is(bu.bhc.ctx.Err(), context.Canceled) {
if errors.Is(bu.healthCheckContext.Err(), context.Canceled) {
return
}
logger.Warnf("ignoring the backend at %s for %s because of dial error: %s", addr, *failTimeout, err)
@@ -467,7 +445,7 @@ func (bu *backendURL) runHealthCheck() {
_ = c.Close()
return
case <-bu.bhc.ctx.Done():
case <-bu.healthCheckContext.Done():
return
}
}
@@ -539,6 +517,7 @@ func (up *URLPrefix) discoverBackendAddrsIfNeeded() {
continue
}
logger.Infof("try to resolve backend IPs for %s", host)
var resolvedAddrs []string
if strings.HasPrefix(host, "srv+") {
// The host has the format 'srv+realhost'. Strip 'srv+' prefix before performing the lookup.
@@ -566,6 +545,7 @@ func (up *URLPrefix) discoverBackendAddrsIfNeeded() {
resolvedAddrs = make([]string, len(addrs))
for i, addr := range addrs {
resolvedAddrs[i] = net.JoinHostPort(addr.String(), port)
logger.Infof("discover backend IPs for %s into %d addresses, one is %s", bu, len(resolvedAddrs), resolvedAddrs[i])
}
}
}
@@ -588,6 +568,7 @@ func (up *URLPrefix) discoverBackendAddrsIfNeeded() {
bus := up.bus.Load()
if areEqualBackendURLs(bus.bus, busNew.bus) {
logger.Infof("resolved addr are the same as the original one")
return
}

View File

@@ -8,10 +8,10 @@ import (
"time"
vmetrics "github.com/VictoriaMetrics/metrics"
"github.com/cheggaaa/pb/v3"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/opentsdb"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/vm"
"github.com/cheggaaa/pb/v3"
)
type otsdbProcessor struct {
@@ -89,6 +89,9 @@ func (op *otsdbProcessor) run(ctx context.Context) error {
// we're going to make serieslist * queryRanges queries, so we should represent that in the progress bar
otsdbSeriesTotal.Add(len(serieslist) * queryRanges)
bar := pb.StartNew(len(serieslist) * queryRanges)
defer func(bar *pb.ProgressBar) {
bar.Finish()
}(bar)
var wg sync.WaitGroup
for range op.otsdbcc {
wg.Go(func() {
@@ -103,22 +106,41 @@ func (op *otsdbProcessor) run(ctx context.Context) error {
}
})
}
runErr := op.sendQueries(ctx, serieslist, seriesCh, errCh, startTime)
/*
Loop through all series for this metric, processing all retentions and time ranges
requested. This loop is our primary "collect data from OpenTSDB loop" and should
be async, sending data to VictoriaMetrics over time.
// Always drain channels and wait for workers to prevent goroutine leaks
The idea with having the select at the inner-most loop is to ensure quick
short-circuiting on error.
*/
for _, series := range serieslist {
for _, rt := range op.oc.Retentions {
for _, tr := range rt.QueryRanges {
select {
case otsdbErr := <-errCh:
return fmt.Errorf("opentsdb error: %s", otsdbErr)
case vmErr := <-op.im.Errors():
otsdbErrorsTotal.Inc()
return fmt.Errorf("import process failed: %s", wrapErr(vmErr, op.isVerbose))
case seriesCh <- queryObj{
Tr: tr, StartTime: startTime,
Series: series, Rt: opentsdb.RetentionMeta{
FirstOrder: rt.FirstOrder, SecondOrder: rt.SecondOrder, AggTime: rt.AggTime}}:
}
}
}
}
// Drain channels per metric
close(seriesCh)
wg.Wait()
close(errCh)
// 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)
}
return fmt.Errorf("import process failed: \n%s", otsdbErr)
}
bar.Finish()
if runErr != nil {
return runErr
}
log.Print(op.im.Stats())
}
op.im.Close()
@@ -133,34 +155,6 @@ func (op *otsdbProcessor) run(ctx context.Context) error {
return nil
}
// sendQueries iterates over all series and retention ranges, sending queries to workers.
// It returns early if ctx is canceled or an error is received.
func (op *otsdbProcessor) sendQueries(ctx context.Context, serieslist []opentsdb.Meta, seriesCh chan<- queryObj, errCh <-chan error, startTime int64) error {
for _, series := range serieslist {
for _, rt := range op.oc.Retentions {
for _, tr := range rt.QueryRanges {
select {
case <-ctx.Done():
return fmt.Errorf("context canceled: %s", ctx.Err())
case otsdbErr := <-errCh:
otsdbErrorsTotal.Inc()
return fmt.Errorf("opentsdb error: %s", otsdbErr)
case vmErr := <-op.im.Errors():
return fmt.Errorf("import process failed: %s", wrapErr(vmErr, op.isVerbose))
case seriesCh <- queryObj{
Tr: tr, StartTime: startTime,
Series: series, Rt: opentsdb.RetentionMeta{
FirstOrder: rt.FirstOrder,
SecondOrder: rt.SecondOrder,
AggTime: rt.AggTime,
}}:
}
}
}
}
return nil
}
func (op *otsdbProcessor) do(s queryObj) error {
start := s.StartTime - s.Tr.Start
end := s.StartTime - s.Tr.End
@@ -169,7 +163,6 @@ func (op *otsdbProcessor) do(s queryObj) error {
return fmt.Errorf("failed to collect data for %v in %v:%v :: %v", 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)
return nil
}
labels := make([]vm.LabelPair, 0, len(data.Tags))

View File

@@ -108,10 +108,10 @@ func (c Client) FindMetrics(q string) ([]string, error) {
if err != nil {
return nil, fmt.Errorf("failed to send GET request to %q: %s", q, err)
}
defer func() { _ = resp.Body.Close() }()
if resp.StatusCode != 200 {
return nil, fmt.Errorf("bad return from OpenTSDB: %d: %v", resp.StatusCode, resp)
}
defer func() { _ = resp.Body.Close() }()
body, err := io.ReadAll(resp.Body)
if err != nil {
return nil, fmt.Errorf("could not retrieve metric data from %q: %s", q, err)
@@ -130,12 +130,12 @@ 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 set GET request to %q: %s", q, err)
}
defer func() { _ = resp.Body.Close() }()
if resp.StatusCode != 200 {
return nil, fmt.Errorf("bad return from OpenTSDB: %d: %v", resp.StatusCode, resp)
}
defer func() { _ = resp.Body.Close() }()
body, err := io.ReadAll(resp.Body)
if err != nil {
return nil, fmt.Errorf("could not retrieve series data from %q: %s", q, err)
@@ -185,7 +185,6 @@ func (c Client) GetData(series Meta, rt RetentionMeta, start int64, end int64, m
if err != nil {
return Metric{}, fmt.Errorf("failed to send GET request to %q: %s", q, err)
}
defer func() { _ = resp.Body.Close() }()
/*
There are three potential failures here, none of which should kill the entire
migration run:
@@ -197,6 +196,7 @@ func (c Client) GetData(series Meta, rt RetentionMeta, start int64, end int64, m
log.Printf("bad response code from OpenTSDB query %v for %q...skipping", resp.StatusCode, q)
return Metric{}, nil
}
defer func() { _ = resp.Body.Close() }()
body, err := io.ReadAll(resp.Body)
if err != nil {
log.Println("couldn't read response body from OpenTSDB query...skipping")
@@ -239,20 +239,27 @@ func (c Client) GetData(series Meta, rt RetentionMeta, start int64, end int64, m
In all "bad" cases, we don't end the migration, we just don't process that particular message
*/
if len(output) < 1 {
// no results returned...return an empty object without error
return Metric{}, nil
}
if len(output) > 1 {
return Metric{}, fmt.Errorf("unexpected number of series returned: %d for query %q; expected 1", len(output), q)
// multiple series returned for a single query. We can't process this right, so...
return Metric{}, nil
}
if len(output[0].AggregateTags) > 0 {
return Metric{}, fmt.Errorf("aggregate tags %v present in response for query %q; series may be suppressed", output[0].AggregateTags, q)
// This failure means we've suppressed potential series somehow...
return Metric{}, nil
}
data := Metric{}
data.Metric = output[0].Metric
data.Tags = output[0].Tags
/*
We evaluate data for correctness before formatting the actual values
to skip a little bit of time if the series has invalid formatting
*/
data, err = modifyData(data, c.Normalize)
if err != nil {
return Metric{}, fmt.Errorf("failed to convert metric data for query %q: %w", q, err)
return Metric{}, nil
}
/*

View File

@@ -32,7 +32,7 @@ func convertDuration(duration string) (time.Duration, error) {
var err error
var timeValue int
if strings.HasSuffix(duration, "y") {
timeValue, err = strconv.Atoi(strings.TrimSuffix(duration, "y"))
timeValue, err = strconv.Atoi(strings.Trim(duration, "y"))
if err != nil {
return 0, fmt.Errorf("invalid time range: %q", duration)
}
@@ -42,7 +42,7 @@ func convertDuration(duration string) (time.Duration, error) {
return 0, fmt.Errorf("invalid time range: %q", duration)
}
} else if strings.HasSuffix(duration, "w") {
timeValue, err = strconv.Atoi(strings.TrimSuffix(duration, "w"))
timeValue, err = strconv.Atoi(strings.Trim(duration, "w"))
if err != nil {
return 0, fmt.Errorf("invalid time range: %q", duration)
}
@@ -52,7 +52,7 @@ func convertDuration(duration string) (time.Duration, error) {
return 0, fmt.Errorf("invalid time range: %q", duration)
}
} else if strings.HasSuffix(duration, "d") {
timeValue, err = strconv.Atoi(strings.TrimSuffix(duration, "d"))
timeValue, err = strconv.Atoi(strings.Trim(duration, "d"))
if err != nil {
return 0, fmt.Errorf("invalid time range: %q", duration)
}
@@ -95,9 +95,6 @@ func convertRetention(retention string, offset int64, msecTime bool) (Retention,
if !msecTime {
queryLength = queryLength / 1000
}
if queryLength <= 0 {
return Retention{}, fmt.Errorf("ttl %q resolves to non-positive query range %d; use a larger duration", chunks[2], queryLength)
}
queryRange := queryLength
// bump by the offset so we don't look at empty ranges any time offset > ttl
queryLength += offset
@@ -141,29 +138,16 @@ func convertRetention(retention string, offset int64, msecTime bool) (Retention,
2. we discover the actual size of each "chunk"
This is second division step
*/
divisor := queryRange / (rowLength * 4)
if divisor == 0 {
querySize = queryRange
} else {
querySize = queryRange / divisor
}
querySize = int64(queryRange / (queryRange / (rowLength * 4)))
} else {
/*
Unless the aggTime (how long a range of data we're requesting per individual point)
is greater than the row size. Then we'll need to use that to determine
how big each individual query should be
*/
divisor := queryRange / (aggTime * 4)
if divisor == 0 {
querySize = queryRange
} else {
querySize = queryRange / divisor
}
querySize = int64(queryRange / (queryRange / (aggTime * 4)))
}
if querySize <= 0 {
return Retention{}, fmt.Errorf("computed non-positive querySize=%d for retention %q; check parameters", querySize, retention)
}
var timeChunks []TimeRange
var i int64
for i = offset; i <= queryLength; i = i + querySize {

View File

@@ -1223,7 +1223,11 @@ func getCommonParamsInternal(r *http.Request, startTime time.Time, requireNonEmp
if err != nil {
return nil, err
}
maxTS := int64(math.MaxInt64 / 1_000_000)
// Limit the `end` arg to the current time +2 days in the same way
// as it is limited during data ingestion.
// See https://github.com/VictoriaMetrics/VictoriaMetrics/blob/ea06d2fd3ccbbb6aa4480ab3b04f7b671408be2a/lib/storage/table.go#L378
// This should fix possible timestamp overflow - see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2669
maxTS := startTime.UnixNano()/1e6 + 2*24*3600*1000
if end > maxTS {
end = maxTS
}

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -37,9 +37,9 @@
<meta property="og:title" content="UI for VictoriaMetrics">
<meta property="og:url" content="https://victoriametrics.com/">
<meta property="og:description" content="Explore and troubleshoot your VictoriaMetrics data">
<script type="module" crossorigin src="./assets/index-fsxQMWD9.js"></script>
<script type="module" crossorigin src="./assets/index-C24BPpD_.js"></script>
<link rel="modulepreload" crossorigin href="./assets/rolldown-runtime-COnpUsM8.js">
<link rel="modulepreload" crossorigin href="./assets/vendor-BF3F25aG.js">
<link rel="modulepreload" crossorigin href="./assets/vendor-BWBgVCcr.js">
<link rel="stylesheet" crossorigin href="./assets/vendor-CnsZ1jie.css">
<link rel="stylesheet" crossorigin href="./assets/index-D2OEy8Ra.css">
</head>

View File

@@ -33,8 +33,6 @@ import (
var (
retentionPeriod = flagutil.NewRetentionDuration("retentionPeriod", "1M", "Data with timestamps outside the retentionPeriod is automatically deleted. The minimum retentionPeriod is 24h or 1d. "+
"See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#retention. See also -retentionFilter")
futureRetention = flagutil.NewRetentionDuration("futureRetention", "2d", "Data with timestamps bigger than now+futureRetention is automatically deleted. "+
"The minimum futureRetention is 2 days. See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#retention")
snapshotAuthKey = flagutil.NewPassword("snapshotAuthKey", "authKey, which must be passed in query string to /snapshot* pages. It overrides -httpAuth.*")
forceMergeAuthKey = flagutil.NewPassword("forceMergeAuthKey", "authKey, which must be passed in query string to /internal/force_merge pages. It overrides -httpAuth.*")
forceFlushAuthKey = flagutil.NewPassword("forceFlushAuthKey", "authKey, which must be passed in query string to /internal/force_flush pages. It overrides -httpAuth.*")
@@ -137,12 +135,7 @@ func Init(resetCacheIfNeeded func(mrs []storage.MetricRow)) {
mergeset.SetDataBlocksSparseCacheSize(cacheSizeIndexDBDataBlocksSparse.IntN())
if retentionPeriod.Duration() < 24*time.Hour {
logger.Fatalf("-retentionPeriod cannot be smaller than a day; got %s. "+
"See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#retention", retentionPeriod)
}
if futureRetention.Duration() < 2*24*time.Hour {
logger.Fatalf("-futureRetention cannot be smaller than 2 days; got %s. "+
"See https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#retention", futureRetention)
logger.Fatalf("-retentionPeriod cannot be smaller than a day; got %s", retentionPeriod)
}
if *idbPrefillStart > 23*time.Hour {
logger.Panicf("-storage.idbPrefillStart cannot exceed 23 hours; got %s", idbPrefillStart)
@@ -152,7 +145,6 @@ func Init(resetCacheIfNeeded func(mrs []storage.MetricRow)) {
WG = syncwg.WaitGroup{}
opts := storage.OpenOptions{
Retention: retentionPeriod.Duration(),
FutureRetention: futureRetention.Duration(),
MaxHourlySeries: getMaxHourlySeries(),
MaxDailySeries: getMaxDailySeries(),
DisablePerDayIndex: *disablePerDayIndex,

View File

@@ -6,7 +6,7 @@ COPY web/ /build/
RUN GOOS=linux GOARCH=amd64 CGO_ENABLED=0 go build -o web-amd64 github.com/VictoriMetrics/vmui/ && \
GOOS=windows GOARCH=amd64 CGO_ENABLED=0 go build -o web-windows github.com/VictoriMetrics/vmui/
FROM alpine:3.23.4
FROM alpine:3.23.3
USER root
COPY --from=build-web-stage /build/web-amd64 /app/web

View File

@@ -1,18 +1,47 @@
import { ArrayRGB } from "../types";
export const baseContrastColors = [
"#e6194b", // red
"#4363d8", // blue
"#3cb44b", // green
"#911eb4", // purple
"#f58231", // orange
"#f032e6", // magenta
"#c8a200", // dark yellow
"#a65628", // brown
"#42d4f4", // cyan
"#a9a9a9", // gray
"#e54040",
"#32a9dc",
"#2ee329",
"#7126a1",
"#e38f0f",
"#3d811a",
"#ffea00",
"#2d2d2d",
"#da42a6",
"#a44e0c",
];
export const hexToRGB = (hex: string): string => {
if (hex.length != 7) return "0, 0, 0";
const r = parseInt(hex.slice(1, 3), 16);
const g = parseInt(hex.slice(3, 5), 16);
const b = parseInt(hex.slice(5, 7), 16);
return `${r}, ${g}, ${b}`;
};
export const getColorFromString = (text: string): string => {
const SEED = 16777215;
const FACTOR = 49979693;
let b = 1;
let d = 0;
let f = 1;
if (text.length > 0) {
for (let i = 0; i < text.length; i++) {
text[i].charCodeAt(0) > d && (d = text[i].charCodeAt(0));
f = parseInt(String(SEED / d));
b = (b + text[i].charCodeAt(0) * f * FACTOR) % SEED;
}
}
let hex = ((b * text.length) % SEED).toString(16);
hex = hex.padEnd(6, hex);
return `#${hex}`;
};
export const getContrastColor = (value: string) => {
let hex = value.replace("#", "").trim();
@@ -41,109 +70,3 @@ export const generateGradient = (start: ArrayRGB, end: ArrayRGB, steps: number)
}
return gradient.map(c => `rgb(${c})`);
};
const clamp = (n: number, min: number, max: number) => Math.min(max, Math.max(min, n));
const hexToRgb = (hex: string) => {
let value = hex.replace("#", "").trim();
if (value.length === 3) {
value = value.split("").map((c) => c + c).join("");
}
if (!/^[0-9a-fA-F]{6}$/.test(value)) {
throw new Error("Invalid HEX color.");
}
return {
r: parseInt(value.slice(0, 2), 16),
g: parseInt(value.slice(2, 4), 16),
b: parseInt(value.slice(4, 6), 16),
};
};
const rgbToHex = (r: number, g: number, b: number) =>
`#${[r, g, b].map((v) => clamp(Math.round(v), 0, 255).toString(16).padStart(2, "0")).join("")}`;
const rgbToHsl = (r: number, g: number, b: number) => {
r /= 255; g /= 255; b /= 255;
const max = Math.max(r, g, b);
const min = Math.min(r, g, b);
const l = (max + min) / 2;
const d = max - min;
let h = 0;
let s = 0;
if (d !== 0) {
s = d / (1 - Math.abs(2 * l - 1));
switch (max) {
case r: h = ((g - b) / d) % 6; break;
case g: h = (b - r) / d + 2; break;
case b: h = (r - g) / d + 4; break;
}
h *= 60;
if (h < 0) h += 360;
}
return { h, s: s * 100, l: l * 100 };
};
const hslToRgb = (h: number, s: number, l: number) => {
s /= 100;
l /= 100;
const c = (1 - Math.abs(2 * l - 1)) * s;
const x = c * (1 - Math.abs((h / 60) % 2 - 1));
const m = l - c / 2;
let r: number;
let g: number;
let b: number;
if (h < 60) [r, g, b] = [c, x, 0];
else if (h < 120) [r, g, b] = [x, c, 0];
else if (h < 180) [r, g, b] = [0, c, x];
else if (h < 240) [r, g, b] = [0, x, c];
else if (h < 300) [r, g, b] = [x, 0, c];
else [r, g, b] = [c, 0, x];
return {
r: (r + m) * 255,
g: (g + m) * 255,
b: (b + m) * 255,
};
};
const varyColor = (hex: string, variant: number) => {
const { r, g, b } = hexToRgb(hex);
const { h, s, l } = rgbToHsl(r, g, b);
const variants = [
{ ds: 0, dl: 0 },
{ ds: -20, dl: -16 },
{ ds: -16, dl: +16 },
{ ds: +14, dl: -20 },
];
const v = variants[variant % variants.length];
const nextS = clamp(s + v.ds, 35, 85);
const nextL = clamp(l + v.dl, 35, 70);
const rgb = hslToRgb(h, nextS, nextL);
return rgbToHex(rgb.r, rgb.g, rgb.b);
};
export const getSeriesColor = (index: number) => {
const baseCount = baseContrastColors.length;
const baseIndex = index % baseCount;
const variantIndex = Math.floor(index / baseCount);
const base = baseContrastColors[(baseIndex + variantIndex) % baseCount];
return varyColor(base, variantIndex);
};

View File

@@ -2,7 +2,7 @@ import { MetricBase, MetricResult } from "../../api/types";
import uPlot, { Series as uPlotSeries } from "uplot";
import { getNameForMetric, promValueToNumber } from "../metric";
import { HideSeriesArgs, LegendItemType, SeriesItem } from "../../types";
import { getSeriesColor } from "../color";
import { baseContrastColors, getColorFromString } from "../color";
import { getMathStats } from "../math";
import { formatPrettyNumber } from "./helpers";
import { drawPoints } from "./scatter";
@@ -17,10 +17,11 @@ export const extractFields = (metric: MetricBase["metric"]): string => {
export const getSeriesItemContext = (data: MetricResult[], hideSeries: string[], alias: string[], showPoints?: boolean, isRawQuery?: boolean) => {
const colorState: {[key: string]: string} = {};
const maxColors = Math.min(data.length, baseContrastColors.length);
for (let i = 0; i < data.length; i++) {
for (let i = 0; i < maxColors; i++) {
const label = getNameForMetric(data[i], alias[data[i].group - 1]);
colorState[label] = getSeriesColor(i);
colorState[label] = baseContrastColors[i];
}
return (d: MetricResult): SeriesItem => {
@@ -31,7 +32,7 @@ export const getSeriesItemContext = (data: MetricResult[], hideSeries: string[],
label,
hasAlias: Boolean(aliasValue),
width: 1.4,
stroke: colorState[label],
stroke: colorState[label] || getColorFromString(label),
points: getPointsSeries(showPoints, isRawQuery),
spanGaps: false,
freeFormFields: d.metric,

View File

@@ -93,14 +93,6 @@ type QueryOpts struct {
Headers http.Header
}
// getTenant returns tenant with optional default value
func (qos *QueryOpts) getTenant() string {
if qos.Tenant == "" {
return "0"
}
return qos.Tenant
}
func (qos *QueryOpts) getHeaders() http.Header {
if qos.Headers == nil {
qos.Headers = make(http.Header)

View File

@@ -28,7 +28,6 @@ func TestSingleBackupRestore(t *testing.T) {
return tc.MustStartVmsingle("vmsingle", []string{
"-storageDataPath=" + storageDataPath,
"-retentionPeriod=100y",
"-futureRetention=2y",
})
},
stopSUT: func() {
@@ -61,13 +60,11 @@ func TestClusterBackupRestore(t *testing.T) {
Vmstorage1Flags: []string{
"-storageDataPath=" + storage1DataPath,
"-retentionPeriod=100y",
"-futureRetention=2y",
},
Vmstorage2Instance: "vmstorage2",
Vmstorage2Flags: []string{
"-storageDataPath=" + storage2DataPath,
"-retentionPeriod=100y",
"-futureRetention=2y",
},
VminsertInstance: "vminsert",
VminsertFlags: []string{},
@@ -100,16 +97,10 @@ func TestClusterBackupRestore(t *testing.T) {
func testBackupRestore(tc *apptest.TestCase, opts testBackupRestoreOpts) {
t := tc.T()
type data struct {
samples []string
wantSeries []map[string]string
wantQueryResults []*apptest.QueryResult
}
genData := func(count int, prefix string, start, step int64) data {
recs := make([]string, count)
wantSeries := make([]map[string]string, count)
wantQueryResults := make([]*apptest.QueryResult, count)
genData := func(count int, prefix string, start, step int64) (recs []string, wantSeries []map[string]string, wantQueryResults []*apptest.QueryResult) {
recs = make([]string, count)
wantSeries = make([]map[string]string, count)
wantQueryResults = make([]*apptest.QueryResult, count)
for i := range count {
name := fmt.Sprintf("%s_%03d", prefix, i)
value := float64(i)
@@ -122,15 +113,7 @@ func testBackupRestore(tc *apptest.TestCase, opts testBackupRestoreOpts) {
Samples: []*apptest.Sample{{Timestamp: timestamp, Value: value}},
}
}
return data{recs, wantSeries, wantQueryResults}
}
concatData := func(d1, d2 data) data {
var d data
d.samples = slices.Concat(d1.samples, d2.samples)
d.wantSeries = slices.Concat(d1.wantSeries, d2.wantSeries)
d.wantQueryResults = slices.Concat(d1.wantQueryResults, d2.wantQueryResults)
return d
return recs, wantSeries, wantQueryResults
}
backupBaseDir, err := filepath.Abs(filepath.Join(tc.Dir(), "backups"))
@@ -207,20 +190,10 @@ func testBackupRestore(tc *apptest.TestCase, opts testBackupRestoreOpts) {
// Use the same number of metrics and time range for all the data ingestions
// below.
const numMetrics = 1000
// With 1000 metrics (one per minute), the time range spans 2 months.
start := time.Date(2025, 1, 1, 0, 0, 0, 0, time.UTC).UnixMilli()
end := time.Date(2025, 3, 1, 0, 0, 0, 0, time.UTC).UnixMilli()
step := (end - start) / numMetrics
batch1 := genData(numMetrics, "batch1", start, step)
batch2 := genData(numMetrics, "batch2", start, step)
batches12 := concatData(batch1, batch2)
now := time.Now().UTC()
startFuture := time.Date(now.Year()+1, 1, 1, 0, 0, 0, 0, time.UTC).UnixMilli()
endFuture := time.Date(now.Year()+1, 3, 1, 0, 0, 0, 0, time.UTC).UnixMilli()
stepFuture := (endFuture - startFuture) / numMetrics
batch1Future := genData(numMetrics, "batch1", startFuture, stepFuture)
batch2Future := genData(numMetrics, "batch2", startFuture, stepFuture)
batches12Future := concatData(batch1Future, batch2Future)
// Verify backup/restore:
//
@@ -234,25 +207,24 @@ func testBackupRestore(tc *apptest.TestCase, opts testBackupRestoreOpts) {
// - Start vmsingle
// - Ensure that the queries return batch1 data only.
batch1Data, wantBatch1Series, wantBatch1QueryResults := genData(numMetrics, "batch1", start, step)
batch2Data, wantBatch2Series, wantBatch2QueryResults := genData(numMetrics, "batch2", start, step)
wantBatch12Series := slices.Concat(wantBatch1Series, wantBatch2Series)
wantBatch12QueryResults := slices.Concat(wantBatch1QueryResults, wantBatch2QueryResults)
sut := opts.startSUT()
sut.PrometheusAPIV1ImportPrometheus(t, batch1.samples, apptest.QueryOpts{})
sut.PrometheusAPIV1ImportPrometheus(t, batch1Future.samples, apptest.QueryOpts{})
sut.PrometheusAPIV1ImportPrometheus(t, batch1Data, apptest.QueryOpts{})
sut.ForceFlush(t)
assertSeries(sut, `{__name__=~"batch1.*"}`, start, end, batch1.wantSeries)
assertSeries(sut, `{__name__=~"batch1.*"}`, startFuture, endFuture, batch1Future.wantSeries)
assertQueryResults(sut, `{__name__=~"batch1.*"}`, start, end, step, batch1.wantQueryResults)
assertQueryResults(sut, `{__name__=~"batch1.*"}`, startFuture, endFuture, stepFuture, batch1Future.wantQueryResults)
assertSeries(sut, `{__name__=~"batch1.*"}`, start, end, wantBatch1Series)
assertQueryResults(sut, `{__name__=~"batch1.*"}`, start, end, step, wantBatch1QueryResults)
createBackup(sut, "batch1")
sut.PrometheusAPIV1ImportPrometheus(t, batch2.samples, apptest.QueryOpts{})
sut.PrometheusAPIV1ImportPrometheus(t, batch2Future.samples, apptest.QueryOpts{})
sut.PrometheusAPIV1ImportPrometheus(t, batch2Data, apptest.QueryOpts{})
sut.ForceFlush(t)
assertSeries(sut, `{__name__=~"batch(1|2).*"}`, start, end, batches12.wantSeries)
assertSeries(sut, `{__name__=~"batch(1|2).*"}`, startFuture, endFuture, batches12Future.wantSeries)
assertQueryResults(sut, `{__name__=~"batch(1|2).*"}`, start, end, step, batches12.wantQueryResults)
assertQueryResults(sut, `{__name__=~"batch(1|2).*"}`, startFuture, endFuture, stepFuture, batches12Future.wantQueryResults)
assertSeries(sut, `{__name__=~"batch(1|2).*"}`, start, end, wantBatch12Series)
assertQueryResults(sut, `{__name__=~"batch(1|2).*"}`, start, end, step, wantBatch12QueryResults)
createBackup(sut, "batch12")
opts.stopSUT()
@@ -261,8 +233,6 @@ func testBackupRestore(tc *apptest.TestCase, opts testBackupRestoreOpts) {
sut = opts.startSUT()
assertSeries(sut, `{__name__=~"batch(1|2).*"}`, start, end, batch1.wantSeries)
assertSeries(sut, `{__name__=~"batch(1|2).*"}`, startFuture, endFuture, batch1Future.wantSeries)
assertQueryResults(sut, `{__name__=~"batch(1|2).*"}`, start, end, step, batch1.wantQueryResults)
assertQueryResults(sut, `{__name__=~"batch(1|2).*"}`, startFuture, endFuture, stepFuture, batch1Future.wantQueryResults)
assertSeries(sut, `{__name__=~"batch1.*"}`, start, end, wantBatch1Series)
assertQueryResults(sut, `{__name__=~"batch1.*"}`, start, end, step, wantBatch1QueryResults)
}

View File

@@ -1,211 +0,0 @@
package tests
import (
"fmt"
"path/filepath"
"testing"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/apptest"
)
func TestSingleFutureTimestamps(t *testing.T) {
tc := apptest.NewTestCase(t)
defer tc.Stop()
opts := testFutureTimestampsOpts{
start: func() apptest.PrometheusWriteQuerier {
return tc.MustStartVmsingle("vmsingle", []string{
"-storageDataPath=" + filepath.Join(tc.Dir(), "vmsingle"),
"-retentionPeriod=100y",
"-futureRetention=100y",
})
},
stop: func() {
tc.StopApp("vmsingle")
},
}
testFutureTimestamps(tc, opts)
}
func TestClusterFutureTimestamps(t *testing.T) {
tc := apptest.NewTestCase(t)
defer tc.Stop()
opts := testFutureTimestampsOpts{
start: func() apptest.PrometheusWriteQuerier {
return tc.MustStartCluster(&apptest.ClusterOptions{
Vmstorage1Instance: "vmstorage1",
Vmstorage1Flags: []string{
"-storageDataPath=" + filepath.Join(tc.Dir(), "vmstorage1"),
"-retentionPeriod=100y",
"-futureRetention=100y",
},
Vmstorage2Instance: "vmstorage2",
Vmstorage2Flags: []string{
"-storageDataPath=" + filepath.Join(tc.Dir(), "vmstorage2"),
"-retentionPeriod=100y",
"-futureRetention=100y",
},
VminsertInstance: "vminsert",
VminsertFlags: []string{},
VmselectInstance: "vmselect",
VmselectFlags: []string{},
})
},
stop: func() {
tc.StopApp("vminsert")
tc.StopApp("vmselect")
tc.StopApp("vmstorage1")
tc.StopApp("vmstorage2")
},
}
testFutureTimestamps(tc, opts)
}
type testFutureTimestampsOpts struct {
start func() apptest.PrometheusWriteQuerier
stop func()
}
func testFutureTimestamps(tc *apptest.TestCase, opts testFutureTimestampsOpts) {
t := tc.T()
// assertSeries retrieves set of all metric names from the storage and
// compares it with the expected set.
assertSeries := func(app apptest.PrometheusQuerier, prefix string, start, end int64, want []map[string]string) {
t.Helper()
query := fmt.Sprintf(`{__name__=~"metric_%s.*"}`, prefix)
tc.Assert(&apptest.AssertOptions{
Msg: "unexpected /api/v1/series response",
Got: func() any {
return app.PrometheusAPIV1Series(t, query, apptest.QueryOpts{
Start: fmt.Sprintf("%d", start),
End: fmt.Sprintf("%d", end),
}).Sort()
},
Want: &apptest.PrometheusAPIV1SeriesResponse{
Status: "success",
Data: want,
},
FailNow: true,
})
}
// assertSeries retrieves all data from the storage and compares it with the
// expected result.
assertQueryResults := func(app apptest.PrometheusQuerier, prefix string, start, end, step int64, want []*apptest.QueryResult) {
t.Helper()
query := fmt.Sprintf(`{__name__=~"metric_%s.*"}`, prefix)
tc.Assert(&apptest.AssertOptions{
Msg: "unexpected /api/v1/query_range response",
Got: func() any {
return app.PrometheusAPIV1QueryRange(t, query, apptest.QueryOpts{
Start: fmt.Sprintf("%d", start),
End: fmt.Sprintf("%d", end),
Step: fmt.Sprintf("%dms", step),
MaxLookback: fmt.Sprintf("%dms", step-1),
NoCache: "1",
})
},
Want: &apptest.PrometheusAPIV1QueryResponse{
Status: "success",
Data: &apptest.QueryData{
ResultType: "matrix",
Result: want,
},
},
FailNow: true,
})
}
f := func(prefix string, startTime, endTime time.Time, wantEmpty bool) {
const numMetrics = 1000
start := startTime.UnixMilli()
end := endTime.UnixMilli()
step := (end - start) / numMetrics
data := genFutureTimestampsData(prefix, numMetrics, start, step)
if wantEmpty {
data.wantSeries = []map[string]string{}
data.wantQueryResults = []*apptest.QueryResult{}
}
// Ingest data and check query results.
sut := opts.start()
sut.PrometheusAPIV1ImportPrometheus(t, data.samples, apptest.QueryOpts{})
sut.ForceFlush(t)
assertSeries(sut, prefix, start, end, data.wantSeries)
assertQueryResults(sut, prefix, start, end, step, data.wantQueryResults)
// Ensure the queries work after restrart.
opts.stop()
sut = opts.start()
assertSeries(sut, prefix, start, end, data.wantSeries)
assertQueryResults(sut, prefix, start, end, step, data.wantQueryResults)
opts.stop()
}
now := time.Now().UTC()
retentionLimit := 100 * 365 * 24 * time.Hour
var start, end time.Time
start = time.Date(now.Year(), now.Month(), now.Day()+1, 0, 0, 0, 0, time.UTC)
end = time.Date(now.Year(), now.Month(), now.Day()+2, 0, 0, 0, 0, time.UTC)
f("future_1d", start, end, false)
start = time.Date(now.Year(), now.Month()+1, 1, 0, 0, 0, 0, time.UTC)
end = time.Date(now.Year(), now.Month()+2, 1, 0, 0, 0, 0, time.UTC)
f("future_1m", start, end, false)
start = time.Date(now.Year()+1, 1, 1, 0, 0, 0, 0, time.UTC)
end = time.Date(now.Year()+2, 1, 1, 0, 0, 0, 0, time.UTC)
f("future_1y", start, end, false)
start = now.Add(retentionLimit - 24*time.Hour)
end = now.Add(retentionLimit)
f("future_1d_before_limit", start, end, false)
start = now.Add(retentionLimit + time.Minute)
end = now.Add(retentionLimit + 24*time.Hour)
f("future_1d_beyond_limit", start, end, true)
}
type futureTimestampsData struct {
samples []string
wantSeries []map[string]string
wantQueryResults []*apptest.QueryResult
}
func genFutureTimestampsData(prefix string, numMetrics, start, step int64) futureTimestampsData {
samples := make([]string, numMetrics)
wantSeries := make([]map[string]string, numMetrics)
wantQueryResults := make([]*apptest.QueryResult, numMetrics)
for i := range numMetrics {
metricName := fmt.Sprintf("metric_%s_%04d", prefix, i)
labelName := fmt.Sprintf("label_%s_%04d", prefix, i)
labelValue := fmt.Sprintf("value_%s_%04d", prefix, i)
value := i
timestamp := start + i*step
samples[i] = fmt.Sprintf(`%s{%s="value", label="%s"} %d %d`, metricName, labelName, labelValue, value, timestamp)
wantSeries[i] = map[string]string{
"__name__": metricName,
labelName: "value",
"label": labelValue,
}
wantQueryResults[i] = &apptest.QueryResult{
Metric: map[string]string{
"__name__": metricName,
labelName: "value",
"label": labelValue,
},
Samples: []*apptest.Sample{{Timestamp: timestamp, Value: float64(value)}},
}
}
return futureTimestampsData{samples, wantSeries, wantQueryResults}
}

View File

@@ -1,186 +0,0 @@
package tests
import (
"encoding/json"
"fmt"
"net/http"
"net/http/httptest"
"sort"
"strconv"
"strings"
"testing"
)
// openTSDBPoint is a single data point served by the mock OpenTSDB server.
type openTSDBPoint struct {
Metric string
Tags map[string]string
Timestamp int64
Value float64
}
// openTSDBMockServer implements the minimal subset of the OpenTSDB HTTP API
// used by vmctl opentsdb: /api/suggest, /api/search/lookup, /api/query.
type openTSDBMockServer struct {
server *httptest.Server
points []openTSDBPoint
}
// newOpenTSDBMockServer starts an httptest server serving the given points.
func newOpenTSDBMockServer(t *testing.T, points []openTSDBPoint) *openTSDBMockServer {
t.Helper()
s := &openTSDBMockServer{points: points}
mux := http.NewServeMux()
mux.HandleFunc("/api/suggest", s.handleSuggest)
mux.HandleFunc("/api/search/lookup", s.handleLookup)
mux.HandleFunc("/api/query", s.handleQuery)
s.server = httptest.NewServer(mux)
return s
}
// close shuts down the server.
func (s *openTSDBMockServer) close() { s.server.Close() }
// httpAddr returns the server URL.
func (s *openTSDBMockServer) httpAddr() string { return s.server.URL }
// handleSuggest serves https://opentsdb.net/docs/build/html/api_http/suggest.html
func (s *openTSDBMockServer) handleSuggest(w http.ResponseWriter, r *http.Request) {
q := r.URL.Query().Get("q")
seen := make(map[string]bool, len(s.points))
var out []string
for _, p := range s.points {
if seen[p.Metric] {
continue
}
if q != "" && !strings.Contains(p.Metric, q) {
continue
}
seen[p.Metric] = true
out = append(out, p.Metric)
}
_ = json.NewEncoder(w).Encode(out)
}
// handleLookup serves https://opentsdb.net/docs/build/html/api_http/search/lookup.html
func (s *openTSDBMockServer) handleLookup(w http.ResponseWriter, r *http.Request) {
metric := r.URL.Query().Get("m")
type meta struct {
Metric string `json:"metric"`
Tags map[string]string `json:"tags"`
}
seen := make(map[string]bool, len(s.points))
var results []meta
for _, p := range s.points {
if p.Metric != metric {
continue
}
key := tagsKey(p.Tags)
if seen[key] {
continue
}
seen[key] = true
results = append(results, meta{p.Metric, p.Tags})
}
_ = json.NewEncoder(w).Encode(map[string]any{
"type": "LOOKUP",
"metric": metric,
"results": results,
})
}
// handleQuery serves https://opentsdb.net/docs/build/html/api_http/query/index.html
func (s *openTSDBMockServer) handleQuery(w http.ResponseWriter, r *http.Request) {
m := r.URL.Query().Get("m")
metric, tagFilter, ok := parseQuery(m)
if !ok {
http.Error(w, "bad query param", http.StatusBadRequest)
return
}
start, err := strconv.ParseInt(r.URL.Query().Get("start"), 10, 64)
if err != nil {
http.Error(w, "bad start param", http.StatusBadRequest)
return
}
end, err := strconv.ParseInt(r.URL.Query().Get("end"), 10, 64)
if err != nil {
http.Error(w, "bad end param", http.StatusBadRequest)
return
}
type resp struct {
Metric string `json:"metric"`
Tags map[string]string `json:"tags"`
AggregateTags []string `json:"aggregateTags"`
Dps map[string]float64 `json:"dps"`
}
grouped := make(map[string]*resp, len(s.points))
for _, p := range s.points {
if p.Metric != metric {
continue
}
if !matchTags(p.Tags, tagFilter) {
continue
}
if p.Timestamp < start || p.Timestamp > end {
continue
}
key := tagsKey(p.Tags)
if _, exists := grouped[key]; !exists {
grouped[key] = &resp{
Metric: p.Metric,
Tags: p.Tags,
AggregateTags: []string{},
Dps: map[string]float64{},
}
}
grouped[key].Dps[fmt.Sprintf("%d", p.Timestamp)] = p.Value
}
out := make([]*resp, 0, len(grouped))
for _, v := range grouped {
out = append(out, v)
}
_ = json.NewEncoder(w).Encode(out)
}
// parseQuery parses the OpenTSDB m= query parameter.
// Format: "<agg>:<bucket>-<agg>-none:<metric>{k=v,k=v}"
func parseQuery(m string) (string, map[string]string, bool) {
parts := strings.SplitN(m, ":", 3)
if len(parts) != 3 {
return "", nil, false
}
metric, tagStr, _ := strings.Cut(parts[2], "{")
tags := make(map[string]string, 4)
tagStr = strings.TrimSuffix(tagStr, "}")
for _, kv := range strings.Split(tagStr, ",") {
if k, v, ok := strings.Cut(kv, "="); ok {
tags[k] = v
}
}
return metric, tags, true
}
func matchTags(got, filter map[string]string) bool {
for k, v := range filter {
if v == "*" {
continue
}
if got[k] != v {
return false
}
}
return true
}
func tagsKey(tags map[string]string) string {
keys := make([]string, 0, len(tags))
for k := range tags {
keys = append(keys, k)
}
sort.Strings(keys)
parts := make([]string, 0, len(keys))
for _, k := range keys {
parts = append(parts, k+"="+tags[k])
}
return strings.Join(parts, ",")
}

View File

@@ -13,7 +13,6 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/apptest"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
)
// TestSingleVMAgentReloadConfigs verifies that vmagent reload new configurations on SIGHUP signal
@@ -513,74 +512,3 @@ func TestSingleVMAgentCardinalityLimiter(t *testing.T) {
t.Fatalf("unexpected vmagent_daily_series_limit_rows_dropped_total value: %d", v)
}
}
func TestClusterVMAgentForwardMetricsMetadata(t *testing.T) {
tc := apptest.NewTestCase(t)
defer tc.Stop()
sut := tc.MustStartDefaultCluster()
vmagent := tc.MustStartVmagent("vmagent", []string{
`-remoteWrite.flushInterval=50ms`,
`-remoteWrite.forcePromProto=true`,
`-enableMultitenantHandlers=true`,
"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent",
fmt.Sprintf(`-remoteWrite.url=http://%s/insert/multitenant/prometheus/api/v1/write`, sut.Vminsert.HTTPAddr()),
}, ``)
prometheusRemoteWriteDataSet := prompb.WriteRequest{
Metadata: []prompb.MetricMetadata{
{MetricFamilyName: "metric_name_4", Help: "some help message", Type: prompb.MetricTypeSummary, AccountID: 100},
},
}
vmagent.PrometheusAPIV1Write(t, prometheusRemoteWriteDataSet, apptest.QueryOpts{Tenant: "multitenant"})
tc.Assert(&apptest.AssertOptions{
Msg: "unexpected /api/v1/metadata response",
Got: func() any {
return sut.PrometheusAPIV1Metadata(t, ``, -1, apptest.QueryOpts{Tenant: "100:0"})
},
Want: &apptest.PrometheusAPIV1Metadata{
Status: "success",
Data: map[string][]apptest.MetadataEntry{
"metric_name_4": {{Help: "some help message", Type: "summary"}},
},
},
})
prometheusRemoteWriteDataSet = prompb.WriteRequest{
Metadata: []prompb.MetricMetadata{
{MetricFamilyName: "metric_name_6", Help: "some help message", Type: prompb.MetricTypeSummary, AccountID: 100},
},
}
// enforce tenant from request uri /insert/tenant_id/prometheus/api/v1/write
vmagent.PrometheusAPIV1Write(t, prometheusRemoteWriteDataSet, apptest.QueryOpts{Tenant: "500:500"})
tc.Assert(&apptest.AssertOptions{
Msg: "unexpected /api/v1/metadata response",
Got: func() any {
return sut.PrometheusAPIV1Metadata(t, ``, -1, apptest.QueryOpts{Tenant: "500:500"})
},
Want: &apptest.PrometheusAPIV1Metadata{
Status: "success",
Data: map[string][]apptest.MetadataEntry{
"metric_name_6": {{Help: "some help message", Type: "summary"}},
},
},
})
tc.Assert(&apptest.AssertOptions{
Msg: "unexpected /api/v1/metadata response",
Got: func() any {
return sut.PrometheusAPIV1Metadata(t, ``, -1, apptest.QueryOpts{Tenant: "multitenant"})
},
Want: &apptest.PrometheusAPIV1Metadata{
Status: "success",
Data: map[string][]apptest.MetadataEntry{
"metric_name_4": {{Help: "some help message", Type: "summary"}},
"metric_name_6": {{Help: "some help message", Type: "summary"}},
},
},
})
}

View File

@@ -1,167 +0,0 @@
package tests
import (
"fmt"
"testing"
"time"
"github.com/google/go-cmp/cmp"
"github.com/google/go-cmp/cmp/cmpopts"
"github.com/VictoriaMetrics/VictoriaMetrics/apptest"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
)
func TestSingleVmctlOpenTSDBProtocol(t *testing.T) {
fs.MustRemoveDir(t.Name())
tc := apptest.NewTestCase(t)
defer tc.Stop()
vmsingleDst := tc.MustStartDefaultVmsingle()
vmAddr := fmt.Sprintf("http://%s/", vmsingleDst.HTTPAddr())
// Generate 60 points at 1-minute intervals starting 2 hours ago.
// This ensures data falls within vmctl's default query window (now - retention).
baseTS := time.Now().Add(-2 * time.Hour).Truncate(time.Minute).Unix()
points := make([]openTSDBPoint, 0, 60)
for i := range 60 {
points = append(points, openTSDBPoint{
Metric: "test.cpu",
Tags: map[string]string{"host": "h1", "env": "prod"},
Timestamp: baseTS + int64(i*60),
Value: float64(i),
})
}
otsdb := newOpenTSDBMockServer(t, points)
defer otsdb.close()
vmctlFlags := []string{
`opentsdb`,
`--otsdb-addr=` + otsdb.httpAddr(),
`--vm-addr=` + vmAddr,
`--otsdb-retentions=ssum-1m-avg:1d:1d`,
`--otsdb-filters=test`,
`--otsdb-normalize`,
`--disable-progress-bar=true`,
`-s`,
}
testOpenTSDBProtocol(tc, vmsingleDst, vmctlFlags, points, "test_cpu", baseTS)
}
func TestClusterVmctlOpenTSDBProtocol(t *testing.T) {
fs.MustRemoveDir(t.Name())
tc := apptest.NewTestCase(t)
defer tc.Stop()
cluster := tc.MustStartDefaultCluster()
vmAddr := fmt.Sprintf("http://%s/", cluster.Vminsert.HTTPAddr())
// Generate 60 points at 1-minute intervals starting 2 hours ago.
baseTS := time.Now().Add(-2 * time.Hour).Truncate(time.Minute).Unix()
points := make([]openTSDBPoint, 0, 60)
for i := range 60 {
points = append(points, openTSDBPoint{
Metric: "test.mem",
Tags: map[string]string{"host": "h1"},
Timestamp: baseTS + int64(i*60),
Value: float64(i * 2),
})
}
otsdb := newOpenTSDBMockServer(t, points)
defer otsdb.close()
vmctlFlags := []string{
`opentsdb`,
`--otsdb-addr=` + otsdb.httpAddr(),
`--vm-addr=` + vmAddr,
`--otsdb-retentions=sum-1m-avg:1d:1d`,
`--otsdb-filters=test`,
`--otsdb-normalize`,
`--disable-progress-bar=true`,
`--vm-account-id=0`,
`-s`,
}
testOpenTSDBProtocol(tc, cluster, vmctlFlags, points, "test_mem", baseTS)
}
func testOpenTSDBProtocol(
tc *apptest.TestCase,
queries apptest.PrometheusWriteQuerier,
vmctlFlags []string,
points []openTSDBPoint,
vmMetricName string,
baseTS int64,
) {
t := tc.T()
t.Helper()
// Build dynamic time range covering all data points with 1-hour padding.
queryStart := time.Unix(baseTS-3600, 0).UTC().Format(time.RFC3339)
queryEnd := time.Unix(baseTS+7200, 0).UTC().Format(time.RFC3339)
cmpOpt := cmpopts.IgnoreFields(apptest.PrometheusAPIV1QueryResponse{}, "Status", "Data.ResultType")
got := queries.PrometheusAPIV1Query(t, `{__name__=~".*"}`, apptest.QueryOpts{
Step: "5m",
Time: queryStart,
})
want := apptest.NewPrometheusAPIV1QueryResponse(t, `{"data":{"result":[]}}`)
if diff := cmp.Diff(want, got, cmpOpt); diff != "" {
t.Errorf("unexpected response (-want, +got):\n%s", diff)
}
tc.MustStartVmctl("vmctl", vmctlFlags)
queries.ForceFlush(t)
expected := buildExpectedOpenTSDBResult(points, vmMetricName)
tc.Assert(&apptest.AssertOptions{
Retries: 300,
Msg: `unexpected metrics stored via opentsdb protocol`,
Got: func() any {
r := queries.PrometheusAPIV1Export(t, fmt.Sprintf(`{__name__=%q}`, vmMetricName), apptest.QueryOpts{
Start: queryStart,
End: queryEnd,
})
r.Sort()
return r.Data.Result
},
Want: expected,
CmpOpts: []cmp.Option{
cmpopts.IgnoreFields(apptest.PrometheusAPIV1QueryResponse{}, "Status", "Data.ResultType"),
},
})
}
func buildExpectedOpenTSDBResult(points []openTSDBPoint, vmMetricName string) []*apptest.QueryResult {
grouped := map[string]*apptest.QueryResult{}
for _, p := range points {
metric := map[string]string{"__name__": vmMetricName}
for k, v := range p.Tags {
metric[k] = v
}
key := tagsKey(metric)
if _, ok := grouped[key]; !ok {
grouped[key] = &apptest.QueryResult{Metric: metric}
}
grouped[key].Samples = append(grouped[key].Samples, &apptest.Sample{
Timestamp: p.Timestamp * 1000,
Value: p.Value,
})
}
out := make([]*apptest.QueryResult, 0, len(grouped))
for _, v := range grouped {
out = append(out, v)
}
resp := apptest.PrometheusAPIV1QueryResponse{
Data: &apptest.QueryData{Result: out},
}
resp.Sort()
return resp.Data.Result
}

View File

@@ -10,10 +10,6 @@ import (
"syscall"
"testing"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prommetadata"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/golang/snappy"
)
// Vmagent holds the state of a vmagent app and provides vmagent-specific functions
@@ -162,31 +158,6 @@ func (app *Vmagent) ReloadRelabelConfigs(t *testing.T) {
t.Fatalf("relabel configs were not reloaded after SIGHUP signal; previous total: %f, current total: %f", prevTotal, currTotal)
}
// PrometheusAPIV1Write is a test helper function that inserts a
// collection of records in Prometheus remote-write format by sending a HTTP
// POST request to /prometheus/api/v1/write vmagent endpoint.
func (app *Vmagent) PrometheusAPIV1Write(t *testing.T, wr prompb.WriteRequest, opts QueryOpts) {
t.Helper()
url := fmt.Sprintf("http://%s/prometheus/api/v1/write", app.httpListenAddr)
if opts.Tenant != "" {
url = fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/write", app.httpListenAddr, opts.Tenant)
}
data := snappy.Encode(nil, wr.MarshalProtobuf(nil))
recordsCount := len(wr.Timeseries)
if prommetadata.IsEnabled() {
recordsCount += len(wr.Metadata)
}
headers := opts.getHeaders()
headers.Set("Content-Type", "application/x-protobuf")
app.sendBlocking(t, recordsCount, func() {
_, statusCode := app.cli.Post(t, url, data, headers)
if statusCode != http.StatusNoContent {
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
}
})
}
// HTTPAddr returns the address at which the vmagent process is listening
// for http connections.
func (app *Vmagent) HTTPAddr() string {
@@ -205,22 +176,16 @@ func (app *Vmagent) HTTPAddr() string {
// If it is, then the data has been sent to vmstorage.
//
// Unreliable if the records are inserted concurrently.
func (app *Vmagent) sendBlocking(t *testing.T, _ int, send func()) {
func (app *Vmagent) sendBlocking(t *testing.T, numRecordsToSend int, send func()) {
t.Helper()
currRowsSentCount := app.remoteWriteRequestsTotal(t)
send()
const (
retries = 20
period = 100 * time.Millisecond
)
// TODO: properly account wantRowsSentCount
// currently vmagent doesn't expose per time-series write information
// so we can only account number of blocks sent via remote write protocol
// it should be suitable for tests purpose
wantRowsSentCount := currRowsSentCount + 1
wantRowsSentCount := app.remoteWriteRequestsTotal(t) + numRecordsToSend
for range retries {
if app.remoteWriteRequestsTotal(t) >= wantRowsSentCount {
return

View File

@@ -106,7 +106,7 @@ func (app *Vminsert) HTTPAddr() string {
func (app *Vminsert) InfluxWrite(t *testing.T, records []string, opts QueryOpts) {
t.Helper()
url := fmt.Sprintf("http://%s/insert/%s/influx/write", app.httpListenAddr, opts.getTenant())
url := fmt.Sprintf("http://%s/insert/%s/influx/write", app.httpListenAddr, opts.Tenant)
uv := opts.asURLValues()
uvs := uv.Encode()
if len(uvs) > 0 {
@@ -141,7 +141,7 @@ func (app *Vminsert) GraphiteWrite(t *testing.T, records []string, _ QueryOpts)
func (app *Vminsert) PrometheusAPIV1ImportCSV(t *testing.T, records []string, opts QueryOpts) {
t.Helper()
url := fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/import/csv", app.httpListenAddr, opts.getTenant())
url := fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/import/csv", app.httpListenAddr, opts.Tenant)
uv := opts.asURLValues()
uvs := uv.Encode()
if len(uvs) > 0 {
@@ -166,7 +166,7 @@ func (app *Vminsert) PrometheusAPIV1ImportCSV(t *testing.T, records []string, op
func (app *Vminsert) PrometheusAPIV1ImportNative(t *testing.T, data []byte, opts QueryOpts) {
t.Helper()
url := fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/import/native", app.httpListenAddr, opts.getTenant())
url := fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/import/native", app.httpListenAddr, opts.Tenant)
uv := opts.asURLValues()
uvs := uv.Encode()
if len(uvs) > 0 {
@@ -190,7 +190,7 @@ func (app *Vminsert) PrometheusAPIV1ImportNative(t *testing.T, data []byte, opts
func (app *Vminsert) OpenTSDBAPIPut(t *testing.T, records []string, opts QueryOpts) {
t.Helper()
url := fmt.Sprintf("http://%s/insert/%s/opentsdb/api/put", app.openTSDBListenAddr, opts.getTenant())
url := fmt.Sprintf("http://%s/insert/%s/opentsdb/api/put", app.openTSDBListenAddr, opts.Tenant)
uv := opts.asURLValues()
uvs := uv.Encode()
if len(uvs) > 0 {
@@ -213,7 +213,7 @@ func (app *Vminsert) OpenTSDBAPIPut(t *testing.T, records []string, opts QueryOp
func (app *Vminsert) PrometheusAPIV1Write(t *testing.T, wr prompb.WriteRequest, opts QueryOpts) {
t.Helper()
url := fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/write", app.httpListenAddr, opts.getTenant())
url := fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/write", app.httpListenAddr, opts.Tenant)
data := snappy.Encode(nil, wr.MarshalProtobuf(nil))
recordsCount := len(wr.Timeseries)
if prommetadata.IsEnabled() {
@@ -238,7 +238,7 @@ func (app *Vminsert) PrometheusAPIV1Write(t *testing.T, wr prompb.WriteRequest,
func (app *Vminsert) PrometheusAPIV1ImportPrometheus(t *testing.T, records []string, opts QueryOpts) {
t.Helper()
url := fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/import/prometheus", app.httpListenAddr, opts.getTenant())
url := fmt.Sprintf("http://%s/insert/%s/prometheus/api/v1/import/prometheus", app.httpListenAddr, opts.Tenant)
uv := opts.asURLValues()
uvs := uv.Encode()
if len(uvs) > 0 {
@@ -287,7 +287,7 @@ func (app *Vminsert) PrometheusAPIV1ImportPrometheus(t *testing.T, records []str
func (app *Vminsert) ZabbixConnectorHistory(t *testing.T, records []string, opts QueryOpts) {
t.Helper()
url := fmt.Sprintf("http://%s/insert/%s/zabbixconnector/api/v1/history", app.httpListenAddr, opts.getTenant())
url := fmt.Sprintf("http://%s/insert/%s/zabbixconnector/api/v1/history", app.httpListenAddr, opts.Tenant)
uv := opts.asURLValues()
uvs := uv.Encode()
if len(uvs) > 0 {

View File

@@ -72,7 +72,7 @@ func (app *Vmselect) HTTPAddr() string {
func (app *Vmselect) PrometheusAPIV1Export(t *testing.T, query string, opts QueryOpts) *PrometheusAPIV1QueryResponse {
t.Helper()
exportURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/export", app.httpListenAddr, opts.getTenant())
exportURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/export", app.httpListenAddr, opts.Tenant)
values := opts.asURLValues()
values.Add("match[]", query)
values.Add("format", "promapi")
@@ -88,7 +88,7 @@ func (app *Vmselect) PrometheusAPIV1Export(t *testing.T, query string, opts Quer
func (app *Vmselect) PrometheusAPIV1ExportNative(t *testing.T, query string, opts QueryOpts) []byte {
t.Helper()
exportURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/export/native", app.httpListenAddr, opts.getTenant())
exportURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/export/native", app.httpListenAddr, opts.Tenant)
values := opts.asURLValues()
values.Add("match[]", query)
values.Add("format", "promapi")
@@ -104,7 +104,7 @@ func (app *Vmselect) PrometheusAPIV1ExportNative(t *testing.T, query string, opt
func (app *Vmselect) PrometheusAPIV1Query(t *testing.T, query string, opts QueryOpts) *PrometheusAPIV1QueryResponse {
t.Helper()
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/query", app.httpListenAddr, opts.getTenant())
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/query", app.httpListenAddr, opts.Tenant)
values := opts.asURLValues()
values.Add("query", query)
@@ -120,7 +120,7 @@ func (app *Vmselect) PrometheusAPIV1Query(t *testing.T, query string, opts Query
func (app *Vmselect) PrometheusAPIV1QueryRange(t *testing.T, query string, opts QueryOpts) *PrometheusAPIV1QueryResponse {
t.Helper()
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/query_range", app.httpListenAddr, opts.getTenant())
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/query_range", app.httpListenAddr, opts.Tenant)
values := opts.asURLValues()
values.Add("query", query)
@@ -135,7 +135,7 @@ func (app *Vmselect) PrometheusAPIV1QueryRange(t *testing.T, query string, opts
func (app *Vmselect) PrometheusAPIV1Series(t *testing.T, matchQuery string, opts QueryOpts) *PrometheusAPIV1SeriesResponse {
t.Helper()
seriesURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/series", app.httpListenAddr, opts.getTenant())
seriesURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/series", app.httpListenAddr, opts.Tenant)
values := opts.asURLValues()
values.Add("match[]", matchQuery)
@@ -150,7 +150,7 @@ func (app *Vmselect) PrometheusAPIV1Series(t *testing.T, matchQuery string, opts
func (app *Vmselect) PrometheusAPIV1SeriesCount(t *testing.T, opts QueryOpts) *PrometheusAPIV1SeriesCountResponse {
t.Helper()
seriesURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/series/count", app.httpListenAddr, opts.getTenant())
seriesURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/series/count", app.httpListenAddr, opts.Tenant)
values := opts.asURLValues()
res, _ := app.cli.PostForm(t, seriesURL, values, opts.Headers)
@@ -167,7 +167,7 @@ func (app *Vmselect) PrometheusAPIV1Labels(t *testing.T, matchQuery string, opts
values := opts.asURLValues()
values.Add("match[]", matchQuery)
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/labels", app.httpListenAddr, opts.getTenant())
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/labels", app.httpListenAddr, opts.Tenant)
res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
return NewPrometheusAPIV1LabelsResponse(t, res)
}
@@ -181,7 +181,7 @@ func (app *Vmselect) PrometheusAPIV1LabelValues(t *testing.T, labelName, matchQu
values := opts.asURLValues()
values.Add("match[]", matchQuery)
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/label/%s/values", app.httpListenAddr, opts.getTenant(), labelName)
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/label/%s/values", app.httpListenAddr, opts.Tenant, labelName)
res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
return NewPrometheusAPIV1LabelValuesResponse(t, res)
@@ -195,7 +195,7 @@ func (app *Vmselect) PrometheusAPIV1Metadata(t *testing.T, metric string, limit
values := opts.asURLValues()
values.Add("metric", metric)
values.Add("limit", strconv.Itoa(limit))
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/metadata", app.httpListenAddr, opts.getTenant())
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/metadata", app.httpListenAddr, opts.Tenant)
res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
return NewPrometheusAPIV1Metadata(t, res)
@@ -208,7 +208,7 @@ func (app *Vmselect) PrometheusAPIV1Metadata(t *testing.T, metric string, limit
func (app *Vmselect) APIV1AdminTSDBDeleteSeries(t *testing.T, matchQuery string, opts QueryOpts) {
t.Helper()
queryURL := fmt.Sprintf("http://%s/delete/%s/prometheus/api/v1/admin/tsdb/delete_series", app.httpListenAddr, opts.getTenant())
queryURL := fmt.Sprintf("http://%s/delete/%s/prometheus/api/v1/admin/tsdb/delete_series", app.httpListenAddr, opts.Tenant)
values := opts.asURLValues()
values.Add("match[]", matchQuery)
@@ -229,7 +229,7 @@ func (app *Vmselect) MetricNamesStats(t *testing.T, limit, le, matchPattern stri
values.Add("limit", limit)
values.Add("le", le)
values.Add("match_pattern", matchPattern)
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/status/metric_names_stats", app.httpListenAddr, opts.getTenant())
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/status/metric_names_stats", app.httpListenAddr, opts.Tenant)
res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
if statusCode != http.StatusOK {
@@ -263,7 +263,7 @@ func (app *Vmselect) MetricNamesStatsReset(t *testing.T, opts QueryOpts) {
func (app *Vmselect) APIV1StatusTSDB(t *testing.T, matchQuery string, date string, topN string, opts QueryOpts) TSDBStatusResponse {
t.Helper()
seriesURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/status/tsdb", app.httpListenAddr, opts.getTenant())
seriesURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/status/tsdb", app.httpListenAddr, opts.Tenant)
values := opts.asURLValues()
addNonEmpty := func(name, value string) {
if len(value) == 0 {
@@ -294,7 +294,7 @@ func (app *Vmselect) APIV1StatusTSDB(t *testing.T, matchQuery string, date strin
func (app *Vmselect) GraphiteMetricsIndex(t *testing.T, opts QueryOpts) GraphiteMetricsIndexResponse {
t.Helper()
seriesURL := fmt.Sprintf("http://%s/select/%s/graphite/metrics/index.json", app.httpListenAddr, opts.getTenant())
seriesURL := fmt.Sprintf("http://%s/select/%s/graphite/metrics/index.json", app.httpListenAddr, opts.Tenant)
res, statusCode := app.cli.Get(t, seriesURL, opts.Headers)
if statusCode != http.StatusOK {
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
@@ -313,7 +313,7 @@ func (app *Vmselect) GraphiteMetricsIndex(t *testing.T, opts QueryOpts) Graphite
func (app *Vmselect) GraphiteTagsTagSeries(t *testing.T, record string, opts QueryOpts) {
t.Helper()
url := fmt.Sprintf("http://%s/select/%s/graphite/tags/tagSeries", app.httpListenAddr, opts.getTenant())
url := fmt.Sprintf("http://%s/select/%s/graphite/tags/tagSeries", app.httpListenAddr, opts.Tenant)
values := opts.asURLValues()
values.Add("path", record)
@@ -326,7 +326,7 @@ func (app *Vmselect) GraphiteTagsTagSeries(t *testing.T, record string, opts Que
func (app *Vmselect) GraphiteTagsTagMultiSeries(t *testing.T, records []string, opts QueryOpts) {
t.Helper()
url := fmt.Sprintf("http://%s/select/%s/graphite/tags/tagMultiSeries", app.httpListenAddr, opts.getTenant())
url := fmt.Sprintf("http://%s/select/%s/graphite/tags/tagMultiSeries", app.httpListenAddr, opts.Tenant)
values := opts.asURLValues()
for _, rec := range records {
values.Add("path", rec)

View File

@@ -9093,20 +9093,18 @@
"type": "prometheus",
"uid": "$ds"
},
"description": "Shows the rate of data rows ingested from write requests. There are two kinds of rows:\n1. Raw sample: each sample consists of a value and a timestamp, see https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples. \n2. Metric metadata: refers to descriptive information about metrics. It can be disabled by setting `-enableMetadata=false`, see https://docs.victoriametrics.com/victoriametrics/vmagent/#metric-metadata.",
"description": "* `*` - unsupported query path\n* `/write` - insert into VM\n* `/metrics` - query VM system metrics\n* `/query` - query instant values\n* `/query_range` - query over a range of time\n* `/series` - match a certain label set\n* `/label/{}/values` - query a list of label values (variables mostly)",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -9115,7 +9113,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -9123,7 +9120,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -9133,7 +9129,6 @@
"mode": "off"
}
},
"decimals": 2,
"links": [],
"mappings": [],
"min": 0,
@@ -9141,8 +9136,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -9158,9 +9152,9 @@
"h": 8,
"w": 12,
"x": 0,
"y": 43
"y": 8385
},
"id": 227,
"id": 97,
"options": {
"legend": {
"calcs": [
@@ -9175,12 +9169,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -9188,30 +9181,15 @@
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (type) > 0 ",
"expr": "sum(rate(vm_http_requests_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) by (path) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "sample: {{type}}",
"legendFormat": "__auto",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_metadata_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (type) > 0 ",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "metadata: {{type}}",
"range": true,
"refId": "B"
}
],
"title": "Rows rate ($instance)",
"title": "Requests rate ($instance)",
"type": "timeseries"
},
{
@@ -9226,13 +9204,11 @@
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
@@ -9241,7 +9217,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -9249,7 +9224,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -9267,8 +9241,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -9304,7 +9277,7 @@
"h": 8,
"w": 12,
"x": 12,
"y": 43
"y": 8385
},
"id": 99,
"options": {
@@ -9321,12 +9294,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -9364,20 +9336,17 @@
"type": "prometheus",
"uid": "$ds"
},
"description": "* `*` - unsupported query path\n* `/write` - insert into VM\n* `/metrics` - query VM system metrics\n* `/query` - query instant values\n* `/query_range` - query over a range of time\n* `/series` - match a certain label set\n* `/label/{}/values` - query a list of label values (variables mostly)",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -9386,7 +9355,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -9394,116 +9362,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"links": [],
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 51
},
"id": 97,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true,
"sortBy": "Last *",
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_http_requests_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) by (path) > 0",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Requests rate ($instance)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -9526,8 +9384,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -9542,8 +9399,8 @@
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 51
"x": 0,
"y": 8393
},
"id": 185,
"options": {
@@ -9560,12 +9417,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -9591,6 +9447,7 @@
"exemplar": true,
"expr": "min(\n rate(process_cpu_seconds_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])\n /\n process_cpu_cores_available{job=~\"$job_insert\", instance=~\"$instance\"}\n)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "min",
@@ -9606,6 +9463,7 @@
"exemplar": true,
"expr": "quantile(0.5,\n rate(process_cpu_seconds_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])\n /\n process_cpu_cores_available{job=~\"$job_insert\", instance=~\"$instance\"}\n)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "median",
@@ -9628,13 +9486,11 @@
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -9643,7 +9499,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -9651,7 +9506,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -9674,8 +9528,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -9690,8 +9543,8 @@
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 59
"x": 12,
"y": 8393
},
"id": 187,
"options": {
@@ -9708,12 +9561,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -9739,6 +9591,7 @@
"exemplar": true,
"expr": "min(\n max_over_time(process_resident_memory_anon_bytes{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])\n /\n vm_available_memory_bytes{job=~\"$job_insert\", instance=~\"$instance\"}\n)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "min",
@@ -9754,6 +9607,7 @@
"exemplar": true,
"expr": "quantile(0.5,\n max_over_time(process_resident_memory_anon_bytes{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])\n /\n vm_available_memory_bytes{job=~\"$job_insert\", instance=~\"$instance\"}\n)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "median",
@@ -9764,115 +9618,6 @@
"title": "Memory (anon) usage % ($instance)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"description": "Shows when vmstorage node is unreachable for vminsert.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"decimals": 0,
"links": [],
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 59
},
"id": 114,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"editorMode": "code",
"expr": "vm_rpc_vmstorage_is_reachable{job=~\"$job\", instance=~\"$instance\"} != 1",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{instance}} => {{addr}}",
"range": true,
"refId": "A"
}
],
"title": "Storage reachability ($instance)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
@@ -9885,13 +9630,11 @@
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -9900,7 +9643,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -9908,7 +9650,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -9926,8 +9667,7 @@
"mode": "absolute",
"steps": [
{
"color": "transparent",
"value": 0
"color": "transparent"
},
{
"color": "red",
@@ -9943,7 +9683,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 67
"y": 8401
},
"id": 139,
"options": {
@@ -9959,12 +9699,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -9990,20 +9729,18 @@
"type": "prometheus",
"uid": "$ds"
},
"description": "Shows network usage between vminserts and vmstorages.",
"description": "Shows when vmstorage node is unreachable for vminsert.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -10012,7 +9749,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -10020,7 +9756,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -10030,14 +9765,15 @@
"mode": "off"
}
},
"decimals": 0,
"links": [],
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -10045,30 +9781,17 @@
}
]
},
"unit": "bps"
"unit": "short"
},
"overrides": [
{
"matcher": {
"id": "byRegexp",
"options": "/read.*/"
},
"properties": [
{
"id": "custom.transform",
"value": "negative-Y"
}
]
}
]
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 67
"y": 8401
},
"id": 209,
"id": 114,
"options": {
"legend": {
"calcs": [
@@ -10077,17 +9800,14 @@
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true,
"sortBy": "Last *",
"sortDesc": true
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -10095,28 +9815,16 @@
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_tcpdialer_read_bytes_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) * 8 > 0",
"expr": "vm_rpc_vmstorage_is_reachable{job=~\"$job\", instance=~\"$instance\"} != 1",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "read from vmstorage",
"legendFormat": "{{instance}} => {{addr}}",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_tcpdialer_written_bytes_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) * 8 > 0",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "write to vmstorage",
"range": true,
"refId": "B"
}
],
"title": "Network usage: vmstorage ($instance)",
"title": "Storage reachability ($instance)",
"type": "timeseries"
},
{
@@ -10131,13 +9839,11 @@
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -10146,7 +9852,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -10154,7 +9859,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -10170,8 +9874,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -10200,7 +9903,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 75
"y": 8409
},
"id": 208,
"options": {
@@ -10216,12 +9919,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -10244,6 +9946,7 @@
"editorMode": "code",
"expr": "sum(rate(vm_tcplistener_written_bytes_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) * 8 > 0",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
"legendFormat": "write to client",
"range": true,
@@ -10258,19 +9961,147 @@
"type": "prometheus",
"uid": "$ds"
},
"description": "Shows network usage between vminserts and vmstorages.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"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": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
},
"unit": "bps"
},
"overrides": [
{
"matcher": {
"id": "byRegexp",
"options": "/read.*/"
},
"properties": [
{
"id": "custom.transform",
"value": "negative-Y"
}
]
}
]
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 8409
},
"id": 209,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true,
"sortBy": "Last *",
"sortDesc": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_tcpdialer_read_bytes_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) * 8 > 0",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "read from vmstorage",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_tcpdialer_written_bytes_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) * 8 > 0",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
"legendFormat": "write to vmstorage",
"range": true,
"refId": "B"
}
],
"title": "Network usage: vmstorage ($instance)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -10279,7 +10110,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -10287,7 +10117,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -10305,8 +10134,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -10322,7 +10150,7 @@
"h": 8,
"w": 12,
"x": 12,
"y": 75
"y": 8417
},
"id": 88,
"options": {
@@ -10339,12 +10167,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {

View File

@@ -9094,20 +9094,18 @@
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"description": "Shows the rate of data rows ingested from write requests. There are two kinds of rows:\n1. Raw sample: each sample consists of a value and a timestamp, see https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples. \n2. Metric metadata: refers to descriptive information about metrics. It can be disabled by setting `-enableMetadata=false`, see https://docs.victoriametrics.com/victoriametrics/vmagent/#metric-metadata.",
"description": "* `*` - unsupported query path\n* `/write` - insert into VM\n* `/metrics` - query VM system metrics\n* `/query` - query instant values\n* `/query_range` - query over a range of time\n* `/series` - match a certain label set\n* `/label/{}/values` - query a list of label values (variables mostly)",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -9116,7 +9114,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -9124,7 +9121,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -9134,7 +9130,6 @@
"mode": "off"
}
},
"decimals": 2,
"links": [],
"mappings": [],
"min": 0,
@@ -9142,8 +9137,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -9159,9 +9153,9 @@
"h": 8,
"w": 12,
"x": 0,
"y": 43
"y": 8385
},
"id": 227,
"id": 97,
"options": {
"legend": {
"calcs": [
@@ -9176,12 +9170,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -9189,30 +9182,15 @@
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (type) > 0 ",
"expr": "sum(rate(vm_http_requests_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) by (path) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "sample: {{type}}",
"legendFormat": "__auto",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_metadata_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (type) > 0 ",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "metadata: {{type}}",
"range": true,
"refId": "B"
}
],
"title": "Rows rate ($instance)",
"title": "Requests rate ($instance)",
"type": "timeseries"
},
{
@@ -9227,13 +9205,11 @@
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
@@ -9242,7 +9218,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -9250,7 +9225,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -9268,8 +9242,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -9305,7 +9278,7 @@
"h": 8,
"w": 12,
"x": 12,
"y": 43
"y": 8385
},
"id": 99,
"options": {
@@ -9322,12 +9295,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -9365,20 +9337,17 @@
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"description": "* `*` - unsupported query path\n* `/write` - insert into VM\n* `/metrics` - query VM system metrics\n* `/query` - query instant values\n* `/query_range` - query over a range of time\n* `/series` - match a certain label set\n* `/label/{}/values` - query a list of label values (variables mostly)",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -9387,7 +9356,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -9395,116 +9363,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"links": [],
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 51
},
"id": 97,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true,
"sortBy": "Last *",
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"targets": [
{
"datasource": {
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_http_requests_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) by (path) > 0",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Requests rate ($instance)",
"type": "timeseries"
},
{
"datasource": {
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -9527,8 +9385,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -9543,8 +9400,8 @@
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 51
"x": 0,
"y": 8393
},
"id": 185,
"options": {
@@ -9561,12 +9418,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -9592,6 +9448,7 @@
"exemplar": true,
"expr": "min(\n rate(process_cpu_seconds_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])\n /\n process_cpu_cores_available{job=~\"$job_insert\", instance=~\"$instance\"}\n)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "min",
@@ -9607,6 +9464,7 @@
"exemplar": true,
"expr": "quantile(0.5,\n rate(process_cpu_seconds_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])\n /\n process_cpu_cores_available{job=~\"$job_insert\", instance=~\"$instance\"}\n)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "median",
@@ -9629,13 +9487,11 @@
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -9644,7 +9500,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -9652,7 +9507,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -9675,8 +9529,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -9691,8 +9544,8 @@
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 59
"x": 12,
"y": 8393
},
"id": 187,
"options": {
@@ -9709,12 +9562,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -9740,6 +9592,7 @@
"exemplar": true,
"expr": "min(\n max_over_time(process_resident_memory_anon_bytes{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])\n /\n vm_available_memory_bytes{job=~\"$job_insert\", instance=~\"$instance\"}\n)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "min",
@@ -9755,6 +9608,7 @@
"exemplar": true,
"expr": "quantile(0.5,\n max_over_time(process_resident_memory_anon_bytes{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])\n /\n vm_available_memory_bytes{job=~\"$job_insert\", instance=~\"$instance\"}\n)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "median",
@@ -9765,115 +9619,6 @@
"title": "Memory (anon) usage % ($instance)",
"type": "timeseries"
},
{
"datasource": {
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"description": "Shows when vmstorage node is unreachable for vminsert.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"decimals": 0,
"links": [],
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 59
},
"id": 114,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"targets": [
{
"datasource": {
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"editorMode": "code",
"expr": "vm_rpc_vmstorage_is_reachable{job=~\"$job\", instance=~\"$instance\"} != 1",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{instance}} => {{addr}}",
"range": true,
"refId": "A"
}
],
"title": "Storage reachability ($instance)",
"type": "timeseries"
},
{
"datasource": {
"type": "victoriametrics-metrics-datasource",
@@ -9886,13 +9631,11 @@
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -9901,7 +9644,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -9909,7 +9651,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -9927,8 +9668,7 @@
"mode": "absolute",
"steps": [
{
"color": "transparent",
"value": 0
"color": "transparent"
},
{
"color": "red",
@@ -9944,7 +9684,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 67
"y": 8401
},
"id": 139,
"options": {
@@ -9960,12 +9700,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -9991,20 +9730,18 @@
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"description": "Shows network usage between vminserts and vmstorages.",
"description": "Shows when vmstorage node is unreachable for vminsert.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -10013,7 +9750,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -10021,7 +9757,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -10031,14 +9766,15 @@
"mode": "off"
}
},
"decimals": 0,
"links": [],
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -10046,30 +9782,17 @@
}
]
},
"unit": "bps"
"unit": "short"
},
"overrides": [
{
"matcher": {
"id": "byRegexp",
"options": "/read.*/"
},
"properties": [
{
"id": "custom.transform",
"value": "negative-Y"
}
]
}
]
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 67
"y": 8401
},
"id": 209,
"id": 114,
"options": {
"legend": {
"calcs": [
@@ -10078,17 +9801,14 @@
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true,
"sortBy": "Last *",
"sortDesc": true
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -10096,28 +9816,16 @@
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_tcpdialer_read_bytes_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) * 8 > 0",
"expr": "vm_rpc_vmstorage_is_reachable{job=~\"$job\", instance=~\"$instance\"} != 1",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "read from vmstorage",
"legendFormat": "{{instance}} => {{addr}}",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_tcpdialer_written_bytes_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) * 8 > 0",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "write to vmstorage",
"range": true,
"refId": "B"
}
],
"title": "Network usage: vmstorage ($instance)",
"title": "Storage reachability ($instance)",
"type": "timeseries"
},
{
@@ -10132,13 +9840,11 @@
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -10147,7 +9853,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -10155,7 +9860,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -10171,8 +9875,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -10201,7 +9904,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 75
"y": 8409
},
"id": 208,
"options": {
@@ -10217,12 +9920,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
@@ -10245,6 +9947,7 @@
"editorMode": "code",
"expr": "sum(rate(vm_tcplistener_written_bytes_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) * 8 > 0",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
"legendFormat": "write to client",
"range": true,
@@ -10259,19 +9962,147 @@
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"description": "Shows network usage between vminserts and vmstorages.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"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": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
},
"unit": "bps"
},
"overrides": [
{
"matcher": {
"id": "byRegexp",
"options": "/read.*/"
},
"properties": [
{
"id": "custom.transform",
"value": "negative-Y"
}
]
}
]
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 8409
},
"id": 209,
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true,
"sortBy": "Last *",
"sortDesc": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_tcpdialer_read_bytes_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) * 8 > 0",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "read from vmstorage",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_tcpdialer_written_bytes_total{job=~\"$job_insert\", instance=~\"$instance\"}[$__rate_interval])) * 8 > 0",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
"legendFormat": "write to vmstorage",
"range": true,
"refId": "B"
}
],
"title": "Network usage: vmstorage ($instance)",
"type": "timeseries"
},
{
"datasource": {
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -10280,7 +10111,6 @@
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
@@ -10288,7 +10118,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -10306,8 +10135,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -10323,7 +10151,7 @@
"h": 8,
"w": 12,
"x": 12,
"y": 75
"y": 8417
},
"id": 88,
"options": {
@@ -10340,12 +10168,11 @@
"sortDesc": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.1.0",
"targets": [
{
"datasource": {

View File

@@ -4020,7 +4020,7 @@
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"description": "Shows the rate of data rows parsed from write requests and scraping. \nThere are two kinds of rows:\n1. Raw sample: each sample consists of a value and a timestamp, see https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples \n2. Metric metadata: refers to descriptive information about metrics. It can be disabled by setting `-enableMetadata=false`, see https://docs.victoriametrics.com/victoriametrics/vmagent/#metric-metadata.",
"description": "Shows the rate of parsed datapoints from write or scrape requests.",
"fieldConfig": {
"defaults": {
"color": {
@@ -4050,7 +4050,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -4067,8 +4066,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -4104,7 +4102,7 @@
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "11.5.0",
"targets": [
{
"datasource": {
@@ -4115,24 +4113,12 @@
"exemplar": true,
"expr": "sum(rate(vm_protoparser_rows_read_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, type) > 0",
"interval": "",
"legendFormat": "sample: {{ type }} ({{job}})",
"legendFormat": "{{ type }} ({{job}})",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_protoparser_metadata_read_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, type) > 0",
"instant": false,
"legendFormat": "metadata: {{ type }} ({{job}})",
"range": true,
"refId": "B"
}
],
"title": "Rows rate ($instance)",
"title": "Datapoints rate ($instance)",
"type": "timeseries"
},
{
@@ -5736,7 +5722,7 @@
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"description": "Shows the rate of data rows ingested from write requests. There are two kinds of rows:\n1. Raw sample: each sample consists of a value and a timestamp, see https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples. \n2. Metric metadata: refers to descriptive information about metrics. It can be disabled by setting `-enableMetadata=false`, see https://docs.victoriametrics.com/victoriametrics/vmagent/#metric-metadata.",
"description": "Shows the rate of rows ingested in vmagent via push protocols.",
"fieldConfig": {
"defaults": {
"color": {
@@ -5749,7 +5735,6 @@
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -5766,7 +5751,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -5783,8 +5767,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -5800,7 +5783,7 @@
"h": 8,
"w": 12,
"x": 12,
"y": 41
"y": 3931
},
"id": 131,
"options": {
@@ -5815,12 +5798,11 @@
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
@@ -5831,24 +5813,12 @@
"exemplar": true,
"expr": "sum(rate(vmagent_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, type) > 0",
"interval": "",
"legendFormat": "sample: {{ type }} ({{job}})",
"legendFormat": "{{ type }} ({{job}})",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "victoriametrics-metrics-datasource",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vmagent_metadata_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, type) > 0",
"instant": false,
"legendFormat": "metadata:{{ type }} ({{job}})",
"range": true,
"refId": "B"
}
],
"title": "Rows rate ($instance)",
"title": "Rows rate ($instance)",
"type": "timeseries"
},
{

View File

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

View File

@@ -4019,7 +4019,7 @@
"type": "prometheus",
"uid": "$ds"
},
"description": "Shows the rate of data rows parsed from write requests and scraping. \nThere are two kinds of rows:\n1. Raw sample: each sample consists of a value and a timestamp, see https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples \n2. Metric metadata: refers to descriptive information about metrics. It can be disabled by setting `-enableMetadata=false`, see https://docs.victoriametrics.com/victoriametrics/vmagent/#metric-metadata.",
"description": "Shows the rate of parsed datapoints from write or scrape requests.",
"fieldConfig": {
"defaults": {
"color": {
@@ -4049,7 +4049,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -4066,8 +4065,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -4103,7 +4101,7 @@
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "11.5.0",
"targets": [
{
"datasource": {
@@ -4114,24 +4112,12 @@
"exemplar": true,
"expr": "sum(rate(vm_protoparser_rows_read_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, type) > 0",
"interval": "",
"legendFormat": "sample: {{ type }} ({{job}})",
"legendFormat": "{{ type }} ({{job}})",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vm_protoparser_metadata_read_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, type) > 0",
"instant": false,
"legendFormat": "metadata: {{ type }} ({{job}})",
"range": true,
"refId": "B"
}
],
"title": "Rows rate ($instance)",
"title": "Datapoints rate ($instance)",
"type": "timeseries"
},
{
@@ -5735,7 +5721,7 @@
"type": "prometheus",
"uid": "$ds"
},
"description": "Shows the rate of data rows ingested from write requests. There are two kinds of rows:\n1. Raw sample: each sample consists of a value and a timestamp, see https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples. \n2. Metric metadata: refers to descriptive information about metrics. It can be disabled by setting `-enableMetadata=false`, see https://docs.victoriametrics.com/victoriametrics/vmagent/#metric-metadata.",
"description": "Shows the rate of rows ingested in vmagent via push protocols.",
"fieldConfig": {
"defaults": {
"color": {
@@ -5748,7 +5734,6 @@
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
@@ -5765,7 +5750,6 @@
"type": "linear"
},
"showPoints": "never",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
@@ -5782,8 +5766,7 @@
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
"color": "green"
},
{
"color": "red",
@@ -5799,7 +5782,7 @@
"h": 8,
"w": 12,
"x": 12,
"y": 41
"y": 3931
},
"id": 131,
"options": {
@@ -5814,12 +5797,11 @@
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "12.4.3",
"pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
@@ -5830,24 +5812,12 @@
"exemplar": true,
"expr": "sum(rate(vmagent_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, type) > 0",
"interval": "",
"legendFormat": "sample: {{ type }} ({{job}})",
"legendFormat": "{{ type }} ({{job}})",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"editorMode": "code",
"expr": "sum(rate(vmagent_metadata_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, type) > 0",
"instant": false,
"legendFormat": "metadata:{{ type }} ({{job}})",
"range": true,
"refId": "B"
}
],
"title": "Rows rate ($instance)",
"title": "Rows rate ($instance)",
"type": "timeseries"
},
{

View File

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

View File

@@ -3,9 +3,9 @@
DOCKER_REGISTRIES ?= docker.io quay.io
DOCKER_NAMESPACE ?= victoriametrics
ROOT_IMAGE ?= alpine:3.23.4
ROOT_IMAGE ?= alpine:3.23.3
ROOT_IMAGE_SCRATCH ?= scratch
CERTS_IMAGE := alpine:3.23.4
CERTS_IMAGE := alpine:3.23.3
GO_BUILDER_IMAGE := golang:1.26.2

View File

@@ -151,7 +151,7 @@ Some alerting rules thresholds are just recommendations and could require an adj
The list of alerting rules is the following:
* [alerts-health.yml](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/deployment/docker/rules/alerts-health.yml):
alerting rules related to all VictoriaMetrics components for tracking their "health" state;
* [alerts-single-node.yml](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/deployment/docker/rules/alerts-single-node.yml):
* [alerts.yml](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/deployment/docker/rules/alerts.yml):
alerting rules related to [single-server VictoriaMetrics](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) installation;
* [alerts-cluster.yml](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/deployment/docker/rules/alerts-cluster.yml):
alerting rules related to [cluster version of VictoriaMetrics](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/);

View File

@@ -3,7 +3,7 @@ services:
# It scrapes targets defined in --promscrape.config
# And forward them to --remoteWrite.url
vmagent:
image: victoriametrics/vmagent:v1.142.0
image: victoriametrics/vmagent:v1.140.0
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:v1.142.0-cluster
image: victoriametrics/vmstorage:v1.140.0-cluster
volumes:
- strgdata-1:/storage
command:
- "--storageDataPath=/storage"
restart: always
vmstorage-2:
image: victoriametrics/vmstorage:v1.142.0-cluster
image: victoriametrics/vmstorage:v1.140.0-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:v1.142.0-cluster
image: victoriametrics/vminsert:v1.140.0-cluster
depends_on:
- "vmstorage-1"
- "vmstorage-2"
@@ -68,7 +68,7 @@ services:
- "--storageNode=vmstorage-2:8400"
restart: always
vminsert-2:
image: victoriametrics/vminsert:v1.142.0-cluster
image: victoriametrics/vminsert:v1.140.0-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:v1.142.0-cluster
image: victoriametrics/vmselect:v1.140.0-cluster
depends_on:
- "vmstorage-1"
- "vmstorage-2"
@@ -90,7 +90,7 @@ services:
- "--vmalert.proxyURL=http://vmalert:8880"
restart: always
vmselect-2:
image: victoriametrics/vmselect:v1.142.0-cluster
image: victoriametrics/vmselect:v1.140.0-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:v1.142.0
image: victoriametrics/vmauth:v1.140.0
depends_on:
- "vmselect-1"
- "vmselect-2"
@@ -119,13 +119,13 @@ services:
# vmalert executes alerting and recording rules
vmalert:
image: victoriametrics/vmalert:v1.142.0
image: victoriametrics/vmalert:v1.140.0
depends_on:
- "vmauth"
ports:
- 8880:8880
volumes:
- ./rules/alerts-cluster.yml:/etc/alerts/alerts-cluster.yml
- ./rules/alerts-cluster.yml:/etc/alerts/alerts.yml
- ./rules/alerts-health.yml:/etc/alerts/alerts-health.yml
- ./rules/alerts-vmagent.yml:/etc/alerts/alerts-vmagent.yml
- ./rules/alerts-vmalert.yml:/etc/alerts/alerts-vmalert.yml

View File

@@ -3,7 +3,7 @@ services:
# It scrapes targets defined in --promscrape.config
# And forward them to --remoteWrite.url
vmagent:
image: victoriametrics/vmagent:v1.142.0
image: victoriametrics/vmagent:v1.140.0
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:v1.142.0
image: victoriametrics/victoria-metrics:v1.140.0
ports:
- 8428:8428
- 8089:8089
@@ -59,14 +59,14 @@ services:
# vmalert executes alerting and recording rules
vmalert:
image: victoriametrics/vmalert:v1.142.0
image: victoriametrics/vmalert:v1.140.0
depends_on:
- "victoriametrics"
- "alertmanager"
ports:
- 8880:8880
volumes:
- ./rules/alerts-single-node.yml:/etc/alerts/alerts-single-node.yml
- ./rules/alerts.yml:/etc/alerts/alerts.yml
- ./rules/alerts-health.yml:/etc/alerts/alerts-health.yml
- ./rules/alerts-vmagent.yml:/etc/alerts/alerts-vmagent.yml
- ./rules/alerts-vmalert.yml:/etc/alerts/alerts-vmalert.yml

View File

@@ -170,57 +170,3 @@ groups:
is saturated by more than 90% and vminsert won't be able to keep up.\n
This usually means that more vminsert or vmstorage nodes must be added to the cluster in order to increase
the total number of vminsert -> vmstorage links."
- alert: MetadataCacheUtilizationIsTooHigh
expr: |
vm_metrics_metadata_storage_size_bytes / vm_metrics_metadata_storage_max_size_bytes > 0.95
for: 15m
labels:
severity: warning
annotations:
summary: "Metadata cache capacity on {{ $labels.instance }} (job={{ $labels.job }}) is utilized for more than 95% for the last 15min"
description: "Metadata cache stores meta information about ingested time series - see https://docs.victoriametrics.com/victoriametrics/#metrics-metadata.
When cache is overutilized, the oldest entries will be dropped out automatically. It may result into incomplete
response for /api/v1/metadata API calls. It doesn't impact regular queries or alerts. Cache size is controlled
via -storage.maxMetadataStorageSize cmd-line flag."
- alert: MetricNameStatsCacheUtilizationIsTooHigh
expr: |
vm_cache_size_bytes{type="storage/metricNamesStatsTracker"} / vm_cache_size_max_bytes{type="storage/metricNamesStatsTracker"} > 0.95
for: 15m
labels:
severity: warning
annotations:
summary: "Cache capacity for tracking metric names usage on {{ $labels.instance }} (job={{ $labels.job }}) is utilized for more than 95% during the last 15min"
description: "Metric names usage cache stores information about unique metric names and how frequently they are queried - see https://docs.victoriametrics.com/victoriametrics/#track-ingested-metrics-usage.
When cache is overutilized, it will stop tracking the new metric names. It has no other negative impact.
Usually, the number of unique metric names is very limited (thousands). The cache can be overutilized only if metric names
are changing too frequently or if the cache size is too low. There are following ways to mitigate cache overutilization:
- disable cache via `--storage.trackMetricNamesStats=false` flag, so metric names usage will stop tracking
- increase the cache size via `--storage.cacheSizeMetricNamesStats` flag
- reset the cache (see docs for details)"
- alert: IndexDBRecordsDrop
expr: increase(vm_indexdb_items_dropped_total[5m]) > 0
labels:
severity: critical
annotations:
summary: "IndexDB skipped registering items during data ingestion with reason={{ $labels.reason }}."
description: |
VictoriaMetrics could skip registering new timeseries during ingestion if they fail the validation process.
For example, `reason=too_long_item` means that time series cannot exceed 64KB. Please, reduce the number
of labels or label values for such series. Or enforce these limits via `-maxLabelsPerTimeseries` and
`-maxLabelValueLen` command-line flags.
- alert: TooManyTSIDMisses
expr: increase(vm_missing_tsids_for_metric_id_total[5m]) > 0
for: 15m
labels:
severity: critical
annotations:
summary: "Unexpected TSID misses for job \"{{ $labels.job }}\" ({{ $labels.instance }}) for the last 15 minutes"
description: |
Unexpected TSID misses for \"{{ $labels.job }}\" ({{ $labels.instance }}) for the last 15 minutes.
If this happens after unclean shutdown of VictoriaMetrics process (via \"kill -9\", OOM or power off),
then this is OK - the alert must go away in a few minutes after the restart.
Otherwise this may point to the corruption of index data.

View File

@@ -82,6 +82,19 @@ groups:
Check the logs for the given target. Check also the \"location\" label at the vm_log_messages_total metric if -loggerLevel command-line flag is set to value other than INFO.
This label contains code locations responsible for generating log messages suppressed by -loggerLevel.
- alert: TooManyTSIDMisses
expr: increase(vm_missing_tsids_for_metric_id_total[5m]) > 0
for: 15m
labels:
severity: critical
annotations:
summary: "Unexpected TSID misses for job \"{{ $labels.job }}\" ({{ $labels.instance }}) for the last 15 minutes"
description: |
Unexpected TSID misses for \"{{ $labels.job }}\" ({{ $labels.instance }}) for the last 15 minutes.
If this happens after unclean shutdown of VictoriaMetrics process (via \"kill -9\", OOM or power off),
then this is OK - the alert must go away in a few minutes after the restart.
Otherwise this may point to the corruption of index data.
- alert: ConcurrentInsertsHitTheLimit
expr: avg_over_time(vm_concurrent_insert_current[1m]) >= vm_concurrent_insert_capacity
for: 15m
@@ -96,6 +109,28 @@ groups:
making write attempts. If vmagent's or vminsert's CPU usage and network saturation are at normal level, then
it might be worth adjusting `-maxConcurrentInserts` cmd-line flag.
- alert: IndexDBRecordsDrop
expr: increase(vm_indexdb_items_dropped_total[5m]) > 0
labels:
severity: critical
annotations:
summary: "IndexDB skipped registering items during data ingestion with reason={{ $labels.reason }}."
description: |
VictoriaMetrics could skip registering new timeseries during ingestion if they fail the validation process.
For example, `reason=too_long_item` means that time series cannot exceed 64KB. Please, reduce the number
of labels or label values for such series. Or enforce these limits via `-maxLabelsPerTimeseries` and
`-maxLabelValueLen` command-line flags.
- alert: RowsRejectedOnIngestion
expr: rate(vm_rows_ignored_total[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
summary: "Some rows are rejected on \"{{ $labels.instance }}\" on ingestion attempt"
description: "Ingested rows on instance \"{{ $labels.instance }}\" are rejected due to the
following reason: \"{{ $labels.reason }}\""
- alert: TooHighQueryLoad
expr: increase(vm_concurrent_select_limit_timeout_total[5m]) > 0
for: 15m
@@ -113,14 +148,3 @@ groups:
* increase compute resources or number of replicas;
* adjust limits `-search.maxConcurrentRequests` and `-search.maxQueueDuration`.
See more at https://docs.victoriametrics.com/victoriametrics/troubleshooting/#slow-queries.
- alert: RowsRejectedOnIngestion
expr: rate(vm_rows_ignored_total[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
summary: "Some rows are rejected on \"{{ $labels.instance }}\" on ingestion attempt"
description: "Ingested rows on instance \"{{ $labels.instance }}\" are rejected due to the
following reason: \"{{ $labels.reason }}\""

View File

@@ -148,45 +148,4 @@ groups:
description: "Metadata cache stores meta information about ingested time series - see https://docs.victoriametrics.com/victoriametrics/#metrics-metadata.
When cache is overutilized, the oldest entries will be dropped out automatically. It may result into incomplete
response for /api/v1/metadata API calls. It doesn't impact regular queries or alerts. Cache size is controlled
via -storage.maxMetadataStorageSize cmd-line flag."
- alert: MetricNameStatsCacheUtilizationIsTooHigh
expr: |
vm_cache_size_bytes{type="storage/metricNamesStatsTracker"} / vm_cache_size_max_bytes{type="storage/metricNamesStatsTracker"} > 0.95
for: 15m
labels:
severity: warning
annotations:
summary: "Cache capacity for tracking metric names usage on {{ $labels.instance }} (job={{ $labels.job }}) is utilized for more than 95% during the last 15min"
description: "Metric names usage cache stores information about unique metric names and how frequently they are queried - see https://docs.victoriametrics.com/victoriametrics/#track-ingested-metrics-usage.
When cache is overutilized, it will stop tracking the new metric names. It has no other negative impact.
Usually, the number of unique metric names is very limited (thousands). The cache can be overutilized only if metric names
are changing too frequently or if the cache size is too low. There are following ways to mitigate cache overutilization:
- disable cache via `--storage.trackMetricNamesStats=false` flag, so metric names usage will stop tracking
- increase the cache size via `--storage.cacheSizeMetricNamesStats` flag
- reset the cache (see docs for details)"
- alert: IndexDBRecordsDrop
expr: increase(vm_indexdb_items_dropped_total[5m]) > 0
labels:
severity: critical
annotations:
summary: "IndexDB skipped registering items during data ingestion with reason={{ $labels.reason }}."
description: |
VictoriaMetrics could skip registering new timeseries during ingestion if they fail the validation process.
For example, `reason=too_long_item` means that time series cannot exceed 64KB. Please, reduce the number
of labels or label values for such series. Or enforce these limits via `-maxLabelsPerTimeseries` and
`-maxLabelValueLen` command-line flags.
- alert: TooManyTSIDMisses
expr: increase(vm_missing_tsids_for_metric_id_total[5m]) > 0
for: 15m
labels:
severity: critical
annotations:
summary: "Unexpected TSID misses for job \"{{ $labels.job }}\" ({{ $labels.instance }}) for the last 15 minutes"
description: |
Unexpected TSID misses for \"{{ $labels.job }}\" ({{ $labels.instance }}) for the last 15 minutes.
If this happens after unclean shutdown of VictoriaMetrics process (via \"kill -9\", OOM or power off),
then this is OK - the alert must go away in a few minutes after the restart.
Otherwise this may point to the corruption of index data.
via -storage.maxMetadataStorageSize cmd-line flag."

View File

@@ -1,6 +1,6 @@
services:
vmagent:
image: victoriametrics/vmagent:v1.142.0
image: victoriametrics/vmagent:v1.140.0
depends_on:
- "victoriametrics"
ports:
@@ -14,7 +14,7 @@ services:
restart: always
victoriametrics:
image: victoriametrics/victoria-metrics:v1.142.0
image: victoriametrics/victoria-metrics:v1.140.0
ports:
- 8428:8428
volumes:
@@ -40,7 +40,7 @@ services:
restart: always
vmalert:
image: victoriametrics/vmalert:v1.142.0
image: victoriametrics/vmalert:v1.140.0
depends_on:
- "victoriametrics"
ports:

View File

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

View File

@@ -48,15 +48,13 @@ Please see example graph illustrating this logic below:
## What data does vmanomaly operate on?
> [!NOTE]
> `vmanomaly` operates on timeseries (metrics) data, and supports both **VictoriaMetrics** and **VictoriaLogs/VictoriaTraces** as data sources to get metrics-compatible data. Choose the source depending on the use case. Single-node / Cluster and OpenSource / Enterprise datasources are supported as well, `vmanomaly` is compatible with both, yet itself requires an [Enterprise license](https://victoriametrics.com/products/enterprise/) to run.
`vmanomaly` operates on timeseries (metrics) data, and supports both **VictoriaMetrics** and **VictoriaLogs** as data sources. Choose the source depending on the use case.
**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/#vlogs-reader) to create log-derived metrics for anomaly detection (e.g., error rates, request latencies).
> [!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.
> 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.
## Using offsets

View File

@@ -9,17 +9,14 @@ sitemap:
In today's fast-paced and complex landscape of system monitoring, [VictoriaMetrics Anomaly Detection](https://victoriametrics.com/products/enterprise/anomaly-detection/) (`vmanomaly`), a part of our [Enterprise offering](https://victoriametrics.com/products/enterprise/), serves as an **observability layer** for SREs and DevOps teams atop of collected data to **automate the detection of anomalies in time-series data**, reducing manual efforts required to identify abnormal system behavior.
Unlike traditional threshold-based alerting, which relies on **raw metric values** and requires constant tuning and maintenance of thresholds and alerting rules, `vmanomaly` introduces a **unified, interpretable [anomaly score](https://docs.victoriametrics.com/anomaly-detection/faq/#what-is-anomaly-score)** - a **de-trended, de-seasonalized metric** generated through machine learning. This approach eliminates the need for frequent manual adjustments by enabling **stable, long-term static thresholds (as simple as `anomaly_score > 1`)** that remain effective over time through continuous model retraining and updates.
Unlike traditional threshold-based alerting, which relies on **raw metric values** and requires constant tuning and maintenance of thresholds and alerting rules, `vmanomaly` introduces a **unified, interpretable [anomaly score](https://docs.victoriametrics.com/anomaly-detection/faq/#what-is-anomaly-score)** - a **de-trended, de-seasonalized metric** generated through machine learning. This approach eliminates the need for frequent manual adjustments by enabling **stable, long-term static thresholds (as simple as `anomaly_score > 1`)** that remain effective over time through continuous model retraining.
By shifting to anomaly-based detection, teams can **identify and respond to potential issues faster**, enhancing system reliability and operational efficiency while significantly **reducing the engineering effort spent on handcrafting and maintaining alerting rules**.
## What does it do?
`vmanomaly` is designed to **periodically analyze new data points** across selected metrics - either requested from [VictoriaMetrics TSDB](https://docs.victoriametrics.com/victoriametrics/) or produced by [VictoriaLogs](https://docs.victoriametrics.com/victorialogs/) or [VictoriaTraces](https://docs.victoriametrics.com/victoriatraces/) metrics [endpoint](https://docs.victoriametrics.com/victorialogs/querying/#querying-log-range-stats) - to generate a **unified metric** called [anomaly score](https://docs.victoriametrics.com/anomaly-detection/faq/#what-is-anomaly-score).
> [!NOTE]
> `vmanomaly` can use both single-node and cluster versions of VictoriaMetrics/VictoriaLogs/VictoriaTraces as a data source, and is compatible with both OpenSource and Enterprise versions of it. However, `vmanomaly` itself requires an Enterprise license to run, and is part of our [Enterprise offering](https://victoriametrics.com/products/enterprise/).
`vmanomaly` is designed to **periodically analyze new data points** across selected metrics (either requested from [VictoriaMetrics TSDB](https://docs.victoriametrics.com/victoriametrics/) or produced by [VictoriaLogs](https://docs.victoriametrics.com/victorialogs/) metrics [endpoint](https://docs.victoriametrics.com/victorialogs/querying/#querying-log-range-stats)), generating a **unified metric** called [anomaly score](https://docs.victoriametrics.com/anomaly-detection/faq/#what-is-anomaly-score).
Key functions:
- **Automated anomaly detection** - continuously scans time-series data to identify deviations from expected behavior.

Binary file not shown.

Before

Width:  |  Height:  |  Size: 357 KiB

After

Width:  |  Height:  |  Size: 51 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 467 KiB

After

Width:  |  Height:  |  Size: 54 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 188 KiB

After

Width:  |  Height:  |  Size: 22 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 234 KiB

After

Width:  |  Height:  |  Size: 25 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 282 KiB

After

Width:  |  Height:  |  Size: 106 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.0 MiB

After

Width:  |  Height:  |  Size: 181 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 929 KiB

After

Width:  |  Height:  |  Size: 164 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 563 KiB

After

Width:  |  Height:  |  Size: 104 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 871 KiB

After

Width:  |  Height:  |  Size: 331 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 310 KiB

After

Width:  |  Height:  |  Size: 93 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 944 KiB

After

Width:  |  Height:  |  Size: 122 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 19 KiB

After

Width:  |  Height:  |  Size: 2.6 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 303 KiB

After

Width:  |  Height:  |  Size: 44 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 681 KiB

After

Width:  |  Height:  |  Size: 140 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 805 KiB

After

Width:  |  Height:  |  Size: 109 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 111 KiB

After

Width:  |  Height:  |  Size: 17 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.2 MiB

After

Width:  |  Height:  |  Size: 160 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 189 KiB

After

Width:  |  Height:  |  Size: 236 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 206 KiB

After

Width:  |  Height:  |  Size: 26 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 206 KiB

After

Width:  |  Height:  |  Size: 26 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 12 KiB

After

Width:  |  Height:  |  Size: 1.5 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 206 KiB

After

Width:  |  Height:  |  Size: 53 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 428 KiB

After

Width:  |  Height:  |  Size: 42 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 37 KiB

After

Width:  |  Height:  |  Size: 9.7 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 740 KiB

After

Width:  |  Height:  |  Size: 34 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 11 KiB

After

Width:  |  Height:  |  Size: 2.4 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 225 KiB

After

Width:  |  Height:  |  Size: 35 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 189 KiB

After

Width:  |  Height:  |  Size: 98 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 26 KiB

After

Width:  |  Height:  |  Size: 11 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 88 KiB

After

Width:  |  Height:  |  Size: 25 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 160 KiB

After

Width:  |  Height:  |  Size: 24 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 93 KiB

After

Width:  |  Height:  |  Size: 19 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 425 KiB

After

Width:  |  Height:  |  Size: 80 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 514 KiB

After

Width:  |  Height:  |  Size: 53 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 193 KiB

After

Width:  |  Height:  |  Size: 32 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 64 KiB

After

Width:  |  Height:  |  Size: 19 KiB

View File

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

Some files were not shown because too many files have changed in this diff Show More