Compare commits
1 Commits
tfss-loops
...
optimize-a
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
de3690671b |
11
.github/pull_request_template.md
vendored
@@ -1,3 +1,10 @@
|
||||
**PLEASE REMOVE LINE BELOW BEFORE SUBMITTING**
|
||||
### Describe Your Changes
|
||||
|
||||
Before creating the PR, make sure you have read and followed the [VictoriaMetrics contributing guidelines](https://docs.victoriametrics.com/victoriametrics/contributing/#pull-request-checklist).
|
||||
Please provide a brief description of the changes you made. Be as specific as possible to help others understand the purpose and impact of your modifications.
|
||||
|
||||
### Checklist
|
||||
|
||||
The following checks are **mandatory**:
|
||||
|
||||
- [ ] My change adheres to [VictoriaMetrics contributing guidelines](https://docs.victoriametrics.com/victoriametrics/contributing/#pull-request-checklist).
|
||||
- [ ] My change adheres to [VictoriaMetrics development goals](https://docs.victoriametrics.com/victoriametrics/goals/).
|
||||
|
||||
2
.github/workflows/check-licenses.yml
vendored
@@ -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
|
||||
|
||||
8
.github/workflows/codeql-analysis-go.yml
vendored
@@ -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'
|
||||
|
||||
2
.github/workflows/test.yml
vendored
@@ -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
|
||||
|
||||
@@ -118,8 +118,8 @@ func main() {
|
||||
logger.Fatalf("cannot stop the webservice: %s", err)
|
||||
}
|
||||
logger.Infof("successfully shut down the webservice in %.3f seconds", time.Since(startTime).Seconds())
|
||||
vminsertcommon.StopIngestionRateLimiter()
|
||||
vminsert.Stop()
|
||||
vminsertcommon.StopIngestionRateLimiter()
|
||||
|
||||
vmstorage.Stop()
|
||||
vmselect.Stop()
|
||||
|
||||
@@ -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")
|
||||
}
|
||||
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
|
||||
@@ -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
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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`,
|
||||
}
|
||||
|
||||
|
||||
@@ -409,9 +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()
|
||||
|
||||
|
||||
@@ -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)
|
||||
|
||||
@@ -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{
|
||||
|
||||
@@ -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
|
||||
}
|
||||
}
|
||||
|
||||
@@ -481,9 +481,6 @@ func tryProcessingRequest(w http.ResponseWriter, r *http.Request, targetURL *url
|
||||
canRetry := !bbOK || bb.canRetry()
|
||||
|
||||
res, err := ui.rt.RoundTrip(req)
|
||||
if err == nil {
|
||||
defer func() { _ = res.Body.Close() }()
|
||||
}
|
||||
|
||||
if errors.Is(r.Context().Err(), context.Canceled) {
|
||||
// Do not retry canceled requests.
|
||||
@@ -553,6 +550,7 @@ func tryProcessingRequest(w http.ResponseWriter, r *http.Request, targetURL *url
|
||||
w.WriteHeader(res.StatusCode)
|
||||
|
||||
err = copyStreamToClient(w, res.Body)
|
||||
_ = res.Body.Close()
|
||||
|
||||
if errors.Is(r.Context().Err(), context.Canceled) {
|
||||
// Do not retry canceled requests.
|
||||
|
||||
@@ -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))
|
||||
|
||||
@@ -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
|
||||
}
|
||||
|
||||
/*
|
||||
|
||||
@@ -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 {
|
||||
|
||||
@@ -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
|
||||
}
|
||||
|
||||
@@ -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,
|
||||
|
||||
1240
app/vmui/packages/vmui/package-lock.json
generated
@@ -23,14 +23,14 @@
|
||||
"classnames": "^2.5.1",
|
||||
"dayjs": "^1.11.20",
|
||||
"lodash.debounce": "^4.0.8",
|
||||
"marked": "^18.0.0",
|
||||
"preact": "^10.29.1",
|
||||
"qs": "^6.15.1",
|
||||
"marked": "^17.0.5",
|
||||
"preact": "^10.29.0",
|
||||
"qs": "^6.15.0",
|
||||
"react-input-mask": "^2.0.4",
|
||||
"react-router-dom": "^7.14.1",
|
||||
"react-router-dom": "^7.13.2",
|
||||
"uplot": "^1.6.32",
|
||||
"vite": "^8.0.8",
|
||||
"web-vitals": "^5.2.0"
|
||||
"vite": "^8.0.7",
|
||||
"web-vitals": "^5.1.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@eslint/eslintrc": "^3.3.5",
|
||||
@@ -39,24 +39,24 @@
|
||||
"@testing-library/jest-dom": "^6.9.1",
|
||||
"@testing-library/preact": "^3.2.4",
|
||||
"@types/lodash.debounce": "^4.0.9",
|
||||
"@types/node": "^25.6.0",
|
||||
"@types/node": "^25.5.0",
|
||||
"@types/qs": "^6.15.0",
|
||||
"@types/react": "^19.2.14",
|
||||
"@types/react-input-mask": "^3.0.6",
|
||||
"@types/react-router-dom": "^5.3.3",
|
||||
"@typescript-eslint/eslint-plugin": "^8.58.2",
|
||||
"@typescript-eslint/parser": "^8.58.2",
|
||||
"@typescript-eslint/eslint-plugin": "^8.57.2",
|
||||
"@typescript-eslint/parser": "^8.57.2",
|
||||
"cross-env": "^10.1.0",
|
||||
"eslint": "^9.39.2",
|
||||
"eslint-plugin-react": "^7.37.5",
|
||||
"eslint-plugin-unused-imports": "^4.4.1",
|
||||
"globals": "^17.5.0",
|
||||
"globals": "^17.4.0",
|
||||
"http-proxy-middleware": "^3.0.5",
|
||||
"jsdom": "^29.0.2",
|
||||
"postcss": "^8.5.10",
|
||||
"sass-embedded": "^1.99.0",
|
||||
"typescript": "^6.0.2",
|
||||
"vitest": "^4.1.4"
|
||||
"jsdom": "^29.0.1",
|
||||
"postcss": "^8.5.8",
|
||||
"sass-embedded": "^1.98.0",
|
||||
"typescript": "^5.9.3",
|
||||
"vitest": "^4.1.1"
|
||||
},
|
||||
"browserslist": {
|
||||
"production": [
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import { useMemo } from "preact/compat";
|
||||
import "./style.scss";
|
||||
import { Alert as APIAlert, Group } from "../../../types";
|
||||
import { Link } from "react-router-dom";
|
||||
import { Alert as APIAlert } from "../../../types";
|
||||
import { createSearchParams } from "react-router-dom";
|
||||
import Button from "../../Main/Button/Button";
|
||||
import Badges, { BadgeColor } from "../Badges";
|
||||
import { formatEventTime } from "../helpers";
|
||||
@@ -9,14 +9,12 @@ import {
|
||||
SearchIcon,
|
||||
} from "../../Main/Icons";
|
||||
import CodeExample from "../../Main/CodeExample/CodeExample";
|
||||
import router from "../../../router";
|
||||
|
||||
interface BaseAlertProps {
|
||||
item: APIAlert;
|
||||
group?: Group;
|
||||
}
|
||||
|
||||
const BaseAlert = ({ item, group }: BaseAlertProps) => {
|
||||
const BaseAlert = ({ item }: BaseAlertProps) => {
|
||||
const query = item?.expression;
|
||||
const alertLabels = item?.labels || {};
|
||||
const alertLabelsItems = useMemo(() => {
|
||||
@@ -26,19 +24,13 @@ const BaseAlert = ({ item, group }: BaseAlertProps) => {
|
||||
}]));
|
||||
}, [alertLabels]);
|
||||
|
||||
const queryLink = useMemo(() => {
|
||||
if (!group?.interval) return;
|
||||
|
||||
const params = new URLSearchParams({
|
||||
const openQueryLink = () => {
|
||||
const params = {
|
||||
"g0.expr": query,
|
||||
"g0.end_time": item.activeAt,
|
||||
// Interval is the Group's evaluation interval in float seconds as present in the file. See: /app/vmalert/rule/web.go
|
||||
"g0.step_input": `${group.interval}s`,
|
||||
"g0.relative_time": "none",
|
||||
});
|
||||
|
||||
return `${router.home}?${params.toString()}`;
|
||||
}, [query, item.activeAt, group?.interval]);
|
||||
"g0.end_time": ""
|
||||
};
|
||||
window.open(`#/?${createSearchParams(params).toString()}`, "_blank", "noopener noreferrer");
|
||||
};
|
||||
|
||||
return (
|
||||
<div className="vm-explore-alerts-alert-item">
|
||||
@@ -53,22 +45,15 @@ const BaseAlert = ({ item, group }: BaseAlertProps) => {
|
||||
style={{ "text-align": "end" }}
|
||||
colSpan={2}
|
||||
>
|
||||
{queryLink && (
|
||||
<Link
|
||||
to={queryLink}
|
||||
target={"_blank"}
|
||||
rel="noreferrer"
|
||||
>
|
||||
<Button
|
||||
size="small"
|
||||
variant="outlined"
|
||||
color="gray"
|
||||
startIcon={<SearchIcon />}
|
||||
>
|
||||
<span className="vm-button-text">Run query</span>
|
||||
</Button>
|
||||
</Link>
|
||||
)}
|
||||
<Button
|
||||
size="small"
|
||||
variant="outlined"
|
||||
color="gray"
|
||||
startIcon={<SearchIcon />}
|
||||
onClick={openQueryLink}
|
||||
>
|
||||
<span className="vm-button-text">Run query</span>
|
||||
</Button>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
||||
@@ -1,21 +1,19 @@
|
||||
import { useMemo } from "preact/compat";
|
||||
import "./style.scss";
|
||||
import { Group, Rule as APIRule } from "../../../types";
|
||||
import { useNavigate, Link } from "react-router-dom";
|
||||
import { Rule as APIRule } from "../../../types";
|
||||
import { useNavigate, createSearchParams } from "react-router-dom";
|
||||
import { SearchIcon, DetailsIcon } from "../../Main/Icons";
|
||||
import Button from "../../Main/Button/Button";
|
||||
import Alert from "../../Main/Alert/Alert";
|
||||
import Badges, { BadgeColor } from "../Badges";
|
||||
import { formatDuration, formatEventTime } from "../helpers";
|
||||
import CodeExample from "../../Main/CodeExample/CodeExample";
|
||||
import router from "../../../router";
|
||||
|
||||
interface BaseRuleProps {
|
||||
item: APIRule;
|
||||
group?: Group;
|
||||
}
|
||||
|
||||
const BaseRule = ({ item, group }: BaseRuleProps) => {
|
||||
const BaseRule = ({ item }: BaseRuleProps) => {
|
||||
const query = item?.query;
|
||||
const navigate = useNavigate();
|
||||
const openAlertLink = (id: string) => {
|
||||
@@ -35,19 +33,13 @@ const BaseRule = ({ item, group }: BaseRuleProps) => {
|
||||
}]));
|
||||
}, [ruleLabels]);
|
||||
|
||||
const queryLink = useMemo(() => {
|
||||
if (!group?.interval) return;
|
||||
|
||||
const params = new URLSearchParams({
|
||||
const openQueryLink = () => {
|
||||
const params = {
|
||||
"g0.expr": query,
|
||||
"g0.end_time": item.lastEvaluation,
|
||||
// Interval is the Group's evaluation interval in float seconds as present in the file. See: /app/vmalert/rule/web.go
|
||||
"g0.step_input": `${group.interval}s`,
|
||||
"g0.relative_time": "none",
|
||||
});
|
||||
|
||||
return `${router.home}?${params.toString()}`;
|
||||
}, [query, item.lastEvaluation, group?.interval]);
|
||||
"g0.end_time": ""
|
||||
};
|
||||
window.open(`#/?${createSearchParams(params).toString()}`, "_blank", "noopener noreferrer");
|
||||
};
|
||||
|
||||
return (
|
||||
<div className="vm-explore-alerts-rule-item">
|
||||
@@ -62,22 +54,15 @@ const BaseRule = ({ item, group }: BaseRuleProps) => {
|
||||
style={{ "text-align": "end" }}
|
||||
colSpan={2}
|
||||
>
|
||||
{queryLink && (
|
||||
<Link
|
||||
to={queryLink}
|
||||
target={"_blank"}
|
||||
rel="noreferrer"
|
||||
>
|
||||
<Button
|
||||
size="small"
|
||||
variant="outlined"
|
||||
color="gray"
|
||||
startIcon={<SearchIcon />}
|
||||
>
|
||||
<span className="vm-button-text">Run query</span>
|
||||
</Button>
|
||||
</Link>
|
||||
)}
|
||||
<Button
|
||||
size="small"
|
||||
variant="outlined"
|
||||
color="gray"
|
||||
startIcon={<SearchIcon />}
|
||||
onClick={openQueryLink}
|
||||
>
|
||||
<span className="vm-button-text">Run query</span>
|
||||
</Button>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
||||
@@ -2,16 +2,15 @@ import { FC } from "preact/compat";
|
||||
import ItemHeader from "../ItemHeader";
|
||||
import Accordion from "../../Main/Accordion/Accordion";
|
||||
import "./style.scss";
|
||||
import { Group, Rule as APIRule } from "../../../types";
|
||||
import { Rule as APIRule } from "../../../types";
|
||||
import BaseRule from "../BaseRule";
|
||||
|
||||
interface RuleProps {
|
||||
states: Record<string, number>;
|
||||
rule: APIRule;
|
||||
group: Group;
|
||||
}
|
||||
|
||||
const Rule: FC<RuleProps> = ({ states, rule, group }) => {
|
||||
const Rule: FC<RuleProps> = ({ states, rule }) => {
|
||||
const state = Object.keys(states).length > 0 ? Object.keys(states)[0] : "ok";
|
||||
return (
|
||||
<div className={`vm-explore-alerts-rule vm-badge-item ${state.replace(" ", "-")}`}>
|
||||
@@ -26,10 +25,7 @@ const Rule: FC<RuleProps> = ({ states, rule, group }) => {
|
||||
name={rule.name}
|
||||
/>}
|
||||
>
|
||||
<BaseRule
|
||||
item={rule}
|
||||
group={group}
|
||||
/>
|
||||
<BaseRule item={rule} />
|
||||
</Accordion>
|
||||
</div>
|
||||
);
|
||||
|
||||
@@ -50,6 +50,7 @@ const RulesHeader = ({
|
||||
label="Rule type"
|
||||
placeholder="Please select rule type"
|
||||
onChange={onChangeRuleType}
|
||||
autofocus={!!types.length && !isMobile}
|
||||
includeAll
|
||||
searchable
|
||||
/>
|
||||
|
||||
@@ -17,7 +17,7 @@ export const formatDuration = (raw: number) => {
|
||||
|
||||
export const formatEventTime = (raw: string) => {
|
||||
const t = dayjs(raw);
|
||||
return t.year() <= 1 ? "Never" : t.tz().format("DD MMM YYYY HH:mm:ss");
|
||||
return t.year() <= 1 ? "Never" : t.format("DD MMM YYYY HH:mm:ss");
|
||||
};
|
||||
|
||||
export const getStates = (rule: Rule) => {
|
||||
|
||||
@@ -2,11 +2,10 @@ import Spinner from "../../components/Main/Spinner/Spinner";
|
||||
import Alert from "../../components/Main/Alert/Alert";
|
||||
import { useFetchItem } from "./hooks/useFetchItem";
|
||||
import "./style.scss";
|
||||
import { Alert as APIAlert, Group as APIGroup } from "../../types";
|
||||
import { Alert as APIAlert } from "../../types";
|
||||
import ItemHeader from "../../components/ExploreAlerts/ItemHeader";
|
||||
import BaseAlert from "../../components/ExploreAlerts/BaseAlert";
|
||||
import Modal from "../../components/Main/Modal/Modal";
|
||||
import { useFetchGroup } from "./hooks/useFetchGroup";
|
||||
|
||||
interface ExploreAlertProps {
|
||||
groupId: string;
|
||||
@@ -18,19 +17,10 @@ interface ExploreAlertProps {
|
||||
const ExploreAlert = ({ groupId, id, mode, onClose }: ExploreAlertProps) => {
|
||||
const {
|
||||
item,
|
||||
isLoading: isLoadingItem,
|
||||
error: errorItem,
|
||||
isLoading,
|
||||
error,
|
||||
} = useFetchItem<APIAlert>({ groupId, id, mode });
|
||||
|
||||
const {
|
||||
group,
|
||||
isLoading: isLoadingGroup,
|
||||
error: errorGroup,
|
||||
} = useFetchGroup<APIGroup>({ id: groupId });
|
||||
|
||||
const error = errorItem || errorGroup;
|
||||
const isLoading = isLoadingItem || isLoadingGroup;
|
||||
|
||||
if (isLoading) return (
|
||||
<Spinner />
|
||||
);
|
||||
@@ -61,12 +51,7 @@ const ExploreAlert = ({ groupId, id, mode, onClose }: ExploreAlertProps) => {
|
||||
onClose={onClose}
|
||||
>
|
||||
<div className="vm-explore-alerts">
|
||||
{item ? (
|
||||
<BaseAlert
|
||||
item={item}
|
||||
group={group}
|
||||
/>
|
||||
) : (
|
||||
{item && (<BaseAlert item={item} />) || (
|
||||
<Alert variant="info">{noItemFound}</Alert>
|
||||
)}
|
||||
</div>
|
||||
|
||||
@@ -2,12 +2,11 @@ import Spinner from "../../components/Main/Spinner/Spinner";
|
||||
import Alert from "../../components/Main/Alert/Alert";
|
||||
import { useFetchItem } from "./hooks/useFetchItem";
|
||||
import "./style.scss";
|
||||
import { Group as APIGroup, Rule as APIRule } from "../../types";
|
||||
import { Rule as APIRule } from "../../types";
|
||||
import ItemHeader from "../../components/ExploreAlerts/ItemHeader";
|
||||
import BaseRule from "../../components/ExploreAlerts/BaseRule";
|
||||
import Modal from "../../components/Main/Modal/Modal";
|
||||
import { getStates } from "../../components/ExploreAlerts/helpers";
|
||||
import { useFetchGroup } from "./hooks/useFetchGroup";
|
||||
|
||||
interface ExploreRuleProps {
|
||||
groupId: string;
|
||||
@@ -19,19 +18,10 @@ interface ExploreRuleProps {
|
||||
const ExploreRule = ({ groupId, id, mode, onClose }: ExploreRuleProps) => {
|
||||
const {
|
||||
item,
|
||||
isLoading: isLoadingItem,
|
||||
error: errorItem,
|
||||
isLoading,
|
||||
error,
|
||||
} = useFetchItem<APIRule>({ groupId, id, mode });
|
||||
|
||||
const {
|
||||
group,
|
||||
isLoading: isLoadingGroup,
|
||||
error: errorGroup,
|
||||
} = useFetchGroup<APIGroup>({ id: groupId });
|
||||
|
||||
const error = errorItem || errorGroup;
|
||||
const isLoading = isLoadingItem || isLoadingGroup;
|
||||
|
||||
if (isLoading) return (
|
||||
<Spinner />
|
||||
);
|
||||
@@ -59,12 +49,7 @@ const ExploreRule = ({ groupId, id, mode, onClose }: ExploreRuleProps) => {
|
||||
onClose={onClose}
|
||||
>
|
||||
<div className="vm-explore-alerts">
|
||||
{item ? (
|
||||
<BaseRule
|
||||
item={item}
|
||||
group={group}
|
||||
/>
|
||||
) : (
|
||||
{item && (<BaseRule item={item} />) || (
|
||||
<Alert variant="info">{noItemFound}</Alert>
|
||||
)}
|
||||
</div>
|
||||
|
||||
@@ -132,7 +132,7 @@ const ExploreRules: FC = () => {
|
||||
newParams.set("page_num", "1");
|
||||
setSearchParams(newParams);
|
||||
const changes = getChanges(title, states);
|
||||
setStates(changes.length === allStates.length ? [] : changes);
|
||||
setStates(changes.length == allStates.length ? [] : changes);
|
||||
}, [states, searchParams]);
|
||||
|
||||
const handleChangeRuleType = useCallback((title: string) => {
|
||||
@@ -186,7 +186,6 @@ const ExploreRules: FC = () => {
|
||||
<Rule
|
||||
key={`rule-${rule.id}`}
|
||||
rule={rule}
|
||||
group={group}
|
||||
states={getStates(rule)}
|
||||
/>
|
||||
))}
|
||||
|
||||
@@ -15,12 +15,13 @@
|
||||
"forceConsistentCasingInFileNames": true,
|
||||
"noFallthroughCasesInSwitch": true,
|
||||
"module": "esnext",
|
||||
"moduleResolution": "bundler",
|
||||
"moduleResolution": "node",
|
||||
"resolveJsonModule": true,
|
||||
"isolatedModules": true,
|
||||
"noEmit": true,
|
||||
"jsx": "react-jsx",
|
||||
"jsxImportSource": "preact",
|
||||
"downlevelIteration": true,
|
||||
"noUnusedLocals": true,
|
||||
"paths": {
|
||||
"react": ["./node_modules/preact/compat/"],
|
||||
@@ -31,8 +32,5 @@
|
||||
},
|
||||
"include": [
|
||||
"src"
|
||||
],
|
||||
"exclude": [
|
||||
"scripts/**/*.ts"
|
||||
]
|
||||
}
|
||||
|
||||
@@ -33,41 +33,37 @@ func (c *Client) CloseConnections() {
|
||||
c.httpCli.CloseIdleConnections()
|
||||
}
|
||||
|
||||
// Get sends an HTTP GET request, returns
|
||||
// Get sends a HTTP GET request, returns
|
||||
// the response body and status code to the caller.
|
||||
func (c *Client) Get(t *testing.T, url string, headers http.Header) (string, int) {
|
||||
func (c *Client) Get(t *testing.T, url string) (string, int) {
|
||||
t.Helper()
|
||||
return c.do(t, http.MethodGet, url, nil, headers)
|
||||
return c.do(t, http.MethodGet, url, "", nil)
|
||||
}
|
||||
|
||||
// Post sends an HTTP POST request, returns
|
||||
// Post sends a HTTP POST request, returns
|
||||
// the response body and status code to the caller.
|
||||
func (c *Client) Post(t *testing.T, url string, data []byte, headers http.Header) (string, int) {
|
||||
func (c *Client) Post(t *testing.T, url, contentType string, data []byte) (string, int) {
|
||||
t.Helper()
|
||||
return c.do(t, http.MethodPost, url, data, headers)
|
||||
return c.do(t, http.MethodPost, url, contentType, data)
|
||||
}
|
||||
|
||||
// PostForm sends an HTTP POST request containing the POST-form data with attached getHeaders, returns
|
||||
// PostForm sends a HTTP POST request containing the POST-form data, returns
|
||||
// the response body and status code to the caller.
|
||||
func (c *Client) PostForm(t *testing.T, url string, data url.Values, headers http.Header) (string, int) {
|
||||
func (c *Client) PostForm(t *testing.T, url string, data url.Values) (string, int) {
|
||||
t.Helper()
|
||||
if headers == nil {
|
||||
headers = make(http.Header)
|
||||
}
|
||||
headers.Set("Content-Type", "application/x-www-form-urlencoded")
|
||||
return c.Post(t, url, []byte(data.Encode()), headers)
|
||||
return c.Post(t, url, "application/x-www-form-urlencoded", []byte(data.Encode()))
|
||||
}
|
||||
|
||||
// Delete sends an HTTP DELETE request and returns the response body and status code
|
||||
// Delete sends a HTTP DELETE request and returns the response body and status code
|
||||
// to the caller.
|
||||
func (c *Client) Delete(t *testing.T, url string) (string, int) {
|
||||
t.Helper()
|
||||
return c.do(t, http.MethodDelete, url, nil, nil)
|
||||
return c.do(t, http.MethodDelete, url, "", nil)
|
||||
}
|
||||
|
||||
// do prepares an HTTP request, sends it to the server, receives the response
|
||||
// do prepares a HTTP request, sends it to the server, receives the response
|
||||
// from the server, returns the response body and status code to the caller.
|
||||
func (c *Client) do(t *testing.T, method, url string, data []byte, headers http.Header) (string, int) {
|
||||
func (c *Client) do(t *testing.T, method, url, contentType string, data []byte) (string, int) {
|
||||
t.Helper()
|
||||
|
||||
req, err := http.NewRequest(method, url, bytes.NewReader(data))
|
||||
@@ -75,7 +71,9 @@ func (c *Client) do(t *testing.T, method, url string, data []byte, headers http.
|
||||
t.Fatalf("could not create a HTTP request: %v", err)
|
||||
}
|
||||
|
||||
req.Header = headers
|
||||
if len(contentType) > 0 {
|
||||
req.Header.Add("Content-Type", contentType)
|
||||
}
|
||||
res, err := c.httpCli.Do(req)
|
||||
if err != nil {
|
||||
t.Fatalf("could not send HTTP request: %v", err)
|
||||
@@ -137,7 +135,7 @@ func (app *ServesMetrics) GetIntMetric(t *testing.T, metricName string) int {
|
||||
func (app *ServesMetrics) GetMetric(t *testing.T, metricName string) float64 {
|
||||
t.Helper()
|
||||
|
||||
metrics, statusCode := app.cli.Get(t, app.metricsURL, nil)
|
||||
metrics, statusCode := app.cli.Get(t, app.metricsURL)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -163,7 +161,7 @@ func (app *ServesMetrics) GetMetricsByPrefix(t *testing.T, prefix string) []floa
|
||||
|
||||
values := []float64{}
|
||||
|
||||
metrics, statusCode := app.cli.Get(t, app.metricsURL, nil)
|
||||
metrics, statusCode := app.cli.Get(t, app.metricsURL)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -192,7 +190,7 @@ func (app *ServesMetrics) GetMetricsByRegexp(t *testing.T, re *regexp.Regexp) []
|
||||
|
||||
values := []float64{}
|
||||
|
||||
metrics, statusCode := app.cli.Get(t, app.metricsURL, nil)
|
||||
metrics, statusCode := app.cli.Get(t, app.metricsURL)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
|
||||
@@ -4,7 +4,6 @@ import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"math"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"slices"
|
||||
"sort"
|
||||
@@ -90,22 +89,6 @@ type QueryOpts struct {
|
||||
LatencyOffset string
|
||||
Format string
|
||||
NoCache string
|
||||
Headers http.Header
|
||||
}
|
||||
|
||||
// getTenant returns tenant with optional default value
|
||||
func (qos *QueryOpts) getTenant() string {
|
||||
if qos.Tenant == "" {
|
||||
return "0"
|
||||
}
|
||||
return qos.Tenant
|
||||
}
|
||||
|
||||
func (qos *QueryOpts) getHeaders() http.Header {
|
||||
if qos.Headers == nil {
|
||||
qos.Headers = make(http.Header)
|
||||
}
|
||||
return qos.Headers
|
||||
}
|
||||
|
||||
func (qos *QueryOpts) asURLValues() url.Values {
|
||||
@@ -135,6 +118,14 @@ func (qos *QueryOpts) asURLValues() url.Values {
|
||||
return uv
|
||||
}
|
||||
|
||||
// getTenant returns tenant with optional default value
|
||||
func (qos *QueryOpts) getTenant() string {
|
||||
if qos.Tenant == "" {
|
||||
return "0"
|
||||
}
|
||||
return qos.Tenant
|
||||
}
|
||||
|
||||
// PrometheusAPIV1QueryResponse is an inmemory representation of the
|
||||
// /prometheus/api/v1/query or /prometheus/api/v1/query_range response.
|
||||
type PrometheusAPIV1QueryResponse struct {
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
|
||||
@@ -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}
|
||||
}
|
||||
@@ -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, ",")
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
@@ -76,13 +76,11 @@ func (app *Vmagent) APIV1ImportPrometheus(t *testing.T, records []string, opts Q
|
||||
// Flushing may still be in progress on the function return.
|
||||
//
|
||||
// See https://docs.victoriametrics.com/victoriametrics/url-examples/#apiv1importprometheus
|
||||
func (app *Vmagent) APIV1ImportPrometheusNoWaitFlush(t *testing.T, records []string, opts QueryOpts) {
|
||||
func (app *Vmagent) APIV1ImportPrometheusNoWaitFlush(t *testing.T, records []string, _ QueryOpts) {
|
||||
t.Helper()
|
||||
|
||||
data := []byte(strings.Join(records, "\n"))
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
_, statusCode := app.cli.Post(t, app.apiV1ImportPrometheusURL, data, headers)
|
||||
_, statusCode := app.cli.Post(t, app.apiV1ImportPrometheusURL, "text/plain", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
|
||||
@@ -114,10 +114,8 @@ func (app *Vminsert) InfluxWrite(t *testing.T, records []string, opts QueryOpts)
|
||||
}
|
||||
|
||||
data := []byte(strings.Join(records, "\n"))
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
app.sendBlocking(t, len(records), func() {
|
||||
_, statusCode := app.cli.Post(t, url, data, headers)
|
||||
_, statusCode := app.cli.Post(t, url, "text/plain", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -148,10 +146,8 @@ func (app *Vminsert) PrometheusAPIV1ImportCSV(t *testing.T, records []string, op
|
||||
url += "?" + uvs
|
||||
}
|
||||
data := []byte(strings.Join(records, "\n"))
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
app.sendBlocking(t, len(records), func() {
|
||||
_, statusCode := app.cli.Post(t, url, data, headers)
|
||||
_, statusCode := app.cli.Post(t, url, "text/plain", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -172,10 +168,8 @@ func (app *Vminsert) PrometheusAPIV1ImportNative(t *testing.T, data []byte, opts
|
||||
if len(uvs) > 0 {
|
||||
url += "?" + uvs
|
||||
}
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
app.sendBlocking(t, 1, func() {
|
||||
_, statusCode := app.cli.Post(t, url, data, headers)
|
||||
_, statusCode := app.cli.Post(t, url, "text/plain", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -197,10 +191,8 @@ func (app *Vminsert) OpenTSDBAPIPut(t *testing.T, records []string, opts QueryOp
|
||||
url += "?" + uvs
|
||||
}
|
||||
data := []byte("[" + strings.Join(records, ",") + "]")
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "application/json")
|
||||
app.sendBlocking(t, len(records), func() {
|
||||
_, statusCode := app.cli.Post(t, url, data, headers)
|
||||
_, statusCode := app.cli.Post(t, url, "application/json", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -219,10 +211,8 @@ func (app *Vminsert) PrometheusAPIV1Write(t *testing.T, wr prompb.WriteRequest,
|
||||
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)
|
||||
_, statusCode := app.cli.Post(t, url, "application/x-protobuf", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -271,10 +261,8 @@ func (app *Vminsert) PrometheusAPIV1ImportPrometheus(t *testing.T, records []str
|
||||
if prommetadata.IsEnabled() {
|
||||
recordsCount += metadataRecords
|
||||
}
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
app.sendBlocking(t, recordsCount, func() {
|
||||
_, statusCode := app.cli.Post(t, url, data, headers)
|
||||
_, statusCode := app.cli.Post(t, url, "text/plain", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -294,10 +282,8 @@ func (app *Vminsert) ZabbixConnectorHistory(t *testing.T, records []string, opts
|
||||
url += "?" + uvs
|
||||
}
|
||||
data := []byte(strings.Join(records, "\n"))
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "application/json")
|
||||
app.sendBlocking(t, len(records), func() {
|
||||
_, statusCode := app.cli.Post(t, url, data, headers)
|
||||
_, statusCode := app.cli.Post(t, url, "application/json", data)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
|
||||
@@ -76,7 +76,7 @@ func (app *Vmselect) PrometheusAPIV1Export(t *testing.T, query string, opts Quer
|
||||
values := opts.asURLValues()
|
||||
values.Add("match[]", query)
|
||||
values.Add("format", "promapi")
|
||||
res, _ := app.cli.PostForm(t, exportURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, exportURL, values)
|
||||
return NewPrometheusAPIV1QueryResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -92,7 +92,7 @@ func (app *Vmselect) PrometheusAPIV1ExportNative(t *testing.T, query string, opt
|
||||
values := opts.asURLValues()
|
||||
values.Add("match[]", query)
|
||||
values.Add("format", "promapi")
|
||||
res, _ := app.cli.PostForm(t, exportURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, exportURL, values)
|
||||
return []byte(res)
|
||||
}
|
||||
|
||||
@@ -108,7 +108,7 @@ func (app *Vmselect) PrometheusAPIV1Query(t *testing.T, query string, opts Query
|
||||
values := opts.asURLValues()
|
||||
values.Add("query", query)
|
||||
|
||||
res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, queryURL, values)
|
||||
return NewPrometheusAPIV1QueryResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -124,7 +124,7 @@ func (app *Vmselect) PrometheusAPIV1QueryRange(t *testing.T, query string, opts
|
||||
values := opts.asURLValues()
|
||||
values.Add("query", query)
|
||||
|
||||
res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, queryURL, values)
|
||||
return NewPrometheusAPIV1QueryResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -139,7 +139,7 @@ func (app *Vmselect) PrometheusAPIV1Series(t *testing.T, matchQuery string, opts
|
||||
values := opts.asURLValues()
|
||||
values.Add("match[]", matchQuery)
|
||||
|
||||
res, _ := app.cli.PostForm(t, seriesURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, seriesURL, values)
|
||||
return NewPrometheusAPIV1SeriesResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -153,7 +153,7 @@ func (app *Vmselect) PrometheusAPIV1SeriesCount(t *testing.T, opts QueryOpts) *P
|
||||
seriesURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/series/count", app.httpListenAddr, opts.getTenant())
|
||||
values := opts.asURLValues()
|
||||
|
||||
res, _ := app.cli.PostForm(t, seriesURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, seriesURL, values)
|
||||
return NewPrometheusAPIV1SeriesCountResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -168,7 +168,7 @@ func (app *Vmselect) PrometheusAPIV1Labels(t *testing.T, matchQuery string, opts
|
||||
values.Add("match[]", matchQuery)
|
||||
|
||||
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/labels", app.httpListenAddr, opts.getTenant())
|
||||
res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, queryURL, values)
|
||||
return NewPrometheusAPIV1LabelsResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -183,7 +183,7 @@ func (app *Vmselect) PrometheusAPIV1LabelValues(t *testing.T, labelName, matchQu
|
||||
values.Add("match[]", matchQuery)
|
||||
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/label/%s/values", app.httpListenAddr, opts.getTenant(), labelName)
|
||||
|
||||
res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, queryURL, values)
|
||||
return NewPrometheusAPIV1LabelValuesResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -197,7 +197,7 @@ func (app *Vmselect) PrometheusAPIV1Metadata(t *testing.T, metric string, limit
|
||||
values.Add("limit", strconv.Itoa(limit))
|
||||
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/metadata", app.httpListenAddr, opts.getTenant())
|
||||
|
||||
res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, queryURL, values)
|
||||
return NewPrometheusAPIV1Metadata(t, res)
|
||||
}
|
||||
|
||||
@@ -212,7 +212,7 @@ func (app *Vmselect) APIV1AdminTSDBDeleteSeries(t *testing.T, matchQuery string,
|
||||
values := opts.asURLValues()
|
||||
values.Add("match[]", matchQuery)
|
||||
|
||||
res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, statusCode := app.cli.PostForm(t, queryURL, values)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
|
||||
}
|
||||
@@ -231,7 +231,7 @@ func (app *Vmselect) MetricNamesStats(t *testing.T, limit, le, matchPattern stri
|
||||
values.Add("match_pattern", matchPattern)
|
||||
queryURL := fmt.Sprintf("http://%s/select/%s/prometheus/api/v1/status/metric_names_stats", app.httpListenAddr, opts.getTenant())
|
||||
|
||||
res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, statusCode := app.cli.PostForm(t, queryURL, values)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
|
||||
}
|
||||
@@ -251,7 +251,7 @@ func (app *Vmselect) MetricNamesStatsReset(t *testing.T, opts QueryOpts) {
|
||||
values := opts.asURLValues()
|
||||
queryURL := fmt.Sprintf("http://%s/admin/api/v1/admin/status/metric_names_stats/reset", app.httpListenAddr)
|
||||
|
||||
res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, statusCode := app.cli.PostForm(t, queryURL, values)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
|
||||
}
|
||||
@@ -275,7 +275,7 @@ func (app *Vmselect) APIV1StatusTSDB(t *testing.T, matchQuery string, date strin
|
||||
addNonEmpty("topN", topN)
|
||||
addNonEmpty("date", date)
|
||||
|
||||
res, statusCode := app.cli.PostForm(t, seriesURL, values, opts.Headers)
|
||||
res, statusCode := app.cli.PostForm(t, seriesURL, values)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
|
||||
}
|
||||
@@ -295,7 +295,7 @@ func (app *Vmselect) GraphiteMetricsIndex(t *testing.T, opts QueryOpts) Graphite
|
||||
t.Helper()
|
||||
|
||||
seriesURL := fmt.Sprintf("http://%s/select/%s/graphite/metrics/index.json", app.httpListenAddr, opts.getTenant())
|
||||
res, statusCode := app.cli.Get(t, seriesURL, opts.Headers)
|
||||
res, statusCode := app.cli.Get(t, seriesURL)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
|
||||
}
|
||||
@@ -317,7 +317,7 @@ func (app *Vmselect) GraphiteTagsTagSeries(t *testing.T, record string, opts Que
|
||||
values := opts.asURLValues()
|
||||
values.Add("path", record)
|
||||
|
||||
_, statusCode := app.cli.PostForm(t, url, values, opts.Headers)
|
||||
_, statusCode := app.cli.PostForm(t, url, values)
|
||||
if got, want := statusCode, http.StatusNotImplemented; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", got, want)
|
||||
}
|
||||
@@ -332,7 +332,7 @@ func (app *Vmselect) GraphiteTagsTagMultiSeries(t *testing.T, records []string,
|
||||
values.Add("path", rec)
|
||||
}
|
||||
|
||||
_, statusCode := app.cli.PostForm(t, url, values, opts.Headers)
|
||||
_, statusCode := app.cli.PostForm(t, url, values)
|
||||
if got, want := statusCode, http.StatusNotImplemented; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", got, want)
|
||||
}
|
||||
@@ -343,7 +343,7 @@ func (app *Vmselect) APIV1AdminTenants(t *testing.T) *AdminTenantsResponse {
|
||||
t.Helper()
|
||||
|
||||
tenantsURL := fmt.Sprintf("http://%s/admin/tenants", app.httpListenAddr)
|
||||
res, statusCode := app.cli.Get(t, tenantsURL, nil)
|
||||
res, statusCode := app.cli.Get(t, tenantsURL)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
|
||||
}
|
||||
|
||||
@@ -98,7 +98,7 @@ func StartVmsingleAt(instance, binary string, flags []string, cli *Client, outpu
|
||||
func (app *Vmsingle) ForceFlush(t *testing.T) {
|
||||
t.Helper()
|
||||
|
||||
_, statusCode := app.cli.Get(t, app.forceFlushURL, nil)
|
||||
_, statusCode := app.cli.Get(t, app.forceFlushURL)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -108,7 +108,7 @@ func (app *Vmsingle) ForceFlush(t *testing.T) {
|
||||
func (app *Vmsingle) ForceMerge(t *testing.T) {
|
||||
t.Helper()
|
||||
|
||||
_, statusCode := app.cli.Get(t, app.forceMergeURL, nil)
|
||||
_, statusCode := app.cli.Get(t, app.forceMergeURL)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -130,9 +130,8 @@ func (app *Vmsingle) InfluxWrite(t *testing.T, records []string, opts QueryOpts)
|
||||
if len(uvs) > 0 {
|
||||
url += "?" + uvs
|
||||
}
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
_, statusCode := app.cli.Post(t, url, data, headers)
|
||||
|
||||
_, statusCode := app.cli.Post(t, url, "text/plain", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -162,9 +161,7 @@ func (app *Vmsingle) PrometheusAPIV1ImportCSV(t *testing.T, records []string, op
|
||||
url += "?" + uvs
|
||||
}
|
||||
data := []byte(strings.Join(records, "\n"))
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
_, statusCode := app.cli.Post(t, url, data, headers)
|
||||
_, statusCode := app.cli.Post(t, url, "text/plain", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -184,9 +181,7 @@ func (app *Vmsingle) PrometheusAPIV1ImportNative(t *testing.T, data []byte, opts
|
||||
if len(uvs) > 0 {
|
||||
url += "?" + uvs
|
||||
}
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
_, statusCode := app.cli.Post(t, url, data, headers)
|
||||
_, statusCode := app.cli.Post(t, url, "text/plain", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -208,9 +203,7 @@ func (app *Vmsingle) OpenTSDBAPIPut(t *testing.T, records []string, opts QueryOp
|
||||
url += "?" + uvs
|
||||
}
|
||||
data := []byte("[" + strings.Join(records, ",") + "]")
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
_, statusCode := app.cli.Post(t, url, data, headers)
|
||||
_, statusCode := app.cli.Post(t, url, "text/plain", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -219,13 +212,11 @@ func (app *Vmsingle) OpenTSDBAPIPut(t *testing.T, records []string, opts QueryOp
|
||||
// PrometheusAPIV1Write is a test helper function that inserts a
|
||||
// collection of records in Prometheus remote-write format by sending a HTTP
|
||||
// POST request to /prometheus/api/v1/write vmsingle endpoint.
|
||||
func (app *Vmsingle) PrometheusAPIV1Write(t *testing.T, wr prompb.WriteRequest, opts QueryOpts) {
|
||||
func (app *Vmsingle) PrometheusAPIV1Write(t *testing.T, wr prompb.WriteRequest, _ QueryOpts) {
|
||||
t.Helper()
|
||||
|
||||
data := snappy.Encode(nil, wr.MarshalProtobuf(nil))
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "application/x-protobuf")
|
||||
_, statusCode := app.cli.Post(t, app.prometheusAPIV1WriteURL, data, headers)
|
||||
_, statusCode := app.cli.Post(t, app.prometheusAPIV1WriteURL, "application/x-protobuf", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -246,10 +237,9 @@ func (app *Vmsingle) PrometheusAPIV1ImportPrometheus(t *testing.T, records []str
|
||||
if len(uvs) > 0 {
|
||||
url += "?" + uvs
|
||||
}
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "text/plain")
|
||||
|
||||
data := []byte(strings.Join(records, "\n"))
|
||||
_, statusCode := app.cli.Post(t, url, data, headers)
|
||||
_, statusCode := app.cli.Post(t, url, "text/plain", data)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusNoContent)
|
||||
}
|
||||
@@ -266,7 +256,7 @@ func (app *Vmsingle) PrometheusAPIV1Export(t *testing.T, query string, opts Quer
|
||||
values.Add("match[]", query)
|
||||
values.Add("format", "promapi")
|
||||
|
||||
res, _ := app.cli.PostForm(t, app.prometheusAPIV1ExportURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, app.prometheusAPIV1ExportURL, values)
|
||||
return NewPrometheusAPIV1QueryResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -283,7 +273,7 @@ func (app *Vmsingle) PrometheusAPIV1ExportNative(t *testing.T, query string, opt
|
||||
values.Add("match[]", query)
|
||||
values.Add("format", "promapi")
|
||||
|
||||
res, _ := app.cli.PostForm(t, app.prometheusAPIV1ExportNativeURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, app.prometheusAPIV1ExportNativeURL, values)
|
||||
return []byte(res)
|
||||
}
|
||||
|
||||
@@ -297,7 +287,7 @@ func (app *Vmsingle) PrometheusAPIV1Query(t *testing.T, query string, opts Query
|
||||
|
||||
values := opts.asURLValues()
|
||||
values.Add("query", query)
|
||||
res, _ := app.cli.PostForm(t, app.prometheusAPIV1QueryURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, app.prometheusAPIV1QueryURL, values)
|
||||
return NewPrometheusAPIV1QueryResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -312,7 +302,7 @@ func (app *Vmsingle) PrometheusAPIV1QueryRange(t *testing.T, query string, opts
|
||||
values := opts.asURLValues()
|
||||
values.Add("query", query)
|
||||
|
||||
res, _ := app.cli.PostForm(t, app.prometheusAPIV1QueryRangeURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, app.prometheusAPIV1QueryRangeURL, values)
|
||||
return NewPrometheusAPIV1QueryResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -326,7 +316,7 @@ func (app *Vmsingle) PrometheusAPIV1Series(t *testing.T, matchQuery string, opts
|
||||
values := opts.asURLValues()
|
||||
values.Add("match[]", matchQuery)
|
||||
|
||||
res, _ := app.cli.PostForm(t, app.prometheusAPIV1SeriesURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, app.prometheusAPIV1SeriesURL, values)
|
||||
return NewPrometheusAPIV1SeriesResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -340,7 +330,7 @@ func (app *Vmsingle) PrometheusAPIV1SeriesCount(t *testing.T, opts QueryOpts) *P
|
||||
values := opts.asURLValues()
|
||||
|
||||
queryURL := fmt.Sprintf("http://%s/prometheus/api/v1/series/count", app.httpListenAddr)
|
||||
res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, queryURL, values)
|
||||
return NewPrometheusAPIV1SeriesCountResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -355,7 +345,7 @@ func (app *Vmsingle) PrometheusAPIV1Labels(t *testing.T, matchQuery string, opts
|
||||
values.Add("match[]", matchQuery)
|
||||
|
||||
queryURL := fmt.Sprintf("http://%s/prometheus/api/v1/labels", app.httpListenAddr)
|
||||
res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, queryURL, values)
|
||||
return NewPrometheusAPIV1LabelsResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -370,7 +360,7 @@ func (app *Vmsingle) PrometheusAPIV1LabelValues(t *testing.T, labelName, matchQu
|
||||
values.Add("match[]", matchQuery)
|
||||
|
||||
queryURL := fmt.Sprintf("http://%s/prometheus/api/v1/label/%s/values", app.httpListenAddr, labelName)
|
||||
res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, queryURL, values)
|
||||
return NewPrometheusAPIV1LabelValuesResponse(t, res)
|
||||
}
|
||||
|
||||
@@ -384,7 +374,7 @@ func (app *Vmsingle) PrometheusAPIV1Metadata(t *testing.T, metric string, limit
|
||||
values.Add("limit", strconv.Itoa(limit))
|
||||
queryURL := fmt.Sprintf("http://%s/prometheus/api/v1/metadata", app.httpListenAddr)
|
||||
|
||||
res, _ := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, _ := app.cli.PostForm(t, queryURL, values)
|
||||
return NewPrometheusAPIV1Metadata(t, res)
|
||||
}
|
||||
|
||||
@@ -399,7 +389,7 @@ func (app *Vmsingle) APIV1AdminTSDBDeleteSeries(t *testing.T, matchQuery string,
|
||||
values := opts.asURLValues()
|
||||
values.Add("match[]", matchQuery)
|
||||
|
||||
res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, statusCode := app.cli.PostForm(t, queryURL, values)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
|
||||
}
|
||||
@@ -412,7 +402,7 @@ func (app *Vmsingle) GraphiteMetricsIndex(t *testing.T, _ QueryOpts) GraphiteMet
|
||||
t.Helper()
|
||||
|
||||
seriesURL := fmt.Sprintf("http://%s/metrics/index.json", app.httpListenAddr)
|
||||
res, statusCode := app.cli.Get(t, seriesURL, nil)
|
||||
res, statusCode := app.cli.Get(t, seriesURL)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
|
||||
}
|
||||
@@ -434,7 +424,7 @@ func (app *Vmsingle) GraphiteTagsTagSeries(t *testing.T, record string, opts Que
|
||||
values := opts.asURLValues()
|
||||
values.Add("path", record)
|
||||
|
||||
_, statusCode := app.cli.PostForm(t, url, values, opts.Headers)
|
||||
_, statusCode := app.cli.PostForm(t, url, values)
|
||||
if got, want := statusCode, http.StatusNotImplemented; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", got, want)
|
||||
}
|
||||
@@ -449,7 +439,7 @@ func (app *Vmsingle) GraphiteTagsTagMultiSeries(t *testing.T, records []string,
|
||||
values.Add("path", rec)
|
||||
}
|
||||
|
||||
_, statusCode := app.cli.PostForm(t, url, values, opts.Headers)
|
||||
_, statusCode := app.cli.PostForm(t, url, values)
|
||||
if got, want := statusCode, http.StatusNotImplemented; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", got, want)
|
||||
}
|
||||
@@ -468,7 +458,7 @@ func (app *Vmsingle) APIV1StatusMetricNamesStats(t *testing.T, limit, le, matchP
|
||||
values.Add("match_pattern", matchPattern)
|
||||
queryURL := fmt.Sprintf("http://%s/api/v1/status/metric_names_stats", app.httpListenAddr)
|
||||
|
||||
res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, statusCode := app.cli.PostForm(t, queryURL, values)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
|
||||
}
|
||||
@@ -488,7 +478,7 @@ func (app *Vmsingle) APIV1AdminStatusMetricNamesStatsReset(t *testing.T, opts Qu
|
||||
values := opts.asURLValues()
|
||||
queryURL := fmt.Sprintf("http://%s/api/v1/admin/status/metric_names_stats/reset", app.httpListenAddr)
|
||||
|
||||
res, statusCode := app.cli.PostForm(t, queryURL, values, opts.Headers)
|
||||
res, statusCode := app.cli.PostForm(t, queryURL, values)
|
||||
if statusCode != http.StatusNoContent {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusNoContent, res)
|
||||
}
|
||||
@@ -501,7 +491,7 @@ func (app *Vmsingle) APIV1AdminStatusMetricNamesStatsReset(t *testing.T, opts Qu
|
||||
func (app *Vmsingle) SnapshotCreate(t *testing.T) *SnapshotCreateResponse {
|
||||
t.Helper()
|
||||
|
||||
data, statusCode := app.cli.Post(t, app.SnapshotCreateURL(), nil, nil)
|
||||
data, statusCode := app.cli.Post(t, app.SnapshotCreateURL(), "", nil)
|
||||
if got, want := statusCode, http.StatusOK; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
|
||||
}
|
||||
@@ -527,7 +517,7 @@ func (app *Vmsingle) APIV1AdminTSDBSnapshot(t *testing.T) *APIV1AdminTSDBSnapsho
|
||||
t.Helper()
|
||||
|
||||
queryURL := fmt.Sprintf("http://%s/api/v1/admin/tsdb/snapshot", app.httpListenAddr)
|
||||
data, statusCode := app.cli.Post(t, queryURL, nil, nil)
|
||||
data, statusCode := app.cli.Post(t, queryURL, "", nil)
|
||||
if got, want := statusCode, http.StatusOK; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
|
||||
}
|
||||
@@ -548,7 +538,7 @@ func (app *Vmsingle) SnapshotList(t *testing.T) *SnapshotListResponse {
|
||||
t.Helper()
|
||||
|
||||
queryURL := fmt.Sprintf("http://%s/snapshot/list", app.httpListenAddr)
|
||||
data, statusCode := app.cli.Get(t, queryURL, nil)
|
||||
data, statusCode := app.cli.Get(t, queryURL)
|
||||
if got, want := statusCode, http.StatusOK; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
|
||||
}
|
||||
@@ -594,7 +584,7 @@ func (app *Vmsingle) SnapshotDeleteAll(t *testing.T) *SnapshotDeleteAllResponse
|
||||
t.Helper()
|
||||
|
||||
queryURL := fmt.Sprintf("http://%s/snapshot/delete_all", app.httpListenAddr)
|
||||
data, statusCode := app.cli.Get(t, queryURL, nil)
|
||||
data, statusCode := app.cli.Get(t, queryURL)
|
||||
if got, want := statusCode, http.StatusOK; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
|
||||
}
|
||||
@@ -625,7 +615,7 @@ func (app *Vmsingle) APIV1StatusTSDB(t *testing.T, matchQuery string, date strin
|
||||
addNonEmpty("topN", topN)
|
||||
addNonEmpty("date", date)
|
||||
|
||||
res, statusCode := app.cli.PostForm(t, seriesURL, values, opts.Headers)
|
||||
res, statusCode := app.cli.PostForm(t, seriesURL, values)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", statusCode, http.StatusOK, res)
|
||||
}
|
||||
@@ -651,9 +641,7 @@ func (app *Vmsingle) ZabbixConnectorHistory(t *testing.T, records []string, opts
|
||||
url += "?" + uvs
|
||||
}
|
||||
data := []byte(strings.Join(records, "\n"))
|
||||
headers := opts.getHeaders()
|
||||
headers.Set("Content-Type", "application/json")
|
||||
_, statusCode := app.cli.Post(t, url, data, headers)
|
||||
_, statusCode := app.cli.Post(t, url, "application/json", data)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
|
||||
@@ -77,7 +77,7 @@ func (app *Vmstorage) ForceFlush(t *testing.T) {
|
||||
t.Helper()
|
||||
|
||||
forceFlushURL := fmt.Sprintf("http://%s/internal/force_flush", app.httpListenAddr)
|
||||
_, statusCode := app.cli.Get(t, forceFlushURL, nil)
|
||||
_, statusCode := app.cli.Get(t, forceFlushURL)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -88,7 +88,7 @@ func (app *Vmstorage) ForceMerge(t *testing.T) {
|
||||
t.Helper()
|
||||
|
||||
forceMergeURL := fmt.Sprintf("http://%s/internal/force_merge", app.httpListenAddr)
|
||||
_, statusCode := app.cli.Get(t, forceMergeURL, nil)
|
||||
_, statusCode := app.cli.Get(t, forceMergeURL)
|
||||
if statusCode != http.StatusOK {
|
||||
t.Fatalf("unexpected status code: got %d, want %d", statusCode, http.StatusOK)
|
||||
}
|
||||
@@ -101,7 +101,7 @@ func (app *Vmstorage) ForceMerge(t *testing.T) {
|
||||
func (app *Vmstorage) SnapshotCreate(t *testing.T) *SnapshotCreateResponse {
|
||||
t.Helper()
|
||||
|
||||
data, statusCode := app.cli.Post(t, app.SnapshotCreateURL(), nil, nil)
|
||||
data, statusCode := app.cli.Post(t, app.SnapshotCreateURL(), "", nil)
|
||||
if got, want := statusCode, http.StatusOK; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
|
||||
}
|
||||
@@ -127,7 +127,7 @@ func (app *Vmstorage) SnapshotList(t *testing.T) *SnapshotListResponse {
|
||||
t.Helper()
|
||||
|
||||
queryURL := fmt.Sprintf("http://%s/snapshot/list", app.httpListenAddr)
|
||||
data, statusCode := app.cli.Get(t, queryURL, nil)
|
||||
data, statusCode := app.cli.Get(t, queryURL)
|
||||
if got, want := statusCode, http.StatusOK; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
|
||||
}
|
||||
@@ -173,7 +173,7 @@ func (app *Vmstorage) SnapshotDeleteAll(t *testing.T) *SnapshotDeleteAllResponse
|
||||
t.Helper()
|
||||
|
||||
queryURL := fmt.Sprintf("http://%s/snapshot/delete_all", app.httpListenAddr)
|
||||
data, statusCode := app.cli.Post(t, queryURL, nil, nil)
|
||||
data, statusCode := app.cli.Post(t, queryURL, "", nil)
|
||||
if got, want := statusCode, http.StatusOK; got != want {
|
||||
t.Fatalf("unexpected status code: got %d, want %d, resp text=%q", got, want, data)
|
||||
}
|
||||
|
||||
@@ -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/);
|
||||
|
||||
@@ -125,7 +125,7 @@ services:
|
||||
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
|
||||
|
||||
@@ -66,7 +66,7 @@ services:
|
||||
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
|
||||
|
||||
@@ -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.
|
||||
@@ -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 }}\""
|
||||
|
||||
|
||||
@@ -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."
|
||||
@@ -59,7 +59,7 @@ services:
|
||||
- '--external.alert.source=explore?orgId=1&left=["now-1h","now","VictoriaMetrics",{"expr": },{"mode":"Metrics"},{"ui":[true,true,true,"none"]}]'
|
||||
restart: always
|
||||
vmanomaly:
|
||||
image: victoriametrics/vmanomaly:v1.29.3
|
||||
image: victoriametrics/vmanomaly:v1.29.2
|
||||
depends_on:
|
||||
- "victoriametrics"
|
||||
ports:
|
||||
|
||||
@@ -14,11 +14,6 @@ aliases:
|
||||
---
|
||||
Please find the changelog for VictoriaMetrics Anomaly Detection below.
|
||||
|
||||
## v1.29.3
|
||||
Released: 2026-04-16
|
||||
|
||||
- UI: Updated [vmanomaly UI](https://docs.victoriametrics.com/anomaly-detection/ui/) from [v1.6.0](https://docs.victoriametrics.com/anomaly-detection/ui/#v160) to [v1.6.1](https://docs.victoriametrics.com/anomaly-detection/ui/#v161), see respective [release notes](https://docs.victoriametrics.com/anomaly-detection/ui/#v161) for details.
|
||||
|
||||
## v1.29.2
|
||||
Released: 2026-04-02
|
||||
|
||||
|
||||
@@ -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
|
||||
@@ -423,7 +421,7 @@ services:
|
||||
# ...
|
||||
vmanomaly:
|
||||
container_name: vmanomaly
|
||||
image: victoriametrics/vmanomaly:v1.29.3
|
||||
image: victoriametrics/vmanomaly:v1.29.2
|
||||
# ...
|
||||
restart: always
|
||||
volumes:
|
||||
@@ -641,7 +639,7 @@ options:
|
||||
Here’s an example of using the config splitter to divide configurations based on the `extra_filters` argument from the reader section:
|
||||
|
||||
```sh
|
||||
docker pull victoriametrics/vmanomaly:v1.29.3 && docker image tag victoriametrics/vmanomaly:v1.29.3 vmanomaly
|
||||
docker pull victoriametrics/vmanomaly:v1.29.2 && docker image tag victoriametrics/vmanomaly:v1.29.2 vmanomaly
|
||||
```
|
||||
|
||||
```sh
|
||||
|
||||
@@ -45,8 +45,8 @@ There are 2 types of compatibility to consider when migrating in stateful mode:
|
||||
|
||||
| Group start | Group end | Compatibility | Notes |
|
||||
|---------|--------- |------------|-------|
|
||||
| [v1.29.3](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1293) | Latest* | Fully Compatible | Just a placeholder for new releases |
|
||||
| [v1.29.1](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1291) | [v1.29.3](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1293) | Fully Compatible | - |
|
||||
| [v1.29.2](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1292) | Latest* | Fully Compatible | Just a placeholder for new releases |
|
||||
| [v1.29.1](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1291) | [v1.29.2](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1292) | Fully Compatible | - |
|
||||
| [v1.28.7](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1287) | [v1.29.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1290) | Partially compatible* | Dumped models of class [prophet](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet) and [seasonal quantile](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-seasonal-quantile) have problems with loading to [v1.29.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1290) due to dropped `pytz` library. **Upgrading directly from v1.28.7 to [v1.29.1](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1291) with a fix is suggested** |
|
||||
| [v1.26.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1262) | [v1.28.7](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1287) | Fully Compatible | [v1.28.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1280) introduced [rolling](https://docs.victoriametrics.com/anomaly-detection/components/models/#rolling-models) model class drop in favor of [online](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-models) models (`rolling_quantile` and `std` models), however, it does not impact compatibility, as artifacts were not produced by default for rolling models. Also, offline `mad` and `zscore` models are redirecting to their respective online counterparts since [v1.28.4](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1284). |
|
||||
| [v1.25.3](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1253) | [v1.26.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1270) | Partially Compatible* | [v1.25.3](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1253) introduced `forecast_at` argument for base [univariate](https://docs.victoriametrics.com/anomaly-detection/components/models/#univariate-models) and `Prophet` [models](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet), however, itself remains backward-reversible from newer states like [v1.26.2](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1262), [v1.27.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1270). (All models except `isolation_forest_multivariate` class will be dropped) |
|
||||
@@ -81,4 +81,4 @@ In stateless mode, the migration process is almost straightforward as there are
|
||||
# Other VmReader settings...
|
||||
sampling_period: 1m
|
||||
...
|
||||
```
|
||||
```
|
||||
@@ -122,7 +122,7 @@ Below are the steps to get `vmanomaly` up and running inside a Docker container:
|
||||
1. Pull Docker image:
|
||||
|
||||
```sh
|
||||
docker pull victoriametrics/vmanomaly:v1.29.3
|
||||
docker pull victoriametrics/vmanomaly:v1.29.2
|
||||
```
|
||||
|
||||
2. Create the license file with your license key.
|
||||
@@ -142,7 +142,7 @@ docker run -it \
|
||||
-v ./license:/license \
|
||||
-v ./config.yaml:/config.yaml \
|
||||
-p 8490:8490 \
|
||||
victoriametrics/vmanomaly:v1.29.3 \
|
||||
victoriametrics/vmanomaly:v1.29.2 \
|
||||
/config.yaml \
|
||||
--licenseFile=/license \
|
||||
--loggerLevel=INFO \
|
||||
@@ -159,7 +159,7 @@ docker run -it \
|
||||
-e VMANOMALY_DATA_DUMPS_DIR=/tmp/vmanomaly/data \
|
||||
-e VMANOMALY_MODEL_DUMPS_DIR=/tmp/vmanomaly/models \
|
||||
-p 8490:8490 \
|
||||
victoriametrics/vmanomaly:v1.29.3 \
|
||||
victoriametrics/vmanomaly:v1.29.2 \
|
||||
/config.yaml \
|
||||
--licenseFile=/license \
|
||||
--loggerLevel=INFO \
|
||||
@@ -172,7 +172,7 @@ services:
|
||||
# ...
|
||||
vmanomaly:
|
||||
container_name: vmanomaly
|
||||
image: victoriametrics/vmanomaly:v1.29.3
|
||||
image: victoriametrics/vmanomaly:v1.29.2
|
||||
# ...
|
||||
restart: always
|
||||
volumes:
|
||||
|
||||
@@ -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.
|
||||
|
||||
@@ -315,7 +315,7 @@ docker run -it --rm \
|
||||
-e VMANOMALY_MCP_SERVER_URL=http://mcp-vmanomaly:8081/mcp \
|
||||
-p 8080:8080 \
|
||||
-p 8490:8490 \
|
||||
victoriametrics/vmanomaly:v1.29.3 \
|
||||
victoriametrics/vmanomaly:v1.29.2 \
|
||||
vmanomaly_config.yaml
|
||||
```
|
||||
|
||||
@@ -640,23 +640,6 @@ If the **results** look good and the **model configuration should be deployed in
|
||||
|
||||
## Changelog
|
||||
|
||||
### v1.6.1
|
||||
Released: 2026-04-16
|
||||
|
||||
vmanomaly version: [v1.29.3](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1293)
|
||||
|
||||
- IMPROVEMENT: Consecutive anomalies (when "streaks" option is enabled) are now grouped in the Visualization Panel as a single anomaly line instead of multiple dots for reduced visual noise and better representation of prolonged anomalous periods, while still showing the exact anomaly score and labels on hover.
|
||||
|
||||
- IMPROVEMENT: Raw query results now refresh automatically after time range changes; yet anomaly detection results are preserved until "Detect Anomalies" button is hit again, to avoid recalculating anomalies on the new time range without explicit user action, which could be costly if the new time range is large and the model is complex.
|
||||
|
||||
- IMPROVEMENT: Table legend view is now enabled by default for sorting and filtering enablement.
|
||||
|
||||
- BUGFIX: Generated config and example alert outputs now preserve configured fit/infer values correctly and avoid invalid float-based duration strings in generated YAML, which could lead to data validation errors if copied to production configuration without adjustments.
|
||||
|
||||
- BUGFIX: Fixed multiple confusing anomaly UI behaviors around scheduler fields (fit_every, infer_every) and generated artifacts.
|
||||
|
||||
- BUGFIX: Chart y-axis range is now updating after legend series selection (regression introduced in v1.6.0).
|
||||
|
||||
### v1.6.0
|
||||
Released: 2026-04-02
|
||||
|
||||
|
||||
|
Before Width: | Height: | Size: 357 KiB After Width: | Height: | Size: 51 KiB |
|
Before Width: | Height: | Size: 467 KiB After Width: | Height: | Size: 54 KiB |
|
Before Width: | Height: | Size: 188 KiB After Width: | Height: | Size: 22 KiB |
@@ -395,7 +395,7 @@ services:
|
||||
restart: always
|
||||
vmanomaly:
|
||||
container_name: vmanomaly
|
||||
image: victoriametrics/vmanomaly:v1.29.3
|
||||
image: victoriametrics/vmanomaly:v1.29.2
|
||||
depends_on:
|
||||
- "victoriametrics"
|
||||
ports:
|
||||
|
||||
|
Before Width: | Height: | Size: 234 KiB After Width: | Height: | Size: 25 KiB |
|
Before Width: | Height: | Size: 282 KiB After Width: | Height: | Size: 106 KiB |
|
Before Width: | Height: | Size: 1.0 MiB After Width: | Height: | Size: 181 KiB |
|
Before Width: | Height: | Size: 929 KiB After Width: | Height: | Size: 164 KiB |
|
Before Width: | Height: | Size: 563 KiB After Width: | Height: | Size: 104 KiB |
|
Before Width: | Height: | Size: 871 KiB After Width: | Height: | Size: 331 KiB |
|
Before Width: | Height: | Size: 310 KiB After Width: | Height: | Size: 93 KiB |
|
Before Width: | Height: | Size: 944 KiB After Width: | Height: | Size: 122 KiB |
|
Before Width: | Height: | Size: 19 KiB After Width: | Height: | Size: 2.6 KiB |
|
Before Width: | Height: | Size: 303 KiB After Width: | Height: | Size: 44 KiB |
|
Before Width: | Height: | Size: 681 KiB After Width: | Height: | Size: 140 KiB |
|
Before Width: | Height: | Size: 805 KiB After Width: | Height: | Size: 109 KiB |
|
Before Width: | Height: | Size: 111 KiB After Width: | Height: | Size: 17 KiB |
|
Before Width: | Height: | Size: 1.2 MiB After Width: | Height: | Size: 160 KiB |
|
Before Width: | Height: | Size: 189 KiB After Width: | Height: | Size: 236 KiB |
|
Before Width: | Height: | Size: 206 KiB After Width: | Height: | Size: 26 KiB |
|
Before Width: | Height: | Size: 206 KiB After Width: | Height: | Size: 26 KiB |
|
Before Width: | Height: | Size: 12 KiB After Width: | Height: | Size: 1.5 KiB |
|
Before Width: | Height: | Size: 206 KiB After Width: | Height: | Size: 53 KiB |
|
Before Width: | Height: | Size: 428 KiB After Width: | Height: | Size: 42 KiB |
|
Before Width: | Height: | Size: 37 KiB After Width: | Height: | Size: 9.7 KiB |
|
Before Width: | Height: | Size: 740 KiB After Width: | Height: | Size: 34 KiB |
|
Before Width: | Height: | Size: 11 KiB After Width: | Height: | Size: 2.4 KiB |
|
Before Width: | Height: | Size: 225 KiB After Width: | Height: | Size: 35 KiB |
|
Before Width: | Height: | Size: 189 KiB After Width: | Height: | Size: 98 KiB |
|
Before Width: | Height: | Size: 26 KiB After Width: | Height: | Size: 11 KiB |
|
Before Width: | Height: | Size: 88 KiB After Width: | Height: | Size: 25 KiB |
|
Before Width: | Height: | Size: 160 KiB After Width: | Height: | Size: 24 KiB |
|
Before Width: | Height: | Size: 93 KiB After Width: | Height: | Size: 19 KiB |
|
Before Width: | Height: | Size: 425 KiB After Width: | Height: | Size: 80 KiB |
|
Before Width: | Height: | Size: 514 KiB After Width: | Height: | Size: 53 KiB |
|
Before Width: | Height: | Size: 193 KiB After Width: | Height: | Size: 32 KiB |
|
Before Width: | Height: | Size: 64 KiB After Width: | Height: | Size: 19 KiB |
@@ -62,13 +62,11 @@ Pull requests requirements:
|
||||
1. The pull request must conform to [VictoriaMetrics development goals](https://docs.victoriametrics.com/victoriametrics/goals/).
|
||||
1. Don't use `master` branch for making PRs, as it makes it impossible for reviewers to modify the changes.
|
||||
1. All commits need to be [signed](https://docs.github.com/en/authentication/managing-commit-signature-verification/signing-commits).
|
||||
1. Pull request title should be prefixed with `<dir>/<component>:` to show what component has been changed, i.e. `app/vmalert: fix...`.
|
||||
Pull request description should contain clear and concise description of what was done, why it is needed and for what purpose.
|
||||
Use clear language, so reviewers can quickly understand the change and its impact.
|
||||
1. A commit message should contain clear and concise description of what was done and for what purpose.
|
||||
Use the imperative, present tense: "change" not "changed" nor "changes". Read your commit message as "This commit will ..", don't capitalize the first letter.
|
||||
Message should be prefixed with `<dir>/<component>:` to show what component has been changed, i.e. `app/vmalert: fix...`.
|
||||
1. A link to the issue(s) related to the change, if any. Use `Fixes [issue link]` if the PR resolves the issue, or `Related to [issue link]` for reference.
|
||||
1. Tests proving that the change is effective. Tests are expected for non-trivial new functionality or non-trivial modifications.
|
||||
Bug fixes must include tests unless a maintainer explicitly agrees otherwise.
|
||||
See [this style guide](https://itnext.io/f-tests-as-a-replacement-for-table-driven-tests-in-go-8814a8b19e9e) for tests.
|
||||
1. Tests proving that the change is effective. See [this style guide](https://itnext.io/f-tests-as-a-replacement-for-table-driven-tests-in-go-8814a8b19e9e) for tests.
|
||||
To run tests and code checks locally, execute commands `make test-full` and `make check-all`.
|
||||
1. Try to not extend the scope of the pull requests outside the issue, do not make unrelated changes.
|
||||
1. Update [docs](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/docs) if needed. For example, adding a new flag or changing behavior of existing flags or features
|
||||
|
||||
@@ -1511,16 +1511,6 @@ value than before, then data outside the configured period will be eventually de
|
||||
|
||||
VictoriaMetrics does not support indefinite retention, but you can specify an arbitrarily high duration, e.g. `-retentionPeriod=100y`.
|
||||
|
||||
By default, VictoriaMetrics doesn't accept samples with timestamps bigger than `now+2d`, e.g. 2 days in the future.
|
||||
If you need accepting samples with bigger timestamps, then specify the desired "future retention" via `-futureRetention` command-line flag.
|
||||
This flag accepts values starting from `2d`.
|
||||
|
||||
For example, the following command starts VictoriaMetrics, which accepts samples with timestamps up to a year in the future:
|
||||
|
||||
```sh
|
||||
/path/to/victoria-metrics -futureRetention=1y
|
||||
```
|
||||
|
||||
### Multiple retentions
|
||||
|
||||
Distinct retentions for distinct time series can be configured via [retention filters](#retention-filters)
|
||||
|
||||
@@ -26,34 +26,12 @@ See also [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-rel
|
||||
|
||||
## tip
|
||||
|
||||
* FEATURE: all VictoriaMetrics components: add support for reading cpu/memory limits configured via [systemd slices](https://www.freedesktop.org/software/systemd/man/latest/systemd.slice.html). Previously, only limits set directly on the process's own cgroup were detected. See [#10635](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10635). Thanks to @andriibeee for the contribution.
|
||||
* FEATURE: [vmctl](https://docs.victoriametrics.com/victoriametrics/vmctl/): improve error handling at opentsdb migration. See [#10797](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10797)
|
||||
* FEATURE: [vmui](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmui): now `Run query` link on the Alerting Rules page correctly propagates the alert’s interval and evaluation time. See [#10366](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10366).
|
||||
* FEATURE: [alerts](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/deployment/docker/rules): add new `MetricNameStatsCacheUtilizationIsTooHigh` alerting rule to track overutilization of [Metric names usage stats tracker](https://docs.victoriametrics.com/victoriametrics/#track-ingested-metrics-usage) (used in [Cardinality Explorer](https://docs.victoriametrics.com/victoriametrics/#cardinality-explorer)). See [#10840](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10840).
|
||||
* FEATURE: [stream aggregation](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/): add `vm_streamaggr_counter_resets_total` metric for `total*`, `increase*` and `rate*` outputs that is useful for aggregation behaviour tracking. These metrics help to identify issues described in [Troubleshooting: counter resets](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#counter-resets).
|
||||
* FEATURE: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): add the support of ingestion and retrieval of samples with timestamps in the future. The new `-futureRetention` flag controls how far in the future the timestamps are allowed to be. See [827](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/827) and [10718](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10718).
|
||||
|
||||
* BUGFIX: `vminsert` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): fix increased memory usage after upgrade to [v1.140.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.140.0) by properly accounting for internal buffer count when calculating per-storage buffer size. See [#10725](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10725#issuecomment-4282256709).
|
||||
* BUGFIX: all VictoriaMetrics components: properly parse IPv6 source address when accepting connections with proxy protocol v2 enabled. See [#10839](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10839). Thanks to @andriibeee for the contribution.
|
||||
* BUGFIX: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) and [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/): `-maxScrapeSize` is now correctly applied when reading response bodies, including non-OK scrape error responses. See [#10804](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10804).
|
||||
* BUGFIX: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/): fix `ec2_sd_configs` returning 401 `AuthFailure` from AWS when credentials are obtained via IRSA, instance role or `AWS_CONTAINER_CREDENTIALS_*` env vars. The regression was introduced in [v1.140.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.140.0). See [#10815](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10815).
|
||||
* BUGFIX: [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/): fix leak of backend TCP connections, file descriptors and goroutines when the client cancels the request after the backend response has been received. See [#10833](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10833). Thanks to @andriibeee for the contribution.
|
||||
* BUGFIX: [vmauth](https://docs.victoriametrics.com/victoriametrics/vmauth/): fix a rare panic during config reload when a backend is marked as broken. See [#10806](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10806).
|
||||
* BUGFIX: `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): stop logging warnings about failed handshakes when the `clusternative` port receives TCP healthchecks from load balancers. See [#10786](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10786). Thanks to @andriibeee for the contribution.
|
||||
* BUGFIX: [vmrestore](https://docs.victoriametrics.com/victoriametrics/vmrestore/): fix an issue where vmrestore could hang indefinitely when interrupted during backup download. See [#10794](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10794).
|
||||
* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/): properly execute graceful shutdown for vmsingle if `-maxIngestionRate` is configured. See [#10795](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10795).
|
||||
* BUGFIX: [vmui](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmui): fix time display on Alerting Rules page to use selected timezone. See [#10827](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10827).
|
||||
* BUGFIX: [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/): delete labels from rule results if they are specified with an empty string value in rule or group labels. See [#10766](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10766).
|
||||
* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): fix incorrect evaluation of binary operations caused by an ordering bug (e.g. `10 - (3 + 3 + 4)` being evaluated as `10 - 3 + 3 + 4`). The issue was introduced in v1.140.0, v1.136.4, and v1.122.19. See [#10856](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10856).
|
||||
|
||||
## [v1.140.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.140.0)
|
||||
|
||||
Released at 2026-04-10
|
||||
|
||||
**Update Note 1:** [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): [CSV export](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-export-csv-data) (`/api/v1/export/csv`) now adds a header row as the first line of the response, so existing CSV-processing scripts may need to skip this header. See [#10666](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10666).
|
||||
|
||||
**Update Note 2:** [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/): Due to an ordering bug in binary operations, some queries may produce incorrect results. For example, `10 - (3 + 3 + 4)` is evaluated as `10 - 3 + 3 + 4`. The issue was introduced in versions v1.140.0, v1.136.4, v1.122.19, and is addressed in upcoming releases. It is strongly recommended to avoid these versions entirely. See [#10856](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10856).
|
||||
|
||||
* SECURITY: upgrade Go builder from Go1.26.1 to Go1.26.2. See [the list of issues addressed in Go1.26.2](https://github.com/golang/go/issues?q=milestone%3AGo1.26.2%20label%3ACherryPickApproved).
|
||||
|
||||
* FEATURE: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/): add per-URL `-remoteWrite.disableMetadata` flag to disable metadata sending for specific remote storage URLs. See [#10711](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10711). Thanks to @evkuzin for the contribution.
|
||||
@@ -157,20 +135,8 @@ It enables back `Discovered targets` debug UI by default.
|
||||
* BUGFIX: `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): properly apply `extra_filters[]` filter when querying `vm_account_id` or `vm_project_id` labels via [multitenant](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#multitenancy) request for `/api/v1/label/…/values` API. Before, `extra_filters` was ignored. See [#10503](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10503).
|
||||
* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): revert the use of rollup result cache for [instant queries](https://docs.victoriametrics.com/keyConcepts.html#instant-query) that contain [`rate`](https://docs.victoriametrics.com/MetricsQL.html#rate) function with a lookbehind window larger than `-search.minWindowForInstantRollupOptimization`. The cache usage was removed since [v1.132.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.132.0). See [#10098](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10098#issuecomment-3895011084) for more details.
|
||||
|
||||
## [v1.136.5](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.136.5)
|
||||
|
||||
Released at 2026-04-23
|
||||
|
||||
**v1.136.x is a line of [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-releases/). It contains important up-to-date bugfixes for [VictoriaMetrics enterprise](https://docs.victoriametrics.com/victoriametrics/enterprise/).
|
||||
All these fixes are also included in [the latest community release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest).
|
||||
The v1.136.x line will be supported for at least 12 months since [v1.136.0](https://docs.victoriametrics.com/victoriametrics/changelog/#v11360) release**
|
||||
|
||||
* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): fix incorrect evaluation of binary operations caused by an ordering bug (e.g. `10 - (3 + 3 + 4)` being evaluated as `10 - 3 + 3 + 4`). The issue was introduced in v1.140.0, v1.136.4, and v1.122.19. See [#10856](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10856).
|
||||
|
||||
## [v1.136.4](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.136.4)
|
||||
|
||||
**Update Note 1:** [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/): Due to an ordering bug in binary operations, some queries may produce incorrect results. For example, `10 - (3 + 3 + 4)` is evaluated as `10 - 3 + 3 + 4`. The issue was introduced in versions v1.140.0, v1.136.4, v1.122.19, and is addressed in upcoming releases. It is strongly recommended to avoid these versions entirely. See [#10856](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10856).
|
||||
|
||||
Released at 2026-04-10
|
||||
|
||||
**v1.136.x is a line of [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-releases/). It contains important up-to-date bugfixes for [VictoriaMetrics enterprise](https://docs.victoriametrics.com/victoriametrics/enterprise/).
|
||||
@@ -320,13 +286,9 @@ Released at 2026-01-16
|
||||
Released at 2026-01-02
|
||||
|
||||
**Update Note 1:** [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): Upgrading to per-partition index requires registering all active time series. Expect slow down of data ingestion and queries during upgrade roll-out. This is a one-time operation. Additionally, for users with retention periods shorter than 1 month the disk usage may increase.
|
||||
|
||||
**Update Note 2:** [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): Certain data and query patterns may cause high CPU utilization due to [10154](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/10154). See [10297](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10297).
|
||||
|
||||
**Update Note 3:** [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): lock contention in the ingestion path may cause frequent context switches and storage connection saturation spikes. See [10367](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10367). Addressed in `v1.135.0`.
|
||||
|
||||
**Update Note 4:** [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): TSDB status may be empty if the partition index does not have records for the requested date. See [10315](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10315). Addressed in `v1.135.0`.
|
||||
|
||||
**Update Note 5:** [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): `indexdb/tagFiltersToMetricIDs`, `indexdb/metricID` and `indexdb/date_metricID` cache metrics are not reported properly. See [10275](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10275). Addressed in `v1.135.0`.
|
||||
|
||||
* SECURITY: upgrade base docker image (Alpine) from 3.22.2 to 3.23.2. See [Alpine 3.23.2 release notes](https://www.alpinelinux.org/posts/Alpine-3.23.2-released.html).
|
||||
@@ -393,20 +355,8 @@ See changes [here](https://docs.victoriametrics.com/victoriametrics/changelog/ch
|
||||
|
||||
See changes [here](https://docs.victoriametrics.com/victoriametrics/changelog/changelog_2025/#v11230)
|
||||
|
||||
## [v1.122.20](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.122.20)
|
||||
|
||||
Released at 2026-04-23
|
||||
|
||||
**v1.122.x is a line of [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-releases/). It contains important up-to-date bugfixes for [VictoriaMetrics enterprise](https://docs.victoriametrics.com/victoriametrics/enterprise/).
|
||||
All these fixes are also included in [the latest community release](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/latest).
|
||||
The v1.122.x line will be supported for at least 12 months since [v1.122.0](https://docs.victoriametrics.com/victoriametrics/changelog/#v11220) release**
|
||||
|
||||
* BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): fix incorrect evaluation of binary operations caused by an ordering bug (e.g. `10 - (3 + 3 + 4)` being evaluated as `10 - 3 + 3 + 4`). The issue was introduced in v1.140.0, v1.136.4, and v1.122.19. See [#10856](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10856).
|
||||
|
||||
## [v1.122.19](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.122.19)
|
||||
|
||||
**Update Note 1:** [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/): Due to an ordering bug in binary operations, some queries may produce incorrect results. For example, `10 - (3 + 3 + 4)` is evaluated as `10 - 3 + 3 + 4`. The issue was introduced in versions v1.140.0, v1.136.4, v1.122.19, and is addressed in upcoming releases. It is strongly recommended to avoid these versions entirely. See [#10856](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10856).
|
||||
|
||||
Released at 2026-04-10
|
||||
|
||||
**v1.122.x is a line of [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-releases/). It contains important up-to-date bugfixes for [VictoriaMetrics enterprise](https://docs.victoriametrics.com/victoriametrics/enterprise/).
|
||||
@@ -1556,4 +1506,4 @@ See changes [here](https://docs.victoriametrics.com/victoriametrics/changelog/ch
|
||||
|
||||
## Previous releases
|
||||
|
||||
See [releases page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases).
|
||||
See [releases page](https://github.com/VictoriaMetrics/VictoriaMetrics/releases).
|
||||
|
||||
@@ -338,7 +338,7 @@ Following convention is a good practice.
|
||||
|
||||
Every measurement can contain an arbitrary number of `key="value"` labels. The good practice is to keep this number limited.
|
||||
Otherwise, it would be difficult to deal with measurements containing a big number of labels.
|
||||
By default, VictoriaMetrics limits the number of labels per measurement to `40` and drops other labels.
|
||||
By default, VictoriaMetrics limits the number of labels per measurement to `30` and drops other labels.
|
||||
This limit can be changed via `-maxLabelsPerTimeseries` command-line flag if necessary (but this isn't recommended).
|
||||
|
||||
Every label value can contain an arbitrary string value. The good practice is to use short and meaningful label values to
|
||||
|
||||
@@ -9,29 +9,13 @@ sitemap:
|
||||
[vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) and [single-node VictoriaMetrics](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/)
|
||||
can aggregate incoming [samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) in streaming mode **by time** and **by labels** before data is written to remote storage
|
||||
(or local storage for single-node VictoriaMetrics).
|
||||
```mermaid
|
||||
flowchart LR
|
||||
A["requests_total{instance=foo}"] --> V[vmagent]
|
||||
B["requests_total{instance=bar}"] --> V
|
||||
C["requests_total{instance=baz}"] --> V
|
||||
V --> D[requests_total:rate5m]
|
||||
```
|
||||
The aggregation is applied to all the metrics received via any [supported data ingestion protocol](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-import-time-series-data)
|
||||
and/or scraped from [Prometheus-compatible targets](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-scrape-prometheus-exporters-such-as-node-exporter),
|
||||
and allows building [flexible processing pipelines](#routing).
|
||||
|
||||
# Features
|
||||
> By default, stream aggregation ignores timestamps associated with the input [samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples). It expects that the ingested samples have timestamps close to the current time. See [how to ignore old samples](#ignoring-old-samples).
|
||||
|
||||
Stream aggregation has the following features:
|
||||
|
||||
- It can calculate [aggregates](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs) on ingested samples before they're sent to remote destination;
|
||||
- It is applied to all the metric samples received via any [supported data ingestion protocol](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-import-time-series-data)
|
||||
and/or scraped from [Prometheus-compatible targets](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-scrape-prometheus-exporters-such-as-node-exporter)
|
||||
- It can filter out raw samples matched by aggregation rules, so raw data will never reach the remote destination. See `--streamAggr.keepInput` and `-streamAggr.dropInput` in [aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/);
|
||||
- It allows building [flexible processing pipelines](#routing);
|
||||
|
||||
# Limitations
|
||||
|
||||
- Stream aggregation **ignores timestamps associated with the input [samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples)**.
|
||||
It expects that the ingested samples have timestamps close to the current time. See [how to ignore old samples](#ignoring-old-samples).
|
||||
- Aggregation state is held in the process memory and will be lost on process restart.
|
||||
> If `-streamAggr.dedupInterval` is enabled, out-of-order samples (older than already received) within the configured interval are treated as duplicates and ignored. See [de-duplication](#deduplication).
|
||||
|
||||
# Use cases
|
||||
|
||||
@@ -57,41 +41,35 @@ and not available for [Statsd metrics format](https://github.com/statsd/statsd/b
|
||||
|
||||
## Recording rules alternative
|
||||
|
||||
Sometimes [rules](https://docs.victoriametrics.com/victoriametrics/vmalert/#rules) may require non-trivial amounts of CPU, RAM,
|
||||
disk IO and network bandwidth for processing on the metrics storage side.
|
||||
|
||||
For example, if the `http_request_duration_seconds` histogram is generated by thousands of application instances,
|
||||
then the alerting query `histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket[2m])) without (instance)) > 0.5`
|
||||
can become slow, since it needs to scan a large number of unique [time series](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#time-series).
|
||||
|
||||
This alerting query can be accelerated by pre-calculating
|
||||
the `sum(rate(http_request_duration_seconds_bucket[5m])) without (instance)` via [recording rule](https://docs.victoriametrics.com/victoriametrics/vmalert/#recording-rules).
|
||||
But it only shifts slowness from the alerting rule to the recording rule, since calculation still has to happen somewhere.
|
||||
It is better to substitute the slow recording rule with the following [stream aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config):
|
||||
Sometimes [alerting queries](https://docs.victoriametrics.com/victoriametrics/vmalert/#alerting-rules) may require non-trivial amounts of CPU, RAM,
|
||||
disk IO and network bandwidth at metrics storage side. For example, if `http_request_duration_seconds` histogram is generated by thousands
|
||||
of application instances, then the alerting query `histogram_quantile(0.99, sum(increase(http_request_duration_seconds_bucket[5m])) without (instance)) > 0.5`
|
||||
can become slow, since it needs to scan too big number of unique [time series](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#time-series)
|
||||
with `http_request_duration_seconds_bucket` name. This alerting query can be accelerated by pre-calculating
|
||||
the `sum(increase(http_request_duration_seconds_bucket[5m])) without (instance)` via [recording rule](https://docs.victoriametrics.com/victoriametrics/vmalert/#recording-rules).
|
||||
But this recording rule may take too much time to execute too. In this case the slow recording rule can be substituted
|
||||
with the following [stream aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config):
|
||||
|
||||
```yaml
|
||||
- match: 'http_request_duration_seconds_bucket'
|
||||
interval: 1m
|
||||
interval: 5m
|
||||
without: [instance]
|
||||
outputs: [rate_sum]
|
||||
outputs: [total]
|
||||
```
|
||||
|
||||
> Field `interval` should be set to a value at least several times higher than the matched metrics collection interval.
|
||||
|
||||
This stream aggregation generates `http_request_duration_seconds_bucket:1m_without_instance_rate_sum` output series according to [output metric naming](#output-metric-names).
|
||||
This stream aggregation generates `http_request_duration_seconds_bucket:5m_without_instance_total` output series according to [output metric naming](#output-metric-names).
|
||||
Then these series can be used in [alerting rules](https://docs.victoriametrics.com/victoriametrics/vmalert/#alerting-rules):
|
||||
|
||||
```metricsql
|
||||
histogram_quantile(0.99, avg_over_time(http_request_duration_seconds_bucket:1m_without_instance_rate_sum[5m])) > 0.5
|
||||
histogram_quantile(0.99, last_over_time(http_request_duration_seconds_bucket:5m_without_instance_total[5m])) > 0.5
|
||||
```
|
||||
|
||||
This query executes much faster than the original one because it needs to scan fewer time series.
|
||||
This query is executed much faster than the original query, because it needs to scan much lower number of time series.
|
||||
|
||||
> `avg_over_time(<aggregate:1m>[5m])` is similar to recording rules calculating rate over a sliding window of `5m` with `1m` interval.
|
||||
If the sliding window isn't important, then simply omit the `avg_over_time` aggregation in the expression.
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at `output` field.
|
||||
See also [aggregating by labels](#aggregating-by-labels).
|
||||
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at the `output` field.
|
||||
See also [aggregating by labels](#aggregating-by-labels), [aggregating histograms](#aggregating-histograms).
|
||||
Field `interval` is recommended to be set to a value at least several times higher than your metrics collect interval.
|
||||
|
||||
## Reducing the number of stored samples
|
||||
|
||||
@@ -111,7 +89,7 @@ to one sample per 5 minutes per each input time series (this operation is also k
|
||||
interval: 5m
|
||||
outputs: [total]
|
||||
|
||||
# Downsample other metrics with `count_samples`, `sum_samples`, `min`, and `max` outputs
|
||||
# Downsample other metrics with `count_samples`, `sum_samples`, `min` and `max` outputs
|
||||
# See https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs
|
||||
- match: '{__name__!~".+_total"}'
|
||||
interval: 5m
|
||||
@@ -131,14 +109,14 @@ some_metric:5m_min
|
||||
some_metric:5m_max
|
||||
```
|
||||
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at the `output` field.
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at `output` field.
|
||||
See also [aggregating histograms](#aggregating-histograms) and [aggregating by labels](#aggregating-by-labels).
|
||||
|
||||
## Reducing the number of stored series
|
||||
|
||||
Sometimes applications may generate too many [time series](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#time-series).
|
||||
For example, the `http_requests_total` metric may have `path` or `user` label with too many unique values.
|
||||
In this case, the following stream aggregation can be used for reducing the number of metrics stored in VictoriaMetrics:
|
||||
For example, the `http_requests_total` metric may have `path` or `user` label with too big number of unique values.
|
||||
In this case the following stream aggregation can be used for reducing the number metrics stored in VictoriaMetrics:
|
||||
|
||||
```yaml
|
||||
- match: 'http_requests_total'
|
||||
@@ -156,17 +134,17 @@ The aggregated output metric has the following name according to [output metric
|
||||
http_requests_total:30s_without_path_user_total
|
||||
```
|
||||
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at the `output` field.
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at `output` field.
|
||||
See also [aggregating histograms](#aggregating-histograms).
|
||||
|
||||
## Counting input samples
|
||||
|
||||
If the monitored application generates event-based metrics, then it may be useful to count the number of such metrics
|
||||
at the stream aggregation level.
|
||||
at stream aggregation level.
|
||||
|
||||
For example, if an advertising server generates `hits{some="labels"} 1` and `clicks{some="labels"} 1` metrics
|
||||
per each incoming hit and click, then the following [stream aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config)
|
||||
can be used for counting these metrics every 30-second interval:
|
||||
can be used for counting these metrics per every 30 second interval:
|
||||
|
||||
```yaml
|
||||
- match: '{__name__=~"hits|clicks"}'
|
||||
@@ -182,7 +160,7 @@ hits:30s_count_samples count1
|
||||
clicks:30s_count_samples count2
|
||||
```
|
||||
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at the `output` field.
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at `output` field.
|
||||
See also [aggregating by labels](#aggregating-by-labels).
|
||||
|
||||
## Summing input metrics
|
||||
@@ -208,12 +186,12 @@ hits:1m_sum_samples sum1
|
||||
clicks:1m_sum_samples sum2
|
||||
```
|
||||
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at the `output` field.
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at `output` field.
|
||||
See also [aggregating by labels](#aggregating-by-labels).
|
||||
|
||||
## Quantiles over input metrics
|
||||
|
||||
If the monitored application generates measurement metrics for each request, then it may be useful to calculate
|
||||
If the monitored application generates measurement metrics per each request, then it may be useful to calculate
|
||||
the pre-defined set of [percentiles](https://en.wikipedia.org/wiki/Percentile) over these measurements.
|
||||
|
||||
For example, if the monitored application generates `request_duration_seconds N` and `response_size_bytes M` metrics
|
||||
@@ -238,12 +216,12 @@ response_size_bytes:30s_quantiles{quantile="0.50"} value1
|
||||
response_size_bytes:30s_quantiles{quantile="0.99"} value2
|
||||
```
|
||||
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at the `output` field.
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at `output` field.
|
||||
See also [histograms over input metrics](#histograms-over-input-metrics) and [aggregating by labels](#aggregating-by-labels).
|
||||
|
||||
## Histograms over input metrics
|
||||
|
||||
If the monitored application generates measurement metrics for each request, then it may be useful to calculate
|
||||
If the monitored application generates measurement metrics per each request, then it may be useful to calculate
|
||||
a [histogram](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#histogram) over these metrics.
|
||||
|
||||
For example, if the monitored application generates `request_duration_seconds N` and `response_size_bytes M` metrics
|
||||
@@ -289,7 +267,7 @@ The resulting histogram buckets can be queried with [MetricsQL](https://docs.vic
|
||||
histogram_stddev(sum(increase(request_duration_seconds:60s_histogram_bucket[1h])) by (vmrange))
|
||||
```
|
||||
|
||||
This query uses the [histogram_stddev](https://docs.victoriametrics.com/victoriametrics/metricsql/#histogram_stddev) function.
|
||||
This query uses [histogram_stddev](https://docs.victoriametrics.com/victoriametrics/metricsql/#histogram_stddev) function.
|
||||
|
||||
1. An estimated share of requests with the duration smaller than `0.5s` over the last hour:
|
||||
|
||||
@@ -299,7 +277,7 @@ The resulting histogram buckets can be queried with [MetricsQL](https://docs.vic
|
||||
|
||||
This query uses [histogram_share](https://docs.victoriametrics.com/victoriametrics/metricsql/#histogram_share) function.
|
||||
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at the `output` field.
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at `output` field.
|
||||
See also [quantiles over input metrics](#quantiles-over-input-metrics) and [aggregating by labels](#aggregating-by-labels).
|
||||
|
||||
## Aggregating histograms
|
||||
@@ -339,24 +317,19 @@ Please note, histograms can be aggregated if their `le` labels are configured id
|
||||
[VictoriaMetrics histogram buckets](https://valyala.medium.com/improving-histogram-usability-for-prometheus-and-grafana-bc7e5df0e350)
|
||||
have no such requirement.
|
||||
|
||||
Stream aggregation of histogram buckets is very sensitive to sample delays. Histogram is logical group of independent time series (buckets) that are supposed to be updated uniformly.
|
||||
Aggregation can't guarantee that within one aggregation intervals all samples belonging to one histogram were updated. Situations like this can cause [accuracy issues](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4580).
|
||||
The recommended ways for improving accuracy are:
|
||||
- enable [aggregation windows](#aggregation-windows);
|
||||
- increase `interval` ;
|
||||
- ensure that vmagent has no resource shortage;
|
||||
- ensure that samples delivery pipeline has no resource shortage or queue accumulation, so it can deliver samples fast.
|
||||
It's recommended to use [aggregation windows](#aggregation-windows) when aggregating histograms if you observe [accuracy issues](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4580).
|
||||
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at the `output` field.
|
||||
See [the list of aggregate output](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs), which can be specified at `output` field.
|
||||
See also [histograms over input metrics](#histograms-over-input-metrics) and [quantiles over input metrics](#quantiles-over-input-metrics).
|
||||
|
||||
|
||||
# Routing
|
||||
|
||||
[Single-node VictoriaMetrics](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) supports relabeling,
|
||||
deduplication and stream aggregation for all the received data, scraped or pushed.
|
||||
The processed data is then stored in local storage, and **can't be forwarded further**.
|
||||
The processed data is then stored in local storage and **can't be forwarded further**.
|
||||
|
||||
[vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) supports relabeling, deduplication, and stream aggregation for all
|
||||
[vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) supports relabeling, deduplication and stream aggregation for all
|
||||
the received data, scraped or pushed. See the [processing order for vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/#life-of-a-sample).
|
||||
|
||||
Typical scenarios for data routing with `vmagent`:
|
||||
@@ -369,44 +342,42 @@ Typical scenarios for data routing with `vmagent`:
|
||||
|
||||
# Deduplication
|
||||
|
||||
If `-streamAggr.dedupInterval` is enabled, out-of-order samples (older than already received) within the configured interval are treated as duplicates and ignored. See [deduplication](#deduplication).
|
||||
[vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) supports online [de-duplication](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication) of samples
|
||||
before sending them to the configured `-remoteWrite.url`. The de-duplication can be enabled via the following options:
|
||||
|
||||
[vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) supports [deduplication](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication) of samples
|
||||
before sending them to the configured `-remoteWrite.url`. The deduplication can be enabled via the following options:
|
||||
|
||||
- By specifying the desired deduplication interval via `-streamAggr.dedupInterval` command-line flag for all received data
|
||||
- By specifying the desired de-duplication interval via `-streamAggr.dedupInterval` command-line flag for all received data
|
||||
or via `-remoteWrite.streamAggr.dedupInterval` command-line flag for the particular `-remoteWrite.url` destination.
|
||||
For example, `./vmagent -remoteWrite.url=http://remote-storage/api/v1/write -remoteWrite.streamAggr.dedupInterval=30s` instructs `vmagent` to leave
|
||||
only the last sample for each seen [time series](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#time-series) every 30 seconds.
|
||||
only the last sample per each seen [time series](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#time-series) per every 30 seconds.
|
||||
The de-deduplication is performed after applying [relabeling](https://docs.victoriametrics.com/victoriametrics/relabeling/) and
|
||||
before performing the aggregation.
|
||||
|
||||
- By specifying the `dedup_interval` option individually per each [stream aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config)
|
||||
- By specifying `dedup_interval` option individually per each [stream aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config)
|
||||
in `-remoteWrite.streamAggr.config` or `-streamAggr.config` configs.
|
||||
|
||||
[Single-node VictoriaMetrics](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) supports two types of de-duplication:
|
||||
- After storing the duplicate samples in local storage. See [`-dedup.minScrapeInterval`](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication) command-line option.
|
||||
- Before storing the duplicate samples in local storage. This type of deduplication can be enabled via the following options:
|
||||
- By specifying the desired deduplication interval via the `-streamAggr.dedupInterval` command-line flag.
|
||||
For example, `./victoria-metrics -streamAggr.dedupInterval=30s` instructs VictoriaMetrics to leave only the last sample for each
|
||||
- After storing the duplicate samples to local storage. See [`-dedup.minScrapeInterval`](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication) command-line option.
|
||||
- Before storing the duplicate samples to local storage. This type of de-duplication can be enabled via the following options:
|
||||
- By specifying the desired de-duplication interval via `-streamAggr.dedupInterval` command-line flag.
|
||||
For example, `./victoria-metrics -streamAggr.dedupInterval=30s` instructs VictoriaMetrics to leave only the last sample per each
|
||||
seen [time series](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#time-series) per every 30 seconds.
|
||||
The deduplication is performed after applying `-relabelConfig` [relabeling](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#relabeling).
|
||||
The de-duplication is performed after applying `-relabelConfig` [relabeling](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#relabeling).
|
||||
|
||||
- By specifying `dedup_interval` option individually per each [stream aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config) at `-streamAggr.config`.
|
||||
|
||||
It is possible to drop the given labels before applying the deduplication. See [these docs](#dropping-unneeded-labels).
|
||||
It is possible to drop the given labels before applying the de-duplication. See [these docs](#dropping-unneeded-labels).
|
||||
|
||||
The online deduplication uses the same logic as [`-dedup.minScrapeInterval` command-line flag](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication) at VictoriaMetrics.
|
||||
The online de-duplication uses the same logic as [`-dedup.minScrapeInterval` command-line flag](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication) at VictoriaMetrics.
|
||||
|
||||
Deduplication is applied before stream aggregation rules and can drop samples before they get matched for aggregation.
|
||||
De-duplication is applied before stream aggregation rules and can drop samples before they get matched for aggregation.
|
||||
|
||||
# Relabeling
|
||||
|
||||
It is possible to apply [arbitrary relabeling](https://docs.victoriametrics.com/victoriametrics/relabeling/) to input and output metrics
|
||||
during stream aggregation via `input_relabel_configs` and `output_relabel_configs` options in [stream aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config).
|
||||
|
||||
Relabeling rules inside `input_relabel_configs` are applied to samples matching the `match` filters before optional [deduplication](# deduplication).
|
||||
Relabeling rules in `output_relabel_configs` are applied to aggregated samples before they are sent to the remote storage.
|
||||
Relabeling rules inside `input_relabel_configs` are applied to samples matching the `match` filters before optional [deduplication](#deduplication).
|
||||
Relabeling rules inside `output_relabel_configs` are applied to aggregated samples before sending them to the remote storage.
|
||||
|
||||
For example, the following config removes the `:1m_sum_samples` suffix added [to the output metric name](#output-metric-names):
|
||||
|
||||
@@ -473,12 +444,12 @@ For example:
|
||||
- if `interval: 1m` is set, then the aggregated data is flushed to the storage at the end of every minute
|
||||
- if `interval: 1h` is set, then the aggregated data is flushed to the storage at the end of every hour
|
||||
|
||||
If you do not need such an alignment, then set the `no_align_flush_to_interval: true` option in the [aggregate config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config).
|
||||
In this case, aggregated data flushes will be aligned to the `vmagent` start time or to [config reload](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#configuration-update) time.
|
||||
If you do not need such an alignment, then set `no_align_flush_to_interval: true` option in the [aggregate config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config).
|
||||
In this case aggregated data flushes will be aligned to the `vmagent` start time or to [config reload](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#configuration-update) time.
|
||||
|
||||
The aggregated data on the first and the last interval is dropped during `vmagent` start, restart, or [config reload](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#configuration-update),
|
||||
since the first and last aggregation intervals are incomplete, they usually contain incomplete, confusing data.
|
||||
If you need to preserve the aggregated data on these intervals, then set `flush_on_shutdown: true` option in the [aggregate config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config).
|
||||
The aggregated data on the first and the last interval is dropped during `vmagent` start, restart or [config reload](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#configuration-update),
|
||||
since the first and the last aggregation intervals are incomplete, so they usually contain incomplete confusing data.
|
||||
If you need preserving the aggregated data on these intervals, then set `flush_on_shutdown: true` option in the [aggregate config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config).
|
||||
|
||||
See also:
|
||||
|
||||
@@ -509,7 +480,7 @@ The `keep_metric_names` option can be used if only a single output is set in [`o
|
||||
|
||||
## Aggregating by labels
|
||||
|
||||
By default, all labels from the input metrics are preserved in the output metrics. For example,
|
||||
All the labels for the input metrics are preserved by default in the output metrics. For example,
|
||||
the input metric `foo{app="bar",instance="host1"}` results to the output metric `foo:1m_sum_samples{app="bar",instance="host1"}`
|
||||
when the following [stream aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config) is used:
|
||||
|
||||
@@ -518,7 +489,7 @@ when the following [stream aggregation config](https://docs.victoriametrics.com/
|
||||
outputs: [sum_samples]
|
||||
```
|
||||
|
||||
The input labels can be removed via a `without` list specified in the config. For example, the following config
|
||||
The input labels can be removed via `without` list specified in the config. For example, the following config
|
||||
removes the `instance` label from output metrics by summing input samples across all the instances:
|
||||
|
||||
```yaml
|
||||
@@ -530,7 +501,7 @@ removes the `instance` label from output metrics by summing input samples across
|
||||
In this case the `foo{app="bar",instance="..."}` input metrics are transformed into `foo:1m_without_instance_sum_samples{app="bar"}`
|
||||
output metric according to [output metric naming](#output-metric-names).
|
||||
|
||||
It is possible to specify the exact list of labels in the output metrics via the `by` list.
|
||||
It is possible specifying the exact list of labels in the output metrics via `by` list.
|
||||
For example, the following config sums input samples by the `app` label:
|
||||
|
||||
```yaml
|
||||
@@ -542,7 +513,7 @@ For example, the following config sums input samples by the `app` label:
|
||||
In this case the `foo{app="bar",instance="..."}` input metrics are transformed into `foo:1m_by_app_sum_samples{app="bar"}`
|
||||
output metric according to [output metric naming](#output-metric-names).
|
||||
|
||||
The labels used in `by` and `without` lists can be modified via the `input_relabel_configs` section - see [these docs](#relabeling).
|
||||
The labels used in `by` and `without` lists can be modified via `input_relabel_configs` section - see [these docs](#relabeling).
|
||||
|
||||
See also [aggregation outputs](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#aggregation-outputs).
|
||||
|
||||
@@ -600,7 +571,6 @@ Below is an example of an `aggr.yaml` configuration that drops the `replica` and
|
||||
# Troubleshooting
|
||||
|
||||
- [Unexpected spikes for `total` or `increase` outputs](#staleness).
|
||||
- [Excessively large values for `total*`, `increase*`, and `rate*` outputs](#counter-resets).
|
||||
- [Lower than expected values for `total_prometheus` and `increase_prometheus` outputs](#staleness).
|
||||
- [High memory usage and CPU usage](#high-resource-usage).
|
||||
- [Unexpected results in vmagent cluster mode](#cluster-mode).
|
||||
@@ -608,33 +578,29 @@ Below is an example of an `aggr.yaml` configuration that drops the `replica` and
|
||||
|
||||
## Aggregation windows
|
||||
|
||||
By default, stream aggregation and deduplication store a single state for each aggregation output result.
|
||||
By default, stream aggregation and deduplication stores a single state per each aggregation output result.
|
||||
The data for each aggregator is flushed independently once per aggregation interval. But there's no guarantee that
|
||||
incoming samples with timestamps close to the aggregation interval's end will get into it. For example, when aggregating
|
||||
with `interval: 1m`, a data sample with timestamp 1739473078 (18:57:59) can fall into the aggregation round `18:58:00` or `18:59:00`.
|
||||
It depends on network lag, load, clock synchronization, etc. In most scenarios, it doesn't impact aggregation or
|
||||
deduplication results, which are consistent within the margin of error. But for metrics represented as a collection of series,
|
||||
with `interval: 1m` a data sample with timestamp 1739473078 (18:57:59) can fall into aggregation round `18:58:00` or `18:59:00`.
|
||||
It depends on network lag, load, clock synchronization, etc. In most scenarios it doesn't impact aggregation or
|
||||
deduplication results, which are consistent within margin of error. But for metrics represented as a collection of series,
|
||||
like [histograms](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#histogram), such inaccuracy leads to invalid aggregation results.
|
||||
|
||||
For this case, streaming aggregation and deduplication support mode with aggregation windows for the current and previous state.
|
||||
With this mode, flush doesn't happen immediately but is shifted by a calculated sample lag that improves correctness for delayed data. {{% available_from "v1.112.0" %}}
|
||||
For this case, streaming aggregation and deduplication support mode with aggregation windows for current and previous state.
|
||||
With this mode, flush doesn't happen immediately but is shifted by a calculated samples lag that improves correctness for delayed data. {{% available_from "v1.112.0" %}}
|
||||
|
||||
Enabling this mode has increased resource usage: memory usage is expected to double as aggregation will store two states
|
||||
instead of one. However, this significantly improves the accuracy of calculations. Aggregation windows can be enabled via
|
||||
Enabling of this mode has increased resource usage: memory usage is expected to double as aggregation will store two states
|
||||
instead of one. However, this significantly improves accuracy of calculations. Aggregation windows can be enabled via
|
||||
the following settings:
|
||||
|
||||
- `-streamAggr.enableWindows` at [single-node VictoriaMetrics](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/)
|
||||
and [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/). At [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/)
|
||||
`-remoteWrite.streamAggr.enableWindows` flag can be specified individually for each `-remoteWrite.url`.
|
||||
If one of these flags is set, all aggregators will use fixed windows. In conjunction with `-remoteWrite.streamAggr.dedupInterval` or
|
||||
`-streamAggr.dedupInterval` fixed aggregation windows are enabled on the deduplicator as well.
|
||||
`-remoteWrite.streamAggr.enableWindows` flag can be specified individually per each `-remoteWrite.url`.
|
||||
If one of these flags is set, then all aggregators will be using fixed windows. In conjunction with `-remoteWrite.streamAggr.dedupInterval` or
|
||||
`-streamAggr.dedupInterval` fixed aggregation windows are enabled on deduplicator as well.
|
||||
- `enable_windows` option in [aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#stream-aggregation-config).
|
||||
It allows enabling aggregation windows for a specific aggregator.
|
||||
|
||||
## Counter resets
|
||||
|
||||
If counter-specific outputs, such as `total*`, `rate*`, and `increase*`, produce values that are significantly higher than anticipated, then check the `vm_streamaggr_counter_resets_total` metric. This metric increments each time when [counter reset event](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#counter) happens and could be caused by duplication or collision of raw samples. If you observe duplication or collision, try solving this problem by either fixing the source of these metrics or by [deduplicating](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#deduplication) these samples before aggregation.
|
||||
|
||||
## Staleness
|
||||
|
||||
The following outputs track the last seen per-series values in order to properly calculate output values:
|
||||
@@ -647,7 +613,7 @@ The following outputs track the last seen per-series values in order to properly
|
||||
- [total](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#total)
|
||||
- [total_prometheus](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#total_prometheus)
|
||||
|
||||
The last seen per-series value is dropped if no new samples are received for the given time series during two consecutive aggregations
|
||||
The last seen per-series value is dropped if no new samples are received for the given time series during two consecutive aggregation
|
||||
intervals specified in [stream aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config) via `interval` option.
|
||||
If a new sample for the existing time series is received after that, then it is treated as the first sample for a new time series.
|
||||
This may lead to the following issues:
|
||||
@@ -661,16 +627,16 @@ These issues can be fixed in the following ways:
|
||||
- By increasing the `interval` option at [stream aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config), so it covers the expected
|
||||
delays in data ingestion pipelines.
|
||||
- By specifying the `staleness_interval` option at [stream aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config), so it covers the expected
|
||||
delays in data ingestion pipelines. By default, the `staleness_interval` is equal to `2 x interval`.
|
||||
delays in data ingestion pipelines. By default, the `staleness_interval` equals to `2 x interval`.
|
||||
|
||||
## High resource usage
|
||||
|
||||
The following solutions can help reduce memory usage and CPU usage during streaming aggregation:
|
||||
The following solutions can help reducing memory usage and CPU usage during streaming aggregation:
|
||||
|
||||
- To use more specific `match` filters at [streaming aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config), so only the really needed
|
||||
[raw samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) are aggregated.
|
||||
- To increase the aggregation interval by specifying a bigger duration for the `interval` option at [streaming aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config).
|
||||
- To generate a lower number of output time series by using less specific [`by` list](#aggregating-by-labels) or more specific [`without` list](#aggregating-by-labels).
|
||||
- To increase aggregation interval by specifying bigger duration for the `interval` option at [streaming aggregation config](https://docs.victoriametrics.com/victoriametrics/stream-aggregation/configuration/#stream-aggregation-config).
|
||||
- To generate lower number of output time series by using less specific [`by` list](#aggregating-by-labels) or more specific [`without` list](#aggregating-by-labels).
|
||||
- To drop unneeded long labels in input samples via [input_relabel_configs](#relabeling).
|
||||
|
||||
## Cluster mode
|
||||
@@ -683,32 +649,32 @@ For example, if more than one `vmagent` instance calculates [increase](https://d
|
||||
with `by: [path]` option, then all the `vmagent` instances will aggregate samples to the same set of time series with different `path` labels.
|
||||
The proper fix would be [adding a unique label](https://docs.victoriametrics.com/victoriametrics/vmagent/#adding-labels-to-metrics) for all the output samples
|
||||
produced by each `vmagent`, so they are aggregated into distinct sets of [time series](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#time-series).
|
||||
These time series can then be aggregated later as needed during querying.
|
||||
These time series then can be aggregated later as needed during querying.
|
||||
|
||||
If `vmagent` instances run in Docker or Kubernetes, then you can refer to `POD_NAME` or `HOSTNAME` environment variables
|
||||
If `vmagent` instances run in Docker or Kubernetes, then you can refer `POD_NAME` or `HOSTNAME` environment variables
|
||||
as a unique label value per each `vmagent` via `-remoteWrite.label=vmagent=%{HOSTNAME}` command-line flag.
|
||||
See [these docs](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#environment-variables) on how to refer to environment variables in VictoriaMetrics components.
|
||||
See [these docs](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#environment-variables) on how to refer environment variables in VictoriaMetrics components.
|
||||
|
||||
## Common mistakes
|
||||
|
||||
### Put aggregator behind load balancer
|
||||
|
||||
When configuring the aggregation rule, ensure that `vmagent` receives all required data to satisfy the `match` rule.
|
||||
If traffic to the vmagent goes through the load balancer, it could happen that vmagent will be receiving only a fraction of the data
|
||||
When configuring the aggregation rule, make sure that `vmagent` receives all the required data to satisfy the `match` rule.
|
||||
If traffic to the vmagent goes through the load balancer, it could happen that vmagent will be receiving only fraction of the data
|
||||
and produce incomplete aggregations.
|
||||
|
||||
To keep aggregation results consistent, ensure that vmagent receives all required data for aggregation. In case you need to
|
||||
To keep aggregation results consistent, make sure that vmagent receives all the required data for aggregation. In case if you need to
|
||||
split the load across multiple vmagents, try sharding the traffic among them via metric names or labels.
|
||||
For example, see how vmagent could consistently [shard data across remote write destinations](https://docs.victoriametrics.com/victoriametrics/vmagent/#sharding-among-remote-storages)
|
||||
via `-remoteWrite.shardByURL.labels` or `-remoteWrite.shardByURL.ignoreLabels` cmd-line flags.
|
||||
|
||||
### Create aggregator per each recording rule
|
||||
|
||||
Stream aggregation can be used as an alternative for [recording rules](#recording-rules-alternative).
|
||||
But creating an aggregation rule for each recording rule can lead to elevated resource usage on the vmagent,
|
||||
Stream aggregation can be used as alternative for [recording rules](#recording-rules-alternative).
|
||||
But creating an aggregation rule per each recording rule can lead to elevated resource usage on the vmagent,
|
||||
because the ingestion stream should be matched against every configured aggregation rule.
|
||||
|
||||
To optimize this, we recommend merging together aggregations that only differ in match expressions.
|
||||
To optimize this, we recommend merging together aggregations which only differ in match expressions.
|
||||
For example, let's see the following list of recording rules:
|
||||
|
||||
```yaml
|
||||
@@ -738,7 +704,7 @@ These rules can be effectively converted into a single aggregation rule:
|
||||
replacement: "instance:$1:rate:sum"
|
||||
```
|
||||
|
||||
**Note**: having a separate aggregator for a certain `match` expression can only be justified when the aggregator cannot keep up with all
|
||||
**Note**: having separate aggregator for a certain `match` expression can only be justified when aggregator cannot keep up with all
|
||||
the data pushed to an aggregator within an aggregation interval.
|
||||
|
||||
### Use identical --remoteWrite.streamAggr.config for all remote writes
|
||||
@@ -750,9 +716,9 @@ across multiple `-remoteWrite.url`.
|
||||
|
||||
### Use aggregated metrics like original ones
|
||||
|
||||
Stream aggregation allows keeping original metric names after aggregation by using the `keep_metric_names` setting.
|
||||
But the "meaning" of aggregated metrics is usually different from that of the original metrics.
|
||||
Make sure that you update queries in your alerting rules and dashboards accordingly if you used the `keep_metric_names` setting.
|
||||
Stream aggregation allows keeping original metric names after aggregation by using `keep_metric_names` setting.
|
||||
But the "meaning" of aggregated metrics is usually different to original ones after the aggregation.
|
||||
Make sure that you updated queries in your alerting rules and dashboards accordingly if you used `keep_metric_names` setting.
|
||||
|
||||
### Use different deduplication intervals on storage and vmagent
|
||||
|
||||
@@ -763,7 +729,7 @@ To avoid this, set `-streamAggr.dedupInterval` or `-remoteWrite.streamAggr.dedup
|
||||
|
||||
---
|
||||
|
||||
The section below contains backward-compatible anchors for links that were moved or renamed.
|
||||
Section below contains backward-compatible anchors for links that were moved or renamed.
|
||||
|
||||
###### Configuration
|
||||
|
||||
|
||||
@@ -284,12 +284,9 @@ expr: <string>
|
||||
# Available starting from https://docs.victoriametrics.com/victoriametrics/changelog/#v1860
|
||||
[ update_entries_limit: <integer> | default 0 ]
|
||||
|
||||
# Labels to add or overwrite labels from other external label sources, such as group labels, for each alert.
|
||||
# Labels to add or overwrite for each alert.
|
||||
# Labels are merged with labels received from `expr` evaluation and uniquely identify each generated alert.
|
||||
#
|
||||
# In case of conflicts, original labels are kept with prefix `exported_`.
|
||||
# As a special case, specifying a label with an empty string value removes the label from the result if it exists
|
||||
# in the original query result; otherwise, it is ignored.
|
||||
#
|
||||
# Labels only support limited templating variables in https://docs.victoriametrics.com/victoriametrics/vmalert/#templating,
|
||||
# including `$labels`, `$value` and `$expr`, to avoid breaking alert states or causing cardinality issue with results.
|
||||
@@ -419,11 +416,8 @@ record: <string>
|
||||
# must contain valid Graphite expression.
|
||||
expr: <string>
|
||||
|
||||
# Labels to add or overwrite labels from other external label sources, such as group labels, before storing the result.
|
||||
#
|
||||
# Labels to add or overwrite before storing the result.
|
||||
# In case of conflicts, original labels are kept with prefix `exported_`.
|
||||
# As a special case, specifying a label with an empty string value removes the label from the result if it exists
|
||||
# in the original query result; otherwise, it is ignored.
|
||||
#
|
||||
# Labels do not support templating in https://docs.victoriametrics.com/victoriametrics/vmalert/#templating due to cardinality concerns. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/8171.
|
||||
labels:
|
||||
|
||||
@@ -1523,11 +1523,7 @@ It is recommended to protect the following endpoints with authKeys:
|
||||
* `/metrics` with `-metricsAuthKey` command-line flag, so unauthorized users couldn't access [vmauth metrics](https://docs.victoriametrics.com/victoriametrics/vmauth/#monitoring).
|
||||
* `/debug/pprof` with `-pprofAuthKey` command-line flag, so unauthorized users couldn't access [profiling information](#profiling).
|
||||
|
||||
As an alternative, you can serve internal API routes on a different listen address using the command-line flag `-httpInternalListenAddr=127.0.0.1:8426`{{% available_from "v1.111.0" %}}.
|
||||
To enable TLS on the public listener while keeping the internal listener non-TLS, configure multiple listeners like this:
|
||||
```
|
||||
/path/to/vmauth -httpInternalListenAddr=,localhost:8426 -httpListenAddr=0.0.0.0:443, -tls=true,false -tlsCertFile=a-cert.crt -tlsKeyFile=a-key.key
|
||||
```
|
||||
As an alternative, you can serve internal API routes on a different listen address using the command-line flag `-httpInternalListenAddr=127.0.0.1:8426`. {{% available_from "v1.111.0" %}}
|
||||
|
||||
`vmauth` also supports restricting access by IP - see [these docs](#ip-filters). See also [concurrency limiting docs](#concurrency-limiting).
|
||||
|
||||
|
||||