Compare commits

..

2 Commits

Author SHA1 Message Date
func25
3af0a6fac3 update 2026-07-29 12:55:51 +02:00
func25
a1bcfbf440 update 2026-07-29 12:55:48 +02:00
32 changed files with 107 additions and 969 deletions

View File

@@ -2,6 +2,7 @@
[![Latest Release](https://img.shields.io/github/v/release/VictoriaMetrics/VictoriaMetrics?sort=semver&label=&filter=!*-victorialogs&logo=github&labelColor=gray&color=gray&link=https%3A%2F%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics%2Freleases%2Flatest)](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
[![Docker Pulls](https://img.shields.io/docker/pulls/victoriametrics/victoria-metrics?label=&logo=docker&logoColor=white&labelColor=2496ED&color=2496ED&link=https%3A%2F%2Fhub.docker.com%2Fr%2Fvictoriametrics%2Fvictoria-metrics)](https://hub.docker.com/u/victoriametrics)
[![Go Report](https://goreportcard.com/badge/github.com/VictoriaMetrics/VictoriaMetrics?link=https%3A%2F%2Fgoreportcard.com%2Freport%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics)](https://goreportcard.com/report/github.com/VictoriaMetrics/VictoriaMetrics)
[![Build Status](https://github.com/VictoriaMetrics/VictoriaMetrics/actions/workflows/build.yml/badge.svg?branch=master&link=https%3A%2F%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics%2Factions)](https://github.com/VictoriaMetrics/VictoriaMetrics/actions/workflows/build.yml)
[![License](https://img.shields.io/github/license/VictoriaMetrics/VictoriaMetrics?labelColor=green&label=&link=https%3A%2F%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics%2Fblob%2Fmaster%2FLICENSE)](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/LICENSE)
[![Join Slack](https://img.shields.io/badge/Join%20Slack-4A154B?logo=slack)](https://slack.victoriametrics.com)

View File

@@ -11,7 +11,6 @@ import (
"strings"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
@@ -268,11 +267,7 @@ func (c *Client) do(req *http.Request) (*http.Response, error) {
if resp.StatusCode != http.StatusOK {
body, _ := io.ReadAll(resp.Body)
_ = resp.Body.Close()
err = &httpserver.ErrorWithStatusCode{
StatusCode: resp.StatusCode,
Err: fmt.Errorf("unexpected response code %d for %s. Response body %s", resp.StatusCode, ru, body),
}
return nil, err
return nil, fmt.Errorf("unexpected response code %d for %s. Response body %s", resp.StatusCode, ru, body)
}
return resp, nil
}

View File

@@ -31,8 +31,6 @@ type Alert struct {
State AlertState
// Expr contains expression that was executed to generate the Alert
Expr string
// Interval contains the evaluation interval of the Alert's group
Interval time.Duration
// ActiveAt defines the moment of time when Alert has become active
ActiveAt time.Time
// Start defines the moment of time when Alert has become firing
@@ -86,7 +84,6 @@ type AlertTplData struct {
Labels map[string]string
Value float64
Expr string
Interval time.Duration
AlertID uint64
GroupID uint64
ActiveAt time.Time
@@ -99,7 +96,6 @@ var tplHeaders = []string{
"{{ $type := .Type }}",
"{{ $labels := .Labels }}",
"{{ $expr := .Expr }}",
"{{ $interval := .Interval }}",
"{{ $externalLabels := .ExternalLabels }}",
"{{ $externalURL := .ExternalURL }}",
"{{ $alertID := .AlertID }}",
@@ -119,7 +115,6 @@ func (a *Alert) ExecTemplate(q templates.QueryFn, labels, annotations map[string
Type: a.Type,
Labels: labels,
Expr: a.Expr,
Interval: a.Interval,
AlertID: a.ID,
GroupID: a.GroupID,
ActiveAt: a.ActiveAt,

View File

@@ -129,17 +129,6 @@ func TestAlertExecTemplate(t *testing.T) {
"exprEscapedHTML": "vm_rows{"label"="bar"}<0",
})
// interval-template
f(&Alert{
Interval: 10 * time.Second,
}, map[string]string{
"interval": "{{ .Interval }}",
"intervalVariable": "{{ $interval }}",
}, map[string]string{
"interval": "10s",
"intervalVariable": "10s",
})
// query
f(&Alert{
Expr: `vm_rows{"label"="bar"}>0`,

View File

@@ -25,12 +25,11 @@ var (
replayMaxDatapoints = flag.Int("replay.maxDatapointsPerQuery", 1e3,
"Max number of data points expected in one request. It affects the max time range for every '/query_range' request during the replay. The higher the value, the less requests will be made during replay.")
replayRuleRetryAttempts = flag.Int("replay.ruleRetryAttempts", 5,
"Defines how many retries to make before giving up on rule if request for it returns a retriable error.")
"Defines how many retries to make before giving up on rule if request for it returns an error.")
disableProgressBar = flag.Bool("replay.disableProgressBar", false, "Whether to disable rendering progress bars during the replay. "+
"Progress bar rendering might be verbose or break the logs parsing, so it is recommended to be disabled when not used in interactive mode.")
ruleEvaluationConcurrency = flag.Int("replay.ruleEvaluationConcurrency", 1, "The maximum number of concurrent '/query_range' requests when replay recording rule or alerting rule with for=0. "+
"Increasing this value when replaying for a long time, since each request is limited by -replay.maxDatapointsPerQuery.")
continueWithExecutionErr = flag.Bool("replay.continueWithExecutionErr", false, "Whether to continue replaying other rules if a rule execution fails with a 422 response code, which can happen due to an expression syntax error or a resource limit being hit.")
)
func replay(groupsCfg []config.Group, qb datasource.QuerierBuilder, rw remotewrite.RWClient) (totalRows, droppedRows int, err error) {
@@ -74,7 +73,7 @@ func replay(groupsCfg []config.Group, qb datasource.QuerierBuilder, rw remotewri
for _, cfg := range groupsCfg {
ng := rule.NewGroup(cfg, qb, *evaluationInterval, labels)
totalRows += ng.Replay(tFrom, tTo, rw, *replayMaxDatapoints, *replayRuleRetryAttempts, *replayRulesDelay, *disableProgressBar, *ruleEvaluationConcurrency, *continueWithExecutionErr)
totalRows += ng.Replay(tFrom, tTo, rw, *replayMaxDatapoints, *replayRuleRetryAttempts, *replayRulesDelay, *disableProgressBar, *ruleEvaluationConcurrency)
}
logger.Infof("replay evaluation finished, generated %d samples", totalRows)
if err := rw.Close(); err != nil {

View File

@@ -8,10 +8,8 @@ import (
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutil"
"github.com/VictoriaMetrics/metricsql"
)
type fakeReplayQuerier struct {
@@ -34,14 +32,6 @@ func (fc *fakeRWClient) Close() error {
}
func (fr *fakeReplayQuerier) QueryRange(_ context.Context, q string, from, to time.Time) (res datasource.Result, err error) {
_, err = metricsql.Parse(q)
if err != nil {
return res, &httpserver.ErrorWithStatusCode{
StatusCode: 422,
Err: err,
}
}
key := fmt.Sprintf("%s+%s", from.Format("15:04:05"), to.Format("15:04:05"))
dps, ok := fr.registry[q]
if !ok {
@@ -285,28 +275,4 @@ func TestReplay(t *testing.T) {
},
},
}, 10)
// rule with wrong expression won't break the other rule with continueWithExecutionErr
continueWithExecutionErrOld := *continueWithExecutionErr
defer func() {
*continueWithExecutionErr = continueWithExecutionErrOld
}()
*continueWithExecutionErr = true
f("2021-01-01T12:00:00.000Z", "2021-01-01T12:02:30.000Z", 1, 1, time.Millisecond, []config.Group{
{Rules: []config.Rule{{Record: "foo", Expr: "sum(up)"}}},
{Rules: []config.Rule{{Record: "bar", Expr: "up ++"}}},
}, &fakeReplayQuerier{
registry: map[string]map[string][]datasource.Metric{
"sum(up)": {
"12:00:00+12:01:00": {
{
Timestamps: []int64{1, 2},
Values: []float64{1, 2},
},
},
"12:01:00+12:02:00": {},
"12:02:00+12:02:30": {},
},
},
}, 2)
}

View File

@@ -530,7 +530,6 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
ar.logDebugf(ts, a, "INACTIVE => PENDING")
}
a.Value = m.Values[0]
a.Interval = ar.EvalInterval
a.Annotations = annotations
a.KeepFiringSince = time.Time{}
continue
@@ -613,7 +612,6 @@ func (ar *AlertingRule) expandAnnotationTemplates(m datasource.Metric, qFn templ
Type: ar.Type.String(),
Labels: ls.origin,
Expr: ar.Expr,
Interval: ar.EvalInterval,
AlertID: hash(ls.processed),
GroupID: ar.GroupID,
ActiveAt: activeAt,
@@ -675,7 +673,6 @@ func (ar *AlertingRule) newAlert(m datasource.Metric, start time.Time, labels, a
Name: ar.Name,
Type: ar.Type.String(),
Expr: ar.Expr,
Interval: ar.EvalInterval,
For: ar.For,
ActiveAt: start,
Value: m.Values[0],

View File

@@ -662,7 +662,6 @@ func TestAlertingRuleExecRange(t *testing.T) {
GroupID: fakeGroup.GetID(),
Name: "for-pending",
Type: config.NewPrometheusType().String(),
Interval: time.Second,
Labels: map[string]string{"alertname": "for-pending"},
Annotations: map[string]string{},
State: notifier.StatePending,
@@ -683,7 +682,6 @@ func TestAlertingRuleExecRange(t *testing.T) {
GroupID: fakeGroup.GetID(),
Name: "for-firing",
Type: config.NewPrometheusType().String(),
Interval: 3 * time.Second,
Labels: map[string]string{"alertname": "for-firing"},
Annotations: map[string]string{},
State: notifier.StateFiring,
@@ -705,7 +703,6 @@ func TestAlertingRuleExecRange(t *testing.T) {
GroupID: fakeGroup.GetID(),
Name: "for-hold-pending",
Type: config.NewPrometheusType().String(),
Interval: time.Second,
Labels: map[string]string{"alertname": "for-hold-pending"},
Annotations: map[string]string{},
State: notifier.StatePending,
@@ -762,7 +759,6 @@ func TestAlertingRuleExecRange(t *testing.T) {
GroupID: fakeGroup.GetID(),
Name: "multi-series",
Type: config.NewPrometheusType().String(),
Interval: 3 * time.Second,
Labels: map[string]string{"alertname": "multi-series"},
Annotations: map[string]string{},
State: notifier.StateFiring,
@@ -775,7 +771,6 @@ func TestAlertingRuleExecRange(t *testing.T) {
GroupID: fakeGroup.GetID(),
Name: "multi-series",
Type: config.NewPrometheusType().String(),
Interval: 3 * time.Second,
Labels: map[string]string{"alertname": "multi-series", "foo": "bar"},
Annotations: map[string]string{},
State: notifier.StatePending,
@@ -1139,8 +1134,7 @@ func TestAlertingRule_Template(t *testing.T) {
fq.Add(metrics...)
fq.SetPartialResponse(isResponsePartial)
ts := time.Unix(3600, 0)
if _, err := rule.exec(context.TODO(), ts, 0); err != nil {
if _, err := rule.exec(context.TODO(), time.Now(), 0); err != nil {
t.Fatalf("unexpected error: %s", err)
}
for hash, expAlert := range alertsExpected {
@@ -1158,14 +1152,12 @@ func TestAlertingRule_Template(t *testing.T) {
}
f(&AlertingRule{
Name: "common",
EvalInterval: time.Hour,
Name: "common",
Labels: map[string]string{
"region": "east",
},
Annotations: map[string]string{
"summary": `{{ $labels.alertname }}: Too high connection number for "{{ $labels.instance }}"`,
"dashboard": `&from={{ ($activeAt.Add (parseDurationTime (printf "-%s" .Interval))).UnixMilli }}&to={{ $activeAt.UnixMilli }}`,
"summary": `{{ $labels.alertname }}: Too high connection number for "{{ $labels.instance }}"`,
},
alerts: make(map[uint64]*notifier.Alert),
}, []datasource.Metric{
@@ -1174,8 +1166,7 @@ func TestAlertingRule_Template(t *testing.T) {
}, false, map[uint64]*notifier.Alert{
hash(map[string]string{alertNameLabel: "common", "region": "east", "instance": "foo"}): {
Annotations: map[string]string{
"summary": `common: Too high connection number for "foo"`,
"dashboard": "&from=0&to=3600000",
"summary": `common: Too high connection number for "foo"`,
},
Labels: map[string]string{
alertNameLabel: "common",
@@ -1185,8 +1176,7 @@ func TestAlertingRule_Template(t *testing.T) {
},
hash(map[string]string{alertNameLabel: "common", "region": "east", "instance": "bar"}): {
Annotations: map[string]string{
"summary": `common: Too high connection number for "bar"`,
"dashboard": "&from=0&to=3600000",
"summary": `common: Too high connection number for "bar"`,
},
Labels: map[string]string{
alertNameLabel: "common",
@@ -1398,7 +1388,7 @@ func TestAlertingRule_ToLabels(t *testing.T) {
"alertname": "ConfigurationReloadFailure",
"alertgroup": "vmalert",
"pod": "vmalert-0",
"invalid_label": `error evaluating template: template: :1:326: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
"invalid_label": `error evaluating template: template: :1:298: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
}
expectedProcessedLabels := map[string]string{
@@ -1408,7 +1398,7 @@ func TestAlertingRule_ToLabels(t *testing.T) {
"exported_alertname": "ConfigurationReloadFailure",
"group": "vmalert",
"alertgroup": "vmalert",
"invalid_label": `error evaluating template: template: :1:326: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
"invalid_label": `error evaluating template: template: :1:298: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
}
ls, err := ar.toLabels(metric, nil)

View File

@@ -548,7 +548,7 @@ func (g *Group) infof(format string, args ...any) {
}
// Replay performs group replay
func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoint, replayRuleRetryAttempts int, replayDelay time.Duration, disableProgressBar bool, ruleEvaluationConcurrency int, continueWithExecutionErr bool) int {
func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoint, replayRuleRetryAttempts int, replayDelay time.Duration, disableProgressBar bool, ruleEvaluationConcurrency int) int {
var total int
step := g.Interval * time.Duration(maxDataPoint)
ri := rangeIterator{start: start, end: end, step: step}
@@ -576,7 +576,7 @@ func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoi
if !disableProgressBar {
bar = pb.StartNew(iterations)
}
total += replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency, continueWithExecutionErr)
total += replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency)
if bar != nil {
bar.Finish()
}
@@ -598,7 +598,7 @@ func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoi
rule := g.Rules[i]
sem <- struct{}{}
wg.Go(func() {
res <- replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency, continueWithExecutionErr)
res <- replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency)
<-sem
})
}
@@ -618,7 +618,7 @@ func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoi
return total
}
func replayRuleRange(r Rule, ri rangeIterator, bar *pb.ProgressBar, rw remotewrite.RWClient, replayRuleRetryAttempts, ruleEvaluationConcurrency int, continueWithExecutionErr bool) int {
func replayRuleRange(r Rule, ri rangeIterator, bar *pb.ProgressBar, rw remotewrite.RWClient, replayRuleRetryAttempts, ruleEvaluationConcurrency int) int {
fmt.Printf("> Rule %q (ID: %d)\n", r, r.ID())
// alerting rule with for>0 can't be replayed concurrently, since the status change might depend on the previous evaluation
// see https://github.com/VictoriaMetrics/VictoriaMetrics/commit/abcb21aa5ee918ba9a4e9cde495dba06e1e9564c
@@ -633,7 +633,7 @@ func replayRuleRange(r Rule, ri rangeIterator, bar *pb.ProgressBar, rw remotewri
start := ri.s
end := ri.e
wg.Go(func() {
n, err := replayRule(r, start, end, rw, replayRuleRetryAttempts, continueWithExecutionErr)
n, err := replayRule(r, start, end, rw, replayRuleRetryAttempts)
if err != nil {
logger.Fatalf("rule %q: %s", r, err)
}

View File

@@ -4,14 +4,12 @@ import (
"context"
"errors"
"fmt"
"net/http"
"sync"
"time"
"github.com/VictoriaMetrics/metrics"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/remotewrite"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
)
@@ -120,7 +118,7 @@ func (s *ruleState) add(e StateEntry) {
s.entries[s.cur] = e
}
func replayRule(r Rule, start, end time.Time, rw remotewrite.RWClient, replayRuleRetryAttempts int, continueWithExecutionErr bool) (int, error) {
func replayRule(r Rule, start, end time.Time, rw remotewrite.RWClient, replayRuleRetryAttempts int) (int, error) {
var err error
var tss []prompb.TimeSeries
for i := range replayRuleRetryAttempts {
@@ -128,21 +126,6 @@ func replayRule(r Rule, start, end time.Time, rw remotewrite.RWClient, replayRul
if err == nil {
break
}
// retry request if possible to tolerate temporary network or datasource unavailability issues
var esc *httpserver.ErrorWithStatusCode
if errors.As(err, &esc) {
statusCode := esc.StatusCode
// if the status code is 422, it means that the query was executed but failed due to an expression syntax error or a the resource limit being hit,
// continue replaying but skip the problematic execution if continueWithExecutionErr is true, otherwise, return the error without retry.
if statusCode == http.StatusUnprocessableEntity {
if continueWithExecutionErr {
logger.Errorf("rule %q: %s", r, err)
return 0, nil
} else {
return 0, err
}
}
}
logger.Errorf("attempt %d to execute rule %q failed: %s", i+1, r, err)
time.Sleep(time.Second)
}

View File

@@ -8,14 +8,12 @@ import (
"io"
"net/http"
"net/url"
"strconv"
"strings"
"time"
"github.com/gogo/protobuf/proto"
"github.com/golang/snappy"
"github.com/prometheus/prometheus/config"
"github.com/prometheus/prometheus/model/histogram"
"github.com/prometheus/prometheus/prompb"
"github.com/prometheus/prometheus/storage/remote"
"github.com/prometheus/prometheus/tsdb/chunkenc"
@@ -236,29 +234,9 @@ func processResponse(body io.ReadCloser, callback StreamCallback) error {
// shouldn't be accounted as an error.
for _, res := range readResp.Results {
for _, ts := range res.Timeseries {
// A series contains either float samples or native histogram samples.
// Both fields are processed independently, since a series may switch
// from float to native histogram representation at some point in time,
// so the requested time range may contain samples of both types.
if len(ts.Samples) > 0 {
vmTs := convertSamples(ts.Samples, ts.Labels)
if err := callback(vmTs); err != nil {
return err
}
}
if len(ts.Histograms) > 0 {
hSamples := make([]histogramSample, 0, len(ts.Histograms))
for _, h := range ts.Histograms {
hSamples = append(hSamples, histogramSample{
timestamp: h.Timestamp,
fh: h.ToFloatHistogram(),
})
}
for _, vmTs := range convertHistograms(hSamples, ts.Labels) {
if err := callback(vmTs); err != nil {
return err
}
}
vmTs := convertSamples(ts.Samples, ts.Labels)
if err := callback(vmTs); err != nil {
return err
}
}
}
@@ -285,45 +263,17 @@ func processStreamResponse(body io.ReadCloser, callback StreamCallback) error {
for _, series := range res.ChunkedSeries {
samples := make([]prompb.Sample, 0)
var hSamples []histogramSample
for _, chunk := range series.Chunks {
switch chunk.Type {
case prompb.Chunk_XOR, prompb.Chunk_UNKNOWN:
// In proto3 the `type` field may be left unset (UNKNOWN) for XOR chunks.
// Prometheus remote.proto: "REQUIREMENT: when using proto3, this field
// MUST be set when using anything else than XOR". Senders before native
// histograms support (Prometheus < 2.40) do not set this field at all,
// so UNKNOWN chunks must be parsed as XOR ones.
s, err := parseSamples(chunk.Data)
if err != nil {
return err
}
samples = append(samples, s...)
case prompb.Chunk_HISTOGRAM, prompb.Chunk_FLOAT_HISTOGRAM:
hs, err := parseHistograms(chunk.Type, chunk.Data)
if err != nil {
return err
}
hSamples = append(hSamples, hs...)
default:
return fmt.Errorf("unsupported chunk encoding %q", chunk.Type)
s, err := parseSamples(chunk.Data)
if err != nil {
return err
}
samples = append(samples, s...)
}
// A series contains either XOR chunks or native histogram chunks.
// Both are processed independently, since a series may switch
// from float to native histogram representation at some point in time,
// so the requested time range may contain chunks of both types.
if len(samples) > 0 {
ts := convertSamples(samples, series.Labels)
if err := callback(ts); err != nil {
return err
}
}
for _, ts := range convertHistograms(hSamples, series.Labels) {
if err := callback(ts); err != nil {
return err
}
ts := convertSamples(samples, series.Labels)
if err := callback(ts); err != nil {
return err
}
}
}
@@ -362,151 +312,6 @@ func parseSamples(chunk []byte) ([]prompb.Sample, error) {
return samples, it.Err()
}
// histogramSample represents a single native histogram sample.
type histogramSample struct {
timestamp int64
fh *histogram.FloatHistogram
}
func parseHistograms(encoding prompb.Chunk_Encoding, chunk []byte) ([]histogramSample, error) {
var enc chunkenc.Encoding
switch encoding {
case prompb.Chunk_HISTOGRAM:
enc = chunkenc.EncHistogram
case prompb.Chunk_FLOAT_HISTOGRAM:
enc = chunkenc.EncFloatHistogram
default:
return nil, fmt.Errorf("unsupported histogram chunk encoding %q", encoding)
}
c, err := chunkenc.FromData(enc, chunk)
if err != nil {
return nil, fmt.Errorf("error read chunk: %w", err)
}
var hSamples []histogramSample
it := c.Iterator(nil)
for {
typ := it.Next()
if typ == chunkenc.ValNone {
break
}
switch typ {
case chunkenc.ValHistogram:
ts, h := it.AtHistogram(nil)
hSamples = append(hSamples, histogramSample{
timestamp: ts,
fh: h.ToFloat(nil),
})
case chunkenc.ValFloatHistogram:
ts, fh := it.AtFloatHistogram(nil)
hSamples = append(hSamples, histogramSample{
timestamp: ts,
fh: fh,
})
default:
// Skip unsupported values
continue
}
}
if err := it.Err(); err != nil {
return nil, fmt.Errorf("error iterate over chunks: %w", err)
}
return hSamples, nil
}
// convertHistograms converts native histogram samples into VictoriaMetrics histogram
// time series in the same way as VictoriaMetrics converts native histograms
// received via Prometheus remote write protocol: every native histogram sample
// is converted into `<name>_count` and `<name>_sum` series plus a set of
// `<name>_bucket` series with `vmrange` labels containing non-cumulative bucket counts.
// The only difference is that for native histograms with custom buckets (NHCB)
// bucket bounds are taken from the custom values, while the remote write protocol
// parser ignores custom values and estimates the bounds with the exponential formula.
// See https://prometheus.io/docs/specs/native_histograms/#data-model
func convertHistograms(hSamples []histogramSample, labels []prompb.Label) []*vm.TimeSeries {
if len(hSamples) == 0 {
return nil
}
labelPairs := make([]vm.LabelPair, 0, len(labels))
nameValue := ""
for _, label := range labels {
if label.Name == "__name__" {
nameValue = label.Value
continue
}
labelPairs = append(labelPairs, vm.LabelPair{Name: label.Name, Value: label.Value})
}
// the metric has no name, skip it in the same way as VictoriaMetrics does
// when it receives a native histogram without the metric name via remote write protocol.
if nameValue == "" {
return nil
}
countSeries := &vm.TimeSeries{
Name: nameValue + "_count",
LabelPairs: labelPairs,
}
sumSeries := &vm.TimeSeries{
Name: nameValue + "_sum",
LabelPairs: labelPairs,
}
bucketSeries := make(map[string]*vm.TimeSeries)
// vmranges preserves the order of bucketSeries creation
// in order to get deterministic results.
var vmranges []string
for _, hs := range hSamples {
fh := hs.fh
countSeries.Timestamps = append(countSeries.Timestamps, hs.timestamp)
countSeries.Values = append(countSeries.Values, fh.Count)
sumSeries.Timestamps = append(sumSeries.Timestamps, hs.timestamp)
sumSeries.Values = append(sumSeries.Values, fh.Sum)
it := fh.AllBucketIterator()
for it.Next() {
b := it.At()
if b.Count <= 0 {
continue
}
vmrange := formatVmrange(b.Lower, b.Upper)
s := bucketSeries[vmrange]
if s == nil {
bucketLabelPairs := make([]vm.LabelPair, len(labelPairs), len(labelPairs)+1)
copy(bucketLabelPairs, labelPairs)
bucketLabelPairs = append(bucketLabelPairs, vm.LabelPair{Name: "vmrange", Value: vmrange})
s = &vm.TimeSeries{
Name: nameValue + "_bucket",
LabelPairs: bucketLabelPairs,
}
bucketSeries[vmrange] = s
vmranges = append(vmranges, vmrange)
}
s.Timestamps = append(s.Timestamps, hs.timestamp)
s.Values = append(s.Values, b.Count)
}
}
tss := make([]*vm.TimeSeries, 0, 2+len(vmranges))
tss = append(tss, countSeries, sumSeries)
for _, vmrange := range vmranges {
tss = append(tss, bucketSeries[vmrange])
}
return tss
}
// formatVmrange formats the given bucket bounds into `vmrange` label value
// in the same way as VictoriaMetrics does for native histograms
// received via Prometheus remote write protocol.
func formatVmrange(lower, upper float64) string {
b := make([]byte, 0, 24)
b = strconv.AppendFloat(b, lower, 'e', 3, 64)
b = append(b, "..."...)
b = strconv.AppendFloat(b, upper, 'e', 3, 64)
return string(b)
}
type keyValue struct {
key string
value string

View File

@@ -1,334 +0,0 @@
package remoteread
import (
"bytes"
"io"
"reflect"
"testing"
"github.com/gogo/protobuf/proto"
"github.com/golang/snappy"
"github.com/prometheus/prometheus/model/histogram"
"github.com/prometheus/prometheus/prompb"
"github.com/prometheus/prometheus/storage/remote"
"github.com/prometheus/prometheus/tsdb/chunkenc"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/vm"
)
func testHistogram(mul int64) *histogram.Histogram {
return &histogram.Histogram{
Schema: 0,
Count: uint64(10 * mul),
Sum: 25.5 * float64(mul),
ZeroThreshold: 0.001,
ZeroCount: uint64(2 * mul),
PositiveSpans: []histogram.Span{{Offset: 0, Length: 2}},
PositiveBuckets: []int64{1 * mul, 2 * mul},
NegativeSpans: []histogram.Span{{Offset: 0, Length: 1}},
NegativeBuckets: []int64{4 * mul},
}
}
func TestConvertHistograms(t *testing.T) {
f := func(hSamples []histogramSample, labels []prompb.Label, expected []*vm.TimeSeries) {
t.Helper()
tss := convertHistograms(hSamples, labels)
if !reflect.DeepEqual(tss, expected) {
t.Fatalf("unexpected result\ngot:\n%v\nwant:\n%v", tss, expected)
}
}
// series without samples
f(nil, []prompb.Label{{Name: "__name__", Value: "foo"}}, nil)
// series without the metric name must be skipped
f([]histogramSample{
{timestamp: 1000, fh: testHistogram(1).ToFloat(nil)},
}, []prompb.Label{{Name: "job", Value: "bar"}}, nil)
// native histogram must be converted to _count, _sum and _bucket series
// in the same way as VictoriaMetrics does for Prometheus remote write protocol
labels := []prompb.Label{
{Name: "__name__", Value: "request_duration_seconds"},
{Name: "job", Value: "bar"},
}
jobLabel := []vm.LabelPair{{Name: "job", Value: "bar"}}
bucketLabels := func(vmrange string) []vm.LabelPair {
return []vm.LabelPair{
{Name: "job", Value: "bar"},
{Name: "vmrange", Value: vmrange},
}
}
f([]histogramSample{
{timestamp: 1000, fh: testHistogram(1).ToFloat(nil)},
{timestamp: 2000, fh: testHistogram(2).ToFloat(nil)},
}, labels, []*vm.TimeSeries{
{
Name: "request_duration_seconds_count",
LabelPairs: jobLabel,
Timestamps: []int64{1000, 2000},
Values: []float64{10, 20},
},
{
Name: "request_duration_seconds_sum",
LabelPairs: jobLabel,
Timestamps: []int64{1000, 2000},
Values: []float64{25.5, 51},
},
{
Name: "request_duration_seconds_bucket",
LabelPairs: bucketLabels("-1.000e+00...-5.000e-01"),
Timestamps: []int64{1000, 2000},
Values: []float64{4, 8},
},
{
Name: "request_duration_seconds_bucket",
LabelPairs: bucketLabels("-1.000e-03...1.000e-03"),
Timestamps: []int64{1000, 2000},
Values: []float64{2, 4},
},
{
Name: "request_duration_seconds_bucket",
LabelPairs: bucketLabels("5.000e-01...1.000e+00"),
Timestamps: []int64{1000, 2000},
Values: []float64{1, 2},
},
{
Name: "request_duration_seconds_bucket",
LabelPairs: bucketLabels("1.000e+00...2.000e+00"),
Timestamps: []int64{1000, 2000},
Values: []float64{3, 6},
},
})
}
func TestParseHistograms(t *testing.T) {
c := chunkenc.NewHistogramChunk()
app, err := c.Appender()
if err != nil {
t.Fatalf("cannot create chunk appender: %s", err)
}
if _, _, _, err := app.AppendHistogram(nil, 0, 1000, testHistogram(1), true); err != nil {
t.Fatalf("cannot append histogram: %s", err)
}
if _, _, _, err := app.AppendHistogram(nil, 0, 2000, testHistogram(2), true); err != nil {
t.Fatalf("cannot append histogram: %s", err)
}
hSamples, err := parseHistograms(prompb.Chunk_HISTOGRAM, c.Bytes())
if err != nil {
t.Fatalf("cannot parse histogram chunk: %s", err)
}
if len(hSamples) != 2 {
t.Fatalf("unexpected number of histogram samples; got %d; want 2", len(hSamples))
}
for i, expected := range []struct {
timestamp int64
count float64
sum float64
}{
{timestamp: 1000, count: 10, sum: 25.5},
{timestamp: 2000, count: 20, sum: 51},
} {
if hSamples[i].timestamp != expected.timestamp {
t.Fatalf("unexpected timestamp; got %d; want %d", hSamples[i].timestamp, expected.timestamp)
}
if hSamples[i].fh.Count != expected.count {
t.Fatalf("unexpected count; got %f; want %f", hSamples[i].fh.Count, expected.count)
}
if hSamples[i].fh.Sum != expected.sum {
t.Fatalf("unexpected sum; got %f; want %f", hSamples[i].fh.Sum, expected.sum)
}
}
// unsupported chunk encoding must return error
if _, err := parseHistograms(prompb.Chunk_XOR, c.Bytes()); err == nil {
t.Fatalf("expecting non-nil error for unsupported chunk encoding")
}
}
func TestProcessResponse(t *testing.T) {
readResp := &prompb.ReadResponse{
Results: []*prompb.QueryResult{
{
Timeseries: []*prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "__name__", Value: "cpu_usage"},
{Name: "job", Value: "bar"},
},
Samples: []prompb.Sample{
{Timestamp: 1000, Value: 1.5},
},
},
{
Labels: []prompb.Label{
{Name: "__name__", Value: "request_duration_seconds"},
{Name: "job", Value: "bar"},
},
Histograms: []prompb.Histogram{
prompb.FromIntHistogram(1000, testHistogram(1)),
},
},
},
},
},
}
data, err := proto.Marshal(readResp)
if err != nil {
t.Fatalf("cannot marshal ReadResponse: %s", err)
}
compressed := snappy.Encode(nil, data)
var tss []*vm.TimeSeries
err = processResponse(io.NopCloser(bytes.NewReader(compressed)), func(ts *vm.TimeSeries) error {
tss = append(tss, ts)
return nil
})
if err != nil {
t.Fatalf("cannot process response: %s", err)
}
// 1 float series + _count + _sum + 4 buckets
if len(tss) != 7 {
t.Fatalf("unexpected number of time series; got %d; want 7", len(tss))
}
if tss[0].Name != "cpu_usage" || !reflect.DeepEqual(tss[0].Values, []float64{1.5}) {
t.Fatalf("unexpected float series: %v", tss[0])
}
if tss[1].Name != "request_duration_seconds_count" || !reflect.DeepEqual(tss[1].Values, []float64{10}) {
t.Fatalf("unexpected _count series: %v", tss[1])
}
if tss[2].Name != "request_duration_seconds_sum" || !reflect.DeepEqual(tss[2].Values, []float64{25.5}) {
t.Fatalf("unexpected _sum series: %v", tss[2])
}
for _, ts := range tss[3:] {
if ts.Name != "request_duration_seconds_bucket" {
t.Fatalf("unexpected bucket series name %q", ts.Name)
}
}
}
type nopFlusher struct{}
func (nopFlusher) Flush() {}
func TestProcessStreamResponse(t *testing.T) {
// build a histogram chunk
hc := chunkenc.NewHistogramChunk()
hApp, err := hc.Appender()
if err != nil {
t.Fatalf("cannot create histogram chunk appender: %s", err)
}
if _, _, _, err := hApp.AppendHistogram(nil, 0, 1000, testHistogram(1), true); err != nil {
t.Fatalf("cannot append histogram: %s", err)
}
// build a float chunk
xc := chunkenc.NewXORChunk()
xApp, err := xc.Appender()
if err != nil {
t.Fatalf("cannot create xor chunk appender: %s", err)
}
xApp.Append(0, 1000, 1.5)
res := &prompb.ChunkedReadResponse{
ChunkedSeries: []*prompb.ChunkedSeries{
{
Labels: []prompb.Label{
{Name: "__name__", Value: "request_duration_seconds"},
{Name: "job", Value: "bar"},
},
Chunks: []prompb.Chunk{
{Type: prompb.Chunk_HISTOGRAM, Data: hc.Bytes()},
},
},
{
Labels: []prompb.Label{
{Name: "__name__", Value: "cpu_usage"},
},
Chunks: []prompb.Chunk{
{Type: prompb.Chunk_XOR, Data: xc.Bytes()},
},
},
{
Labels: []prompb.Label{
{Name: "__name__", Value: "memory_usage"},
},
Chunks: []prompb.Chunk{
// the `type` field may be unset for XOR chunks,
// such chunks must be parsed as XOR ones
{Type: prompb.Chunk_UNKNOWN, Data: xc.Bytes()},
},
},
},
}
data, err := proto.Marshal(res)
if err != nil {
t.Fatalf("cannot marshal ChunkedReadResponse: %s", err)
}
var buf bytes.Buffer
cw := remote.NewChunkedWriter(&buf, nopFlusher{})
if _, err := cw.Write(data); err != nil {
t.Fatalf("cannot write chunked response: %s", err)
}
var tss []*vm.TimeSeries
err = processStreamResponse(io.NopCloser(&buf), func(ts *vm.TimeSeries) error {
tss = append(tss, ts)
return nil
})
if err != nil {
t.Fatalf("cannot process stream response: %s", err)
}
// _count + _sum + 4 buckets + 1 float series + 1 float series from UNKNOWN chunk
if len(tss) != 8 {
t.Fatalf("unexpected number of time series; got %d; want 8", len(tss))
}
if tss[0].Name != "request_duration_seconds_count" || !reflect.DeepEqual(tss[0].Values, []float64{10}) {
t.Fatalf("unexpected _count series: %v", tss[0])
}
if tss[1].Name != "request_duration_seconds_sum" || !reflect.DeepEqual(tss[1].Values, []float64{25.5}) {
t.Fatalf("unexpected _sum series: %v", tss[1])
}
for _, ts := range tss[2:6] {
if ts.Name != "request_duration_seconds_bucket" {
t.Fatalf("unexpected bucket series name %q", ts.Name)
}
}
if tss[6].Name != "cpu_usage" || !reflect.DeepEqual(tss[6].Values, []float64{1.5}) {
t.Fatalf("unexpected float series: %v", tss[6])
}
if tss[7].Name != "memory_usage" || !reflect.DeepEqual(tss[7].Values, []float64{1.5}) {
t.Fatalf("unexpected float series from UNKNOWN chunk: %v", tss[7])
}
}
func TestParseFloatHistograms(t *testing.T) {
c := chunkenc.NewFloatHistogramChunk()
app, err := c.Appender()
if err != nil {
t.Fatalf("cannot create chunk appender: %s", err)
}
fh := testHistogram(1).ToFloat(nil)
if _, _, _, err := app.AppendFloatHistogram(nil, 0, 1000, fh, true); err != nil {
t.Fatalf("cannot append float histogram: %s", err)
}
hSamples, err := parseHistograms(prompb.Chunk_FLOAT_HISTOGRAM, c.Bytes())
if err != nil {
t.Fatalf("cannot parse float histogram chunk: %s", err)
}
if len(hSamples) != 1 {
t.Fatalf("unexpected number of histogram samples; got %d; want 1", len(hSamples))
}
if hSamples[0].timestamp != 1000 {
t.Fatalf("unexpected timestamp; got %d; want 1000", hSamples[0].timestamp)
}
if hSamples[0].fh.Count != 10 {
t.Fatalf("unexpected count; got %f; want 10", hSamples[0].fh.Count)
}
}

View File

@@ -1,4 +1,4 @@
import { forwardRef, useImperativeHandle, useRef } from "preact/compat";
import { FC, useRef } from "preact/compat";
import ServerConfigurator from "./ServerConfigurator/ServerConfigurator";
import { ArrowDownIcon, SettingsIcon } from "../../Main/Icons";
import Button from "../../Main/Button/Button";
@@ -19,11 +19,7 @@ export interface ChildComponentHandle {
handleApply: () => void;
}
export interface GlobalSettingsHandle {
open: () => void;
}
const GlobalSettings = forwardRef<GlobalSettingsHandle>((_, ref) => {
const GlobalSettings: FC = () => {
const { isMobile } = useDeviceDetect();
const appModeEnable = getAppModeEnable();
@@ -70,10 +66,6 @@ const GlobalSettings = forwardRef<GlobalSettingsHandle>((_, ref) => {
}
].filter(control => control.show);
useImperativeHandle(ref, () => ({
open: handleOpen,
}));
return <>
{isMobile ? (
<div
@@ -139,6 +131,6 @@ const GlobalSettings = forwardRef<GlobalSettingsHandle>((_, ref) => {
</Modal>
)}
</>;
});
};
export default GlobalSettings;

View File

@@ -1,52 +0,0 @@
import { FC } from "preact/compat";
import Button from "../../../Main/Button/Button";
import { useTimeState } from "../../../../state/time/TimeStateContext";
import useDeviceDetect from "../../../../hooks/useDeviceDetect";
import { getUTCByTimezone } from "../../../../utils/time";
import { useMemo } from "react";
import { ArrowDownIcon, PlanetIcon } from "../../../Main/Icons";
type Props = {
onOpenSettings?: () => void;
}
const TimeZonePreview: FC<Props> = ({ onOpenSettings }) => {
const { isMobile } = useDeviceDetect();
const { timezone } = useTimeState();
const utcOffset = useMemo(() => getUTCByTimezone(timezone), [timezone]);
const handleOpenSettings = () => {
onOpenSettings && onOpenSettings();
};
if (isMobile) {
return (
<button
className="vm-mobile-option"
onClick={handleOpenSettings}
>
<span className="vm-mobile-option__icon"><PlanetIcon/></span>
<div className="vm-mobile-option-text">
<span className="vm-mobile-option-text__label">Time zone</span>
<span className="vm-mobile-option-text__value">{utcOffset}</span>
</div>
<span className="vm-mobile-option__arrow"><ArrowDownIcon/></span>
</button>
);
}
return (
<Button
className="vm-header-button"
onClick={handleOpenSettings}
startIcon={<PlanetIcon/>}
>
{utcOffset}
</Button>
);
};
export default TimeZonePreview;

View File

@@ -117,8 +117,6 @@ const StepConfigurator: FC = () => {
if (step === value || step === defaultStep) handleApply(defaultStep);
}, [isHistogram, displayType]);
const textValue = isAutoStep ? `auto (${customStep})` : customStep;
return (
<div
className="vm-step-control"
@@ -132,7 +130,7 @@ const StepConfigurator: FC = () => {
<span className="vm-mobile-option__icon"><TimelineIcon/></span>
<div className="vm-mobile-option-text">
<span className="vm-mobile-option-text__label">Step</span>
<span className="vm-mobile-option-text__value">{textValue}</span>
<span className="vm-mobile-option-text__value">{customStep}</span>
</div>
<span className="vm-mobile-option__arrow"><ArrowDownIcon/></span>
</div>
@@ -144,7 +142,7 @@ const StepConfigurator: FC = () => {
startIcon={<TimelineIcon/>}
onClick={toggleOpenOptions}
>
Step: {textValue}
Step: {isAutoStep ? `auto (${customStep})` : customStep}
</Button>
)}
<Popper

View File

@@ -19,11 +19,7 @@ import useBoolean from "../../../../hooks/useBoolean";
import useWindowSize from "../../../../hooks/useWindowSize";
import usePrevious from "../../../../hooks/usePrevious";
type Props = {
onOpenSettings?: () => void;
}
export const TimeSelector: FC<Props> = ({ onOpenSettings }) => {
export const TimeSelector: FC = () => {
const { isMobile } = useDeviceDetect();
const { isDarkTheme } = useAppState();
const wrapperRef = useRef<HTMLDivElement>(null);
@@ -57,7 +53,7 @@ export const TimeSelector: FC<Props> = ({ onOpenSettings }) => {
setFrom(formatDateForNativeInput(dateFromSeconds(start)));
}, [timezone, start]);
const setDuration = ({ duration, until, id }: { duration: string, until: Date, id: string }) => {
const setDuration = ({ duration, until, id }: {duration: string, until: Date, id: string}) => {
dispatch({ type: "SET_RELATIVE_TIME", payload: { duration, until, id } });
handleCloseOptions();
};
@@ -79,23 +75,16 @@ export const TimeSelector: FC<Props> = ({ onOpenSettings }) => {
const setTimeAndClosePicker = () => {
if (from && until) {
dispatch({
type: "SET_PERIOD", payload: {
from: dayjs.tz(from).toDate(),
to: dayjs.tz(until).toDate()
}
});
dispatch({ type: "SET_PERIOD", payload: {
from: dayjs.tz(from).toDate(),
to: dayjs.tz(until).toDate()
} });
}
handleCloseOptions();
};
const onSwitchToNow = () => dispatch({ type: "RUN_QUERY_TO_NOW" });
const handleOpenSettings = () => {
onOpenSettings && onOpenSettings();
handleCloseOptions();
};
const onCancelClick = () => {
setUntil(formatDateForNativeInput(dateFromSeconds(end)));
setFrom(formatDateForNativeInput(dateFromSeconds(start)));
@@ -151,7 +140,6 @@ export const TimeSelector: FC<Props> = ({ onOpenSettings }) => {
</Tooltip>
)}
</div>
<Popper
open={openOptions}
buttonRef={buttonRef}
@@ -191,17 +179,13 @@ export const TimeSelector: FC<Props> = ({ onOpenSettings }) => {
onEnter={setTimeAndClosePicker}
/>
</div>
<button
type="button"
className="vm-time-selector-left-timezone"
onClick={handleOpenSettings}
>
<span className="vm-time-selector-left-timezone__title">{activeTimezone.region}</span>
<span className="vm-time-selector-left-timezone__utc">{activeTimezone.utc}</span>
</button>
<div className="vm-time-selector-left-timezone">
<div className="vm-time-selector-left-timezone__title">{activeTimezone.region}</div>
<div className="vm-time-selector-left-timezone__utc">{activeTimezone.utc}</div>
</div>
<Button
variant="text"
startIcon={<AlarmIcon/>}
startIcon={<AlarmIcon />}
onClick={onSwitchToNow}
>
switch to now

View File

@@ -40,12 +40,8 @@
gap: $padding-small;
font-size: $font-size-small;
margin-bottom: $padding-small;
cursor: pointer;
&:hover {
color: $color-primary;
text-decoration: underline;
}
&__title {}
&__utc {
display: inline-flex;

View File

@@ -633,14 +633,3 @@ export const DebugIcon = () => (
/>
</svg>
);
export const PlanetIcon = () => (
<svg
viewBox="0 0 24 24"
fill="currentColor"
>
<path
d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2M4 12c0-.61.08-1.21.21-1.78L8.99 15v1c0 1.1.9 2 2 2v1.93C7.06 19.43 4 16.07 4 12m13.89 5.4c-.26-.81-1-1.4-1.9-1.4h-1v-3c0-.55-.45-1-1-1h-6v-2h2c.55 0 1-.45 1-1V7h2c1.1 0 2-.9 2-2v-.41C17.92 5.77 20 8.65 20 12c0 2.08-.81 3.98-2.11 5.4"
></path>
</svg>
);

View File

@@ -11,7 +11,6 @@
&_mobile {
display: grid;
grid-template-columns: 1fr;
gap: 0;
padding: 0;
flex-grow: initial;

View File

@@ -6,11 +6,9 @@ import StepConfigurator from "../../components/Configurators/StepConfigurator/St
import { TimeSelector } from "../../components/Configurators/TimeRangeSettings/TimeSelector/TimeSelector";
import CardinalityDatePicker from "../../components/Configurators/CardinalityDatePicker/CardinalityDatePicker";
import { ExecutionControls } from "../../components/Configurators/TimeRangeSettings/ExecutionControls/ExecutionControls";
import GlobalSettings, { GlobalSettingsHandle } from "../../components/Configurators/GlobalSettings/GlobalSettings";
import GlobalSettings from "../../components/Configurators/GlobalSettings/GlobalSettings";
import ShortcutKeys from "../../components/Main/ShortcutKeys/ShortcutKeys";
import { ControlsProps } from "../Header/HeaderControls/HeaderControls";
import { useRef } from "react";
import TimeZonePreview from "../../components/Configurators/GlobalSettings/TimeZonePreview/TimeZonePreview";
const ControlsMainLayout: FC<ControlsProps> = ({
displaySidebar,
@@ -19,7 +17,6 @@ const ControlsMainLayout: FC<ControlsProps> = ({
accountIds,
closeModal,
}) => {
const settingsRef = useRef<GlobalSettingsHandle>(null);
return (
<div
@@ -30,15 +27,14 @@ const ControlsMainLayout: FC<ControlsProps> = ({
>
{headerSetup?.tenant && <TenantsConfiguration accountIds={accountIds || []}/>}
{headerSetup?.stepControl && <StepConfigurator/>}
{headerSetup?.timeSelector && <TimeSelector onOpenSettings={() => settingsRef.current?.open()}/>}
{headerSetup?.timeSelector && <TimeSelector/>}
{headerSetup?.cardinalityDatePicker && <CardinalityDatePicker/>}
<TimeZonePreview onOpenSettings={() => settingsRef.current?.open()}/>
{headerSetup?.executionControls && <ExecutionControls
tooltip={headerSetup?.executionControls?.tooltip}
useAutorefresh={headerSetup?.executionControls?.useAutorefresh}
closeModal={closeModal}
/>}
<GlobalSettings ref={settingsRef}/>
<GlobalSettings/>
{!displaySidebar && <ShortcutKeys/>}
</div>
);

View File

@@ -1,12 +1,11 @@
@use "src/styles/variables" as *;
.vm-mobile-option {
display: grid;
grid-template-columns: auto 1fr auto;
display: flex;
align-items: center;
justify-content: flex-start;
gap: $padding-global;
padding: $padding-global $padding-small;
gap: $padding-small;
padding: calc($padding-medium/2) 0;
width: 100%;
user-select: none;
@@ -18,33 +17,14 @@
}
&__icon {
position: relative;
display: flex;
width: 40px;
height: 40px;
width: 22px;
height: 22px;
color: $color-primary;
&:after {
content: "";
position: absolute;
top: 0;
left: 0;
width: 100%;
height: 100%;
opacity: 0.1;
background-color: currentColor;
border-radius: $border-radius-medium;
}
svg {
width: 21px;
height: auto;
}
}
&__arrow {
width: 20px;
height: 20px;
width: 14px;
height: 14px;
transform: rotate(-90deg);
color: $color-primary;
}
@@ -52,13 +32,11 @@
&-text {
display: grid;
align-items: center;
height: 100%;
gap: calc($padding-small / 2);
gap: 2px;
flex-grow: 1;
text-align: left;
&__label {
font-weight: 600;
font-weight: bold;
}
&__value {

View File

@@ -59,7 +59,7 @@ func (ms *PrometheusMockStorage) Read(_ context.Context, query *prompb.Query, so
}
if !notMatch {
q.Timeseries = append(q.Timeseries, &prompb.TimeSeries{Labels: s.Labels, Samples: s.Samples, Histograms: s.Histograms})
q.Timeseries = append(q.Timeseries, &prompb.TimeSeries{Labels: s.Labels, Samples: s.Samples})
}
}

View File

@@ -12,7 +12,6 @@ import (
"github.com/gogo/protobuf/proto"
"github.com/golang/snappy"
"github.com/prometheus/prometheus/model/histogram"
"github.com/prometheus/prometheus/model/labels"
"github.com/prometheus/prometheus/prompb"
"github.com/prometheus/prometheus/storage/remote"
@@ -87,17 +86,10 @@ func (rrs *RemoteReadServer) getReadHandler(t *testing.T) http.Handler {
samples = append(samples, sample)
}
}
var histograms []prompb.Histogram
for _, h := range s.Histograms {
if h.Timestamp >= startTs && h.Timestamp < endTs {
histograms = append(histograms, h)
}
}
var series prompb.TimeSeries
if len(samples) > 0 || len(histograms) > 0 {
if len(samples) > 0 {
series.Labels = s.Labels
series.Samples = samples
series.Histograms = histograms
}
ts[i] = &series
}
@@ -325,37 +317,6 @@ func generateRemoteReadSamples(idx int, startTime, endTime, numOfSamples int64)
return samples
}
// GenerateRemoteReadHistogramSeries generates a remote read series
// with native histogram samples within the given time range.
func GenerateRemoteReadHistogramSeries(start, end, numOfSamples int64) []*prompb.TimeSeries {
timeSeries := &prompb.TimeSeries{
Labels: []prompb.Label{
{Name: labels.MetricName, Value: "vm_histogram_metric"},
{Name: "job", Value: "0"},
},
}
delta := (end - start) / numOfSamples
mul := int64(0)
for t := start; t != end; t += delta {
mul++
h := &histogram.Histogram{
Schema: 0,
Count: uint64(10 * mul),
Sum: 25.5 * float64(mul),
ZeroThreshold: 0.001,
ZeroCount: uint64(2 * mul),
PositiveSpans: []histogram.Span{{Offset: 0, Length: 2}},
PositiveBuckets: []int64{mul, 2 * mul},
NegativeSpans: []histogram.Span{{Offset: 0, Length: 1}},
NegativeBuckets: []int64{4 * mul},
}
timeSeries.Histograms = append(timeSeries.Histograms, prompb.FromIntHistogram(t*1000, h))
}
return []*prompb.TimeSeries{timeSeries}
}
func labelsToLabelsProto(ls labels.Labels) []prompb.Label {
result := make([]prompb.Label, 0, ls.Len())
ls.Range(func(l labels.Label) {

View File

@@ -75,118 +75,6 @@ func TestClusterVmctlRemoteReadProtocol(t *testing.T) {
testRemoteReadProtocol(tc, clusterDst, newRemoteReadServer, vmctlFlags)
}
func TestSingleVmctlRemoteReadNativeHistograms(t *testing.T) {
fs.MustRemoveDir(t.Name())
tc := apptest.NewTestCase(t)
defer tc.Stop()
vmsingleDst := tc.MustStartDefaultVmsingle()
vmAddr := fmt.Sprintf("http://%s/", vmsingleDst.HTTPAddr())
vmctlFlags := []string{
`remote-read`,
`--remote-read-filter-time-start=2025-06-11T15:31:10Z`,
`--remote-read-filter-time-end=2025-06-11T15:31:20Z`,
`--remote-read-step-interval=minute`,
`--vm-addr=` + vmAddr,
`--disable-progress-bar=true`,
}
testRemoteReadNativeHistograms(tc, vmsingleDst, NewRemoteReadServer, vmctlFlags)
}
func TestSingleVmctlRemoteReadStreamNativeHistograms(t *testing.T) {
fs.MustRemoveDir(t.Name())
tc := apptest.NewTestCase(t)
defer tc.Stop()
vmsingleDst := tc.MustStartDefaultVmsingle()
vmAddr := fmt.Sprintf("http://%s/", vmsingleDst.HTTPAddr())
vmctlFlags := []string{
`remote-read`,
`--remote-read-filter-time-start=2025-06-11T15:31:10Z`,
`--remote-read-filter-time-end=2025-06-11T15:31:20Z`,
`--remote-read-step-interval=minute`,
`--vm-addr=` + vmAddr,
`--remote-read-use-stream=true`,
`--disable-progress-bar=true`,
}
testRemoteReadNativeHistograms(tc, vmsingleDst, NewRemoteReadStreamServer, vmctlFlags)
}
// testRemoteReadNativeHistograms verifies that native histograms are migrated
// as _count, _sum and _bucket series with vmrange labels in the same way
// as VictoriaMetrics converts native histograms received via Prometheus remote write protocol.
func testRemoteReadNativeHistograms(tc *apptest.TestCase, sut apptest.PrometheusWriteQuerier, newRemoteReadServer func(t *testing.T, series []*prompb.TimeSeries) *RemoteReadServer, vmctlFlags []string) {
t := tc.T()
t.Helper()
series := GenerateRemoteReadHistogramSeries(1749655870, 1749655880, 2)
rrs := newRemoteReadServer(t, series)
defer rrs.Close()
vmctlFlags = append(vmctlFlags, `--remote-read-src-addr=`+rrs.HTTPAddr())
tc.MustStartVmctl("vmctl", vmctlFlags)
sut.ForceFlush(t)
tc.Assert(&apptest.AssertOptions{
Retries: 300,
Msg: `unexpected native histogram metrics stored on vmsingle via the prometheus protocol`,
Got: func() any {
got := sut.PrometheusAPIV1Export(t, `{__name__=~".*"}`, apptest.QueryOpts{
Start: "2025-06-11T15:31:10Z",
End: "2025-06-11T15:32:20Z",
})
got.Sort()
return got.Data.Result
},
Want: expectedNativeHistogramQueryResult(),
CmpOpts: []cmp.Option{
cmpopts.IgnoreFields(apptest.PrometheusAPIV1QueryResponse{}, "Status", "Data.ResultType"),
},
})
}
// expectedNativeHistogramQueryResult returns the series expected to be stored in VictoriaMetrics
// after migrating the series generated by GenerateRemoteReadHistogramSeries(1749655870, 1749655880, 2).
func expectedNativeHistogramQueryResult() []*apptest.QueryResult {
metric := func(name, vmrange string) map[string]string {
m := map[string]string{
"__name__": name,
"job": "0",
}
if vmrange != "" {
m["vmrange"] = vmrange
}
return m
}
samples := func(v1, v2 float64) []*apptest.Sample {
return []*apptest.Sample{
{Timestamp: 1749655870000, Value: v1},
{Timestamp: 1749655875000, Value: v2},
}
}
resp := &apptest.PrometheusAPIV1QueryResponse{
Data: &apptest.QueryData{
Result: []*apptest.QueryResult{
{Metric: metric("vm_histogram_metric_count", ""), Samples: samples(10, 20)},
{Metric: metric("vm_histogram_metric_sum", ""), Samples: samples(25.5, 51)},
{Metric: metric("vm_histogram_metric_bucket", "-1.000e+00...-5.000e-01"), Samples: samples(4, 8)},
{Metric: metric("vm_histogram_metric_bucket", "-1.000e-03...1.000e-03"), Samples: samples(2, 4)},
{Metric: metric("vm_histogram_metric_bucket", "5.000e-01...1.000e+00"), Samples: samples(1, 2)},
{Metric: metric("vm_histogram_metric_bucket", "1.000e+00...2.000e+00"), Samples: samples(3, 6)},
},
},
}
// sort in the same way as the exported result
resp.Sort()
return resp.Data.Result
}
func testRemoteReadProtocol(tc *apptest.TestCase, sut apptest.PrometheusWriteQuerier, newRemoteReadServer func(t *testing.T) *RemoteReadServer, vmctlFlags []string) {
t := tc.T()
t.Helper()

View File

@@ -156,6 +156,13 @@ See [our blog](https://victoriametrics.com/blog) for the latest articles written
* [Why irate from Prometheus doesn't capture spikes](https://valyala.medium.com/why-irate-from-prometheus-doesnt-capture-spikes-45f9896d7832)
* [VictoriaMetrics: PromQL compliance](https://medium.com/@romanhavronenko/victoriametrics-promql-compliance-d4318203f51e)
* [How do open source solutions for logs work: Elasticsearch, Loki and VictoriaLogs](https://itnext.io/how-do-open-source-solutions-for-logs-work-elasticsearch-loki-and-victorialogs-9f7097ecbc2f)
* [How vmagent Collects and Ships Metrics Fast with Aggregation, Deduplication, and More](https://victoriametrics.com/blog/vmagent-how-it-works/)
* [When Metrics Meet vminsert: A Data-Delivery Story](https://victoriametrics.com/blog/vminsert-how-it-works/)
* [How vmstorage Handles Data Ingestion From vminsert](https://victoriametrics.com/blog/vmstorage-how-it-handles-data-ingestion/)
* [How vmstorage Processes Data: Retention, Merging, Deduplication...](https://victoriametrics.com/blog/vmstorage-retention-merging-deduplication/)
* [How vmstorage's IndexDB Works](https://victoriametrics.com/blog/vmstorage-how-indexdb-works/)
* [How vmstorage Handles Query Requests From vmselect](https://victoriametrics.com/blog/vmstorage-how-it-handles-query-requests/)
* [Inside vmselect: The Query Processing Engine of VictoriaMetrics](https://victoriametrics.com/blog/vmselect-how-it-works/)
### Tutorials, guides and how-to articles
@@ -173,6 +180,12 @@ See [our guides](https://docs.victoriametrics.com/guides/) for the up-to-date gu
* [Prometheus storage: tech terms for humans](https://valyala.medium.com/prometheus-storage-technical-terms-for-humans-4ab4de6c3d48)
* [Cardinality explorer](https://victoriametrics.com/blog/cardinality-explorer/)
* [Rules backfilling via vmalert](https://victoriametrics.com/blog/rules-replay/)
* [vmagent: Key Features Explained in Under 15 Minutes](https://victoriametrics.com/blog/vmagent-key-features-explained/)
* [Prometheus Metrics Explained: Counters, Gauges, Histograms & Summaries](https://victoriametrics.com/blog/prometheus-monitoring-metrics-counters-gauges-histogram-summaries/)
* [Prometheus Monitoring: Instant Queries and Range Queries Explained](https://victoriametrics.com/blog/prometheus-monitoring-instant-range-query/)
* [Prometheus Monitoring: Functions, Subqueries, Operators, and Modifiers](https://victoriametrics.com/blog/prometheus-monitoring-function-operator-modifier/)
* [Prometheus Alerting 101: Rules, Recording Rules, and Alertmanager](https://victoriametrics.com/blog/alerting-recording-rules-alertmanager/)
* [Alerting Best Practices](https://victoriametrics.com/blog/alerting-best-practices/)
### Other articles

View File

@@ -59,6 +59,11 @@ It increases cluster availability, and simplifies cluster maintenance as well as
![Cluster Scheme](Cluster-VictoriaMetrics-components.webp)
> Further reading, deep dives into how each service works internally:
> - `vmstorage`: [How vmstorage Handles Data Ingestion From vminsert](https://victoriametrics.com/blog/vmstorage-how-it-handles-data-ingestion/), [How vmstorage's IndexDB Works](https://victoriametrics.com/blog/vmstorage-how-indexdb-works/), [How vmstorage Handles Query Requests From vmselect](https://victoriametrics.com/blog/vmstorage-how-it-handles-query-requests/).
> - `vminsert`: [When Metrics Meet vminsert: A Data-Delivery Story](https://victoriametrics.com/blog/vminsert-how-it-works/).
> - `vmselect`: [Inside vmselect: The Query Processing Engine of VictoriaMetrics](https://victoriametrics.com/blog/vmselect-how-it-works/).
## vmui
VictoriaMetrics cluster version provides UI for query troubleshooting and exploration. The UI is available at
@@ -829,9 +834,9 @@ See also [minimum downtime strategy](#minimum-downtime-strategy).
## Slowness-based re-routing
By default{{% available_from "#" %}}, `vminsert` automatically re-routes writes away from the slowest `vmstorage` node
to preserve maximum ingestion throughput. This prevents a single slow `vmstorage` node
from throttling the entire cluster.
By default{{% available_from "#" %}}, `vminsert` automatically [re-route writes](https://victoriametrics.com/blog/vminsert-how-it-works/#31-rerouting)
away from the slowest `vmstorage` node to preserve maximum ingestion throughput. This prevents a single slow `vmstorage`
node from throttling the entire cluster.
Re-routing occurs only when all of the following conditions hold:
- the storage send buffer is full.
@@ -878,7 +883,7 @@ See also [resource usage limits docs](#resource-usage-limits).
## Rebalancing
Every `vminsert` node evenly spreads (shards) incoming data among `vmstorage` nodes specified in the `-storageNode` command-line flag.
Every `vminsert` node [evenly spreads (shards) incoming data](https://victoriametrics.com/blog/vminsert-how-it-works/#3-sharding-and-buffering) among `vmstorage` nodes specified in the `-storageNode` command-line flag.
This guarantees even distribution of the ingested data among `vmstorage` nodes. When new `vmstorage` nodes are added to the `-storageNode`
command-line flag at `vminsert`, then only newly ingested data is distributed evenly among old and new `vmstorage` nodes, while
historical data remains on the old `vmstorage` nodes. This speeds up data ingestion and querying for the majority of production workloads,
@@ -1026,7 +1031,7 @@ By default, VictoriaMetrics offloads replication to the underlying storage point
which guarantees data durability. VictoriaMetrics supports application-level replication if replicated durable persistent disks cannot be used for some reason.
The replication can be enabled by passing `-replicationFactor=N` command-line flag to `vminsert`. This instructs `vminsert` to store `N` copies for every ingested sample
on `N` distinct `vmstorage` nodes. This guarantees that all the stored data remains available for querying if up to `N-1` `vmstorage` nodes are unavailable.
on `N` distinct `vmstorage` nodes. This guarantees that all the stored data remains available for querying if up to `N-1` `vmstorage` nodes are unavailable. See [how `vminsert` replicates each sample to `N` `vmstorage` nodes](https://victoriametrics.com/blog/vminsert-how-it-works/#4-replication-and-sending-data-to-vmstorage) for details.
Passing `-replicationFactor=N` command-line flag to `vmselect` instructs it to not mark responses as `partial` if less than `-replicationFactor` vmstorage nodes are unavailable during the query.
See [cluster availability docs](#cluster-availability) for details.
@@ -1061,7 +1066,7 @@ deduplication can't be guaranteed when samples and sample duplicates for the sam
- when `vmstorage` node has no enough capacity for processing incoming data stream. Then `vminsert` re-routes new samples to other `vmstorage` nodes.
It is recommended to set **the same** `-dedup.minScrapeInterval` command-line flag value to both `vmselect` and `vmstorage` nodes
to ensure query results consistency, even if storage layer didn't complete deduplication yet.
to ensure query results consistency, even if [storage layer didn't complete deduplication](https://victoriametrics.com/blog/vmstorage-retention-merging-deduplication/#deduplication) yet.
## Metrics Metadata

View File

@@ -1405,6 +1405,9 @@ for fast block lookups, which belong to the given `TSID` and cover the given tim
* various background maintenance tasks such as [de-duplication](#deduplication), [downsampling](#downsampling)
and [freeing up disk space for the deleted time series](#how-to-delete-time-series) are performed during the merge
See how `vmstorage` [selects parts for background merging](https://victoriametrics.com/blog/vmstorage-retention-merging-deduplication/#merge-process),
including merge limits and monitoring metrics.
Newly added `parts` either successfully appear in the storage or fail to appear.
The newly added `part` is atomically registered in the `parts.json` file under the corresponding partition
after it is fully written and [fsynced](https://man7.org/linux/man-pages/man2/fsync.2.html) to the storage.
@@ -1532,6 +1535,8 @@ are **eventually deleted** during [background merge](https://medium.com/@valyala
The time range covered by data part is **not limited by retention period unit**. One data part can cover hours or days of
data. Hence, a data part can be deleted only **when fully outside the configured retention**.
See more about partitions and parts in the [Storage section](#storage).
See how the [retention and free-disk watchers manage storage](https://victoriametrics.com/blog/vmstorage-retention-merging-deduplication/#retention-free-disk-space-guard-and-downsampling)
for implementation details and monitoring metrics.
The maximum disk space usage for a given `-retentionPeriod` is going to be (`-retentionPeriod` + 1) months.
For example, if `-retentionPeriod` is set to 1, data for January is deleted on March 1st.

View File

@@ -32,20 +32,14 @@ See also [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-rel
* SECURITY: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): restrict `/api/v1/admin/tsdb/delete_series`, `/tags/delSeries` endpoints to `POST` method only to prevent some [SSRF](https://en.wikipedia.org/wiki/Server-side_request_forgery)-based data deletion attacks. See [#5552](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5552).
* FEATURE: [dashboards](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/dashboards): add `Fsync avg duration` panel to the Troubleshooting section of the single-node, cluster, and vmagent dashboards. This panel surfaces degradation of IO operation for faster incident triage. See [#10432](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10432).
* FEATURE: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/): add `name` label identifying the corresponding `-remoteWrite.url` target to the `vm_persistentqueue_*` metrics exposed by persistent queue. See [#7944](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7944). Thanks to @tIGO for contribution.
* FEATURE: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/): add `-remoteWrite.obfuscateLabels` flag for hashing values of the specified labels before sending metrics to the corresponding `-remoteWrite.url`. This allows sharing metrics with external systems while keeping sensitive label values hidden. See [#10599](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10599).
* FEATURE: [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/): add `-replay.continueWithExecutionErr` flag to allow continuing to replay other rules when a rule execution fails with a 422 response code, which can happen due to an expression syntax error or a resource limit being hit. See [11313](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11313).
* FEATURE: [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/): add template variable `$interval` to expose the alerting rule group's evaluation interval. This allows generating dashboard links with a lookback window relative to the rule's interval, for example `&from={{ ($activeAt.Add (parseDurationTime (printf "-%s" .Interval))).UnixMilli }}&to={{ $activeAt.UnixMilli }}`. See this issue [#11232](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11232) for more details. Thanks to @1solomonwakhungu for contribution.
* FEATURE: [vmbackupmanager](https://docs.victoriametrics.com/victoriametrics/vmbackupmanager/) and [alerts](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/deployment/docker/rules): introduce `vm_backup_last_success_at` metric to track the last successful backup by type. Add [alerting rules](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/deployment/docker/rules/alerts-vmbackupmanager.yml) `NoLatestBackupWithinLastDay`, `NoHourlyBackupWithinLastDay`,
`NoDailyBackupWithinLast3Days`, `NoWeeklyBackupWithinLast14Days` and `NoMonthlyBackupWithinLast62Days` to remind users about the missing backups. See [#11217](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11217).
* FEATURE: [vmctl](https://docs.victoriametrics.com/victoriametrics/vmctl/): support [Prometheus native histograms](https://prometheus.io/docs/specs/native_histograms/) migration in [remote read mode](https://docs.victoriametrics.com/victoriametrics/vmctl/remoteread/). Native histograms are converted into `_count`, `_sum` and `_bucket` series with `vmrange` labels in the same way as VictoriaMetrics converts native histograms received via Prometheus remote write protocol, except that for native histograms with custom buckets the original bucket bounds are preserved instead of being estimated with the exponential formula. Previously native histograms were silently ignored in `SAMPLES` mode, while in stream mode the migration failed with `EOF` error. See [#11292](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11292). Thanks to @liuxu623 for contribution.
* FEATURE: `vminsert` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): enable [slowness-based re-routing](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#slowness-based-re-routing) by default. Previously, `-disableRerouting` defaulted to `true`, which limited ingestion throughput to the slowest `vmstorage` node. Now `-disableRerouting` defaults to `false`, so `vminsert` automatically routes data away from the slowest `vmstorage` node, improving overall ingestion performance. Slowness re-routing is automatically disabled when `-replicationFactor` is greater than 1. See [#11287](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11287).
* FEATURE: [vmui](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmui): persist the selected auto-refresh interval in the URL. See [VictoriaLogs#1310](https://github.com/VictoriaMetrics/VictoriaLogs/issues/1310).
* FEATURE: [vmui](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#vmui): show the selected time zone UTC offset next to the date/time controls and allow opening time zone settings from it.
* FEATURE: [dashboards](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/dashboards): add `Fsync avg duration` panel to the Troubleshooting section of the single-node, cluster, and vmagent dashboards. This panel surfaces degradation of IO operation for faster incident triage. See [#10432](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10432).
* FEATURE: [vmbackupmanager](https://docs.victoriametrics.com/victoriametrics/vmbackupmanager/) and [alerts](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/deployment/docker/rules): introduce `vm_backup_last_success_at` metric to track the last successful backup by type. Add [alerting rules](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/deployment/docker/rules/alerts-vmbackupmanager.yml) `NoLatestBackupWithinLastDay`, `NoHourlyBackupWithinLastDay`, `NoDailyBackupWithinLast3Days`, `NoWeeklyBackupWithinLast14Days` and `NoMonthlyBackupWithinLast62Days` to remind users about the missing backups. See [#11217](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11217).
* FEATURE: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/): add `-remoteWrite.obfuscateLabels` flag for hashing values of the specified labels before sending metrics to the corresponding `-remoteWrite.url`. This allows sharing metrics with external systems while keeping sensitive label values hidden. See [#10599](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10599).
* BUGFIX: [MetricsQL](https://docs.victoriametrics.com/victoriametrics/metricsql/): properly drop data points filtered out by an inner [comparison operation](https://prometheus.io/docs/prometheus/latest/querying/operators/#comparison-binary-operators) when its result is used on the right side of another comparison. Previously, queries like `foo != (bar > 100)` could return unexpected results because filtered-out data points are represented internally as `NaN`, and `value != NaN` evaluates to `true`. Comparisons against explicitly present `NaN` values keep the previous behavior. See [#10018](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10018). Thanks to @zasdaym for contribution.
* BUGFIX: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) and [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/): ignore HTTP proxy environment variables when scraping targets over Unix domain sockets. See [#11318](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11318). Thanks to @lwmacct for contribution.
* BUGFIX: [vmalert](https://docs.victoriametrics.com/victoriametrics/vmalert/): fixed the display of rule state badges on the `Groups` page in the web UI. See [#11160](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11160).
* BUGFIX: [vmbackupmanager](https://docs.victoriametrics.com/victoriametrics/vmbackupmanager/): previously, `vmbackupmanager` was crashing on startup when it failed to restore backup state from remote storage, causing a crash loop. Now it logs the error and continues running, retrying the state restore before each scheduled backup. Added `vm_backup_errors_total{type="restoreState"}` metric to track backup state restore failures. See [#11217](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/11217).

View File

@@ -141,6 +141,7 @@ to other remote storage systems that support Prometheus `remote_write` protocol
If a single remote storage instance is temporarily unavailable, the collected data remains available on the other remote storage instances.
`vmagent` buffers the collected data in files at `-remoteWrite.tmpDataPath` until the remote storage becomes available again.
Then it sends the buffered data to the remote storage in order to prevent data gaps.
See how `vmagent` [selects shards and places replicas](https://victoriametrics.com/blog/vmagent-how-it-works/#step-4-sharding--replication) for implementation details.
[VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/) already supports replication,
so there is no need to specify multiple `-remoteWrite.url` flags when writing data to the same cluster.
@@ -150,7 +151,8 @@ See [these docs](https://docs.victoriametrics.com/victoriametrics/cluster-victor
`vmagent` can add, remove, or update labels on the collected data before sending it to the remote storage.
It can filter scrape targets or remove unwanted samples via Prometheus-like relabeling.
Please see the [Relabeling cookbook](https://docs.victoriametrics.com/victoriametrics/relabeling/) for details.
Please see the [Relabeling cookbook](https://docs.victoriametrics.com/victoriametrics/relabeling/) for configuration examples.
For ingestion pipeline internals, see how `vmagent` [applies global relabeling and cardinality limits](https://victoriametrics.com/blog/vmagent-how-it-works/#step-2-global-relabeling-cardinality-reduction).
### Sharding among remote storages
@@ -268,7 +270,9 @@ for the collected samples. Examples:
```sh
./vmagent -remoteWrite.url=http://remote-storage/api/v1/write -streamAggr.dropInputLabels=replica -streamAggr.dedupInterval=60s
```
See how `vmagent` [orders global deduplication and stream aggregation](https://victoriametrics.com/blog/vmagent-how-it-works/#step-3-global-deduplication--stream-aggregation) in the ingestion pipeline.
### Monitoring Data eXchange
The Monitoring Data eXchange (MDX){{% available_from "v1.147.0" %}} feature allows `vmagent` to forward only VictoriaMetrics metrics to selected `-remoteWrite.url` destinations while dropping metrics from non-VictoriaMetrics services.
@@ -359,6 +363,8 @@ in addition to the pull-based Prometheus-compatible targets' scraping:
* Prometheus exposition format via `http://<vmagent>:8429/api/v1/import/prometheus`. See [these docs](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-import-data-in-prometheus-exposition-format) for details.
* Arbitrary CSV data via `http://<vmagent>:8429/api/v1/import/csv`. See [these docs](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-import-csv-data).
See how `vmagent` [handles concurrency, decompression, and stream parsing](https://victoriametrics.com/blog/vmagent-how-it-works/#step-1-receiving-data-via-api-or-scrape) during ingestion.
## How to collect metrics in Prometheus format
Specify the path to the `prometheus.yml` file via the `-promscrape.config` command-line flag. `vmagent` takes into account the following
@@ -1066,6 +1072,7 @@ This behavior can be changed with the `-remoteWrite.inmemoryQueues` {{% availabl
When set to a non-zero value, vmagent starts the given number of additional workers,
which send only recently ingested data from the in-memory queue, while the workers configured via `-remoteWrite.queues` drain the file-based backlog concurrently.
This reduces the delivery lag for fresh samples after remote storage outages or slowdowns. The flag can be set individually per each `-remoteWrite.url`.
See how the [in-memory and file-based queues manage blocks](https://victoriametrics.com/blog/vmagent-how-it-works/#in-memory-queue) for implementation details.
Note that these workers are started in addition to the workers configured via `-remoteWrite.queues`, so the total number of concurrent connections to
the remote storage becomes the sum of both flags. Take this into account if the remote storage limits the number of concurrent requests.

View File

@@ -341,7 +341,6 @@ The following variables are available in templating:
| $externalLabels or .ExternalLabels | List of labels configured via `-external.label` command-line flag. | `Issues with {{ $labels.instance }} (datacenter-{{ $externalLabels.dc }})` |
| $externalURL or .ExternalURL | URL configured via `-external.url` command-line flag. Used for cases when vmalert is hidden behind proxy. | `Visit {{ $externalURL }} for more details` |
| $isPartial or .IsPartial | Indicates whether the latest rule query response from the datasource(that supports returning `isPartial` option, such as vmcluster) could be partial. | `{{ if $isPartial }}WARNING: The latest alert state may be a false alarm due to a partial response from the datasource.{{ end }}` |
| $interval or .Interval | Alerting rule group's evaluation interval. | `http://vm-grafana.com/<dashboard-id>?viewPanel=<panel-id>&from={{ ($activeAt.Add (parseDurationTime (printf "-%s" .Interval))).UnixMilli }}&to={{ $activeAt.UnixMilli }}` |
Additionally, `vmalert` provides some extra templating functions listed in [template functions](#template-functions) and [reusable templates](#reusable-templates).
@@ -1025,6 +1024,9 @@ Try the following tips to avoid common issues:
In that case, the default step will be used (`-datasource.queryStep`) and may cause unexpected results compared to
executing this query in vmui/Grafana, where step is adjusted differently.
See [practical examples for reducing alert noise](https://victoriametrics.com/blog/alerting-best-practices/#reducing-noise),
including aggregating alerts and configuring inhibition.
### Rule state
vmalert keeps the last `-rule.updateEntriesLimit` updates (or `update_entries_limit` [per-rule config](https://docs.victoriametrics.com/victoriametrics/vmalert/#alerting-rules))
@@ -1080,6 +1082,9 @@ Sometimes, it's hard to understand why a specific alert fired or not. Keep in mi
If evaluation returns error (i.e. datasource is unavailable), alert state doesn't change.
If at least one evaluation returns no data, then alert's `for` state resets.
See [how to tune the `for` parameter](https://victoriametrics.com/blog/alerting-best-practices/#the-for-param),
including its tradeoff with the query lookbehind window.
> Note: The alert state is tracked separately for each time series returned during evaluation.
> For example, if the 1st evaluation returns series A and B, and the 2nd evaluation returns only B the alert will remain active **only for B**.

View File

@@ -404,8 +404,6 @@ See the docs at https://docs.victoriametrics.com/victoriametrics/vmalert/ .
Optional TLS server name to use for connections to -remoteWrite.url. By default, the server name from -remoteWrite.url is used
-remoteWrite.url string
Optional URL to persist alerts state and recording rules results in form of timeseries. It must support either VictoriaMetrics remote write protocol or Prometheus remote_write protocol. Supports address in the form of IP address with a port (e.g., http://127.0.0.1:8428) or DNS SRV record. For example, if -remoteWrite.url=http://127.0.0.1:8428 is specified, then the alerts state will be written to http://127.0.0.1:8428/api/v1/write . See also -remoteWrite.disablePathAppend, '-remoteWrite.showURL'.
-replay.continueWithExecutionErr bool
Whether to continue replaying other rules if a rule execution fails with a 422 response code, which can happen due to an expression syntax error or a resource limit being hit.
-replay.disableProgressBar
Whether to disable rendering progress bars during the replay. Progress bar rendering might be verbose or break the logs parsing, so it is recommended to be disabled when not used in interactive mode.
-replay.maxDatapointsPerQuery int
@@ -413,7 +411,7 @@ See the docs at https://docs.victoriametrics.com/victoriametrics/vmalert/ .
-replay.ruleEvaluationConcurrency int
The maximum number of concurrent '/query_range' requests when replay recording rule or alerting rule with for=0. Increasing this value when replaying for a long time, since each request is limited by -replay.maxDatapointsPerQuery. (default 1)
-replay.ruleRetryAttempts int
Defines how many retries to make before giving up on rule if request for it returns a retriable error. (default 5)
Defines how many retries to make before giving up on rule if request for it returns an error. (default 5)
-replay.rulesDelay duration
Delay before evaluating the next rule within the group. Is important for chained rules. Keep it equal or bigger than -remoteWrite.flushInterval. When set to >0, replay ignores group's concurrency setting. (default 1s)
-replay.timeFrom string

View File

@@ -90,11 +90,7 @@ func newClient(ctx context.Context, sw *ScrapeWork) (*client, error) {
}
tr := httputil.NewTransport(false, "vm_promscrape")
if sw.UnixSocket != "" {
// Unix sockets are direct local endpoints and cannot be reached via HTTP proxies.
// Proxy could be set implicitly via global env variable HTTP_PROXY
tr.Proxy = nil
} else if proxyURLFunc != nil {
if proxyURLFunc != nil {
tr.Proxy = proxyURLFunc
}
tr.TLSHandshakeTimeout = 10 * time.Second